You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@hive.apache.org by jc...@apache.org on 2019/01/04 00:24:00 UTC
[01/35] hive git commit: HIVE-16957: Support CTAS for auto gather
column stats (Jesus Camacho Rodriguez, reviewed by Ashutosh Chauhan)
Repository: hive
Updated Branches:
refs/heads/master 691c4cb0a -> 138b00cad
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/rcfile_default_format.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/rcfile_default_format.q.out b/ql/src/test/results/clientpositive/rcfile_default_format.q.out
index e552adf..bdbe91b 100644
--- a/ql/src/test/results/clientpositive/rcfile_default_format.q.out
+++ b/ql/src/test/results/clientpositive/rcfile_default_format.q.out
@@ -69,7 +69,7 @@ Retention: 0
#### A masked pattern was here ####
Table Type: MANAGED_TABLE
Table Parameters:
- COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"key\":\"true\",\"value\":\"true\"}}
bucketing_version 2
numFiles 1
numRows 500
@@ -167,7 +167,7 @@ Retention: 0
#### A masked pattern was here ####
Table Type: MANAGED_TABLE
Table Parameters:
- COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"key\":\"true\",\"value\":\"true\"}}
bucketing_version 2
numFiles 1
numRows 500
@@ -214,7 +214,7 @@ Retention: 0
#### A masked pattern was here ####
Table Type: MANAGED_TABLE
Table Parameters:
- COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"key\":\"true\",\"value\":\"true\"}}
bucketing_version 2
numFiles 1
numRows 500
@@ -303,7 +303,7 @@ Retention: 0
#### A masked pattern was here ####
Table Type: MANAGED_TABLE
Table Parameters:
- COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"key\":\"true\",\"value\":\"true\"}}
bucketing_version 2
numFiles 1
numRows 500
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/sample_islocalmode_hook_use_metadata.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/sample_islocalmode_hook_use_metadata.q.out b/ql/src/test/results/clientpositive/sample_islocalmode_hook_use_metadata.q.out
index c967a31..4ad2957 100644
--- a/ql/src/test/results/clientpositive/sample_islocalmode_hook_use_metadata.q.out
+++ b/ql/src/test/results/clientpositive/sample_islocalmode_hook_use_metadata.q.out
@@ -80,7 +80,7 @@ Retention: 0
#### A masked pattern was here ####
Table Type: MANAGED_TABLE
Table Parameters:
- COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"key\":\"true\",\"value\":\"true\"}}
bucketing_version 2
numFiles 1
numRows 1500
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/show_materialized_views.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/show_materialized_views.q.out b/ql/src/test/results/clientpositive/show_materialized_views.q.out
index 6f5ba6a..c332851 100644
--- a/ql/src/test/results/clientpositive/show_materialized_views.q.out
+++ b/ql/src/test/results/clientpositive/show_materialized_views.q.out
@@ -231,7 +231,7 @@ Retention: 0
#### A masked pattern was here ####
Table Type: MATERIALIZED_VIEW
Table Parameters:
- COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"ds\":\"true\",\"key\":\"true\",\"value\":\"true\"}}
bucketing_version 2
numFiles 0
numRows 0
@@ -272,7 +272,7 @@ Retention: 0
#### A masked pattern was here ####
Table Type: MATERIALIZED_VIEW
Table Parameters:
- COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"ds\":\"true\",\"key\":\"true\",\"value\":\"true\"}}
bucketing_version 2
numFiles 0
numRows 0
@@ -312,7 +312,7 @@ Retention: 0
#### A masked pattern was here ####
Table Type: MATERIALIZED_VIEW
Table Parameters:
- COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"ds\":\"true\",\"key\":\"true\",\"value\":\"true\"}}
bucketing_version 2
numFiles 0
numRows 0
@@ -404,7 +404,7 @@ Retention: 0
#### A masked pattern was here ####
Table Type: MATERIALIZED_VIEW
Table Parameters:
- COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"a\":\"true\"}}
bucketing_version 2
numFiles 0
numRows 0
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/skewjoin_noskew.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/skewjoin_noskew.q.out b/ql/src/test/results/clientpositive/skewjoin_noskew.q.out
index 0c3b188..130fb33 100644
--- a/ql/src/test/results/clientpositive/skewjoin_noskew.q.out
+++ b/ql/src/test/results/clientpositive/skewjoin_noskew.q.out
@@ -12,13 +12,14 @@ POSTHOOK: Output: database:default
POSTHOOK: Output: default@noskew
STAGE DEPENDENCIES:
Stage-1 is a root stage
- Stage-6 depends on stages: Stage-1 , consists of Stage-7, Stage-2
- Stage-7
- Stage-5 depends on stages: Stage-7
- Stage-2 depends on stages: Stage-5
+ Stage-7 depends on stages: Stage-1 , consists of Stage-8, Stage-2
+ Stage-8
+ Stage-6 depends on stages: Stage-8
+ Stage-2 depends on stages: Stage-6
Stage-0 depends on stages: Stage-2
- Stage-8 depends on stages: Stage-0
- Stage-3 depends on stages: Stage-8
+ Stage-9 depends on stages: Stage-0, Stage-4
+ Stage-3 depends on stages: Stage-9
+ Stage-4 depends on stages: Stage-2
STAGE PLANS:
Stage: Stage-1
@@ -74,10 +75,10 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
- Stage: Stage-6
+ Stage: Stage-7
Conditional Operator
- Stage: Stage-7
+ Stage: Stage-8
Map Reduce Local Work
Alias -> Map Local Tables:
1
@@ -91,7 +92,7 @@ STAGE PLANS:
0 reducesinkkey0 (type: string)
1 reducesinkkey0 (type: string)
- Stage: Stage-5
+ Stage: Stage-6
Map Reduce
Map Operator Tree:
TableScan
@@ -138,6 +139,21 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.noskew
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: string)
+ outputColumnNames: col1, col2
+ Statistics: Num rows: 30 Data size: 300 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: compute_stats(col1, 'hll'), compute_stats(col2, 'hll')
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
Stage: Stage-0
Move Operator
@@ -145,7 +161,7 @@ STAGE PLANS:
hdfs directory: true
#### A masked pattern was here ####
- Stage: Stage-8
+ Stage: Stage-9
Create Table Operator:
Create Table
columns: key string, value string
@@ -157,6 +173,33 @@ STAGE PLANS:
Stage: Stage-3
Stats Work
Basic Stats Work:
+ Column Stats Desc:
+ Columns: key, value
+ Column Types: string, string
+ Table: default.noskew
+
+ Stage: Stage-4
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>)
+ Execution mode: vectorized
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
PREHOOK: query: create table noskew as select a.* from src a join src b on a.key=b.key order by a.key limit 30
PREHOOK: type: CREATETABLE_AS_SELECT
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/skewjoin_onesideskew.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/skewjoin_onesideskew.q.out b/ql/src/test/results/clientpositive/skewjoin_onesideskew.q.out
index c923a53..6108173 100644
--- a/ql/src/test/results/clientpositive/skewjoin_onesideskew.q.out
+++ b/ql/src/test/results/clientpositive/skewjoin_onesideskew.q.out
@@ -88,12 +88,13 @@ POSTHOOK: Output: database:default
POSTHOOK: Output: default@result_n1
STAGE DEPENDENCIES:
Stage-1 is a root stage
- Stage-5 depends on stages: Stage-1 , consists of Stage-6, Stage-0
- Stage-6
- Stage-4 depends on stages: Stage-6
- Stage-0 depends on stages: Stage-4
- Stage-7 depends on stages: Stage-0
- Stage-2 depends on stages: Stage-7
+ Stage-6 depends on stages: Stage-1 , consists of Stage-7, Stage-0, Stage-3
+ Stage-7
+ Stage-5 depends on stages: Stage-7
+ Stage-0 depends on stages: Stage-5
+ Stage-8 depends on stages: Stage-0, Stage-3
+ Stage-2 depends on stages: Stage-8
+ Stage-3 depends on stages: Stage-5
STAGE PLANS:
Stage: Stage-1
@@ -150,11 +151,26 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.result_n1
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: string)
+ outputColumnNames: col1, col2
+ Statistics: Num rows: 3 Data size: 23 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: compute_stats(col1, 'hll'), compute_stats(col2, 'hll')
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
- Stage: Stage-5
+ Stage: Stage-6
Conditional Operator
- Stage: Stage-6
+ Stage: Stage-7
Map Reduce Local Work
Alias -> Map Local Tables:
1
@@ -168,7 +184,7 @@ STAGE PLANS:
0 reducesinkkey0 (type: string)
1 reducesinkkey0 (type: string)
- Stage: Stage-4
+ Stage: Stage-5
Map Reduce
Map Operator Tree:
TableScan
@@ -187,6 +203,21 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.result_n1
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: string)
+ outputColumnNames: col1, col2
+ Statistics: Num rows: 3 Data size: 23 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: compute_stats(col1, 'hll'), compute_stats(col2, 'hll')
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
Local Work:
Map Reduce Local Work
@@ -196,7 +227,7 @@ STAGE PLANS:
hdfs directory: true
#### A masked pattern was here ####
- Stage: Stage-7
+ Stage: Stage-8
Create Table Operator:
Create Table
columns: key string, value string
@@ -208,6 +239,33 @@ STAGE PLANS:
Stage: Stage-2
Stats Work
Basic Stats Work:
+ Column Stats Desc:
+ Columns: key, value
+ Column Types: string, string
+ Table: default.result_n1
+
+ Stage: Stage-3
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>)
+ Execution mode: vectorized
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
PREHOOK: query: CREATE TABLE result_n1 AS SELECT a.* FROM skewtable a JOIN nonskewtable b ON a.key=b.key
PREHOOK: type: CREATETABLE_AS_SELECT
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/smb_mapjoin9.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/smb_mapjoin9.q.out b/ql/src/test/results/clientpositive/smb_mapjoin9.q.out
index 1550ca9..1b06cc0 100644
--- a/ql/src/test/results/clientpositive/smb_mapjoin9.q.out
+++ b/ql/src/test/results/clientpositive/smb_mapjoin9.q.out
@@ -281,6 +281,27 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.smb_mapjoin9_results
+ Select Operator
+ expressions: _col0 (type: int), _col1 (type: string), '2010-10-15' (type: string), _col3 (type: int)
+ outputColumnNames: col1, col2, col3, col4
+ Group By Operator
+ aggregations: compute_stats(col1, 'hll'), compute_stats(col2, 'hll'), compute_stats(col3, 'hll'), compute_stats(col4, 'hll')
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Reduce Output Operator
+ sort order:
+ value expressions: _col0 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col2 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col3 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>)
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2), compute_stats(VALUE._col3)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1, _col2, _col3
+ File Output Operator
+ compressed: false
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
Stage: Stage-7
Conditional Operator
@@ -309,6 +330,10 @@ STAGE PLANS:
Stage: Stage-2
Stats Work
Basic Stats Work:
+ Column Stats Desc:
+ Columns: k1, value, ds, k2
+ Column Types: int, string, string, int
+ Table: default.smb_mapjoin9_results
Stage: Stage-3
Map Reduce
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/spark/subquery_scalar.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/subquery_scalar.q.out b/ql/src/test/results/clientpositive/spark/subquery_scalar.q.out
index 6c25b58..d7d652f 100644
--- a/ql/src/test/results/clientpositive/spark/subquery_scalar.q.out
+++ b/ql/src/test/results/clientpositive/spark/subquery_scalar.q.out
@@ -506,6 +506,7 @@ STAGE PLANS:
Reduce Output Operator
sort order:
Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE
+ TopN Hash Memory Usage: 0.1
Execution mode: vectorized
Map 6
Map Operator Tree:
@@ -1067,6 +1068,7 @@ STAGE PLANS:
key expressions: _col0 (type: int)
sort order: +
Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+ TopN Hash Memory Usage: 0.1
Reducer 3
Execution mode: vectorized
Reduce Operator Tree:
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/spark/subquery_select.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/subquery_select.q.out b/ql/src/test/results/clientpositive/spark/subquery_select.q.out
index 3104c5c..ead76b4 100644
--- a/ql/src/test/results/clientpositive/spark/subquery_select.q.out
+++ b/ql/src/test/results/clientpositive/spark/subquery_select.q.out
@@ -2931,7 +2931,7 @@ STAGE PLANS:
Reducer 4 <- Reducer 3 (PARTITION-LEVEL SORT, 1), Reducer 8 (PARTITION-LEVEL SORT, 1)
Reducer 5 <- Map 9 (PARTITION-LEVEL SORT, 1), Reducer 4 (PARTITION-LEVEL SORT, 1)
Reducer 6 <- Reducer 5 (SORT, 1)
- Reducer 8 <- Map 7 (SORT, 1)
+ Reducer 8 <- Map 1 (SORT, 1)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -2947,20 +2947,6 @@ STAGE PLANS:
key expressions: _col0 (type: int)
sort order: +
Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
- Execution mode: vectorized
- Map 7
- Map Operator Tree:
- TableScan
- alias: part
- Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: p_size (type: int)
- outputColumnNames: _col0
- Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: int)
- sort order: +
- Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
TopN Hash Memory Usage: 0.1
Execution mode: vectorized
Map 9
@@ -3647,6 +3633,7 @@ STAGE PLANS:
key expressions: _col0 (type: int)
sort order: +
Statistics: Num rows: 26 Data size: 234 Basic stats: COMPLETE Column stats: NONE
+ TopN Hash Memory Usage: 0.1
Reducer 11
Execution mode: vectorized
Reduce Operator Tree:
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/stats5.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/stats5.q.out b/ql/src/test/results/clientpositive/stats5.q.out
index 902eb87..d9c8276 100644
--- a/ql/src/test/results/clientpositive/stats5.q.out
+++ b/ql/src/test/results/clientpositive/stats5.q.out
@@ -59,7 +59,7 @@ Retention: 0
#### A masked pattern was here ####
Table Type: MANAGED_TABLE
Table Parameters:
- COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"key\":\"true\",\"value\":\"true\"}}
bucketing_version 2
numFiles 1
numRows 500
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/tez/explainanalyze_1.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/tez/explainanalyze_1.q.out b/ql/src/test/results/clientpositive/tez/explainanalyze_1.q.out
index 30ec550..77395ad 100644
--- a/ql/src/test/results/clientpositive/tez/explainanalyze_1.q.out
+++ b/ql/src/test/results/clientpositive/tez/explainanalyze_1.q.out
@@ -90,23 +90,34 @@ POSTHOOK: Output: database:default
POSTHOOK: Output: default@t_n28
Plan optimized by CBO.
+Vertex dependency in root stage
+Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE)
+
Stage-3
Stats Work{}
Stage-4
Create Table Operator:
name:default.t_n28
- Stage-2
- Dependency Collection{}
- Stage-1
- Map 1
- File Output Operator [FS_2]
- table:{"name:":"default.t_n28"}
- Select Operator [SEL_1] (rows=500/500 width=87)
- Output:["_col0"]
- TableScan [TS_0] (rows=500/500 width=87)
- default@src,src,Tbl:COMPLETE,Col:COMPLETE,Output:["key"]
Stage-0
Move Operator
+ Stage-1
+ Reducer 2
+ File Output Operator [FS_11]
+ Group By Operator [GBY_9] (rows=1/1 width=440)
+ Output:["_col0"],aggregations:["compute_stats(VALUE._col0, 'hll')"]
+ <-Map 1 [CUSTOM_SIMPLE_EDGE]
+ File Output Operator [FS_2]
+ table:{"name:":"default.t_n28"}
+ Select Operator [SEL_1] (rows=500/500 width=87)
+ Output:["_col0"]
+ TableScan [TS_0] (rows=500/500 width=87)
+ default@src,src,Tbl:COMPLETE,Col:COMPLETE,Output:["key"]
+ PARTITION_ONLY_SHUFFLE [RS_8]
+ Select Operator [SEL_7] (rows=500/500 width=87)
+ Output:["col1"]
+ Please refer to the previous Select Operator [SEL_1]
+ Stage-2
+ Dependency Collection{}
Please refer to the previous Stage-1
PREHOOK: query: create table t_n28 as select key from src
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/tez/explainanalyze_3.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/tez/explainanalyze_3.q.out b/ql/src/test/results/clientpositive/tez/explainanalyze_3.q.out
index de68440..70ab178 100644
--- a/ql/src/test/results/clientpositive/tez/explainanalyze_3.q.out
+++ b/ql/src/test/results/clientpositive/tez/explainanalyze_3.q.out
@@ -298,14 +298,14 @@ Stage-2
Stage-0
Reducer 2
File Output Operator [FS_5]
- Group By Operator [GBY_3] (rows=1/1 width=1248)
+ Group By Operator [GBY_3] (rows=1/1 width=880)
Output:["_col0","_col1"],aggregations:["compute_stats(VALUE._col0, 'hll')","compute_stats(VALUE._col2, 'hll')"]
<-Map 1 [CUSTOM_SIMPLE_EDGE]
PARTITION_ONLY_SHUFFLE [RS_2]
- Select Operator [SEL_1] (rows=500/500 width=350)
+ Select Operator [SEL_1] (rows=500/500 width=178)
Output:["key","value"]
- TableScan [TS_0] (rows=500/500 width=350)
- default@src_stats,src_stats,Tbl:COMPLETE,Col:NONE,Output:["key","value"]
+ TableScan [TS_0] (rows=500/500 width=178)
+ default@src_stats,src_stats,Tbl:COMPLETE,Col:COMPLETE,Output:["key","value"]
PREHOOK: query: CREATE TEMPORARY MACRO SIGMOID (x DOUBLE) 1.0 / (1.0 + EXP(-x))
PREHOOK: type: CREATEMACRO
@@ -398,23 +398,34 @@ POSTHOOK: Output: database:default
POSTHOOK: Output: default@src_autho_test_n4
Plan optimized by CBO.
+Vertex dependency in root stage
+Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE)
+
Stage-3
Stats Work{}
Stage-4
Create Table Operator:
name:default.src_autho_test_n4
- Stage-2
- Dependency Collection{}
- Stage-1
- Map 1 vectorized
- File Output Operator [FS_4]
- table:{"name:":"default.src_autho_test_n4"}
- Select Operator [SEL_3] (rows=500/1 width=178)
- Output:["_col0","_col1"]
- TableScan [TS_0] (rows=500/1 width=178)
- default@src,src,Tbl:COMPLETE,Col:COMPLETE,Output:["key","value"]
Stage-0
Move Operator
+ Stage-1
+ Reducer 2
+ File Output Operator [FS_11]
+ Group By Operator [GBY_9] (rows=1/1 width=880)
+ Output:["_col0","_col1"],aggregations:["compute_stats(VALUE._col0, 'hll')","compute_stats(VALUE._col2, 'hll')"]
+ <-Map 1 [CUSTOM_SIMPLE_EDGE] vectorized
+ File Output Operator [FS_13]
+ table:{"name:":"default.src_autho_test_n4"}
+ Select Operator [SEL_12] (rows=500/1 width=178)
+ Output:["_col0","_col1"]
+ TableScan [TS_0] (rows=500/1 width=178)
+ default@src,src,Tbl:COMPLETE,Col:COMPLETE,Output:["key","value"]
+ PARTITION_ONLY_SHUFFLE [RS_15]
+ Select Operator [SEL_14] (rows=500/1 width=178)
+ Output:["col1","col2"]
+ Please refer to the previous Select Operator [SEL_12]
+ Stage-2
+ Dependency Collection{}
Please refer to the previous Stage-1
PREHOOK: query: create table src_autho_test_n4 as select * from src
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/tez/explainanalyze_5.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/tez/explainanalyze_5.q.out b/ql/src/test/results/clientpositive/tez/explainanalyze_5.q.out
index 4e222b5..68e8e5a 100644
--- a/ql/src/test/results/clientpositive/tez/explainanalyze_5.q.out
+++ b/ql/src/test/results/clientpositive/tez/explainanalyze_5.q.out
@@ -65,14 +65,14 @@ Stage-2
Stage-0
Reducer 2
File Output Operator [FS_5]
- Group By Operator [GBY_3] (rows=1/1 width=1248)
+ Group By Operator [GBY_3] (rows=1/1 width=880)
Output:["_col0","_col1"],aggregations:["compute_stats(VALUE._col0, 'hll')","compute_stats(VALUE._col2, 'hll')"]
<-Map 1 [CUSTOM_SIMPLE_EDGE]
PARTITION_ONLY_SHUFFLE [RS_2]
- Select Operator [SEL_1] (rows=500/500 width=350)
+ Select Operator [SEL_1] (rows=500/500 width=178)
Output:["key","value"]
- TableScan [TS_0] (rows=500/500 width=350)
- default@src_stats_n0,src_stats_n0,Tbl:COMPLETE,Col:NONE,Output:["key","value"]
+ TableScan [TS_0] (rows=500/500 width=178)
+ default@src_stats_n0,src_stats_n0,Tbl:COMPLETE,Col:COMPLETE,Output:["key","value"]
PREHOOK: query: drop table src_multi2_n7
PREHOOK: type: DROPTABLE
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/tez/explainuser_3.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/tez/explainuser_3.q.out b/ql/src/test/results/clientpositive/tez/explainuser_3.q.out
index 69b4ba4..2b2027c 100644
--- a/ql/src/test/results/clientpositive/tez/explainuser_3.q.out
+++ b/ql/src/test/results/clientpositive/tez/explainuser_3.q.out
@@ -326,23 +326,36 @@ POSTHOOK: Output: database:default
POSTHOOK: Output: default@src_autho_test_n3
Plan optimized by CBO.
+Vertex dependency in root stage
+Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE)
+
Stage-3
Stats Work{}
Stage-4
Create Table Operator:
name:default.src_autho_test_n3
- Stage-2
- Dependency Collection{}
- Stage-1
- Map 1 vectorized
- File Output Operator [FS_4]
- table:{"name:":"default.src_autho_test_n3"}
- Select Operator [SEL_3] (rows=500 width=178)
- Output:["_col0","_col1"]
- TableScan [TS_0] (rows=500 width=178)
- default@src,src,Tbl:COMPLETE,Col:COMPLETE,Output:["key","value"]
Stage-0
Move Operator
+ Stage-1
+ Reducer 2
+ File Output Operator [FS_12]
+ Group By Operator [GBY_10] (rows=1 width=880)
+ Output:["_col0","_col1"],aggregations:["compute_stats(VALUE._col0)","compute_stats(VALUE._col1)"]
+ <-Map 1 [CUSTOM_SIMPLE_EDGE]
+ File Output Operator [FS_2]
+ table:{"name:":"default.src_autho_test_n3"}
+ Select Operator [SEL_1] (rows=500 width=178)
+ Output:["_col0","_col1"]
+ TableScan [TS_0] (rows=500 width=178)
+ default@src,src,Tbl:COMPLETE,Col:COMPLETE,Output:["key","value"]
+ PARTITION_ONLY_SHUFFLE [RS_9]
+ Group By Operator [GBY_8] (rows=1 width=880)
+ Output:["_col0","_col1"],aggregations:["compute_stats(col1, 'hll')","compute_stats(col2, 'hll')"]
+ Select Operator [SEL_7] (rows=500 width=178)
+ Output:["col1","col2"]
+ Please refer to the previous Select Operator [SEL_1]
+ Stage-2
+ Dependency Collection{}
Please refer to the previous Stage-1
PREHOOK: query: create table src_autho_test_n3 as select * from src
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/udtf_explode.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/udtf_explode.q.out b/ql/src/test/results/clientpositive/udtf_explode.q.out
index df1194e..ff68554 100644
--- a/ql/src/test/results/clientpositive/udtf_explode.q.out
+++ b/ql/src/test/results/clientpositive/udtf_explode.q.out
@@ -86,6 +86,8 @@ STAGE PLANS:
sort order:
Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE
tag: -1
+ TopN: 3
+ TopN Hash Memory Usage: 0.1
value expressions: _col0 (type: int)
auto parallelism: false
Path -> Alias:
@@ -362,6 +364,8 @@ STAGE PLANS:
sort order:
Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE
tag: -1
+ TopN: 3
+ TopN Hash Memory Usage: 0.1
value expressions: _col0 (type: int), _col1 (type: string)
auto parallelism: false
Path -> Alias:
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/union24.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/union24.q.out b/ql/src/test/results/clientpositive/union24.q.out
index bcc5e7d..e9477a0 100644
--- a/ql/src/test/results/clientpositive/union24.q.out
+++ b/ql/src/test/results/clientpositive/union24.q.out
@@ -137,7 +137,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"count":"true","key":"true"}}
bucket_count -1
bucketing_version 2
column.name.delimiter ,
@@ -159,7 +159,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"count":"true","key":"true"}}
bucket_count -1
bucketing_version 2
column.name.delimiter ,
@@ -379,7 +379,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"count":"true","key":"true"}}
bucket_count -1
bucketing_version 2
column.name.delimiter ,
@@ -401,7 +401,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"count":"true","key":"true"}}
bucket_count -1
bucketing_version 2
column.name.delimiter ,
@@ -427,7 +427,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"count":"true","key":"true"}}
bucket_count -1
bucketing_version 2
column.name.delimiter ,
@@ -449,7 +449,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"count":"true","key":"true"}}
bucket_count -1
bucketing_version 2
column.name.delimiter ,
@@ -475,7 +475,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"count":"true","key":"true"}}
bucket_count -1
bucketing_version 2
column.name.delimiter ,
@@ -497,7 +497,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"count":"true","key":"true"}}
bucket_count -1
bucketing_version 2
column.name.delimiter ,
@@ -687,7 +687,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"count":"true","key":"true"}}
bucket_count -1
bucketing_version 2
column.name.delimiter ,
@@ -709,7 +709,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"count":"true","key":"true"}}
bucket_count -1
bucketing_version 2
column.name.delimiter ,
@@ -735,7 +735,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"count":"true","key":"true"}}
bucket_count -1
bucketing_version 2
column.name.delimiter ,
@@ -757,7 +757,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"count":"true","key":"true"}}
bucket_count -1
bucketing_version 2
column.name.delimiter ,
@@ -947,7 +947,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"count":"true","key":"true"}}
bucket_count -1
bucketing_version 2
column.name.delimiter ,
@@ -969,7 +969,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"count":"true","key":"true"}}
bucket_count -1
bucketing_version 2
column.name.delimiter ,
@@ -995,7 +995,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"count":"true","key":"true"}}
bucket_count -1
bucketing_version 2
column.name.delimiter ,
@@ -1017,7 +1017,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"count":"true","key":"true"}}
bucket_count -1
bucketing_version 2
column.name.delimiter ,
@@ -1197,7 +1197,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"count":"true","key":"true"}}
bucket_count -1
bucketing_version 2
column.name.delimiter ,
@@ -1219,7 +1219,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"count":"true","key":"true"}}
bucket_count -1
bucketing_version 2
column.name.delimiter ,
@@ -1245,7 +1245,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"count":"true","key":"true"}}
bucket_count -1
bucketing_version 2
column.name.delimiter ,
@@ -1267,7 +1267,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"count":"true","key":"true"}}
bucket_count -1
bucketing_version 2
column.name.delimiter ,
@@ -1528,7 +1528,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"count":"true","key":"true"}}
bucket_count -1
bucketing_version 2
column.name.delimiter ,
@@ -1550,7 +1550,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"count":"true","key":"true"}}
bucket_count -1
bucketing_version 2
column.name.delimiter ,
@@ -1576,7 +1576,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"count":"true","key":"true"}}
bucket_count -1
bucketing_version 2
column.name.delimiter ,
@@ -1598,7 +1598,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"count":"true","key":"true"}}
bucket_count -1
bucketing_version 2
column.name.delimiter ,
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/union25.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/union25.q.out b/ql/src/test/results/clientpositive/union25.q.out
index 755c1ce..93f40be 100644
--- a/ql/src/test/results/clientpositive/union25.q.out
+++ b/ql/src/test/results/clientpositive/union25.q.out
@@ -69,14 +69,15 @@ POSTHOOK: Input: default@tmp_srcpart@ds=2008-04-08/hr=11
POSTHOOK: Output: database:default
POSTHOOK: Output: default@tmp_unionall
STAGE DEPENDENCIES:
- Stage-4 is a root stage
- Stage-2 depends on stages: Stage-4
+ Stage-5 is a root stage
+ Stage-2 depends on stages: Stage-5
Stage-0 depends on stages: Stage-2
- Stage-6 depends on stages: Stage-0
- Stage-3 depends on stages: Stage-6
+ Stage-7 depends on stages: Stage-0, Stage-4
+ Stage-3 depends on stages: Stage-7
+ Stage-4 depends on stages: Stage-2
STAGE PLANS:
- Stage: Stage-4
+ Stage: Stage-5
Map Reduce
Map Operator Tree:
TableScan
@@ -195,6 +196,21 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.tmp_unionall
+ Select Operator
+ expressions: _col0 (type: bigint), _col1 (type: string), _col2 (type: string)
+ outputColumnNames: col1, col2, col3
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: compute_stats(col1, 'hll'), compute_stats(col2, 'hll'), compute_stats(col3, 'hll')
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 1304 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
Stage: Stage-0
Move Operator
@@ -202,7 +218,7 @@ STAGE PLANS:
hdfs directory: true
#### A masked pattern was here ####
- Stage: Stage-6
+ Stage: Stage-7
Create Table Operator:
Create Table
columns: counts bigint, key string, value string
@@ -214,4 +230,31 @@ STAGE PLANS:
Stage: Stage-3
Stats Work
Basic Stats Work:
+ Column Stats Desc:
+ Columns: counts, key, value
+ Column Types: bigint, string, string
+ Table: default.tmp_unionall
+
+ Stage: Stage-4
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 1304 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col2 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>)
+ Execution mode: vectorized
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/vector_decimal_6.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/vector_decimal_6.q.out b/ql/src/test/results/clientpositive/vector_decimal_6.q.out
index f7d7276..33694e5 100644
--- a/ql/src/test/results/clientpositive/vector_decimal_6.q.out
+++ b/ql/src/test/results/clientpositive/vector_decimal_6.q.out
@@ -584,6 +584,26 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat
serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde
name: default.DECIMAL_6_3
+ Select Operator
+ expressions: _col0 (type: decimal(11,5)), _col1 (type: int)
+ outputColumnNames: col1, col2
+ Statistics: Num rows: 27 Data size: 2572 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: compute_stats(col1, 'hll'), compute_stats(col2, 'hll')
+ mode: complete
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 1056 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: struct<columntype:string,min:decimal(11,5),max:decimal(11,5),countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col1 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 1056 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 1056 Basic stats: COMPLETE Column stats: NONE
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
Stage: Stage-0
Move Operator
@@ -603,6 +623,10 @@ STAGE PLANS:
Stage: Stage-2
Stats Work
Basic Stats Work:
+ Column Stats Desc:
+ Columns: k, v
+ Column Types: decimal(11,5), int
+ Table: default.DECIMAL_6_3
PREHOOK: query: CREATE TABLE DECIMAL_6_3 STORED AS ORC AS SELECT key + 5.5 AS k, value * 11 AS v from DECIMAL_6_1 ORDER BY v
PREHOOK: type: CREATETABLE_AS_SELECT
[03/35] hive git commit: HIVE-16957: Support CTAS for auto gather
column stats (Jesus Camacho Rodriguez, reviewed by Ashutosh Chauhan)
Posted by jc...@apache.org.
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/llap/vectorized_dynamic_semijoin_reduction.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/vectorized_dynamic_semijoin_reduction.q.out b/ql/src/test/results/clientpositive/llap/vectorized_dynamic_semijoin_reduction.q.out
index a1924ce..3681739 100644
--- a/ql/src/test/results/clientpositive/llap/vectorized_dynamic_semijoin_reduction.q.out
+++ b/ql/src/test/results/clientpositive/llap/vectorized_dynamic_semijoin_reduction.q.out
@@ -58,7 +58,7 @@ STAGE PLANS:
TableScan
alias: a
filterExpr: (key_int is not null and (key_int BETWEEN DynamicValue(RS_7_b_key_int_min) AND DynamicValue(RS_7_b_key_int_max) and in_bloom_filter(key_int, DynamicValue(RS_7_b_key_int_bloom_filter)))) (type: boolean)
- Statistics: Num rows: 500 Data size: 1904 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
Filter Operator
@@ -67,7 +67,7 @@ STAGE PLANS:
native: true
predicateExpression: FilterExprAndExpr(children: SelectColumnIsNotNull(col 1:int), FilterExprAndExpr(children: FilterLongColumnBetweenDynamicValue(col 1:int, left 0, right 0), VectorInBloomFilterColDynamicValue))
predicate: ((key_int BETWEEN DynamicValue(RS_7_b_key_int_min) AND DynamicValue(RS_7_b_key_int_max) and in_bloom_filter(key_int, DynamicValue(RS_7_b_key_int_bloom_filter))) and key_int is not null) (type: boolean)
- Statistics: Num rows: 475 Data size: 1808 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: key_int (type: int)
outputColumnNames: _col0
@@ -75,7 +75,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [1]
- Statistics: Num rows: 475 Data size: 1808 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
@@ -84,7 +84,7 @@ STAGE PLANS:
className: VectorReduceSinkLongOperator
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 475 Data size: 1808 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized, llap
LLAP IO: all inputs
Map Vectorization:
@@ -101,7 +101,7 @@ STAGE PLANS:
TableScan
alias: b
filterExpr: key_int is not null (type: boolean)
- Statistics: Num rows: 57 Data size: 224 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 57 Data size: 228 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
Filter Operator
@@ -110,7 +110,7 @@ STAGE PLANS:
native: true
predicateExpression: SelectColumnIsNotNull(col 1:int)
predicate: key_int is not null (type: boolean)
- Statistics: Num rows: 55 Data size: 216 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 57 Data size: 228 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: key_int (type: int)
outputColumnNames: _col0
@@ -118,7 +118,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [1]
- Statistics: Num rows: 55 Data size: 216 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 57 Data size: 228 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
@@ -127,7 +127,7 @@ STAGE PLANS:
className: VectorReduceSinkLongOperator
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 55 Data size: 216 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 57 Data size: 228 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: int)
outputColumnNames: _col0
@@ -135,9 +135,9 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [1]
- Statistics: Num rows: 55 Data size: 216 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 57 Data size: 228 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
- aggregations: min(_col0), max(_col0), bloom_filter(_col0, expectedEntries=55)
+ aggregations: min(_col0), max(_col0), bloom_filter(_col0, expectedEntries=57)
Group By Vectorization:
aggregators: VectorUDAFMinLong(col 1:int) -> int, VectorUDAFMaxLong(col 1:int) -> int, VectorUDAFBloomFilter(col 1:int) -> binary
className: VectorGroupByOperator
@@ -147,14 +147,14 @@ STAGE PLANS:
projectedOutputColumnNums: [0, 1, 2]
mode: hash
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
Reduce Sink Vectorization:
className: VectorReduceSinkEmptyKeyOperator
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: int), _col1 (type: int), _col2 (type: binary)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -176,15 +176,15 @@ STAGE PLANS:
keys:
0 _col0 (type: int)
1 _col0 (type: int)
- Statistics: Num rows: 522 Data size: 1988 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 94 Data size: 752 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count()
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: bigint)
MergeJoin Vectorization:
enabled: false
@@ -209,13 +209,13 @@ STAGE PLANS:
projectedOutputColumnNums: [0]
mode: mergepartial
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -230,7 +230,7 @@ STAGE PLANS:
vectorized: true
Reduce Operator Tree:
Group By Operator
- aggregations: min(VALUE._col0), max(VALUE._col1), bloom_filter(VALUE._col2, expectedEntries=55)
+ aggregations: min(VALUE._col0), max(VALUE._col1), bloom_filter(VALUE._col2, expectedEntries=57)
Group By Vectorization:
aggregators: VectorUDAFMinLong(col 0:int) -> int, VectorUDAFMaxLong(col 1:int) -> int, VectorUDAFBloomFilterMerge(col 2:binary) -> binary
className: VectorGroupByOperator
@@ -240,14 +240,14 @@ STAGE PLANS:
projectedOutputColumnNums: [0, 1, 2]
mode: final
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
Reduce Sink Vectorization:
className: VectorReduceSinkEmptyKeyOperator
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: int), _col1 (type: int), _col2 (type: binary)
Stage: Stage-0
@@ -301,7 +301,7 @@ STAGE PLANS:
TableScan
alias: a
filterExpr: (key_str is not null and (key_str BETWEEN DynamicValue(RS_7_b_key_str_min) AND DynamicValue(RS_7_b_key_str_max) and in_bloom_filter(key_str, DynamicValue(RS_7_b_key_str_bloom_filter)))) (type: boolean)
- Statistics: Num rows: 500 Data size: 87584 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
Filter Operator
@@ -310,7 +310,7 @@ STAGE PLANS:
native: true
predicateExpression: FilterExprAndExpr(children: SelectColumnIsNotNull(col 0:string), FilterExprAndExpr(children: FilterStringColumnBetweenDynamicValue(col 0:string, left NULL, right NULL), VectorInBloomFilterColDynamicValue))
predicate: ((key_str BETWEEN DynamicValue(RS_7_b_key_str_min) AND DynamicValue(RS_7_b_key_str_max) and in_bloom_filter(key_str, DynamicValue(RS_7_b_key_str_bloom_filter))) and key_str is not null) (type: boolean)
- Statistics: Num rows: 475 Data size: 83204 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: key_str (type: string)
outputColumnNames: _col0
@@ -318,7 +318,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0]
- Statistics: Num rows: 475 Data size: 83204 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
@@ -327,7 +327,7 @@ STAGE PLANS:
className: VectorReduceSinkStringOperator
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 475 Data size: 83204 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized, llap
LLAP IO: all inputs
Map Vectorization:
@@ -344,7 +344,7 @@ STAGE PLANS:
TableScan
alias: b
filterExpr: key_str is not null (type: boolean)
- Statistics: Num rows: 57 Data size: 10304 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 57 Data size: 4902 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
Filter Operator
@@ -353,7 +353,7 @@ STAGE PLANS:
native: true
predicateExpression: SelectColumnIsNotNull(col 0:string)
predicate: key_str is not null (type: boolean)
- Statistics: Num rows: 55 Data size: 9942 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 57 Data size: 4902 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: key_str (type: string)
outputColumnNames: _col0
@@ -361,7 +361,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0]
- Statistics: Num rows: 55 Data size: 9942 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 57 Data size: 4902 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
@@ -370,7 +370,7 @@ STAGE PLANS:
className: VectorReduceSinkStringOperator
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 55 Data size: 9942 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 57 Data size: 4902 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: string)
outputColumnNames: _col0
@@ -378,9 +378,9 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0]
- Statistics: Num rows: 55 Data size: 9942 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 57 Data size: 4902 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
- aggregations: min(_col0), max(_col0), bloom_filter(_col0, expectedEntries=55)
+ aggregations: min(_col0), max(_col0), bloom_filter(_col0, expectedEntries=57)
Group By Vectorization:
aggregators: VectorUDAFMinString(col 0:string) -> string, VectorUDAFMaxString(col 0:string) -> string, VectorUDAFBloomFilter(col 0:string) -> binary
className: VectorGroupByOperator
@@ -390,14 +390,14 @@ STAGE PLANS:
projectedOutputColumnNums: [0, 1, 2]
mode: hash
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 1 Data size: 736 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
Reduce Sink Vectorization:
className: VectorReduceSinkEmptyKeyOperator
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 1 Data size: 736 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: binary)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -419,15 +419,15 @@ STAGE PLANS:
keys:
0 _col0 (type: string)
1 _col0 (type: string)
- Statistics: Num rows: 522 Data size: 91524 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 90 Data size: 720 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count()
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: bigint)
MergeJoin Vectorization:
enabled: false
@@ -452,13 +452,13 @@ STAGE PLANS:
projectedOutputColumnNums: [0]
mode: mergepartial
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -473,7 +473,7 @@ STAGE PLANS:
vectorized: true
Reduce Operator Tree:
Group By Operator
- aggregations: min(VALUE._col0), max(VALUE._col1), bloom_filter(VALUE._col2, expectedEntries=55)
+ aggregations: min(VALUE._col0), max(VALUE._col1), bloom_filter(VALUE._col2, expectedEntries=57)
Group By Vectorization:
aggregators: VectorUDAFMinString(col 0:string) -> string, VectorUDAFMaxString(col 1:string) -> string, VectorUDAFBloomFilterMerge(col 2:binary) -> binary
className: VectorGroupByOperator
@@ -483,14 +483,14 @@ STAGE PLANS:
projectedOutputColumnNums: [0, 1, 2]
mode: final
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 1 Data size: 736 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
Reduce Sink Vectorization:
className: VectorReduceSinkEmptyKeyOperator
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 1 Data size: 736 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: binary)
Stage: Stage-0
@@ -544,7 +544,7 @@ STAGE PLANS:
TableScan
alias: a
filterExpr: (key_str is not null and (key_str BETWEEN DynamicValue(RS_7_b_key_str_min) AND DynamicValue(RS_7_b_key_str_max) and in_bloom_filter(key_str, DynamicValue(RS_7_b_key_str_bloom_filter)))) (type: boolean)
- Statistics: Num rows: 500 Data size: 87584 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
Filter Operator
@@ -553,7 +553,7 @@ STAGE PLANS:
native: true
predicateExpression: FilterExprAndExpr(children: SelectColumnIsNotNull(col 0:string), FilterExprAndExpr(children: FilterStringColumnBetweenDynamicValue(col 0:string, left NULL, right NULL), VectorInBloomFilterColDynamicValue))
predicate: ((key_str BETWEEN DynamicValue(RS_7_b_key_str_min) AND DynamicValue(RS_7_b_key_str_max) and in_bloom_filter(key_str, DynamicValue(RS_7_b_key_str_bloom_filter))) and key_str is not null) (type: boolean)
- Statistics: Num rows: 475 Data size: 83204 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: key_str (type: string)
outputColumnNames: _col0
@@ -561,7 +561,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0]
- Statistics: Num rows: 475 Data size: 83204 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
@@ -570,7 +570,7 @@ STAGE PLANS:
className: VectorReduceSinkStringOperator
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 475 Data size: 83204 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized, llap
LLAP IO: all inputs
Map Vectorization:
@@ -587,7 +587,7 @@ STAGE PLANS:
TableScan
alias: b
filterExpr: key_str is not null (type: boolean)
- Statistics: Num rows: 57 Data size: 10304 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 57 Data size: 4902 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
Filter Operator
@@ -596,7 +596,7 @@ STAGE PLANS:
native: true
predicateExpression: SelectColumnIsNotNull(col 0:string)
predicate: key_str is not null (type: boolean)
- Statistics: Num rows: 55 Data size: 9942 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 57 Data size: 4902 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: key_str (type: string)
outputColumnNames: _col0
@@ -604,7 +604,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0]
- Statistics: Num rows: 55 Data size: 9942 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 57 Data size: 4902 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
@@ -613,7 +613,7 @@ STAGE PLANS:
className: VectorReduceSinkStringOperator
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 55 Data size: 9942 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 57 Data size: 4902 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: string)
outputColumnNames: _col0
@@ -621,9 +621,9 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0]
- Statistics: Num rows: 55 Data size: 9942 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 57 Data size: 4902 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
- aggregations: min(_col0), max(_col0), bloom_filter(_col0, expectedEntries=55)
+ aggregations: min(_col0), max(_col0), bloom_filter(_col0, expectedEntries=57)
Group By Vectorization:
aggregators: VectorUDAFMinString(col 0:string) -> string, VectorUDAFMaxString(col 0:string) -> string, VectorUDAFBloomFilter(col 0:string) -> binary
className: VectorGroupByOperator
@@ -633,14 +633,14 @@ STAGE PLANS:
projectedOutputColumnNums: [0, 1, 2]
mode: hash
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 1 Data size: 736 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
Reduce Sink Vectorization:
className: VectorReduceSinkEmptyKeyOperator
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 1 Data size: 736 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: binary)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -662,15 +662,15 @@ STAGE PLANS:
keys:
0 _col0 (type: string)
1 _col0 (type: string)
- Statistics: Num rows: 522 Data size: 91524 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 90 Data size: 720 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count()
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: bigint)
MergeJoin Vectorization:
enabled: false
@@ -695,13 +695,13 @@ STAGE PLANS:
projectedOutputColumnNums: [0]
mode: mergepartial
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -716,7 +716,7 @@ STAGE PLANS:
vectorized: true
Reduce Operator Tree:
Group By Operator
- aggregations: min(VALUE._col0), max(VALUE._col1), bloom_filter(VALUE._col2, expectedEntries=55)
+ aggregations: min(VALUE._col0), max(VALUE._col1), bloom_filter(VALUE._col2, expectedEntries=57)
Group By Vectorization:
aggregators: VectorUDAFMinString(col 0:string) -> string, VectorUDAFMaxString(col 1:string) -> string, VectorUDAFBloomFilterMerge(col 2:binary) -> binary
className: VectorGroupByOperator
@@ -726,14 +726,14 @@ STAGE PLANS:
projectedOutputColumnNums: [0, 1, 2]
mode: final
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 1 Data size: 736 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
Reduce Sink Vectorization:
className: VectorReduceSinkEmptyKeyOperator
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 1 Data size: 736 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: binary)
Stage: Stage-0
@@ -787,7 +787,7 @@ STAGE PLANS:
TableScan
alias: a
filterExpr: (key_int is not null and (key_int BETWEEN DynamicValue(RS_10_b_key_int_min) AND DynamicValue(RS_10_b_key_int_max) and in_bloom_filter(key_int, DynamicValue(RS_10_b_key_int_bloom_filter)))) (type: boolean)
- Statistics: Num rows: 500 Data size: 1904 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
Filter Operator
@@ -796,7 +796,7 @@ STAGE PLANS:
native: true
predicateExpression: FilterExprAndExpr(children: SelectColumnIsNotNull(col 1:int), FilterExprAndExpr(children: FilterLongColumnBetweenDynamicValue(col 1:int, left 0, right 0), VectorInBloomFilterColDynamicValue))
predicate: ((key_int BETWEEN DynamicValue(RS_10_b_key_int_min) AND DynamicValue(RS_10_b_key_int_max) and in_bloom_filter(key_int, DynamicValue(RS_10_b_key_int_bloom_filter))) and key_int is not null) (type: boolean)
- Statistics: Num rows: 475 Data size: 1808 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: key_int (type: int)
outputColumnNames: _col0
@@ -804,7 +804,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [1]
- Statistics: Num rows: 475 Data size: 1808 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
@@ -813,7 +813,7 @@ STAGE PLANS:
className: VectorReduceSinkLongOperator
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 475 Data size: 1808 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized, llap
LLAP IO: all inputs
Map Vectorization:
@@ -830,7 +830,7 @@ STAGE PLANS:
TableScan
alias: b
filterExpr: key_int is not null (type: boolean)
- Statistics: Num rows: 57 Data size: 224 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 57 Data size: 228 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
Filter Operator
@@ -839,7 +839,7 @@ STAGE PLANS:
native: true
predicateExpression: SelectColumnIsNotNull(col 1:int)
predicate: key_int is not null (type: boolean)
- Statistics: Num rows: 55 Data size: 216 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 57 Data size: 228 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: key_int (type: int)
outputColumnNames: _col0
@@ -847,7 +847,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [1]
- Statistics: Num rows: 55 Data size: 216 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 57 Data size: 228 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
@@ -856,7 +856,7 @@ STAGE PLANS:
className: VectorReduceSinkLongOperator
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 55 Data size: 216 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 57 Data size: 228 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: int)
outputColumnNames: _col0
@@ -864,9 +864,9 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [1]
- Statistics: Num rows: 55 Data size: 216 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 57 Data size: 228 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
- aggregations: min(_col0), max(_col0), bloom_filter(_col0, expectedEntries=55)
+ aggregations: min(_col0), max(_col0), bloom_filter(_col0, expectedEntries=57)
Group By Vectorization:
aggregators: VectorUDAFMinLong(col 1:int) -> int, VectorUDAFMaxLong(col 1:int) -> int, VectorUDAFBloomFilter(col 1:int) -> binary
className: VectorGroupByOperator
@@ -876,14 +876,14 @@ STAGE PLANS:
projectedOutputColumnNums: [0, 1, 2]
mode: hash
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
Reduce Sink Vectorization:
className: VectorReduceSinkEmptyKeyOperator
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: int), _col1 (type: int), _col2 (type: binary)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -901,7 +901,7 @@ STAGE PLANS:
TableScan
alias: c
filterExpr: key_int is not null (type: boolean)
- Statistics: Num rows: 57 Data size: 224 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 57 Data size: 228 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
Filter Operator
@@ -910,7 +910,7 @@ STAGE PLANS:
native: true
predicateExpression: SelectColumnIsNotNull(col 1:int)
predicate: key_int is not null (type: boolean)
- Statistics: Num rows: 55 Data size: 216 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 57 Data size: 228 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: key_int (type: int)
outputColumnNames: _col0
@@ -918,7 +918,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [1]
- Statistics: Num rows: 55 Data size: 216 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 57 Data size: 228 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
@@ -927,7 +927,7 @@ STAGE PLANS:
className: VectorReduceSinkLongOperator
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 55 Data size: 216 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 57 Data size: 228 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized, llap
LLAP IO: all inputs
Map Vectorization:
@@ -950,15 +950,15 @@ STAGE PLANS:
0 _col0 (type: int)
1 _col0 (type: int)
2 _col0 (type: int)
- Statistics: Num rows: 1045 Data size: 3977 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 94 Data size: 752 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count()
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: bigint)
MergeJoin Vectorization:
enabled: false
@@ -983,13 +983,13 @@ STAGE PLANS:
projectedOutputColumnNums: [0]
mode: mergepartial
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -1004,7 +1004,7 @@ STAGE PLANS:
vectorized: true
Reduce Operator Tree:
Group By Operator
- aggregations: min(VALUE._col0), max(VALUE._col1), bloom_filter(VALUE._col2, expectedEntries=55)
+ aggregations: min(VALUE._col0), max(VALUE._col1), bloom_filter(VALUE._col2, expectedEntries=57)
Group By Vectorization:
aggregators: VectorUDAFMinLong(col 0:int) -> int, VectorUDAFMaxLong(col 1:int) -> int, VectorUDAFBloomFilterMerge(col 2:binary) -> binary
className: VectorGroupByOperator
@@ -1014,14 +1014,14 @@ STAGE PLANS:
projectedOutputColumnNums: [0, 1, 2]
mode: final
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
Reduce Sink Vectorization:
className: VectorReduceSinkEmptyKeyOperator
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: int), _col1 (type: int), _col2 (type: binary)
Stage: Stage-0
@@ -1075,7 +1075,7 @@ STAGE PLANS:
TableScan
alias: a
filterExpr: (key_str is not null and key_int is not null and (key_str BETWEEN DynamicValue(RS_7_b_key_str_min) AND DynamicValue(RS_7_b_key_str_max) and in_bloom_filter(key_str, DynamicValue(RS_7_b_key_str_bloom_filter)))) (type: boolean)
- Statistics: Num rows: 500 Data size: 89488 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
Filter Operator
@@ -1084,7 +1084,7 @@ STAGE PLANS:
native: true
predicateExpression: FilterExprAndExpr(children: SelectColumnIsNotNull(col 0:string), SelectColumnIsNotNull(col 1:int), FilterExprAndExpr(children: FilterStringColumnBetweenDynamicValue(col 0:string, left NULL, right NULL), VectorInBloomFilterColDynamicValue))
predicate: ((key_str BETWEEN DynamicValue(RS_7_b_key_str_min) AND DynamicValue(RS_7_b_key_str_max) and in_bloom_filter(key_str, DynamicValue(RS_7_b_key_str_bloom_filter))) and key_int is not null and key_str is not null) (type: boolean)
- Statistics: Num rows: 450 Data size: 80539 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: key_str (type: string), key_int (type: int)
outputColumnNames: _col0, _col1
@@ -1092,7 +1092,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1]
- Statistics: Num rows: 450 Data size: 80539 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string), _col1 (type: int)
sort order: ++
@@ -1101,7 +1101,7 @@ STAGE PLANS:
className: VectorReduceSinkMultiKeyOperator
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 450 Data size: 80539 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized, llap
LLAP IO: all inputs
Map Vectorization:
@@ -1118,7 +1118,7 @@ STAGE PLANS:
TableScan
alias: b
filterExpr: (key_str is not null and key_int is not null) (type: boolean)
- Statistics: Num rows: 57 Data size: 10528 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 57 Data size: 5130 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
Filter Operator
@@ -1127,7 +1127,7 @@ STAGE PLANS:
native: true
predicateExpression: FilterExprAndExpr(children: SelectColumnIsNotNull(col 0:string), SelectColumnIsNotNull(col 1:int))
predicate: (key_int is not null and key_str is not null) (type: boolean)
- Statistics: Num rows: 53 Data size: 9789 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 57 Data size: 5130 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: key_str (type: string), key_int (type: int)
outputColumnNames: _col0, _col1
@@ -1135,7 +1135,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1]
- Statistics: Num rows: 53 Data size: 9789 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 57 Data size: 5130 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string), _col1 (type: int)
sort order: ++
@@ -1144,7 +1144,7 @@ STAGE PLANS:
className: VectorReduceSinkMultiKeyOperator
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 53 Data size: 9789 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 57 Data size: 5130 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: string)
outputColumnNames: _col0
@@ -1152,9 +1152,9 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0]
- Statistics: Num rows: 53 Data size: 9789 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 57 Data size: 4902 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
- aggregations: min(_col0), max(_col0), bloom_filter(_col0, expectedEntries=53)
+ aggregations: min(_col0), max(_col0), bloom_filter(_col0, expectedEntries=57)
Group By Vectorization:
aggregators: VectorUDAFMinString(col 0:string) -> string, VectorUDAFMaxString(col 0:string) -> string, VectorUDAFBloomFilter(col 0:string) -> binary
className: VectorGroupByOperator
@@ -1164,14 +1164,14 @@ STAGE PLANS:
projectedOutputColumnNums: [0, 1, 2]
mode: hash
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 1 Data size: 740 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
Reduce Sink Vectorization:
className: VectorReduceSinkEmptyKeyOperator
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 1 Data size: 740 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: binary)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -1193,15 +1193,15 @@ STAGE PLANS:
keys:
0 _col0 (type: string), _col1 (type: int)
1 _col0 (type: string), _col1 (type: int)
- Statistics: Num rows: 495 Data size: 88592 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 90 Data size: 720 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count()
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: bigint)
MergeJoin Vectorization:
enabled: false
@@ -1226,13 +1226,13 @@ STAGE PLANS:
projectedOutputColumnNums: [0]
mode: mergepartial
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -1247,7 +1247,7 @@ STAGE PLANS:
vectorized: true
Reduce Operator Tree:
Group By Operator
- aggregations: min(VALUE._col0), max(VALUE._col1), bloom_filter(VALUE._col2, expectedEntries=53)
+ aggregations: min(VALUE._col0), max(VALUE._col1), bloom_filter(VALUE._col2, expectedEntries=57)
Group By Vectorization:
aggregators: VectorUDAFMinString(col 0:string) -> string, VectorUDAFMaxString(col 1:string) -> string, VectorUDAFBloomFilterMerge(col 2:binary) -> binary
className: VectorGroupByOperator
@@ -1257,14 +1257,14 @@ STAGE PLANS:
projectedOutputColumnNums: [0, 1, 2]
mode: final
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 1 Data size: 740 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
Reduce Sink Vectorization:
className: VectorReduceSinkEmptyKeyOperator
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 1 Data size: 740 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: binary)
Stage: Stage-0
@@ -1318,7 +1318,7 @@ STAGE PLANS:
TableScan
alias: a
filterExpr: (key_int is not null and (key_int BETWEEN DynamicValue(RS_7_b_key_int_min) AND DynamicValue(RS_7_b_key_int_max) and in_bloom_filter(key_int, DynamicValue(RS_7_b_key_int_bloom_filter)))) (type: boolean)
- Statistics: Num rows: 500 Data size: 1904 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
Filter Operator
@@ -1327,7 +1327,7 @@ STAGE PLANS:
native: true
predicateExpression: FilterExprAndExpr(children: SelectColumnIsNotNull(col 1:int), FilterExprAndExpr(children: FilterLongColumnBetweenDynamicValue(col 1:int, left 0, right 0), VectorInBloomFilterColDynamicValue))
predicate: ((key_int BETWEEN DynamicValue(RS_7_b_key_int_min) AND DynamicValue(RS_7_b_key_int_max) and in_bloom_filter(key_int, DynamicValue(RS_7_b_key_int_bloom_filter))) and key_int is not null) (type: boolean)
- Statistics: Num rows: 475 Data size: 1808 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: key_int (type: int)
outputColumnNames: _col0
@@ -1335,7 +1335,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [1]
- Statistics: Num rows: 475 Data size: 1808 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
@@ -1344,7 +1344,7 @@ STAGE PLANS:
className: VectorReduceSinkLongOperator
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 475 Data size: 1808 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized, llap
LLAP IO: all inputs
Map Vectorization:
@@ -1361,7 +1361,7 @@ STAGE PLANS:
TableScan
alias: b
filterExpr: ((value) IN ('nonexistent1', 'nonexistent2') and key_int is not null) (type: boolean)
- Statistics: Num rows: 57 Data size: 10528 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 57 Data size: 5358 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
Filter Operator
@@ -1370,7 +1370,7 @@ STAGE PLANS:
native: true
predicateExpression: FilterExprAndExpr(children: FilterStringColumnInList(col 2, values nonexistent1, nonexistent2), SelectColumnIsNotNull(col 1:int))
predicate: ((value) IN ('nonexistent1', 'nonexistent2') and key_int is not null) (type: boolean)
- Statistics: Num rows: 8 Data size: 1477 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 188 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: key_int (type: int)
outputColumnNames: _col0
@@ -1378,7 +1378,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [1]
- Statistics: Num rows: 8 Data size: 1477 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
@@ -1387,7 +1387,7 @@ STAGE PLANS:
className: VectorReduceSinkLongOperator
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 8 Data size: 1477 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: int)
outputColumnNames: _col0
@@ -1395,9 +1395,9 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [1]
- Statistics: Num rows: 8 Data size: 1477 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
- aggregations: min(_col0), max(_col0), bloom_filter(_col0, expectedEntries=8)
+ aggregations: min(_col0), max(_col0), bloom_filter(_col0, expectedEntries=2)
Group By Vectorization:
aggregators: VectorUDAFMinLong(col 1:int) -> int, VectorUDAFMaxLong(col 1:int) -> int, VectorUDAFBloomFilter(col 1:int) -> binary
className: VectorGroupByOperator
@@ -1407,14 +1407,14 @@ STAGE PLANS:
projectedOutputColumnNums: [0, 1, 2]
mode: hash
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 1 Data size: 200 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
Reduce Sink Vectorization:
className: VectorReduceSinkEmptyKeyOperator
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 1 Data size: 200 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: int), _col1 (type: int), _col2 (type: binary)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -1436,15 +1436,15 @@ STAGE PLANS:
keys:
0 _col0 (type: int)
1 _col0 (type: int)
- Statistics: Num rows: 522 Data size: 1988 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count()
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: bigint)
MergeJoin Vectorization:
enabled: false
@@ -1469,13 +1469,13 @@ STAGE PLANS:
projectedOutputColumnNums: [0]
mode: mergepartial
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -1490,7 +1490,7 @@ STAGE PLANS:
vectorized: true
Reduce Operator Tree:
Group By Operator
- aggregations: min(VALUE._col0), max(VALUE._col1), bloom_filter(VALUE._col2, expectedEntries=8)
+ aggregations: min(VALUE._col0), max(VALUE._col1), bloom_filter(VALUE._col2, expectedEntries=2)
Group By Vectorization:
aggregators: VectorUDAFMinLong(col 0:int) -> int, VectorUDAFMaxLong(col 1:int) -> int, VectorUDAFBloomFilterMerge(col 2:binary) -> binary
className: VectorGroupByOperator
@@ -1500,14 +1500,14 @@ STAGE PLANS:
projectedOutputColumnNums: [0, 1, 2]
mode: final
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 1 Data size: 200 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
Reduce Sink Vectorization:
className: VectorReduceSinkEmptyKeyOperator
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 1 Data size: 200 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: int), _col1 (type: int), _col2 (type: binary)
Stage: Stage-0
@@ -1575,19 +1575,19 @@ STAGE PLANS:
TableScan
alias: a
filterExpr: (key_int is not null and (key_int BETWEEN DynamicValue(RS_7_b_key_int_min) AND DynamicValue(RS_7_b_key_int_max) and in_bloom_filter(key_int, DynamicValue(RS_7_b_key_int_bloom_filter)))) (type: boolean)
- Statistics: Num rows: 500 Data size: 1904 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: ((key_int BETWEEN DynamicValue(RS_7_b_key_int_min) AND DynamicValue(RS_7_b_key_int_max) and in_bloom_filter(key_int, DynamicValue(RS_7_b_key_int_bloom_filter))) and key_int is not null) (type: boolean)
- Statistics: Num rows: 475 Data size: 1808 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: key_int (type: int)
outputColumnNames: _col0
- Statistics: Num rows: 475 Data size: 1808 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 475 Data size: 1808 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized, llap
LLAP IO: all inputs
Map 4
@@ -1632,15 +1632,15 @@ STAGE PLANS:
keys:
0 _col0 (type: int)
1 _col0 (type: int)
- Statistics: Num rows: 522 Data size: 1988 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 94 Data size: 752 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count()
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: bigint)
Reducer 3
Execution mode: vectorized, llap
@@ -1649,10 +1649,10 @@ STAGE PLANS:
aggregations: count(VALUE._col0)
mode: mergepartial
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
[27/35] hive git commit: HIVE-16957: Support CTAS for auto gather
column stats (Jesus Camacho Rodriguez, reviewed by Ashutosh Chauhan)
Posted by jc...@apache.org.
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/llap/materialized_view_create_rewrite_2.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/materialized_view_create_rewrite_2.q.out b/ql/src/test/results/clientpositive/llap/materialized_view_create_rewrite_2.q.out
index ce57ec1..82415de 100644
--- a/ql/src/test/results/clientpositive/llap/materialized_view_create_rewrite_2.q.out
+++ b/ql/src/test/results/clientpositive/llap/materialized_view_create_rewrite_2.q.out
@@ -28,16 +28,6 @@ POSTHOOK: Lineage: cmv_basetable_n9.a SCRIPT []
POSTHOOK: Lineage: cmv_basetable_n9.b SCRIPT []
POSTHOOK: Lineage: cmv_basetable_n9.c SCRIPT []
POSTHOOK: Lineage: cmv_basetable_n9.d SCRIPT []
-PREHOOK: query: analyze table cmv_basetable_n9 compute statistics for columns
-PREHOOK: type: ANALYZE_TABLE
-PREHOOK: Input: default@cmv_basetable_n9
-PREHOOK: Output: default@cmv_basetable_n9
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table cmv_basetable_n9 compute statistics for columns
-POSTHOOK: type: ANALYZE_TABLE
-POSTHOOK: Input: default@cmv_basetable_n9
-POSTHOOK: Output: default@cmv_basetable_n9
-#### A masked pattern was here ####
PREHOOK: query: create materialized view cmv_mat_view_n9
as select b from cmv_basetable_n9 where c > 10.0 group by a, b, c
PREHOOK: type: CREATE_MATERIALIZED_VIEW
@@ -269,24 +259,24 @@ STAGE PLANS:
TableScan
alias: default.cmv_mat_view_3
filterExpr: (c > 20) (type: boolean)
- Statistics: Num rows: 3 Data size: 1368 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 618 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: (c > 20) (type: boolean)
- Statistics: Num rows: 1 Data size: 456 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 206 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: a (type: int), b (type: varchar(256))
outputColumnNames: a, b
- Statistics: Num rows: 1 Data size: 456 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 206 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
keys: a (type: int), b (type: varchar(256))
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 456 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int), _col1 (type: varchar(256))
sort order: ++
Map-reduce partition columns: _col0 (type: int), _col1 (type: varchar(256))
- Statistics: Num rows: 1 Data size: 456 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: llap
LLAP IO: all inputs
Reducer 2
@@ -296,14 +286,14 @@ STAGE PLANS:
keys: KEY._col0 (type: int), KEY._col1 (type: varchar(256))
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 456 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col1 (type: varchar(256))
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 456 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 90 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 456 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 90 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -367,21 +357,21 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: default.cmv_mat_view_4
- Statistics: Num rows: 5 Data size: 1700 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 450 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: b (type: varchar(256))
outputColumnNames: b
- Statistics: Num rows: 5 Data size: 1700 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 450 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
keys: b (type: varchar(256))
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 5 Data size: 1700 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: varchar(256))
sort order: +
Map-reduce partition columns: _col0 (type: varchar(256))
- Statistics: Num rows: 5 Data size: 1700 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: llap
LLAP IO: all inputs
Reducer 2
@@ -391,10 +381,10 @@ STAGE PLANS:
keys: KEY._col0 (type: varchar(256))
mode: mergepartial
outputColumnNames: _col0
- Statistics: Num rows: 2 Data size: 680 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 2 Data size: 680 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -445,16 +435,6 @@ POSTHOOK: Lineage: cmv_basetable_2_n4.a SCRIPT []
POSTHOOK: Lineage: cmv_basetable_2_n4.b SCRIPT []
POSTHOOK: Lineage: cmv_basetable_2_n4.c SCRIPT []
POSTHOOK: Lineage: cmv_basetable_2_n4.d SCRIPT []
-PREHOOK: query: analyze table cmv_basetable_2_n4 compute statistics for columns
-PREHOOK: type: ANALYZE_TABLE
-PREHOOK: Input: default@cmv_basetable_2_n4
-PREHOOK: Output: default@cmv_basetable_2_n4
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table cmv_basetable_2_n4 compute statistics for columns
-POSTHOOK: type: ANALYZE_TABLE
-POSTHOOK: Input: default@cmv_basetable_2_n4
-POSTHOOK: Output: default@cmv_basetable_2_n4
-#### A masked pattern was here ####
PREHOOK: query: create materialized view cmv_mat_view_5
as select cmv_basetable_n9.a, cmv_basetable_2_n4.c
from cmv_basetable_n9 join cmv_basetable_2_n4 on (cmv_basetable_n9.a = cmv_basetable_2_n4.a)
@@ -570,24 +550,24 @@ STAGE PLANS:
TableScan
alias: default.cmv_mat_view_5
filterExpr: (c > 10.1) (type: boolean)
- Statistics: Num rows: 2 Data size: 232 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 232 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: (c > 10.1) (type: boolean)
- Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: a (type: int)
outputColumnNames: a
- Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
keys: a (type: int)
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: llap
LLAP IO: all inputs
Reducer 2
@@ -597,10 +577,10 @@ STAGE PLANS:
keys: KEY._col0 (type: int)
mode: mergepartial
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/llap/materialized_view_create_rewrite_3.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/materialized_view_create_rewrite_3.q.out b/ql/src/test/results/clientpositive/llap/materialized_view_create_rewrite_3.q.out
index 8fcab1f..e8d0657 100644
--- a/ql/src/test/results/clientpositive/llap/materialized_view_create_rewrite_3.q.out
+++ b/ql/src/test/results/clientpositive/llap/materialized_view_create_rewrite_3.q.out
@@ -28,16 +28,6 @@ POSTHOOK: Lineage: cmv_basetable.a SCRIPT []
POSTHOOK: Lineage: cmv_basetable.b SCRIPT []
POSTHOOK: Lineage: cmv_basetable.c SCRIPT []
POSTHOOK: Lineage: cmv_basetable.d SCRIPT []
-PREHOOK: query: analyze table cmv_basetable compute statistics for columns
-PREHOOK: type: ANALYZE_TABLE
-PREHOOK: Input: default@cmv_basetable
-PREHOOK: Output: default@cmv_basetable
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table cmv_basetable compute statistics for columns
-POSTHOOK: type: ANALYZE_TABLE
-POSTHOOK: Input: default@cmv_basetable
-POSTHOOK: Output: default@cmv_basetable
-#### A masked pattern was here ####
PREHOOK: query: create table cmv_basetable_2 (a int, b varchar(256), c decimal(10,2), d int) stored as orc TBLPROPERTIES ('transactional'='true')
PREHOOK: type: CREATETABLE
PREHOOK: Output: database:default
@@ -62,16 +52,6 @@ POSTHOOK: Lineage: cmv_basetable_2.a SCRIPT []
POSTHOOK: Lineage: cmv_basetable_2.b SCRIPT []
POSTHOOK: Lineage: cmv_basetable_2.c SCRIPT []
POSTHOOK: Lineage: cmv_basetable_2.d SCRIPT []
-PREHOOK: query: analyze table cmv_basetable_2 compute statistics for columns
-PREHOOK: type: ANALYZE_TABLE
-PREHOOK: Input: default@cmv_basetable_2
-PREHOOK: Output: default@cmv_basetable_2
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table cmv_basetable_2 compute statistics for columns
-POSTHOOK: type: ANALYZE_TABLE
-POSTHOOK: Input: default@cmv_basetable_2
-POSTHOOK: Output: default@cmv_basetable_2
-#### A masked pattern was here ####
PREHOOK: query: EXPLAIN
CREATE MATERIALIZED VIEW cmv_mat_view AS
SELECT cmv_basetable.a, cmv_basetable_2.c
@@ -97,7 +77,7 @@ POSTHOOK: Output: default@cmv_mat_view
STAGE DEPENDENCIES:
Stage-1 is a root stage
Stage-2 depends on stages: Stage-1
- Stage-4 depends on stages: Stage-2, Stage-0
+ Stage-4 depends on stages: Stage-0, Stage-2
Stage-3 depends on stages: Stage-4
Stage-5 depends on stages: Stage-3
Stage-0 depends on stages: Stage-1
@@ -107,8 +87,9 @@ STAGE PLANS:
Tez
#### A masked pattern was here ####
Edges:
- Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 4 (SIMPLE_EDGE)
+ Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 5 (SIMPLE_EDGE)
Reducer 3 <- Reducer 2 (SIMPLE_EDGE)
+ Reducer 4 <- Reducer 3 (CUSTOM_SIMPLE_EDGE)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -131,7 +112,7 @@ STAGE PLANS:
Statistics: Num rows: 5 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: llap
LLAP IO: may be used (ACID table)
- Map 4
+ Map 5
Map Operator Tree:
TableScan
alias: cmv_basetable_2
@@ -189,6 +170,34 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat
serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde
name: default.cmv_mat_view
+ Select Operator
+ expressions: _col0 (type: int), _col1 (type: decimal(10,2))
+ outputColumnNames: col1, col2
+ Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: COMPLETE
+ Group By Operator
+ aggregations: compute_stats(col1, 'hll'), compute_stats(col2, 'hll')
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 1056 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 1056 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col0 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,min:decimal(10,2),max:decimal(10,2),countnulls:bigint,bitvector:binary>)
+ Reducer 4
+ Execution mode: llap
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 1088 Basic stats: COMPLETE Column stats: COMPLETE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 1088 Basic stats: COMPLETE Column stats: COMPLETE
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
Stage: Stage-2
Dependency Collection
@@ -211,6 +220,10 @@ STAGE PLANS:
Stage: Stage-3
Stats Work
Basic Stats Work:
+ Column Stats Desc:
+ Columns: a, c
+ Column Types: int, decimal(10,2)
+ Table: default.cmv_mat_view
Stage: Stage-5
Materialized View Work
@@ -313,16 +326,6 @@ POSTHOOK: Lineage: cmv_basetable_2.a SCRIPT []
POSTHOOK: Lineage: cmv_basetable_2.b SCRIPT []
POSTHOOK: Lineage: cmv_basetable_2.c SCRIPT []
POSTHOOK: Lineage: cmv_basetable_2.d SCRIPT []
-PREHOOK: query: analyze table cmv_basetable_2 compute statistics for columns
-PREHOOK: type: ANALYZE_TABLE
-PREHOOK: Input: default@cmv_basetable_2
-PREHOOK: Output: default@cmv_basetable_2
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table cmv_basetable_2 compute statistics for columns
-POSTHOOK: type: ANALYZE_TABLE
-POSTHOOK: Input: default@cmv_basetable_2
-POSTHOOK: Output: default@cmv_basetable_2
-#### A masked pattern was here ####
PREHOOK: query: EXPLAIN
SELECT cmv_basetable.a
FROM cmv_basetable join cmv_basetable_2 ON (cmv_basetable.a = cmv_basetable_2.a)
@@ -518,10 +521,10 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: cmv_basetable_2
- filterExpr: ((c > 10) and (ROW__ID.writeid > 2) and a is not null) (type: boolean)
+ filterExpr: ((c > 10) and (ROW__ID.writeid > 1) and a is not null) (type: boolean)
Statistics: Num rows: 3 Data size: 348 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
- predicate: ((ROW__ID.writeid > 2) and (c > 10) and a is not null) (type: boolean)
+ predicate: ((ROW__ID.writeid > 1) and (c > 10) and a is not null) (type: boolean)
Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: a (type: int), c (type: decimal(10,2))
@@ -539,21 +542,21 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: default.cmv_mat_view
- Statistics: Num rows: 2 Data size: 232 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 232 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: a (type: int), c (type: decimal(10,2))
outputColumnNames: _col0, _col1
- Statistics: Num rows: 2 Data size: 232 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 232 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
keys: _col0 (type: int), _col1 (type: decimal(10,2))
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int), _col1 (type: decimal(10,2))
sort order: ++
Map-reduce partition columns: _col0 (type: int), _col1 (type: decimal(10,2))
- Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: llap
LLAP IO: all inputs
Reducer 2
@@ -589,12 +592,12 @@ STAGE PLANS:
keys: _col0 (type: int), _col1 (type: decimal(10,2))
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int), _col1 (type: decimal(10,2))
sort order: ++
Map-reduce partition columns: _col0 (type: int), _col1 (type: decimal(10,2))
- Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: COMPLETE
Reducer 5
Execution mode: llap
Reduce Operator Tree:
@@ -602,10 +605,10 @@ STAGE PLANS:
keys: KEY._col0 (type: int), KEY._col1 (type: decimal(10,2))
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat
@@ -614,15 +617,15 @@ STAGE PLANS:
Select Operator
expressions: _col0 (type: int), _col1 (type: decimal(10,2))
outputColumnNames: a, c
- Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: compute_stats(a, 'hll'), compute_stats(c, 'hll')
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 1056 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 1 Data size: 1056 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
- Statistics: Num rows: 1 Data size: 1056 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 1 Data size: 1056 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,min:decimal(10,2),max:decimal(10,2),countnulls:bigint,bitvector:binary>)
Reducer 6
Execution mode: llap
@@ -631,10 +634,10 @@ STAGE PLANS:
aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1)
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 1088 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 1 Data size: 1088 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 1088 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 1 Data size: 1088 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -976,16 +979,6 @@ POSTHOOK: Lineage: cmv_irrelevant_table.a SCRIPT []
POSTHOOK: Lineage: cmv_irrelevant_table.b SCRIPT []
POSTHOOK: Lineage: cmv_irrelevant_table.c SCRIPT []
POSTHOOK: Lineage: cmv_irrelevant_table.d SCRIPT []
-PREHOOK: query: analyze table cmv_irrelevant_table compute statistics for columns
-PREHOOK: type: ANALYZE_TABLE
-PREHOOK: Input: default@cmv_irrelevant_table
-PREHOOK: Output: default@cmv_irrelevant_table
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table cmv_irrelevant_table compute statistics for columns
-POSTHOOK: type: ANALYZE_TABLE
-POSTHOOK: Input: default@cmv_irrelevant_table
-POSTHOOK: Output: default@cmv_irrelevant_table
-#### A masked pattern was here ####
PREHOOK: query: EXPLAIN
SELECT cmv_basetable.a
FROM cmv_basetable join cmv_basetable_2 ON (cmv_basetable.a = cmv_basetable_2.a)
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/llap/materialized_view_create_rewrite_4.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/materialized_view_create_rewrite_4.q.out b/ql/src/test/results/clientpositive/llap/materialized_view_create_rewrite_4.q.out
index 8fe194e..1b42330 100644
--- a/ql/src/test/results/clientpositive/llap/materialized_view_create_rewrite_4.q.out
+++ b/ql/src/test/results/clientpositive/llap/materialized_view_create_rewrite_4.q.out
@@ -28,16 +28,6 @@ POSTHOOK: Lineage: cmv_basetable_n5.a SCRIPT []
POSTHOOK: Lineage: cmv_basetable_n5.b SCRIPT []
POSTHOOK: Lineage: cmv_basetable_n5.c SCRIPT []
POSTHOOK: Lineage: cmv_basetable_n5.d SCRIPT []
-PREHOOK: query: analyze table cmv_basetable_n5 compute statistics for columns
-PREHOOK: type: ANALYZE_TABLE
-PREHOOK: Input: default@cmv_basetable_n5
-PREHOOK: Output: default@cmv_basetable_n5
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table cmv_basetable_n5 compute statistics for columns
-POSTHOOK: type: ANALYZE_TABLE
-POSTHOOK: Input: default@cmv_basetable_n5
-POSTHOOK: Output: default@cmv_basetable_n5
-#### A masked pattern was here ####
PREHOOK: query: create table cmv_basetable_2_n2 (a int, b varchar(256), c decimal(10,2), d int) stored as orc TBLPROPERTIES ('transactional'='true')
PREHOOK: type: CREATETABLE
PREHOOK: Output: database:default
@@ -62,16 +52,6 @@ POSTHOOK: Lineage: cmv_basetable_2_n2.a SCRIPT []
POSTHOOK: Lineage: cmv_basetable_2_n2.b SCRIPT []
POSTHOOK: Lineage: cmv_basetable_2_n2.c SCRIPT []
POSTHOOK: Lineage: cmv_basetable_2_n2.d SCRIPT []
-PREHOOK: query: analyze table cmv_basetable_2_n2 compute statistics for columns
-PREHOOK: type: ANALYZE_TABLE
-PREHOOK: Input: default@cmv_basetable_2_n2
-PREHOOK: Output: default@cmv_basetable_2_n2
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table cmv_basetable_2_n2 compute statistics for columns
-POSTHOOK: type: ANALYZE_TABLE
-POSTHOOK: Input: default@cmv_basetable_2_n2
-POSTHOOK: Output: default@cmv_basetable_2_n2
-#### A masked pattern was here ####
PREHOOK: query: EXPLAIN
CREATE MATERIALIZED VIEW cmv_mat_view_n5 DISABLE REWRITE TBLPROPERTIES ('transactional'='true') AS
SELECT cmv_basetable_n5.a, cmv_basetable_2_n2.c, sum(cmv_basetable_2_n2.d)
@@ -97,7 +77,7 @@ POSTHOOK: Output: default@cmv_mat_view_n5
STAGE DEPENDENCIES:
Stage-1 is a root stage
Stage-2 depends on stages: Stage-1
- Stage-4 depends on stages: Stage-2, Stage-0
+ Stage-4 depends on stages: Stage-0, Stage-2
Stage-3 depends on stages: Stage-4
Stage-5 depends on stages: Stage-3
Stage-0 depends on stages: Stage-1
@@ -192,6 +172,27 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat
serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde
name: default.cmv_mat_view_n5
+ Write Type: INSERT
+ Select Operator
+ expressions: _col0 (type: int), _col1 (type: decimal(10,2)), _col2 (type: bigint)
+ outputColumnNames: col1, col2, col3
+ Statistics: Num rows: 1 Data size: 124 Basic stats: COMPLETE Column stats: COMPLETE
+ Group By Operator
+ aggregations: compute_stats(col1, 'hll'), compute_stats(col2, 'hll'), compute_stats(col3, 'hll')
+ mode: complete
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 1480 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: _col0 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col1 (type: struct<columntype:string,min:decimal(10,2),max:decimal(10,2),countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col2 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>)
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 1480 Basic stats: COMPLETE Column stats: COMPLETE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 1480 Basic stats: COMPLETE Column stats: COMPLETE
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
Stage: Stage-2
Dependency Collection
@@ -215,6 +216,10 @@ STAGE PLANS:
Stage: Stage-3
Stats Work
Basic Stats Work:
+ Column Stats Desc:
+ Columns: a, c, _c2
+ Column Types: int, decimal(10,2), bigint
+ Table: default.cmv_mat_view_n5
Stage: Stage-5
Materialized View Work
@@ -224,6 +229,7 @@ STAGE PLANS:
files:
hdfs directory: true
#### A masked pattern was here ####
+ Write Type: INSERT
PREHOOK: query: CREATE MATERIALIZED VIEW cmv_mat_view_n5 DISABLE REWRITE TBLPROPERTIES ('transactional'='true') AS
SELECT cmv_basetable_n5.a, cmv_basetable_2_n2.c, sum(cmv_basetable_2_n2.d)
@@ -245,16 +251,6 @@ POSTHOOK: Input: default@cmv_basetable_2_n2
POSTHOOK: Input: default@cmv_basetable_n5
POSTHOOK: Output: database:default
POSTHOOK: Output: default@cmv_mat_view_n5
-PREHOOK: query: analyze table cmv_mat_view_n5 compute statistics for columns
-PREHOOK: type: ANALYZE_TABLE
-PREHOOK: Input: default@cmv_mat_view_n5
-PREHOOK: Output: default@cmv_mat_view_n5
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table cmv_mat_view_n5 compute statistics for columns
-POSTHOOK: type: ANALYZE_TABLE
-POSTHOOK: Input: default@cmv_mat_view_n5
-POSTHOOK: Output: default@cmv_mat_view_n5
-#### A masked pattern was here ####
PREHOOK: query: DESCRIBE FORMATTED cmv_mat_view_n5
PREHOOK: type: DESCTABLE
PREHOOK: Input: default@cmv_mat_view_n5
@@ -275,10 +271,10 @@ Table Type: MATERIALIZED_VIEW
Table Parameters:
COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"_c2\":\"true\",\"a\":\"true\",\"c\":\"true\"}}
bucketing_version 2
- numFiles 2
+ numFiles 1
numRows 2
rawDataSize 0
- totalSize 736
+ totalSize 809
transactional true
transactional_properties default
#### A masked pattern was here ####
@@ -457,16 +453,6 @@ POSTHOOK: Lineage: cmv_basetable_2_n2.a SCRIPT []
POSTHOOK: Lineage: cmv_basetable_2_n2.b SCRIPT []
POSTHOOK: Lineage: cmv_basetable_2_n2.c SCRIPT []
POSTHOOK: Lineage: cmv_basetable_2_n2.d SCRIPT []
-PREHOOK: query: analyze table cmv_basetable_2_n2 compute statistics for columns
-PREHOOK: type: ANALYZE_TABLE
-PREHOOK: Input: default@cmv_basetable_2_n2
-PREHOOK: Output: default@cmv_basetable_2_n2
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table cmv_basetable_2_n2 compute statistics for columns
-POSTHOOK: type: ANALYZE_TABLE
-POSTHOOK: Input: default@cmv_basetable_2_n2
-POSTHOOK: Output: default@cmv_basetable_2_n2
-#### A masked pattern was here ####
PREHOOK: query: EXPLAIN
ALTER MATERIALIZED VIEW cmv_mat_view_n5 ENABLE REWRITE
PREHOOK: type: ALTER_MATERIALIZED_VIEW_REWRITE
@@ -515,10 +501,10 @@ Table Type: MATERIALIZED_VIEW
Table Parameters:
COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"_c2\":\"true\",\"a\":\"true\",\"c\":\"true\"}}
bucketing_version 2
- numFiles 2
+ numFiles 1
numRows 2
rawDataSize 0
- totalSize 736
+ totalSize 809
transactional true
transactional_properties default
#### A masked pattern was here ####
@@ -766,10 +752,10 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: cmv_basetable_2_n2
- filterExpr: ((c > 10) and (ROW__ID.writeid > 2) and a is not null) (type: boolean)
+ filterExpr: ((c > 10) and (ROW__ID.writeid > 1) and a is not null) (type: boolean)
Statistics: Num rows: 3 Data size: 360 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
- predicate: ((ROW__ID.writeid > 2) and (c > 10) and a is not null) (type: boolean)
+ predicate: ((ROW__ID.writeid > 1) and (c > 10) and a is not null) (type: boolean)
Statistics: Num rows: 1 Data size: 120 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: a (type: int), c (type: decimal(10,2)), d (type: int)
@@ -983,10 +969,10 @@ Table Type: MATERIALIZED_VIEW
Table Parameters:
COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
bucketing_version 2
- numFiles 3
+ numFiles 2
numRows 3
rawDataSize 0
- totalSize 1500
+ totalSize 1573
transactional true
transactional_properties default
#### A masked pattern was here ####
@@ -1247,6 +1233,54 @@ POSTHOOK: Output: default@cmv_mat_view_n5
POSTHOOK: Lineage: cmv_mat_view_n5._c2 EXPRESSION [(cmv_basetable_2_n2)cmv_basetable_2_n2.FieldSchema(name:d, type:int, comment:null), ]
POSTHOOK: Lineage: cmv_mat_view_n5.a SIMPLE [(cmv_basetable_n5)cmv_basetable_n5.FieldSchema(name:a, type:int, comment:null), ]
POSTHOOK: Lineage: cmv_mat_view_n5.c SIMPLE [(cmv_basetable_2_n2)cmv_basetable_2_n2.FieldSchema(name:c, type:decimal(10,2), comment:null), ]
+PREHOOK: query: DESCRIBE FORMATTED cmv_mat_view_n5
+PREHOOK: type: DESCTABLE
+PREHOOK: Input: default@cmv_mat_view_n5
+POSTHOOK: query: DESCRIBE FORMATTED cmv_mat_view_n5
+POSTHOOK: type: DESCTABLE
+POSTHOOK: Input: default@cmv_mat_view_n5
+# col_name data_type comment
+a int
+c decimal(10,2)
+_c2 bigint
+
+# Detailed Table Information
+Database: default
+#### A masked pattern was here ####
+Retention: 0
+#### A masked pattern was here ####
+Table Type: MATERIALIZED_VIEW
+Table Parameters:
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"_c2\":\"true\",\"a\":\"true\",\"c\":\"true\"}}
+ bucketing_version 2
+ numFiles 1
+ numRows 3
+ rawDataSize 0
+ totalSize 814
+ transactional true
+ transactional_properties default
+#### A masked pattern was here ####
+
+# Storage Information
+SerDe Library: org.apache.hadoop.hive.ql.io.orc.OrcSerde
+InputFormat: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
+OutputFormat: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat
+Compressed: No
+Num Buckets: -1
+Bucket Columns: []
+Sort Columns: []
+
+# Materialized View Information
+Original Query: SELECT cmv_basetable_n5.a, cmv_basetable_2_n2.c, sum(cmv_basetable_2_n2.d)
+ FROM cmv_basetable_n5 JOIN cmv_basetable_2_n2 ON (cmv_basetable_n5.a = cmv_basetable_2_n2.a)
+ WHERE cmv_basetable_2_n2.c > 10.0
+ GROUP BY cmv_basetable_n5.a, cmv_basetable_2_n2.c
+Expanded Query: SELECT `cmv_basetable_n5`.`a`, `cmv_basetable_2_n2`.`c`, sum(`cmv_basetable_2_n2`.`d`)
+ FROM `default`.`cmv_basetable_n5` JOIN `default`.`cmv_basetable_2_n2` ON (`cmv_basetable_n5`.`a` = `cmv_basetable_2_n2`.`a`)
+ WHERE `cmv_basetable_2_n2`.`c` > 10.0
+ GROUP BY `cmv_basetable_n5`.`a`, `cmv_basetable_2_n2`.`c`
+Rewrite Enabled: Yes
+Outdated for Rewriting: No
PREHOOK: query: EXPLAIN
SELECT cmv_basetable_n5.a, sum(cmv_basetable_2_n2.d)
FROM cmv_basetable_n5 join cmv_basetable_2_n2 ON (cmv_basetable_n5.a = cmv_basetable_2_n2.a)
@@ -1483,6 +1517,54 @@ POSTHOOK: Output: default@cmv_mat_view_n5
POSTHOOK: Lineage: cmv_mat_view_n5._c2 EXPRESSION [(cmv_basetable_2_n2)cmv_basetable_2_n2.FieldSchema(name:d, type:int, comment:null), ]
POSTHOOK: Lineage: cmv_mat_view_n5.a SIMPLE [(cmv_basetable_n5)cmv_basetable_n5.FieldSchema(name:a, type:int, comment:null), ]
POSTHOOK: Lineage: cmv_mat_view_n5.c SIMPLE [(cmv_basetable_2_n2)cmv_basetable_2_n2.FieldSchema(name:c, type:decimal(10,2), comment:null), ]
+PREHOOK: query: DESCRIBE FORMATTED cmv_mat_view_n5
+PREHOOK: type: DESCTABLE
+PREHOOK: Input: default@cmv_mat_view_n5
+POSTHOOK: query: DESCRIBE FORMATTED cmv_mat_view_n5
+POSTHOOK: type: DESCTABLE
+POSTHOOK: Input: default@cmv_mat_view_n5
+# col_name data_type comment
+a int
+c decimal(10,2)
+_c2 bigint
+
+# Detailed Table Information
+Database: default
+#### A masked pattern was here ####
+Retention: 0
+#### A masked pattern was here ####
+Table Type: MATERIALIZED_VIEW
+Table Parameters:
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"_c2\":\"true\",\"a\":\"true\",\"c\":\"true\"}}
+ bucketing_version 2
+ numFiles 1
+ numRows 2
+ rawDataSize 0
+ totalSize 812
+ transactional true
+ transactional_properties default
+#### A masked pattern was here ####
+
+# Storage Information
+SerDe Library: org.apache.hadoop.hive.ql.io.orc.OrcSerde
+InputFormat: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
+OutputFormat: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat
+Compressed: No
+Num Buckets: -1
+Bucket Columns: []
+Sort Columns: []
+
+# Materialized View Information
+Original Query: SELECT cmv_basetable_n5.a, cmv_basetable_2_n2.c, sum(cmv_basetable_2_n2.d)
+ FROM cmv_basetable_n5 JOIN cmv_basetable_2_n2 ON (cmv_basetable_n5.a = cmv_basetable_2_n2.a)
+ WHERE cmv_basetable_2_n2.c > 10.0
+ GROUP BY cmv_basetable_n5.a, cmv_basetable_2_n2.c
+Expanded Query: SELECT `cmv_basetable_n5`.`a`, `cmv_basetable_2_n2`.`c`, sum(`cmv_basetable_2_n2`.`d`)
+ FROM `default`.`cmv_basetable_n5` JOIN `default`.`cmv_basetable_2_n2` ON (`cmv_basetable_n5`.`a` = `cmv_basetable_2_n2`.`a`)
+ WHERE `cmv_basetable_2_n2`.`c` > 10.0
+ GROUP BY `cmv_basetable_n5`.`a`, `cmv_basetable_2_n2`.`c`
+Rewrite Enabled: Yes
+Outdated for Rewriting: No
PREHOOK: query: EXPLAIN
SELECT cmv_basetable_n5.a, sum(cmv_basetable_2_n2.d)
FROM cmv_basetable_n5 join cmv_basetable_2_n2 ON (cmv_basetable_n5.a = cmv_basetable_2_n2.a)
@@ -1637,10 +1719,10 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: cmv_basetable_2_n2
- filterExpr: ((c > 10) and (ROW__ID.writeid > 6) and a is not null) (type: boolean)
+ filterExpr: ((c > 10) and (ROW__ID.writeid > 4) and a is not null) (type: boolean)
Statistics: Num rows: 3 Data size: 360 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
- predicate: ((ROW__ID.writeid > 6) and (c > 10) and a is not null) (type: boolean)
+ predicate: ((ROW__ID.writeid > 4) and (c > 10) and a is not null) (type: boolean)
Statistics: Num rows: 1 Data size: 120 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: a (type: int), c (type: decimal(10,2)), d (type: int)
@@ -1834,6 +1916,54 @@ POSTHOOK: Output: default@cmv_mat_view_n5
POSTHOOK: Lineage: cmv_mat_view_n5._c2 EXPRESSION [(cmv_mat_view_n5)default.cmv_mat_view_n5.FieldSchema(name:a, type:int, comment:null), (cmv_mat_view_n5)default.cmv_mat_view_n5.FieldSchema(name:c, type:decimal(10,2), comment:null), (cmv_basetable_2_n2)cmv_basetable_2_n2.FieldSchema(name:d, type:int, comment:null), (cmv_mat_view_n5)default.cmv_mat_view_n5.FieldSchema(name:_c2, type:bigint, comment:null), ]
POSTHOOK: Lineage: cmv_mat_view_n5.a SIMPLE [(cmv_basetable_n5)cmv_basetable_n5.FieldSchema(name:a, type:int, comment:null), ]
POSTHOOK: Lineage: cmv_mat_view_n5.c SIMPLE [(cmv_basetable_2_n2)cmv_basetable_2_n2.FieldSchema(name:c, type:decimal(10,2), comment:null), ]
+PREHOOK: query: DESCRIBE FORMATTED cmv_mat_view_n5
+PREHOOK: type: DESCTABLE
+PREHOOK: Input: default@cmv_mat_view_n5
+POSTHOOK: query: DESCRIBE FORMATTED cmv_mat_view_n5
+POSTHOOK: type: DESCTABLE
+POSTHOOK: Input: default@cmv_mat_view_n5
+# col_name data_type comment
+a int
+c decimal(10,2)
+_c2 bigint
+
+# Detailed Table Information
+Database: default
+#### A masked pattern was here ####
+Retention: 0
+#### A masked pattern was here ####
+Table Type: MATERIALIZED_VIEW
+Table Parameters:
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
+ bucketing_version 2
+ numFiles 2
+ numRows 3
+ rawDataSize 0
+ totalSize 1573
+ transactional true
+ transactional_properties default
+#### A masked pattern was here ####
+
+# Storage Information
+SerDe Library: org.apache.hadoop.hive.ql.io.orc.OrcSerde
+InputFormat: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
+OutputFormat: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat
+Compressed: No
+Num Buckets: -1
+Bucket Columns: []
+Sort Columns: []
+
+# Materialized View Information
+Original Query: SELECT cmv_basetable_n5.a, cmv_basetable_2_n2.c, sum(cmv_basetable_2_n2.d)
+ FROM cmv_basetable_n5 JOIN cmv_basetable_2_n2 ON (cmv_basetable_n5.a = cmv_basetable_2_n2.a)
+ WHERE cmv_basetable_2_n2.c > 10.0
+ GROUP BY cmv_basetable_n5.a, cmv_basetable_2_n2.c
+Expanded Query: SELECT `cmv_basetable_n5`.`a`, `cmv_basetable_2_n2`.`c`, sum(`cmv_basetable_2_n2`.`d`)
+ FROM `default`.`cmv_basetable_n5` JOIN `default`.`cmv_basetable_2_n2` ON (`cmv_basetable_n5`.`a` = `cmv_basetable_2_n2`.`a`)
+ WHERE `cmv_basetable_2_n2`.`c` > 10.0
+ GROUP BY `cmv_basetable_n5`.`a`, `cmv_basetable_2_n2`.`c`
+Rewrite Enabled: Yes
+Outdated for Rewriting: No
PREHOOK: query: EXPLAIN
SELECT cmv_basetable_n5.a, sum(cmv_basetable_2_n2.d)
FROM cmv_basetable_n5 join cmv_basetable_2_n2 ON (cmv_basetable_n5.a = cmv_basetable_2_n2.a)
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/llap/materialized_view_create_rewrite_5.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/materialized_view_create_rewrite_5.q.out b/ql/src/test/results/clientpositive/llap/materialized_view_create_rewrite_5.q.out
index 117593e..1b0d9e0 100644
--- a/ql/src/test/results/clientpositive/llap/materialized_view_create_rewrite_5.q.out
+++ b/ql/src/test/results/clientpositive/llap/materialized_view_create_rewrite_5.q.out
@@ -28,16 +28,6 @@ POSTHOOK: Lineage: cmv_basetable_n6.a SCRIPT []
POSTHOOK: Lineage: cmv_basetable_n6.b SCRIPT []
POSTHOOK: Lineage: cmv_basetable_n6.c SCRIPT []
POSTHOOK: Lineage: cmv_basetable_n6.d SCRIPT []
-PREHOOK: query: analyze table cmv_basetable_n6 compute statistics for columns
-PREHOOK: type: ANALYZE_TABLE
-PREHOOK: Input: default@cmv_basetable_n6
-PREHOOK: Output: default@cmv_basetable_n6
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table cmv_basetable_n6 compute statistics for columns
-POSTHOOK: type: ANALYZE_TABLE
-POSTHOOK: Input: default@cmv_basetable_n6
-POSTHOOK: Output: default@cmv_basetable_n6
-#### A masked pattern was here ####
PREHOOK: query: create table cmv_basetable_2_n3 (a int, b varchar(256), c decimal(10,2), d int) stored as orc TBLPROPERTIES ('transactional'='true')
PREHOOK: type: CREATETABLE
PREHOOK: Output: database:default
@@ -62,16 +52,6 @@ POSTHOOK: Lineage: cmv_basetable_2_n3.a SCRIPT []
POSTHOOK: Lineage: cmv_basetable_2_n3.b SCRIPT []
POSTHOOK: Lineage: cmv_basetable_2_n3.c SCRIPT []
POSTHOOK: Lineage: cmv_basetable_2_n3.d SCRIPT []
-PREHOOK: query: analyze table cmv_basetable_2_n3 compute statistics for columns
-PREHOOK: type: ANALYZE_TABLE
-PREHOOK: Input: default@cmv_basetable_2_n3
-PREHOOK: Output: default@cmv_basetable_2_n3
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table cmv_basetable_2_n3 compute statistics for columns
-POSTHOOK: type: ANALYZE_TABLE
-POSTHOOK: Input: default@cmv_basetable_2_n3
-POSTHOOK: Output: default@cmv_basetable_2_n3
-#### A masked pattern was here ####
PREHOOK: query: CREATE MATERIALIZED VIEW cmv_mat_view_n6
TBLPROPERTIES ('transactional'='true') AS
SELECT cmv_basetable_n6.a, cmv_basetable_2_n3.c
@@ -92,16 +72,6 @@ POSTHOOK: Input: default@cmv_basetable_2_n3
POSTHOOK: Input: default@cmv_basetable_n6
POSTHOOK: Output: database:default
POSTHOOK: Output: default@cmv_mat_view_n6
-PREHOOK: query: analyze table cmv_mat_view_n6 compute statistics for columns
-PREHOOK: type: ANALYZE_TABLE
-PREHOOK: Input: default@cmv_mat_view_n6
-PREHOOK: Output: default@cmv_mat_view_n6
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table cmv_mat_view_n6 compute statistics for columns
-POSTHOOK: type: ANALYZE_TABLE
-POSTHOOK: Input: default@cmv_mat_view_n6
-POSTHOOK: Output: default@cmv_mat_view_n6
-#### A masked pattern was here ####
PREHOOK: query: insert into cmv_basetable_2_n3 values
(3, 'charlie', 15.8, 1)
PREHOOK: type: QUERY
@@ -116,16 +86,6 @@ POSTHOOK: Lineage: cmv_basetable_2_n3.a SCRIPT []
POSTHOOK: Lineage: cmv_basetable_2_n3.b SCRIPT []
POSTHOOK: Lineage: cmv_basetable_2_n3.c SCRIPT []
POSTHOOK: Lineage: cmv_basetable_2_n3.d SCRIPT []
-PREHOOK: query: analyze table cmv_basetable_2_n3 compute statistics for columns
-PREHOOK: type: ANALYZE_TABLE
-PREHOOK: Input: default@cmv_basetable_2_n3
-PREHOOK: Output: default@cmv_basetable_2_n3
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table cmv_basetable_2_n3 compute statistics for columns
-POSTHOOK: type: ANALYZE_TABLE
-POSTHOOK: Input: default@cmv_basetable_2_n3
-POSTHOOK: Output: default@cmv_basetable_2_n3
-#### A masked pattern was here ####
PREHOOK: query: EXPLAIN
SELECT cmv_basetable_n6.a
FROM cmv_basetable_n6 join cmv_basetable_2_n3 ON (cmv_basetable_n6.a = cmv_basetable_2_n3.a)
@@ -290,10 +250,10 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: cmv_basetable_2_n3
- filterExpr: ((c > 10) and (ROW__ID.writeid > 2) and a is not null) (type: boolean)
+ filterExpr: ((c > 10) and (ROW__ID.writeid > 1) and a is not null) (type: boolean)
Statistics: Num rows: 3 Data size: 348 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
- predicate: ((ROW__ID.writeid > 2) and (c > 10) and a is not null) (type: boolean)
+ predicate: ((ROW__ID.writeid > 1) and (c > 10) and a is not null) (type: boolean)
Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: a (type: int), c (type: decimal(10,2))
@@ -419,7 +379,7 @@ Table Parameters:
numFiles 2
numRows 5
rawDataSize 0
- totalSize 1071
+ totalSize 1498
transactional true
transactional_properties default
#### A masked pattern was here ####
@@ -1013,10 +973,10 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: cmv_basetable_2_n3
- filterExpr: ((c > 10) and (ROW__ID.writeid > 6) and a is not null) (type: boolean)
+ filterExpr: ((c > 10) and (ROW__ID.writeid > 4) and a is not null) (type: boolean)
Statistics: Num rows: 3 Data size: 348 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
- predicate: ((ROW__ID.writeid > 6) and (c > 10) and a is not null) (type: boolean)
+ predicate: ((ROW__ID.writeid > 4) and (c > 10) and a is not null) (type: boolean)
Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: a (type: int), c (type: decimal(10,2))
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/llap/materialized_view_create_rewrite_dummy.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/materialized_view_create_rewrite_dummy.q.out b/ql/src/test/results/clientpositive/llap/materialized_view_create_rewrite_dummy.q.out
index 485a32e..734ae68 100644
--- a/ql/src/test/results/clientpositive/llap/materialized_view_create_rewrite_dummy.q.out
+++ b/ql/src/test/results/clientpositive/llap/materialized_view_create_rewrite_dummy.q.out
@@ -28,16 +28,6 @@ POSTHOOK: Lineage: cmv_basetable_n0.a SCRIPT []
POSTHOOK: Lineage: cmv_basetable_n0.b SCRIPT []
POSTHOOK: Lineage: cmv_basetable_n0.c SCRIPT []
POSTHOOK: Lineage: cmv_basetable_n0.d SCRIPT []
-PREHOOK: query: analyze table cmv_basetable_n0 compute statistics for columns
-PREHOOK: type: ANALYZE_TABLE
-PREHOOK: Input: default@cmv_basetable_n0
-PREHOOK: Output: default@cmv_basetable_n0
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table cmv_basetable_n0 compute statistics for columns
-POSTHOOK: type: ANALYZE_TABLE
-POSTHOOK: Input: default@cmv_basetable_n0
-POSTHOOK: Output: default@cmv_basetable_n0
-#### A masked pattern was here ####
PREHOOK: query: create materialized view cmv_mat_view_n0
as select a, b, c from cmv_basetable_n0 where a = 2
PREHOOK: type: CREATE_MATERIALIZED_VIEW
@@ -64,7 +54,7 @@ PREHOOK: query: show tblproperties cmv_mat_view_n0
PREHOOK: type: SHOW_TBLPROPERTIES
POSTHOOK: query: show tblproperties cmv_mat_view_n0
POSTHOOK: type: SHOW_TBLPROPERTIES
-COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"}
+COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"a":"true","b":"true","c":"true"}}
bucketing_version 2
numFiles 1
numFilesErasureCoded 0
@@ -98,7 +88,7 @@ PREHOOK: query: show tblproperties cmv_mat_view2
PREHOOK: type: SHOW_TBLPROPERTIES
POSTHOOK: query: show tblproperties cmv_mat_view2
POSTHOOK: type: SHOW_TBLPROPERTIES
-COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"}
+COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"a":"true","c":"true"}}
bucketing_version 2
numFiles 1
numFilesErasureCoded 0
@@ -354,10 +344,10 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: default.cmv_mat_view2
- Statistics: Num rows: 2 Data size: 232 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 232 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
- Statistics: Num rows: 2 Data size: 232 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 232 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: a (type: int), c (type: decimal(10,2))
Execution mode: llap
LLAP IO: all inputs
@@ -371,14 +361,14 @@ STAGE PLANS:
0
1
outputColumnNames: _col0, _col1, _col5
- Statistics: Num rows: 2 Data size: 458 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 456 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: int), _col1 (type: decimal(10,2)), _col0 (type: int), _col5 (type: decimal(10,2))
outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 2 Data size: 458 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 464 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 2 Data size: 458 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 464 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/llap/materialized_view_create_rewrite_multi_db.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/materialized_view_create_rewrite_multi_db.q.out b/ql/src/test/results/clientpositive/llap/materialized_view_create_rewrite_multi_db.q.out
index ecaefad..4bf5c2f 100644
--- a/ql/src/test/results/clientpositive/llap/materialized_view_create_rewrite_multi_db.q.out
+++ b/ql/src/test/results/clientpositive/llap/materialized_view_create_rewrite_multi_db.q.out
@@ -40,16 +40,6 @@ POSTHOOK: Lineage: cmv_basetable_n7.a SCRIPT []
POSTHOOK: Lineage: cmv_basetable_n7.b SCRIPT []
POSTHOOK: Lineage: cmv_basetable_n7.c SCRIPT []
POSTHOOK: Lineage: cmv_basetable_n7.d SCRIPT []
-PREHOOK: query: analyze table cmv_basetable_n7 compute statistics for columns
-PREHOOK: type: ANALYZE_TABLE
-PREHOOK: Input: db1@cmv_basetable_n7
-PREHOOK: Output: db1@cmv_basetable_n7
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table cmv_basetable_n7 compute statistics for columns
-POSTHOOK: type: ANALYZE_TABLE
-POSTHOOK: Input: db1@cmv_basetable_n7
-POSTHOOK: Output: db1@cmv_basetable_n7
-#### A masked pattern was here ####
PREHOOK: query: create database db2
PREHOOK: type: CREATEDATABASE
PREHOOK: Output: database:db2
@@ -88,7 +78,7 @@ PREHOOK: query: show tblproperties cmv_mat_view_n7
PREHOOK: type: SHOW_TBLPROPERTIES
POSTHOOK: query: show tblproperties cmv_mat_view_n7
POSTHOOK: type: SHOW_TBLPROPERTIES
-COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"}
+COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"a":"true","b":"true","c":"true"}}
bucketing_version 2
numFiles 1
numFilesErasureCoded 0
@@ -122,7 +112,7 @@ PREHOOK: query: show tblproperties cmv_mat_view2_n2
PREHOOK: type: SHOW_TBLPROPERTIES
POSTHOOK: query: show tblproperties cmv_mat_view2_n2
POSTHOOK: type: SHOW_TBLPROPERTIES
-COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"}
+COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"a":"true","c":"true"}}
bucketing_version 2
numFiles 1
numFilesErasureCoded 0
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/llap/materialized_view_create_rewrite_rebuild_dummy.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/materialized_view_create_rewrite_rebuild_dummy.q.out b/ql/src/test/results/clientpositive/llap/materialized_view_create_rewrite_rebuild_dummy.q.out
index 32befa5..261cc5f 100644
--- a/ql/src/test/results/clientpositive/llap/materialized_view_create_rewrite_rebuild_dummy.q.out
+++ b/ql/src/test/results/clientpositive/llap/materialized_view_create_rewrite_rebuild_dummy.q.out
@@ -28,16 +28,6 @@ POSTHOOK: Lineage: cmv_basetable_n1.a SCRIPT []
POSTHOOK: Lineage: cmv_basetable_n1.b SCRIPT []
POSTHOOK: Lineage: cmv_basetable_n1.c SCRIPT []
POSTHOOK: Lineage: cmv_basetable_n1.d SCRIPT []
-PREHOOK: query: analyze table cmv_basetable_n1 compute statistics for columns
-PREHOOK: type: ANALYZE_TABLE
-PREHOOK: Input: default@cmv_basetable_n1
-PREHOOK: Output: default@cmv_basetable_n1
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table cmv_basetable_n1 compute statistics for columns
-POSTHOOK: type: ANALYZE_TABLE
-POSTHOOK: Input: default@cmv_basetable_n1
-POSTHOOK: Output: default@cmv_basetable_n1
-#### A masked pattern was here ####
PREHOOK: query: create table cmv_basetable_2_n0 (a int, b varchar(256), c decimal(10,2), d int) stored as orc TBLPROPERTIES ('transactional'='true')
PREHOOK: type: CREATETABLE
PREHOOK: Output: database:default
@@ -62,16 +52,6 @@ POSTHOOK: Lineage: cmv_basetable_2_n0.a SCRIPT []
POSTHOOK: Lineage: cmv_basetable_2_n0.b SCRIPT []
POSTHOOK: Lineage: cmv_basetable_2_n0.c SCRIPT []
POSTHOOK: Lineage: cmv_basetable_2_n0.d SCRIPT []
-PREHOOK: query: analyze table cmv_basetable_2_n0 compute statistics for columns
-PREHOOK: type: ANALYZE_TABLE
-PREHOOK: Input: default@cmv_basetable_2_n0
-PREHOOK: Output: default@cmv_basetable_2_n0
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table cmv_basetable_2_n0 compute statistics for columns
-POSTHOOK: type: ANALYZE_TABLE
-POSTHOOK: Input: default@cmv_basetable_2_n0
-POSTHOOK: Output: default@cmv_basetable_2_n0
-#### A masked pattern was here ####
PREHOOK: query: EXPLAIN
CREATE MATERIALIZED VIEW cmv_mat_view_n1 AS
SELECT cmv_basetable_n1.a, cmv_basetable_2_n0.c
@@ -97,7 +77,7 @@ POSTHOOK: Output: default@cmv_mat_view_n1
STAGE DEPENDENCIES:
Stage-1 is a root stage
Stage-2 depends on stages: Stage-1
- Stage-4 depends on stages: Stage-2, Stage-0
+ Stage-4 depends on stages: Stage-0, Stage-2
Stage-3 depends on stages: Stage-4
Stage-5 depends on stages: Stage-3
Stage-0 depends on stages: Stage-1
@@ -107,8 +87,9 @@ STAGE PLANS:
Tez
#### A masked pattern was here ####
Edges:
- Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 4 (SIMPLE_EDGE)
+ Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 5 (SIMPLE_EDGE)
Reducer 3 <- Reducer 2 (SIMPLE_EDGE)
+ Reducer 4 <- Reducer 3 (CUSTOM_SIMPLE_EDGE)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -131,7 +112,7 @@ STAGE PLANS:
Statistics: Num rows: 5 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized, llap
LLAP IO: may be used (ACID table)
- Map 4
+ Map 5
Map Operator Tree:
TableScan
alias: cmv_basetable_2_n0
@@ -174,7 +155,7 @@ STAGE PLANS:
Map-reduce partition columns: _col0 (type: int), _col1 (type: decimal(10,2))
Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: COMPLETE
Reducer 3
- Execution mode: vectorized, llap
+ Execution mode: llap
Reduce Operator Tree:
Group By Operator
keys: KEY._col0 (type: int), KEY._col1 (type: decimal(10,2))
@@ -189,6 +170,34 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat
serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde
name: default.cmv_mat_view_n1
+ Select Operator
+ expressions: _col0 (type: int), _col1 (type: decimal(10,2))
+ outputColumnNames: col1, col2
+ Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: COMPLETE
+ Group By Operator
+ aggregations: compute_stats(col1, 'hll'), compute_stats(col2, 'hll')
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 1056 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 1056 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col0 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,min:decimal(10,2),max:decimal(10,2),countnulls:bigint,bitvector:binary>)
+ Reducer 4
+ Execution mode: llap
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 1088 Basic stats: COMPLETE Column stats: COMPLETE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 1088 Basic stats: COMPLETE Column stats: COMPLETE
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
Stage: Stage-2
Dependency Collection
@@ -211,6 +220,10 @@ STAGE PLANS:
Stage: Stage-3
Stats Work
Basic Stats Work:
+ Column Stats Desc:
+ Columns: a, c
+ Column Types: int, decimal(10,2)
+ Table: default.cmv_mat_view_n1
Stage: Stage-5
Materialized View Work
@@ -313,16 +326,6 @@ POSTHOOK: Lineage: cmv_basetable_2_n0.a SCRIPT []
POSTHOOK: Lineage: cmv_basetable_2_n0.b SCRIPT []
POSTHOOK: Lineage: cmv_basetable_2_n0.c SCRIPT []
POSTHOOK: Lineage: cmv_basetable_2_n0.d SCRIPT []
-PREHOOK: query: analyze table cmv_basetable_2_n0 compute statistics for columns
-PREHOOK: type: ANALYZE_TABLE
-PREHOOK: Input: default@cmv_basetable_2_n0
-PREHOOK: Output: default@cmv_basetable_2_n0
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table cmv_basetable_2_n0 compute statistics for columns
-POSTHOOK: type: ANALYZE_TABLE
-POSTHOOK: Input: default@cmv_basetable_2_n0
-POSTHOOK: Output: default@cmv_basetable_2_n0
-#### A masked pattern was here ####
PREHOOK: query: EXPLAIN
SELECT cmv_basetable_n1.a
FROM cmv_basetable_n1 join cmv_basetable_2_n0 ON (cmv_basetable_n1.a = cmv_basetable_2_n0.a)
@@ -518,10 +521,10 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: cmv_basetable_2_n0
- filterExpr: ((c > 10) and (ROW__ID.writeid > 2) and a is not null) (type: boolean)
+ filterExpr: ((c > 10) and (ROW__ID.writeid > 1) and a is not null) (type: boolean)
Statistics: Num rows: 3 Data size: 348 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
- predicate: ((ROW__ID.writeid > 2) and (c > 10) and a is not null) (type: boolean)
+ predicate: ((ROW__ID.writeid > 1) and (c > 10) and a is not null) (type: boolean)
Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: a (type: int), c (type: decimal(10,2))
@@ -539,21 +542,21 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: default.cmv_mat_view_n1
- Statistics: Num rows: 2 Data size: 232 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 232 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: a (type: int), c (type: decimal(10,2))
outputColumnNames: _col0, _col1
- Statistics: Num rows: 2 Data size: 232 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 232 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
keys: _col0 (type: int), _col1 (type: decimal(10,2))
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int), _col1 (type: decimal(10,2))
sort order: ++
Map-reduce partition columns: _col0 (type: int), _col1 (type: decimal(10,2))
- Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized, llap
LLAP IO: all inputs
Reducer 2
@@ -589,12 +592,12 @@ STAGE PLANS:
keys: _col0 (type: int), _col1 (type: decimal(10,2))
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int), _col1 (type: decimal(10,2))
sort order: ++
Map-reduce partition columns: _col0 (type: int), _col1 (type: decimal(10,2))
- Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: COMPLETE
Reducer 5
Execution mode: llap
Reduce Operator Tree:
@@ -602,10 +605,10 @@ STAGE PLANS:
keys: KEY._col0 (type: int), KEY._col1 (type: decimal(10,2))
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat
@@ -614,15 +617,15 @@ STAGE PLANS:
Select Operator
expressions: _col0 (type: int), _col1 (type: decimal(10,2))
outputColumnNames: a, c
- Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: compute_stats(a, 'hll'), compute_stats(c, 'hll')
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 1056 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 1 Data size: 1056 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
- Statistics: Num rows: 1 Data size: 1056 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 1 Data size: 1056 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,min:decimal(10,2),max:decimal(10,2),countnulls:bigint,bitvector:binary>)
Reducer 6
Execution mode: llap
@@ -631,10 +634,10 @@ STAGE PLANS:
aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1)
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 1088 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 1 Data size: 1088 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 1088 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 1 Data size: 1088 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -976,16 +979,6 @@ POSTHOOK: Lineage: cmv_irrelevant_table_n0.a SCRIPT []
POSTHOOK: Lineage: cmv_irrelevant_table_n0.b SCRIPT []
POSTHOOK: Lineage: cmv_irrelevant_table_n0.c SCRIPT []
POSTHOOK: Lineage: cmv_irrelevant_table_n0.d SCRIPT []
-PREHOOK: query: analyze table cmv_irrelevant_table_n0 compute statistics for columns
-PREHOOK: type: ANALYZE_TABLE
-PREHOOK: Input: default@cmv_irrelevant_table_n0
-PREHOOK: Output: default@cmv_irrelevant_table_n0
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table cmv_irrelevant_table_n0 compute statistics for columns
-POSTHOOK: type: ANALYZE_TABLE
-POSTHOOK: Input: default@cmv_irrelevant_table_n0
-POSTHOOK: Output: default@cmv_irrelevant_table_n0
-#### A masked pattern was here ####
PREHOOK: query: EXPLAIN
SELECT cmv_basetable_n1.a
FROM cmv_basetable_n1 join cmv_basetable_2_n0 ON (cmv_basetable_n1.a = cmv_basetable_2_n0.a)
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/llap/materialized_view_create_rewrite_time_window.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/materialized_view_create_rewrite_time_window.q.out b/ql/src/test/results/clientpositive/llap/materialized_view_create_rewrite_time_window.q.out
index 06835a1..51be03e 100644
--- a/ql/src/test/results/clientpositive/llap/materialized_view_create_rewrite_time_window.q.out
+++ b/ql/src/test/results/clientpositive/llap/materialized_view_create_rewrite_time_window.q.out
@@ -28,16 +28,6 @@ POSTHOOK: Lineage: cmv_basetable_n3.a SCRIPT []
POSTHOOK: Lineage: cmv_basetable_n3.b SCRIPT []
POSTHOOK: Lineage: cmv_basetable_n3.c SCRIPT []
POSTHOOK: Lineage: cmv_basetable_n3.d SCRIPT []
-PREHOOK: query: analyze table cmv_basetable_n3 compute statistics for columns
-PREHOOK: type: ANALYZE_TABLE
-PREHOOK: Input: default@cmv_basetable_n3
-PREHOOK: Output: default@cmv_basetable_n3
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table cmv_basetable_n3 compute statistics for columns
-POSTHOOK: type: ANALYZE_TABLE
-POSTHOOK: Input: default@cmv_basetable_n3
-POSTHOOK: Output: default@cmv_basetable_n3
-#### A masked pattern was here ####
PREHOOK: query: create table cmv_basetable_2_n1 (a int, b varchar(256), c decimal(10,2), d int) stored as orc TBLPROPERTIES ('transactional'='true')
PREHOOK: type: CREATETABLE
PREHOOK: Output: database:default
@@ -62,16 +52,6 @@ POSTHOOK: Lineage: cmv_basetable_2_n1.a SCRIPT []
POSTHOOK: Lineage: cmv_basetable_2_n1.b SCRIPT []
POSTHOOK: Lineage: cmv_basetable_2_n1.c SCRIPT []
POSTHOOK: Lineage: cmv_basetable_2_n1.d SCRIPT []
-PREHOOK: query: analyze table cmv_basetable_2_n1 compute statistics for columns
-PREHOOK: type: ANALYZE_TABLE
-PREHOOK: Input: default@cmv_basetable_2_n1
-PREHOOK: Output: default@cmv_basetable_2_n1
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table cmv_basetable_2_n1 compute statistics for columns
-POSTHOOK: type: ANALYZE_TABLE
-POSTHOOK: Input: default@cmv_basetable_2_n1
-POSTHOOK: Output: default@cmv_basetable_2_n1
-#### A masked pattern was here ####
PREHOOK: query: EXPLAIN
CREATE MATERIALIZED VIEW cmv_mat_view_n3 DISABLE REWRITE TBLPROPERTIES('rewriting.time.window'='5min') AS
SELECT cmv_basetable_n3.a, cmv_basetable_2_n1.c
@@ -97,7 +77,7 @@ POSTHOOK: Output: default@cmv_mat_view_n3
STAGE DEPENDENCIES:
Stage-1 is a root stage
Stage-2 depends on stages: Stage-1
- Stage-4 depends on stages: Stage-2, Stage-0
+ Stage-4 depends on stages: Stage-0, Stage-2
Stage-3 depends on stages: Stage-4
Stage-5 depends on stages: Stage-3
Stage-0 depends on stages: Stage-1
@@ -107,8 +87,9 @@ STAGE PLANS:
Tez
#### A masked pattern was here ####
Edges:
- Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 4 (SIMPLE_EDGE)
+ Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 5 (SIMPLE_EDGE)
Reducer 3 <- Reducer 2 (SIMPLE_EDGE)
+ Reducer 4 <- Reducer 3 (CUSTOM_SIMPLE_EDGE)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -131,7 +112,7 @@ STAGE PLANS:
Statistics: Num rows: 5 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized, llap
LLAP IO: may be used (ACID table)
- Map 4
+ Map 5
Map Operator Tree:
TableScan
alias: cmv_basetable_2_n1
@@ -174,7 +155,7 @@ STAGE PLANS:
Map-reduce partition columns: _col0 (type: int), _col1 (type: decimal(10,2))
Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: COMPLETE
Reducer 3
- Execution mode: vectorized, llap
+ Execution mode: llap
Reduce Operator Tree:
Group By Operator
keys: KEY._col0 (type: int), KEY._col1 (type: decimal(10,2))
@@ -189,6 +170,34 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat
serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde
name: default.cmv_mat_view_n3
+ Select Operator
+ expressions: _col0 (type: int), _col1 (type: decimal(10,2))
+ outputColumnNames: col1, col2
+ Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: COMPLETE
+ Group By Operator
+ aggregations: compute_stats(col1, 'hll'), compute_stats(col2, 'hll')
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 1056 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 1056 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col0 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,min:decimal(10,2),max:decimal(10,2),countnulls:bigint,bitvector:binary>)
+ Reducer 4
+ Execution mode: llap
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 1088 Basic stats: COMPLETE Column stats: COMPLETE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 1088 Basic stats: COMPLETE Column stats: COMPLETE
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
Stage: Stage-2
Dependency Collection
@@ -212,6 +221,10 @@ STAGE PLANS:
Stage: Stage-3
Stats Work
Basic Stats Work:
+ Column Stats Desc:
+ Columns: a, c
+ Column Types: int, decimal(10,2)
+ Table: default.cmv_mat_view_n3
Stage: Stage-5
Materialized View Work
@@ -259,7 +272,7 @@ Retention: 0
#### A masked pattern was here ####
Table Type: MATERIALIZED_VIEW
Table Parameters:
- COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"a\":\"true\",\"c\":\"true\"}}
bucketing_version 2
numFiles 2
numRows 2
@@ -439,16 +452,6 @@ POSTHOOK: Lineage: cmv_basetable_2_n1.a SCRIPT []
POSTHOOK: Lineage: cmv_basetable_2_n1.b SCRIPT []
POSTHOOK: Lineage: cmv_basetable_2_n1.c SCRIPT []
POSTHOOK: Lineage: cmv_basetable_2_n1.d SCRIPT []
-PREHOOK: query: analyze table cmv_basetable_2_n1 compute statistics for columns
-PREHOOK: type: ANALYZE_TABLE
-PREHOOK: Input: default@cmv_basetable_2_n1
-PREHOOK: Output: default@cmv_basetable_2_n1
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table cmv_basetable_2_n1 compute statistics for columns
-POSTHOOK: type: ANALYZE_TABLE
-POSTHOOK: Input: default@cmv_basetable_2_n1
-POSTHOOK: Output: default@cmv_basetable_2_n1
-#### A masked pattern was here ####
PREHOOK: query: EXPLAIN
ALTER MATERIALIZED VIEW cmv_mat_view_n3 ENABLE REWRITE
PREHOOK: type: ALTER_MATERIALIZED_VIEW_REWRITE
@@ -494,7 +497,7 @@ Retention: 0
#### A masked pattern was here ####
Table Type: MATERIALIZED_VIEW
Table Parameters:
- COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"a\":\"true\",\"c\":\"true\"}}
bucketing_version 2
numFiles 2
numRows 2
@@ -638,10 +641,10 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: cmv_basetable_2_n1
- filterExpr: ((c > 10) and (ROW__ID.writeid > 2) and a is not null) (type: boolean)
+ filterExpr: ((c > 10) and (ROW__ID.writeid > 1) and a is not null) (type: boolean)
Statistics: Num rows: 3 Data size: 348 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
- predicate: ((ROW__ID.writeid > 2) and (c > 10) and a is not null) (type: boolean)
+ predicate: ((ROW__ID.writeid > 1) and (c > 10) and a is not null) (type: boolean)
Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: a (type: int), c (type: decimal(10,2))
@@ -659,21 +662,21 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: default.cmv_mat_view_n3
- Statistics: Num rows: 2 Data size: 232 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 232 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: a (type: int), c (type: decimal(10,2))
outputColumnNames: _col0, _col1
- Statistics: Num rows: 2 Data size: 232 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 232 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
keys: _col0 (type: int), _col1 (type: decimal(10,2))
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int), _col1 (type: decimal(10,2))
sort order: ++
Map-reduce partition columns: _col0 (type: int), _col1 (type: decimal(10,2))
- Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized, llap
LLAP IO: all inputs
Reducer 2
@@ -709,12 +712,12 @@ STAGE PLANS:
keys: _col0 (type: int), _col1 (type: decimal(10,2))
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int), _col1 (type: decimal(10,2))
sort order: ++
Map-reduce partition columns: _col0 (type: int), _col1 (type: decimal(10,2))
- Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: COMPLETE
Reducer 5
Execution mode: llap
Reduce Operator Tree:
@@ -722,10 +725,10 @@ STAGE PLANS:
keys: KEY._col0 (type: int), KEY._col1 (type: decimal(10,2))
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat
@@ -734,15 +737,15 @@ STAGE PLANS:
Select Operator
expressions: _col0 (type: int), _col1 (type: decimal(10,2))
outputColumnNames: a, c
- Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 1 Data size: 116 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: compute_stats(a, 'hll'), compute_stats(c, 'hll')
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 1056 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 1 Data size: 1056 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
- Statistics: Num rows: 1 Data size: 1056 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 1 Data size: 1056 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,min:decimal(10,2),max:decimal(10,2),countnulls:bigint,bitvector:binary>)
Reducer 6
Execution mode: llap
@@ -751,10 +754,10 @@ STAGE PLANS:
aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1)
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 1088 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 1 Data size: 1088 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 1088 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 1 Data size: 1088 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
[14/35] hive git commit: HIVE-16957: Support CTAS for auto gather
column stats (Jesus Camacho Rodriguez, reviewed by Ashutosh Chauhan)
Posted by jc...@apache.org.
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/llap/vector_groupby_grouping_id1.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/vector_groupby_grouping_id1.q.out b/ql/src/test/results/clientpositive/llap/vector_groupby_grouping_id1.q.out
index c7b3659..53888a0 100644
--- a/ql/src/test/results/clientpositive/llap/vector_groupby_grouping_id1.q.out
+++ b/ql/src/test/results/clientpositive/llap/vector_groupby_grouping_id1.q.out
@@ -58,7 +58,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: t1_n17
- Statistics: Num rows: 6 Data size: 2208 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 1026 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:key:string, 1:val:string, 2:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -69,7 +69,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1]
- Statistics: Num rows: 6 Data size: 2208 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 1026 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
Group By Vectorization:
className: VectorGroupByOperator
@@ -81,7 +81,7 @@ STAGE PLANS:
keys: _col0 (type: string), _col1 (type: string), 0L (type: bigint)
mode: hash
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 24 Data size: 8832 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 2148 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: bigint)
sort order: +++
@@ -91,7 +91,7 @@ STAGE PLANS:
keyColumns: 0:string, 1:string, 2:bigint
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 24 Data size: 8832 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 2148 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized, llap
LLAP IO: all inputs
Map Vectorization:
@@ -136,7 +136,7 @@ STAGE PLANS:
keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: bigint)
mode: mergepartial
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 12 Data size: 4416 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 2148 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: string), _col1 (type: string), _col2 (type: bigint)
outputColumnNames: _col0, _col1, _col2
@@ -144,13 +144,13 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1, 2]
- Statistics: Num rows: 12 Data size: 4416 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 2148 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 12 Data size: 4416 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 2148 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -220,7 +220,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: t1_n17
- Statistics: Num rows: 6 Data size: 2208 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 1026 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:key:string, 1:val:string, 2:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -231,7 +231,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1]
- Statistics: Num rows: 6 Data size: 2208 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 1026 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
Group By Vectorization:
className: VectorGroupByOperator
@@ -243,7 +243,7 @@ STAGE PLANS:
keys: _col0 (type: string), _col1 (type: string), 0L (type: bigint)
mode: hash
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 24 Data size: 8832 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 2148 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: bigint)
sort order: +++
@@ -253,7 +253,7 @@ STAGE PLANS:
keyColumns: 0:string, 1:string, 2:bigint
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 24 Data size: 8832 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 2148 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized, llap
LLAP IO: all inputs
Map Vectorization:
@@ -298,7 +298,7 @@ STAGE PLANS:
keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: bigint)
mode: mergepartial
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 12 Data size: 4416 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 2148 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: string), _col1 (type: string), _col2 (type: bigint)
outputColumnNames: _col0, _col1, _col2
@@ -306,13 +306,13 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1, 2]
- Statistics: Num rows: 12 Data size: 4416 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 2148 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 12 Data size: 4416 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 2148 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -382,7 +382,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: t1_n17
- Statistics: Num rows: 6 Data size: 2208 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 1026 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:key:string, 1:val:string, 2:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -393,7 +393,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1]
- Statistics: Num rows: 6 Data size: 2208 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 1026 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
Group By Vectorization:
className: VectorGroupByOperator
@@ -405,7 +405,7 @@ STAGE PLANS:
keys: _col0 (type: string), _col1 (type: string), 0L (type: bigint)
mode: hash
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 18 Data size: 6624 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 9 Data size: 1611 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: bigint)
sort order: +++
@@ -415,7 +415,7 @@ STAGE PLANS:
keyColumns: 0:string, 1:string, 2:bigint
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 18 Data size: 6624 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 9 Data size: 1611 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized, llap
LLAP IO: all inputs
Map Vectorization:
@@ -460,7 +460,7 @@ STAGE PLANS:
keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: bigint)
mode: mergepartial
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 9 Data size: 3312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 9 Data size: 1611 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col2 (type: bigint), _col0 (type: string), _col1 (type: string)
outputColumnNames: _col0, _col1, _col2
@@ -468,13 +468,13 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [2, 0, 1]
- Statistics: Num rows: 9 Data size: 3312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 9 Data size: 1611 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 9 Data size: 3312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 9 Data size: 1611 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -538,7 +538,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: t1_n17
- Statistics: Num rows: 6 Data size: 2208 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 1026 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:key:string, 1:val:string, 2:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -549,7 +549,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1]
- Statistics: Num rows: 6 Data size: 2208 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 1026 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
Group By Vectorization:
className: VectorGroupByOperator
@@ -561,7 +561,7 @@ STAGE PLANS:
keys: _col0 (type: string), _col1 (type: string), 0L (type: bigint)
mode: hash
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 18 Data size: 6624 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 9 Data size: 1611 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: bigint)
sort order: +++
@@ -571,7 +571,7 @@ STAGE PLANS:
keyColumns: 0:string, 1:string, 2:bigint
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 18 Data size: 6624 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 9 Data size: 1611 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized, llap
LLAP IO: all inputs
Map Vectorization:
@@ -616,7 +616,7 @@ STAGE PLANS:
keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: bigint)
mode: mergepartial
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 9 Data size: 3312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 9 Data size: 1611 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col2 (type: bigint), _col0 (type: string), _col1 (type: string)
outputColumnNames: _col0, _col1, _col2
@@ -624,13 +624,13 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [2, 0, 1]
- Statistics: Num rows: 9 Data size: 3312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 9 Data size: 1611 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 9 Data size: 3312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 9 Data size: 1611 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -694,7 +694,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: t1_n17
- Statistics: Num rows: 6 Data size: 2208 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 1026 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:key:string, 1:val:string, 2:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -705,7 +705,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1]
- Statistics: Num rows: 6 Data size: 2208 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 1026 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
Group By Vectorization:
className: VectorGroupByOperator
@@ -717,7 +717,7 @@ STAGE PLANS:
keys: _col0 (type: string), _col1 (type: string), 0L (type: bigint)
mode: hash
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 24 Data size: 8832 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 2148 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: bigint)
sort order: +++
@@ -727,7 +727,7 @@ STAGE PLANS:
keyColumns: 0:string, 1:string, 2:bigint
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 24 Data size: 8832 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 2148 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized, llap
LLAP IO: all inputs
Map Vectorization:
@@ -772,7 +772,7 @@ STAGE PLANS:
keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: bigint)
mode: mergepartial
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 12 Data size: 4416 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 2148 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: string), _col1 (type: string), _col2 (type: bigint), CASE WHEN ((_col2 = 0L)) THEN ('0') WHEN ((_col2 = 1L)) THEN ('1') WHEN ((_col2 = 2L)) THEN ('2') WHEN ((_col2 = 3L)) THEN ('3') ELSE ('nothing') END (type: string)
outputColumnNames: _col0, _col1, _col2, _col3
@@ -781,13 +781,13 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [0, 1, 2, 13]
selectExpressions: IfExprColumnCondExpr(col 3:boolean, col 4:stringcol 12:string)(children: LongColEqualLongScalar(col 2:bigint, val 0) -> 3:boolean, ConstantVectorExpression(val 0) -> 4:string, IfExprColumnCondExpr(col 5:boolean, col 6:stringcol 11:string)(children: LongColEqualLongScalar(col 2:bigint, val 1) -> 5:boolean, ConstantVectorExpression(val 1) -> 6:string, IfExprColumnCondExpr(col 7:boolean, col 8:stringcol 10:string)(children: LongColEqualLongScalar(col 2:bigint, val 2) -> 7:boolean, ConstantVectorExpression(val 2) -> 8:string, IfExprStringScalarStringScalar(col 9:boolean, val 3, val nothing)(children: LongColEqualLongScalar(col 2:bigint, val 3) -> 9:boolean) -> 10:string) -> 11:string) -> 12:string) -> 13:string
- Statistics: Num rows: 12 Data size: 4416 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 4356 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 12 Data size: 4416 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 4356 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -857,7 +857,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: t1_n17
- Statistics: Num rows: 6 Data size: 2208 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 1026 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:key:string, 1:val:string, 2:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -868,7 +868,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1]
- Statistics: Num rows: 6 Data size: 2208 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 1026 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
Group By Vectorization:
className: VectorGroupByOperator
@@ -880,7 +880,7 @@ STAGE PLANS:
keys: _col0 (type: string), _col1 (type: string), 0L (type: bigint)
mode: hash
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 24 Data size: 8832 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 2148 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: bigint)
sort order: +++
@@ -890,7 +890,7 @@ STAGE PLANS:
keyColumns: 0:string, 1:string, 2:bigint
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 24 Data size: 8832 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 2148 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized, llap
LLAP IO: all inputs
Map Vectorization:
@@ -935,7 +935,7 @@ STAGE PLANS:
keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: bigint)
mode: mergepartial
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 12 Data size: 4416 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 2148 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: string), _col1 (type: string), _col2 (type: bigint), CASE WHEN ((_col2 = 0L)) THEN ('0') WHEN ((_col2 = 1L)) THEN ('1') WHEN ((_col2 = 2L)) THEN ('2') WHEN ((_col2 = 3L)) THEN ('3') ELSE ('nothing') END (type: string)
outputColumnNames: _col0, _col1, _col2, _col3
@@ -944,13 +944,13 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [0, 1, 2, 13]
selectExpressions: IfExprColumnCondExpr(col 3:boolean, col 4:stringcol 12:string)(children: LongColEqualLongScalar(col 2:bigint, val 0) -> 3:boolean, ConstantVectorExpression(val 0) -> 4:string, IfExprColumnCondExpr(col 5:boolean, col 6:stringcol 11:string)(children: LongColEqualLongScalar(col 2:bigint, val 1) -> 5:boolean, ConstantVectorExpression(val 1) -> 6:string, IfExprColumnCondExpr(col 7:boolean, col 8:stringcol 10:string)(children: LongColEqualLongScalar(col 2:bigint, val 2) -> 7:boolean, ConstantVectorExpression(val 2) -> 8:string, IfExprStringScalarStringScalar(col 9:boolean, val 3, val nothing)(children: LongColEqualLongScalar(col 2:bigint, val 3) -> 9:boolean) -> 10:string) -> 11:string) -> 12:string) -> 13:string
- Statistics: Num rows: 12 Data size: 4416 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 4356 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 12 Data size: 4416 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 4356 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/llap/vector_groupby_grouping_id2.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/vector_groupby_grouping_id2.q.out b/ql/src/test/results/clientpositive/llap/vector_groupby_grouping_id2.q.out
index ef10ace..4406cf0 100644
--- a/ql/src/test/results/clientpositive/llap/vector_groupby_grouping_id2.q.out
+++ b/ql/src/test/results/clientpositive/llap/vector_groupby_grouping_id2.q.out
@@ -59,7 +59,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: t1_n73
- Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:key:int, 1:value:int, 2:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -70,7 +70,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1]
- Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count()
Group By Vectorization:
@@ -84,7 +84,7 @@ STAGE PLANS:
keys: _col0 (type: int), _col1 (type: int), 0L (type: bigint)
mode: hash
outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 18 Data size: 144 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 9 Data size: 208 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int), _col1 (type: int), _col2 (type: bigint)
sort order: +++
@@ -96,7 +96,7 @@ STAGE PLANS:
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
partitionColumns: 4:double
valueColumns: 3:bigint
- Statistics: Num rows: 18 Data size: 144 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 9 Data size: 208 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col3 (type: bigint)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -144,7 +144,7 @@ STAGE PLANS:
keys: KEY._col0 (type: int), KEY._col1 (type: int), KEY._col2 (type: bigint)
mode: partials
outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 18 Data size: 144 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 9 Data size: 208 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int), _col1 (type: int), _col2 (type: bigint)
sort order: +++
@@ -156,7 +156,7 @@ STAGE PLANS:
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
partitionColumns: 0:int, 1:int
valueColumns: 3:bigint
- Statistics: Num rows: 18 Data size: 144 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 9 Data size: 208 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col3 (type: bigint)
Reducer 3
Execution mode: vectorized, llap
@@ -187,7 +187,7 @@ STAGE PLANS:
keys: KEY._col0 (type: int), KEY._col1 (type: int), KEY._col2 (type: bigint)
mode: final
outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 9 Data size: 72 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 9 Data size: 208 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: int), _col1 (type: int), _col2 (type: bigint), _col3 (type: bigint)
outputColumnNames: _col0, _col1, _col2, _col3
@@ -195,13 +195,13 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1, 2, 3]
- Statistics: Num rows: 9 Data size: 72 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 9 Data size: 208 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 9 Data size: 72 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 9 Data size: 208 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -265,7 +265,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: t1_n73
- Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:key:int, 1:value:int, 2:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -276,7 +276,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1]
- Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count()
Group By Vectorization:
@@ -290,7 +290,7 @@ STAGE PLANS:
keys: _col0 (type: int), _col1 (type: int), 0L (type: bigint)
mode: hash
outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 18 Data size: 144 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 9 Data size: 208 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int), _col1 (type: int), _col2 (type: bigint)
sort order: +++
@@ -302,7 +302,7 @@ STAGE PLANS:
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
partitionColumns: 4:double
valueColumns: 3:bigint
- Statistics: Num rows: 18 Data size: 144 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 9 Data size: 208 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col3 (type: bigint)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -350,7 +350,7 @@ STAGE PLANS:
keys: KEY._col0 (type: int), KEY._col1 (type: int), KEY._col2 (type: bigint)
mode: partials
outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 18 Data size: 144 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 9 Data size: 208 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int), _col1 (type: int), _col2 (type: bigint)
sort order: +++
@@ -362,7 +362,7 @@ STAGE PLANS:
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
partitionColumns: 0:int, 1:int
valueColumns: 3:bigint
- Statistics: Num rows: 18 Data size: 144 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 9 Data size: 208 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col3 (type: bigint)
Reducer 3
Execution mode: vectorized, llap
@@ -393,7 +393,7 @@ STAGE PLANS:
keys: KEY._col0 (type: int), KEY._col1 (type: int), KEY._col2 (type: bigint)
mode: final
outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 9 Data size: 72 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 9 Data size: 208 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: int), _col1 (type: int), _col2 (type: bigint), _col3 (type: bigint)
outputColumnNames: _col0, _col1, _col2, _col3
@@ -401,13 +401,13 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1, 2, 3]
- Statistics: Num rows: 9 Data size: 72 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 9 Data size: 208 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 9 Data size: 72 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 9 Data size: 208 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -483,7 +483,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: t1_n73
- Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:key:int, 1:value:int, 2:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -494,7 +494,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1]
- Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
Group By Vectorization:
className: VectorGroupByOperator
@@ -506,7 +506,7 @@ STAGE PLANS:
keys: _col0 (type: int), _col1 (type: int), 0L (type: bigint)
mode: hash
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 18 Data size: 144 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 9 Data size: 136 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int), _col1 (type: int), _col2 (type: bigint)
sort order: +++
@@ -517,7 +517,7 @@ STAGE PLANS:
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
partitionColumns: 3:double
- Statistics: Num rows: 18 Data size: 144 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 9 Data size: 136 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized, llap
LLAP IO: all inputs
Map Vectorization:
@@ -562,7 +562,7 @@ STAGE PLANS:
keys: KEY._col0 (type: int), KEY._col1 (type: int), KEY._col2 (type: bigint)
mode: partials
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 18 Data size: 144 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 9 Data size: 136 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int), _col1 (type: int), _col2 (type: bigint)
sort order: +++
@@ -573,7 +573,7 @@ STAGE PLANS:
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
partitionColumns: 0:int, 1:int
- Statistics: Num rows: 18 Data size: 144 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 9 Data size: 136 Basic stats: COMPLETE Column stats: COMPLETE
Reducer 3
Execution mode: vectorized, llap
Reduce Vectorization:
@@ -601,7 +601,7 @@ STAGE PLANS:
keys: KEY._col0 (type: int), KEY._col1 (type: int), KEY._col2 (type: bigint)
mode: final
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 9 Data size: 72 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 9 Data size: 136 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col2 (type: bigint)
outputColumnNames: _col2
@@ -609,7 +609,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [2]
- Statistics: Num rows: 9 Data size: 72 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 9 Data size: 136 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count()
Group By Vectorization:
@@ -623,7 +623,7 @@ STAGE PLANS:
keys: _col2 (type: bigint)
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 9 Data size: 72 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: bigint)
sort order: +
@@ -635,7 +635,7 @@ STAGE PLANS:
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
partitionColumns: 2:double
valueColumns: 1:bigint
- Statistics: Num rows: 9 Data size: 72 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: bigint)
Reducer 4
Execution mode: vectorized, llap
@@ -666,7 +666,7 @@ STAGE PLANS:
keys: KEY._col0 (type: bigint)
mode: partials
outputColumnNames: _col0, _col1
- Statistics: Num rows: 9 Data size: 72 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: bigint)
sort order: +
@@ -677,7 +677,7 @@ STAGE PLANS:
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
valueColumns: 1:bigint
- Statistics: Num rows: 9 Data size: 72 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: bigint)
Reducer 5
Execution mode: vectorized, llap
@@ -708,13 +708,13 @@ STAGE PLANS:
keys: KEY._col0 (type: bigint)
mode: final
outputColumnNames: _col0, _col1
- Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -792,7 +792,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: t1_n73
- Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:key:int, 1:value:int, 2:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -803,7 +803,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1]
- Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
Group By Vectorization:
className: VectorGroupByOperator
@@ -815,7 +815,7 @@ STAGE PLANS:
keys: _col0 (type: int), _col1 (type: int), 0L (type: bigint)
mode: hash
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 18 Data size: 144 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 9 Data size: 136 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int), _col1 (type: int), _col2 (type: bigint)
sort order: +++
@@ -826,7 +826,7 @@ STAGE PLANS:
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
partitionColumns: 3:double
- Statistics: Num rows: 18 Data size: 144 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 9 Data size: 136 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized, llap
LLAP IO: all inputs
Map Vectorization:
@@ -871,7 +871,7 @@ STAGE PLANS:
keys: KEY._col0 (type: int), KEY._col1 (type: int), KEY._col2 (type: bigint)
mode: partials
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 18 Data size: 144 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 9 Data size: 136 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int), _col1 (type: int), _col2 (type: bigint)
sort order: +++
@@ -882,7 +882,7 @@ STAGE PLANS:
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
partitionColumns: 0:int, 1:int
- Statistics: Num rows: 18 Data size: 144 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 9 Data size: 136 Basic stats: COMPLETE Column stats: COMPLETE
Reducer 3
Execution mode: vectorized, llap
Reduce Vectorization:
@@ -910,7 +910,7 @@ STAGE PLANS:
keys: KEY._col0 (type: int), KEY._col1 (type: int), KEY._col2 (type: bigint)
mode: final
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 9 Data size: 72 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 9 Data size: 136 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col2 (type: bigint)
outputColumnNames: _col2
@@ -918,7 +918,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [2]
- Statistics: Num rows: 9 Data size: 72 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 9 Data size: 136 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count()
Group By Vectorization:
@@ -932,7 +932,7 @@ STAGE PLANS:
keys: _col2 (type: bigint)
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 9 Data size: 72 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: bigint)
sort order: +
@@ -944,7 +944,7 @@ STAGE PLANS:
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
partitionColumns: 2:double
valueColumns: 1:bigint
- Statistics: Num rows: 9 Data size: 72 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: bigint)
Reducer 4
Execution mode: vectorized, llap
@@ -975,7 +975,7 @@ STAGE PLANS:
keys: KEY._col0 (type: bigint)
mode: partials
outputColumnNames: _col0, _col1
- Statistics: Num rows: 9 Data size: 72 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: bigint)
sort order: +
@@ -986,7 +986,7 @@ STAGE PLANS:
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
valueColumns: 1:bigint
- Statistics: Num rows: 9 Data size: 72 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: bigint)
Reducer 5
Execution mode: vectorized, llap
@@ -1017,13 +1017,13 @@ STAGE PLANS:
keys: KEY._col0 (type: bigint)
mode: final
outputColumnNames: _col0, _col1
- Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -1097,7 +1097,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: t1_n73
- Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:key:int, 1:value:int, 2:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -1108,7 +1108,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1]
- Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
Group By Vectorization:
className: VectorGroupByOperator
@@ -1120,7 +1120,7 @@ STAGE PLANS:
keys: _col0 (type: int), _col1 (type: int), 0L (type: bigint)
mode: hash
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 18 Data size: 144 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 9 Data size: 136 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int), _col1 (type: int), _col2 (type: bigint)
sort order: +++
@@ -1131,7 +1131,7 @@ STAGE PLANS:
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
partitionColumns: 3:double
- Statistics: Num rows: 18 Data size: 144 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 9 Data size: 136 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized, llap
LLAP IO: all inputs
Map Vectorization:
@@ -1176,7 +1176,7 @@ STAGE PLANS:
keys: KEY._col0 (type: int), KEY._col1 (type: int), KEY._col2 (type: bigint)
mode: partials
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 18 Data size: 144 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 9 Data size: 136 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int), _col1 (type: int), _col2 (type: bigint)
sort order: +++
@@ -1187,7 +1187,7 @@ STAGE PLANS:
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
partitionColumns: 0:int, 1:int
- Statistics: Num rows: 18 Data size: 144 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 9 Data size: 136 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int), _col1 (type: int), _col2 (type: bigint)
sort order: +++
@@ -1198,7 +1198,7 @@ STAGE PLANS:
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
partitionColumns: 0:int, 1:int
- Statistics: Num rows: 18 Data size: 144 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 9 Data size: 136 Basic stats: COMPLETE Column stats: COMPLETE
Reducer 3
Execution mode: vectorized, llap
Reduce Vectorization:
@@ -1226,7 +1226,7 @@ STAGE PLANS:
keys: KEY._col0 (type: int), KEY._col1 (type: int), KEY._col2 (type: bigint)
mode: final
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 9 Data size: 72 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 9 Data size: 136 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col2 (type: bigint)
outputColumnNames: _col0
@@ -1234,7 +1234,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [2]
- Statistics: Num rows: 9 Data size: 72 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 9 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: bigint)
sort order: +
@@ -1244,7 +1244,7 @@ STAGE PLANS:
keyColumns: 2:bigint
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 9 Data size: 72 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 9 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE
Reducer 4
Execution mode: llap
Reduce Operator Tree:
@@ -1255,10 +1255,10 @@ STAGE PLANS:
0 _col0 (type: bigint)
1 _col0 (type: bigint)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 9 Data size: 79 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 81 Data size: 1296 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 9 Data size: 79 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 81 Data size: 1296 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -1293,7 +1293,7 @@ STAGE PLANS:
keys: KEY._col0 (type: int), KEY._col1 (type: int), KEY._col2 (type: bigint)
mode: final
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 9 Data size: 72 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 9 Data size: 136 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col2 (type: bigint)
outputColumnNames: _col0
@@ -1301,7 +1301,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [2]
- Statistics: Num rows: 9 Data size: 72 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 9 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: bigint)
sort order: +
@@ -1311,7 +1311,7 @@ STAGE PLANS:
keyColumns: 2:bigint
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 9 Data size: 72 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 9 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE
Stage: Stage-0
Fetch Operator
@@ -1427,7 +1427,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: t1_n73
- Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:key:int, 1:value:int, 2:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -1438,7 +1438,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1]
- Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
Group By Vectorization:
className: VectorGroupByOperator
@@ -1450,7 +1450,7 @@ STAGE PLANS:
keys: _col0 (type: int), _col1 (type: int), 0L (type: bigint)
mode: hash
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 18 Data size: 144 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 9 Data size: 136 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int), _col1 (type: int), _col2 (type: bigint)
sort order: +++
@@ -1461,7 +1461,7 @@ STAGE PLANS:
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
partitionColumns: 3:double
- Statistics: Num rows: 18 Data size: 144 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 9 Data size: 136 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized, llap
LLAP IO: all inputs
Map Vectorization:
@@ -1506,7 +1506,7 @@ STAGE PLANS:
keys: KEY._col0 (type: int), KEY._col1 (type: int), KEY._col2 (type: bigint)
mode: partials
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 18 Data size: 144 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 9 Data size: 136 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int), _col1 (type: int), _col2 (type: bigint)
sort order: +++
@@ -1517,7 +1517,7 @@ STAGE PLANS:
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
partitionColumns: 0:int, 1:int
- Statistics: Num rows: 18 Data size: 144 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 9 Data size: 136 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int), _col1 (type: int), _col2 (type: bigint)
sort order: +++
@@ -1528,7 +1528,7 @@ STAGE PLANS:
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
partitionColumns: 0:int, 1:int
- Statistics: Num rows: 18 Data size: 144 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 9 Data size: 136 Basic stats: COMPLETE Column stats: COMPLETE
Reducer 3
Execution mode: vectorized, llap
Reduce Vectorization:
@@ -1556,7 +1556,7 @@ STAGE PLANS:
keys: KEY._col0 (type: int), KEY._col1 (type: int), KEY._col2 (type: bigint)
mode: final
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 9 Data size: 72 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 9 Data size: 136 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col2 (type: bigint)
outputColumnNames: _col0
@@ -1564,7 +1564,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [2]
- Statistics: Num rows: 9 Data size: 72 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 9 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: bigint)
sort order: +
@@ -1574,7 +1574,7 @@ STAGE PLANS:
keyColumns: 2:bigint
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 9 Data size: 72 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 9 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE
Reducer 4
Execution mode: llap
Reduce Operator Tree:
@@ -1585,10 +1585,10 @@ STAGE PLANS:
0 _col0 (type: bigint)
1 _col0 (type: bigint)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 9 Data size: 79 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 81 Data size: 1296 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 9 Data size: 79 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 81 Data size: 1296 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -1623,7 +1623,7 @@ STAGE PLANS:
keys: KEY._col0 (type: int), KEY._col1 (type: int), KEY._col2 (type: bigint)
mode: final
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 9 Data size: 72 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 9 Data size: 136 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col2 (type: bigint)
outputColumnNames: _col0
@@ -1631,7 +1631,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [2]
- Statistics: Num rows: 9 Data size: 72 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 9 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: bigint)
sort order: +
@@ -1641,7 +1641,7 @@ STAGE PLANS:
keyColumns: 2:bigint
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 9 Data size: 72 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 9 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE
Stage: Stage-0
Fetch Operator
@@ -1748,7 +1748,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: t1_n73
- Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:key:int, 1:value:int, 2:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -1759,7 +1759,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1]
- Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count()
Group By Vectorization:
@@ -1773,7 +1773,7 @@ STAGE PLANS:
keys: _col0 (type: int), _col1 (type: int), 0L (type: bigint)
mode: hash
outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 18 Data size: 144 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 9 Data size: 208 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int), _col1 (type: int), _col2 (type: bigint)
sort order: +++
@@ -1784,7 +1784,7 @@ STAGE PLANS:
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
valueColumns: 3:bigint
- Statistics: Num rows: 18 Data size: 144 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 9 Data size: 208 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col3 (type: bigint)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -1832,7 +1832,7 @@ STAGE PLANS:
keys: KEY._col0 (type: int), KEY._col1 (type: int), KEY._col2 (type: bigint)
mode: mergepartial
outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 9 Data size: 72 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 9 Data size: 208 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: int), _col1 (type: int), _col2 (type: bigint), _col3 (type: bigint)
outputColumnNames: _col0, _col1, _col2, _col3
@@ -1840,13 +1840,13 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1, 2, 3]
- Statistics: Num rows: 9 Data size: 72 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 9 Data size: 208 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 9 Data size: 72 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 9 Data size: 208 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -1920,7 +1920,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: t1_n73
- Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:key:int, 1:value:int, 2:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -1931,7 +1931,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1]
- Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
Group By Vectorization:
className: VectorGroupByOperator
@@ -1943,7 +1943,7 @@ STAGE PLANS:
keys: _col0 (type: int), _col1 (type: int), 0L (type: bigint)
mode: hash
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 18 Data size: 144 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 9 Data size: 136 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int), _col1 (type: int), _col2 (type: bigint)
sort order: +++
@@ -1953,7 +1953,7 @@ STAGE PLANS:
keyColumns: 0:int, 1:int, 2:bigint
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 18 Data size: 144 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 9 Data size: 136 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized, llap
LLAP IO: all inputs
Map Vectorization:
@@ -1998,7 +1998,7 @@ STAGE PLANS:
keys: KEY._col0 (type: int), KEY._col1 (type: int), KEY._col2 (type: bigint)
mode: mergepartial
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 9 Data size: 72 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 9 Data size: 136 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col2 (type: bigint)
outputColumnNames: _col2
@@ -2006,7 +2006,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [2]
- Statistics: Num rows: 9 Data size: 72 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 9 Data size: 136 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count()
Group By Vectorization:
@@ -2020,7 +2020,7 @@ STAGE PLANS:
keys: _col2 (type: bigint)
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 9 Data size: 72 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: bigint)
sort order: +
@@ -2031,7 +2031,7 @@ STAGE PLANS:
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
valueColumns: 1:bigint
- Statistics: Num rows: 9 Data size: 72 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: bigint)
Reducer 3
Execution mode: vectorized, llap
@@ -2062,13 +2062,13 @@ STAGE PLANS:
keys: KEY._col0 (type: bigint)
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -2141,7 +2141,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: t1_n73
- Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:key:int, 1:value:int, 2:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -2152,7 +2152,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1]
- Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
Group By Vectorization:
className: VectorGroupByOperator
@@ -2164,7 +2164,7 @@ STAGE PLANS:
keys: _col0 (type: int), _col1 (type: int), 0L (type: bigint)
mode: hash
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 18 Data size: 144 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 9 Data size: 136 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int), _col1 (type: int), _col2 (type: bigint)
sort order: +++
@@ -2174,7 +2174,7 @@ STAGE PLANS:
keyColumns: 0:int, 1:int, 2:bigint
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 18 Data size: 144 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 9 Data size: 136 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int), _col1 (type: int), _col2 (type: bigint)
sort order: +++
@@ -2184,7 +2184,7 @@ STAGE PLANS:
keyColumns: 0:int, 1:int, 2:bigint
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 18 Data size: 144 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 9 Data size: 136 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized, llap
LLAP IO: all inputs
Map Vectorization:
@@ -2229,7 +2229,7 @@ STAGE PLANS:
keys: KEY._col0 (type: int), KEY._col1 (type: int), KEY._col2 (type: bigint)
mode: mergepartial
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 9 Data size: 72 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 9 Data size: 136 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col2 (type: bigint)
outputColumnNames: _col0
@@ -2237,7 +2237,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [2]
- Statistics: Num rows: 9 Data size: 72 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 9 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: bigint)
sort order: +
@@ -2247,7 +2247,7 @@ STAGE PLANS:
keyColumns: 2:bigint
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 9 Data size: 72 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 9 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE
Reducer 3
Execution mode: llap
Reduce Operator Tree:
@@ -2258,10 +2258,10 @@ STAGE PLANS:
0 _col0 (type: bigint)
1 _col0 (type: bigint)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 9 Data size: 79 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 81 Data size: 1296 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 9 Data size: 79 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 81 Data size: 1296 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -2296,7 +2296,7 @@ STAGE PLANS:
keys: KEY._col0 (type: int), KEY._col1 (type: int), KEY._col2 (type: bigint)
mode: mergepartial
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 9 Data size: 72 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 9 Data size: 136 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col2 (type: bigint)
outputColumnNames: _col0
@@ -2304,7 +2304,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [2]
- Statistics: Num rows: 9 Data size: 72 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 9 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: bigint)
sort order: +
@@ -2314,7 +2314,7 @@ STAGE PLANS:
keyColumns: 2:bigint
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 9 Data size: 72 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 9 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE
Stage: Stage-0
Fetch Operator
[26/35] hive git commit: HIVE-16957: Support CTAS for auto gather
column stats (Jesus Camacho Rodriguez, reviewed by Ashutosh Chauhan)
Posted by jc...@apache.org.
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/llap/materialized_view_create_rewrite_time_window_2.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/materialized_view_create_rewrite_time_window_2.q.out b/ql/src/test/results/clientpositive/llap/materialized_view_create_rewrite_time_window_2.q.out
index 24bd61d..b382fa4 100644
--- a/ql/src/test/results/clientpositive/llap/materialized_view_create_rewrite_time_window_2.q.out
+++ b/ql/src/test/results/clientpositive/llap/materialized_view_create_rewrite_time_window_2.q.out
@@ -28,16 +28,6 @@ POSTHOOK: Lineage: cmv_basetable_n100.a SCRIPT []
POSTHOOK: Lineage: cmv_basetable_n100.b SCRIPT []
POSTHOOK: Lineage: cmv_basetable_n100.c SCRIPT []
POSTHOOK: Lineage: cmv_basetable_n100.d SCRIPT []
-PREHOOK: query: analyze table cmv_basetable_n100 compute statistics for columns
-PREHOOK: type: ANALYZE_TABLE
-PREHOOK: Input: default@cmv_basetable_n100
-PREHOOK: Output: default@cmv_basetable_n100
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table cmv_basetable_n100 compute statistics for columns
-POSTHOOK: type: ANALYZE_TABLE
-POSTHOOK: Input: default@cmv_basetable_n100
-POSTHOOK: Output: default@cmv_basetable_n100
-#### A masked pattern was here ####
PREHOOK: query: create table cmv_basetable_2_n100 (a int, b varchar(256), c decimal(10,2), d int) stored as orc TBLPROPERTIES ('transactional'='true')
PREHOOK: type: CREATETABLE
PREHOOK: Output: database:default
@@ -62,16 +52,6 @@ POSTHOOK: Lineage: cmv_basetable_2_n100.a SCRIPT []
POSTHOOK: Lineage: cmv_basetable_2_n100.b SCRIPT []
POSTHOOK: Lineage: cmv_basetable_2_n100.c SCRIPT []
POSTHOOK: Lineage: cmv_basetable_2_n100.d SCRIPT []
-PREHOOK: query: analyze table cmv_basetable_2_n100 compute statistics for columns
-PREHOOK: type: ANALYZE_TABLE
-PREHOOK: Input: default@cmv_basetable_2_n100
-PREHOOK: Output: default@cmv_basetable_2_n100
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table cmv_basetable_2_n100 compute statistics for columns
-POSTHOOK: type: ANALYZE_TABLE
-POSTHOOK: Input: default@cmv_basetable_2_n100
-POSTHOOK: Output: default@cmv_basetable_2_n100
-#### A masked pattern was here ####
PREHOOK: query: CREATE MATERIALIZED VIEW cmv_mat_view_n300 AS
SELECT cmv_basetable_n100.a, cmv_basetable_2_n100.c
FROM cmv_basetable_n100 JOIN cmv_basetable_2_n100 ON (cmv_basetable_n100.a = cmv_basetable_2_n100.a)
@@ -109,7 +89,7 @@ Retention: 0
#### A masked pattern was here ####
Table Type: MATERIALIZED_VIEW
Table Parameters:
- COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"a\":\"true\",\"c\":\"true\"}}
bucketing_version 2
numFiles 2
numRows 2
@@ -151,16 +131,6 @@ POSTHOOK: Lineage: cmv_basetable_2_n100.a SCRIPT []
POSTHOOK: Lineage: cmv_basetable_2_n100.b SCRIPT []
POSTHOOK: Lineage: cmv_basetable_2_n100.c SCRIPT []
POSTHOOK: Lineage: cmv_basetable_2_n100.d SCRIPT []
-PREHOOK: query: analyze table cmv_basetable_2_n100 compute statistics for columns
-PREHOOK: type: ANALYZE_TABLE
-PREHOOK: Input: default@cmv_basetable_2_n100
-PREHOOK: Output: default@cmv_basetable_2_n100
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table cmv_basetable_2_n100 compute statistics for columns
-POSTHOOK: type: ANALYZE_TABLE
-POSTHOOK: Input: default@cmv_basetable_2_n100
-POSTHOOK: Output: default@cmv_basetable_2_n100
-#### A masked pattern was here ####
PREHOOK: query: DESCRIBE FORMATTED cmv_mat_view_n300
PREHOOK: type: DESCTABLE
PREHOOK: Input: default@cmv_mat_view_n300
@@ -178,7 +148,7 @@ Retention: 0
#### A masked pattern was here ####
Table Type: MATERIALIZED_VIEW
Table Parameters:
- COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"a\":\"true\",\"c\":\"true\"}}
bucketing_version 2
numFiles 2
numRows 2
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/llap/materialized_view_describe.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/materialized_view_describe.q.out b/ql/src/test/results/clientpositive/llap/materialized_view_describe.q.out
index 581cc87..00577c0 100644
--- a/ql/src/test/results/clientpositive/llap/materialized_view_describe.q.out
+++ b/ql/src/test/results/clientpositive/llap/materialized_view_describe.q.out
@@ -66,7 +66,7 @@ Retention: 0
#### A masked pattern was here ####
Table Type: MATERIALIZED_VIEW
Table Parameters:
- COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"a\":\"true\",\"c\":\"true\"}}
bucketing_version 2
comment this is the first view
key foo
@@ -94,7 +94,7 @@ PREHOOK: query: show tblproperties cmv_mat_view_n8
PREHOOK: type: SHOW_TBLPROPERTIES
POSTHOOK: query: show tblproperties cmv_mat_view_n8
POSTHOOK: type: SHOW_TBLPROPERTIES
-COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"}
+COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"a":"true","c":"true"}}
bucketing_version 2
comment this is the first view
key foo
@@ -157,7 +157,7 @@ Retention: 0
#### A masked pattern was here ####
Table Type: MATERIALIZED_VIEW
Table Parameters:
- COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"a\":\"true\"}}
bucketing_version 2
comment this is the second view
key alice
@@ -239,7 +239,7 @@ Retention: 0
#### A masked pattern was here ####
Table Type: MATERIALIZED_VIEW
Table Parameters:
- COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"a\":\"true\",\"b\":\"true\",\"c\":\"true\"}}
bucketing_version 2
comment this is the third view
numFiles 1
@@ -330,7 +330,7 @@ Retention: 0
#### A masked pattern was here ####
Table Type: MATERIALIZED_VIEW
Table Parameters:
- COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"a\":\"true\"}}
bucketing_version 2
comment this is the last view
numFiles 1
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/llap/materialized_view_partitioned.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/materialized_view_partitioned.q.out b/ql/src/test/results/clientpositive/llap/materialized_view_partitioned.q.out
index ba4d76f..2c9b36d 100644
--- a/ql/src/test/results/clientpositive/llap/materialized_view_partitioned.q.out
+++ b/ql/src/test/results/clientpositive/llap/materialized_view_partitioned.q.out
@@ -39,30 +39,69 @@ STAGE PLANS:
Stage: Stage-1
Tez
#### A masked pattern was here ####
+ Edges:
+ Reducer 2 <- Map 1 (SIMPLE_EDGE)
+#### A masked pattern was here ####
Vertices:
Map 1
Map Operator Tree:
TableScan
alias: src_txn
filterExpr: ((UDFToDouble(key) > 200.0D) and (UDFToDouble(key) < 250.0D)) (type: boolean)
- Statistics: Num rows: 500 Data size: 175168 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: ((UDFToDouble(key) < 250.0D) and (UDFToDouble(key) > 200.0D)) (type: boolean)
- Statistics: Num rows: 55 Data size: 19268 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: value (type: string), key (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 55 Data size: 19268 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 55 Data size: 19268 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat
serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde
name: default.partition_mv_1
- Execution mode: vectorized, llap
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: string)
+ outputColumnNames: col1, col2
+ Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE
+ Group By Operator
+ aggregations: compute_stats(col1, 'hll')
+ keys: col2 (type: string)
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 27 Data size: 14229 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 27 Data size: 14229 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col1 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>)
+ Execution mode: llap
LLAP IO: may be used (ACID table)
+ Reducer 2
+ Execution mode: llap
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: compute_stats(VALUE._col0)
+ keys: KEY._col0 (type: string)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 27 Data size: 14229 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: _col1 (type: struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col0 (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 27 Data size: 14229 Basic stats: COMPLETE Column stats: COMPLETE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 27 Data size: 14229 Basic stats: COMPLETE Column stats: COMPLETE
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
Stage: Stage-2
Dependency Collection
@@ -92,6 +131,10 @@ STAGE PLANS:
Stage: Stage-3
Stats Work
Basic Stats Work:
+ Column Stats Desc:
+ Columns: value
+ Column Types: string
+ Table: default.partition_mv_1
Stage: Stage-5
Materialized View Work
@@ -578,17 +621,17 @@ STAGE PLANS:
TableScan
alias: src_txn
filterExpr: ((UDFToDouble(key) > 200.0D) and (UDFToDouble(key) < 250.0D)) (type: boolean)
- Statistics: Num rows: 501 Data size: 175536 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 501 Data size: 90180 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: ((UDFToDouble(key) < 250.0D) and (UDFToDouble(key) > 200.0D)) (type: boolean)
- Statistics: Num rows: 55 Data size: 19270 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 55 Data size: 9900 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: value (type: string), key (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 55 Data size: 19270 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 55 Data size: 9900 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 55 Data size: 19270 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 55 Data size: 9900 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat
@@ -597,18 +640,18 @@ STAGE PLANS:
Select Operator
expressions: _col0 (type: string), _col1 (type: string)
outputColumnNames: value, key
- Statistics: Num rows: 55 Data size: 19270 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 55 Data size: 9900 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: compute_stats(value, 'hll')
keys: key (type: string)
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 55 Data size: 19270 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 27 Data size: 14229 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 55 Data size: 19270 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 27 Data size: 14229 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>)
Execution mode: llap
LLAP IO: may be used (ACID table)
@@ -620,14 +663,14 @@ STAGE PLANS:
keys: KEY._col0 (type: string)
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 27 Data size: 9459 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 27 Data size: 14229 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col1 (type: struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col0 (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 27 Data size: 9459 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 27 Data size: 14229 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 27 Data size: 9459 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 27 Data size: 14229 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -956,19 +999,19 @@ STAGE PLANS:
TableScan
alias: src_txn
filterExpr: ((UDFToDouble(key) > 200.0D) and (UDFToDouble(key) < 250.0D)) (type: boolean)
- Statistics: Num rows: 502 Data size: 175904 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 502 Data size: 90862 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: ((UDFToDouble(key) < 250.0D) and (UDFToDouble(key) > 200.0D)) (type: boolean)
- Statistics: Num rows: 55 Data size: 19272 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 55 Data size: 9955 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: key (type: string), value (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 55 Data size: 19272 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 55 Data size: 9955 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 55 Data size: 19272 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 55 Data size: 9955 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: string)
Execution mode: vectorized, llap
LLAP IO: may be used (ACID table)
@@ -977,19 +1020,19 @@ STAGE PLANS:
TableScan
alias: src_txn_2
filterExpr: ((UDFToDouble(key) > 200.0D) and (UDFToDouble(key) < 250.0D)) (type: boolean)
- Statistics: Num rows: 500 Data size: 87584 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: ((UDFToDouble(key) < 250.0D) and (UDFToDouble(key) > 200.0D)) (type: boolean)
- Statistics: Num rows: 55 Data size: 9634 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 55 Data size: 4785 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: key (type: string)
outputColumnNames: _col0
- Statistics: Num rows: 55 Data size: 9634 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 55 Data size: 4785 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 55 Data size: 9634 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 55 Data size: 4785 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized, llap
LLAP IO: may be used (ACID table)
Reducer 2
@@ -1002,14 +1045,14 @@ STAGE PLANS:
0 _col0 (type: string)
1 _col0 (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 60 Data size: 21199 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 55 Data size: 9955 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col1 (type: string), _col0 (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 60 Data size: 21199 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 55 Data size: 9955 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 60 Data size: 21199 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 55 Data size: 9955 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat
@@ -1018,18 +1061,18 @@ STAGE PLANS:
Select Operator
expressions: _col0 (type: string), _col1 (type: string)
outputColumnNames: value, key
- Statistics: Num rows: 60 Data size: 21199 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 55 Data size: 9955 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: compute_stats(value, 'hll')
keys: key (type: string)
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 60 Data size: 21199 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 27 Data size: 14229 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 60 Data size: 21199 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 27 Data size: 14229 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>)
Reducer 3
Execution mode: llap
@@ -1039,14 +1082,14 @@ STAGE PLANS:
keys: KEY._col0 (type: string)
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 30 Data size: 10599 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 27 Data size: 14229 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col1 (type: struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col0 (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 30 Data size: 10599 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 27 Data size: 14229 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 30 Data size: 10599 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 27 Data size: 14229 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/llap/materialized_view_partitioned_3.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/materialized_view_partitioned_3.q.out b/ql/src/test/results/clientpositive/llap/materialized_view_partitioned_3.q.out
index 4ed30ee..6afa85d 100644
--- a/ql/src/test/results/clientpositive/llap/materialized_view_partitioned_3.q.out
+++ b/ql/src/test/results/clientpositive/llap/materialized_view_partitioned_3.q.out
@@ -41,6 +41,7 @@ STAGE PLANS:
#### A masked pattern was here ####
Edges:
Reducer 2 <- Map 1 (SIMPLE_EDGE)
+ Reducer 3 <- Map 1 (SIMPLE_EDGE)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -48,22 +49,58 @@ STAGE PLANS:
TableScan
alias: src_txn
filterExpr: ((UDFToDouble(key) > 200.0D) and (UDFToDouble(key) < 250.0D)) (type: boolean)
- Statistics: Num rows: 500 Data size: 175168 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: ((UDFToDouble(key) < 250.0D) and (UDFToDouble(key) > 200.0D)) (type: boolean)
- Statistics: Num rows: 55 Data size: 19268 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: value (type: string), key (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 55 Data size: 19268 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: string)
+ outputColumnNames: col1, col2
+ Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE
+ Group By Operator
+ aggregations: compute_stats(col1, 'hll')
+ keys: col2 (type: string)
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 27 Data size: 14229 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 27 Data size: 14229 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col1 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>)
Reduce Output Operator
key expressions: _col1 (type: string)
sort order: +
Map-reduce partition columns: _col1 (type: string)
value expressions: _col0 (type: string)
- Execution mode: vectorized, llap
+ Execution mode: llap
LLAP IO: may be used (ACID table)
Reducer 2
+ Execution mode: llap
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: compute_stats(VALUE._col0)
+ keys: KEY._col0 (type: string)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 27 Data size: 14229 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: _col1 (type: struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col0 (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 27 Data size: 14229 Basic stats: COMPLETE Column stats: COMPLETE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 27 Data size: 14229 Basic stats: COMPLETE Column stats: COMPLETE
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ Reducer 3
Execution mode: vectorized, llap
Reduce Operator Tree:
Select Operator
@@ -72,7 +109,7 @@ STAGE PLANS:
File Output Operator
compressed: false
Dp Sort State: PARTITION_SORTED
- Statistics: Num rows: 55 Data size: 19268 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat
@@ -107,6 +144,10 @@ STAGE PLANS:
Stage: Stage-3
Stats Work
Basic Stats Work:
+ Column Stats Desc:
+ Columns: value
+ Column Types: string
+ Table: default.partition_mv_sdp
Stage: Stage-5
Materialized View Work
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/llap/materialized_view_rewrite_1.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/materialized_view_rewrite_1.q.out b/ql/src/test/results/clientpositive/llap/materialized_view_rewrite_1.q.out
index 735a4db..5714ef8 100644
--- a/ql/src/test/results/clientpositive/llap/materialized_view_rewrite_1.q.out
+++ b/ql/src/test/results/clientpositive/llap/materialized_view_rewrite_1.q.out
@@ -33,16 +33,6 @@ POSTHOOK: Lineage: emps_n3.deptno SCRIPT []
POSTHOOK: Lineage: emps_n3.empid SCRIPT []
POSTHOOK: Lineage: emps_n3.name SCRIPT []
POSTHOOK: Lineage: emps_n3.salary SCRIPT []
-PREHOOK: query: analyze table emps_n3 compute statistics for columns
-PREHOOK: type: ANALYZE_TABLE
-PREHOOK: Input: default@emps_n3
-PREHOOK: Output: default@emps_n3
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table emps_n3 compute statistics for columns
-POSTHOOK: type: ANALYZE_TABLE
-POSTHOOK: Input: default@emps_n3
-POSTHOOK: Output: default@emps_n3
-#### A masked pattern was here ####
PREHOOK: query: create table depts_n2 (
deptno int,
name varchar(256),
@@ -70,16 +60,6 @@ POSTHOOK: Output: default@depts_n2
POSTHOOK: Lineage: depts_n2.deptno SCRIPT []
POSTHOOK: Lineage: depts_n2.locationid SCRIPT []
POSTHOOK: Lineage: depts_n2.name SCRIPT []
-PREHOOK: query: analyze table depts_n2 compute statistics for columns
-PREHOOK: type: ANALYZE_TABLE
-PREHOOK: Input: default@depts_n2
-PREHOOK: Output: default@depts_n2
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table depts_n2 compute statistics for columns
-POSTHOOK: type: ANALYZE_TABLE
-POSTHOOK: Input: default@depts_n2
-POSTHOOK: Output: default@depts_n2
-#### A masked pattern was here ####
PREHOOK: query: create table dependents_n2 (
empid int,
name varchar(256))
@@ -104,16 +84,6 @@ POSTHOOK: Input: _dummy_database@_dummy_table
POSTHOOK: Output: default@dependents_n2
POSTHOOK: Lineage: dependents_n2.empid SCRIPT []
POSTHOOK: Lineage: dependents_n2.name SCRIPT []
-PREHOOK: query: analyze table dependents_n2 compute statistics for columns
-PREHOOK: type: ANALYZE_TABLE
-PREHOOK: Input: default@dependents_n2
-PREHOOK: Output: default@dependents_n2
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table dependents_n2 compute statistics for columns
-POSTHOOK: type: ANALYZE_TABLE
-POSTHOOK: Input: default@dependents_n2
-POSTHOOK: Output: default@dependents_n2
-#### A masked pattern was here ####
PREHOOK: query: create table locations_n2 (
locationid int,
name varchar(256))
@@ -138,16 +108,6 @@ POSTHOOK: Input: _dummy_database@_dummy_table
POSTHOOK: Output: default@locations_n2
POSTHOOK: Lineage: locations_n2.locationid SCRIPT []
POSTHOOK: Lineage: locations_n2.name SCRIPT []
-PREHOOK: query: analyze table locations_n2 compute statistics for columns
-PREHOOK: type: ANALYZE_TABLE
-PREHOOK: Input: default@locations_n2
-PREHOOK: Output: default@locations_n2
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table locations_n2 compute statistics for columns
-POSTHOOK: type: ANALYZE_TABLE
-POSTHOOK: Input: default@locations_n2
-POSTHOOK: Output: default@locations_n2
-#### A masked pattern was here ####
PREHOOK: query: alter table emps_n3 add constraint pk1 primary key (empid) disable novalidate rely
PREHOOK: type: ALTERTABLE_ADDCONSTRAINT
POSTHOOK: query: alter table emps_n3 add constraint pk1 primary key (empid) disable novalidate rely
@@ -184,16 +144,6 @@ POSTHOOK: type: CREATE_MATERIALIZED_VIEW
POSTHOOK: Input: default@emps_n3
POSTHOOK: Output: database:default
POSTHOOK: Output: default@mv1_n2
-PREHOOK: query: analyze table mv1_n2 compute statistics for columns
-PREHOOK: type: ANALYZE_TABLE
-PREHOOK: Input: default@mv1_n2
-PREHOOK: Output: default@mv1_n2
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table mv1_n2 compute statistics for columns
-POSTHOOK: type: ANALYZE_TABLE
-POSTHOOK: Input: default@mv1_n2
-POSTHOOK: Output: default@mv1_n2
-#### A masked pattern was here ####
PREHOOK: query: explain
select *
from (select * from emps_n3 where empid < 120) t
@@ -331,16 +281,6 @@ POSTHOOK: type: CREATE_MATERIALIZED_VIEW
POSTHOOK: Input: default@emps_n3
POSTHOOK: Output: database:default
POSTHOOK: Output: default@mv1_n2
-PREHOOK: query: analyze table mv1_n2 compute statistics for columns
-PREHOOK: type: ANALYZE_TABLE
-PREHOOK: Input: default@mv1_n2
-PREHOOK: Output: default@mv1_n2
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table mv1_n2 compute statistics for columns
-POSTHOOK: type: ANALYZE_TABLE
-POSTHOOK: Input: default@mv1_n2
-POSTHOOK: Output: default@mv1_n2
-#### A masked pattern was here ####
PREHOOK: query: explain
select emps_n3.name, emps_n3.salary, emps_n3.commission
from emps_n3
@@ -422,16 +362,6 @@ POSTHOOK: Input: default@depts_n2
POSTHOOK: Input: default@emps_n3
POSTHOOK: Output: database:default
POSTHOOK: Output: default@mv1_n2
-PREHOOK: query: analyze table mv1_n2 compute statistics for columns
-PREHOOK: type: ANALYZE_TABLE
-PREHOOK: Input: default@mv1_n2
-PREHOOK: Output: default@mv1_n2
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table mv1_n2 compute statistics for columns
-POSTHOOK: type: ANALYZE_TABLE
-POSTHOOK: Input: default@mv1_n2
-POSTHOOK: Output: default@mv1_n2
-#### A masked pattern was here ####
PREHOOK: query: explain
select empid deptno from emps_n3
join depts_n2 using (deptno) where empid = 1
@@ -500,16 +430,6 @@ POSTHOOK: type: CREATE_MATERIALIZED_VIEW
POSTHOOK: Input: default@emps_n3
POSTHOOK: Output: database:default
POSTHOOK: Output: default@mv1_n2
-PREHOOK: query: analyze table mv1_n2 compute statistics for columns
-PREHOOK: type: ANALYZE_TABLE
-PREHOOK: Input: default@mv1_n2
-PREHOOK: Output: default@mv1_n2
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table mv1_n2 compute statistics for columns
-POSTHOOK: type: ANALYZE_TABLE
-POSTHOOK: Input: default@mv1_n2
-POSTHOOK: Output: default@mv1_n2
-#### A masked pattern was here ####
PREHOOK: query: explain
select * from emps_n3 where empid > 120
union all select * from emps_n3 where empid < 150
@@ -627,16 +547,6 @@ POSTHOOK: type: CREATE_MATERIALIZED_VIEW
POSTHOOK: Input: default@emps_n3
POSTHOOK: Output: database:default
POSTHOOK: Output: default@mv1_n2
-PREHOOK: query: analyze table mv1_n2 compute statistics for columns
-PREHOOK: type: ANALYZE_TABLE
-PREHOOK: Input: default@mv1_n2
-PREHOOK: Output: default@mv1_n2
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table mv1_n2 compute statistics for columns
-POSTHOOK: type: ANALYZE_TABLE
-POSTHOOK: Input: default@mv1_n2
-POSTHOOK: Output: default@mv1_n2
-#### A masked pattern was here ####
PREHOOK: query: explain
select empid, deptno from emps_n3 group by empid, deptno
PREHOOK: type: QUERY
@@ -695,16 +605,6 @@ POSTHOOK: type: CREATE_MATERIALIZED_VIEW
POSTHOOK: Input: default@emps_n3
POSTHOOK: Output: database:default
POSTHOOK: Output: default@mv1_n2
-PREHOOK: query: analyze table mv1_n2 compute statistics for columns
-PREHOOK: type: ANALYZE_TABLE
-PREHOOK: Input: default@mv1_n2
-PREHOOK: Output: default@mv1_n2
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table mv1_n2 compute statistics for columns
-POSTHOOK: type: ANALYZE_TABLE
-POSTHOOK: Input: default@mv1_n2
-POSTHOOK: Output: default@mv1_n2
-#### A masked pattern was here ####
PREHOOK: query: explain
select empid, name from emps_n3 group by empid, name
PREHOOK: type: QUERY
@@ -763,16 +663,6 @@ POSTHOOK: type: CREATE_MATERIALIZED_VIEW
POSTHOOK: Input: default@emps_n3
POSTHOOK: Output: database:default
POSTHOOK: Output: default@mv1_n2
-PREHOOK: query: analyze table mv1_n2 compute statistics for columns
-PREHOOK: type: ANALYZE_TABLE
-PREHOOK: Input: default@mv1_n2
-PREHOOK: Output: default@mv1_n2
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table mv1_n2 compute statistics for columns
-POSTHOOK: type: ANALYZE_TABLE
-POSTHOOK: Input: default@mv1_n2
-POSTHOOK: Output: default@mv1_n2
-#### A masked pattern was here ####
PREHOOK: query: explain
select name, salary from emps_n3 group by name, salary
PREHOOK: type: QUERY
@@ -834,16 +724,6 @@ POSTHOOK: type: CREATE_MATERIALIZED_VIEW
POSTHOOK: Input: default@emps_n3
POSTHOOK: Output: database:default
POSTHOOK: Output: default@mv1_n2
-PREHOOK: query: analyze table mv1_n2 compute statistics for columns
-PREHOOK: type: ANALYZE_TABLE
-PREHOOK: Input: default@mv1_n2
-PREHOOK: Output: default@mv1_n2
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table mv1_n2 compute statistics for columns
-POSTHOOK: type: ANALYZE_TABLE
-POSTHOOK: Input: default@mv1_n2
-POSTHOOK: Output: default@mv1_n2
-#### A masked pattern was here ####
PREHOOK: query: explain
select name from emps_n3 group by name
PREHOOK: type: QUERY
@@ -945,16 +825,6 @@ POSTHOOK: type: CREATE_MATERIALIZED_VIEW
POSTHOOK: Input: default@emps_n3
POSTHOOK: Output: database:default
POSTHOOK: Output: default@mv1_n2
-PREHOOK: query: analyze table mv1_n2 compute statistics for columns
-PREHOOK: type: ANALYZE_TABLE
-PREHOOK: Input: default@mv1_n2
-PREHOOK: Output: default@mv1_n2
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table mv1_n2 compute statistics for columns
-POSTHOOK: type: ANALYZE_TABLE
-POSTHOOK: Input: default@mv1_n2
-POSTHOOK: Output: default@mv1_n2
-#### A masked pattern was here ####
PREHOOK: query: explain
select name from emps_n3 where deptno = 10 group by name
PREHOOK: type: QUERY
@@ -1057,16 +927,6 @@ POSTHOOK: type: CREATE_MATERIALIZED_VIEW
POSTHOOK: Input: default@emps_n3
POSTHOOK: Output: database:default
POSTHOOK: Output: default@mv1_n2
-PREHOOK: query: analyze table mv1_n2 compute statistics for columns
-PREHOOK: type: ANALYZE_TABLE
-PREHOOK: Input: default@mv1_n2
-PREHOOK: Output: default@mv1_n2
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table mv1_n2 compute statistics for columns
-POSTHOOK: type: ANALYZE_TABLE
-POSTHOOK: Input: default@mv1_n2
-POSTHOOK: Output: default@mv1_n2
-#### A masked pattern was here ####
PREHOOK: query: explain
select name from emps_n3 group by name
PREHOOK: type: QUERY
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/llap/materialized_view_rewrite_10.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/materialized_view_rewrite_10.q.out b/ql/src/test/results/clientpositive/llap/materialized_view_rewrite_10.q.out
index 3ed5609..94940ac 100644
--- a/ql/src/test/results/clientpositive/llap/materialized_view_rewrite_10.q.out
+++ b/ql/src/test/results/clientpositive/llap/materialized_view_rewrite_10.q.out
@@ -33,16 +33,6 @@ POSTHOOK: Lineage: emps_n10.deptno SCRIPT []
POSTHOOK: Lineage: emps_n10.empid SCRIPT []
POSTHOOK: Lineage: emps_n10.name SCRIPT []
POSTHOOK: Lineage: emps_n10.salary SCRIPT []
-PREHOOK: query: analyze table emps_n10 compute statistics for columns
-PREHOOK: type: ANALYZE_TABLE
-PREHOOK: Input: default@emps_n10
-PREHOOK: Output: default@emps_n10
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table emps_n10 compute statistics for columns
-POSTHOOK: type: ANALYZE_TABLE
-POSTHOOK: Input: default@emps_n10
-POSTHOOK: Output: default@emps_n10
-#### A masked pattern was here ####
PREHOOK: query: create materialized view mv1_n10 as
select deptno, sum(salary), count(salary) as a
from emps_n10 group by deptno
@@ -57,16 +47,6 @@ POSTHOOK: type: CREATE_MATERIALIZED_VIEW
POSTHOOK: Input: default@emps_n10
POSTHOOK: Output: database:default
POSTHOOK: Output: default@mv1_n10
-PREHOOK: query: analyze table mv1_n10 compute statistics for columns
-PREHOOK: type: ANALYZE_TABLE
-PREHOOK: Input: default@mv1_n10
-PREHOOK: Output: default@mv1_n10
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table mv1_n10 compute statistics for columns
-POSTHOOK: type: ANALYZE_TABLE
-POSTHOOK: Input: default@mv1_n10
-POSTHOOK: Output: default@mv1_n10
-#### A masked pattern was here ####
PREHOOK: query: explain
select deptno, avg(salary) as a
from emps_n10 group by deptno
@@ -132,16 +112,6 @@ POSTHOOK: type: CREATE_MATERIALIZED_VIEW
POSTHOOK: Input: default@emps_n10
POSTHOOK: Output: database:default
POSTHOOK: Output: default@mv1_n10
-PREHOOK: query: analyze table mv1_n10 compute statistics for columns
-PREHOOK: type: ANALYZE_TABLE
-PREHOOK: Input: default@mv1_n10
-PREHOOK: Output: default@mv1_n10
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table mv1_n10 compute statistics for columns
-POSTHOOK: type: ANALYZE_TABLE
-POSTHOOK: Input: default@mv1_n10
-POSTHOOK: Output: default@mv1_n10
-#### A masked pattern was here ####
PREHOOK: query: explain
select salary, avg(salary) as a
from emps_n10 group by salary
@@ -208,16 +178,6 @@ POSTHOOK: type: CREATE_MATERIALIZED_VIEW
POSTHOOK: Input: default@emps_n10
POSTHOOK: Output: database:default
POSTHOOK: Output: default@mv1_n10
-PREHOOK: query: analyze table mv1_n10 compute statistics for columns
-PREHOOK: type: ANALYZE_TABLE
-PREHOOK: Input: default@mv1_n10
-PREHOOK: Output: default@mv1_n10
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table mv1_n10 compute statistics for columns
-POSTHOOK: type: ANALYZE_TABLE
-POSTHOOK: Input: default@mv1_n10
-POSTHOOK: Output: default@mv1_n10
-#### A masked pattern was here ####
PREHOOK: query: explain
select salary, avg(salary) as a
from emps_n10 where salary > 0 group by salary
@@ -305,16 +265,6 @@ POSTHOOK: Lineage: emps_n10_2.deptno SCRIPT []
POSTHOOK: Lineage: emps_n10_2.empid SCRIPT []
POSTHOOK: Lineage: emps_n10_2.name SCRIPT []
POSTHOOK: Lineage: emps_n10_2.salary SCRIPT []
-PREHOOK: query: analyze table emps_n10_2 compute statistics for columns
-PREHOOK: type: ANALYZE_TABLE
-PREHOOK: Input: default@emps_n10_2
-PREHOOK: Output: default@emps_n10_2
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table emps_n10_2 compute statistics for columns
-POSTHOOK: type: ANALYZE_TABLE
-POSTHOOK: Input: default@emps_n10_2
-POSTHOOK: Output: default@emps_n10_2
-#### A masked pattern was here ####
PREHOOK: query: create materialized view mv1_n10 as
select salary, sum(salary), count(salary) as a
from emps_n10_2 where salary > 0 group by salary
@@ -329,16 +279,6 @@ POSTHOOK: type: CREATE_MATERIALIZED_VIEW
POSTHOOK: Input: default@emps_n10_2
POSTHOOK: Output: database:default
POSTHOOK: Output: default@mv1_n10
-PREHOOK: query: analyze table mv1_n10 compute statistics for columns
-PREHOOK: type: ANALYZE_TABLE
-PREHOOK: Input: default@mv1_n10
-PREHOOK: Output: default@mv1_n10
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table mv1_n10 compute statistics for columns
-POSTHOOK: type: ANALYZE_TABLE
-POSTHOOK: Input: default@mv1_n10
-POSTHOOK: Output: default@mv1_n10
-#### A masked pattern was here ####
PREHOOK: query: explain
select avg(salary)
from emps_n10_2 where salary > 0
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/llap/materialized_view_rewrite_2.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/materialized_view_rewrite_2.q.out b/ql/src/test/results/clientpositive/llap/materialized_view_rewrite_2.q.out
index d5afe3f..f87b55b 100644
--- a/ql/src/test/results/clientpositive/llap/materialized_view_rewrite_2.q.out
+++ b/ql/src/test/results/clientpositive/llap/materialized_view_rewrite_2.q.out
@@ -33,16 +33,6 @@ POSTHOOK: Lineage: emps_n0.deptno SCRIPT []
POSTHOOK: Lineage: emps_n0.empid SCRIPT []
POSTHOOK: Lineage: emps_n0.name SCRIPT []
POSTHOOK: Lineage: emps_n0.salary SCRIPT []
-PREHOOK: query: analyze table emps_n0 compute statistics for columns
-PREHOOK: type: ANALYZE_TABLE
-PREHOOK: Input: default@emps_n0
-PREHOOK: Output: default@emps_n0
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table emps_n0 compute statistics for columns
-POSTHOOK: type: ANALYZE_TABLE
-POSTHOOK: Input: default@emps_n0
-POSTHOOK: Output: default@emps_n0
-#### A masked pattern was here ####
PREHOOK: query: create table depts_n0 (
deptno int,
name varchar(256),
@@ -70,16 +60,6 @@ POSTHOOK: Output: default@depts_n0
POSTHOOK: Lineage: depts_n0.deptno SCRIPT []
POSTHOOK: Lineage: depts_n0.locationid SCRIPT []
POSTHOOK: Lineage: depts_n0.name SCRIPT []
-PREHOOK: query: analyze table depts_n0 compute statistics for columns
-PREHOOK: type: ANALYZE_TABLE
-PREHOOK: Input: default@depts_n0
-PREHOOK: Output: default@depts_n0
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table depts_n0 compute statistics for columns
-POSTHOOK: type: ANALYZE_TABLE
-POSTHOOK: Input: default@depts_n0
-POSTHOOK: Output: default@depts_n0
-#### A masked pattern was here ####
PREHOOK: query: create table dependents_n0 (
empid int,
name varchar(256))
@@ -104,16 +84,6 @@ POSTHOOK: Input: _dummy_database@_dummy_table
POSTHOOK: Output: default@dependents_n0
POSTHOOK: Lineage: dependents_n0.empid SCRIPT []
POSTHOOK: Lineage: dependents_n0.name SCRIPT []
-PREHOOK: query: analyze table dependents_n0 compute statistics for columns
-PREHOOK: type: ANALYZE_TABLE
-PREHOOK: Input: default@dependents_n0
-PREHOOK: Output: default@dependents_n0
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table dependents_n0 compute statistics for columns
-POSTHOOK: type: ANALYZE_TABLE
-POSTHOOK: Input: default@dependents_n0
-POSTHOOK: Output: default@dependents_n0
-#### A masked pattern was here ####
PREHOOK: query: create table locations_n0 (
locationid int,
name varchar(256))
@@ -138,16 +108,6 @@ POSTHOOK: Input: _dummy_database@_dummy_table
POSTHOOK: Output: default@locations_n0
POSTHOOK: Lineage: locations_n0.locationid SCRIPT []
POSTHOOK: Lineage: locations_n0.name SCRIPT []
-PREHOOK: query: analyze table locations_n0 compute statistics for columns
-PREHOOK: type: ANALYZE_TABLE
-PREHOOK: Input: default@locations_n0
-PREHOOK: Output: default@locations_n0
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table locations_n0 compute statistics for columns
-POSTHOOK: type: ANALYZE_TABLE
-POSTHOOK: Input: default@locations_n0
-POSTHOOK: Output: default@locations_n0
-#### A masked pattern was here ####
PREHOOK: query: alter table emps_n0 add constraint pk1 primary key (empid) disable novalidate rely
PREHOOK: type: ALTERTABLE_ADDCONSTRAINT
POSTHOOK: query: alter table emps_n0 add constraint pk1 primary key (empid) disable novalidate rely
@@ -190,16 +150,6 @@ POSTHOOK: Input: default@depts_n0
POSTHOOK: Input: default@emps_n0
POSTHOOK: Output: database:default
POSTHOOK: Output: default@mv1_n0
-PREHOOK: query: analyze table mv1_n0 compute statistics for columns
-PREHOOK: type: ANALYZE_TABLE
-PREHOOK: Input: default@mv1_n0
-PREHOOK: Output: default@mv1_n0
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table mv1_n0 compute statistics for columns
-POSTHOOK: type: ANALYZE_TABLE
-POSTHOOK: Input: default@mv1_n0
-POSTHOOK: Output: default@mv1_n0
-#### A masked pattern was here ####
PREHOOK: query: explain
select empid from emps_n0
join depts_n0 using (deptno) where depts_n0.deptno > 20
@@ -278,16 +228,6 @@ POSTHOOK: Input: default@depts_n0
POSTHOOK: Input: default@emps_n0
POSTHOOK: Output: database:default
POSTHOOK: Output: default@mv1_n0
-PREHOOK: query: analyze table mv1_n0 compute statistics for columns
-PREHOOK: type: ANALYZE_TABLE
-PREHOOK: Input: default@mv1_n0
-PREHOOK: Output: default@mv1_n0
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table mv1_n0 compute statistics for columns
-POSTHOOK: type: ANALYZE_TABLE
-POSTHOOK: Input: default@mv1_n0
-POSTHOOK: Output: default@mv1_n0
-#### A masked pattern was here ####
PREHOOK: query: explain
select empid from emps_n0
join depts_n0 using (deptno) where depts_n0.deptno > 20
@@ -366,16 +306,6 @@ POSTHOOK: Input: default@depts_n0
POSTHOOK: Input: default@emps_n0
POSTHOOK: Output: database:default
POSTHOOK: Output: default@mv1_n0
-PREHOOK: query: analyze table mv1_n0 compute statistics for columns
-PREHOOK: type: ANALYZE_TABLE
-PREHOOK: Input: default@mv1_n0
-PREHOOK: Output: default@mv1_n0
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table mv1_n0 compute statistics for columns
-POSTHOOK: type: ANALYZE_TABLE
-POSTHOOK: Input: default@mv1_n0
-POSTHOOK: Output: default@mv1_n0
-#### A masked pattern was here ####
PREHOOK: query: explain
select empid from emps_n0
join depts_n0 using (deptno) where depts_n0.deptno > 20
@@ -454,16 +384,6 @@ POSTHOOK: Input: default@depts_n0
POSTHOOK: Input: default@emps_n0
POSTHOOK: Output: database:default
POSTHOOK: Output: default@mv1_n0
-PREHOOK: query: analyze table mv1_n0 compute statistics for columns
-PREHOOK: type: ANALYZE_TABLE
-PREHOOK: Input: default@mv1_n0
-PREHOOK: Output: default@mv1_n0
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table mv1_n0 compute statistics for columns
-POSTHOOK: type: ANALYZE_TABLE
-POSTHOOK: Input: default@mv1_n0
-POSTHOOK: Output: default@mv1_n0
-#### A masked pattern was here ####
PREHOOK: query: explain
select depts_n0.deptno from depts_n0
join emps_n0 using (deptno) where emps_n0.empid > 15
@@ -547,16 +467,6 @@ POSTHOOK: Input: default@depts_n0
POSTHOOK: Input: default@emps_n0
POSTHOOK: Output: database:default
POSTHOOK: Output: default@mv1_n0
-PREHOOK: query: analyze table mv1_n0 compute statistics for columns
-PREHOOK: type: ANALYZE_TABLE
-PREHOOK: Input: default@mv1_n0
-PREHOOK: Output: default@mv1_n0
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table mv1_n0 compute statistics for columns
-POSTHOOK: type: ANALYZE_TABLE
-POSTHOOK: Input: default@mv1_n0
-POSTHOOK: Output: default@mv1_n0
-#### A masked pattern was here ####
PREHOOK: query: explain
select depts_n0.deptno from depts_n0
join emps_n0 using (deptno) where emps_n0.empid > 15
@@ -693,7 +603,7 @@ POSTHOOK: query: drop materialized view mv1_n0
POSTHOOK: type: DROP_MATERIALIZED_VIEW
POSTHOOK: Input: default@mv1_n0
POSTHOOK: Output: default@mv1_n0
-Warning: Shuffle Join MERGEJOIN[18][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Reducer 2' is a cross product
+Warning: Shuffle Join MERGEJOIN[28][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Reducer 2' is a cross product
PREHOOK: query: create materialized view mv1_n0 as
select depts_n0.name, dependents_n0.name as name2, emps_n0.deptno, depts_n0.deptno as deptno2, dependents_n0.empid
from depts_n0, dependents_n0, emps_n0
@@ -716,16 +626,6 @@ POSTHOOK: Input: default@depts_n0
POSTHOOK: Input: default@emps_n0
POSTHOOK: Output: database:default
POSTHOOK: Output: default@mv1_n0
-PREHOOK: query: analyze table mv1_n0 compute statistics for columns
-PREHOOK: type: ANALYZE_TABLE
-PREHOOK: Input: default@mv1_n0
-PREHOOK: Output: default@mv1_n0
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table mv1_n0 compute statistics for columns
-POSTHOOK: type: ANALYZE_TABLE
-POSTHOOK: Input: default@mv1_n0
-POSTHOOK: Output: default@mv1_n0
-#### A masked pattern was here ####
PREHOOK: query: explain
select dependents_n0.empid
from depts_n0
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/llap/materialized_view_rewrite_3.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/materialized_view_rewrite_3.q.out b/ql/src/test/results/clientpositive/llap/materialized_view_rewrite_3.q.out
index 91f6982..93bda76 100644
--- a/ql/src/test/results/clientpositive/llap/materialized_view_rewrite_3.q.out
+++ b/ql/src/test/results/clientpositive/llap/materialized_view_rewrite_3.q.out
@@ -33,16 +33,6 @@ POSTHOOK: Lineage: emps_n9.deptno SCRIPT []
POSTHOOK: Lineage: emps_n9.empid SCRIPT []
POSTHOOK: Lineage: emps_n9.name SCRIPT []
POSTHOOK: Lineage: emps_n9.salary SCRIPT []
-PREHOOK: query: analyze table emps_n9 compute statistics for columns
-PREHOOK: type: ANALYZE_TABLE
-PREHOOK: Input: default@emps_n9
-PREHOOK: Output: default@emps_n9
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table emps_n9 compute statistics for columns
-POSTHOOK: type: ANALYZE_TABLE
-POSTHOOK: Input: default@emps_n9
-POSTHOOK: Output: default@emps_n9
-#### A masked pattern was here ####
PREHOOK: query: create table depts_n7 (
deptno int,
name varchar(256),
@@ -70,16 +60,6 @@ POSTHOOK: Output: default@depts_n7
POSTHOOK: Lineage: depts_n7.deptno SCRIPT []
POSTHOOK: Lineage: depts_n7.locationid SCRIPT []
POSTHOOK: Lineage: depts_n7.name SCRIPT []
-PREHOOK: query: analyze table depts_n7 compute statistics for columns
-PREHOOK: type: ANALYZE_TABLE
-PREHOOK: Input: default@depts_n7
-PREHOOK: Output: default@depts_n7
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table depts_n7 compute statistics for columns
-POSTHOOK: type: ANALYZE_TABLE
-POSTHOOK: Input: default@depts_n7
-POSTHOOK: Output: default@depts_n7
-#### A masked pattern was here ####
PREHOOK: query: create table dependents_n5 (
empid int,
name varchar(256))
@@ -104,16 +84,6 @@ POSTHOOK: Input: _dummy_database@_dummy_table
POSTHOOK: Output: default@dependents_n5
POSTHOOK: Lineage: dependents_n5.empid SCRIPT []
POSTHOOK: Lineage: dependents_n5.name SCRIPT []
-PREHOOK: query: analyze table dependents_n5 compute statistics for columns
-PREHOOK: type: ANALYZE_TABLE
-PREHOOK: Input: default@dependents_n5
-PREHOOK: Output: default@dependents_n5
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table dependents_n5 compute statistics for columns
-POSTHOOK: type: ANALYZE_TABLE
-POSTHOOK: Input: default@dependents_n5
-POSTHOOK: Output: default@dependents_n5
-#### A masked pattern was here ####
PREHOOK: query: create table locations_n5 (
locationid int,
name varchar(256))
@@ -138,16 +108,6 @@ POSTHOOK: Input: _dummy_database@_dummy_table
POSTHOOK: Output: default@locations_n5
POSTHOOK: Lineage: locations_n5.locationid SCRIPT []
POSTHOOK: Lineage: locations_n5.name SCRIPT []
-PREHOOK: query: analyze table locations_n5 compute statistics for columns
-PREHOOK: type: ANALYZE_TABLE
-PREHOOK: Input: default@locations_n5
-PREHOOK: Output: default@locations_n5
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table locations_n5 compute statistics for columns
-POSTHOOK: type: ANALYZE_TABLE
-POSTHOOK: Input: default@locations_n5
-POSTHOOK: Output: default@locations_n5
-#### A masked pattern was here ####
PREHOOK: query: alter table emps_n9 add constraint pk1 primary key (empid) disable novalidate rely
PREHOOK: type: ALTERTABLE_ADDCONSTRAINT
POSTHOOK: query: alter table emps_n9 add constraint pk1 primary key (empid) disable novalidate rely
@@ -188,16 +148,6 @@ POSTHOOK: Input: default@depts_n7
POSTHOOK: Input: default@emps_n9
POSTHOOK: Output: database:default
POSTHOOK: Output: default@mv1_n5
-PREHOOK: query: analyze table mv1_n5 compute statistics for columns
-PREHOOK: type: ANALYZE_TABLE
-PREHOOK: Input: default@mv1_n5
-PREHOOK: Output: default@mv1_n5
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table mv1_n5 compute statistics for columns
-POSTHOOK: type: ANALYZE_TABLE
-POSTHOOK: Input: default@mv1_n5
-POSTHOOK: Output: default@mv1_n5
-#### A masked pattern was here ####
PREHOOK: query: explain
select empid deptno from emps_n9
join depts_n7 using (deptno) where empid = 1
@@ -270,16 +220,6 @@ POSTHOOK: Input: default@depts_n7
POSTHOOK: Input: default@emps_n9
POSTHOOK: Output: database:default
POSTHOOK: Output: default@mv1_n5
-PREHOOK: query: analyze table mv1_n5 compute statistics for columns
-PREHOOK: type: ANALYZE_TABLE
-PREHOOK: Input: default@mv1_n5
-PREHOOK: Output: default@mv1_n5
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table mv1_n5 compute statistics for columns
-POSTHOOK: type: ANALYZE_TABLE
-POSTHOOK: Input: default@mv1_n5
-POSTHOOK: Output: default@mv1_n5
-#### A masked pattern was here ####
PREHOOK: query: explain
select empid deptno from emps_n9
join depts_n7 using (deptno) where empid > 1
@@ -356,16 +296,6 @@ POSTHOOK: Input: default@depts_n7
POSTHOOK: Input: default@emps_n9
POSTHOOK: Output: database:default
POSTHOOK: Output: default@mv1_n5
-PREHOOK: query: analyze table mv1_n5 compute statistics for columns
-PREHOOK: type: ANALYZE_TABLE
-PREHOOK: Input: default@mv1_n5
-PREHOOK: Output: default@mv1_n5
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table mv1_n5 compute statistics for columns
-POSTHOOK: type: ANALYZE_TABLE
-POSTHOOK: Input: default@mv1_n5
-POSTHOOK: Output: default@mv1_n5
-#### A masked pattern was here ####
PREHOOK: query: explain
select empid deptno from emps_n9
join depts_n7 using (deptno) where empid = 1
@@ -440,16 +370,6 @@ POSTHOOK: Input: default@depts_n7
POSTHOOK: Input: default@emps_n9
POSTHOOK: Output: database:default
POSTHOOK: Output: default@mv1_n5
-PREHOOK: query: analyze table mv1_n5 compute statistics for columns
-PREHOOK: type: ANALYZE_TABLE
-PREHOOK: Input: default@mv1_n5
-PREHOOK: Output: default@mv1_n5
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table mv1_n5 compute statistics for columns
-POSTHOOK: type: ANALYZE_TABLE
-POSTHOOK: Input: default@mv1_n5
-POSTHOOK: Output: default@mv1_n5
-#### A masked pattern was here ####
PREHOOK: query: explain
select dependents_n5.empid
from depts_n7
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/llap/materialized_view_rewrite_4.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/materialized_view_rewrite_4.q.out b/ql/src/test/results/clientpositive/llap/materialized_view_rewrite_4.q.out
index 18efcba..2442ecc 100644
--- a/ql/src/test/results/clientpositive/llap/materialized_view_rewrite_4.q.out
+++ b/ql/src/test/results/clientpositive/llap/materialized_view_rewrite_4.q.out
@@ -33,16 +33,6 @@ POSTHOOK: Lineage: emps_n5.deptno SCRIPT []
POSTHOOK: Lineage: emps_n5.empid SCRIPT []
POSTHOOK: Lineage: emps_n5.name SCRIPT []
POSTHOOK: Lineage: emps_n5.salary SCRIPT []
-PREHOOK: query: analyze table emps_n5 compute statistics for columns
-PREHOOK: type: ANALYZE_TABLE
-PREHOOK: Input: default@emps_n5
-PREHOOK: Output: default@emps_n5
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table emps_n5 compute statistics for columns
-POSTHOOK: type: ANALYZE_TABLE
-POSTHOOK: Input: default@emps_n5
-POSTHOOK: Output: default@emps_n5
-#### A masked pattern was here ####
PREHOOK: query: create table depts_n4 (
deptno int,
name varchar(256),
@@ -70,16 +60,6 @@ POSTHOOK: Output: default@depts_n4
POSTHOOK: Lineage: depts_n4.deptno SCRIPT []
POSTHOOK: Lineage: depts_n4.locationid SCRIPT []
POSTHOOK: Lineage: depts_n4.name SCRIPT []
-PREHOOK: query: analyze table depts_n4 compute statistics for columns
-PREHOOK: type: ANALYZE_TABLE
-PREHOOK: Input: default@depts_n4
-PREHOOK: Output: default@depts_n4
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table depts_n4 compute statistics for columns
-POSTHOOK: type: ANALYZE_TABLE
-POSTHOOK: Input: default@depts_n4
-POSTHOOK: Output: default@depts_n4
-#### A masked pattern was here ####
PREHOOK: query: create table dependents_n3 (
empid int,
name varchar(256))
@@ -104,16 +84,6 @@ POSTHOOK: Input: _dummy_database@_dummy_table
POSTHOOK: Output: default@dependents_n3
POSTHOOK: Lineage: dependents_n3.empid SCRIPT []
POSTHOOK: Lineage: dependents_n3.name SCRIPT []
-PREHOOK: query: analyze table dependents_n3 compute statistics for columns
-PREHOOK: type: ANALYZE_TABLE
-PREHOOK: Input: default@dependents_n3
-PREHOOK: Output: default@dependents_n3
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table dependents_n3 compute statistics for columns
-POSTHOOK: type: ANALYZE_TABLE
-POSTHOOK: Input: default@dependents_n3
-POSTHOOK: Output: default@dependents_n3
-#### A masked pattern was here ####
PREHOOK: query: create table locations_n3 (
locationid int,
name varchar(256))
@@ -138,16 +108,6 @@ POSTHOOK: Input: _dummy_database@_dummy_table
POSTHOOK: Output: default@locations_n3
POSTHOOK: Lineage: locations_n3.locationid SCRIPT []
POSTHOOK: Lineage: locations_n3.name SCRIPT []
-PREHOOK: query: analyze table locations_n3 compute statistics for columns
-PREHOOK: type: ANALYZE_TABLE
-PREHOOK: Input: default@locations_n3
-PREHOOK: Output: default@locations_n3
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table locations_n3 compute statistics for columns
-POSTHOOK: type: ANALYZE_TABLE
-POSTHOOK: Input: default@locations_n3
-POSTHOOK: Output: default@locations_n3
-#### A masked pattern was here ####
PREHOOK: query: alter table emps_n5 add constraint pk1 primary key (empid) disable novalidate rely
PREHOOK: type: ALTERTABLE_ADDCONSTRAINT
POSTHOOK: query: alter table emps_n5 add constraint pk1 primary key (empid) disable novalidate rely
@@ -186,16 +146,6 @@ POSTHOOK: type: CREATE_MATERIALIZED_VIEW
POSTHOOK: Input: default@emps_n5
POSTHOOK: Output: database:default
POSTHOOK: Output: default@mv1_n3
-PREHOOK: query: analyze table mv1_n3 compute statistics for columns
-PREHOOK: type: ANALYZE_TABLE
-PREHOOK: Input: default@mv1_n3
-PREHOOK: Output: default@mv1_n3
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table mv1_n3 compute statistics for columns
-POSTHOOK: type: ANALYZE_TABLE
-POSTHOOK: Input: default@mv1_n3
-POSTHOOK: Output: default@mv1_n3
-#### A masked pattern was here ####
PREHOOK: query: explain
select name, count(*) as c, sum(empid) as s
from emps_n5 group by name
@@ -310,16 +260,6 @@ POSTHOOK: type: CREATE_MATERIALIZED_VIEW
POSTHOOK: Input: default@emps_n5
POSTHOOK: Output: database:default
POSTHOOK: Output: default@mv1_n3
-PREHOOK: query: analyze table mv1_n3 compute statistics for columns
-PREHOOK: type: ANALYZE_TABLE
-PREHOOK: Input: default@mv1_n3
-PREHOOK: Output: default@mv1_n3
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table mv1_n3 compute statistics for columns
-POSTHOOK: type: ANALYZE_TABLE
-POSTHOOK: Input: default@mv1_n3
-POSTHOOK: Output: default@mv1_n3
-#### A masked pattern was here ####
PREHOOK: query: explain
select salary, name, sum(empid) as s, count(*) as c
from emps_n5 group by name, salary
@@ -391,16 +331,6 @@ POSTHOOK: Input: default@depts_n4
POSTHOOK: Input: default@emps_n5
POSTHOOK: Output: database:default
POSTHOOK: Output: default@mv1_n3
-PREHOOK: query: analyze table mv1_n3 compute statistics for columns
-PREHOOK: type: ANALYZE_TABLE
-PREHOOK: Input: default@mv1_n3
-PREHOOK: Output: default@mv1_n3
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table mv1_n3 compute statistics for columns
-POSTHOOK: type: ANALYZE_TABLE
-POSTHOOK: Input: default@mv1_n3
-POSTHOOK: Output: default@mv1_n3
-#### A masked pattern was here ####
PREHOOK: query: explain
select depts_n4.deptno, count(*) as c, sum(empid) as s
from emps_n5 join depts_n4 using (deptno)
@@ -525,16 +455,6 @@ POSTHOOK: Input: default@depts_n4
POSTHOOK: Input: default@emps_n5
POSTHOOK: Output: database:default
POSTHOOK: Output: default@mv1_n3
-PREHOOK: query: analyze table mv1_n3 compute statistics for columns
-PREHOOK: type: ANALYZE_TABLE
-PREHOOK: Input: default@mv1_n3
-PREHOOK: Output: default@mv1_n3
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table mv1_n3 compute statistics for columns
-POSTHOOK: type: ANALYZE_TABLE
-POSTHOOK: Input: default@mv1_n3
-POSTHOOK: Output: default@mv1_n3
-#### A masked pattern was here ####
PREHOOK: query: explain
select depts_n4.deptno, sum(empid) as s
from emps_n5 join depts_n4 using (deptno)
@@ -654,16 +574,6 @@ POSTHOOK: Input: default@depts_n4
POSTHOOK: Input: default@emps_n5
POSTHOOK: Output: database:default
POSTHOOK: Output: default@mv1_n3
-PREHOOK: query: analyze table mv1_n3 compute statistics for columns
-PREHOOK: type: ANALYZE_TABLE
-PREHOOK: Input: default@mv1_n3
-PREHOOK: Output: default@mv1_n3
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table mv1_n3 compute statistics for columns
-POSTHOOK: type: ANALYZE_TABLE
-POSTHOOK: Input: default@mv1_n3
-POSTHOOK: Output: default@mv1_n3
-#### A masked pattern was here ####
PREHOOK: query: explain
select depts_n4.deptno, sum(empid) + 1 as s
from emps_n5 join depts_n4 using (deptno)
@@ -793,16 +703,6 @@ POSTHOOK: Input: default@depts_n4
POSTHOOK: Input: default@emps_n5
POSTHOOK: Output: database:default
POSTHOOK: Output: default@mv1_n3
-PREHOOK: query: analyze table mv1_n3 compute statistics for columns
-PREHOOK: type: ANALYZE_TABLE
-PREHOOK: Input: default@mv1_n3
-PREHOOK: Output: default@mv1_n3
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table mv1_n3 compute statistics for columns
-POSTHOOK: type: ANALYZE_TABLE
-POSTHOOK: Input: default@mv1_n3
-POSTHOOK: Output: default@mv1_n3
-#### A masked pattern was here ####
PREHOOK: query: explain
select dependents_n3.empid, sum(salary) as s
from emps_n5
@@ -978,16 +878,6 @@ POSTHOOK: Input: default@dependents_n3
POSTHOOK: Input: default@emps_n5
POSTHOOK: Output: database:default
POSTHOOK: Output: default@mv1_n3
-PREHOOK: query: analyze table mv1_n3 compute statistics for columns
-PREHOOK: type: ANALYZE_TABLE
-PREHOOK: Input: default@mv1_n3
-PREHOOK: Output: default@mv1_n3
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table mv1_n3 compute statistics for columns
-POSTHOOK: type: ANALYZE_TABLE
-POSTHOOK: Input: default@mv1_n3
-POSTHOOK: Output: default@mv1_n3
-#### A masked pattern was here ####
PREHOOK: query: explain
select emps_n5.deptno, count(distinct salary) as s
from emps_n5
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/llap/materialized_view_rewrite_5.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/materialized_view_rewrite_5.q.out b/ql/src/test/results/clientpositive/llap/materialized_view_rewrite_5.q.out
index e4c939e..b865675 100644
--- a/ql/src/test/results/clientpositive/llap/materialized_view_rewrite_5.q.out
+++ b/ql/src/test/results/clientpositive/llap/materialized_view_rewrite_5.q.out
@@ -33,16 +33,6 @@ POSTHOOK: Lineage: emps_n2.deptno SCRIPT []
POSTHOOK: Lineage: emps_n2.empid SCRIPT []
POSTHOOK: Lineage: emps_n2.name SCRIPT []
POSTHOOK: Lineage: emps_n2.salary SCRIPT []
-PREHOOK: query: analyze table emps_n2 compute statistics for columns
-PREHOOK: type: ANALYZE_TABLE
-PREHOOK: Input: default@emps_n2
-PREHOOK: Output: default@emps_n2
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table emps_n2 compute statistics for columns
-POSTHOOK: type: ANALYZE_TABLE
-POSTHOOK: Input: default@emps_n2
-POSTHOOK: Output: default@emps_n2
-#### A masked pattern was here ####
PREHOOK: query: create table depts_n1 (
deptno int,
name varchar(256),
@@ -70,16 +60,6 @@ POSTHOOK: Output: default@depts_n1
POSTHOOK: Lineage: depts_n1.deptno SCRIPT []
POSTHOOK: Lineage: depts_n1.locationid SCRIPT []
POSTHOOK: Lineage: depts_n1.name SCRIPT []
-PREHOOK: query: analyze table depts_n1 compute statistics for columns
-PREHOOK: type: ANALYZE_TABLE
-PREHOOK: Input: default@depts_n1
-PREHOOK: Output: default@depts_n1
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table depts_n1 compute statistics for columns
-POSTHOOK: type: ANALYZE_TABLE
-POSTHOOK: Input: default@depts_n1
-POSTHOOK: Output: default@depts_n1
-#### A masked pattern was here ####
PREHOOK: query: create table dependents_n1 (
empid int,
name varchar(256))
@@ -104,16 +84,6 @@ POSTHOOK: Input: _dummy_database@_dummy_table
POSTHOOK: Output: default@dependents_n1
POSTHOOK: Lineage: dependents_n1.empid SCRIPT []
POSTHOOK: Lineage: dependents_n1.name SCRIPT []
-PREHOOK: query: analyze table dependents_n1 compute statistics for columns
-PREHOOK: type: ANALYZE_TABLE
-PREHOOK: Input: default@dependents_n1
-PREHOOK: Output: default@dependents_n1
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table dependents_n1 compute statistics for columns
-POSTHOOK: type: ANALYZE_TABLE
-POSTHOOK: Input: default@dependents_n1
-POSTHOOK: Output: default@dependents_n1
-#### A masked pattern was here ####
PREHOOK: query: create table locations_n1 (
locationid int,
name varchar(256))
@@ -138,16 +108,6 @@ POSTHOOK: Input: _dummy_database@_dummy_table
POSTHOOK: Output: default@locations_n1
POSTHOOK: Lineage: locations_n1.locationid SCRIPT []
POSTHOOK: Lineage: locations_n1.name SCRIPT []
-PREHOOK: query: analyze table locations_n1 compute statistics for columns
-PREHOOK: type: ANALYZE_TABLE
-PREHOOK: Input: default@locations_n1
-PREHOOK: Output: default@locations_n1
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table locations_n1 compute statistics for columns
-POSTHOOK: type: ANALYZE_TABLE
-POSTHOOK: Input: default@locations_n1
-POSTHOOK: Output: default@locations_n1
-#### A masked pattern was here ####
PREHOOK: query: alter table emps_n2 add constraint pk1 primary key (empid) disable novalidate rely
PREHOOK: type: ALTERTABLE_ADDCONSTRAINT
POSTHOOK: query: alter table emps_n2 add constraint pk1 primary key (empid) disable novalidate rely
@@ -200,16 +160,6 @@ POSTHOOK: type: CREATE_MATERIALIZED_VIEW
POSTHOOK: Input: default@emps_n2
POSTHOOK: Output: database:default
POSTHOOK: Output: default@mv1_n1
-PREHOOK: query: analyze table mv1_n1 compute statistics for columns
-PREHOOK: type: ANALYZE_TABLE
-PREHOOK: Input: default@mv1_n1
-PREHOOK: Output: default@mv1_n1
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table mv1_n1 compute statistics for columns
-POSTHOOK: type: ANALYZE_TABLE
-POSTHOOK: Input: default@mv1_n1
-POSTHOOK: Output: default@mv1_n1
-#### A masked pattern was here ####
PREHOOK: query: explain
select name from emps_n2 where deptno >= 20 group by name
PREHOOK: type: QUERY
@@ -314,16 +264,6 @@ POSTHOOK: type: CREATE_MATERIALIZED_VIEW
POSTHOOK: Input: default@emps_n2
POSTHOOK: Output: database:default
POSTHOOK: Output: default@mv1_n1
-PREHOOK: query: analyze table mv1_n1 compute statistics for columns
-PREHOOK: type: ANALYZE_TABLE
-PREHOOK: Input: default@mv1_n1
-PREHOOK: Output: default@mv1_n1
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table mv1_n1 compute statistics for columns
-POSTHOOK: type: ANALYZE_TABLE
-POSTHOOK: Input: default@mv1_n1
-POSTHOOK: Output: default@mv1_n1
-#### A masked pattern was here ####
PREHOOK: query: explain
select name, sum(empid) as s
from emps_n2 where deptno > 15 group by name
@@ -451,16 +391,6 @@ POSTHOOK: Input: default@emps_n2
POSTHOOK: Input: default@locations_n1
POSTHOOK: Output: database:default
POSTHOOK: Output: default@mv1_n1
-PREHOOK: query: analyze table mv1_n1 compute statistics for columns
-PREHOOK: type: ANALYZE_TABLE
-PREHOOK: Input: default@mv1_n1
-PREHOOK: Output: default@mv1_n1
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table mv1_n1 compute statistics for columns
-POSTHOOK: type: ANALYZE_TABLE
-POSTHOOK: Input: default@mv1_n1
-POSTHOOK: Output: default@mv1_n1
-#### A masked pattern was here ####
PREHOOK: query: explain
select dependents_n1.empid
from depts_n1
@@ -604,16 +534,6 @@ POSTHOOK: Input: default@depts_n1
POSTHOOK: Input: default@emps_n2
POSTHOOK: Output: database:default
POSTHOOK: Output: default@mv1_n1
-PREHOOK: query: analyze table mv1_n1 compute statistics for columns
-PREHOOK: type: ANALYZE_TABLE
-PREHOOK: Input: default@mv1_n1
-PREHOOK: Output: default@mv1_n1
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table mv1_n1 compute statistics for columns
-POSTHOOK: type: ANALYZE_TABLE
-POSTHOOK: Input: default@mv1_n1
-POSTHOOK: Output: default@mv1_n1
-#### A masked pattern was here ####
PREHOOK: query: explain
select deptno from emps_n2 group by deptno
PREHOOK: type: QUERY
@@ -719,16 +639,6 @@ POSTHOOK: Input: default@depts_n1
POSTHOOK: Input: default@emps_n2
POSTHOOK: Output: database:default
POSTHOOK: Output: default@mv1_n1
-PREHOOK: query: analyze table mv1_n1 compute statistics for columns
-PREHOOK: type: ANALYZE_TABLE
-PREHOOK: Input: default@mv1_n1
-PREHOOK: Output: default@mv1_n1
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table mv1_n1 compute statistics for columns
-POSTHOOK: type: ANALYZE_TABLE
-POSTHOOK: Input: default@mv1_n1
-POSTHOOK: Output: default@mv1_n1
-#### A masked pattern was here ####
PREHOOK: query: explain
select deptno, empid, sum(empid) as s, count(*) as c
from emps_n2 group by empid, deptno
@@ -803,16 +713,6 @@ POSTHOOK: Input: default@dependents_n1
POSTHOOK: Input: default@emps_n2
POSTHOOK: Output: database:default
POSTHOOK: Output: default@mv1_n1
-PREHOOK: query: analyze table mv1_n1 compute statistics for columns
-PREHOOK: type: ANALYZE_TABLE
-PREHOOK: Input: default@mv1_n1
-PREHOOK: Output: default@mv1_n1
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table mv1_n1 compute statistics for columns
-POSTHOOK: type: ANALYZE_TABLE
-POSTHOOK: Input: default@mv1_n1
-POSTHOOK: Output: default@mv1_n1
-#### A masked pattern was here ####
PREHOOK: query: explain
select dependents_n1.empid, sum(salary) as s
from emps_n2
@@ -945,16 +845,6 @@ POSTHOOK: Input: default@dependents_n1
POSTHOOK: Input: default@emps_n2
POSTHOOK: Output: database:default
POSTHOOK: Output: default@mv1_n1
-PREHOOK: query: analyze table mv1_n1 compute statistics for columns
-PREHOOK: type: ANALYZE_TABLE
-PREHOOK: Input: default@mv1_n1
-PREHOOK: Output: default@mv1_n1
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table mv1_n1 compute statistics for columns
-POSTHOOK: type: ANALYZE_TABLE
-POSTHOOK: Input: default@mv1_n1
-POSTHOOK: Output: default@mv1_n1
-#### A masked pattern was here ####
PREHOOK: query: explain
select depts_n1.name, sum(salary) as s
from emps_n2
@@ -1102,7 +992,7 @@ POSTHOOK: query: drop materialized view mv1_n1
POSTHOOK: type: DROP_MATERIALIZED_VIEW
POSTHOOK: Input: default@mv1_n1
POSTHOOK: Output: default@mv1_n1
-Warning: Shuffle Join MERGEJOIN[13][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product
+Warning: Shuffle Join MERGEJOIN[23][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product
PREHOOK: query: create materialized view mv1_n1 as
select a.empid deptno from
(select * from emps_n2 where empid = 1) a
@@ -1125,16 +1015,6 @@ POSTHOOK: Input: default@depts_n1
POSTHOOK: Input: default@emps_n2
POSTHOOK: Output: database:default
POSTHOOK: Output: default@mv1_n1
-PREHOOK: query: analyze table mv1_n1 compute statistics for columns
-PREHOOK: type: ANALYZE_TABLE
-PREHOOK: Input: default@mv1_n1
-PREHOOK: Output: default@mv1_n1
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table mv1_n1 compute statistics for columns
-POSTHOOK: type: ANALYZE_TABLE
-POSTHOOK: Input: default@mv1_n1
-POSTHOOK: Output: default@mv1_n1
-#### A masked pattern was here ####
PREHOOK: query: explain
select a.empid from
(select * from emps_n2 where empid = 1) a
@@ -1192,7 +1072,7 @@ POSTHOOK: query: drop materialized view mv1_n1
POSTHOOK: type: DROP_MATERIALIZED_VIEW
POSTHOOK: Input: default@mv1_n1
POSTHOOK: Output: default@mv1_n1
-Warning: Shuffle Join MERGEJOIN[13][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product
+Warning: Shuffle Join MERGEJOIN[23][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product
PREHOOK: query: create materialized view mv1_n1 as
select a.empid, a.deptno from
(select * from emps_n2 where empid = 1) a
@@ -1215,16 +1095,6 @@ POSTHOOK: Input: default@depts_n1
POSTHOOK: Input: default@emps_n2
POSTHOOK: Output: database:default
POSTHOOK: Output: default@mv1_n1
-PREHOOK: query: analyze table mv1_n1 compute statistics for columns
-PREHOOK: type: ANALYZE_TABLE
-PREHOOK: Input: default@mv1_n1
-PREHOOK: Output: default@mv1_n1
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table mv1_n1 compute statistics for columns
-POSTHOOK: type: ANALYZE_TABLE
-POSTHOOK: Input: default@mv1_n1
-POSTHOOK: Output: default@mv1_n1
-#### A masked pattern was here ####
PREHOOK: query: explain
select a.empid from
(select * from emps_n2 where empid = 1) a
@@ -1300,16 +1170,6 @@ POSTHOOK: Input: default@depts_n1
POSTHOOK: Input: default@emps_n2
POSTHOOK: Output: database:default
POSTHOOK: Output: default@mv1_n1
-PREHOOK: query: analyze table mv1_n1 compute statistics for columns
-PREHOOK: type: ANALYZE_TABLE
-PREHOOK: Input: default@mv1_n1
-PREHOOK: Output: default@mv1_n1
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table mv1_n1 compute statistics for columns
-POSTHOOK: type: ANALYZE_TABLE
-POSTHOOK: Input: default@mv1_n1
-POSTHOOK: Output: default@mv1_n1
-#### A masked pattern was here ####
PREHOOK: query: explain
select empid from emps_n2 where empid = 1
PREHOOK: type: QUERY
@@ -1355,7 +1215,7 @@ POSTHOOK: query: drop materialized view mv1_n1
POSTHOOK: type: DROP_MATERIALIZED_VIEW
POSTHOOK: Input: default@mv1_n1
POSTHOOK: Output: default@mv1_n1
-Warning: Shuffle Join MERGEJOIN[13][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product
+Warning: Shuffle Join MERGEJOIN[23][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product
PREHOOK: query: create materialized view mv1_n1 as
select emps_n2.empid, emps_n2.deptno from emps_n2
join depts_n1 on (emps_n2.deptno = depts_n1.deptno)
@@ -1378,16 +1238,6 @@ POSTHOOK: Input: default@depts_n1
POSTHOOK: Input: default@emps_n2
POSTHOOK: Output: database:default
POSTHOOK: Output: default@mv1_n1
-PREHOOK: query: analyze table mv1_n1 compute statistics for columns
-PREHOOK: type: ANALYZE_TABLE
-PREHOOK: Input: default@mv1_n1
-PREHOOK: Output: default@mv1_n1
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table mv1_n1 compute statistics for columns
-POSTHOOK: type: ANALYZE_TABLE
-POSTHOOK: Input: default@mv1_n1
-POSTHOOK: Output: default@mv1_n1
-#### A masked pattern was here ####
PREHOOK: query: explain
select emps_n2.empid from emps_n2
join dependents_n1 on (emps_n2.empid = dependents_n1.empid)
@@ -1445,7 +1295,7 @@ POSTHOOK: query: drop materialized view mv1_n1
POSTHOOK: type: DROP_MATERIALIZED_VIEW
POSTHOOK: Input: default@mv1_n1
POSTHOOK: Output: default@mv1_n1
-Warning: Shuffle Join MERGEJOIN[13][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product
+Warning: Shuffle Join MERGEJOIN[23][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product
PREHOOK: query: create materialized view mv1_n1 as
select emps_n2.empid, emps_n2.deptno from emps_n2
join depts_n1 a on (emps_n2.deptno=a.deptno)
@@ -1470,16 +1320,6 @@ POSTHOOK: Input: default@depts_n1
POSTHOOK: Input: default@emps_n2
POSTHOOK: Output: database:default
POSTHOOK: Output: default@mv1_n1
-PREHOOK: query: analyze table mv1_n1 compute statistics for columns
-PREHOOK: type: ANALYZE_TABLE
-PREHOOK: Input: default@mv1_n1
-PREHOOK: Output: default@mv1_n1
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table mv1_n1 compute statistics for columns
-POSTHOOK: type: ANALYZE_TABLE
-POSTHOOK: Input: default@mv1_n1
-POSTHOOK: Output: default@mv1_n1
-#### A masked pattern was here ####
PREHOOK: query: explain
select emps_n2.empid from emps_n2
join dependents_n1 on (emps_n2.empid = dependents_n1.empid)
@@ -1561,16 +1401,6 @@ POSTHOOK: Input: default@depts_n1
POSTHOOK: Input: default@emps_n2
POSTHOOK: Output: database:default
POSTHOOK: Output: default@mv1_n1
-PREHOOK: query: analyze table mv1_n1 compute statistics for columns
-PREHOOK: type: ANALYZE_TABLE
-PREHOOK: Input: default@mv1_n1
-PREHOOK: Output: default@mv1_n1
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table mv1_n1 compute statistics for columns
-POSTHOOK: type: ANALYZE_TABLE
-POSTHOOK: Input: default@mv1_n1
-POSTHOOK: Output: default@mv1_n1
-#### A masked pattern was here ####
PREHOOK: query: explain
select emps_n2.empid from emps_n2
join dependents_n1 on (emps_n2.empid = dependents_n1.empid)
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/llap/materialized_view_rewrite_6.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/materialized_view_rewrite_6.q.out b/ql/src/test/results/clientpositive/llap/materialized_view_rewrite_6.q.out
index 899e50a..b66cd57 100644
--- a/ql/src/test/results/clientpositive/llap/materialized_view_rewrite_6.q.out
+++ b/ql/src/test/results/clientpositive/llap/materialized_view_rewrite_6.q.out
@@ -33,16 +33,6 @@ POSTHOOK: Lineage: emps.deptno SCRIPT []
POSTHOOK: Lineage: emps.empid SCRIPT []
POSTHOOK: Lineage: emps.name SCRIPT []
POSTHOOK: Lineage: emps.salary SCRIPT []
-PREHOOK: query: analyze table emps compute statistics for columns
-PREHOOK: type: ANALYZE_TABLE
-PREHOOK: Input: default@emps
-PREHOOK: Output: default@emps
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table emps compute statistics for columns
-POSTHOOK: type: ANALYZE_TABLE
-POSTHOOK: Input: default@emps
-POSTHOOK: Output: default@emps
-#### A masked pattern was here ####
PREHOOK: query: create table depts (
deptno int,
name varchar(256),
@@ -70,16 +60,6 @@ POSTHOOK: Output: default@depts
POSTHOOK: Lineage: depts.deptno SCRIPT []
POSTHOOK: Lineage: depts.locationid SCRIPT []
POSTHOOK: Lineage: depts.name SCRIPT []
-PREHOOK: query: analyze table depts compute statistics for columns
-PREHOOK: type: ANALYZE_TABLE
-PREHOOK: Input: default@depts
-PREHOOK: Output: default@depts
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table depts compute statistics for columns
-POSTHOOK: type: ANALYZE_TABLE
-POSTHOOK: Input: default@depts
-POSTHOOK: Output: default@depts
-#### A masked pattern was here ####
PREHOOK: query: create table dependents (
empid int,
name varchar(256))
@@ -104,16 +84,6 @@ POSTHOOK: Input: _dummy_database@_dummy_table
POSTHOOK: Output: default@dependents
POSTHOOK: Lineage: dependents.empid SCRIPT []
POSTHOOK: Lineage: dependents.name SCRIPT []
-PREHOOK: query: analyze table dependents compute statistics for columns
-PREHOOK: type: ANALYZE_TABLE
-PREHOOK: Input: default@dependents
-PREHOOK: Output: default@dependents
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table dependents compute statistics for columns
-POSTHOOK: type: ANALYZE_TABLE
-POSTHOOK: Input: default@dependents
-POSTHOOK: Output: default@dependents
-#### A masked pattern was here ####
PREHOOK: query: create table locations (
locationid int,
name varchar(256))
@@ -138,16 +108,6 @@ POSTHOOK: Input: _dummy_database@_dummy_table
POSTHOOK: Output: default@locations
POSTHOOK: Lineage: locations.locationid SCRIPT []
POSTHOOK: Lineage: locations.name SCRIPT []
-PREHOOK: query: analyze table locations compute statistics for columns
-PREHOOK: type: ANALYZE_TABLE
-PREHOOK: Input: default@locations
-PREHOOK: Output: default@locations
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table locations compute statistics for columns
-POSTHOOK: type: ANALYZE_TABLE
-POSTHOOK: Input: default@locations
-POSTHOOK: Output: default@locations
-#### A masked pattern was here ####
PREHOOK: query: alter table emps add constraint pk1 primary key (empid) disable novalidate rely
PREHOOK: type: ALTERTABLE_ADDCONSTRAINT
POSTHOOK: query: alter table emps add constraint pk1 primary key (empid) disable novalidate rely
@@ -202,16 +162,6 @@ POSTHOOK: type: CREATE_MATERIALIZED_VIEW
POSTHOOK: Input: default@emps
POSTHOOK: Output: database:default
POSTHOOK: Output: default@mv1
-PREHOOK: query: analyze table mv1 compute statistics for columns
-PREHOOK: type: ANALYZE_TABLE
-PREHOOK: Input: default@mv1
-PREHOOK: Output: default@mv1
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table mv1 compute statistics for columns
-POSTHOOK: type: ANALYZE_TABLE
-POSTHOOK: Input: default@mv1
-POSTHOOK: Output: default@mv1
-#### A masked pattern was here ####
PREHOOK: query: explain
select salary, sum(empid) + 1 as s
from emps where deptno > 10 group by salary
@@ -327,16 +277,6 @@ POSTHOOK: type: CREATE_MATERIALIZED_VIEW
POSTHOOK: Input: default@emps
POSTHOOK: Output: database:default
POSTHOOK: Output: default@mv1
-PREHOOK: query: analyze table mv1 compute statistics for columns
-PREHOOK: type: ANALYZE_TABLE
-PREHOOK: Input: default@mv1
-PREHOOK: Output: default@mv1
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table mv1 compute statistics for columns
-POSTHOOK: type: ANALYZE_TABLE
-POSTHOOK: Input: default@mv1
-POSTHOOK: Output: default@mv1
-#### A masked pattern was here ####
PREHOOK: query: explain
select salary + 1, sum(empid) + 1 as s
from emps where deptno > 15 group by salary
@@ -456,16 +396,6 @@ POSTHOOK: Input: default@depts
POSTHOOK: Input: default@emps
POSTHOOK: Output: database:default
POSTHOOK: Output: default@mv1
-PREHOOK: query: analyze table mv1 compute statistics for columns
-PREHOOK: type: ANALYZE_TABLE
-PREHOOK: Input: default@mv1
-PREHOOK: Output: default@mv1
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table mv1 compute statistics for columns
-POSTHOOK: type: ANALYZE_TABLE
-POSTHOOK: Input: default@mv1
-POSTHOOK: Output: default@mv1
-#### A masked pattern was here ####
PREHOOK: query: explain
select dependents.empid
from emps
@@ -616,16 +546,6 @@ POSTHOOK: Input: default@depts
POSTHOOK: Input: default@emps
POSTHOOK: Output: database:default
POSTHOOK: Output: default@mv1
-PREHOOK: query: analyze table mv1 compute statistics for columns
-PREHOOK: type: ANALYZE_TABLE
-PREHOOK: Input: default@mv1
-PREHOOK: Output: default@mv1
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table mv1 compute statistics for columns
-POSTHOOK: type: ANALYZE_TABLE
-POSTHOOK: Input: default@mv1
-POSTHOOK: Output: default@mv1
-#### A masked pattern was here ####
PREHOOK: query: explain
select dependents.empid
from depts
@@ -804,16 +724,6 @@ POSTHOOK: Input: default@dependents
POSTHOOK: Input: default@emps
POSTHOOK: Output: database:default
POSTHOOK: Output: default@mv1
-PREHOOK: query: analyze table mv1 compute statistics for columns
-PREHOOK: type: ANALYZE_TABLE
-PREHOOK: Input: default@mv1
-PREHOOK: Output: default@mv1
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table mv1 compute statistics for columns
-POSTHOOK: type: ANALYZE_TABLE
-POSTHOOK: Input: default@mv1
-POSTHOOK: Output: default@mv1
-#### A masked pattern was here ####
PREHOOK: query: explain
select emps.empid, dependents.empid, emps.deptno
from emps
[24/35] hive git commit: HIVE-16957: Support CTAS for auto gather
column stats (Jesus Camacho Rodriguez, reviewed by Ashutosh Chauhan)
Posted by jc...@apache.org.
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/llap/materialized_view_rewrite_ssb.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/materialized_view_rewrite_ssb.q.out b/ql/src/test/results/clientpositive/llap/materialized_view_rewrite_ssb.q.out
index f6aadd5..d98a9b6 100644
--- a/ql/src/test/results/clientpositive/llap/materialized_view_rewrite_ssb.q.out
+++ b/ql/src/test/results/clientpositive/llap/materialized_view_rewrite_ssb.q.out
@@ -528,56 +528,6 @@ POSTHOOK: Lineage: lineorder_n0.lo_shippriority SIMPLE [(lineorder_ext_n0)lineor
POSTHOOK: Lineage: lineorder_n0.lo_suppkey SIMPLE [(lineorder_ext_n0)lineorder_ext_n0.FieldSchema(name:lo_suppkey, type:bigint, comment:null), ]
POSTHOOK: Lineage: lineorder_n0.lo_supplycost SIMPLE [(lineorder_ext_n0)lineorder_ext_n0.FieldSchema(name:lo_supplycost, type:double, comment:null), ]
POSTHOOK: Lineage: lineorder_n0.lo_tax SIMPLE [(lineorder_ext_n0)lineorder_ext_n0.FieldSchema(name:lo_tax, type:double, comment:null), ]
-PREHOOK: query: analyze table customer_n1 compute statistics for columns
-PREHOOK: type: ANALYZE_TABLE
-PREHOOK: Input: default@customer_n1
-PREHOOK: Output: default@customer_n1
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table customer_n1 compute statistics for columns
-POSTHOOK: type: ANALYZE_TABLE
-POSTHOOK: Input: default@customer_n1
-POSTHOOK: Output: default@customer_n1
-#### A masked pattern was here ####
-PREHOOK: query: analyze table dates_n0 compute statistics for columns
-PREHOOK: type: ANALYZE_TABLE
-PREHOOK: Input: default@dates_n0
-PREHOOK: Output: default@dates_n0
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table dates_n0 compute statistics for columns
-POSTHOOK: type: ANALYZE_TABLE
-POSTHOOK: Input: default@dates_n0
-POSTHOOK: Output: default@dates_n0
-#### A masked pattern was here ####
-PREHOOK: query: analyze table ssb_part_n0 compute statistics for columns
-PREHOOK: type: ANALYZE_TABLE
-PREHOOK: Input: default@ssb_part_n0
-PREHOOK: Output: default@ssb_part_n0
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table ssb_part_n0 compute statistics for columns
-POSTHOOK: type: ANALYZE_TABLE
-POSTHOOK: Input: default@ssb_part_n0
-POSTHOOK: Output: default@ssb_part_n0
-#### A masked pattern was here ####
-PREHOOK: query: analyze table supplier_n0 compute statistics for columns
-PREHOOK: type: ANALYZE_TABLE
-PREHOOK: Input: default@supplier_n0
-PREHOOK: Output: default@supplier_n0
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table supplier_n0 compute statistics for columns
-POSTHOOK: type: ANALYZE_TABLE
-POSTHOOK: Input: default@supplier_n0
-POSTHOOK: Output: default@supplier_n0
-#### A masked pattern was here ####
-PREHOOK: query: analyze table lineorder_n0 compute statistics for columns
-PREHOOK: type: ANALYZE_TABLE
-PREHOOK: Input: default@lineorder_n0
-PREHOOK: Output: default@lineorder_n0
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table lineorder_n0 compute statistics for columns
-POSTHOOK: type: ANALYZE_TABLE
-POSTHOOK: Input: default@lineorder_n0
-POSTHOOK: Output: default@lineorder_n0
-#### A masked pattern was here ####
PREHOOK: query: CREATE MATERIALIZED VIEW `ssb_mv_n0`
AS
SELECT
@@ -697,22 +647,22 @@ STAGE PLANS:
TableScan
alias: default.ssb_mv_n0
filterExpr: ((d_year = 1993) and (lo_quantity < 25.0D) and lo_discount BETWEEN 1.0D AND 3.0D) (type: boolean)
- Statistics: Num rows: 1 Data size: 28 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: ((d_year = 1993) and (lo_quantity < 25.0D) and lo_discount BETWEEN 1.0D AND 3.0D) (type: boolean)
- Statistics: Num rows: 1 Data size: 28 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: discounted_price (type: double)
outputColumnNames: discounted_price
- Statistics: Num rows: 1 Data size: 28 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: sum(discounted_price)
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 36 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
- Statistics: Num rows: 1 Data size: 36 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: double)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -723,10 +673,10 @@ STAGE PLANS:
aggregations: sum(VALUE._col0)
mode: mergepartial
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 36 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 36 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -785,22 +735,22 @@ STAGE PLANS:
TableScan
alias: default.ssb_mv_n0
filterExpr: ((d_yearmonthnum = 199401) and lo_discount BETWEEN 4.0D AND 6.0D and lo_quantity BETWEEN 26.0D AND 35.0D) (type: boolean)
- Statistics: Num rows: 1 Data size: 28 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: ((d_yearmonthnum = 199401) and lo_discount BETWEEN 4.0D AND 6.0D and lo_quantity BETWEEN 26.0D AND 35.0D) (type: boolean)
- Statistics: Num rows: 1 Data size: 28 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: discounted_price (type: double)
outputColumnNames: discounted_price
- Statistics: Num rows: 1 Data size: 28 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: sum(discounted_price)
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 36 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
- Statistics: Num rows: 1 Data size: 36 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: double)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -811,10 +761,10 @@ STAGE PLANS:
aggregations: sum(VALUE._col0)
mode: mergepartial
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 36 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 36 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -875,22 +825,22 @@ STAGE PLANS:
TableScan
alias: default.ssb_mv_n0
filterExpr: ((d_year = 1994) and (d_weeknuminyear = 6) and lo_discount BETWEEN 5.0D AND 7.0D and lo_quantity BETWEEN 26.0D AND 35.0D) (type: boolean)
- Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: ((d_weeknuminyear = 6) and (d_year = 1994) and lo_discount BETWEEN 5.0D AND 7.0D and lo_quantity BETWEEN 26.0D AND 35.0D) (type: boolean)
- Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: discounted_price (type: double)
outputColumnNames: discounted_price
- Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: sum(discounted_price)
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 40 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
- Statistics: Num rows: 1 Data size: 40 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: double)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -901,10 +851,10 @@ STAGE PLANS:
aggregations: sum(VALUE._col0)
mode: mergepartial
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 40 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 40 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -978,25 +928,25 @@ STAGE PLANS:
TableScan
alias: default.ssb_mv_n0
filterExpr: ((p_category = 'MFGR#12') and (s_region = 'AMERICA')) (type: boolean)
- Statistics: Num rows: 1 Data size: 564 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 264 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: ((p_category = 'MFGR#12') and (s_region = 'AMERICA')) (type: boolean)
- Statistics: Num rows: 1 Data size: 564 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 264 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: d_year (type: int), p_brand1 (type: string), lo_revenue (type: double)
outputColumnNames: d_year, p_brand1, lo_revenue
- Statistics: Num rows: 1 Data size: 564 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 264 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: sum(lo_revenue)
keys: d_year (type: int), p_brand1 (type: string)
mode: hash
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 1 Data size: 564 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int), _col1 (type: string)
sort order: ++
Map-reduce partition columns: _col0 (type: int), _col1 (type: string)
- Statistics: Num rows: 1 Data size: 564 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col2 (type: double)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -1008,15 +958,15 @@ STAGE PLANS:
keys: KEY._col0 (type: int), KEY._col1 (type: string)
mode: mergepartial
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 1 Data size: 564 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col2 (type: double), _col0 (type: int), _col1 (type: string)
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 1 Data size: 564 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col1 (type: int), _col2 (type: string)
sort order: ++
- Statistics: Num rows: 1 Data size: 564 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: double)
Reducer 3
Execution mode: vectorized, llap
@@ -1024,10 +974,10 @@ STAGE PLANS:
Select Operator
expressions: VALUE._col0 (type: double), KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: string)
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 1 Data size: 564 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 564 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -1101,25 +1051,25 @@ STAGE PLANS:
TableScan
alias: default.ssb_mv_n0
filterExpr: ((s_region = 'ASIA') and p_brand1 BETWEEN 'MFGR#2221' AND 'MFGR#2228') (type: boolean)
- Statistics: Num rows: 1 Data size: 380 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: ((s_region = 'ASIA') and p_brand1 BETWEEN 'MFGR#2221' AND 'MFGR#2228') (type: boolean)
- Statistics: Num rows: 1 Data size: 380 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: d_year (type: int), p_brand1 (type: string), lo_revenue (type: double)
outputColumnNames: d_year, p_brand1, lo_revenue
- Statistics: Num rows: 1 Data size: 380 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: sum(lo_revenue)
keys: d_year (type: int), p_brand1 (type: string)
mode: hash
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 1 Data size: 380 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int), _col1 (type: string)
sort order: ++
Map-reduce partition columns: _col0 (type: int), _col1 (type: string)
- Statistics: Num rows: 1 Data size: 380 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col2 (type: double)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -1131,15 +1081,15 @@ STAGE PLANS:
keys: KEY._col0 (type: int), KEY._col1 (type: string)
mode: mergepartial
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 1 Data size: 380 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col2 (type: double), _col0 (type: int), _col1 (type: string)
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 1 Data size: 380 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col1 (type: int), _col2 (type: string)
sort order: ++
- Statistics: Num rows: 1 Data size: 380 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: double)
Reducer 3
Execution mode: vectorized, llap
@@ -1147,10 +1097,10 @@ STAGE PLANS:
Select Operator
expressions: VALUE._col0 (type: double), KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: string)
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 1 Data size: 380 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 380 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -1224,25 +1174,25 @@ STAGE PLANS:
TableScan
alias: default.ssb_mv_n0
filterExpr: ((p_brand1 = 'MFGR#2239') and (s_region = 'EUROPE')) (type: boolean)
- Statistics: Num rows: 1 Data size: 380 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: ((p_brand1 = 'MFGR#2239') and (s_region = 'EUROPE')) (type: boolean)
- Statistics: Num rows: 1 Data size: 380 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: d_year (type: int), lo_revenue (type: double)
outputColumnNames: d_year, lo_revenue
- Statistics: Num rows: 1 Data size: 380 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: sum(lo_revenue)
keys: d_year (type: int)
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 380 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 1 Data size: 380 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: double)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -1254,15 +1204,15 @@ STAGE PLANS:
keys: KEY._col0 (type: int)
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 380 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col1 (type: double), _col0 (type: int)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 380 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col1 (type: int)
sort order: +
- Statistics: Num rows: 1 Data size: 380 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: double)
Reducer 3
Execution mode: vectorized, llap
@@ -1270,10 +1220,10 @@ STAGE PLANS:
Select Operator
expressions: VALUE._col0 (type: double), KEY.reducesinkkey0 (type: int), 'MFGR#2239' (type: string)
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 1 Data size: 380 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 105 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 380 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 105 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -1351,25 +1301,25 @@ STAGE PLANS:
TableScan
alias: default.ssb_mv_n0
filterExpr: ((d_year >= 1992) and (c_region = 'ASIA') and (s_region = 'ASIA') and (d_year <= 1997)) (type: boolean)
- Statistics: Num rows: 1 Data size: 748 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 348 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: ((c_region = 'ASIA') and (d_year <= 1997) and (d_year >= 1992) and (s_region = 'ASIA')) (type: boolean)
- Statistics: Num rows: 1 Data size: 748 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 348 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: c_nation (type: string), d_year (type: int), s_nation (type: string), lo_revenue (type: double)
outputColumnNames: c_nation, d_year, s_nation, lo_revenue
- Statistics: Num rows: 1 Data size: 748 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 348 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: sum(lo_revenue)
keys: d_year (type: int), c_nation (type: string), s_nation (type: string)
mode: hash
outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 1 Data size: 748 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string)
sort order: +++
Map-reduce partition columns: _col0 (type: int), _col1 (type: string), _col2 (type: string)
- Statistics: Num rows: 1 Data size: 748 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col3 (type: double)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -1381,15 +1331,15 @@ STAGE PLANS:
keys: KEY._col0 (type: int), KEY._col1 (type: string), KEY._col2 (type: string)
mode: mergepartial
outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 1 Data size: 748 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col1 (type: string), _col2 (type: string), _col0 (type: int), _col3 (type: double)
outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 1 Data size: 748 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col2 (type: int), _col3 (type: double)
sort order: +-
- Statistics: Num rows: 1 Data size: 748 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: string), _col1 (type: string)
Reducer 3
Execution mode: vectorized, llap
@@ -1397,10 +1347,10 @@ STAGE PLANS:
Select Operator
expressions: VALUE._col0 (type: string), VALUE._col1 (type: string), KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: double)
outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 1 Data size: 748 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 748 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -1476,25 +1426,25 @@ STAGE PLANS:
TableScan
alias: default.ssb_mv_n0
filterExpr: ((d_year >= 1992) and (c_nation = 'UNITED STATES') and (s_nation = 'UNITED STATES') and (d_year <= 1997)) (type: boolean)
- Statistics: Num rows: 1 Data size: 748 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 348 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: ((c_nation = 'UNITED STATES') and (d_year <= 1997) and (d_year >= 1992) and (s_nation = 'UNITED STATES')) (type: boolean)
- Statistics: Num rows: 1 Data size: 748 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 348 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: c_city (type: string), d_year (type: int), s_city (type: string), lo_revenue (type: double)
outputColumnNames: c_city, d_year, s_city, lo_revenue
- Statistics: Num rows: 1 Data size: 748 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 348 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: sum(lo_revenue)
keys: d_year (type: int), c_city (type: string), s_city (type: string)
mode: hash
outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 1 Data size: 748 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string)
sort order: +++
Map-reduce partition columns: _col0 (type: int), _col1 (type: string), _col2 (type: string)
- Statistics: Num rows: 1 Data size: 748 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col3 (type: double)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -1506,15 +1456,15 @@ STAGE PLANS:
keys: KEY._col0 (type: int), KEY._col1 (type: string), KEY._col2 (type: string)
mode: mergepartial
outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 1 Data size: 748 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col1 (type: string), _col2 (type: string), _col0 (type: int), _col3 (type: double)
outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 1 Data size: 748 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col2 (type: int), _col3 (type: double)
sort order: +-
- Statistics: Num rows: 1 Data size: 748 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: string), _col1 (type: string)
Reducer 3
Execution mode: vectorized, llap
@@ -1522,10 +1472,10 @@ STAGE PLANS:
Select Operator
expressions: VALUE._col0 (type: string), VALUE._col1 (type: string), KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: double)
outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 1 Data size: 748 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 748 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -1601,21 +1551,21 @@ STAGE PLANS:
TableScan
alias: default.ssb_mv_n0
filterExpr: ((c_city) IN ('UNITED KI1', 'UNITED KI5') and (s_city) IN ('UNITED KI1', 'UNITED KI5') and (d_year >= 1992) and (d_year <= 1997)) (type: boolean)
- Statistics: Num rows: 1 Data size: 380 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: ((c_city) IN ('UNITED KI1', 'UNITED KI5') and (d_year <= 1997) and (d_year >= 1992) and (s_city) IN ('UNITED KI1', 'UNITED KI5')) (type: boolean)
- Statistics: Num rows: 1 Data size: 380 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: sum(lo_revenue)
keys: d_year (type: int), c_city (type: string), s_city (type: string)
mode: hash
outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 1 Data size: 380 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string)
sort order: +++
Map-reduce partition columns: _col0 (type: int), _col1 (type: string), _col2 (type: string)
- Statistics: Num rows: 1 Data size: 380 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col3 (type: double)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -1627,15 +1577,15 @@ STAGE PLANS:
keys: KEY._col0 (type: int), KEY._col1 (type: string), KEY._col2 (type: string)
mode: mergepartial
outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 1 Data size: 380 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col1 (type: string), _col2 (type: string), _col0 (type: int), _col3 (type: double)
outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 1 Data size: 380 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col2 (type: int), _col3 (type: double)
sort order: +-
- Statistics: Num rows: 1 Data size: 380 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: string), _col1 (type: string)
Reducer 3
Execution mode: vectorized, llap
@@ -1643,10 +1593,10 @@ STAGE PLANS:
Select Operator
expressions: VALUE._col0 (type: string), VALUE._col1 (type: string), KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: double)
outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 1 Data size: 380 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 380 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -1722,25 +1672,25 @@ STAGE PLANS:
TableScan
alias: default.ssb_mv_n0
filterExpr: ((c_city) IN ('UNITED KI1', 'UNITED KI5') and (s_city) IN ('UNITED KI1', 'UNITED KI5') and (d_yearmonth = 'Dec1997')) (type: boolean)
- Statistics: Num rows: 1 Data size: 564 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 264 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: ((c_city) IN ('UNITED KI1', 'UNITED KI5') and (d_yearmonth = 'Dec1997') and (s_city) IN ('UNITED KI1', 'UNITED KI5')) (type: boolean)
- Statistics: Num rows: 1 Data size: 564 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 264 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: c_city (type: string), d_year (type: int), s_city (type: string), lo_revenue (type: double)
outputColumnNames: c_city, d_year, s_city, lo_revenue
- Statistics: Num rows: 1 Data size: 564 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 264 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: sum(lo_revenue)
keys: d_year (type: int), c_city (type: string), s_city (type: string)
mode: hash
outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 1 Data size: 564 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string)
sort order: +++
Map-reduce partition columns: _col0 (type: int), _col1 (type: string), _col2 (type: string)
- Statistics: Num rows: 1 Data size: 564 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col3 (type: double)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -1752,15 +1702,15 @@ STAGE PLANS:
keys: KEY._col0 (type: int), KEY._col1 (type: string), KEY._col2 (type: string)
mode: mergepartial
outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 1 Data size: 564 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col1 (type: string), _col2 (type: string), _col0 (type: int), _col3 (type: double)
outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 1 Data size: 564 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col2 (type: int), _col3 (type: double)
sort order: +-
- Statistics: Num rows: 1 Data size: 564 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: string), _col1 (type: string)
Reducer 3
Execution mode: vectorized, llap
@@ -1768,10 +1718,10 @@ STAGE PLANS:
Select Operator
expressions: VALUE._col0 (type: string), VALUE._col1 (type: string), KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: double)
outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 1 Data size: 564 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 564 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -1853,25 +1803,25 @@ STAGE PLANS:
TableScan
alias: default.ssb_mv_n0
filterExpr: ((p_mfgr) IN ('MFGR#1', 'MFGR#2') and (c_region = 'AMERICA') and (s_region = 'AMERICA')) (type: boolean)
- Statistics: Num rows: 1 Data size: 748 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 348 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: ((c_region = 'AMERICA') and (p_mfgr) IN ('MFGR#1', 'MFGR#2') and (s_region = 'AMERICA')) (type: boolean)
- Statistics: Num rows: 1 Data size: 748 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 348 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: c_nation (type: string), d_year (type: int), net_revenue (type: double)
outputColumnNames: c_nation, d_year, net_revenue
- Statistics: Num rows: 1 Data size: 748 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 348 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: sum(net_revenue)
keys: d_year (type: int), c_nation (type: string)
mode: hash
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 1 Data size: 748 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int), _col1 (type: string)
sort order: ++
Map-reduce partition columns: _col0 (type: int), _col1 (type: string)
- Statistics: Num rows: 1 Data size: 748 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col2 (type: double)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -1883,11 +1833,11 @@ STAGE PLANS:
keys: KEY._col0 (type: int), KEY._col1 (type: string)
mode: mergepartial
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 1 Data size: 748 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int), _col1 (type: string)
sort order: ++
- Statistics: Num rows: 1 Data size: 748 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col2 (type: double)
Reducer 3
Execution mode: vectorized, llap
@@ -1895,10 +1845,10 @@ STAGE PLANS:
Select Operator
expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: string), VALUE._col0 (type: double)
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 1 Data size: 748 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 748 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -1982,25 +1932,25 @@ STAGE PLANS:
TableScan
alias: default.ssb_mv_n0
filterExpr: ((d_year) IN (1997, 1998) and (p_mfgr) IN ('MFGR#1', 'MFGR#2') and (c_region = 'AMERICA') and (s_region = 'AMERICA')) (type: boolean)
- Statistics: Num rows: 1 Data size: 932 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 432 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: ((c_region = 'AMERICA') and (d_year) IN (1997, 1998) and (p_mfgr) IN ('MFGR#1', 'MFGR#2') and (s_region = 'AMERICA')) (type: boolean)
- Statistics: Num rows: 1 Data size: 932 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 432 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: d_year (type: int), p_category (type: string), s_nation (type: string), net_revenue (type: double)
outputColumnNames: d_year, p_category, s_nation, net_revenue
- Statistics: Num rows: 1 Data size: 932 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 432 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: sum(net_revenue)
keys: d_year (type: int), s_nation (type: string), p_category (type: string)
mode: hash
outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 1 Data size: 932 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string)
sort order: +++
Map-reduce partition columns: _col0 (type: int), _col1 (type: string), _col2 (type: string)
- Statistics: Num rows: 1 Data size: 932 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col3 (type: double)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -2012,11 +1962,11 @@ STAGE PLANS:
keys: KEY._col0 (type: int), KEY._col1 (type: string), KEY._col2 (type: string)
mode: mergepartial
outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 1 Data size: 932 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string)
sort order: +++
- Statistics: Num rows: 1 Data size: 932 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col3 (type: double)
Reducer 3
Execution mode: vectorized, llap
@@ -2024,10 +1974,10 @@ STAGE PLANS:
Select Operator
expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string), VALUE._col0 (type: double)
outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 1 Data size: 932 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 932 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -2111,25 +2061,25 @@ STAGE PLANS:
TableScan
alias: default.ssb_mv_n0
filterExpr: ((d_year) IN (1997, 1998) and (c_region = 'AMERICA') and (p_category = 'MFGR#14') and (s_nation = 'UNITED STATES')) (type: boolean)
- Statistics: Num rows: 1 Data size: 932 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 432 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: ((c_region = 'AMERICA') and (d_year) IN (1997, 1998) and (p_category = 'MFGR#14') and (s_nation = 'UNITED STATES')) (type: boolean)
- Statistics: Num rows: 1 Data size: 932 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 432 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: d_year (type: int), p_brand1 (type: string), s_city (type: string), net_revenue (type: double)
outputColumnNames: d_year, p_brand1, s_city, net_revenue
- Statistics: Num rows: 1 Data size: 932 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 432 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: sum(net_revenue)
keys: d_year (type: int), s_city (type: string), p_brand1 (type: string)
mode: hash
outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 1 Data size: 932 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string)
sort order: +++
Map-reduce partition columns: _col0 (type: int), _col1 (type: string), _col2 (type: string)
- Statistics: Num rows: 1 Data size: 932 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col3 (type: double)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -2141,11 +2091,11 @@ STAGE PLANS:
keys: KEY._col0 (type: int), KEY._col1 (type: string), KEY._col2 (type: string)
mode: mergepartial
outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 1 Data size: 932 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string)
sort order: +++
- Statistics: Num rows: 1 Data size: 932 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col3 (type: double)
Reducer 3
Execution mode: vectorized, llap
@@ -2153,10 +2103,10 @@ STAGE PLANS:
Select Operator
expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string), VALUE._col0 (type: double)
outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 1 Data size: 932 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 932 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
[30/35] hive git commit: HIVE-16957: Support CTAS for auto gather
column stats (Jesus Camacho Rodriguez, reviewed by Ashutosh Chauhan)
Posted by jc...@apache.org.
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/llap/dynamic_partition_pruning.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/dynamic_partition_pruning.q.out b/ql/src/test/results/clientpositive/llap/dynamic_partition_pruning.q.out
index 6954647..adf8011 100644
--- a/ql/src/test/results/clientpositive/llap/dynamic_partition_pruning.q.out
+++ b/ql/src/test/results/clientpositive/llap/dynamic_partition_pruning.q.out
@@ -55,7 +55,7 @@ POSTHOOK: Output: default@srcpart_date_n2
STAGE DEPENDENCIES:
Stage-1 is a root stage
Stage-2 depends on stages: Stage-1
- Stage-4 depends on stages: Stage-2, Stage-0
+ Stage-4 depends on stages: Stage-0, Stage-2
Stage-3 depends on stages: Stage-4
Stage-0 depends on stages: Stage-1
@@ -65,6 +65,7 @@ STAGE PLANS:
#### A masked pattern was here ####
Edges:
Reducer 2 <- Map 1 (SIMPLE_EDGE)
+ Reducer 3 <- Reducer 2 (CUSTOM_SIMPLE_EDGE)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -108,6 +109,34 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.srcpart_date_n2
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: string)
+ outputColumnNames: col1, col2
+ Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: COMPLETE
+ Group By Operator
+ aggregations: compute_stats(col1, 'hll'), compute_stats(col2, 'hll')
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col0 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>)
+ Reducer 3
+ Execution mode: llap
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
Stage: Stage-2
Dependency Collection
@@ -124,6 +153,10 @@ STAGE PLANS:
Stage: Stage-3
Stats Work
Basic Stats Work:
+ Column Stats Desc:
+ Columns: ds, date
+ Column Types: string, string
+ Table: default.srcpart_date_n2
Stage: Stage-0
Move Operator
@@ -266,33 +299,33 @@ STAGE PLANS:
TableScan
alias: srcpart_date_n2
filterExpr: ((date = '2008-04-08') and ds is not null) (type: boolean)
- Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 376 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: ((date = '2008-04-08') and ds is not null) (type: boolean)
- Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: ds (type: string)
outputColumnNames: _col0
- Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: string)
outputColumnNames: _col0
- Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
keys: _col0 (type: string)
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: COMPLETE
Dynamic Partitioning Event Operator
Target column: ds (string)
Target Input: srcpart
Partition key expr: ds
- Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: COMPLETE
Target Vertex: Map 1
Execution mode: llap
LLAP IO: no inputs
@@ -305,15 +338,15 @@ STAGE PLANS:
keys:
0 _col0 (type: string)
1 _col0 (type: string)
- Statistics: Num rows: 2200 Data size: 404800 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1000 Data size: 8000 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count()
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: bigint)
Reducer 3
Execution mode: llap
@@ -322,10 +355,10 @@ STAGE PLANS:
aggregations: count(VALUE._col0)
mode: mergepartial
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -409,19 +442,19 @@ STAGE PLANS:
TableScan
alias: srcpart_date_n2
filterExpr: ((date = '2008-04-08') and ds is not null) (type: boolean)
- Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 376 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: ((date = '2008-04-08') and ds is not null) (type: boolean)
- Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: ds (type: string)
outputColumnNames: _col0
- Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: llap
LLAP IO: no inputs
Reducer 2
@@ -433,15 +466,15 @@ STAGE PLANS:
keys:
0 _col0 (type: string)
1 _col0 (type: string)
- Statistics: Num rows: 2200 Data size: 404800 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1000 Data size: 8000 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count()
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: bigint)
Reducer 3
Execution mode: llap
@@ -450,10 +483,10 @@ STAGE PLANS:
aggregations: count(VALUE._col0)
mode: mergepartial
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -550,33 +583,33 @@ STAGE PLANS:
TableScan
alias: srcpart_date_n2
filterExpr: ((date = '2008-04-08') and ds is not null) (type: boolean)
- Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 376 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: ((date = '2008-04-08') and ds is not null) (type: boolean)
- Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: day(CAST( ds AS DATE)) (type: int)
outputColumnNames: _col0
- Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: int)
outputColumnNames: _col0
- Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
keys: _col0 (type: int)
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE
Dynamic Partitioning Event Operator
Target column: ds (string)
Target Input: srcpart
Partition key expr: day(CAST( ds AS DATE))
- Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE
Target Vertex: Map 1
Execution mode: llap
LLAP IO: no inputs
@@ -589,15 +622,15 @@ STAGE PLANS:
keys:
0 _col0 (type: int)
1 _col0 (type: int)
- Statistics: Num rows: 2200 Data size: 8800 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 64 Data size: 512 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count()
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: bigint)
Reducer 3
Execution mode: llap
@@ -606,10 +639,10 @@ STAGE PLANS:
aggregations: count(VALUE._col0)
mode: mergepartial
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -693,19 +726,19 @@ STAGE PLANS:
TableScan
alias: srcpart_date_n2
filterExpr: ((date = '2008-04-08') and ds is not null) (type: boolean)
- Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 376 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: ((date = '2008-04-08') and ds is not null) (type: boolean)
- Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: day(CAST( ds AS DATE)) (type: int)
outputColumnNames: _col0
- Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: llap
LLAP IO: no inputs
Reducer 2
@@ -717,15 +750,15 @@ STAGE PLANS:
keys:
0 _col0 (type: int)
1 _col0 (type: int)
- Statistics: Num rows: 2200 Data size: 8800 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 64 Data size: 512 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count()
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: bigint)
Reducer 3
Execution mode: llap
@@ -734,10 +767,10 @@ STAGE PLANS:
aggregations: count(VALUE._col0)
mode: mergepartial
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -826,33 +859,33 @@ STAGE PLANS:
TableScan
alias: srcpart_date_n2
filterExpr: ((date = '2008-04-08') and ds is not null) (type: boolean)
- Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 376 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: ((date = '2008-04-08') and ds is not null) (type: boolean)
- Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: ds (type: string)
outputColumnNames: _col0
- Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: string)
outputColumnNames: _col0
- Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
keys: _col0 (type: string)
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: COMPLETE
Dynamic Partitioning Event Operator
Target column: ds (string)
Target Input: srcpart
Partition key expr: ds
- Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: COMPLETE
Target Vertex: Map 1
Execution mode: llap
LLAP IO: no inputs
@@ -861,33 +894,33 @@ STAGE PLANS:
TableScan
alias: srcpart_hour_n0
filterExpr: ((UDFToDouble(hour) = 11.0D) and hr is not null) (type: boolean)
- Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 344 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: ((UDFToDouble(hour) = 11.0D) and hr is not null) (type: boolean)
- Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: hr (type: string)
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 86 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 86 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: string)
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 86 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
keys: _col0 (type: string)
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 86 Basic stats: COMPLETE Column stats: COMPLETE
Dynamic Partitioning Event Operator
Target column: hr (string)
Target Input: srcpart
Partition key expr: hr
- Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 86 Basic stats: COMPLETE Column stats: COMPLETE
Target Vertex: Map 1
Execution mode: llap
LLAP IO: no inputs
@@ -901,12 +934,12 @@ STAGE PLANS:
0 _col0 (type: string)
1 _col0 (type: string)
outputColumnNames: _col1
- Statistics: Num rows: 2200 Data size: 809600 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1000 Data size: 184000 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col1 (type: string)
sort order: +
Map-reduce partition columns: _col1 (type: string)
- Statistics: Num rows: 2200 Data size: 809600 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1000 Data size: 184000 Basic stats: COMPLETE Column stats: COMPLETE
Reducer 3
Execution mode: llap
Reduce Operator Tree:
@@ -916,15 +949,15 @@ STAGE PLANS:
keys:
0 _col1 (type: string)
1 _col0 (type: string)
- Statistics: Num rows: 2420 Data size: 890560 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1000 Data size: 8000 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count()
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: bigint)
Reducer 4
Execution mode: llap
@@ -933,10 +966,10 @@ STAGE PLANS:
aggregations: count(VALUE._col0)
mode: mergepartial
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -1030,19 +1063,19 @@ STAGE PLANS:
TableScan
alias: srcpart_date_n2
filterExpr: ((date = '2008-04-08') and ds is not null) (type: boolean)
- Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 376 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: ((date = '2008-04-08') and ds is not null) (type: boolean)
- Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: ds (type: string)
outputColumnNames: _col0
- Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: llap
LLAP IO: no inputs
Map 6
@@ -1050,19 +1083,19 @@ STAGE PLANS:
TableScan
alias: srcpart_hour_n0
filterExpr: ((UDFToDouble(hour) = 11.0D) and hr is not null) (type: boolean)
- Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 344 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: ((UDFToDouble(hour) = 11.0D) and hr is not null) (type: boolean)
- Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: hr (type: string)
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 86 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 86 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: llap
LLAP IO: no inputs
Reducer 2
@@ -1075,12 +1108,12 @@ STAGE PLANS:
0 _col0 (type: string)
1 _col0 (type: string)
outputColumnNames: _col1
- Statistics: Num rows: 2200 Data size: 809600 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1000 Data size: 184000 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col1 (type: string)
sort order: +
Map-reduce partition columns: _col1 (type: string)
- Statistics: Num rows: 2200 Data size: 809600 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1000 Data size: 184000 Basic stats: COMPLETE Column stats: COMPLETE
Reducer 3
Execution mode: llap
Reduce Operator Tree:
@@ -1090,15 +1123,15 @@ STAGE PLANS:
keys:
0 _col1 (type: string)
1 _col0 (type: string)
- Statistics: Num rows: 2420 Data size: 890560 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1000 Data size: 8000 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count()
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: bigint)
Reducer 4
Execution mode: llap
@@ -1107,10 +1140,10 @@ STAGE PLANS:
aggregations: count(VALUE._col0)
mode: mergepartial
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -1208,48 +1241,48 @@ STAGE PLANS:
TableScan
alias: srcpart_date_hour_n0
filterExpr: ((date = '2008-04-08') and (UDFToDouble(hour) = 11.0D) and ds is not null and hr is not null) (type: boolean)
- Statistics: Num rows: 4 Data size: 2944 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4 Data size: 1440 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: ((UDFToDouble(hour) = 11.0D) and (date = '2008-04-08') and ds is not null and hr is not null) (type: boolean)
- Statistics: Num rows: 2 Data size: 1472 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: ds (type: string), hr (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 2 Data size: 1472 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string), _col1 (type: string)
sort order: ++
Map-reduce partition columns: _col0 (type: string), _col1 (type: string)
- Statistics: Num rows: 2 Data size: 1472 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: string)
outputColumnNames: _col0
- Statistics: Num rows: 2 Data size: 1472 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
keys: _col0 (type: string)
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 2 Data size: 1472 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
Dynamic Partitioning Event Operator
Target column: ds (string)
Target Input: srcpart
Partition key expr: ds
- Statistics: Num rows: 2 Data size: 1472 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
Target Vertex: Map 1
Select Operator
expressions: _col1 (type: string)
outputColumnNames: _col0
- Statistics: Num rows: 2 Data size: 1472 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
keys: _col0 (type: string)
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 2 Data size: 1472 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
Dynamic Partitioning Event Operator
Target column: hr (string)
Target Input: srcpart
Partition key expr: hr
- Statistics: Num rows: 2 Data size: 1472 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
Target Vertex: Map 1
Execution mode: llap
LLAP IO: no inputs
@@ -1262,15 +1295,15 @@ STAGE PLANS:
keys:
0 _col0 (type: string), _col1 (type: string)
1 _col0 (type: string), _col1 (type: string)
- Statistics: Num rows: 2200 Data size: 809600 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1000 Data size: 8000 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count()
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: bigint)
Reducer 3
Execution mode: llap
@@ -1279,10 +1312,10 @@ STAGE PLANS:
aggregations: count(VALUE._col0)
mode: mergepartial
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -1366,19 +1399,19 @@ STAGE PLANS:
TableScan
alias: srcpart_date_hour_n0
filterExpr: ((date = '2008-04-08') and (UDFToDouble(hour) = 11.0D) and ds is not null and hr is not null) (type: boolean)
- Statistics: Num rows: 4 Data size: 2944 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4 Data size: 1440 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: ((UDFToDouble(hour) = 11.0D) and (date = '2008-04-08') and ds is not null and hr is not null) (type: boolean)
- Statistics: Num rows: 2 Data size: 1472 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: ds (type: string), hr (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 2 Data size: 1472 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string), _col1 (type: string)
sort order: ++
Map-reduce partition columns: _col0 (type: string), _col1 (type: string)
- Statistics: Num rows: 2 Data size: 1472 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: llap
LLAP IO: no inputs
Reducer 2
@@ -1390,15 +1423,15 @@ STAGE PLANS:
keys:
0 _col0 (type: string), _col1 (type: string)
1 _col0 (type: string), _col1 (type: string)
- Statistics: Num rows: 2200 Data size: 809600 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1000 Data size: 8000 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count()
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: bigint)
Reducer 3
Execution mode: llap
@@ -1407,10 +1440,10 @@ STAGE PLANS:
aggregations: count(VALUE._col0)
mode: mergepartial
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -1505,33 +1538,33 @@ STAGE PLANS:
TableScan
alias: srcpart_date_n2
filterExpr: ((date = 'I DONT EXIST') and ds is not null) (type: boolean)
- Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 376 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: ((date = 'I DONT EXIST') and ds is not null) (type: boolean)
- Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: ds (type: string)
outputColumnNames: _col0
- Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: string)
outputColumnNames: _col0
- Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
keys: _col0 (type: string)
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: COMPLETE
Dynamic Partitioning Event Operator
Target column: ds (string)
Target Input: srcpart
Partition key expr: ds
- Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: COMPLETE
Target Vertex: Map 1
Execution mode: llap
LLAP IO: no inputs
@@ -1544,15 +1577,15 @@ STAGE PLANS:
keys:
0 _col0 (type: string)
1 _col0 (type: string)
- Statistics: Num rows: 2200 Data size: 404800 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1000 Data size: 8000 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count()
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: bigint)
Reducer 3
Execution mode: llap
@@ -1561,10 +1594,10 @@ STAGE PLANS:
aggregations: count(VALUE._col0)
mode: mergepartial
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -1648,19 +1681,19 @@ STAGE PLANS:
TableScan
alias: srcpart_date_n2
filterExpr: ((date = 'I DONT EXIST') and ds is not null) (type: boolean)
- Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 376 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: ((date = 'I DONT EXIST') and ds is not null) (type: boolean)
- Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: ds (type: string)
outputColumnNames: _col0
- Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: llap
LLAP IO: no inputs
Reducer 2
@@ -1672,15 +1705,15 @@ STAGE PLANS:
keys:
0 _col0 (type: string)
1 _col0 (type: string)
- Statistics: Num rows: 2200 Data size: 404800 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1000 Data size: 8000 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count()
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: bigint)
Reducer 3
Execution mode: llap
@@ -1689,10 +1722,10 @@ STAGE PLANS:
aggregations: count(VALUE._col0)
mode: mergepartial
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -1785,33 +1818,33 @@ STAGE PLANS:
TableScan
alias: srcpart_double_hour_n0
filterExpr: ((UDFToDouble(hour) = 11.0D) and hr is not null) (type: boolean)
- Statistics: Num rows: 2 Data size: 384 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 188 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: ((UDFToDouble(hour) = 11.0D) and hr is not null) (type: boolean)
- Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: UDFToDouble(UDFToInteger((hr / 2.0D))) (type: double)
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: double)
sort order: +
Map-reduce partition columns: _col0 (type: double)
- Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: double)
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
keys: _col0 (type: double)
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Dynamic Partitioning Event Operator
Target column: hr (string)
Target Input: srcpart
Partition key expr: UDFToDouble(hr)
- Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Target Vertex: Map 1
Execution mode: llap
LLAP IO: no inputs
@@ -1824,15 +1857,15 @@ STAGE PLANS:
keys:
0 _col0 (type: double)
1 _col0 (type: double)
- Statistics: Num rows: 2200 Data size: 17600 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1000 Data size: 8000 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count()
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: bigint)
Reducer 3
Execution mode: llap
@@ -1841,10 +1874,10 @@ STAGE PLANS:
aggregations: count(VALUE._col0)
mode: mergepartial
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -1928,33 +1961,33 @@ STAGE PLANS:
TableScan
alias: srcpart_double_hour_n0
filterExpr: ((UDFToDouble(hour) = 11.0D) and hr is not null) (type: boolean)
- Statistics: Num rows: 2 Data size: 384 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 188 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: ((UDFToDouble(hour) = 11.0D) and hr is not null) (type: boolean)
- Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: hr (type: double)
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: double)
sort order: +
Map-reduce partition columns: _col0 (type: double)
- Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: double)
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
keys: _col0 (type: double)
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Dynamic Partitioning Event Operator
Target column: hr (string)
Target Input: srcpart
Partition key expr: (UDFToDouble(hr) * 2.0D)
- Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Target Vertex: Map 1
Execution mode: llap
LLAP IO: no inputs
@@ -1967,15 +2000,15 @@ STAGE PLANS:
keys:
0 _col0 (type: double)
1 _col0 (type: double)
- Statistics: Num rows: 2200 Data size: 17600 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1000 Data size: 8000 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count()
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: bigint)
Reducer 3
Execution mode: llap
@@ -1984,10 +2017,10 @@ STAGE PLANS:
aggregations: count(VALUE._col0)
mode: mergepartial
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -2071,19 +2104,19 @@ STAGE PLANS:
TableScan
alias: srcpart_double_hour_n0
filterExpr: ((UDFToDouble(hour) = 11.0D) and hr is not null) (type: boolean)
- Statistics: Num rows: 2 Data size: 384 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 188 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: ((UDFToDouble(hour) = 11.0D) and hr is not null) (type: boolean)
- Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: UDFToDouble(UDFToInteger((hr / 2.0D))) (type: double)
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: double)
sort order: +
Map-reduce partition columns: _col0 (type: double)
- Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: llap
LLAP IO: no inputs
Reducer 2
@@ -2095,15 +2128,15 @@ STAGE PLANS:
keys:
0 _col0 (type: double)
1 _col0 (type: double)
- Statistics: Num rows: 2200 Data size: 17600 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1000 Data size: 8000 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count()
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: bigint)
Reducer 3
Execution mode: llap
@@ -2112,10 +2145,10 @@ STAGE PLANS:
aggregations: count(VALUE._col0)
mode: mergepartial
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -2199,19 +2232,19 @@ STAGE PLANS:
TableScan
alias: srcpart_double_hour_n0
filterExpr: ((UDFToDouble(hour) = 11.0D) and hr is not null) (type: boolean)
- Statistics: Num rows: 2 Data size: 384 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 188 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: ((UDFToDouble(hour) = 11.0D) and hr is not null) (type: boolean)
- Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: hr (type: double)
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: double)
sort order: +
Map-reduce partition columns: _col0 (type: double)
- Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: llap
LLAP IO: no inputs
Reducer 2
@@ -2223,15 +2256,15 @@ STAGE PLANS:
keys:
0 _col0 (type: double)
1 _col0 (type: double)
- Statistics: Num rows: 2200 Data size: 17600 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1000 Data size: 8000 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count()
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: bigint)
Reducer 3
Execution mode: llap
@@ -2240,10 +2273,10 @@ STAGE PLANS:
aggregations: count(VALUE._col0)
mode: mergepartial
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -2340,33 +2373,33 @@ STAGE PLANS:
TableScan
alias: srcpart_double_hour_n0
filterExpr: ((UDFToDouble(hour) = 11.0D) and hr is not null) (type: boolean)
- Statistics: Num rows: 2 Data size: 384 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 188 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: ((UDFToDouble(hour) = 11.0D) and hr is not null) (type: boolean)
- Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: CAST( hr AS STRING) (type: string)
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: string)
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
keys: _col0 (type: string)
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE
Dynamic Partitioning Event Operator
Target column: hr (string)
Target Input: srcpart
Partition key expr: CAST( (UDFToDouble(hr) * 2.0D) AS STRING)
- Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE
Target Vertex: Map 1
Execution mode: llap
LLAP IO: no inputs
@@ -2379,15 +2412,15 @@ STAGE PLANS:
keys:
0 _col0 (type: string)
1 _col0 (type: string)
- Statistics: Num rows: 2200 Data size: 404800 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1000 Data size: 8000 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count()
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: bigint)
Reducer 3
Execution mode: llap
@@ -2396,10 +2429,10 @@ STAGE PLANS:
aggregations: count(VALUE._col0)
mode: mergepartial
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -2626,17 +2659,17 @@ STAGE PLANS:
TableScan
alias: srcpart_date_hour_n0
filterExpr: ((date = '2008-04-08') and (UDFToDouble(hour) = 11.0D)) (type: boolean)
- Statistics: Num rows: 4 Data size: 2944 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4 Data size: 1440 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: ((UDFToDouble(hour) = 11.0D) and (date = '2008-04-08')) (type: boolean)
- Statistics: Num rows: 2 Data size: 1472 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: ds (type: string), hr (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 2 Data size: 1472 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
- Statistics: Num rows: 2 Data size: 1472 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: string), _col1 (type: string)
Execution mode: llap
LLAP IO: no inputs
@@ -2651,17 +2684,17 @@ STAGE PLANS:
1
outputColumnNames: _col0, _col1, _col2, _col3
residual filter predicates: {((_col0 = _col2) or (_col1 = _col3))}
- Statistics: Num rows: 4000 Data size: 4420000 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2000 Data size: 1096000 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
- Statistics: Num rows: 4000 Data size: 4420000 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2000 Data size: 1096000 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count()
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: bigint)
Reducer 3
Execution mode: llap
@@ -2670,10 +2703,10 @@ STAGE PLANS:
aggregations: count(VALUE._col0)
mode: mergepartial
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -2757,48 +2790,48 @@ STAGE PLANS:
TableScan
alias: srcpart_date_hour_n0
filterExpr: ((date = '2008-04-08') and (UDFToDouble(hour) = 11.0D) and ds is not null and hr is not null) (type: boolean)
- Statistics: Num rows: 4 Data size: 2944 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4 Data size: 1440 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: ((UDFToDouble(hour) = 11.0D) and (date = '2008-04-08') and ds is not null and hr is not null) (type: boolean)
- Statistics: Num rows: 2 Data size: 1472 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: ds (type: string), hr (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 2 Data size: 1472 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string), _col1 (type: string)
sort order: ++
Map-reduce partition columns: _col0 (type: string), _col1 (type: string)
- Statistics: Num rows: 2 Data size: 1472 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: string)
outputColumnNames: _col0
- Statistics: Num rows: 2 Data size: 1472 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
keys: _col0 (type: string)
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 2 Data size: 1472 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
Dynamic Partitioning Event Operator
Target column: ds (string)
Target Input: srcpart
Partition key expr: ds
- Statistics: Num rows: 2 Data size: 1472 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
Target Vertex: Map 1
Select Operator
expressions: _col1 (type: string)
outputColumnNames: _col0
- Statistics: Num rows: 2 Data size: 1472 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
keys: _col0 (type: string)
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 2 Data size: 1472 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
Dynamic Partitioning Event Operator
Target column: hr (string)
Target Input: srcpart
Partition key expr: hr
- Statistics: Num rows: 2 Data size: 1472 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
Target Vertex: Map 1
Execution mode: llap
LLAP IO: no inputs
@@ -2811,15 +2844,15 @@ STAGE PLANS:
keys:
0 _col0 (type: string), _col1 (type: string)
1 _col0 (type: string), _col1 (type: string)
- Statistics: Num rows: 2200 Data size: 809600 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1000 Data size: 8000 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count()
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: bigint)
Reducer 3
Execution mode: llap
@@ -2828,10 +2861,10 @@ STAGE PLANS:
aggregations: count(VALUE._col0)
mode: mergepartial
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -2915,33 +2948,33 @@ STAGE PLANS:
TableScan
alias: srcpart_date_n2
filterExpr: ((date = '2008-04-08') and ds is not null) (type: boolean)
- Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 376 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: ((date = '2008-04-08') and ds is not null) (type: boolean)
- Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: ds (type: string)
outputColumnNames: _col0
- Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: string)
outputColumnNames: _col0
- Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
keys: _col0 (type: string)
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: COMPLETE
Dynamic Partitioning Event Operator
Target column: ds (string)
Target Input: srcpart
Partition key expr: ds
- Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: COMPLETE
Target Vertex: Map 1
Execution mode: llap
LLAP IO: no inputs
@@ -2954,15 +2987,15 @@ STAGE PLANS:
keys:
0 _col0 (type: string)
1 _col0 (type: string)
- Statistics: Num rows: 2200 Data size: 404800 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1000 Data size: 8000 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count()
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: bigint)
Reducer 3
Execution mode: llap
@@ -2971,10 +3004,10 @@ STAGE PLANS:
aggregations: count(VALUE._col0)
mode: mergepartial
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop
<TRUNCATED>
[06/35] hive git commit: HIVE-16957: Support CTAS for auto gather
column stats (Jesus Camacho Rodriguez, reviewed by Ashutosh Chauhan)
Posted by jc...@apache.org.
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/llap/vector_like_2.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/vector_like_2.q.out b/ql/src/test/results/clientpositive/llap/vector_like_2.q.out
index 99ca5d6..ec80136 100644
--- a/ql/src/test/results/clientpositive/llap/vector_like_2.q.out
+++ b/ql/src/test/results/clientpositive/llap/vector_like_2.q.out
@@ -49,7 +49,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: foo
- Statistics: Num rows: 3 Data size: 267 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 3 Data size: 552 Basic stats: COMPLETE Column stats: NONE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:a:string, 1:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -61,7 +61,7 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [0, 2]
selectExpressions: SelectStringColLikeStringScalar(col 0:string) -> 2:boolean
- Statistics: Num rows: 3 Data size: 279 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 3 Data size: 552 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
@@ -71,7 +71,7 @@ STAGE PLANS:
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
valueColumns: 2:boolean
- Statistics: Num rows: 3 Data size: 279 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 3 Data size: 552 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: boolean)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -113,13 +113,13 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1]
- Statistics: Num rows: 3 Data size: 279 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 3 Data size: 552 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 3 Data size: 279 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 3 Data size: 552 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/llap/vector_llap_io_data_conversion.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/vector_llap_io_data_conversion.q.out b/ql/src/test/results/clientpositive/llap/vector_llap_io_data_conversion.q.out
index 25fa939..7bce43c 100644
--- a/ql/src/test/results/clientpositive/llap/vector_llap_io_data_conversion.q.out
+++ b/ql/src/test/results/clientpositive/llap/vector_llap_io_data_conversion.q.out
@@ -91,7 +91,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: varchar_ctas_1
- Statistics: Num rows: 10 Data size: 2820 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 1920 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:vs:varchar(10), 1:c1:int, 2:c2:string, 3:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -102,7 +102,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1, 2]
- Statistics: Num rows: 10 Data size: 2820 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 1920 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: varchar(10)), _col1 (type: int), _col2 (type: string)
sort order: +++
@@ -111,7 +111,7 @@ STAGE PLANS:
keyColumns: 0:varchar(10), 1:int, 2:string
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 10 Data size: 2820 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 1920 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized, llap
LLAP IO: all inputs
Map Vectorization:
@@ -152,13 +152,13 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1, 2]
- Statistics: Num rows: 10 Data size: 2820 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 1920 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 10 Data size: 2820 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 1920 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/llap/vector_nullsafe_join.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/vector_nullsafe_join.q.out b/ql/src/test/results/clientpositive/llap/vector_nullsafe_join.q.out
index e943eb0..6d49db9 100644
--- a/ql/src/test/results/clientpositive/llap/vector_nullsafe_join.q.out
+++ b/ql/src/test/results/clientpositive/llap/vector_nullsafe_join.q.out
@@ -54,7 +54,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: a
- Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
Map Join Operator
@@ -74,7 +74,7 @@ STAGE PLANS:
outputColumnNames: _col0, _col1, _col5, _col6
input vertices:
1 Map 2
- Statistics: Num rows: 6 Data size: 52 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 160 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: int), _col1 (type: int), _col5 (type: int), _col6 (type: int)
outputColumnNames: _col0, _col1, _col2, _col3
@@ -82,13 +82,13 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1, 2, 3]
- Statistics: Num rows: 6 Data size: 52 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 160 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 6 Data size: 52 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 160 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -108,7 +108,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: b
- Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
Reduce Output Operator
@@ -119,7 +119,7 @@ STAGE PLANS:
className: VectorReduceSinkLongOperator
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: key (type: int)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -187,7 +187,7 @@ STAGE PLANS:
TableScan
alias: a
filterExpr: key is not null (type: boolean)
- Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
Filter Operator
@@ -196,7 +196,7 @@ STAGE PLANS:
native: true
predicateExpression: SelectColumnIsNotNull(col 0:int)
predicate: key is not null (type: boolean)
- Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE
Map Join Operator
condition map:
Inner Join 0 to 1
@@ -216,7 +216,7 @@ STAGE PLANS:
input vertices:
1 Map 2
2 Map 3
- Statistics: Num rows: 13 Data size: 105 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: int), _col1 (type: int), _col5 (type: int), _col6 (type: int), _col10 (type: int), _col11 (type: int)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
@@ -224,13 +224,13 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1, 2, 3, 4, 5]
- Statistics: Num rows: 13 Data size: 105 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 13 Data size: 105 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -251,7 +251,7 @@ STAGE PLANS:
TableScan
alias: b
filterExpr: value is not null (type: boolean)
- Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
Filter Operator
@@ -260,7 +260,7 @@ STAGE PLANS:
native: true
predicateExpression: SelectColumnIsNotNull(col 1:int)
predicate: value is not null (type: boolean)
- Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: value (type: int)
sort order: +
@@ -269,7 +269,7 @@ STAGE PLANS:
className: VectorReduceSinkLongOperator
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: key (type: int)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -287,7 +287,7 @@ STAGE PLANS:
TableScan
alias: c
filterExpr: key is not null (type: boolean)
- Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
Filter Operator
@@ -296,7 +296,7 @@ STAGE PLANS:
native: true
predicateExpression: SelectColumnIsNotNull(col 0:int)
predicate: key is not null (type: boolean)
- Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: key (type: int)
sort order: +
@@ -305,7 +305,7 @@ STAGE PLANS:
className: VectorReduceSinkLongOperator
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: value (type: int)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -363,7 +363,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: a
- Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
Map Join Operator
@@ -386,7 +386,7 @@ STAGE PLANS:
input vertices:
1 Map 2
2 Map 3
- Statistics: Num rows: 13 Data size: 105 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 24 Data size: 528 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: int), _col1 (type: int), _col5 (type: int), _col6 (type: int), _col10 (type: int), _col11 (type: int)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
@@ -394,13 +394,13 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1, 2, 3, 4, 5]
- Statistics: Num rows: 13 Data size: 105 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 24 Data size: 528 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 13 Data size: 105 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 24 Data size: 528 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -420,7 +420,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: b
- Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
Reduce Output Operator
@@ -431,7 +431,7 @@ STAGE PLANS:
className: VectorReduceSinkLongOperator
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: key (type: int)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -448,7 +448,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: c
- Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
Reduce Output Operator
@@ -459,7 +459,7 @@ STAGE PLANS:
className: VectorReduceSinkLongOperator
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: value (type: int)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -545,7 +545,7 @@ STAGE PLANS:
TableScan
alias: a
filterExpr: value is not null (type: boolean)
- Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
Filter Operator
@@ -554,7 +554,7 @@ STAGE PLANS:
native: true
predicateExpression: SelectColumnIsNotNull(col 1:int)
predicate: value is not null (type: boolean)
- Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE
Map Join Operator
condition map:
Inner Join 0 to 1
@@ -575,7 +575,7 @@ STAGE PLANS:
input vertices:
1 Map 2
2 Map 3
- Statistics: Num rows: 13 Data size: 105 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: int), _col1 (type: int), _col5 (type: int), _col6 (type: int), _col10 (type: int), _col11 (type: int)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
@@ -583,13 +583,13 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1, 2, 3, 4, 5]
- Statistics: Num rows: 13 Data size: 105 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 13 Data size: 105 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -610,7 +610,7 @@ STAGE PLANS:
TableScan
alias: b
filterExpr: key is not null (type: boolean)
- Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
Filter Operator
@@ -619,7 +619,7 @@ STAGE PLANS:
native: true
predicateExpression: SelectColumnIsNotNull(col 0:int)
predicate: key is not null (type: boolean)
- Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: value (type: int), key (type: int)
sort order: ++
@@ -628,7 +628,7 @@ STAGE PLANS:
className: VectorReduceSinkMultiKeyOperator
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized, llap
LLAP IO: all inputs
Map Vectorization:
@@ -645,7 +645,7 @@ STAGE PLANS:
TableScan
alias: c
filterExpr: value is not null (type: boolean)
- Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
Filter Operator
@@ -654,7 +654,7 @@ STAGE PLANS:
native: true
predicateExpression: SelectColumnIsNotNull(col 1:int)
predicate: value is not null (type: boolean)
- Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: key (type: int), value (type: int)
sort order: ++
@@ -663,7 +663,7 @@ STAGE PLANS:
className: VectorReduceSinkMultiKeyOperator
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized, llap
LLAP IO: all inputs
Map Vectorization:
@@ -720,7 +720,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: a
- Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
Map Join Operator
@@ -743,7 +743,7 @@ STAGE PLANS:
input vertices:
1 Map 2
2 Map 3
- Statistics: Num rows: 13 Data size: 105 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 24 Data size: 528 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: int), _col1 (type: int), _col5 (type: int), _col6 (type: int), _col10 (type: int), _col11 (type: int)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
@@ -751,13 +751,13 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1, 2, 3, 4, 5]
- Statistics: Num rows: 13 Data size: 105 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 24 Data size: 528 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 13 Data size: 105 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 24 Data size: 528 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -777,7 +777,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: b
- Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
Reduce Output Operator
@@ -788,7 +788,7 @@ STAGE PLANS:
className: VectorReduceSinkMultiKeyOperator
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized, llap
LLAP IO: all inputs
Map Vectorization:
@@ -804,7 +804,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: c
- Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
Reduce Output Operator
@@ -815,7 +815,7 @@ STAGE PLANS:
className: VectorReduceSinkMultiKeyOperator
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized, llap
LLAP IO: all inputs
Map Vectorization:
@@ -896,7 +896,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: a
- Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:key:int, 1:value:int, 2:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -912,7 +912,7 @@ STAGE PLANS:
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
valueColumns: 1:int
- Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: value (type: int)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -935,7 +935,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: b
- Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:key:int, 1:value:int, 2:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -962,7 +962,7 @@ STAGE PLANS:
outputColumnNames: _col0, _col1, _col5, _col6
input vertices:
0 Map 1
- Statistics: Num rows: 6 Data size: 52 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 160 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: int), _col1 (type: int), _col5 (type: int), _col6 (type: int)
outputColumnNames: _col0, _col1, _col2, _col3
@@ -970,13 +970,13 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1, 2, 3]
- Statistics: Num rows: 6 Data size: 52 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 160 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 6 Data size: 52 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 160 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -1092,7 +1092,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: a
- Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
Map Join Operator
@@ -1112,7 +1112,7 @@ STAGE PLANS:
outputColumnNames: _col0, _col1, _col5, _col6
input vertices:
1 Map 2
- Statistics: Num rows: 6 Data size: 52 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 160 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: int), _col1 (type: int), _col5 (type: int), _col6 (type: int)
outputColumnNames: _col0, _col1, _col2, _col3
@@ -1120,13 +1120,13 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1, 2, 3]
- Statistics: Num rows: 6 Data size: 52 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 160 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 6 Data size: 52 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 160 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -1146,7 +1146,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: b
- Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
Reduce Output Operator
@@ -1157,7 +1157,7 @@ STAGE PLANS:
className: VectorReduceSinkLongOperator
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: key (type: int)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -1225,7 +1225,7 @@ STAGE PLANS:
TableScan
alias: a
filterExpr: key is not null (type: boolean)
- Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
Filter Operator
@@ -1234,7 +1234,7 @@ STAGE PLANS:
native: true
predicateExpression: SelectColumnIsNotNull(col 0:int)
predicate: key is not null (type: boolean)
- Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE
Map Join Operator
condition map:
Inner Join 0 to 1
@@ -1254,7 +1254,7 @@ STAGE PLANS:
input vertices:
1 Map 2
2 Map 3
- Statistics: Num rows: 13 Data size: 105 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: int), _col1 (type: int), _col5 (type: int), _col6 (type: int), _col10 (type: int), _col11 (type: int)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
@@ -1262,13 +1262,13 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1, 2, 3, 4, 5]
- Statistics: Num rows: 13 Data size: 105 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 13 Data size: 105 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -1289,7 +1289,7 @@ STAGE PLANS:
TableScan
alias: b
filterExpr: value is not null (type: boolean)
- Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
Filter Operator
@@ -1298,7 +1298,7 @@ STAGE PLANS:
native: true
predicateExpression: SelectColumnIsNotNull(col 1:int)
predicate: value is not null (type: boolean)
- Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: value (type: int)
sort order: +
@@ -1307,7 +1307,7 @@ STAGE PLANS:
className: VectorReduceSinkLongOperator
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: key (type: int)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -1325,7 +1325,7 @@ STAGE PLANS:
TableScan
alias: c
filterExpr: key is not null (type: boolean)
- Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
Filter Operator
@@ -1334,7 +1334,7 @@ STAGE PLANS:
native: true
predicateExpression: SelectColumnIsNotNull(col 0:int)
predicate: key is not null (type: boolean)
- Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: key (type: int)
sort order: +
@@ -1343,7 +1343,7 @@ STAGE PLANS:
className: VectorReduceSinkLongOperator
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: value (type: int)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -1401,7 +1401,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: a
- Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
Map Join Operator
@@ -1424,7 +1424,7 @@ STAGE PLANS:
input vertices:
1 Map 2
2 Map 3
- Statistics: Num rows: 13 Data size: 105 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 24 Data size: 528 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: int), _col1 (type: int), _col5 (type: int), _col6 (type: int), _col10 (type: int), _col11 (type: int)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
@@ -1432,13 +1432,13 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1, 2, 3, 4, 5]
- Statistics: Num rows: 13 Data size: 105 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 24 Data size: 528 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 13 Data size: 105 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 24 Data size: 528 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -1458,7 +1458,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: b
- Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
Reduce Output Operator
@@ -1469,7 +1469,7 @@ STAGE PLANS:
className: VectorReduceSinkLongOperator
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: key (type: int)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -1486,7 +1486,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: c
- Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
Reduce Output Operator
@@ -1497,7 +1497,7 @@ STAGE PLANS:
className: VectorReduceSinkLongOperator
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: value (type: int)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -1583,7 +1583,7 @@ STAGE PLANS:
TableScan
alias: a
filterExpr: value is not null (type: boolean)
- Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
Filter Operator
@@ -1592,7 +1592,7 @@ STAGE PLANS:
native: true
predicateExpression: SelectColumnIsNotNull(col 1:int)
predicate: value is not null (type: boolean)
- Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE
Map Join Operator
condition map:
Inner Join 0 to 1
@@ -1613,7 +1613,7 @@ STAGE PLANS:
input vertices:
1 Map 2
2 Map 3
- Statistics: Num rows: 13 Data size: 105 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: int), _col1 (type: int), _col5 (type: int), _col6 (type: int), _col10 (type: int), _col11 (type: int)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
@@ -1621,13 +1621,13 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1, 2, 3, 4, 5]
- Statistics: Num rows: 13 Data size: 105 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 13 Data size: 105 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -1648,7 +1648,7 @@ STAGE PLANS:
TableScan
alias: b
filterExpr: key is not null (type: boolean)
- Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
Filter Operator
@@ -1657,7 +1657,7 @@ STAGE PLANS:
native: true
predicateExpression: SelectColumnIsNotNull(col 0:int)
predicate: key is not null (type: boolean)
- Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: value (type: int), key (type: int)
sort order: ++
@@ -1666,7 +1666,7 @@ STAGE PLANS:
className: VectorReduceSinkMultiKeyOperator
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized, llap
LLAP IO: all inputs
Map Vectorization:
@@ -1683,7 +1683,7 @@ STAGE PLANS:
TableScan
alias: c
filterExpr: value is not null (type: boolean)
- Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
Filter Operator
@@ -1692,7 +1692,7 @@ STAGE PLANS:
native: true
predicateExpression: SelectColumnIsNotNull(col 1:int)
predicate: value is not null (type: boolean)
- Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: key (type: int), value (type: int)
sort order: ++
@@ -1701,7 +1701,7 @@ STAGE PLANS:
className: VectorReduceSinkMultiKeyOperator
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized, llap
LLAP IO: all inputs
Map Vectorization:
@@ -1758,7 +1758,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: a
- Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
Map Join Operator
@@ -1781,7 +1781,7 @@ STAGE PLANS:
input vertices:
1 Map 2
2 Map 3
- Statistics: Num rows: 13 Data size: 105 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 24 Data size: 528 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: int), _col1 (type: int), _col5 (type: int), _col6 (type: int), _col10 (type: int), _col11 (type: int)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
@@ -1789,13 +1789,13 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1, 2, 3, 4, 5]
- Statistics: Num rows: 13 Data size: 105 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 24 Data size: 528 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 13 Data size: 105 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 24 Data size: 528 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -1815,7 +1815,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: b
- Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
Reduce Output Operator
@@ -1826,7 +1826,7 @@ STAGE PLANS:
className: VectorReduceSinkMultiKeyOperator
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized, llap
LLAP IO: all inputs
Map Vectorization:
@@ -1842,7 +1842,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: c
- Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
Reduce Output Operator
@@ -1853,7 +1853,7 @@ STAGE PLANS:
className: VectorReduceSinkMultiKeyOperator
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized, llap
LLAP IO: all inputs
Map Vectorization:
@@ -1934,7 +1934,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: a
- Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:key:int, 1:value:int, 2:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -1950,7 +1950,7 @@ STAGE PLANS:
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
valueColumns: 1:int
- Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: value (type: int)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -1973,7 +1973,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: b
- Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:key:int, 1:value:int, 2:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -2000,7 +2000,7 @@ STAGE PLANS:
outputColumnNames: _col0, _col1, _col5, _col6
input vertices:
0 Map 1
- Statistics: Num rows: 6 Data size: 52 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 160 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: int), _col1 (type: int), _col5 (type: int), _col6 (type: int)
outputColumnNames: _col0, _col1, _col2, _col3
@@ -2008,13 +2008,13 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1, 2, 3]
- Statistics: Num rows: 6 Data size: 52 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 160 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 6 Data size: 52 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 160 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/llap/vector_number_compare_projection.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/vector_number_compare_projection.q.out b/ql/src/test/results/clientpositive/llap/vector_number_compare_projection.q.out
index 0546346..e220d5d 100644
--- a/ql/src/test/results/clientpositive/llap/vector_number_compare_projection.q.out
+++ b/ql/src/test/results/clientpositive/llap/vector_number_compare_projection.q.out
@@ -131,7 +131,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: vectortab2k_orc
- Statistics: Num rows: 2001 Data size: 22824 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2001 Data size: 22784 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
Select Operator
@@ -142,7 +142,7 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [11]
selectExpressions: VectorUDFAdaptor(hash(t,si,i,(t < 0Y),(si <= 0S),(i = 0)))(children: LongColLessLongScalar(col 0:tinyint, val 0) -> 8:boolean, LongColLessEqualLongScalar(col 1:smallint, val 0) -> 9:boolean, LongColEqualLongScalar(col 2:int, val 0) -> 10:boolean) -> 11:int
- Statistics: Num rows: 2001 Data size: 22824 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2001 Data size: 22784 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: sum(_col0)
Group By Vectorization:
@@ -154,14 +154,14 @@ STAGE PLANS:
projectedOutputColumnNums: [0]
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
Reduce Sink Vectorization:
className: VectorReduceSinkEmptyKeyOperator
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: bigint)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -194,13 +194,13 @@ STAGE PLANS:
projectedOutputColumnNums: [0]
mode: mergepartial
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -261,7 +261,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: vectortab2k_orc
- Statistics: Num rows: 2001 Data size: 38040 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2001 Data size: 38128 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
Select Operator
@@ -272,7 +272,7 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [12]
selectExpressions: VectorUDFAdaptor(hash(t,si,i,b,(t > 0Y),(si >= 0S),(i <> 0),(b > 0L)))(children: LongColGreaterLongScalar(col 0:tinyint, val 0) -> 8:boolean, LongColGreaterEqualLongScalar(col 1:smallint, val 0) -> 9:boolean, LongColNotEqualLongScalar(col 2:int, val 0) -> 10:boolean, LongColGreaterLongScalar(col 3:bigint, val 0) -> 11:boolean) -> 12:int
- Statistics: Num rows: 2001 Data size: 38040 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2001 Data size: 38128 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: sum(_col0)
Group By Vectorization:
@@ -284,14 +284,14 @@ STAGE PLANS:
projectedOutputColumnNums: [0]
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 28 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
Reduce Sink Vectorization:
className: VectorReduceSinkEmptyKeyOperator
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 1 Data size: 28 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: bigint)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -324,13 +324,13 @@ STAGE PLANS:
projectedOutputColumnNums: [0]
mode: mergepartial
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 28 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 1 Data size: 28 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/llap/vector_partitioned_date_time.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/vector_partitioned_date_time.q.out b/ql/src/test/results/clientpositive/llap/vector_partitioned_date_time.q.out
index b7db028..09435b3 100644
--- a/ql/src/test/results/clientpositive/llap/vector_partitioned_date_time.q.out
+++ b/ql/src/test/results/clientpositive/llap/vector_partitioned_date_time.q.out
@@ -275,7 +275,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: flights_tiny_orc
- Statistics: Num rows: 137 Data size: 62304 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 137 Data size: 39456 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
Select Operator
@@ -285,7 +285,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1, 2, 3, 4, 5]
- Statistics: Num rows: 137 Data size: 62304 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 137 Data size: 39456 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col5 (type: int), _col2 (type: date)
sort order: ++
@@ -293,7 +293,7 @@ STAGE PLANS:
className: VectorReduceSinkObjectHashOperator
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 137 Data size: 62304 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 137 Data size: 39456 Basic stats: COMPLETE Column stats: COMPLETE
TopN Hash Memory Usage: 0.1
value expressions: _col0 (type: string), _col1 (type: string), _col3 (type: timestamp), _col4 (type: float)
Execution mode: vectorized, llap
@@ -323,13 +323,13 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [2, 3, 1, 4, 5, 0]
- Statistics: Num rows: 137 Data size: 62304 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 137 Data size: 39456 Basic stats: COMPLETE Column stats: COMPLETE
Limit
Number of rows: 25
Limit Vectorization:
className: VectorLimitOperator
native: true
- Statistics: Num rows: 25 Data size: 11350 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 25 Data size: 7200 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col5 (type: int), _col2 (type: date)
sort order: ++
@@ -337,7 +337,7 @@ STAGE PLANS:
className: VectorReduceSinkObjectHashOperator
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 25 Data size: 11350 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 25 Data size: 7200 Basic stats: COMPLETE Column stats: COMPLETE
TopN Hash Memory Usage: 0.1
value expressions: _col0 (type: string), _col1 (type: string), _col3 (type: timestamp), _col4 (type: float)
Reducer 3
@@ -356,19 +356,19 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [2, 3, 1, 4, 5, 0]
- Statistics: Num rows: 25 Data size: 11350 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 25 Data size: 7200 Basic stats: COMPLETE Column stats: COMPLETE
Limit
Number of rows: 25
Limit Vectorization:
className: VectorLimitOperator
native: true
- Statistics: Num rows: 25 Data size: 11350 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 25 Data size: 7200 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 25 Data size: 11350 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 25 Data size: 7200 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -443,7 +443,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: flights_tiny_orc
- Statistics: Num rows: 137 Data size: 7392 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 137 Data size: 7672 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
Select Operator
@@ -453,7 +453,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [2]
- Statistics: Num rows: 137 Data size: 7392 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 137 Data size: 7672 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count()
Group By Vectorization:
@@ -467,7 +467,7 @@ STAGE PLANS:
keys: fl_date (type: date)
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 137 Data size: 7392 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 68 Data size: 4352 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: date)
sort order: +
@@ -476,7 +476,7 @@ STAGE PLANS:
className: VectorReduceSinkMultiKeyOperator
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 137 Data size: 7392 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 68 Data size: 4352 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: bigint)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -511,13 +511,13 @@ STAGE PLANS:
keys: KEY._col0 (type: date)
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 68 Data size: 3669 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 34 Data size: 2176 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 68 Data size: 3669 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 34 Data size: 2176 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -2876,7 +2876,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: flights_tiny_parquet
- Statistics: Num rows: 137 Data size: 62304 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 137 Data size: 39456 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
Select Operator
@@ -2886,7 +2886,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1, 2, 3, 4, 5]
- Statistics: Num rows: 137 Data size: 62304 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 137 Data size: 39456 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col5 (type: int), _col2 (type: date)
sort order: ++
@@ -2894,7 +2894,7 @@ STAGE PLANS:
className: VectorReduceSinkObjectHashOperator
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 137 Data size: 62304 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 137 Data size: 39456 Basic stats: COMPLETE Column stats: COMPLETE
TopN Hash Memory Usage: 0.1
value expressions: _col0 (type: string), _col1 (type: string), _col3 (type: timestamp), _col4 (type: float)
Execution mode: vectorized, llap
@@ -2924,13 +2924,13 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [2, 3, 1, 4, 5, 0]
- Statistics: Num rows: 137 Data size: 62304 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 137 Data size: 39456 Basic stats: COMPLETE Column stats: COMPLETE
Limit
Number of rows: 25
Limit Vectorization:
className: VectorLimitOperator
native: true
- Statistics: Num rows: 25 Data size: 11350 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 25 Data size: 7200 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col5 (type: int), _col2 (type: date)
sort order: ++
@@ -2938,7 +2938,7 @@ STAGE PLANS:
className: VectorReduceSinkObjectHashOperator
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 25 Data size: 11350 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 25 Data size: 7200 Basic stats: COMPLETE Column stats: COMPLETE
TopN Hash Memory Usage: 0.1
value expressions: _col0 (type: string), _col1 (type: string), _col3 (type: timestamp), _col4 (type: float)
Reducer 3
@@ -2957,19 +2957,19 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [2, 3, 1, 4, 5, 0]
- Statistics: Num rows: 25 Data size: 11350 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 25 Data size: 7200 Basic stats: COMPLETE Column stats: COMPLETE
Limit
Number of rows: 25
Limit Vectorization:
className: VectorLimitOperator
native: true
- Statistics: Num rows: 25 Data size: 11350 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 25 Data size: 7200 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 25 Data size: 11350 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 25 Data size: 7200 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -3044,7 +3044,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: flights_tiny_parquet
- Statistics: Num rows: 137 Data size: 7392 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 137 Data size: 7672 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
Select Operator
@@ -3054,7 +3054,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [2]
- Statistics: Num rows: 137 Data size: 7392 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 137 Data size: 7672 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count()
Group By Vectorization:
@@ -3068,7 +3068,7 @@ STAGE PLANS:
keys: fl_date (type: date)
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 137 Data size: 7392 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 68 Data size: 4352 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: date)
sort order: +
@@ -3077,7 +3077,7 @@ STAGE PLANS:
className: VectorReduceSinkMultiKeyOperator
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 137 Data size: 7392 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 68 Data size: 4352 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: bigint)
Execution mode: vectorized, llap
LLAP IO: all inputs (cache only)
@@ -3112,13 +3112,13 @@ STAGE PLANS:
keys: KEY._col0 (type: date)
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 68 Data size: 3669 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 34 Data size: 2176 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 68 Data size: 3669 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 34 Data size: 2176 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
[25/35] hive git commit: HIVE-16957: Support CTAS for auto gather
column stats (Jesus Camacho Rodriguez, reviewed by Ashutosh Chauhan)
Posted by jc...@apache.org.
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/llap/materialized_view_rewrite_7.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/materialized_view_rewrite_7.q.out b/ql/src/test/results/clientpositive/llap/materialized_view_rewrite_7.q.out
index 902a8d4..03acafa 100644
--- a/ql/src/test/results/clientpositive/llap/materialized_view_rewrite_7.q.out
+++ b/ql/src/test/results/clientpositive/llap/materialized_view_rewrite_7.q.out
@@ -33,16 +33,6 @@ POSTHOOK: Lineage: emps_n8.deptno SCRIPT []
POSTHOOK: Lineage: emps_n8.empid SCRIPT []
POSTHOOK: Lineage: emps_n8.name SCRIPT []
POSTHOOK: Lineage: emps_n8.salary SCRIPT []
-PREHOOK: query: analyze table emps_n8 compute statistics for columns
-PREHOOK: type: ANALYZE_TABLE
-PREHOOK: Input: default@emps_n8
-PREHOOK: Output: default@emps_n8
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table emps_n8 compute statistics for columns
-POSTHOOK: type: ANALYZE_TABLE
-POSTHOOK: Input: default@emps_n8
-POSTHOOK: Output: default@emps_n8
-#### A masked pattern was here ####
PREHOOK: query: create table depts_n6 (
deptno int,
name varchar(256),
@@ -70,16 +60,6 @@ POSTHOOK: Output: default@depts_n6
POSTHOOK: Lineage: depts_n6.deptno SCRIPT []
POSTHOOK: Lineage: depts_n6.locationid SCRIPT []
POSTHOOK: Lineage: depts_n6.name SCRIPT []
-PREHOOK: query: analyze table depts_n6 compute statistics for columns
-PREHOOK: type: ANALYZE_TABLE
-PREHOOK: Input: default@depts_n6
-PREHOOK: Output: default@depts_n6
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table depts_n6 compute statistics for columns
-POSTHOOK: type: ANALYZE_TABLE
-POSTHOOK: Input: default@depts_n6
-POSTHOOK: Output: default@depts_n6
-#### A masked pattern was here ####
PREHOOK: query: create table dependents_n4 (
empid int,
name varchar(256))
@@ -104,16 +84,6 @@ POSTHOOK: Input: _dummy_database@_dummy_table
POSTHOOK: Output: default@dependents_n4
POSTHOOK: Lineage: dependents_n4.empid SCRIPT []
POSTHOOK: Lineage: dependents_n4.name SCRIPT []
-PREHOOK: query: analyze table dependents_n4 compute statistics for columns
-PREHOOK: type: ANALYZE_TABLE
-PREHOOK: Input: default@dependents_n4
-PREHOOK: Output: default@dependents_n4
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table dependents_n4 compute statistics for columns
-POSTHOOK: type: ANALYZE_TABLE
-POSTHOOK: Input: default@dependents_n4
-POSTHOOK: Output: default@dependents_n4
-#### A masked pattern was here ####
PREHOOK: query: create table locations_n4 (
locationid int,
name varchar(256))
@@ -138,16 +108,6 @@ POSTHOOK: Input: _dummy_database@_dummy_table
POSTHOOK: Output: default@locations_n4
POSTHOOK: Lineage: locations_n4.locationid SCRIPT []
POSTHOOK: Lineage: locations_n4.name SCRIPT []
-PREHOOK: query: analyze table locations_n4 compute statistics for columns
-PREHOOK: type: ANALYZE_TABLE
-PREHOOK: Input: default@locations_n4
-PREHOOK: Output: default@locations_n4
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table locations_n4 compute statistics for columns
-POSTHOOK: type: ANALYZE_TABLE
-POSTHOOK: Input: default@locations_n4
-POSTHOOK: Output: default@locations_n4
-#### A masked pattern was here ####
PREHOOK: query: alter table emps_n8 add constraint pk1 primary key (empid) disable novalidate rely
PREHOOK: type: ALTERTABLE_ADDCONSTRAINT
POSTHOOK: query: alter table emps_n8 add constraint pk1 primary key (empid) disable novalidate rely
@@ -218,16 +178,6 @@ POSTHOOK: Input: default@emps_n8
POSTHOOK: Input: default@locations_n4
POSTHOOK: Output: database:default
POSTHOOK: Output: default@mv1_n4
-PREHOOK: query: analyze table mv1_n4 compute statistics for columns
-PREHOOK: type: ANALYZE_TABLE
-PREHOOK: Input: default@mv1_n4
-PREHOOK: Output: default@mv1_n4
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table mv1_n4 compute statistics for columns
-POSTHOOK: type: ANALYZE_TABLE
-POSTHOOK: Input: default@mv1_n4
-POSTHOOK: Output: default@mv1_n4
-#### A masked pattern was here ####
PREHOOK: query: explain
select dependents_n4.empid, depts_n6.deptno
from depts_n6
@@ -525,16 +475,6 @@ POSTHOOK: Input: default@emps_n8
POSTHOOK: Input: default@locations_n4
POSTHOOK: Output: database:default
POSTHOOK: Output: default@mv1_n4
-PREHOOK: query: analyze table mv1_n4 compute statistics for columns
-PREHOOK: type: ANALYZE_TABLE
-PREHOOK: Input: default@mv1_n4
-PREHOOK: Output: default@mv1_n4
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table mv1_n4 compute statistics for columns
-POSTHOOK: type: ANALYZE_TABLE
-POSTHOOK: Input: default@mv1_n4
-POSTHOOK: Output: default@mv1_n4
-#### A masked pattern was here ####
PREHOOK: query: explain
select dependents_n4.empid, count(emps_n8.salary) + 1
from depts_n6
@@ -864,16 +804,6 @@ POSTHOOK: Input: default@depts_n6
POSTHOOK: Input: default@emps_n8
POSTHOOK: Output: database:default
POSTHOOK: Output: default@mv1_n4
-PREHOOK: query: analyze table mv1_n4 compute statistics for columns
-PREHOOK: type: ANALYZE_TABLE
-PREHOOK: Input: default@mv1_n4
-PREHOOK: Output: default@mv1_n4
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table mv1_n4 compute statistics for columns
-POSTHOOK: type: ANALYZE_TABLE
-POSTHOOK: Input: default@mv1_n4
-POSTHOOK: Output: default@mv1_n4
-#### A masked pattern was here ####
PREHOOK: query: explain
select dependents_n4.empid
from depts_n6
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/llap/materialized_view_rewrite_8.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/materialized_view_rewrite_8.q.out b/ql/src/test/results/clientpositive/llap/materialized_view_rewrite_8.q.out
index aa8763f..a11c846 100644
--- a/ql/src/test/results/clientpositive/llap/materialized_view_rewrite_8.q.out
+++ b/ql/src/test/results/clientpositive/llap/materialized_view_rewrite_8.q.out
@@ -40,16 +40,6 @@ POSTHOOK: Lineage: source_table_001.my_date SCRIPT []
POSTHOOK: Lineage: source_table_001.my_id SCRIPT []
POSTHOOK: Lineage: source_table_001.my_id2 SCRIPT []
POSTHOOK: Lineage: source_table_001.up_volume SCRIPT []
-PREHOOK: query: analyze table source_table_001 compute statistics for columns
-PREHOOK: type: ANALYZE_TABLE
-PREHOOK: Input: default@source_table_001
-PREHOOK: Output: default@source_table_001
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table source_table_001 compute statistics for columns
-POSTHOOK: type: ANALYZE_TABLE
-POSTHOOK: Input: default@source_table_001
-POSTHOOK: Output: default@source_table_001
-#### A masked pattern was here ####
PREHOOK: query: CREATE MATERIALIZED VIEW source_table_001_mv AS
SELECT
SUM(A.DOWN_VOLUME) AS DOWN_VOLUME_SUM,
@@ -72,16 +62,6 @@ POSTHOOK: type: CREATE_MATERIALIZED_VIEW
POSTHOOK: Input: default@source_table_001
POSTHOOK: Output: database:default
POSTHOOK: Output: default@source_table_001_mv
-PREHOOK: query: analyze table source_table_001_mv compute statistics for columns
-PREHOOK: type: ANALYZE_TABLE
-PREHOOK: Input: default@source_table_001_mv
-PREHOOK: Output: default@source_table_001_mv
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table source_table_001_mv compute statistics for columns
-POSTHOOK: type: ANALYZE_TABLE
-POSTHOOK: Input: default@source_table_001_mv
-POSTHOOK: Output: default@source_table_001_mv
-#### A masked pattern was here ####
PREHOOK: query: explain
select
SUM(A.DOWN_VOLUME) AS DOWNLOAD_VOLUME_BYTES,
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/llap/materialized_view_rewrite_9.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/materialized_view_rewrite_9.q.out b/ql/src/test/results/clientpositive/llap/materialized_view_rewrite_9.q.out
index 3c1de08..ea50495 100644
--- a/ql/src/test/results/clientpositive/llap/materialized_view_rewrite_9.q.out
+++ b/ql/src/test/results/clientpositive/llap/materialized_view_rewrite_9.q.out
@@ -40,16 +40,6 @@ POSTHOOK: Lineage: source_table_001_n0.my_date SCRIPT []
POSTHOOK: Lineage: source_table_001_n0.my_id SCRIPT []
POSTHOOK: Lineage: source_table_001_n0.my_id2 SCRIPT []
POSTHOOK: Lineage: source_table_001_n0.up_volume SCRIPT []
-PREHOOK: query: analyze table source_table_001_n0 compute statistics for columns
-PREHOOK: type: ANALYZE_TABLE
-PREHOOK: Input: default@source_table_001_n0
-PREHOOK: Output: default@source_table_001_n0
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table source_table_001_n0 compute statistics for columns
-POSTHOOK: type: ANALYZE_TABLE
-POSTHOOK: Input: default@source_table_001_n0
-POSTHOOK: Output: default@source_table_001_n0
-#### A masked pattern was here ####
PREHOOK: query: CREATE MATERIALIZED VIEW source_table_001_mv_n0 AS
SELECT
SUM(A.DOWN_VOLUME) AS DOWN_VOLUME_SUM,
@@ -72,16 +62,6 @@ POSTHOOK: type: CREATE_MATERIALIZED_VIEW
POSTHOOK: Input: default@source_table_001_n0
POSTHOOK: Output: database:default
POSTHOOK: Output: default@source_table_001_mv_n0
-PREHOOK: query: analyze table source_table_001_mv_n0 compute statistics for columns
-PREHOOK: type: ANALYZE_TABLE
-PREHOOK: Input: default@source_table_001_mv_n0
-PREHOOK: Output: default@source_table_001_mv_n0
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table source_table_001_mv_n0 compute statistics for columns
-POSTHOOK: type: ANALYZE_TABLE
-POSTHOOK: Input: default@source_table_001_mv_n0
-POSTHOOK: Output: default@source_table_001_mv_n0
-#### A masked pattern was here ####
PREHOOK: query: explain
select
SUM(A.DOWN_VOLUME) AS DOWNLOAD_VOLUME_BYTES,
@@ -194,16 +174,6 @@ POSTHOOK: type: CREATE_MATERIALIZED_VIEW
POSTHOOK: Input: default@source_table_001_n0
POSTHOOK: Output: database:default
POSTHOOK: Output: default@source_table_001_mv_n0
-PREHOOK: query: analyze table source_table_001_mv_n0 compute statistics for columns
-PREHOOK: type: ANALYZE_TABLE
-PREHOOK: Input: default@source_table_001_mv_n0
-PREHOOK: Output: default@source_table_001_mv_n0
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table source_table_001_mv_n0 compute statistics for columns
-POSTHOOK: type: ANALYZE_TABLE
-POSTHOOK: Input: default@source_table_001_mv_n0
-POSTHOOK: Output: default@source_table_001_mv_n0
-#### A masked pattern was here ####
PREHOOK: query: explain
select
SUM(A.DOWN_VOLUME) AS DOWNLOAD_VOLUME_BYTES,
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/llap/materialized_view_rewrite_empty.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/materialized_view_rewrite_empty.q.out b/ql/src/test/results/clientpositive/llap/materialized_view_rewrite_empty.q.out
index 610ab6d..61a9365 100644
--- a/ql/src/test/results/clientpositive/llap/materialized_view_rewrite_empty.q.out
+++ b/ql/src/test/results/clientpositive/llap/materialized_view_rewrite_empty.q.out
@@ -18,16 +18,6 @@ stored as orc TBLPROPERTIES ('transactional'='true')
POSTHOOK: type: CREATETABLE
POSTHOOK: Output: database:default
POSTHOOK: Output: default@emps_mv_rewrite_empty
-PREHOOK: query: analyze table emps_mv_rewrite_empty compute statistics for columns
-PREHOOK: type: ANALYZE_TABLE
-PREHOOK: Input: default@emps_mv_rewrite_empty
-PREHOOK: Output: default@emps_mv_rewrite_empty
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table emps_mv_rewrite_empty compute statistics for columns
-POSTHOOK: type: ANALYZE_TABLE
-POSTHOOK: Input: default@emps_mv_rewrite_empty
-POSTHOOK: Output: default@emps_mv_rewrite_empty
-#### A masked pattern was here ####
PREHOOK: query: create materialized view emps_mv_rewrite_empty_mv1 as
select * from emps_mv_rewrite_empty where empid < 150
PREHOOK: type: CREATE_MATERIALIZED_VIEW
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/llap/materialized_view_rewrite_no_join_opt.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/materialized_view_rewrite_no_join_opt.q.out b/ql/src/test/results/clientpositive/llap/materialized_view_rewrite_no_join_opt.q.out
index 806df43..b022ee8 100644
--- a/ql/src/test/results/clientpositive/llap/materialized_view_rewrite_no_join_opt.q.out
+++ b/ql/src/test/results/clientpositive/llap/materialized_view_rewrite_no_join_opt.q.out
@@ -33,16 +33,6 @@ POSTHOOK: Lineage: emps_n30.deptno SCRIPT []
POSTHOOK: Lineage: emps_n30.empid SCRIPT []
POSTHOOK: Lineage: emps_n30.name SCRIPT []
POSTHOOK: Lineage: emps_n30.salary SCRIPT []
-PREHOOK: query: analyze table emps_n30 compute statistics for columns
-PREHOOK: type: ANALYZE_TABLE
-PREHOOK: Input: default@emps_n30
-PREHOOK: Output: default@emps_n30
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table emps_n30 compute statistics for columns
-POSTHOOK: type: ANALYZE_TABLE
-POSTHOOK: Input: default@emps_n30
-POSTHOOK: Output: default@emps_n30
-#### A masked pattern was here ####
PREHOOK: query: create table depts_n20 (
deptno int,
name varchar(256),
@@ -70,16 +60,6 @@ POSTHOOK: Output: default@depts_n20
POSTHOOK: Lineage: depts_n20.deptno SCRIPT []
POSTHOOK: Lineage: depts_n20.locationid SCRIPT []
POSTHOOK: Lineage: depts_n20.name SCRIPT []
-PREHOOK: query: analyze table depts_n20 compute statistics for columns
-PREHOOK: type: ANALYZE_TABLE
-PREHOOK: Input: default@depts_n20
-PREHOOK: Output: default@depts_n20
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table depts_n20 compute statistics for columns
-POSTHOOK: type: ANALYZE_TABLE
-POSTHOOK: Input: default@depts_n20
-POSTHOOK: Output: default@depts_n20
-#### A masked pattern was here ####
PREHOOK: query: create table dependents_n20 (
empid int,
name varchar(256))
@@ -104,16 +84,6 @@ POSTHOOK: Input: _dummy_database@_dummy_table
POSTHOOK: Output: default@dependents_n20
POSTHOOK: Lineage: dependents_n20.empid SCRIPT []
POSTHOOK: Lineage: dependents_n20.name SCRIPT []
-PREHOOK: query: analyze table dependents_n20 compute statistics for columns
-PREHOOK: type: ANALYZE_TABLE
-PREHOOK: Input: default@dependents_n20
-PREHOOK: Output: default@dependents_n20
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table dependents_n20 compute statistics for columns
-POSTHOOK: type: ANALYZE_TABLE
-POSTHOOK: Input: default@dependents_n20
-POSTHOOK: Output: default@dependents_n20
-#### A masked pattern was here ####
PREHOOK: query: create table locations_n20 (
locationid int,
name varchar(256))
@@ -138,16 +108,6 @@ POSTHOOK: Input: _dummy_database@_dummy_table
POSTHOOK: Output: default@locations_n20
POSTHOOK: Lineage: locations_n20.locationid SCRIPT []
POSTHOOK: Lineage: locations_n20.name SCRIPT []
-PREHOOK: query: analyze table locations_n20 compute statistics for columns
-PREHOOK: type: ANALYZE_TABLE
-PREHOOK: Input: default@locations_n20
-PREHOOK: Output: default@locations_n20
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table locations_n20 compute statistics for columns
-POSTHOOK: type: ANALYZE_TABLE
-POSTHOOK: Input: default@locations_n20
-POSTHOOK: Output: default@locations_n20
-#### A masked pattern was here ####
PREHOOK: query: alter table emps_n30 add constraint pk1 primary key (empid) disable novalidate rely
PREHOOK: type: ALTERTABLE_ADDCONSTRAINT
POSTHOOK: query: alter table emps_n30 add constraint pk1 primary key (empid) disable novalidate rely
@@ -186,16 +146,6 @@ POSTHOOK: type: CREATE_MATERIALIZED_VIEW
POSTHOOK: Input: default@emps_n30
POSTHOOK: Output: database:default
POSTHOOK: Output: default@mv1_n20
-PREHOOK: query: analyze table mv1_n20 compute statistics for columns
-PREHOOK: type: ANALYZE_TABLE
-PREHOOK: Input: default@mv1_n20
-PREHOOK: Output: default@mv1_n20
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table mv1_n20 compute statistics for columns
-POSTHOOK: type: ANALYZE_TABLE
-POSTHOOK: Input: default@mv1_n20
-POSTHOOK: Output: default@mv1_n20
-#### A masked pattern was here ####
PREHOOK: query: explain
select emps_n30.name, emps_n30.salary, emps_n30.commission
from emps_n30
@@ -339,16 +289,6 @@ POSTHOOK: Input: default@depts_n20
POSTHOOK: Input: default@emps_n30
POSTHOOK: Output: database:default
POSTHOOK: Output: default@mv1_n20
-PREHOOK: query: analyze table mv1_n20 compute statistics for columns
-PREHOOK: type: ANALYZE_TABLE
-PREHOOK: Input: default@mv1_n20
-PREHOOK: Output: default@mv1_n20
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table mv1_n20 compute statistics for columns
-POSTHOOK: type: ANALYZE_TABLE
-POSTHOOK: Input: default@mv1_n20
-POSTHOOK: Output: default@mv1_n20
-#### A masked pattern was here ####
PREHOOK: query: explain
select depts_n20.deptno, count(*) as c, sum(empid) as s
from emps_n30 join depts_n20 using (deptno)
@@ -475,16 +415,6 @@ POSTHOOK: Input: default@dependents_n20
POSTHOOK: Input: default@emps_n30
POSTHOOK: Output: database:default
POSTHOOK: Output: default@mv1_n20
-PREHOOK: query: analyze table mv1_n20 compute statistics for columns
-PREHOOK: type: ANALYZE_TABLE
-PREHOOK: Input: default@mv1_n20
-PREHOOK: Output: default@mv1_n20
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table mv1_n20 compute statistics for columns
-POSTHOOK: type: ANALYZE_TABLE
-POSTHOOK: Input: default@mv1_n20
-POSTHOOK: Output: default@mv1_n20
-#### A masked pattern was here ####
PREHOOK: query: explain
select dependents_n20.empid, sum(salary) as s
from emps_n30
@@ -651,16 +581,6 @@ POSTHOOK: Input: default@dependents_n20
POSTHOOK: Input: default@emps_n30
POSTHOOK: Output: database:default
POSTHOOK: Output: default@mv1_n20
-PREHOOK: query: analyze table mv1_n20 compute statistics for columns
-PREHOOK: type: ANALYZE_TABLE
-PREHOOK: Input: default@mv1_n20
-PREHOOK: Output: default@mv1_n20
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table mv1_n20 compute statistics for columns
-POSTHOOK: type: ANALYZE_TABLE
-POSTHOOK: Input: default@mv1_n20
-POSTHOOK: Output: default@mv1_n20
-#### A masked pattern was here ####
PREHOOK: query: explain
select emps_n30.empid, dependents_n20.empid, emps_n30.deptno
from emps_n30
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/llap/materialized_view_rewrite_no_join_opt_2.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/materialized_view_rewrite_no_join_opt_2.q.out b/ql/src/test/results/clientpositive/llap/materialized_view_rewrite_no_join_opt_2.q.out
index 61b0efc..d9a48fb 100644
--- a/ql/src/test/results/clientpositive/llap/materialized_view_rewrite_no_join_opt_2.q.out
+++ b/ql/src/test/results/clientpositive/llap/materialized_view_rewrite_no_join_opt_2.q.out
@@ -33,16 +33,6 @@ POSTHOOK: Lineage: emps_n30.deptno SCRIPT []
POSTHOOK: Lineage: emps_n30.empid SCRIPT []
POSTHOOK: Lineage: emps_n30.name SCRIPT []
POSTHOOK: Lineage: emps_n30.salary SCRIPT []
-PREHOOK: query: analyze table emps_n30 compute statistics for columns
-PREHOOK: type: ANALYZE_TABLE
-PREHOOK: Input: default@emps_n30
-PREHOOK: Output: default@emps_n30
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table emps_n30 compute statistics for columns
-POSTHOOK: type: ANALYZE_TABLE
-POSTHOOK: Input: default@emps_n30
-POSTHOOK: Output: default@emps_n30
-#### A masked pattern was here ####
PREHOOK: query: create table depts_n20 (
deptno int,
name varchar(256),
@@ -70,16 +60,6 @@ POSTHOOK: Output: default@depts_n20
POSTHOOK: Lineage: depts_n20.deptno SCRIPT []
POSTHOOK: Lineage: depts_n20.locationid SCRIPT []
POSTHOOK: Lineage: depts_n20.name SCRIPT []
-PREHOOK: query: analyze table depts_n20 compute statistics for columns
-PREHOOK: type: ANALYZE_TABLE
-PREHOOK: Input: default@depts_n20
-PREHOOK: Output: default@depts_n20
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table depts_n20 compute statistics for columns
-POSTHOOK: type: ANALYZE_TABLE
-POSTHOOK: Input: default@depts_n20
-POSTHOOK: Output: default@depts_n20
-#### A masked pattern was here ####
PREHOOK: query: create table dependents_n20 (
empid int,
name varchar(256))
@@ -104,16 +84,6 @@ POSTHOOK: Input: _dummy_database@_dummy_table
POSTHOOK: Output: default@dependents_n20
POSTHOOK: Lineage: dependents_n20.empid SCRIPT []
POSTHOOK: Lineage: dependents_n20.name SCRIPT []
-PREHOOK: query: analyze table dependents_n20 compute statistics for columns
-PREHOOK: type: ANALYZE_TABLE
-PREHOOK: Input: default@dependents_n20
-PREHOOK: Output: default@dependents_n20
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table dependents_n20 compute statistics for columns
-POSTHOOK: type: ANALYZE_TABLE
-POSTHOOK: Input: default@dependents_n20
-POSTHOOK: Output: default@dependents_n20
-#### A masked pattern was here ####
PREHOOK: query: create table locations_n20 (
locationid int,
name varchar(256))
@@ -138,16 +108,6 @@ POSTHOOK: Input: _dummy_database@_dummy_table
POSTHOOK: Output: default@locations_n20
POSTHOOK: Lineage: locations_n20.locationid SCRIPT []
POSTHOOK: Lineage: locations_n20.name SCRIPT []
-PREHOOK: query: analyze table locations_n20 compute statistics for columns
-PREHOOK: type: ANALYZE_TABLE
-PREHOOK: Input: default@locations_n20
-PREHOOK: Output: default@locations_n20
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table locations_n20 compute statistics for columns
-POSTHOOK: type: ANALYZE_TABLE
-POSTHOOK: Input: default@locations_n20
-POSTHOOK: Output: default@locations_n20
-#### A masked pattern was here ####
PREHOOK: query: alter table emps_n30 add constraint pk1 primary key (empid) disable novalidate rely
PREHOOK: type: ALTERTABLE_ADDCONSTRAINT
POSTHOOK: query: alter table emps_n30 add constraint pk1 primary key (empid) disable novalidate rely
@@ -190,20 +150,6 @@ POSTHOOK: Lineage: mv1_part_n2 PARTITION(deptno=10).commission SIMPLE [(emps_n30
POSTHOOK: Lineage: mv1_part_n2 PARTITION(deptno=10).empid SIMPLE [(emps_n30)emps_n30.FieldSchema(name:empid, type:int, comment:null), ]
POSTHOOK: Lineage: mv1_part_n2 PARTITION(deptno=10).name SIMPLE [(emps_n30)emps_n30.FieldSchema(name:name, type:varchar(256), comment:null), ]
POSTHOOK: Lineage: mv1_part_n2 PARTITION(deptno=10).salary SIMPLE [(emps_n30)emps_n30.FieldSchema(name:salary, type:float, comment:null), ]
-PREHOOK: query: analyze table mv1_part_n2 compute statistics for columns
-PREHOOK: type: ANALYZE_TABLE
-PREHOOK: Input: default@mv1_part_n2
-PREHOOK: Input: default@mv1_part_n2@deptno=10
-PREHOOK: Output: default@mv1_part_n2
-PREHOOK: Output: default@mv1_part_n2@deptno=10
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table mv1_part_n2 compute statistics for columns
-POSTHOOK: type: ANALYZE_TABLE
-POSTHOOK: Input: default@mv1_part_n2
-POSTHOOK: Input: default@mv1_part_n2@deptno=10
-POSTHOOK: Output: default@mv1_part_n2
-POSTHOOK: Output: default@mv1_part_n2@deptno=10
-#### A masked pattern was here ####
PREHOOK: query: explain
select *
from (select * from emps_n30 where empid < 120) t
@@ -369,24 +315,6 @@ POSTHOOK: Lineage: mv1_part_n2 PARTITION(deptno=10).salary SIMPLE [(emps_n30)emp
POSTHOOK: Lineage: mv1_part_n2 PARTITION(deptno=20).commission SIMPLE [(emps_n30)emps_n30.FieldSchema(name:commission, type:int, comment:null), ]
POSTHOOK: Lineage: mv1_part_n2 PARTITION(deptno=20).name SIMPLE [(emps_n30)emps_n30.FieldSchema(name:name, type:varchar(256), comment:null), ]
POSTHOOK: Lineage: mv1_part_n2 PARTITION(deptno=20).salary SIMPLE [(emps_n30)emps_n30.FieldSchema(name:salary, type:float, comment:null), ]
-PREHOOK: query: analyze table mv1_part_n2 compute statistics for columns
-PREHOOK: type: ANALYZE_TABLE
-PREHOOK: Input: default@mv1_part_n2
-PREHOOK: Input: default@mv1_part_n2@deptno=10
-PREHOOK: Input: default@mv1_part_n2@deptno=20
-PREHOOK: Output: default@mv1_part_n2
-PREHOOK: Output: default@mv1_part_n2@deptno=10
-PREHOOK: Output: default@mv1_part_n2@deptno=20
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table mv1_part_n2 compute statistics for columns
-POSTHOOK: type: ANALYZE_TABLE
-POSTHOOK: Input: default@mv1_part_n2
-POSTHOOK: Input: default@mv1_part_n2@deptno=10
-POSTHOOK: Input: default@mv1_part_n2@deptno=20
-POSTHOOK: Output: default@mv1_part_n2
-POSTHOOK: Output: default@mv1_part_n2@deptno=10
-POSTHOOK: Output: default@mv1_part_n2@deptno=20
-#### A masked pattern was here ####
PREHOOK: query: explain
select emps_n30.name, emps_n30.salary, emps_n30.commission
from emps_n30
@@ -546,20 +474,6 @@ POSTHOOK: Lineage: mv1_part_n2 PARTITION(deptno=10).commission SIMPLE [(emps_n30
POSTHOOK: Lineage: mv1_part_n2 PARTITION(deptno=10).empid SIMPLE [(emps_n30)emps_n30.FieldSchema(name:empid, type:int, comment:null), ]
POSTHOOK: Lineage: mv1_part_n2 PARTITION(deptno=10).name SIMPLE [(emps_n30)emps_n30.FieldSchema(name:name, type:varchar(256), comment:null), ]
POSTHOOK: Lineage: mv1_part_n2 PARTITION(deptno=10).salary SIMPLE [(emps_n30)emps_n30.FieldSchema(name:salary, type:float, comment:null), ]
-PREHOOK: query: analyze table mv1_part_n2 compute statistics for columns
-PREHOOK: type: ANALYZE_TABLE
-PREHOOK: Input: default@mv1_part_n2
-PREHOOK: Input: default@mv1_part_n2@deptno=10
-PREHOOK: Output: default@mv1_part_n2
-PREHOOK: Output: default@mv1_part_n2@deptno=10
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table mv1_part_n2 compute statistics for columns
-POSTHOOK: type: ANALYZE_TABLE
-POSTHOOK: Input: default@mv1_part_n2
-POSTHOOK: Input: default@mv1_part_n2@deptno=10
-POSTHOOK: Output: default@mv1_part_n2
-POSTHOOK: Output: default@mv1_part_n2@deptno=10
-#### A masked pattern was here ####
PREHOOK: query: explain
select * from emps_n30 where empid > 120
union all select * from emps_n30 where empid < 150
@@ -690,32 +604,6 @@ POSTHOOK: Lineage: mv1_part_n2 PARTITION(name=Bill).salary SIMPLE [(emps_n30)emp
POSTHOOK: Lineage: mv1_part_n2 PARTITION(name=Eric).salary SIMPLE [(emps_n30)emps_n30.FieldSchema(name:salary, type:float, comment:null), ]
POSTHOOK: Lineage: mv1_part_n2 PARTITION(name=Sebastian).salary SIMPLE [(emps_n30)emps_n30.FieldSchema(name:salary, type:float, comment:null), ]
POSTHOOK: Lineage: mv1_part_n2 PARTITION(name=Theodore).salary SIMPLE [(emps_n30)emps_n30.FieldSchema(name:salary, type:float, comment:null), ]
-PREHOOK: query: analyze table mv1_part_n2 compute statistics for columns
-PREHOOK: type: ANALYZE_TABLE
-PREHOOK: Input: default@mv1_part_n2
-PREHOOK: Input: default@mv1_part_n2@name=Bill
-PREHOOK: Input: default@mv1_part_n2@name=Eric
-PREHOOK: Input: default@mv1_part_n2@name=Sebastian
-PREHOOK: Input: default@mv1_part_n2@name=Theodore
-PREHOOK: Output: default@mv1_part_n2
-PREHOOK: Output: default@mv1_part_n2@name=Bill
-PREHOOK: Output: default@mv1_part_n2@name=Eric
-PREHOOK: Output: default@mv1_part_n2@name=Sebastian
-PREHOOK: Output: default@mv1_part_n2@name=Theodore
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table mv1_part_n2 compute statistics for columns
-POSTHOOK: type: ANALYZE_TABLE
-POSTHOOK: Input: default@mv1_part_n2
-POSTHOOK: Input: default@mv1_part_n2@name=Bill
-POSTHOOK: Input: default@mv1_part_n2@name=Eric
-POSTHOOK: Input: default@mv1_part_n2@name=Sebastian
-POSTHOOK: Input: default@mv1_part_n2@name=Theodore
-POSTHOOK: Output: default@mv1_part_n2
-POSTHOOK: Output: default@mv1_part_n2@name=Bill
-POSTHOOK: Output: default@mv1_part_n2@name=Eric
-POSTHOOK: Output: default@mv1_part_n2@name=Sebastian
-POSTHOOK: Output: default@mv1_part_n2@name=Theodore
-#### A masked pattern was here ####
PREHOOK: query: explain
select name, salary from emps_n30 group by name, salary
PREHOOK: type: QUERY
@@ -802,32 +690,6 @@ POSTHOOK: Lineage: mv1_part_n2 PARTITION(name=Bill).salary SIMPLE [(emps_n30)emp
POSTHOOK: Lineage: mv1_part_n2 PARTITION(name=Eric).salary SIMPLE [(emps_n30)emps_n30.FieldSchema(name:salary, type:float, comment:null), ]
POSTHOOK: Lineage: mv1_part_n2 PARTITION(name=Sebastian).salary SIMPLE [(emps_n30)emps_n30.FieldSchema(name:salary, type:float, comment:null), ]
POSTHOOK: Lineage: mv1_part_n2 PARTITION(name=Theodore).salary SIMPLE [(emps_n30)emps_n30.FieldSchema(name:salary, type:float, comment:null), ]
-PREHOOK: query: analyze table mv1_part_n2 compute statistics for columns
-PREHOOK: type: ANALYZE_TABLE
-PREHOOK: Input: default@mv1_part_n2
-PREHOOK: Input: default@mv1_part_n2@name=Bill
-PREHOOK: Input: default@mv1_part_n2@name=Eric
-PREHOOK: Input: default@mv1_part_n2@name=Sebastian
-PREHOOK: Input: default@mv1_part_n2@name=Theodore
-PREHOOK: Output: default@mv1_part_n2
-PREHOOK: Output: default@mv1_part_n2@name=Bill
-PREHOOK: Output: default@mv1_part_n2@name=Eric
-PREHOOK: Output: default@mv1_part_n2@name=Sebastian
-PREHOOK: Output: default@mv1_part_n2@name=Theodore
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table mv1_part_n2 compute statistics for columns
-POSTHOOK: type: ANALYZE_TABLE
-POSTHOOK: Input: default@mv1_part_n2
-POSTHOOK: Input: default@mv1_part_n2@name=Bill
-POSTHOOK: Input: default@mv1_part_n2@name=Eric
-POSTHOOK: Input: default@mv1_part_n2@name=Sebastian
-POSTHOOK: Input: default@mv1_part_n2@name=Theodore
-POSTHOOK: Output: default@mv1_part_n2
-POSTHOOK: Output: default@mv1_part_n2@name=Bill
-POSTHOOK: Output: default@mv1_part_n2@name=Eric
-POSTHOOK: Output: default@mv1_part_n2@name=Sebastian
-POSTHOOK: Output: default@mv1_part_n2@name=Theodore
-#### A masked pattern was here ####
PREHOOK: query: explain
select name from emps_n30 group by name
PREHOOK: type: QUERY
@@ -952,28 +814,6 @@ POSTHOOK: Output: default@mv1_part_n2@name=Theodore
POSTHOOK: Lineage: mv1_part_n2 PARTITION(name=Bill).salary SIMPLE [(emps_n30)emps_n30.FieldSchema(name:salary, type:float, comment:null), ]
POSTHOOK: Lineage: mv1_part_n2 PARTITION(name=Sebastian).salary SIMPLE [(emps_n30)emps_n30.FieldSchema(name:salary, type:float, comment:null), ]
POSTHOOK: Lineage: mv1_part_n2 PARTITION(name=Theodore).salary SIMPLE [(emps_n30)emps_n30.FieldSchema(name:salary, type:float, comment:null), ]
-PREHOOK: query: analyze table mv1_part_n2 compute statistics for columns
-PREHOOK: type: ANALYZE_TABLE
-PREHOOK: Input: default@mv1_part_n2
-PREHOOK: Input: default@mv1_part_n2@name=Bill
-PREHOOK: Input: default@mv1_part_n2@name=Sebastian
-PREHOOK: Input: default@mv1_part_n2@name=Theodore
-PREHOOK: Output: default@mv1_part_n2
-PREHOOK: Output: default@mv1_part_n2@name=Bill
-PREHOOK: Output: default@mv1_part_n2@name=Sebastian
-PREHOOK: Output: default@mv1_part_n2@name=Theodore
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table mv1_part_n2 compute statistics for columns
-POSTHOOK: type: ANALYZE_TABLE
-POSTHOOK: Input: default@mv1_part_n2
-POSTHOOK: Input: default@mv1_part_n2@name=Bill
-POSTHOOK: Input: default@mv1_part_n2@name=Sebastian
-POSTHOOK: Input: default@mv1_part_n2@name=Theodore
-POSTHOOK: Output: default@mv1_part_n2
-POSTHOOK: Output: default@mv1_part_n2@name=Bill
-POSTHOOK: Output: default@mv1_part_n2@name=Sebastian
-POSTHOOK: Output: default@mv1_part_n2@name=Theodore
-#### A masked pattern was here ####
PREHOOK: query: explain
select name from emps_n30 where deptno = 10 group by name
PREHOOK: type: QUERY
@@ -1105,32 +945,6 @@ POSTHOOK: Lineage: mv1_part_n2 PARTITION(name=Sebastian).salary SIMPLE [(emps_n3
POSTHOOK: Lineage: mv1_part_n2 PARTITION(name=Theodore).c EXPRESSION [(emps_n30)emps_n30.null, ]
POSTHOOK: Lineage: mv1_part_n2 PARTITION(name=Theodore).s EXPRESSION [(emps_n30)emps_n30.FieldSchema(name:empid, type:int, comment:null), ]
POSTHOOK: Lineage: mv1_part_n2 PARTITION(name=Theodore).salary SIMPLE [(emps_n30)emps_n30.FieldSchema(name:salary, type:float, comment:null), ]
-PREHOOK: query: analyze table mv1_part_n2 compute statistics for columns
-PREHOOK: type: ANALYZE_TABLE
-PREHOOK: Input: default@mv1_part_n2
-PREHOOK: Input: default@mv1_part_n2@name=Bill
-PREHOOK: Input: default@mv1_part_n2@name=Eric
-PREHOOK: Input: default@mv1_part_n2@name=Sebastian
-PREHOOK: Input: default@mv1_part_n2@name=Theodore
-PREHOOK: Output: default@mv1_part_n2
-PREHOOK: Output: default@mv1_part_n2@name=Bill
-PREHOOK: Output: default@mv1_part_n2@name=Eric
-PREHOOK: Output: default@mv1_part_n2@name=Sebastian
-PREHOOK: Output: default@mv1_part_n2@name=Theodore
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table mv1_part_n2 compute statistics for columns
-POSTHOOK: type: ANALYZE_TABLE
-POSTHOOK: Input: default@mv1_part_n2
-POSTHOOK: Input: default@mv1_part_n2@name=Bill
-POSTHOOK: Input: default@mv1_part_n2@name=Eric
-POSTHOOK: Input: default@mv1_part_n2@name=Sebastian
-POSTHOOK: Input: default@mv1_part_n2@name=Theodore
-POSTHOOK: Output: default@mv1_part_n2
-POSTHOOK: Output: default@mv1_part_n2@name=Bill
-POSTHOOK: Output: default@mv1_part_n2@name=Eric
-POSTHOOK: Output: default@mv1_part_n2@name=Sebastian
-POSTHOOK: Output: default@mv1_part_n2@name=Theodore
-#### A masked pattern was here ####
PREHOOK: query: explain
select name from emps_n30 group by name
PREHOOK: type: QUERY
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/llap/materialized_view_rewrite_part_1.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/materialized_view_rewrite_part_1.q.out b/ql/src/test/results/clientpositive/llap/materialized_view_rewrite_part_1.q.out
index 68f4947..786e2c7 100644
--- a/ql/src/test/results/clientpositive/llap/materialized_view_rewrite_part_1.q.out
+++ b/ql/src/test/results/clientpositive/llap/materialized_view_rewrite_part_1.q.out
@@ -33,16 +33,6 @@ POSTHOOK: Lineage: emps_n30.deptno SCRIPT []
POSTHOOK: Lineage: emps_n30.empid SCRIPT []
POSTHOOK: Lineage: emps_n30.name SCRIPT []
POSTHOOK: Lineage: emps_n30.salary SCRIPT []
-PREHOOK: query: analyze table emps_n30 compute statistics for columns
-PREHOOK: type: ANALYZE_TABLE
-PREHOOK: Input: default@emps_n30
-PREHOOK: Output: default@emps_n30
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table emps_n30 compute statistics for columns
-POSTHOOK: type: ANALYZE_TABLE
-POSTHOOK: Input: default@emps_n30
-POSTHOOK: Output: default@emps_n30
-#### A masked pattern was here ####
PREHOOK: query: create table depts_n20 (
deptno int,
name varchar(256),
@@ -70,16 +60,6 @@ POSTHOOK: Output: default@depts_n20
POSTHOOK: Lineage: depts_n20.deptno SCRIPT []
POSTHOOK: Lineage: depts_n20.locationid SCRIPT []
POSTHOOK: Lineage: depts_n20.name SCRIPT []
-PREHOOK: query: analyze table depts_n20 compute statistics for columns
-PREHOOK: type: ANALYZE_TABLE
-PREHOOK: Input: default@depts_n20
-PREHOOK: Output: default@depts_n20
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table depts_n20 compute statistics for columns
-POSTHOOK: type: ANALYZE_TABLE
-POSTHOOK: Input: default@depts_n20
-POSTHOOK: Output: default@depts_n20
-#### A masked pattern was here ####
PREHOOK: query: create table dependents_n20 (
empid int,
name varchar(256))
@@ -104,16 +84,6 @@ POSTHOOK: Input: _dummy_database@_dummy_table
POSTHOOK: Output: default@dependents_n20
POSTHOOK: Lineage: dependents_n20.empid SCRIPT []
POSTHOOK: Lineage: dependents_n20.name SCRIPT []
-PREHOOK: query: analyze table dependents_n20 compute statistics for columns
-PREHOOK: type: ANALYZE_TABLE
-PREHOOK: Input: default@dependents_n20
-PREHOOK: Output: default@dependents_n20
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table dependents_n20 compute statistics for columns
-POSTHOOK: type: ANALYZE_TABLE
-POSTHOOK: Input: default@dependents_n20
-POSTHOOK: Output: default@dependents_n20
-#### A masked pattern was here ####
PREHOOK: query: create table locations_n20 (
locationid int,
name varchar(256))
@@ -138,16 +108,6 @@ POSTHOOK: Input: _dummy_database@_dummy_table
POSTHOOK: Output: default@locations_n20
POSTHOOK: Lineage: locations_n20.locationid SCRIPT []
POSTHOOK: Lineage: locations_n20.name SCRIPT []
-PREHOOK: query: analyze table locations_n20 compute statistics for columns
-PREHOOK: type: ANALYZE_TABLE
-PREHOOK: Input: default@locations_n20
-PREHOOK: Output: default@locations_n20
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table locations_n20 compute statistics for columns
-POSTHOOK: type: ANALYZE_TABLE
-POSTHOOK: Input: default@locations_n20
-POSTHOOK: Output: default@locations_n20
-#### A masked pattern was here ####
PREHOOK: query: alter table emps_n30 add constraint pk1 primary key (empid) disable novalidate rely
PREHOOK: type: ALTERTABLE_ADDCONSTRAINT
POSTHOOK: query: alter table emps_n30 add constraint pk1 primary key (empid) disable novalidate rely
@@ -190,20 +150,6 @@ POSTHOOK: Lineage: mv1_part_n2 PARTITION(deptno=10).commission SIMPLE [(emps_n30
POSTHOOK: Lineage: mv1_part_n2 PARTITION(deptno=10).empid SIMPLE [(emps_n30)emps_n30.FieldSchema(name:empid, type:int, comment:null), ]
POSTHOOK: Lineage: mv1_part_n2 PARTITION(deptno=10).name SIMPLE [(emps_n30)emps_n30.FieldSchema(name:name, type:varchar(256), comment:null), ]
POSTHOOK: Lineage: mv1_part_n2 PARTITION(deptno=10).salary SIMPLE [(emps_n30)emps_n30.FieldSchema(name:salary, type:float, comment:null), ]
-PREHOOK: query: analyze table mv1_part_n2 compute statistics for columns
-PREHOOK: type: ANALYZE_TABLE
-PREHOOK: Input: default@mv1_part_n2
-PREHOOK: Input: default@mv1_part_n2@deptno=10
-PREHOOK: Output: default@mv1_part_n2
-PREHOOK: Output: default@mv1_part_n2@deptno=10
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table mv1_part_n2 compute statistics for columns
-POSTHOOK: type: ANALYZE_TABLE
-POSTHOOK: Input: default@mv1_part_n2
-POSTHOOK: Input: default@mv1_part_n2@deptno=10
-POSTHOOK: Output: default@mv1_part_n2
-POSTHOOK: Output: default@mv1_part_n2@deptno=10
-#### A masked pattern was here ####
PREHOOK: query: explain
select *
from (select * from emps_n30 where empid < 120) t
@@ -369,24 +315,6 @@ POSTHOOK: Lineage: mv1_part_n2 PARTITION(deptno=10).salary SIMPLE [(emps_n30)emp
POSTHOOK: Lineage: mv1_part_n2 PARTITION(deptno=20).commission SIMPLE [(emps_n30)emps_n30.FieldSchema(name:commission, type:int, comment:null), ]
POSTHOOK: Lineage: mv1_part_n2 PARTITION(deptno=20).name SIMPLE [(emps_n30)emps_n30.FieldSchema(name:name, type:varchar(256), comment:null), ]
POSTHOOK: Lineage: mv1_part_n2 PARTITION(deptno=20).salary SIMPLE [(emps_n30)emps_n30.FieldSchema(name:salary, type:float, comment:null), ]
-PREHOOK: query: analyze table mv1_part_n2 compute statistics for columns
-PREHOOK: type: ANALYZE_TABLE
-PREHOOK: Input: default@mv1_part_n2
-PREHOOK: Input: default@mv1_part_n2@deptno=10
-PREHOOK: Input: default@mv1_part_n2@deptno=20
-PREHOOK: Output: default@mv1_part_n2
-PREHOOK: Output: default@mv1_part_n2@deptno=10
-PREHOOK: Output: default@mv1_part_n2@deptno=20
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table mv1_part_n2 compute statistics for columns
-POSTHOOK: type: ANALYZE_TABLE
-POSTHOOK: Input: default@mv1_part_n2
-POSTHOOK: Input: default@mv1_part_n2@deptno=10
-POSTHOOK: Input: default@mv1_part_n2@deptno=20
-POSTHOOK: Output: default@mv1_part_n2
-POSTHOOK: Output: default@mv1_part_n2@deptno=10
-POSTHOOK: Output: default@mv1_part_n2@deptno=20
-#### A masked pattern was here ####
PREHOOK: query: explain
select emps_n30.name, emps_n30.salary, emps_n30.commission
from emps_n30
@@ -476,20 +404,6 @@ POSTHOOK: Lineage: mv1_part_n2 PARTITION(deptno=10).commission SIMPLE [(emps_n30
POSTHOOK: Lineage: mv1_part_n2 PARTITION(deptno=10).empid SIMPLE [(emps_n30)emps_n30.FieldSchema(name:empid, type:int, comment:null), ]
POSTHOOK: Lineage: mv1_part_n2 PARTITION(deptno=10).name SIMPLE [(emps_n30)emps_n30.FieldSchema(name:name, type:varchar(256), comment:null), ]
POSTHOOK: Lineage: mv1_part_n2 PARTITION(deptno=10).salary SIMPLE [(emps_n30)emps_n30.FieldSchema(name:salary, type:float, comment:null), ]
-PREHOOK: query: analyze table mv1_part_n2 compute statistics for columns
-PREHOOK: type: ANALYZE_TABLE
-PREHOOK: Input: default@mv1_part_n2
-PREHOOK: Input: default@mv1_part_n2@deptno=10
-PREHOOK: Output: default@mv1_part_n2
-PREHOOK: Output: default@mv1_part_n2@deptno=10
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table mv1_part_n2 compute statistics for columns
-POSTHOOK: type: ANALYZE_TABLE
-POSTHOOK: Input: default@mv1_part_n2
-POSTHOOK: Input: default@mv1_part_n2@deptno=10
-POSTHOOK: Output: default@mv1_part_n2
-POSTHOOK: Output: default@mv1_part_n2@deptno=10
-#### A masked pattern was here ####
PREHOOK: query: explain
select * from emps_n30 where empid > 120
union all select * from emps_n30 where empid < 150
@@ -620,32 +534,6 @@ POSTHOOK: Lineage: mv1_part_n2 PARTITION(name=Bill).salary SIMPLE [(emps_n30)emp
POSTHOOK: Lineage: mv1_part_n2 PARTITION(name=Eric).salary SIMPLE [(emps_n30)emps_n30.FieldSchema(name:salary, type:float, comment:null), ]
POSTHOOK: Lineage: mv1_part_n2 PARTITION(name=Sebastian).salary SIMPLE [(emps_n30)emps_n30.FieldSchema(name:salary, type:float, comment:null), ]
POSTHOOK: Lineage: mv1_part_n2 PARTITION(name=Theodore).salary SIMPLE [(emps_n30)emps_n30.FieldSchema(name:salary, type:float, comment:null), ]
-PREHOOK: query: analyze table mv1_part_n2 compute statistics for columns
-PREHOOK: type: ANALYZE_TABLE
-PREHOOK: Input: default@mv1_part_n2
-PREHOOK: Input: default@mv1_part_n2@name=Bill
-PREHOOK: Input: default@mv1_part_n2@name=Eric
-PREHOOK: Input: default@mv1_part_n2@name=Sebastian
-PREHOOK: Input: default@mv1_part_n2@name=Theodore
-PREHOOK: Output: default@mv1_part_n2
-PREHOOK: Output: default@mv1_part_n2@name=Bill
-PREHOOK: Output: default@mv1_part_n2@name=Eric
-PREHOOK: Output: default@mv1_part_n2@name=Sebastian
-PREHOOK: Output: default@mv1_part_n2@name=Theodore
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table mv1_part_n2 compute statistics for columns
-POSTHOOK: type: ANALYZE_TABLE
-POSTHOOK: Input: default@mv1_part_n2
-POSTHOOK: Input: default@mv1_part_n2@name=Bill
-POSTHOOK: Input: default@mv1_part_n2@name=Eric
-POSTHOOK: Input: default@mv1_part_n2@name=Sebastian
-POSTHOOK: Input: default@mv1_part_n2@name=Theodore
-POSTHOOK: Output: default@mv1_part_n2
-POSTHOOK: Output: default@mv1_part_n2@name=Bill
-POSTHOOK: Output: default@mv1_part_n2@name=Eric
-POSTHOOK: Output: default@mv1_part_n2@name=Sebastian
-POSTHOOK: Output: default@mv1_part_n2@name=Theodore
-#### A masked pattern was here ####
PREHOOK: query: explain
select name, salary from emps_n30 group by name, salary
PREHOOK: type: QUERY
@@ -732,32 +620,6 @@ POSTHOOK: Lineage: mv1_part_n2 PARTITION(name=Bill).salary SIMPLE [(emps_n30)emp
POSTHOOK: Lineage: mv1_part_n2 PARTITION(name=Eric).salary SIMPLE [(emps_n30)emps_n30.FieldSchema(name:salary, type:float, comment:null), ]
POSTHOOK: Lineage: mv1_part_n2 PARTITION(name=Sebastian).salary SIMPLE [(emps_n30)emps_n30.FieldSchema(name:salary, type:float, comment:null), ]
POSTHOOK: Lineage: mv1_part_n2 PARTITION(name=Theodore).salary SIMPLE [(emps_n30)emps_n30.FieldSchema(name:salary, type:float, comment:null), ]
-PREHOOK: query: analyze table mv1_part_n2 compute statistics for columns
-PREHOOK: type: ANALYZE_TABLE
-PREHOOK: Input: default@mv1_part_n2
-PREHOOK: Input: default@mv1_part_n2@name=Bill
-PREHOOK: Input: default@mv1_part_n2@name=Eric
-PREHOOK: Input: default@mv1_part_n2@name=Sebastian
-PREHOOK: Input: default@mv1_part_n2@name=Theodore
-PREHOOK: Output: default@mv1_part_n2
-PREHOOK: Output: default@mv1_part_n2@name=Bill
-PREHOOK: Output: default@mv1_part_n2@name=Eric
-PREHOOK: Output: default@mv1_part_n2@name=Sebastian
-PREHOOK: Output: default@mv1_part_n2@name=Theodore
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table mv1_part_n2 compute statistics for columns
-POSTHOOK: type: ANALYZE_TABLE
-POSTHOOK: Input: default@mv1_part_n2
-POSTHOOK: Input: default@mv1_part_n2@name=Bill
-POSTHOOK: Input: default@mv1_part_n2@name=Eric
-POSTHOOK: Input: default@mv1_part_n2@name=Sebastian
-POSTHOOK: Input: default@mv1_part_n2@name=Theodore
-POSTHOOK: Output: default@mv1_part_n2
-POSTHOOK: Output: default@mv1_part_n2@name=Bill
-POSTHOOK: Output: default@mv1_part_n2@name=Eric
-POSTHOOK: Output: default@mv1_part_n2@name=Sebastian
-POSTHOOK: Output: default@mv1_part_n2@name=Theodore
-#### A masked pattern was here ####
PREHOOK: query: explain
select name from emps_n30 group by name
PREHOOK: type: QUERY
@@ -882,28 +744,6 @@ POSTHOOK: Output: default@mv1_part_n2@name=Theodore
POSTHOOK: Lineage: mv1_part_n2 PARTITION(name=Bill).salary SIMPLE [(emps_n30)emps_n30.FieldSchema(name:salary, type:float, comment:null), ]
POSTHOOK: Lineage: mv1_part_n2 PARTITION(name=Sebastian).salary SIMPLE [(emps_n30)emps_n30.FieldSchema(name:salary, type:float, comment:null), ]
POSTHOOK: Lineage: mv1_part_n2 PARTITION(name=Theodore).salary SIMPLE [(emps_n30)emps_n30.FieldSchema(name:salary, type:float, comment:null), ]
-PREHOOK: query: analyze table mv1_part_n2 compute statistics for columns
-PREHOOK: type: ANALYZE_TABLE
-PREHOOK: Input: default@mv1_part_n2
-PREHOOK: Input: default@mv1_part_n2@name=Bill
-PREHOOK: Input: default@mv1_part_n2@name=Sebastian
-PREHOOK: Input: default@mv1_part_n2@name=Theodore
-PREHOOK: Output: default@mv1_part_n2
-PREHOOK: Output: default@mv1_part_n2@name=Bill
-PREHOOK: Output: default@mv1_part_n2@name=Sebastian
-PREHOOK: Output: default@mv1_part_n2@name=Theodore
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table mv1_part_n2 compute statistics for columns
-POSTHOOK: type: ANALYZE_TABLE
-POSTHOOK: Input: default@mv1_part_n2
-POSTHOOK: Input: default@mv1_part_n2@name=Bill
-POSTHOOK: Input: default@mv1_part_n2@name=Sebastian
-POSTHOOK: Input: default@mv1_part_n2@name=Theodore
-POSTHOOK: Output: default@mv1_part_n2
-POSTHOOK: Output: default@mv1_part_n2@name=Bill
-POSTHOOK: Output: default@mv1_part_n2@name=Sebastian
-POSTHOOK: Output: default@mv1_part_n2@name=Theodore
-#### A masked pattern was here ####
PREHOOK: query: explain
select name from emps_n30 where deptno = 10 group by name
PREHOOK: type: QUERY
@@ -1035,32 +875,6 @@ POSTHOOK: Lineage: mv1_part_n2 PARTITION(name=Sebastian).salary SIMPLE [(emps_n3
POSTHOOK: Lineage: mv1_part_n2 PARTITION(name=Theodore).c EXPRESSION [(emps_n30)emps_n30.null, ]
POSTHOOK: Lineage: mv1_part_n2 PARTITION(name=Theodore).s EXPRESSION [(emps_n30)emps_n30.FieldSchema(name:empid, type:int, comment:null), ]
POSTHOOK: Lineage: mv1_part_n2 PARTITION(name=Theodore).salary SIMPLE [(emps_n30)emps_n30.FieldSchema(name:salary, type:float, comment:null), ]
-PREHOOK: query: analyze table mv1_part_n2 compute statistics for columns
-PREHOOK: type: ANALYZE_TABLE
-PREHOOK: Input: default@mv1_part_n2
-PREHOOK: Input: default@mv1_part_n2@name=Bill
-PREHOOK: Input: default@mv1_part_n2@name=Eric
-PREHOOK: Input: default@mv1_part_n2@name=Sebastian
-PREHOOK: Input: default@mv1_part_n2@name=Theodore
-PREHOOK: Output: default@mv1_part_n2
-PREHOOK: Output: default@mv1_part_n2@name=Bill
-PREHOOK: Output: default@mv1_part_n2@name=Eric
-PREHOOK: Output: default@mv1_part_n2@name=Sebastian
-PREHOOK: Output: default@mv1_part_n2@name=Theodore
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table mv1_part_n2 compute statistics for columns
-POSTHOOK: type: ANALYZE_TABLE
-POSTHOOK: Input: default@mv1_part_n2
-POSTHOOK: Input: default@mv1_part_n2@name=Bill
-POSTHOOK: Input: default@mv1_part_n2@name=Eric
-POSTHOOK: Input: default@mv1_part_n2@name=Sebastian
-POSTHOOK: Input: default@mv1_part_n2@name=Theodore
-POSTHOOK: Output: default@mv1_part_n2
-POSTHOOK: Output: default@mv1_part_n2@name=Bill
-POSTHOOK: Output: default@mv1_part_n2@name=Eric
-POSTHOOK: Output: default@mv1_part_n2@name=Sebastian
-POSTHOOK: Output: default@mv1_part_n2@name=Theodore
-#### A masked pattern was here ####
PREHOOK: query: explain
select name from emps_n30 group by name
PREHOOK: type: QUERY
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/llap/materialized_view_rewrite_part_2.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/materialized_view_rewrite_part_2.q.out b/ql/src/test/results/clientpositive/llap/materialized_view_rewrite_part_2.q.out
index 67a11c0..9765fdb 100644
--- a/ql/src/test/results/clientpositive/llap/materialized_view_rewrite_part_2.q.out
+++ b/ql/src/test/results/clientpositive/llap/materialized_view_rewrite_part_2.q.out
@@ -33,16 +33,6 @@ POSTHOOK: Lineage: emps_n00.deptno SCRIPT []
POSTHOOK: Lineage: emps_n00.empid SCRIPT []
POSTHOOK: Lineage: emps_n00.name SCRIPT []
POSTHOOK: Lineage: emps_n00.salary SCRIPT []
-PREHOOK: query: analyze table emps_n00 compute statistics for columns
-PREHOOK: type: ANALYZE_TABLE
-PREHOOK: Input: default@emps_n00
-PREHOOK: Output: default@emps_n00
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table emps_n00 compute statistics for columns
-POSTHOOK: type: ANALYZE_TABLE
-POSTHOOK: Input: default@emps_n00
-POSTHOOK: Output: default@emps_n00
-#### A masked pattern was here ####
PREHOOK: query: create table depts_n00 (
deptno int,
name varchar(256),
@@ -70,16 +60,6 @@ POSTHOOK: Output: default@depts_n00
POSTHOOK: Lineage: depts_n00.deptno SCRIPT []
POSTHOOK: Lineage: depts_n00.locationid SCRIPT []
POSTHOOK: Lineage: depts_n00.name SCRIPT []
-PREHOOK: query: analyze table depts_n00 compute statistics for columns
-PREHOOK: type: ANALYZE_TABLE
-PREHOOK: Input: default@depts_n00
-PREHOOK: Output: default@depts_n00
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table depts_n00 compute statistics for columns
-POSTHOOK: type: ANALYZE_TABLE
-POSTHOOK: Input: default@depts_n00
-POSTHOOK: Output: default@depts_n00
-#### A masked pattern was here ####
PREHOOK: query: create table dependents_n00 (
empid int,
name varchar(256))
@@ -104,16 +84,6 @@ POSTHOOK: Input: _dummy_database@_dummy_table
POSTHOOK: Output: default@dependents_n00
POSTHOOK: Lineage: dependents_n00.empid SCRIPT []
POSTHOOK: Lineage: dependents_n00.name SCRIPT []
-PREHOOK: query: analyze table dependents_n00 compute statistics for columns
-PREHOOK: type: ANALYZE_TABLE
-PREHOOK: Input: default@dependents_n00
-PREHOOK: Output: default@dependents_n00
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table dependents_n00 compute statistics for columns
-POSTHOOK: type: ANALYZE_TABLE
-POSTHOOK: Input: default@dependents_n00
-POSTHOOK: Output: default@dependents_n00
-#### A masked pattern was here ####
PREHOOK: query: create table locations_n00 (
locationid int,
name varchar(256))
@@ -138,16 +108,6 @@ POSTHOOK: Input: _dummy_database@_dummy_table
POSTHOOK: Output: default@locations_n00
POSTHOOK: Lineage: locations_n00.locationid SCRIPT []
POSTHOOK: Lineage: locations_n00.name SCRIPT []
-PREHOOK: query: analyze table locations_n00 compute statistics for columns
-PREHOOK: type: ANALYZE_TABLE
-PREHOOK: Input: default@locations_n00
-PREHOOK: Output: default@locations_n00
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table locations_n00 compute statistics for columns
-POSTHOOK: type: ANALYZE_TABLE
-POSTHOOK: Input: default@locations_n00
-POSTHOOK: Output: default@locations_n00
-#### A masked pattern was here ####
PREHOOK: query: alter table emps_n00 add constraint pk1 primary key (empid) disable novalidate rely
PREHOOK: type: ALTERTABLE_ADDCONSTRAINT
POSTHOOK: query: alter table emps_n00 add constraint pk1 primary key (empid) disable novalidate rely
@@ -193,20 +153,6 @@ POSTHOOK: Output: database:default
POSTHOOK: Output: default@mv1_part_n0
POSTHOOK: Output: default@mv1_part_n0@deptno=20
POSTHOOK: Lineage: mv1_part_n0 PARTITION(deptno=20).empid SIMPLE [(emps_n00)emps_n00.FieldSchema(name:empid, type:int, comment:null), ]
-PREHOOK: query: analyze table mv1_part_n0 compute statistics for columns
-PREHOOK: type: ANALYZE_TABLE
-PREHOOK: Input: default@mv1_part_n0
-PREHOOK: Input: default@mv1_part_n0@deptno=20
-PREHOOK: Output: default@mv1_part_n0
-PREHOOK: Output: default@mv1_part_n0@deptno=20
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table mv1_part_n0 compute statistics for columns
-POSTHOOK: type: ANALYZE_TABLE
-POSTHOOK: Input: default@mv1_part_n0
-POSTHOOK: Input: default@mv1_part_n0@deptno=20
-POSTHOOK: Output: default@mv1_part_n0
-POSTHOOK: Output: default@mv1_part_n0@deptno=20
-#### A masked pattern was here ####
PREHOOK: query: explain
select empid from emps_n00
join depts_n00 using (deptno) where depts_n00.deptno >= 20
@@ -291,20 +237,6 @@ POSTHOOK: Output: database:default
POSTHOOK: Output: default@mv1_part_n0
POSTHOOK: Output: default@mv1_part_n0@deptno=20
POSTHOOK: Lineage: mv1_part_n0 PARTITION(deptno=20).empid SIMPLE [(emps_n00)emps_n00.FieldSchema(name:empid, type:int, comment:null), ]
-PREHOOK: query: analyze table mv1_part_n0 compute statistics for columns
-PREHOOK: type: ANALYZE_TABLE
-PREHOOK: Input: default@mv1_part_n0
-PREHOOK: Input: default@mv1_part_n0@deptno=20
-PREHOOK: Output: default@mv1_part_n0
-PREHOOK: Output: default@mv1_part_n0@deptno=20
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table mv1_part_n0 compute statistics for columns
-POSTHOOK: type: ANALYZE_TABLE
-POSTHOOK: Input: default@mv1_part_n0
-POSTHOOK: Input: default@mv1_part_n0@deptno=20
-POSTHOOK: Output: default@mv1_part_n0
-POSTHOOK: Output: default@mv1_part_n0@deptno=20
-#### A masked pattern was here ####
PREHOOK: query: explain
select empid from emps_n00
join depts_n00 using (deptno) where depts_n00.deptno >= 20
@@ -389,20 +321,6 @@ POSTHOOK: Output: database:default
POSTHOOK: Output: default@mv1_part_n0
POSTHOOK: Output: default@mv1_part_n0@deptno=20
POSTHOOK: Lineage: mv1_part_n0 PARTITION(deptno=20).empid SIMPLE [(emps_n00)emps_n00.FieldSchema(name:empid, type:int, comment:null), ]
-PREHOOK: query: analyze table mv1_part_n0 compute statistics for columns
-PREHOOK: type: ANALYZE_TABLE
-PREHOOK: Input: default@mv1_part_n0
-PREHOOK: Input: default@mv1_part_n0@deptno=20
-PREHOOK: Output: default@mv1_part_n0
-PREHOOK: Output: default@mv1_part_n0@deptno=20
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table mv1_part_n0 compute statistics for columns
-POSTHOOK: type: ANALYZE_TABLE
-POSTHOOK: Input: default@mv1_part_n0
-POSTHOOK: Input: default@mv1_part_n0@deptno=20
-POSTHOOK: Output: default@mv1_part_n0
-POSTHOOK: Output: default@mv1_part_n0@deptno=20
-#### A masked pattern was here ####
PREHOOK: query: explain
select empid from emps_n00
join depts_n00 using (deptno) where depts_n00.deptno >= 20
@@ -489,24 +407,6 @@ POSTHOOK: Output: default@mv1_part_n0@deptno=10
POSTHOOK: Output: default@mv1_part_n0@deptno=20
POSTHOOK: Lineage: mv1_part_n0 PARTITION(deptno=10).empid SIMPLE [(emps_n00)emps_n00.FieldSchema(name:empid, type:int, comment:null), ]
POSTHOOK: Lineage: mv1_part_n0 PARTITION(deptno=20).empid SIMPLE [(emps_n00)emps_n00.FieldSchema(name:empid, type:int, comment:null), ]
-PREHOOK: query: analyze table mv1_part_n0 compute statistics for columns
-PREHOOK: type: ANALYZE_TABLE
-PREHOOK: Input: default@mv1_part_n0
-PREHOOK: Input: default@mv1_part_n0@deptno=10
-PREHOOK: Input: default@mv1_part_n0@deptno=20
-PREHOOK: Output: default@mv1_part_n0
-PREHOOK: Output: default@mv1_part_n0@deptno=10
-PREHOOK: Output: default@mv1_part_n0@deptno=20
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table mv1_part_n0 compute statistics for columns
-POSTHOOK: type: ANALYZE_TABLE
-POSTHOOK: Input: default@mv1_part_n0
-POSTHOOK: Input: default@mv1_part_n0@deptno=10
-POSTHOOK: Input: default@mv1_part_n0@deptno=20
-POSTHOOK: Output: default@mv1_part_n0
-POSTHOOK: Output: default@mv1_part_n0@deptno=10
-POSTHOOK: Output: default@mv1_part_n0@deptno=20
-#### A masked pattern was here ####
PREHOOK: query: explain
select depts_n00.deptno from depts_n00
join emps_n00 using (deptno) where emps_n00.empid > 15
@@ -603,24 +503,6 @@ POSTHOOK: Output: default@mv1_part_n0@deptno=10
POSTHOOK: Output: default@mv1_part_n0@deptno=20
POSTHOOK: Lineage: mv1_part_n0 PARTITION(deptno=10).empid SIMPLE [(emps_n00)emps_n00.FieldSchema(name:empid, type:int, comment:null), ]
POSTHOOK: Lineage: mv1_part_n0 PARTITION(deptno=20).empid SIMPLE [(emps_n00)emps_n00.FieldSchema(name:empid, type:int, comment:null), ]
-PREHOOK: query: analyze table mv1_part_n0 compute statistics for columns
-PREHOOK: type: ANALYZE_TABLE
-PREHOOK: Input: default@mv1_part_n0
-PREHOOK: Input: default@mv1_part_n0@deptno=10
-PREHOOK: Input: default@mv1_part_n0@deptno=20
-PREHOOK: Output: default@mv1_part_n0
-PREHOOK: Output: default@mv1_part_n0@deptno=10
-PREHOOK: Output: default@mv1_part_n0@deptno=20
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table mv1_part_n0 compute statistics for columns
-POSTHOOK: type: ANALYZE_TABLE
-POSTHOOK: Input: default@mv1_part_n0
-POSTHOOK: Input: default@mv1_part_n0@deptno=10
-POSTHOOK: Input: default@mv1_part_n0@deptno=20
-POSTHOOK: Output: default@mv1_part_n0
-POSTHOOK: Output: default@mv1_part_n0@deptno=10
-POSTHOOK: Output: default@mv1_part_n0@deptno=20
-#### A masked pattern was here ####
PREHOOK: query: explain
select depts_n00.deptno from depts_n00
join emps_n00 using (deptno) where emps_n00.empid > 15
@@ -780,7 +662,7 @@ POSTHOOK: query: drop materialized view mv1_part_n0
POSTHOOK: type: DROP_MATERIALIZED_VIEW
POSTHOOK: Input: default@mv1_part_n0
POSTHOOK: Output: default@mv1_part_n0
-Warning: Shuffle Join MERGEJOIN[19][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Reducer 2' is a cross product
+Warning: Shuffle Join MERGEJOIN[29][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Reducer 2' is a cross product
PREHOOK: query: create materialized view mv1_part_n0 partitioned on (deptno2) as
select depts_n00.name, dependents_n00.name as name2, emps_n00.deptno, depts_n00.deptno as deptno2, dependents_n00.empid
from depts_n00, dependents_n00, emps_n00
@@ -814,24 +696,6 @@ POSTHOOK: Lineage: mv1_part_n0 PARTITION(deptno2=30).deptno SIMPLE [(emps_n00)em
POSTHOOK: Lineage: mv1_part_n0 PARTITION(deptno2=30).empid SIMPLE [(dependents_n00)dependents_n00.FieldSchema(name:empid, type:int, comment:null), ]
POSTHOOK: Lineage: mv1_part_n0 PARTITION(deptno2=30).name SIMPLE [(depts_n00)depts_n00.FieldSchema(name:name, type:varchar(256), comment:null), ]
POSTHOOK: Lineage: mv1_part_n0 PARTITION(deptno2=30).name2 SIMPLE [(dependents_n00)dependents_n00.FieldSchema(name:name, type:varchar(256), comment:null), ]
-PREHOOK: query: analyze table mv1_part_n0 compute statistics for columns
-PREHOOK: type: ANALYZE_TABLE
-PREHOOK: Input: default@mv1_part_n0
-PREHOOK: Input: default@mv1_part_n0@deptno2=20
-PREHOOK: Input: default@mv1_part_n0@deptno2=30
-PREHOOK: Output: default@mv1_part_n0
-PREHOOK: Output: default@mv1_part_n0@deptno2=20
-PREHOOK: Output: default@mv1_part_n0@deptno2=30
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table mv1_part_n0 compute statistics for columns
-POSTHOOK: type: ANALYZE_TABLE
-POSTHOOK: Input: default@mv1_part_n0
-POSTHOOK: Input: default@mv1_part_n0@deptno2=20
-POSTHOOK: Input: default@mv1_part_n0@deptno2=30
-POSTHOOK: Output: default@mv1_part_n0
-POSTHOOK: Output: default@mv1_part_n0@deptno2=20
-POSTHOOK: Output: default@mv1_part_n0@deptno2=30
-#### A masked pattern was here ####
PREHOOK: query: explain
select dependents_n00.empid
from depts_n00
[10/35] hive git commit: HIVE-16957: Support CTAS for auto gather
column stats (Jesus Camacho Rodriguez, reviewed by Ashutosh Chauhan)
Posted by jc...@apache.org.
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/llap/vector_groupby_grouping_sets_limit.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/vector_groupby_grouping_sets_limit.q.out b/ql/src/test/results/clientpositive/llap/vector_groupby_grouping_sets_limit.q.out
index a629617..ac2ac11 100644
--- a/ql/src/test/results/clientpositive/llap/vector_groupby_grouping_sets_limit.q.out
+++ b/ql/src/test/results/clientpositive/llap/vector_groupby_grouping_sets_limit.q.out
@@ -60,7 +60,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: t1_n110
- Statistics: Num rows: 6 Data size: 2208 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 1020 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:a:string, 1:b:string, 2:c:string, 3:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -71,11 +71,11 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1]
- Statistics: Num rows: 6 Data size: 2208 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 1020 Basic stats: COMPLETE Column stats: COMPLETE
Top N Key Operator
sort order: +++
keys: a (type: string), b (type: string), 0L (type: bigint)
- Statistics: Num rows: 6 Data size: 2208 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 1020 Basic stats: COMPLETE Column stats: COMPLETE
top n: 10
Top N Key Vectorization:
className: VectorTopNKeyOperator
@@ -94,7 +94,7 @@ STAGE PLANS:
keys: a (type: string), b (type: string), 0L (type: bigint)
mode: hash
outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 24 Data size: 8832 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 2232 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: bigint)
sort order: +++
@@ -105,7 +105,7 @@ STAGE PLANS:
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
valueColumns: 3:bigint
- Statistics: Num rows: 24 Data size: 8832 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 2232 Basic stats: COMPLETE Column stats: COMPLETE
TopN Hash Memory Usage: 0.1
value expressions: _col3 (type: bigint)
Execution mode: vectorized, llap
@@ -154,7 +154,7 @@ STAGE PLANS:
keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: bigint)
mode: mergepartial
outputColumnNames: _col0, _col1, _col3
- Statistics: Num rows: 12 Data size: 4416 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 2232 Basic stats: COMPLETE Column stats: COMPLETE
pruneGroupingSetId: true
Select Operator
expressions: _col0 (type: string), _col1 (type: string), _col3 (type: bigint)
@@ -163,7 +163,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1, 2]
- Statistics: Num rows: 12 Data size: 4416 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 2136 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string), _col1 (type: string)
sort order: ++
@@ -173,7 +173,7 @@ STAGE PLANS:
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
valueColumns: 2:bigint
- Statistics: Num rows: 12 Data size: 4416 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 2136 Basic stats: COMPLETE Column stats: COMPLETE
TopN Hash Memory Usage: 0.1
value expressions: _col2 (type: bigint)
Reducer 3
@@ -199,19 +199,19 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1, 2]
- Statistics: Num rows: 12 Data size: 4416 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 2136 Basic stats: COMPLETE Column stats: COMPLETE
Limit
Number of rows: 10
Limit Vectorization:
className: VectorLimitOperator
native: true
- Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -274,7 +274,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: t1_n110
- Statistics: Num rows: 6 Data size: 2208 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 1020 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:a:string, 1:b:string, 2:c:string, 3:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -285,11 +285,11 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1]
- Statistics: Num rows: 6 Data size: 2208 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 1020 Basic stats: COMPLETE Column stats: COMPLETE
Top N Key Operator
sort order: +++
keys: a (type: string), b (type: string), 0L (type: bigint)
- Statistics: Num rows: 6 Data size: 2208 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 1020 Basic stats: COMPLETE Column stats: COMPLETE
top n: 10
Top N Key Vectorization:
className: VectorTopNKeyOperator
@@ -308,7 +308,7 @@ STAGE PLANS:
keys: a (type: string), b (type: string), 0L (type: bigint)
mode: hash
outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 24 Data size: 8832 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 2232 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: bigint)
sort order: +++
@@ -319,7 +319,7 @@ STAGE PLANS:
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
valueColumns: 3:bigint
- Statistics: Num rows: 24 Data size: 8832 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 2232 Basic stats: COMPLETE Column stats: COMPLETE
TopN Hash Memory Usage: 0.1
value expressions: _col3 (type: bigint)
Execution mode: vectorized, llap
@@ -368,7 +368,7 @@ STAGE PLANS:
keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: bigint)
mode: mergepartial
outputColumnNames: _col0, _col1, _col3
- Statistics: Num rows: 12 Data size: 4416 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 2232 Basic stats: COMPLETE Column stats: COMPLETE
pruneGroupingSetId: true
Select Operator
expressions: _col0 (type: string), _col1 (type: string), _col3 (type: bigint)
@@ -377,7 +377,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1, 2]
- Statistics: Num rows: 12 Data size: 4416 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 2136 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string), _col1 (type: string)
sort order: ++
@@ -387,7 +387,7 @@ STAGE PLANS:
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
valueColumns: 2:bigint
- Statistics: Num rows: 12 Data size: 4416 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 2136 Basic stats: COMPLETE Column stats: COMPLETE
TopN Hash Memory Usage: 0.1
value expressions: _col2 (type: bigint)
Reducer 3
@@ -413,19 +413,19 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1, 2]
- Statistics: Num rows: 12 Data size: 4416 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 2136 Basic stats: COMPLETE Column stats: COMPLETE
Limit
Number of rows: 10
Limit Vectorization:
className: VectorLimitOperator
native: true
- Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -488,7 +488,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: t1_n110
- Statistics: Num rows: 6 Data size: 2208 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 1020 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:a:string, 1:b:string, 2:c:string, 3:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -499,11 +499,11 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1]
- Statistics: Num rows: 6 Data size: 2208 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 1020 Basic stats: COMPLETE Column stats: COMPLETE
Top N Key Operator
sort order: +++
keys: a (type: string), b (type: string), 0L (type: bigint)
- Statistics: Num rows: 6 Data size: 2208 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 1020 Basic stats: COMPLETE Column stats: COMPLETE
top n: 10
Top N Key Vectorization:
className: VectorTopNKeyOperator
@@ -522,7 +522,7 @@ STAGE PLANS:
keys: a (type: string), b (type: string), 0L (type: bigint)
mode: hash
outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 12 Data size: 4416 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 1116 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: bigint)
sort order: +++
@@ -533,7 +533,7 @@ STAGE PLANS:
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
valueColumns: 3:bigint
- Statistics: Num rows: 12 Data size: 4416 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 1116 Basic stats: COMPLETE Column stats: COMPLETE
TopN Hash Memory Usage: 0.1
value expressions: _col3 (type: bigint)
Execution mode: vectorized, llap
@@ -582,7 +582,7 @@ STAGE PLANS:
keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: bigint)
mode: mergepartial
outputColumnNames: _col0, _col1, _col3
- Statistics: Num rows: 6 Data size: 2208 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 1116 Basic stats: COMPLETE Column stats: COMPLETE
pruneGroupingSetId: true
Select Operator
expressions: _col0 (type: string), _col1 (type: string), _col3 (type: bigint)
@@ -591,7 +591,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1, 2]
- Statistics: Num rows: 6 Data size: 2208 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 1068 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string), _col1 (type: string)
sort order: ++
@@ -601,7 +601,7 @@ STAGE PLANS:
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
valueColumns: 2:bigint
- Statistics: Num rows: 6 Data size: 2208 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 1068 Basic stats: COMPLETE Column stats: COMPLETE
TopN Hash Memory Usage: 0.1
value expressions: _col2 (type: bigint)
Reducer 3
@@ -627,19 +627,19 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1, 2]
- Statistics: Num rows: 6 Data size: 2208 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 1068 Basic stats: COMPLETE Column stats: COMPLETE
Limit
Number of rows: 10
Limit Vectorization:
className: VectorLimitOperator
native: true
- Statistics: Num rows: 6 Data size: 2208 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 1068 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 6 Data size: 2208 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 1068 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -702,7 +702,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: t1_n110
- Statistics: Num rows: 6 Data size: 3312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 1530 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:a:string, 1:b:string, 2:c:string, 3:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -713,11 +713,11 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1, 2]
- Statistics: Num rows: 6 Data size: 3312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 1530 Basic stats: COMPLETE Column stats: COMPLETE
Top N Key Operator
sort order: ++++
keys: a (type: string), b (type: string), c (type: string), 0L (type: bigint)
- Statistics: Num rows: 6 Data size: 3312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 1530 Basic stats: COMPLETE Column stats: COMPLETE
top n: 10
Top N Key Vectorization:
className: VectorTopNKeyOperator
@@ -734,7 +734,7 @@ STAGE PLANS:
keys: a (type: string), b (type: string), c (type: string), 0L (type: bigint)
mode: hash
outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 18 Data size: 9936 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 9 Data size: 2367 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: bigint)
sort order: ++++
@@ -744,7 +744,7 @@ STAGE PLANS:
keyColumns: 0:string, 1:string, 2:string, 3:bigint
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 18 Data size: 9936 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 9 Data size: 2367 Basic stats: COMPLETE Column stats: COMPLETE
TopN Hash Memory Usage: 0.1
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -790,7 +790,7 @@ STAGE PLANS:
keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: string), KEY._col3 (type: bigint)
mode: mergepartial
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 9 Data size: 4968 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 9 Data size: 2367 Basic stats: COMPLETE Column stats: COMPLETE
pruneGroupingSetId: true
Select Operator
expressions: _col0 (type: string)
@@ -799,7 +799,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0]
- Statistics: Num rows: 9 Data size: 4968 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 9 Data size: 765 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
@@ -808,7 +808,7 @@ STAGE PLANS:
keyColumns: 0:string
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 9 Data size: 4968 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 9 Data size: 765 Basic stats: COMPLETE Column stats: COMPLETE
TopN Hash Memory Usage: 0.1
Reducer 3
Execution mode: vectorized, llap
@@ -833,19 +833,19 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0]
- Statistics: Num rows: 9 Data size: 4968 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 9 Data size: 765 Basic stats: COMPLETE Column stats: COMPLETE
Limit
Number of rows: 10
Limit Vectorization:
className: VectorLimitOperator
native: true
- Statistics: Num rows: 9 Data size: 4968 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 9 Data size: 765 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 9 Data size: 4968 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 9 Data size: 765 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -908,7 +908,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: t1_n110
- Statistics: Num rows: 6 Data size: 1104 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 510 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:a:string, 1:b:string, 2:c:string, 3:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -919,11 +919,11 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0]
- Statistics: Num rows: 6 Data size: 1104 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 510 Basic stats: COMPLETE Column stats: COMPLETE
Top N Key Operator
sort order: +
keys: a (type: string)
- Statistics: Num rows: 6 Data size: 1104 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 510 Basic stats: COMPLETE Column stats: COMPLETE
top n: 10
Top N Key Vectorization:
className: VectorTopNKeyOperator
@@ -940,7 +940,7 @@ STAGE PLANS:
keys: a (type: string)
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 6 Data size: 1104 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 255 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
@@ -950,7 +950,7 @@ STAGE PLANS:
keyColumns: 0:string
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 6 Data size: 1104 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 255 Basic stats: COMPLETE Column stats: COMPLETE
TopN Hash Memory Usage: 0.1
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -996,7 +996,7 @@ STAGE PLANS:
keys: KEY._col0 (type: string)
mode: mergepartial
outputColumnNames: _col0
- Statistics: Num rows: 3 Data size: 552 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 255 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
@@ -1005,7 +1005,7 @@ STAGE PLANS:
keyColumns: 0:string
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 3 Data size: 552 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 255 Basic stats: COMPLETE Column stats: COMPLETE
TopN Hash Memory Usage: 0.1
Reducer 3
Execution mode: vectorized, llap
@@ -1030,19 +1030,19 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0]
- Statistics: Num rows: 3 Data size: 552 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 255 Basic stats: COMPLETE Column stats: COMPLETE
Limit
Number of rows: 10
Limit Vectorization:
className: VectorLimitOperator
native: true
- Statistics: Num rows: 3 Data size: 552 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 255 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 3 Data size: 552 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 255 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -1100,7 +1100,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: t1_n110
- Statistics: Num rows: 6 Data size: 2208 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 1020 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:a:string, 1:b:string, 2:c:string, 3:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -1112,11 +1112,11 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [6]
selectExpressions: DoubleColAddDoubleColumn(col 4:double, col 5:double)(children: CastStringToDouble(col 0:string) -> 4:double, CastStringToDouble(col 1:string) -> 5:double) -> 6:double
- Statistics: Num rows: 6 Data size: 2208 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 1020 Basic stats: COMPLETE Column stats: COMPLETE
Top N Key Operator
sort order: +
keys: _col0 (type: double)
- Statistics: Num rows: 6 Data size: 2208 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 1020 Basic stats: COMPLETE Column stats: COMPLETE
top n: 10
Top N Key Vectorization:
className: VectorTopNKeyOperator
@@ -1135,7 +1135,7 @@ STAGE PLANS:
keys: _col0 (type: double)
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 6 Data size: 2208 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: double)
sort order: +
@@ -1146,7 +1146,7 @@ STAGE PLANS:
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
valueColumns: 1:bigint
- Statistics: Num rows: 6 Data size: 2208 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE
TopN Hash Memory Usage: 0.1
value expressions: _col1 (type: bigint)
Execution mode: vectorized, llap
@@ -1195,7 +1195,7 @@ STAGE PLANS:
keys: KEY._col0 (type: double)
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 3 Data size: 1104 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: double)
sort order: +
@@ -1205,7 +1205,7 @@ STAGE PLANS:
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
valueColumns: 1:bigint
- Statistics: Num rows: 3 Data size: 1104 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE
TopN Hash Memory Usage: 0.1
value expressions: _col1 (type: bigint)
Reducer 3
@@ -1231,19 +1231,19 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1]
- Statistics: Num rows: 3 Data size: 1104 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE
Limit
Number of rows: 10
Limit Vectorization:
className: VectorLimitOperator
native: true
- Statistics: Num rows: 3 Data size: 1104 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 3 Data size: 1104 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/llap/vector_grouping_sets.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/vector_grouping_sets.q.out b/ql/src/test/results/clientpositive/llap/vector_grouping_sets.q.out
index d0274b8..8b64678 100644
--- a/ql/src/test/results/clientpositive/llap/vector_grouping_sets.q.out
+++ b/ql/src/test/results/clientpositive/llap/vector_grouping_sets.q.out
@@ -157,7 +157,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: store_n1
- Statistics: Num rows: 12 Data size: 2208 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 1200 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
Select Operator
@@ -167,7 +167,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [1]
- Statistics: Num rows: 12 Data size: 2208 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 1200 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
Group By Vectorization:
className: VectorGroupByOperator
@@ -179,7 +179,7 @@ STAGE PLANS:
keys: s_store_id (type: string), 0L (type: bigint)
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 24 Data size: 4416 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 1296 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string), _col1 (type: bigint)
sort order: ++
@@ -188,7 +188,7 @@ STAGE PLANS:
className: VectorReduceSinkMultiKeyOperator
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 24 Data size: 4416 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 1296 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized, llap
LLAP IO: all inputs
Map Vectorization:
@@ -220,14 +220,14 @@ STAGE PLANS:
keys: KEY._col0 (type: string), KEY._col1 (type: bigint)
mode: mergepartial
outputColumnNames: _col0
- Statistics: Num rows: 12 Data size: 2208 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 1296 Basic stats: COMPLETE Column stats: COMPLETE
pruneGroupingSetId: true
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 12 Data size: 2208 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 1296 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -292,7 +292,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: store_n1
- Statistics: Num rows: 12 Data size: 2208 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 1200 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
Select Operator
@@ -302,7 +302,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [1]
- Statistics: Num rows: 12 Data size: 2208 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 1200 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
Group By Vectorization:
className: VectorGroupByOperator
@@ -314,7 +314,7 @@ STAGE PLANS:
keys: _col0 (type: string), 0L (type: bigint)
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 24 Data size: 4416 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 1296 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string), _col1 (type: bigint)
sort order: ++
@@ -323,7 +323,7 @@ STAGE PLANS:
className: VectorReduceSinkMultiKeyOperator
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 24 Data size: 4416 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 1296 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized, llap
LLAP IO: all inputs
Map Vectorization:
@@ -355,7 +355,7 @@ STAGE PLANS:
keys: KEY._col0 (type: string), KEY._col1 (type: bigint)
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 12 Data size: 2208 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 1296 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: string), _col1 (type: bigint)
outputColumnNames: _col0, _col1
@@ -363,13 +363,13 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1]
- Statistics: Num rows: 12 Data size: 2208 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 1296 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 12 Data size: 2208 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 1296 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -430,21 +430,21 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: store_n1
- Statistics: Num rows: 12 Data size: 2208 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 1200 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: s_store_id (type: string)
outputColumnNames: _col0
- Statistics: Num rows: 12 Data size: 2208 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 1200 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
keys: _col0 (type: string), 0L (type: bigint)
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 24 Data size: 4416 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 1296 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string), _col1 (type: bigint)
sort order: ++
Map-reduce partition columns: _col0 (type: string), _col1 (type: bigint)
- Statistics: Num rows: 24 Data size: 4416 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 1296 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized, llap
LLAP IO: all inputs
Reducer 2
@@ -454,14 +454,14 @@ STAGE PLANS:
keys: KEY._col0 (type: string), KEY._col1 (type: bigint)
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 12 Data size: 2208 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 1296 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: string), _col1 (type: bigint)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 12 Data size: 2208 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 1296 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 12 Data size: 2208 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 1296 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/llap/vector_if_expr_2.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/vector_if_expr_2.q.out b/ql/src/test/results/clientpositive/llap/vector_if_expr_2.q.out
index e9e82d6..8bf3016 100644
--- a/ql/src/test/results/clientpositive/llap/vector_if_expr_2.q.out
+++ b/ql/src/test/results/clientpositive/llap/vector_if_expr_2.q.out
@@ -50,7 +50,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: foo
- Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: NONE
TableScan Vectorization:
native: true
Select Operator
@@ -61,7 +61,7 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [0, 4]
selectExpressions: IfExprLongColumnLongScalar(col 3:boolean, col 1:int, val 0)(children: LongColGreaterLongScalar(col 0:int, val 0) -> 3:boolean) -> 4:int
- Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
@@ -69,7 +69,7 @@ STAGE PLANS:
className: VectorReduceSinkObjectHashOperator
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: int)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -98,13 +98,13 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1]
- Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/llap/vector_include_no_sel.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/vector_include_no_sel.q.out b/ql/src/test/results/clientpositive/llap/vector_include_no_sel.q.out
index 57411c4..e38914c 100644
--- a/ql/src/test/results/clientpositive/llap/vector_include_no_sel.q.out
+++ b/ql/src/test/results/clientpositive/llap/vector_include_no_sel.q.out
@@ -200,7 +200,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: customer_demographics
- Statistics: Num rows: 200 Data size: 35908 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 200 Data size: 17800 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
Reduce Output Operator
@@ -210,7 +210,7 @@ STAGE PLANS:
native: false
nativeConditionsMet: hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
nativeConditionsNotMet: hive.vectorized.execution.reducesink.new.enabled IS false
- Statistics: Num rows: 200 Data size: 35908 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 200 Data size: 17800 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: cd_demo_sk (type: int), cd_marital_status (type: string)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -227,7 +227,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: store_sales_n1
- Statistics: Num rows: 1000 Data size: 3804 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1000 Data size: 3796 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
Reduce Output Operator
@@ -237,7 +237,7 @@ STAGE PLANS:
native: false
nativeConditionsMet: hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
nativeConditionsNotMet: hive.vectorized.execution.reducesink.new.enabled IS false
- Statistics: Num rows: 1000 Data size: 3804 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1000 Data size: 3796 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: ss_cdemo_sk (type: int)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -260,20 +260,20 @@ STAGE PLANS:
0
1
outputColumnNames: _col0, _col2, _col16
- Statistics: Num rows: 200000 Data size: 36868800 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 200000 Data size: 18599796 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: (((_col0 = _col16) and (_col2 = 'M')) or ((_col0 = _col16) and (_col2 = 'U'))) (type: boolean)
- Statistics: Num rows: 100000 Data size: 18434400 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 40000 Data size: 3719964 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
- Statistics: Num rows: 100000 Data size: 18434400 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 40000 Data size: 3719964 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count(1)
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: bigint)
MergeJoin Vectorization:
enabled: false
@@ -298,13 +298,13 @@ STAGE PLANS:
projectedOutputColumnNums: [0]
mode: mergepartial
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/llap/vector_interval_mapjoin.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/vector_interval_mapjoin.q.out b/ql/src/test/results/clientpositive/llap/vector_interval_mapjoin.q.out
index 29acbec..abf998e 100644
--- a/ql/src/test/results/clientpositive/llap/vector_interval_mapjoin.q.out
+++ b/ql/src/test/results/clientpositive/llap/vector_interval_mapjoin.q.out
@@ -207,7 +207,7 @@ STAGE PLANS:
TableScan
alias: vectortab_a_1korc
filterExpr: (dt is not null and ts is not null and s is not null) (type: boolean)
- Statistics: Num rows: 1000 Data size: 266280 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1000 Data size: 187480 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
Filter Operator
@@ -216,7 +216,7 @@ STAGE PLANS:
native: true
predicateExpression: FilterExprAndExpr(children: SelectColumnIsNotNull(col 12:date), SelectColumnIsNotNull(col 10:timestamp), SelectColumnIsNotNull(col 8:string))
predicate: (dt is not null and s is not null and ts is not null) (type: boolean)
- Statistics: Num rows: 850 Data size: 226338 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 954 Data size: 178852 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: s (type: string), (dt - CAST( ts AS DATE)) (type: interval_day_time)
outputColumnNames: _col0, _col1
@@ -225,7 +225,7 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [8, 15]
selectExpressions: DateColSubtractDateColumn(col 12:date, col 14:date)(children: CastTimestampToDate(col 10:timestamp) -> 14:date) -> 15:interval_day_time
- Statistics: Num rows: 850 Data size: 226338 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 954 Data size: 101124 Basic stats: COMPLETE Column stats: COMPLETE
Map Join Operator
condition map:
Inner Join 0 to 1
@@ -240,7 +240,7 @@ STAGE PLANS:
outputColumnNames: _col0, _col1, _col2
input vertices:
1 Map 2
- Statistics: Num rows: 935 Data size: 248971 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 33319 Data size: 6663800 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: string), _col2 (type: string), _col1 (type: interval_day_time)
outputColumnNames: _col0, _col1, _col2
@@ -248,13 +248,13 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [8, 8, 15]
- Statistics: Num rows: 935 Data size: 248971 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 33319 Data size: 6663800 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 935 Data size: 248971 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 33319 Data size: 6663800 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -275,7 +275,7 @@ STAGE PLANS:
TableScan
alias: vectortab_b_1korc
filterExpr: (dt is not null and ts is not null and s is not null) (type: boolean)
- Statistics: Num rows: 1000 Data size: 266280 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1000 Data size: 186864 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
Filter Operator
@@ -284,7 +284,7 @@ STAGE PLANS:
native: true
predicateExpression: FilterExprAndExpr(children: SelectColumnIsNotNull(col 12:date), SelectColumnIsNotNull(col 10:timestamp), SelectColumnIsNotNull(col 8:string))
predicate: (dt is not null and s is not null and ts is not null) (type: boolean)
- Statistics: Num rows: 850 Data size: 226338 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 943 Data size: 176202 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: s (type: string), (dt - CAST( ts AS DATE)) (type: interval_day_time)
outputColumnNames: _col0, _col1
@@ -293,7 +293,7 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [8, 15]
selectExpressions: DateColSubtractDateColumn(col 12:date, col 14:date)(children: CastTimestampToDate(col 10:timestamp) -> 14:date) -> 15:interval_day_time
- Statistics: Num rows: 850 Data size: 226338 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 943 Data size: 99958 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string), _col1 (type: interval_day_time)
sort order: ++
@@ -302,7 +302,7 @@ STAGE PLANS:
className: VectorReduceSinkMultiKeyOperator
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 850 Data size: 226338 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 943 Data size: 99958 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized, llap
LLAP IO: all inputs
Map Vectorization:
[09/35] hive git commit: HIVE-16957: Support CTAS for auto gather
column stats (Jesus Camacho Rodriguez, reviewed by Ashutosh Chauhan)
Posted by jc...@apache.org.
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/llap/vector_join30.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/vector_join30.q.out b/ql/src/test/results/clientpositive/llap/vector_join30.q.out
index 9eb0893..7c873c1 100644
--- a/ql/src/test/results/clientpositive/llap/vector_join30.q.out
+++ b/ql/src/test/results/clientpositive/llap/vector_join30.q.out
@@ -52,7 +52,7 @@ STAGE PLANS:
TableScan
alias: orcsrc_n0
filterExpr: key is not null (type: boolean)
- Statistics: Num rows: 500 Data size: 87584 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:key:string, 1:value:string, 2:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -62,7 +62,7 @@ STAGE PLANS:
native: true
predicateExpression: SelectColumnIsNotNull(col 0:string)
predicate: key is not null (type: boolean)
- Statistics: Num rows: 475 Data size: 83204 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: key (type: string)
outputColumnNames: _col0
@@ -70,7 +70,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0]
- Statistics: Num rows: 475 Data size: 83204 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
@@ -80,7 +80,7 @@ STAGE PLANS:
keyColumns: 0:string
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 475 Data size: 83204 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized, llap
LLAP IO: all inputs
Map Vectorization:
@@ -103,7 +103,7 @@ STAGE PLANS:
TableScan
alias: orcsrc_n0
filterExpr: key is not null (type: boolean)
- Statistics: Num rows: 500 Data size: 175168 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:key:string, 1:value:string, 2:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -113,7 +113,7 @@ STAGE PLANS:
native: true
predicateExpression: SelectColumnIsNotNull(col 0:string)
predicate: key is not null (type: boolean)
- Statistics: Num rows: 475 Data size: 166409 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: key (type: string), value (type: string)
outputColumnNames: _col0, _col1
@@ -121,7 +121,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1]
- Statistics: Num rows: 475 Data size: 166409 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
Map Join Operator
condition map:
Inner Join 0 to 1
@@ -141,7 +141,7 @@ STAGE PLANS:
outputColumnNames: _col2, _col3
input vertices:
0 Map 1
- Statistics: Num rows: 522 Data size: 91524 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 791 Data size: 140798 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: sum(hash(_col2,_col3))
Group By Vectorization:
@@ -153,7 +153,7 @@ STAGE PLANS:
projectedOutputColumnNums: [0]
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
Reduce Sink Vectorization:
@@ -161,7 +161,7 @@ STAGE PLANS:
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
valueColumns: 0:bigint
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: bigint)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -207,13 +207,13 @@ STAGE PLANS:
projectedOutputColumnNums: [0]
mode: mergepartial
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -266,7 +266,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: orcsrc_n0
- Statistics: Num rows: 500 Data size: 87584 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:key:string, 1:value:string, 2:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -277,7 +277,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0]
- Statistics: Num rows: 500 Data size: 87584 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
Map Join Operator
condition map:
Left Outer Join 0 to 1
@@ -297,7 +297,7 @@ STAGE PLANS:
outputColumnNames: _col2, _col3
input vertices:
1 Map 3
- Statistics: Num rows: 550 Data size: 96342 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 791 Data size: 140798 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: sum(hash(_col2,_col3))
Group By Vectorization:
@@ -309,7 +309,7 @@ STAGE PLANS:
projectedOutputColumnNums: [0]
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
Reduce Sink Vectorization:
@@ -317,7 +317,7 @@ STAGE PLANS:
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
valueColumns: 0:bigint
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: bigint)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -340,7 +340,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: orcsrc_n0
- Statistics: Num rows: 500 Data size: 175168 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:key:string, 1:value:string, 2:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -351,7 +351,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1]
- Statistics: Num rows: 500 Data size: 175168 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
@@ -362,7 +362,7 @@ STAGE PLANS:
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
valueColumns: 1:string
- Statistics: Num rows: 500 Data size: 175168 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: string)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -408,13 +408,13 @@ STAGE PLANS:
projectedOutputColumnNums: [0]
mode: mergepartial
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -467,7 +467,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: orcsrc_n0
- Statistics: Num rows: 500 Data size: 87584 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:key:string, 1:value:string, 2:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -478,7 +478,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0]
- Statistics: Num rows: 500 Data size: 87584 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
@@ -488,7 +488,7 @@ STAGE PLANS:
keyColumns: 0:string
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 500 Data size: 87584 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized, llap
LLAP IO: all inputs
Map Vectorization:
@@ -510,7 +510,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: orcsrc_n0
- Statistics: Num rows: 500 Data size: 175168 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:key:string, 1:value:string, 2:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -521,7 +521,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1]
- Statistics: Num rows: 500 Data size: 175168 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
Map Join Operator
condition map:
Right Outer Join 0 to 1
@@ -540,7 +540,7 @@ STAGE PLANS:
outputColumnNames: _col2, _col3
input vertices:
0 Map 1
- Statistics: Num rows: 550 Data size: 96342 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 791 Data size: 140798 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: sum(hash(_col2,_col3))
Group By Vectorization:
@@ -552,7 +552,7 @@ STAGE PLANS:
projectedOutputColumnNums: [0]
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
Reduce Sink Vectorization:
@@ -560,7 +560,7 @@ STAGE PLANS:
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
valueColumns: 0:bigint
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: bigint)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -606,13 +606,13 @@ STAGE PLANS:
projectedOutputColumnNums: [0]
mode: mergepartial
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -665,7 +665,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: orcsrc_n0
- Statistics: Num rows: 500 Data size: 87584 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:key:string, 1:value:string, 2:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -676,7 +676,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0]
- Statistics: Num rows: 500 Data size: 87584 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
@@ -686,7 +686,7 @@ STAGE PLANS:
keyColumns: 0:string
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 500 Data size: 87584 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized, llap
LLAP IO: all inputs
Map Vectorization:
@@ -708,7 +708,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: orcsrc_n0
- Statistics: Num rows: 500 Data size: 175168 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:key:string, 1:value:string, 2:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -719,7 +719,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1]
- Statistics: Num rows: 500 Data size: 175168 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
@@ -730,7 +730,7 @@ STAGE PLANS:
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
valueColumns: 1:string
- Statistics: Num rows: 500 Data size: 175168 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: string)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -759,15 +759,15 @@ STAGE PLANS:
0 _col0 (type: string)
1 _col0 (type: string)
outputColumnNames: _col2, _col3
- Statistics: Num rows: 550 Data size: 96342 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1000 Data size: 178000 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: sum(hash(_col2,_col3))
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: bigint)
MergeJoin Vectorization:
enabled: false
@@ -799,13 +799,13 @@ STAGE PLANS:
projectedOutputColumnNums: [0]
mode: mergepartial
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -865,7 +865,7 @@ STAGE PLANS:
TableScan
alias: orcsrc_n0
filterExpr: key is not null (type: boolean)
- Statistics: Num rows: 500 Data size: 87584 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:key:string, 1:value:string, 2:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -875,7 +875,7 @@ STAGE PLANS:
native: true
predicateExpression: SelectColumnIsNotNull(col 0:string)
predicate: key is not null (type: boolean)
- Statistics: Num rows: 475 Data size: 83204 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: key (type: string)
outputColumnNames: _col0
@@ -883,7 +883,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0]
- Statistics: Num rows: 475 Data size: 83204 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
@@ -893,7 +893,7 @@ STAGE PLANS:
keyColumns: 0:string
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 475 Data size: 83204 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized, llap
LLAP IO: all inputs
Map Vectorization:
@@ -916,7 +916,7 @@ STAGE PLANS:
TableScan
alias: orcsrc_n0
filterExpr: key is not null (type: boolean)
- Statistics: Num rows: 500 Data size: 175168 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:key:string, 1:value:string, 2:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -926,7 +926,7 @@ STAGE PLANS:
native: true
predicateExpression: SelectColumnIsNotNull(col 0:string)
predicate: key is not null (type: boolean)
- Statistics: Num rows: 475 Data size: 166409 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: key (type: string), value (type: string)
outputColumnNames: _col0, _col1
@@ -934,7 +934,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1]
- Statistics: Num rows: 475 Data size: 166409 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
Map Join Operator
condition map:
Inner Join 0 to 1
@@ -954,7 +954,7 @@ STAGE PLANS:
input vertices:
0 Map 1
2 Map 4
- Statistics: Num rows: 1045 Data size: 183048 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1251 Data size: 222678 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: sum(hash(_col2,_col3))
Group By Vectorization:
@@ -966,7 +966,7 @@ STAGE PLANS:
projectedOutputColumnNums: [0]
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
Reduce Sink Vectorization:
@@ -974,7 +974,7 @@ STAGE PLANS:
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
valueColumns: 0:bigint
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: bigint)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -998,7 +998,7 @@ STAGE PLANS:
TableScan
alias: orcsrc_n0
filterExpr: key is not null (type: boolean)
- Statistics: Num rows: 500 Data size: 87584 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:key:string, 1:value:string, 2:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -1008,7 +1008,7 @@ STAGE PLANS:
native: true
predicateExpression: SelectColumnIsNotNull(col 0:string)
predicate: key is not null (type: boolean)
- Statistics: Num rows: 475 Data size: 83204 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: key (type: string)
outputColumnNames: _col0
@@ -1016,7 +1016,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0]
- Statistics: Num rows: 475 Data size: 83204 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
@@ -1026,7 +1026,7 @@ STAGE PLANS:
keyColumns: 0:string
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 475 Data size: 83204 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized, llap
LLAP IO: all inputs
Map Vectorization:
@@ -1071,13 +1071,13 @@ STAGE PLANS:
projectedOutputColumnNums: [0]
mode: mergepartial
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -1136,7 +1136,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: orcsrc_n0
- Statistics: Num rows: 500 Data size: 87584 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:key:string, 1:value:string, 2:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -1147,7 +1147,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0]
- Statistics: Num rows: 500 Data size: 87584 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
@@ -1157,7 +1157,7 @@ STAGE PLANS:
keyColumns: 0:string
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 500 Data size: 87584 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized, llap
LLAP IO: all inputs
Map Vectorization:
@@ -1179,7 +1179,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: orcsrc_n0
- Statistics: Num rows: 500 Data size: 175168 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:key:string, 1:value:string, 2:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -1190,7 +1190,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1]
- Statistics: Num rows: 500 Data size: 175168 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
@@ -1201,7 +1201,7 @@ STAGE PLANS:
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
valueColumns: 1:string
- Statistics: Num rows: 500 Data size: 175168 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: string)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -1224,7 +1224,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: orcsrc_n0
- Statistics: Num rows: 500 Data size: 87584 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:key:string, 1:value:string, 2:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -1235,7 +1235,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0]
- Statistics: Num rows: 500 Data size: 87584 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
@@ -1245,7 +1245,7 @@ STAGE PLANS:
keyColumns: 0:string
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 500 Data size: 87584 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized, llap
LLAP IO: all inputs
Map Vectorization:
@@ -1275,15 +1275,15 @@ STAGE PLANS:
1 _col0 (type: string)
2 _col0 (type: string)
outputColumnNames: _col2, _col3
- Statistics: Num rows: 1100 Data size: 192684 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1251 Data size: 222678 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: sum(hash(_col2,_col3))
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: bigint)
MergeJoin Vectorization:
enabled: false
@@ -1315,13 +1315,13 @@ STAGE PLANS:
projectedOutputColumnNums: [0]
mode: mergepartial
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -1380,7 +1380,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: orcsrc_n0
- Statistics: Num rows: 500 Data size: 87584 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:key:string, 1:value:string, 2:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -1391,7 +1391,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0]
- Statistics: Num rows: 500 Data size: 87584 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
@@ -1401,7 +1401,7 @@ STAGE PLANS:
keyColumns: 0:string
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 500 Data size: 87584 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized, llap
LLAP IO: all inputs
Map Vectorization:
@@ -1423,7 +1423,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: orcsrc_n0
- Statistics: Num rows: 500 Data size: 175168 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:key:string, 1:value:string, 2:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -1434,7 +1434,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1]
- Statistics: Num rows: 500 Data size: 175168 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
@@ -1445,7 +1445,7 @@ STAGE PLANS:
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
valueColumns: 1:string
- Statistics: Num rows: 500 Data size: 175168 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: string)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -1468,7 +1468,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: orcsrc_n0
- Statistics: Num rows: 500 Data size: 87584 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:key:string, 1:value:string, 2:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -1479,7 +1479,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0]
- Statistics: Num rows: 500 Data size: 87584 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
@@ -1489,7 +1489,7 @@ STAGE PLANS:
keyColumns: 0:string
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 500 Data size: 87584 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized, llap
LLAP IO: all inputs
Map Vectorization:
@@ -1519,15 +1519,15 @@ STAGE PLANS:
1 _col0 (type: string)
2 _col0 (type: string)
outputColumnNames: _col2, _col3
- Statistics: Num rows: 1100 Data size: 192684 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1251 Data size: 222678 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: sum(hash(_col2,_col3))
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: bigint)
MergeJoin Vectorization:
enabled: false
@@ -1559,13 +1559,13 @@ STAGE PLANS:
projectedOutputColumnNums: [0]
mode: mergepartial
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -1624,7 +1624,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: orcsrc_n0
- Statistics: Num rows: 500 Data size: 87584 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:key:string, 1:value:string, 2:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -1635,7 +1635,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0]
- Statistics: Num rows: 500 Data size: 87584 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
@@ -1645,7 +1645,7 @@ STAGE PLANS:
keyColumns: 0:string
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 500 Data size: 87584 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized, llap
LLAP IO: all inputs
Map Vectorization:
@@ -1667,7 +1667,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: orcsrc_n0
- Statistics: Num rows: 500 Data size: 175168 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:key:string, 1:value:string, 2:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -1678,7 +1678,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1]
- Statistics: Num rows: 500 Data size: 175168 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
@@ -1689,7 +1689,7 @@ STAGE PLANS:
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
valueColumns: 1:string
- Statistics: Num rows: 500 Data size: 175168 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: string)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -1712,7 +1712,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: orcsrc_n0
- Statistics: Num rows: 500 Data size: 87584 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:key:string, 1:value:string, 2:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -1723,7 +1723,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0]
- Statistics: Num rows: 500 Data size: 87584 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
@@ -1733,7 +1733,7 @@ STAGE PLANS:
keyColumns: 0:string
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 500 Data size: 87584 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized, llap
LLAP IO: all inputs
Map Vectorization:
@@ -1763,15 +1763,15 @@ STAGE PLANS:
1 _col0 (type: string)
2 _col0 (type: string)
outputColumnNames: _col2, _col3
- Statistics: Num rows: 1100 Data size: 192684 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1251 Data size: 222678 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: sum(hash(_col2,_col3))
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: bigint)
MergeJoin Vectorization:
enabled: false
@@ -1803,13 +1803,13 @@ STAGE PLANS:
projectedOutputColumnNums: [0]
mode: mergepartial
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -1868,7 +1868,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: orcsrc_n0
- Statistics: Num rows: 500 Data size: 87584 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:key:string, 1:value:string, 2:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -1879,7 +1879,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0]
- Statistics: Num rows: 500 Data size: 87584 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
@@ -1889,7 +1889,7 @@ STAGE PLANS:
keyColumns: 0:string
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 500 Data size: 87584 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized, llap
LLAP IO: all inputs
Map Vectorization:
@@ -1911,7 +1911,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: orcsrc_n0
- Statistics: Num rows: 500 Data size: 175168 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:key:string, 1:value:string, 2:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -1922,7 +1922,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1]
- Statistics: Num rows: 500 Data size: 175168 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
@@ -1933,7 +1933,7 @@ STAGE PLANS:
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
valueColumns: 1:string
- Statistics: Num rows: 500 Data size: 175168 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: string)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -1956,7 +1956,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: orcsrc_n0
- Statistics: Num rows: 500 Data size: 87584 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:key:string, 1:value:string, 2:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -1967,7 +1967,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0]
- Statistics: Num rows: 500 Data size: 87584 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
@@ -1977,7 +1977,7 @@ STAGE PLANS:
keyColumns: 0:string
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 500 Data size: 87584 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized, llap
LLAP IO: all inputs
Map Vectorization:
@@ -2007,15 +2007,15 @@ STAGE PLANS:
1 _col0 (type: string)
2 _col0 (type: string)
outputColumnNames: _col2, _col3
- Statistics: Num rows: 1100 Data size: 192684 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1251 Data size: 222678 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: sum(hash(_col2,_col3))
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: bigint)
MergeJoin Vectorization:
enabled: false
@@ -2047,13 +2047,13 @@ STAGE PLANS:
projectedOutputColumnNums: [0]
mode: mergepartial
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -2112,7 +2112,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: orcsrc_n0
- Statistics: Num rows: 500 Data size: 87584 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:key:string, 1:value:string, 2:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -2123,7 +2123,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0]
- Statistics: Num rows: 500 Data size: 87584 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
@@ -2133,7 +2133,7 @@ STAGE PLANS:
keyColumns: 0:string
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 500 Data size: 87584 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized, llap
LLAP IO: all inputs
Map Vectorization:
@@ -2155,7 +2155,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: orcsrc_n0
- Statistics: Num rows: 500 Data size: 175168 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:key:string, 1:value:string, 2:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -2166,7 +2166,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1]
- Statistics: Num rows: 500 Data size: 175168 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
@@ -2177,7 +2177,7 @@ STAGE PLANS:
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
valueColumns: 1:string
- Statistics: Num rows: 500 Data size: 175168 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: string)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -2200,7 +2200,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: orcsrc_n0
- Statistics: Num rows: 500 Data size: 87584 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:key:string, 1:value:string, 2:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -2211,7 +2211,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0]
- Statistics: Num rows: 500 Data size: 87584 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
@@ -2221,7 +2221,7 @@ STAGE PLANS:
keyColumns: 0:string
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 500 Data size: 87584 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized, llap
LLAP IO: all inputs
Map Vectorization:
@@ -2251,15 +2251,15 @@ STAGE PLANS:
1 _col0 (type: string)
2 _col0 (type: string)
outputColumnNames: _col2, _col3
- Statistics: Num rows: 1100 Data size: 192684 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1251 Data size: 222678 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: sum(hash(_col2,_col3))
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: bigint)
MergeJoin Vectorization:
enabled: false
@@ -2291,13 +2291,13 @@ STAGE PLANS:
projectedOutputColumnNums: [0]
mode: mergepartial
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -2356,7 +2356,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: orcsrc_n0
- Statistics: Num rows: 500 Data size: 87584 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:key:string, 1:value:string, 2:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -2367,7 +2367,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0]
- Statistics: Num rows: 500 Data size: 87584 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
@@ -2377,7 +2377,7 @@ STAGE PLANS:
keyColumns: 0:string
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 500 Data size: 87584 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized, llap
LLAP IO: all inputs
Map Vectorization:
@@ -2399,7 +2399,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: orcsrc_n0
- Statistics: Num rows: 500 Data size: 175168 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:key:string, 1:value:string, 2:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -2410,7 +2410,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1]
- Statistics: Num rows: 500 Data size: 175168 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
@@ -2421,7 +2421,7 @@ STAGE PLANS:
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
valueColumns: 1:string
- Statistics: Num rows: 500 Data size: 175168 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: string)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -2444,7 +2444,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: orcsrc_n0
- Statistics: Num rows: 500 Data size: 87584 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:key:string, 1:value:string, 2:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -2455,7 +2455,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0]
- Statistics: Num rows: 500 Data size: 87584 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
@@ -2465,7 +2465,7 @@ STAGE PLANS:
keyColumns: 0:string
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 500 Data size: 87584 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized, llap
LLAP IO: all inputs
Map Vectorization:
@@ -2495,15 +2495,15 @@ STAGE PLANS:
1 _col0 (type: string)
2 _col0 (type: string)
outputColumnNames: _col2, _col3
- Statistics: Num rows: 1100 Data size: 192684 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1251 Data size: 222678 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: sum(hash(_col2,_col3))
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: bigint)
MergeJoin Vectorization:
enabled: false
@@ -2535,13 +2535,13 @@ STAGE PLANS:
projectedOutputColumnNums: [0]
mode: mergepartial
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -2600,7 +2600,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: orcsrc_n0
- Statistics: Num rows: 500 Data size: 87584 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:key:string, 1:value:string, 2:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -2611,7 +2611,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0]
- Statistics: Num rows: 500 Data size: 87584 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
@@ -2621,7 +2621,7 @@ STAGE PLANS:
keyColumns: 0:string
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 500 Data size: 87584 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized, llap
LLAP IO: all inputs
Map Vectorization:
@@ -2643,7 +2643,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: orcsrc_n0
- Statistics: Num rows: 500 Data size: 175168 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:key:string, 1:value:string, 2:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -2654,7 +2654,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1]
- Statistics: Num rows: 500 Data size: 175168 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
@@ -2665,7 +2665,7 @@ STAGE PLANS:
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
valueColumns: 1:string
- Statistics: Num rows: 500 Data size: 175168 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: string)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -2688,7 +2688,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: orcsrc_n0
- Statistics: Num rows: 500 Data size: 87584 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:key:string, 1:value:string, 2:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -2699,7 +2699,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0]
- Statistics: Num rows: 500 Data size: 87584 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
@@ -2709,7 +2709,7 @@ STAGE PLANS:
keyColumns: 0:string
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 500 Data size: 87584 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized, llap
LLAP IO: all inputs
Map Vectorization:
@@ -2739,15 +2739,15 @@ STAGE PLANS:
1 _col0 (type: string)
2 _col0 (type: string)
outputColumnNames: _col2, _col3
- Statistics: Num rows: 1100 Data size: 192684 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1251 Data size: 222678 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: sum(hash(_col2,_col3))
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: bigint)
MergeJoin Vectorization:
enabled: false
@@ -2779,13 +2779,13 @@ STAGE PLANS:
projectedOutputColumnNums: [0]
mode: mergepartial
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -2844,7 +2844,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: orcsrc_n0
- Statistics: Num rows: 500 Data size: 87584 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:key:string, 1:value:string, 2:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -2855,7 +2855,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0]
- Statistics: Num rows: 500 Data size: 87584 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
@@ -2865,7 +2865,7 @@ STAGE PLANS:
keyColumns: 0:string
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] I
<TRUNCATED>
[19/35] hive git commit: HIVE-16957: Support CTAS for auto gather
column stats (Jesus Camacho Rodriguez, reviewed by Ashutosh Chauhan)
Posted by jc...@apache.org.
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/llap/semijoin_hint.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/semijoin_hint.q.out b/ql/src/test/results/clientpositive/llap/semijoin_hint.q.out
index e5109ad..4221b63 100644
--- a/ql/src/test/results/clientpositive/llap/semijoin_hint.q.out
+++ b/ql/src/test/results/clientpositive/llap/semijoin_hint.q.out
@@ -3358,26 +3358,6 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.merge_tmp_table
- Select Operator
- expressions: _col0 (type: int)
- outputColumnNames: val
- Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE
- Group By Operator
- aggregations: compute_stats(val, 'hll')
- mode: complete
- outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 432 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col0 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>)
- outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 432 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 1 Data size: 432 Basic stats: COMPLETE Column stats: NONE
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
Reducer 6
Execution mode: llap
Reduce Operator Tree:
@@ -3481,10 +3461,6 @@ STAGE PLANS:
Stage: Stage-8
Stats Work
Basic Stats Work:
- Column Stats Desc:
- Columns: val
- Column Types: int
- Table: default.merge_tmp_table
Stage: Stage-1
Move Operator
@@ -3719,26 +3695,6 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.merge_tmp_table
- Select Operator
- expressions: _col0 (type: int)
- outputColumnNames: val
- Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE
- Group By Operator
- aggregations: compute_stats(val, 'hll')
- mode: complete
- outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 432 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col0 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>)
- outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 432 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 1 Data size: 432 Basic stats: COMPLETE Column stats: NONE
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
Reducer 6
Execution mode: llap
Reduce Operator Tree:
@@ -3842,10 +3798,6 @@ STAGE PLANS:
Stage: Stage-8
Stats Work
Basic Stats Work:
- Column Stats Desc:
- Columns: val
- Column Types: int
- Table: default.merge_tmp_table
Stage: Stage-1
Move Operator
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/llap/sqlmerge.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/sqlmerge.q.out b/ql/src/test/results/clientpositive/llap/sqlmerge.q.out
index 0994995..6dc252a 100644
--- a/ql/src/test/results/clientpositive/llap/sqlmerge.q.out
+++ b/ql/src/test/results/clientpositive/llap/sqlmerge.q.out
@@ -210,26 +210,6 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.merge_tmp_table
- Select Operator
- expressions: _col0 (type: int)
- outputColumnNames: val
- Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE
- Group By Operator
- aggregations: compute_stats(val, 'hll')
- mode: complete
- outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 432 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col0 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>)
- outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 432 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 1 Data size: 432 Basic stats: COMPLETE Column stats: NONE
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
Reducer 6
Execution mode: llap
Reduce Operator Tree:
@@ -321,10 +301,6 @@ STAGE PLANS:
Stage: Stage-8
Stats Work
Basic Stats Work:
- Column Stats Desc:
- Columns: val
- Column Types: int
- Table: default.merge_tmp_table
Stage: Stage-1
Move Operator
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/llap/sqlmerge_stats.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/sqlmerge_stats.q.out b/ql/src/test/results/clientpositive/llap/sqlmerge_stats.q.out
index cd178cf..20c2bb4 100644
--- a/ql/src/test/results/clientpositive/llap/sqlmerge_stats.q.out
+++ b/ql/src/test/results/clientpositive/llap/sqlmerge_stats.q.out
@@ -269,26 +269,6 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.merge_tmp_table
- Select Operator
- expressions: _col0 (type: int)
- outputColumnNames: val
- Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE
- Group By Operator
- aggregations: compute_stats(val, 'hll')
- mode: complete
- outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 424 Basic stats: COMPLETE Column stats: COMPLETE
- Select Operator
- expressions: _col0 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>)
- outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 424 Basic stats: COMPLETE Column stats: COMPLETE
- File Output Operator
- compressed: false
- Statistics: Num rows: 1 Data size: 424 Basic stats: COMPLETE Column stats: COMPLETE
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
Reducer 5
Execution mode: llap
Reduce Operator Tree:
@@ -365,10 +345,6 @@ STAGE PLANS:
Stage: Stage-6
Stats Work
Basic Stats Work:
- Column Stats Desc:
- Columns: val
- Column Types: int
- Table: default.merge_tmp_table
Stage: Stage-0
Move Operator
@@ -820,26 +796,6 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.merge_tmp_table
- Select Operator
- expressions: _col0 (type: int)
- outputColumnNames: val
- Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE
- Group By Operator
- aggregations: compute_stats(val, 'hll')
- mode: complete
- outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 424 Basic stats: COMPLETE Column stats: COMPLETE
- Select Operator
- expressions: _col0 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>)
- outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 424 Basic stats: COMPLETE Column stats: COMPLETE
- File Output Operator
- compressed: false
- Statistics: Num rows: 1 Data size: 424 Basic stats: COMPLETE Column stats: COMPLETE
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
Reducer 5
Execution mode: llap
Reduce Operator Tree:
@@ -916,10 +872,6 @@ STAGE PLANS:
Stage: Stage-6
Stats Work
Basic Stats Work:
- Column Stats Desc:
- Columns: val
- Column Types: int
- Table: default.merge_tmp_table
Stage: Stage-0
Move Operator
@@ -1123,26 +1075,6 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.merge_tmp_table
- Select Operator
- expressions: _col0 (type: int)
- outputColumnNames: val
- Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE
- Group By Operator
- aggregations: compute_stats(val, 'hll')
- mode: complete
- outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 424 Basic stats: COMPLETE Column stats: COMPLETE
- Select Operator
- expressions: _col0 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>)
- outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 424 Basic stats: COMPLETE Column stats: COMPLETE
- File Output Operator
- compressed: false
- Statistics: Num rows: 1 Data size: 424 Basic stats: COMPLETE Column stats: COMPLETE
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
Reducer 5
Execution mode: llap
Reduce Operator Tree:
@@ -1219,10 +1151,6 @@ STAGE PLANS:
Stage: Stage-6
Stats Work
Basic Stats Work:
- Column Stats Desc:
- Columns: val
- Column Types: int
- Table: default.merge_tmp_table
Stage: Stage-0
Move Operator
@@ -1426,26 +1354,6 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.merge_tmp_table
- Select Operator
- expressions: _col0 (type: int)
- outputColumnNames: val
- Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE
- Group By Operator
- aggregations: compute_stats(val, 'hll')
- mode: complete
- outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 424 Basic stats: COMPLETE Column stats: COMPLETE
- Select Operator
- expressions: _col0 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>)
- outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 424 Basic stats: COMPLETE Column stats: COMPLETE
- File Output Operator
- compressed: false
- Statistics: Num rows: 1 Data size: 424 Basic stats: COMPLETE Column stats: COMPLETE
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
Reducer 5
Execution mode: llap
Reduce Operator Tree:
@@ -1522,10 +1430,6 @@ STAGE PLANS:
Stage: Stage-6
Stats Work
Basic Stats Work:
- Column Stats Desc:
- Columns: val
- Column Types: int
- Table: default.merge_tmp_table
Stage: Stage-0
Move Operator
@@ -1729,26 +1633,6 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.merge_tmp_table
- Select Operator
- expressions: _col0 (type: int)
- outputColumnNames: val
- Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE
- Group By Operator
- aggregations: compute_stats(val, 'hll')
- mode: complete
- outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 424 Basic stats: COMPLETE Column stats: COMPLETE
- Select Operator
- expressions: _col0 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>)
- outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 424 Basic stats: COMPLETE Column stats: COMPLETE
- File Output Operator
- compressed: false
- Statistics: Num rows: 1 Data size: 424 Basic stats: COMPLETE Column stats: COMPLETE
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
Reducer 5
Execution mode: llap
Reduce Operator Tree:
@@ -1825,10 +1709,6 @@ STAGE PLANS:
Stage: Stage-6
Stats Work
Basic Stats Work:
- Column Stats Desc:
- Columns: val
- Column Types: int
- Table: default.merge_tmp_table
Stage: Stage-0
Move Operator
@@ -2083,26 +1963,6 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.merge_tmp_table
- Select Operator
- expressions: _col0 (type: int)
- outputColumnNames: val
- Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE
- Group By Operator
- aggregations: compute_stats(val, 'hll')
- mode: complete
- outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 424 Basic stats: COMPLETE Column stats: COMPLETE
- Select Operator
- expressions: _col0 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>)
- outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 424 Basic stats: COMPLETE Column stats: COMPLETE
- File Output Operator
- compressed: false
- Statistics: Num rows: 1 Data size: 424 Basic stats: COMPLETE Column stats: COMPLETE
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
Reducer 5
Execution mode: llap
Reduce Operator Tree:
@@ -2179,10 +2039,6 @@ STAGE PLANS:
Stage: Stage-6
Stats Work
Basic Stats Work:
- Column Stats Desc:
- Columns: val
- Column Types: int
- Table: default.merge_tmp_table
Stage: Stage-1
Move Operator
@@ -2431,26 +2287,6 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.merge_tmp_table
- Select Operator
- expressions: _col0 (type: int)
- outputColumnNames: val
- Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE
- Group By Operator
- aggregations: compute_stats(val, 'hll')
- mode: complete
- outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 424 Basic stats: COMPLETE Column stats: COMPLETE
- Select Operator
- expressions: _col0 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>)
- outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 424 Basic stats: COMPLETE Column stats: COMPLETE
- File Output Operator
- compressed: false
- Statistics: Num rows: 1 Data size: 424 Basic stats: COMPLETE Column stats: COMPLETE
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
Reducer 5
Execution mode: llap
Reduce Operator Tree:
@@ -2527,10 +2363,6 @@ STAGE PLANS:
Stage: Stage-6
Stats Work
Basic Stats Work:
- Column Stats Desc:
- Columns: val
- Column Types: int
- Table: default.merge_tmp_table
Stage: Stage-0
Move Operator
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/llap/subquery_scalar.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/subquery_scalar.q.out b/ql/src/test/results/clientpositive/llap/subquery_scalar.q.out
index e830835..1cf281a 100644
--- a/ql/src/test/results/clientpositive/llap/subquery_scalar.q.out
+++ b/ql/src/test/results/clientpositive/llap/subquery_scalar.q.out
@@ -504,6 +504,7 @@ STAGE PLANS:
Reduce Output Operator
sort order:
Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE
+ TopN Hash Memory Usage: 0.1
Execution mode: vectorized, llap
LLAP IO: no inputs
Map 6
@@ -1071,6 +1072,7 @@ STAGE PLANS:
key expressions: _col0 (type: int)
sort order: +
Statistics: Num rows: 26 Data size: 104 Basic stats: COMPLETE Column stats: COMPLETE
+ TopN Hash Memory Usage: 0.1
PTF Operator
Function definitions:
Input definition
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/llap/subquery_select.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/subquery_select.q.out b/ql/src/test/results/clientpositive/llap/subquery_select.q.out
index d3cc980..6255abd 100644
--- a/ql/src/test/results/clientpositive/llap/subquery_select.q.out
+++ b/ql/src/test/results/clientpositive/llap/subquery_select.q.out
@@ -3001,6 +3001,7 @@ STAGE PLANS:
key expressions: _col0 (type: int)
sort order: +
Statistics: Num rows: 26 Data size: 104 Basic stats: COMPLETE Column stats: COMPLETE
+ TopN Hash Memory Usage: 0.1
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
@@ -3614,12 +3615,11 @@ STAGE PLANS:
#### A masked pattern was here ####
Edges:
Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 6 (SIMPLE_EDGE)
- Reducer 3 <- Reducer 2 (XPROD_EDGE), Reducer 8 (XPROD_EDGE)
+ Reducer 3 <- Reducer 2 (XPROD_EDGE), Reducer 7 (XPROD_EDGE)
Reducer 4 <- Map 1 (CUSTOM_SIMPLE_EDGE)
- Reducer 5 <- Map 9 (CUSTOM_SIMPLE_EDGE), Reducer 4 (CUSTOM_SIMPLE_EDGE)
+ Reducer 5 <- Map 8 (CUSTOM_SIMPLE_EDGE), Reducer 4 (CUSTOM_SIMPLE_EDGE)
Reducer 6 <- Reducer 5 (SIMPLE_EDGE)
- Reducer 7 <- Reducer 5 (SIMPLE_EDGE)
- Reducer 8 <- Reducer 7 (CUSTOM_SIMPLE_EDGE)
+ Reducer 7 <- Reducer 6 (CUSTOM_SIMPLE_EDGE)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -3652,7 +3652,7 @@ STAGE PLANS:
value expressions: _col0 (type: int)
Execution mode: vectorized, llap
LLAP IO: no inputs
- Map 9
+ Map 8
Map Operator Tree:
TableScan
alias: part
@@ -3733,10 +3733,6 @@ STAGE PLANS:
sort order: +
Statistics: Num rows: 26 Data size: 104 Basic stats: COMPLETE Column stats: COMPLETE
TopN Hash Memory Usage: 0.1
- Reduce Output Operator
- key expressions: _col0 (type: int)
- sort order: +
- Statistics: Num rows: 26 Data size: 104 Basic stats: COMPLETE Column stats: COMPLETE
Reducer 6
Execution mode: vectorized, llap
Reduce Operator Tree:
@@ -3757,16 +3753,6 @@ STAGE PLANS:
Map-reduce partition columns: _col0 (type: int)
Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: boolean)
- Reducer 7
- Execution mode: vectorized, llap
- Reduce Operator Tree:
- Select Operator
- expressions: KEY.reducesinkkey0 (type: int)
- outputColumnNames: _col0
- Statistics: Num rows: 26 Data size: 104 Basic stats: COMPLETE Column stats: COMPLETE
- Limit
- Number of rows: 1
- Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count(), count(_col0)
mode: hash
@@ -3776,7 +3762,7 @@ STAGE PLANS:
sort order:
Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: bigint), _col1 (type: bigint)
- Reducer 8
+ Reducer 7
Execution mode: vectorized, llap
Reduce Operator Tree:
Group By Operator
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/llap/tez_dml.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/tez_dml.q.out b/ql/src/test/results/clientpositive/llap/tez_dml.q.out
index ef30b30..1e8ab44 100644
--- a/ql/src/test/results/clientpositive/llap/tez_dml.q.out
+++ b/ql/src/test/results/clientpositive/llap/tez_dml.q.out
@@ -11,7 +11,7 @@ POSTHOOK: Output: default@tmp_src
STAGE DEPENDENCIES:
Stage-1 is a root stage
Stage-2 depends on stages: Stage-1
- Stage-4 depends on stages: Stage-2, Stage-0
+ Stage-4 depends on stages: Stage-0, Stage-2
Stage-3 depends on stages: Stage-4
Stage-0 depends on stages: Stage-1
@@ -62,7 +62,7 @@ STAGE PLANS:
Statistics: Num rows: 250 Data size: 24750 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: string)
Reducer 3
- Execution mode: vectorized, llap
+ Execution mode: llap
Reduce Operator Tree:
Select Operator
expressions: VALUE._col0 (type: string), KEY.reducesinkkey0 (type: bigint)
@@ -76,6 +76,26 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.tmp_src
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: bigint)
+ outputColumnNames: col1, col2
+ Statistics: Num rows: 250 Data size: 24750 Basic stats: COMPLETE Column stats: COMPLETE
+ Group By Operator
+ aggregations: compute_stats(col1, 'hll'), compute_stats(col2, 'hll')
+ mode: complete
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: _col0 (type: struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col1 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
Stage: Stage-2
Dependency Collection
@@ -92,6 +112,10 @@ STAGE PLANS:
Stage: Stage-3
Stats Work
Basic Stats Work:
+ Column Stats Desc:
+ Columns: value, cnt
+ Column Types: string, bigint
+ Table: default.tmp_src
Stage: Stage-0
Move Operator
@@ -455,39 +479,41 @@ STAGE PLANS:
#### A masked pattern was here ####
Edges:
Reducer 2 <- Map 1 (SIMPLE_EDGE)
- Reducer 3 <- Map 1 (SIMPLE_EDGE)
#### A masked pattern was here ####
Vertices:
Map 1
Map Operator Tree:
TableScan
alias: tmp_src
- Statistics: Num rows: 309 Data size: 56640 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 309 Data size: 30591 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: value (type: string), cnt (type: bigint)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 309 Data size: 56640 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 309 Data size: 30591 Basic stats: COMPLETE Column stats: COMPLETE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 309 Data size: 30591 Basic stats: COMPLETE Column stats: COMPLETE
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.tmp_src_part
Select Operator
expressions: _col0 (type: string), UDFToInteger(_col1) (type: int)
outputColumnNames: c, d
- Statistics: Num rows: 309 Data size: 56640 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 309 Data size: 29355 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: compute_stats(c, 'hll')
keys: d (type: int)
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 309 Data size: 56640 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 2220 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 309 Data size: 56640 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 2220 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>)
- Reduce Output Operator
- key expressions: _col1 (type: bigint)
- sort order: +
- Map-reduce partition columns: _col1 (type: bigint)
- value expressions: _col0 (type: string)
Execution mode: llap
LLAP IO: no inputs
Reducer 2
@@ -498,33 +524,18 @@ STAGE PLANS:
keys: KEY._col0 (type: int)
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 154 Data size: 28228 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 2220 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col1 (type: struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col0 (type: int)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 154 Data size: 28228 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 2220 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 154 Data size: 28228 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 2220 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- Reducer 3
- Execution mode: vectorized, llap
- Reduce Operator Tree:
- Select Operator
- expressions: VALUE._col0 (type: string), KEY._col1 (type: bigint)
- outputColumnNames: _col0, _col1
- File Output Operator
- compressed: false
- Dp Sort State: PARTITION_SORTED
- Statistics: Num rows: 309 Data size: 56640 Basic stats: COMPLETE Column stats: NONE
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.tmp_src_part
Stage: Stage-2
Dependency Collection
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/llap/tez_nway_join.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/tez_nway_join.q.out b/ql/src/test/results/clientpositive/llap/tez_nway_join.q.out
index 0bf2796..288f64c 100644
--- a/ql/src/test/results/clientpositive/llap/tez_nway_join.q.out
+++ b/ql/src/test/results/clientpositive/llap/tez_nway_join.q.out
@@ -60,14 +60,14 @@ STAGE PLANS:
TableScan
alias: a
filterExpr: key is not null (type: boolean)
- Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE
Filter Operator
predicate: key is not null (type: boolean)
- Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: key (type: int)
outputColumnNames: _col0
- Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE
Map Join Operator
condition map:
Inner Join 0 to 1
@@ -79,15 +79,15 @@ STAGE PLANS:
input vertices:
1 Map 3
2 Map 4
- Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 6 Data size: 26 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: count()
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
sort order:
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
value expressions: _col0 (type: bigint)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -96,19 +96,19 @@ STAGE PLANS:
TableScan
alias: b
filterExpr: key is not null (type: boolean)
- Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: NONE
Filter Operator
predicate: key is not null (type: boolean)
- Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: key (type: int)
outputColumnNames: _col0
- Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: NONE
Execution mode: vectorized, llap
LLAP IO: all inputs
Map 4
@@ -116,19 +116,19 @@ STAGE PLANS:
TableScan
alias: c
filterExpr: key is not null (type: boolean)
- Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: NONE
Filter Operator
predicate: key is not null (type: boolean)
- Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: key (type: int)
outputColumnNames: _col0
- Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: NONE
Execution mode: vectorized, llap
LLAP IO: all inputs
Reducer 2
@@ -138,10 +138,10 @@ STAGE PLANS:
aggregations: count(VALUE._col0)
mode: mergepartial
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -181,14 +181,14 @@ STAGE PLANS:
TableScan
alias: a
filterExpr: key is not null (type: boolean)
- Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE
Filter Operator
predicate: key is not null (type: boolean)
- Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: key (type: int)
outputColumnNames: _col0
- Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE
Map Join Operator
condition map:
Inner Join 0 to 1
@@ -198,7 +198,7 @@ STAGE PLANS:
outputColumnNames: _col0
input vertices:
1 Map 3
- Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 3 Data size: 13 Basic stats: COMPLETE Column stats: NONE
Map Join Operator
condition map:
Inner Join 0 to 1
@@ -207,15 +207,15 @@ STAGE PLANS:
1 _col0 (type: int)
input vertices:
1 Map 4
- Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 3 Data size: 14 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: count()
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
sort order:
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
value expressions: _col0 (type: bigint)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -224,19 +224,19 @@ STAGE PLANS:
TableScan
alias: b
filterExpr: key is not null (type: boolean)
- Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: NONE
Filter Operator
predicate: key is not null (type: boolean)
- Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: key (type: int)
outputColumnNames: _col0
- Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: NONE
Execution mode: vectorized, llap
LLAP IO: all inputs
Map 4
@@ -244,19 +244,19 @@ STAGE PLANS:
TableScan
alias: c
filterExpr: key is not null (type: boolean)
- Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: NONE
Filter Operator
predicate: key is not null (type: boolean)
- Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: key (type: int)
outputColumnNames: _col0
- Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: NONE
Execution mode: vectorized, llap
LLAP IO: all inputs
Reducer 2
@@ -266,10 +266,10 @@ STAGE PLANS:
aggregations: count(VALUE._col0)
mode: mergepartial
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -330,48 +330,48 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: a
- Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: key (type: int)
outputColumnNames: _col0
- Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE
Execution mode: vectorized, llap
LLAP IO: all inputs
Map 4
Map Operator Tree:
TableScan
alias: b
- Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: key (type: int)
outputColumnNames: _col0
- Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: NONE
Execution mode: vectorized, llap
LLAP IO: all inputs
Map 5
Map Operator Tree:
TableScan
alias: c
- Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: key (type: int)
outputColumnNames: _col0
- Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: NONE
Execution mode: vectorized, llap
LLAP IO: all inputs
Reducer 2
@@ -385,15 +385,15 @@ STAGE PLANS:
0 _col0 (type: int)
1 _col0 (type: int)
2 _col0 (type: int)
- Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 6 Data size: 26 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: count()
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
sort order:
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
value expressions: _col0 (type: bigint)
Reducer 3
Execution mode: vectorized, llap
@@ -402,10 +402,10 @@ STAGE PLANS:
aggregations: count(VALUE._col0)
mode: mergepartial
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -444,11 +444,11 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: a
- Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: key (type: int)
outputColumnNames: _col0
- Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE
Map Join Operator
condition map:
Left Outer Join 0 to 1
@@ -458,7 +458,7 @@ STAGE PLANS:
outputColumnNames: _col0
input vertices:
1 Map 3
- Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 3 Data size: 13 Basic stats: COMPLETE Column stats: NONE
Map Join Operator
condition map:
Left Outer Join 0 to 1
@@ -467,15 +467,15 @@ STAGE PLANS:
1 _col0 (type: int)
input vertices:
1 Map 4
- Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 3 Data size: 14 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: count()
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
sort order:
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
value expressions: _col0 (type: bigint)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -483,32 +483,32 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: b
- Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: key (type: int)
outputColumnNames: _col0
- Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: NONE
Execution mode: vectorized, llap
LLAP IO: all inputs
Map 4
Map Operator Tree:
TableScan
alias: c
- Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: key (type: int)
outputColumnNames: _col0
- Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: NONE
Execution mode: vectorized, llap
LLAP IO: all inputs
Reducer 2
@@ -518,10 +518,10 @@ STAGE PLANS:
aggregations: count(VALUE._col0)
mode: mergepartial
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/llap/tez_smb_reduce_side.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/tez_smb_reduce_side.q.out b/ql/src/test/results/clientpositive/llap/tez_smb_reduce_side.q.out
index 7ceeb41..5f8cbaf 100644
--- a/ql/src/test/results/clientpositive/llap/tez_smb_reduce_side.q.out
+++ b/ql/src/test/results/clientpositive/llap/tez_smb_reduce_side.q.out
@@ -87,18 +87,18 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: x
- Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count(value)
keys: key (type: string)
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 95 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 95 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: bigint)
Execution mode: vectorized, llap
LLAP IO: no inputs
@@ -106,22 +106,22 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: y
- Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 348 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: key (type: string), value (type: string)
outputColumnNames: key, value
- Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 348 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count(value)
keys: key (type: string)
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: bigint)
Execution mode: vectorized, llap
LLAP IO: no inputs
@@ -132,7 +132,7 @@ STAGE PLANS:
keys: KEY._col0 (type: string)
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 95 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: llap
Reduce Operator Tree:
Group By Operator
@@ -140,7 +140,7 @@ STAGE PLANS:
keys: KEY._col0 (type: string)
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: COMPLETE
Merge Join Operator
condition map:
Right Outer Join 0 to 1
@@ -148,19 +148,19 @@ STAGE PLANS:
0 _col0 (type: string)
1 _col0 (type: string)
outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 189 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: hash(_col0) (type: int), hash(_col1) (type: int), hash(_col2) (type: int), hash(_col3) (type: int)
outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 1 Data size: 404 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 189 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: sum(_col0), sum(_col1), sum(_col2), sum(_col3)
mode: hash
outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
- Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: bigint), _col1 (type: bigint), _col2 (type: bigint), _col3 (type: bigint)
Reducer 5
Execution mode: vectorized, llap
@@ -169,10 +169,10 @@ STAGE PLANS:
aggregations: sum(VALUE._col0), sum(VALUE._col1), sum(VALUE._col2), sum(VALUE._col3)
mode: mergepartial
outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
[16/35] hive git commit: HIVE-16957: Support CTAS for auto gather
column stats (Jesus Camacho Rodriguez, reviewed by Ashutosh Chauhan)
Posted by jc...@apache.org.
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/llap/vector_case_when_1.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/vector_case_when_1.q.out b/ql/src/test/results/clientpositive/llap/vector_case_when_1.q.out
index 5f94d60..6529758 100644
--- a/ql/src/test/results/clientpositive/llap/vector_case_when_1.q.out
+++ b/ql/src/test/results/clientpositive/llap/vector_case_when_1.q.out
@@ -204,7 +204,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: lineitem_test
- Statistics: Num rows: 101 Data size: 57327 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 101 Data size: 58277 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:l_orderkey:int, 1:l_partkey:int, 2:l_suppkey:int, 3:l_linenumber:int, 4:l_quantity:int, 5:l_extendedprice:double, 6:l_discount:double, 7:l_tax:decimal(10,2)/DECIMAL_64, 8:l_returnflag:char(1), 9:l_linestatus:char(1), 10:l_shipdate:date, 11:l_commitdate:date, 12:l_receiptdate:date, 13:l_shipinstruct:varchar(20), 14:l_shipmode:char(10), 15:l_comment:string, 16:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -216,13 +216,13 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [4, 21, 26, 31, 35, 39, 43, 45, 47, 49, 51, 53, 55, 59, 62, 65, 68]
selectExpressions: VectorUDFAdaptor(CASE WHEN ((l_quantity = 1)) THEN ('Single') WHEN ((l_quantity = 2)) THEN ('Two') WHEN ((l_quantity < 10)) THEN ('Some') WHEN ((l_quantity < 100)) THEN ('Many') ELSE ('Huge number') END)(children: LongColEqualLongScalar(col 4:int, val 1) -> 17:boolean, LongColEqualLongScalar(col 4:int, val 2) -> 18:boolean, LongColLessLongScalar(col 4:int, val 10) -> 19:boolean, LongColLessLongScalar(col 4:int, val 100) -> 20:boolean) -> 21:string, VectorUDFAdaptor(CASE WHEN ((l_quantity = 1)) THEN ('Single') WHEN ((l_quantity = 2)) THEN ('Two') WHEN ((l_quantity < 10)) THEN ('Some') WHEN ((l_quantity < 100)) THEN ('Many') ELSE (null) END)(children: LongColEqualLongScalar(col 4:int, val 1) -> 22:boolean, LongColEqualLongScalar(col 4:int, val 2) -> 23:boolean, LongColLessLongScalar(col 4:int, val 10) -> 24:boolean, LongColLessLongScalar(col 4:int, val 100) -> 25:boolean) -> 26:string, VectorUDFAdaptor(CASE WHEN ((l_quantity = 1)) THEN ('Sing
le') WHEN ((l_quantity = 2)) THEN ('Two') WHEN ((l_quantity < 10)) THEN ('Some') WHEN ((l_quantity < 100)) THEN (null) ELSE (null) END)(children: LongColEqualLongScalar(col 4:int, val 1) -> 27:boolean, LongColEqualLongScalar(col 4:int, val 2) -> 28:boolean, LongColLessLongScalar(col 4:int, val 10) -> 29:boolean, LongColLessLongScalar(col 4:int, val 100) -> 30:boolean) -> 31:string, IfExprLongColumnLongColumn(col 32:boolean, col 33:date, col 34:date)(children: StringGroupColEqualCharScalar(col 14:char(10), val SHIP) -> 32:boolean, VectorUDFDateAddColScalar(col 10:date, val 10) -> 33:date, VectorUDFDateAddColScalar(col 10:date, val 5) -> 34:date) -> 35:date, VectorUDFAdaptor(CASE WHEN ((l_returnflag = 'N')) THEN ((l_extendedprice * (1.0D - l_discount))) ELSE (0) END)(children: StringGroupColEqualCharScalar(col 8:char(1), val N) -> 36:boolean, DoubleColMultiplyDoubleColumn(col 5:double, col 37:double)(children: DoubleScalarSubtractDoubleColumn(val 1.0, col 6:double) -> 37:double) -> 38
:double) -> 39:double, VectorUDFAdaptor(CASE WHEN ((l_returnflag = 'N')) THEN ((l_extendedprice * (1.0D - l_discount))) ELSE (0.0D) END)(children: StringGroupColEqualCharScalar(col 8:char(1), val N) -> 40:boolean, DoubleColMultiplyDoubleColumn(col 5:double, col 41:double)(children: DoubleScalarSubtractDoubleColumn(val 1.0, col 6:double) -> 41:double) -> 42:double) -> 43:double, VectorUDFAdaptor(if((CAST( l_shipinstruct AS STRING) = 'DELIVER IN PERSON'), null, l_tax))(children: StringGroupColEqualStringScalar(col 13:string, val DELIVER IN PERSON)(children: col 13:varchar(20)) -> 44:boolean) -> 45:decimal(10,2), VectorUDFAdaptor(if((CAST( l_shipinstruct AS STRING) = 'TAKE BACK RETURN'), l_tax, null))(children: StringGroupColEqualStringScalar(col 13:string, val TAKE BACK RETURN)(children: col 13:varchar(20)) -> 46:boolean) -> 47:decimal(10,2), VectorUDFAdaptor(if((CAST( l_shipinstruct AS STRING) = 'DELIVER IN PERSON'), 0, l_tax))(children: StringGroupColEqualStringScalar(col 13:string,
val DELIVER IN PERSON)(children: col 13:varchar(20)) -> 48:boolean) -> 49:decimal(12,2), VectorUDFAdaptor(if((CAST( l_shipinstruct AS STRING) = 'TAKE BACK RETURN'), l_tax, 0))(children: StringGroupColEqualStringScalar(col 13:string, val TAKE BACK RETURN)(children: col 13:varchar(20)) -> 50:boolean) -> 51:decimal(12,2), IfExprDecimal64ScalarDecimal64Column(col 52:boolean, decimal64Val 0, decimalVal 0, col 7:decimal(10,2)/DECIMAL_64)(children: StringGroupColEqualStringScalar(col 13:string, val DELIVER IN PERSON)(children: col 13:varchar(20)) -> 52:boolean) -> 53:decimal(10,2)/DECIMAL_64, IfExprDecimal64ColumnDecimal64Scalar(col 54:boolean, col 7:decimal(10,2)/DECIMAL_64, decimal64Val 0, decimalVal 0)(children: StringGroupColEqualStringScalar(col 13:string, val TAKE BACK RETURN)(children: col 13:varchar(20)) -> 54:boolean) -> 55:decimal(10,2)/DECIMAL_64, IfExprTimestampColumnColumn(col 56:boolean, col 57:timestampcol 58:timestamp)(children: LongColGreaterLongScalar(col 1:int, val 30)
-> 56:boolean, CastDateToTimestamp(col 12:date) -> 57:timestamp, CastDateToTimestamp(col 11:date) -> 58:timestamp) -> 59:timestamp, VectorUDFAdaptor(if((l_suppkey > 10000), datediff(l_receiptdate, l_commitdate), null))(children: LongColGreaterLongScalar(col 2:int, val 10000) -> 60:boolean, VectorUDFDateDiffColCol(col 12:date, col 11:date) -> 61:int) -> 62:int, VectorUDFAdaptor(if((l_suppkey > 10000), null, datediff(l_receiptdate, l_commitdate)))(children: LongColGreaterLongScalar(col 2:int, val 10000) -> 63:boolean, VectorUDFDateDiffColCol(col 12:date, col 11:date) -> 64:int) -> 65:int, IfExprLongScalarLongScalar(col 67:boolean, val 14245, val 14609)(children: LongColGreaterLongScalar(col 66:int, val 100)(children: LongColModuloLongScalar(col 2:int, val 500) -> 66:int) -> 67:boolean) -> 68:date
- Statistics: Num rows: 101 Data size: 57327 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 101 Data size: 141804 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 101 Data size: 57327 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 101 Data size: 141804 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -541,7 +541,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: lineitem_test
- Statistics: Num rows: 101 Data size: 57327 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 101 Data size: 58277 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:l_orderkey:int, 1:l_partkey:int, 2:l_suppkey:int, 3:l_linenumber:int, 4:l_quantity:int, 5:l_extendedprice:double, 6:l_discount:double, 7:l_tax:decimal(10,2)/DECIMAL_64, 8:l_returnflag:char(1), 9:l_linestatus:char(1), 10:l_shipdate:date, 11:l_commitdate:date, 12:l_receiptdate:date, 13:l_shipinstruct:varchar(20), 14:l_shipmode:char(10), 15:l_comment:string, 16:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -553,13 +553,13 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [4, 24, 33, 40, 44, 49, 53, 55, 57, 59, 61, 63, 65, 69, 72, 75, 78]
selectExpressions: IfExprStringScalarStringGroupColumn(col 17:boolean, val Singlecol 23:string)(children: LongColEqualLongScalar(col 4:int, val 1) -> 17:boolean, IfExprStringScalarStringGroupColumn(col 18:boolean, val Twocol 22:string)(children: LongColEqualLongScalar(col 4:int, val 2) -> 18:boolean, IfExprStringScalarStringGroupColumn(col 19:boolean, val Somecol 21:string)(children: LongColLessLongScalar(col 4:int, val 10) -> 19:boolean, IfExprStringScalarStringScalar(col 20:boolean, val Many, val Huge number)(children: LongColLessLongScalar(col 4:int, val 100) -> 20:boolean) -> 21:string) -> 22:string) -> 23:string) -> 24:string, IfExprStringScalarStringGroupColumn(col 25:boolean, val Singlecol 32:string)(children: LongColEqualLongScalar(col 4:int, val 1) -> 25:boolean, IfExprStringScalarStringGroupColumn(col 26:boolean, val Twocol 31:string)(children: LongColEqualLongScalar(col 4:int, val 2) -> 26:boolean, IfExprStringScalarStringGroupColumn(col 27:boolean
, val Somecol 30:string)(children: LongColLessLongScalar(col 4:int, val 10) -> 27:boolean, IfExprColumnNull(col 28:boolean, col 29:string, null)(children: LongColLessLongScalar(col 4:int, val 100) -> 28:boolean, ConstantVectorExpression(val Many) -> 29:string) -> 30:string) -> 31:string) -> 32:string) -> 33:string, IfExprStringScalarStringGroupColumn(col 34:boolean, val Singlecol 39:string)(children: LongColEqualLongScalar(col 4:int, val 1) -> 34:boolean, IfExprStringScalarStringGroupColumn(col 35:boolean, val Twocol 38:string)(children: LongColEqualLongScalar(col 4:int, val 2) -> 35:boolean, IfExprStringScalarStringGroupColumn(col 36:boolean, val Somecol 37:string)(children: LongColLessLongScalar(col 4:int, val 10) -> 36:boolean, IfExprNullNull(null, null) -> 37:string) -> 38:string) -> 39:string) -> 40:string, IfExprLongColumnLongColumn(col 41:boolean, col 42:date, col 43:date)(children: StringGroupColEqualCharScalar(col 14:char(10), val SHIP) -> 41:boolean, VectorUDFDateAddColSca
lar(col 10:date, val 10) -> 42:date, VectorUDFDateAddColScalar(col 10:date, val 5) -> 43:date) -> 44:date, IfExprDoubleColumnDoubleColumn(col 45:boolean, col 47:doublecol 48:double)(children: StringGroupColEqualCharScalar(col 8:char(1), val N) -> 45:boolean, DoubleColMultiplyDoubleColumn(col 5:double, col 46:double)(children: DoubleScalarSubtractDoubleColumn(val 1.0, col 6:double) -> 46:double) -> 47:double, ConstantVectorExpression(val 0.0) -> 48:double) -> 49:double, IfExprDoubleColumnDoubleScalar(col 50:boolean, col 52:double, val 0.0)(children: StringGroupColEqualCharScalar(col 8:char(1), val N) -> 50:boolean, DoubleColMultiplyDoubleColumn(col 5:double, col 51:double)(children: DoubleScalarSubtractDoubleColumn(val 1.0, col 6:double) -> 51:double) -> 52:double) -> 53:double, IfExprNullColumn(col 54:boolean, null, col 79)(children: StringGroupColEqualStringScalar(col 13:string, val DELIVER IN PERSON)(children: col 13:varchar(20)) -> 54:boolean, ConvertDecimal64ToDecimal(col 7:deci
mal(10,2)/DECIMAL_64) -> 79:decimal(10,2)) -> 55:decimal(10,2), IfExprColumnNull(col 56:boolean, col 80:decimal(10,2), null)(children: StringGroupColEqualStringScalar(col 13:string, val TAKE BACK RETURN)(children: col 13:varchar(20)) -> 56:boolean, ConvertDecimal64ToDecimal(col 7:decimal(10,2)/DECIMAL_64) -> 80:decimal(10,2)) -> 57:decimal(10,2), VectorUDFAdaptor(if((CAST( l_shipinstruct AS STRING) = 'DELIVER IN PERSON'), 0, l_tax))(children: StringGroupColEqualStringScalar(col 13:string, val DELIVER IN PERSON)(children: col 13:varchar(20)) -> 58:boolean) -> 59:decimal(12,2), VectorUDFAdaptor(if((CAST( l_shipinstruct AS STRING) = 'TAKE BACK RETURN'), l_tax, 0))(children: StringGroupColEqualStringScalar(col 13:string, val TAKE BACK RETURN)(children: col 13:varchar(20)) -> 60:boolean) -> 61:decimal(12,2), IfExprDecimal64ScalarDecimal64Column(col 62:boolean, decimal64Val 0, decimalVal 0, col 7:decimal(10,2)/DECIMAL_64)(children: StringGroupColEqualStringScalar(col 13:string, val DELIVE
R IN PERSON)(children: col 13:varchar(20)) -> 62:boolean) -> 63:decimal(10,2)/DECIMAL_64, IfExprDecimal64ColumnDecimal64Scalar(col 64:boolean, col 7:decimal(10,2)/DECIMAL_64, decimal64Val 0, decimalVal 0)(children: StringGroupColEqualStringScalar(col 13:string, val TAKE BACK RETURN)(children: col 13:varchar(20)) -> 64:boolean) -> 65:decimal(10,2)/DECIMAL_64, IfExprTimestampColumnColumn(col 66:boolean, col 67:timestampcol 68:timestamp)(children: LongColGreaterLongScalar(col 1:int, val 30) -> 66:boolean, CastDateToTimestamp(col 12:date) -> 67:timestamp, CastDateToTimestamp(col 11:date) -> 68:timestamp) -> 69:timestamp, IfExprColumnNull(col 70:boolean, col 71:int, null)(children: LongColGreaterLongScalar(col 2:int, val 10000) -> 70:boolean, VectorUDFDateDiffColCol(col 12:date, col 11:date) -> 71:int) -> 72:int, IfExprNullColumn(col 73:boolean, null, col 74)(children: LongColGreaterLongScalar(col 2:int, val 10000) -> 73:boolean, VectorUDFDateDiffColCol(col 12:date, col 11:date) -> 74:in
t) -> 75:int, IfExprLongScalarLongScalar(col 77:boolean, val 14245, val 14609)(children: LongColGreaterLongScalar(col 76:int, val 100)(children: LongColModuloLongScalar(col 2:int, val 500) -> 76:int) -> 77:boolean) -> 78:date
- Statistics: Num rows: 101 Data size: 57327 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 101 Data size: 141804 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 101 Data size: 57327 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 101 Data size: 141804 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -878,7 +878,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: lineitem_test
- Statistics: Num rows: 101 Data size: 57327 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 101 Data size: 58277 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:l_orderkey:int, 1:l_partkey:int, 2:l_suppkey:int, 3:l_linenumber:int, 4:l_quantity:int, 5:l_extendedprice:double, 6:l_discount:double, 7:l_tax:decimal(10,2)/DECIMAL_64, 8:l_returnflag:char(1), 9:l_linestatus:char(1), 10:l_shipdate:date, 11:l_commitdate:date, 12:l_receiptdate:date, 13:l_shipinstruct:varchar(20), 14:l_shipmode:char(10), 15:l_comment:string, 16:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -890,13 +890,13 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [4, 27, 39, 49, 53, 58, 63, 65, 67, 72, 77, 79, 81, 85, 88, 91, 94]
selectExpressions: IfExprColumnCondExpr(col 17:boolean, col 18:stringcol 26:string)(children: LongColEqualLongScalar(col 4:int, val 1) -> 17:boolean, ConstantVectorExpression(val Single) -> 18:string, IfExprColumnCondExpr(col 19:boolean, col 20:stringcol 25:string)(children: LongColEqualLongScalar(col 4:int, val 2) -> 19:boolean, ConstantVectorExpression(val Two) -> 20:string, IfExprColumnCondExpr(col 21:boolean, col 22:stringcol 24:string)(children: LongColLessLongScalar(col 4:int, val 10) -> 21:boolean, ConstantVectorExpression(val Some) -> 22:string, IfExprStringScalarStringScalar(col 23:boolean, val Many, val Huge number)(children: LongColLessLongScalar(col 4:int, val 100) -> 23:boolean) -> 24:string) -> 25:string) -> 26:string) -> 27:string, IfExprColumnCondExpr(col 28:boolean, col 29:stringcol 38:string)(children: LongColEqualLongScalar(col 4:int, val 1) -> 28:boolean, ConstantVectorExpression(val Single) -> 29:string, IfExprColumnCondExpr(col 30:boolea
n, col 31:stringcol 37:string)(children: LongColEqualLongScalar(col 4:int, val 2) -> 30:boolean, ConstantVectorExpression(val Two) -> 31:string, IfExprColumnCondExpr(col 32:boolean, col 33:stringcol 36:string)(children: LongColLessLongScalar(col 4:int, val 10) -> 32:boolean, ConstantVectorExpression(val Some) -> 33:string, IfExprColumnNull(col 34:boolean, col 35:string, null)(children: LongColLessLongScalar(col 4:int, val 100) -> 34:boolean, ConstantVectorExpression(val Many) -> 35:string) -> 36:string) -> 37:string) -> 38:string) -> 39:string, IfExprColumnCondExpr(col 40:boolean, col 41:stringcol 48:string)(children: LongColEqualLongScalar(col 4:int, val 1) -> 40:boolean, ConstantVectorExpression(val Single) -> 41:string, IfExprColumnCondExpr(col 42:boolean, col 43:stringcol 47:string)(children: LongColEqualLongScalar(col 4:int, val 2) -> 42:boolean, ConstantVectorExpression(val Two) -> 43:string, IfExprColumnCondExpr(col 44:boolean, col 45:stringcol 46:string)(children: LongColLes
sLongScalar(col 4:int, val 10) -> 44:boolean, ConstantVectorExpression(val Some) -> 45:string, IfExprNullNull(null, null) -> 46:string) -> 47:string) -> 48:string) -> 49:string, IfExprCondExprCondExpr(col 50:boolean, col 51:datecol 52:date)(children: StringGroupColEqualCharScalar(col 14:char(10), val SHIP) -> 50:boolean, VectorUDFDateAddColScalar(col 10:date, val 10) -> 51:date, VectorUDFDateAddColScalar(col 10:date, val 5) -> 52:date) -> 53:date, IfExprCondExprCondExpr(col 54:boolean, col 56:doublecol 57:double)(children: StringGroupColEqualCharScalar(col 8:char(1), val N) -> 54:boolean, DoubleColMultiplyDoubleColumn(col 5:double, col 55:double)(children: DoubleScalarSubtractDoubleColumn(val 1.0, col 6:double) -> 55:double) -> 56:double, ConstantVectorExpression(val 0.0) -> 57:double) -> 58:double, IfExprCondExprColumn(col 59:boolean, col 61:double, col 62:double)(children: StringGroupColEqualCharScalar(col 8:char(1), val N) -> 59:boolean, DoubleColMultiplyDoubleColumn(col 5:double
, col 60:double)(children: DoubleScalarSubtractDoubleColumn(val 1.0, col 6:double) -> 60:double) -> 61:double, ConstantVectorExpression(val 0.0) -> 62:double) -> 63:double, IfExprNullColumn(col 64:boolean, null, col 95)(children: StringGroupColEqualStringScalar(col 13:string, val DELIVER IN PERSON)(children: col 13:varchar(20)) -> 64:boolean, ConvertDecimal64ToDecimal(col 7:decimal(10,2)/DECIMAL_64) -> 95:decimal(10,2)) -> 65:decimal(10,2), IfExprColumnNull(col 66:boolean, col 96:decimal(10,2), null)(children: StringGroupColEqualStringScalar(col 13:string, val TAKE BACK RETURN)(children: col 13:varchar(20)) -> 66:boolean, ConvertDecimal64ToDecimal(col 7:decimal(10,2)/DECIMAL_64) -> 96:decimal(10,2)) -> 67:decimal(10,2), VectorUDFAdaptor(if((CAST( l_shipinstruct AS STRING) = 'DELIVER IN PERSON'), 0, l_tax))(children: StringGroupColEqualStringScalar(col 13:string, val DELIVER IN PERSON)(children: col 13:varchar(20)) -> 71:boolean) -> 72:decimal(12,2), VectorUDFAdaptor(if((CAST( l_ship
instruct AS STRING) = 'TAKE BACK RETURN'), l_tax, 0))(children: StringGroupColEqualStringScalar(col 13:string, val TAKE BACK RETURN)(children: col 13:varchar(20)) -> 76:boolean) -> 77:decimal(12,2), IfExprDecimal64ScalarDecimal64Column(col 78:boolean, decimal64Val 0, decimalVal 0, col 7:decimal(10,2)/DECIMAL_64)(children: StringGroupColEqualStringScalar(col 13:string, val DELIVER IN PERSON)(children: col 13:varchar(20)) -> 78:boolean) -> 79:decimal(10,2)/DECIMAL_64, IfExprDecimal64ColumnDecimal64Scalar(col 80:boolean, col 7:decimal(10,2)/DECIMAL_64, decimal64Val 0, decimalVal 0)(children: StringGroupColEqualStringScalar(col 13:string, val TAKE BACK RETURN)(children: col 13:varchar(20)) -> 80:boolean) -> 81:decimal(10,2)/DECIMAL_64, IfExprCondExprCondExpr(col 82:boolean, col 83:timestampcol 84:timestamp)(children: LongColGreaterLongScalar(col 1:int, val 30) -> 82:boolean, CastDateToTimestamp(col 12:date) -> 83:timestamp, CastDateToTimestamp(col 11:date) -> 84:timestamp) -> 85:timesta
mp, IfExprCondExprNull(col 86:boolean, col 87:int, null)(children: LongColGreaterLongScalar(col 2:int, val 10000) -> 86:boolean, VectorUDFDateDiffColCol(col 12:date, col 11:date) -> 87:int) -> 88:int, IfExprNullCondExpr(col 89:boolean, null, col 90:int)(children: LongColGreaterLongScalar(col 2:int, val 10000) -> 89:boolean, VectorUDFDateDiffColCol(col 12:date, col 11:date) -> 90:int) -> 91:int, IfExprLongScalarLongScalar(col 93:boolean, val 14245, val 14609)(children: LongColGreaterLongScalar(col 92:int, val 100)(children: LongColModuloLongScalar(col 2:int, val 500) -> 92:int) -> 93:boolean) -> 94:date
- Statistics: Num rows: 101 Data size: 57327 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 101 Data size: 141804 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 101 Data size: 57327 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 101 Data size: 141804 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/llap/vector_char_mapjoin1.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/vector_char_mapjoin1.q.out b/ql/src/test/results/clientpositive/llap/vector_char_mapjoin1.q.out
index 23024d3..d6f01ae 100644
--- a/ql/src/test/results/clientpositive/llap/vector_char_mapjoin1.q.out
+++ b/ql/src/test/results/clientpositive/llap/vector_char_mapjoin1.q.out
@@ -154,7 +154,7 @@ STAGE PLANS:
TableScan
alias: a
filterExpr: c2 is not null (type: boolean)
- Statistics: Num rows: 3 Data size: 294 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 273 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
Filter Operator
@@ -163,7 +163,7 @@ STAGE PLANS:
native: true
predicateExpression: SelectColumnIsNotNull(col 1:char(10))
predicate: c2 is not null (type: boolean)
- Statistics: Num rows: 3 Data size: 294 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 273 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: c1 (type: int), c2 (type: char(10))
outputColumnNames: _col0, _col1
@@ -171,7 +171,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1]
- Statistics: Num rows: 3 Data size: 294 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 273 Basic stats: COMPLETE Column stats: COMPLETE
Map Join Operator
condition map:
Inner Join 0 to 1
@@ -186,7 +186,7 @@ STAGE PLANS:
outputColumnNames: _col0, _col1, _col2, _col3
input vertices:
1 Map 3
- Statistics: Num rows: 3 Data size: 323 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4 Data size: 728 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
@@ -194,7 +194,7 @@ STAGE PLANS:
className: VectorReduceSinkObjectHashOperator
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 3 Data size: 323 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4 Data size: 728 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: char(10)), _col2 (type: int), _col3 (type: char(10))
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -212,7 +212,7 @@ STAGE PLANS:
TableScan
alias: b
filterExpr: c2 is not null (type: boolean)
- Statistics: Num rows: 3 Data size: 294 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 273 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
Filter Operator
@@ -221,7 +221,7 @@ STAGE PLANS:
native: true
predicateExpression: SelectColumnIsNotNull(col 1:char(10))
predicate: c2 is not null (type: boolean)
- Statistics: Num rows: 3 Data size: 294 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 273 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: c1 (type: int), c2 (type: char(10))
outputColumnNames: _col0, _col1
@@ -229,7 +229,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1]
- Statistics: Num rows: 3 Data size: 294 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 273 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col1 (type: char(10))
sort order: +
@@ -238,7 +238,7 @@ STAGE PLANS:
className: VectorReduceSinkStringOperator
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 3 Data size: 294 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 273 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: int)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -267,13 +267,13 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1, 2, 3]
- Statistics: Num rows: 3 Data size: 323 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4 Data size: 728 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 3 Data size: 323 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4 Data size: 728 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -321,8 +321,8 @@ STAGE PLANS:
Tez
#### A masked pattern was here ####
Edges:
- Map 2 <- Map 1 (BROADCAST_EDGE)
- Reducer 3 <- Map 2 (SIMPLE_EDGE)
+ Map 1 <- Map 3 (BROADCAST_EDGE)
+ Reducer 2 <- Map 1 (SIMPLE_EDGE)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -330,7 +330,7 @@ STAGE PLANS:
TableScan
alias: a
filterExpr: c2 is not null (type: boolean)
- Statistics: Num rows: 3 Data size: 294 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 273 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
Filter Operator
@@ -339,7 +339,7 @@ STAGE PLANS:
native: true
predicateExpression: SelectColumnIsNotNull(col 1:char(10))
predicate: c2 is not null (type: boolean)
- Statistics: Num rows: 3 Data size: 294 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 273 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: c1 (type: int), c2 (type: char(10))
outputColumnNames: _col0, _col1
@@ -347,17 +347,31 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1]
- Statistics: Num rows: 3 Data size: 294 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col1 (type: char(20))
- sort order: +
- Map-reduce partition columns: _col1 (type: char(20))
- Reduce Sink Vectorization:
- className: VectorReduceSinkStringOperator
+ Statistics: Num rows: 3 Data size: 273 Basic stats: COMPLETE Column stats: COMPLETE
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col1 (type: char(20))
+ 1 _col1 (type: char(20))
+ Map Join Vectorization:
+ className: VectorMapJoinInnerStringOperator
native: true
- nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 3 Data size: 294 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col0 (type: int)
+ nativeConditionsMet: hive.mapjoin.optimized.hashtable IS true, hive.vectorized.execution.mapjoin.native.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, One MapJoin Condition IS true, No nullsafe IS true, Small table vectorizes IS true, Optimized Table and Supports Key Types IS true
+ hashTableImplementationType: OPTIMIZED
+ outputColumnNames: _col0, _col1, _col2, _col3
+ input vertices:
+ 1 Map 3
+ Statistics: Num rows: 4 Data size: 728 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ key expressions: _col0 (type: int)
+ sort order: +
+ Reduce Sink Vectorization:
+ className: VectorReduceSinkObjectHashOperator
+ native: true
+ nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
+ Statistics: Num rows: 4 Data size: 728 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col1 (type: char(10)), _col2 (type: int), _col3 (type: char(20))
Execution mode: vectorized, llap
LLAP IO: all inputs
Map Vectorization:
@@ -369,12 +383,12 @@ STAGE PLANS:
allNative: true
usesVectorUDFAdaptor: false
vectorized: true
- Map 2
+ Map 3
Map Operator Tree:
TableScan
alias: b
filterExpr: c2 is not null (type: boolean)
- Statistics: Num rows: 3 Data size: 324 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 273 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
Filter Operator
@@ -383,7 +397,7 @@ STAGE PLANS:
native: true
predicateExpression: SelectColumnIsNotNull(col 1:char(20))
predicate: c2 is not null (type: boolean)
- Statistics: Num rows: 3 Data size: 324 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 273 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: c1 (type: int), c2 (type: char(20))
outputColumnNames: _col0, _col1
@@ -391,31 +405,17 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1]
- Statistics: Num rows: 3 Data size: 324 Basic stats: COMPLETE Column stats: NONE
- Map Join Operator
- condition map:
- Inner Join 0 to 1
- keys:
- 0 _col1 (type: char(20))
- 1 _col1 (type: char(20))
- Map Join Vectorization:
- className: VectorMapJoinInnerStringOperator
+ Statistics: Num rows: 3 Data size: 273 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ key expressions: _col1 (type: char(20))
+ sort order: +
+ Map-reduce partition columns: _col1 (type: char(20))
+ Reduce Sink Vectorization:
+ className: VectorReduceSinkStringOperator
native: true
- nativeConditionsMet: hive.mapjoin.optimized.hashtable IS true, hive.vectorized.execution.mapjoin.native.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, One MapJoin Condition IS true, No nullsafe IS true, Small table vectorizes IS true, Optimized Table and Supports Key Types IS true
- hashTableImplementationType: OPTIMIZED
- outputColumnNames: _col0, _col1, _col2, _col3
- input vertices:
- 0 Map 1
- Statistics: Num rows: 3 Data size: 323 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: int)
- sort order: +
- Reduce Sink Vectorization:
- className: VectorReduceSinkObjectHashOperator
- native: true
- nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 3 Data size: 323 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col1 (type: char(10)), _col2 (type: int), _col3 (type: char(20))
+ nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
+ Statistics: Num rows: 3 Data size: 273 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col0 (type: int)
Execution mode: vectorized, llap
LLAP IO: all inputs
Map Vectorization:
@@ -427,7 +427,7 @@ STAGE PLANS:
allNative: true
usesVectorUDFAdaptor: false
vectorized: true
- Reducer 3
+ Reducer 2
Execution mode: vectorized, llap
Reduce Vectorization:
enabled: true
@@ -443,13 +443,13 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1, 2, 3]
- Statistics: Num rows: 3 Data size: 323 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4 Data size: 728 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 3 Data size: 323 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4 Data size: 728 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -499,8 +499,8 @@ STAGE PLANS:
Tez
#### A masked pattern was here ####
Edges:
- Map 2 <- Map 1 (BROADCAST_EDGE)
- Reducer 3 <- Map 2 (SIMPLE_EDGE)
+ Map 1 <- Map 3 (BROADCAST_EDGE)
+ Reducer 2 <- Map 1 (SIMPLE_EDGE)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -508,7 +508,7 @@ STAGE PLANS:
TableScan
alias: a
filterExpr: c2 is not null (type: boolean)
- Statistics: Num rows: 3 Data size: 294 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 273 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
Filter Operator
@@ -517,7 +517,7 @@ STAGE PLANS:
native: true
predicateExpression: SelectColumnIsNotNull(col 1:char(10))
predicate: c2 is not null (type: boolean)
- Statistics: Num rows: 3 Data size: 294 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 273 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: c1 (type: int), c2 (type: char(10)), CAST( c2 AS STRING) (type: string)
outputColumnNames: _col0, _col1, _col2
@@ -525,17 +525,39 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1, 1]
- Statistics: Num rows: 3 Data size: 294 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col2 (type: string)
- sort order: +
- Map-reduce partition columns: _col2 (type: string)
- Reduce Sink Vectorization:
- className: VectorReduceSinkStringOperator
+ Statistics: Num rows: 3 Data size: 825 Basic stats: COMPLETE Column stats: COMPLETE
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col2 (type: string)
+ 1 _col1 (type: string)
+ Map Join Vectorization:
+ className: VectorMapJoinInnerStringOperator
native: true
- nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 3 Data size: 294 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col0 (type: int), _col1 (type: char(10))
+ nativeConditionsMet: hive.mapjoin.optimized.hashtable IS true, hive.vectorized.execution.mapjoin.native.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, One MapJoin Condition IS true, No nullsafe IS true, Small table vectorizes IS true, Optimized Table and Supports Key Types IS true
+ hashTableImplementationType: OPTIMIZED
+ outputColumnNames: _col0, _col1, _col3, _col4
+ input vertices:
+ 1 Map 3
+ Statistics: Num rows: 3 Data size: 549 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: _col0 (type: int), _col1 (type: char(10)), _col3 (type: int), _col4 (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Select Vectorization:
+ className: VectorSelectOperator
+ native: true
+ projectedOutputColumnNums: [0, 1, 3, 1]
+ Statistics: Num rows: 3 Data size: 549 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ key expressions: _col0 (type: int)
+ sort order: +
+ Reduce Sink Vectorization:
+ className: VectorReduceSinkObjectHashOperator
+ native: true
+ nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
+ Statistics: Num rows: 3 Data size: 549 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col1 (type: char(10)), _col2 (type: int), _col3 (type: string)
Execution mode: vectorized, llap
LLAP IO: all inputs
Map Vectorization:
@@ -547,12 +569,12 @@ STAGE PLANS:
allNative: true
usesVectorUDFAdaptor: false
vectorized: true
- Map 2
+ Map 3
Map Operator Tree:
TableScan
alias: b
filterExpr: c2 is not null (type: boolean)
- Statistics: Num rows: 3 Data size: 564 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 276 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
Filter Operator
@@ -561,7 +583,7 @@ STAGE PLANS:
native: true
predicateExpression: SelectColumnIsNotNull(col 1:string)
predicate: c2 is not null (type: boolean)
- Statistics: Num rows: 3 Data size: 564 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 276 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: c1 (type: int), c2 (type: string)
outputColumnNames: _col0, _col1
@@ -569,39 +591,17 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1]
- Statistics: Num rows: 3 Data size: 564 Basic stats: COMPLETE Column stats: NONE
- Map Join Operator
- condition map:
- Inner Join 0 to 1
- keys:
- 0 _col2 (type: string)
- 1 _col1 (type: string)
- Map Join Vectorization:
- className: VectorMapJoinInnerStringOperator
+ Statistics: Num rows: 3 Data size: 276 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ key expressions: _col1 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col1 (type: string)
+ Reduce Sink Vectorization:
+ className: VectorReduceSinkStringOperator
native: true
- nativeConditionsMet: hive.mapjoin.optimized.hashtable IS true, hive.vectorized.execution.mapjoin.native.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, One MapJoin Condition IS true, No nullsafe IS true, Small table vectorizes IS true, Optimized Table and Supports Key Types IS true
- hashTableImplementationType: OPTIMIZED
- outputColumnNames: _col0, _col1, _col3, _col4
- input vertices:
- 0 Map 1
- Statistics: Num rows: 3 Data size: 323 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col0 (type: int), _col1 (type: char(10)), _col3 (type: int), _col4 (type: string)
- outputColumnNames: _col0, _col1, _col2, _col3
- Select Vectorization:
- className: VectorSelectOperator
- native: true
- projectedOutputColumnNums: [3, 4, 0, 1]
- Statistics: Num rows: 3 Data size: 323 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: int)
- sort order: +
- Reduce Sink Vectorization:
- className: VectorReduceSinkObjectHashOperator
- native: true
- nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 3 Data size: 323 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col1 (type: char(10)), _col2 (type: int), _col3 (type: string)
+ nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
+ Statistics: Num rows: 3 Data size: 276 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col0 (type: int)
Execution mode: vectorized, llap
LLAP IO: all inputs
Map Vectorization:
@@ -613,7 +613,7 @@ STAGE PLANS:
allNative: true
usesVectorUDFAdaptor: false
vectorized: true
- Reducer 3
+ Reducer 2
Execution mode: vectorized, llap
Reduce Vectorization:
enabled: true
@@ -629,13 +629,13 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1, 2, 3]
- Statistics: Num rows: 3 Data size: 323 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 549 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 3 Data size: 323 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 549 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/llap/vector_char_varchar_1.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/vector_char_varchar_1.q.out b/ql/src/test/results/clientpositive/llap/vector_char_varchar_1.q.out
index d2db6db..e919a70 100644
--- a/ql/src/test/results/clientpositive/llap/vector_char_varchar_1.q.out
+++ b/ql/src/test/results/clientpositive/llap/vector_char_varchar_1.q.out
@@ -46,7 +46,7 @@ PLAN VECTORIZATION:
STAGE DEPENDENCIES:
Stage-1 is a root stage
Stage-2 depends on stages: Stage-1
- Stage-4 depends on stages: Stage-2, Stage-0
+ Stage-4 depends on stages: Stage-0, Stage-2
Stage-3 depends on stages: Stage-4
Stage-0 depends on stages: Stage-1
@@ -54,52 +54,68 @@ STAGE PLANS:
Stage: Stage-1
Tez
#### A masked pattern was here ####
+ Edges:
+ Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE)
+#### A masked pattern was here ####
Vertices:
Map 1
Map Operator Tree:
TableScan
alias: varchar_table
Statistics: Num rows: 6 Data size: 564 Basic stats: COMPLETE Column stats: NONE
- TableScan Vectorization:
- native: true
- vectorizationSchemaColumns: [0:vs:varchar(10), 1:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
Select Operator
expressions: length(vs) (type: int), reverse(vs) (type: string)
outputColumnNames: _col0, _col1
- Select Vectorization:
- className: VectorSelectOperator
- native: true
- projectedOutputColumnNums: [2, 3]
- selectExpressions: StringLength(col 0:varchar(10)) -> 2:int, VectorUDFAdaptor(reverse(vs)) -> 3:string
Statistics: Num rows: 6 Data size: 564 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
- File Sink Vectorization:
- className: VectorFileSinkOperator
- native: false
Statistics: Num rows: 6 Data size: 564 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.varchar_ctas_1
- Execution mode: vectorized, llap
+ Select Operator
+ expressions: _col0 (type: int), _col1 (type: string)
+ outputColumnNames: col1, col2
+ Statistics: Num rows: 6 Data size: 564 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: compute_stats(col1, 'hll'), compute_stats(col2, 'hll')
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 958 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 958 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>)
+ Execution mode: llap
LLAP IO: no inputs
Map Vectorization:
enabled: true
enabledConditionsMet: hive.vectorized.use.vector.serde.deserialize IS true
- inputFormatFeatureSupport: [DECIMAL_64]
- featureSupportInUse: [DECIMAL_64]
inputFileFormats: org.apache.hadoop.mapred.TextInputFormat
- allNative: false
- usesVectorUDFAdaptor: true
- vectorized: true
- rowBatchContext:
- dataColumnCount: 1
- includeColumns: [0]
- dataColumns: vs:varchar(10)
- partitionColumnCount: 0
- scratchColumnTypeNames: [bigint, string]
+ notVectorizedReason: Aggregation Function expression for GROUPBY operator: UDF compute_stats not supported
+ vectorized: false
+ Reducer 2
+ Execution mode: llap
+ Reduce Vectorization:
+ enabled: true
+ enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true
+ notVectorizedReason: Aggregation Function expression for GROUPBY operator: UDF compute_stats not supported
+ vectorized: false
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 974 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 974 Basic stats: COMPLETE Column stats: NONE
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
Stage: Stage-2
Dependency Collection
@@ -116,6 +132,10 @@ STAGE PLANS:
Stage: Stage-3
Stats Work
Basic Stats Work:
+ Column Stats Desc:
+ Columns: _c0, _c1
+ Column Types: int, string
+ Table: default.varchar_ctas_1
Stage: Stage-0
Move Operator
@@ -199,7 +219,7 @@ PLAN VECTORIZATION:
STAGE DEPENDENCIES:
Stage-1 is a root stage
Stage-2 depends on stages: Stage-1
- Stage-4 depends on stages: Stage-2, Stage-0
+ Stage-4 depends on stages: Stage-0, Stage-2
Stage-3 depends on stages: Stage-4
Stage-0 depends on stages: Stage-1
@@ -207,52 +227,68 @@ STAGE PLANS:
Stage: Stage-1
Tez
#### A masked pattern was here ####
+ Edges:
+ Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE)
+#### A masked pattern was here ####
Vertices:
Map 1
Map Operator Tree:
TableScan
alias: char_table
Statistics: Num rows: 6 Data size: 564 Basic stats: COMPLETE Column stats: NONE
- TableScan Vectorization:
- native: true
- vectorizationSchemaColumns: [0:vs:char(10), 1:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
Select Operator
expressions: length(vs) (type: int), reverse(vs) (type: string)
outputColumnNames: _col0, _col1
- Select Vectorization:
- className: VectorSelectOperator
- native: true
- projectedOutputColumnNums: [2, 3]
- selectExpressions: StringLength(col 0:char(10)) -> 2:int, VectorUDFAdaptor(reverse(vs)) -> 3:string
Statistics: Num rows: 6 Data size: 564 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
- File Sink Vectorization:
- className: VectorFileSinkOperator
- native: false
Statistics: Num rows: 6 Data size: 564 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.char_ctas_1
- Execution mode: vectorized, llap
+ Select Operator
+ expressions: _col0 (type: int), _col1 (type: string)
+ outputColumnNames: col1, col2
+ Statistics: Num rows: 6 Data size: 564 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: compute_stats(col1, 'hll'), compute_stats(col2, 'hll')
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 958 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 958 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>)
+ Execution mode: llap
LLAP IO: no inputs
Map Vectorization:
enabled: true
enabledConditionsMet: hive.vectorized.use.vector.serde.deserialize IS true
- inputFormatFeatureSupport: [DECIMAL_64]
- featureSupportInUse: [DECIMAL_64]
inputFileFormats: org.apache.hadoop.mapred.TextInputFormat
- allNative: false
- usesVectorUDFAdaptor: true
- vectorized: true
- rowBatchContext:
- dataColumnCount: 1
- includeColumns: [0]
- dataColumns: vs:char(10)
- partitionColumnCount: 0
- scratchColumnTypeNames: [bigint, string]
+ notVectorizedReason: Aggregation Function expression for GROUPBY operator: UDF compute_stats not supported
+ vectorized: false
+ Reducer 2
+ Execution mode: llap
+ Reduce Vectorization:
+ enabled: true
+ enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true
+ notVectorizedReason: Aggregation Function expression for GROUPBY operator: UDF compute_stats not supported
+ vectorized: false
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 974 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 974 Basic stats: COMPLETE Column stats: NONE
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
Stage: Stage-2
Dependency Collection
@@ -269,6 +305,10 @@ STAGE PLANS:
Stage: Stage-3
Stats Work
Basic Stats Work:
+ Column Stats Desc:
+ Columns: _c0, _c1
+ Column Types: int, string
+ Table: default.char_ctas_1
Stage: Stage-0
Move Operator
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/llap/vector_count.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/vector_count.q.out b/ql/src/test/results/clientpositive/llap/vector_count.q.out
index a0f301e..2ca934e 100644
--- a/ql/src/test/results/clientpositive/llap/vector_count.q.out
+++ b/ql/src/test/results/clientpositive/llap/vector_count.q.out
@@ -71,22 +71,22 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: abcd
- Statistics: Num rows: 7 Data size: 112 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 7 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: a (type: int), b (type: int), c (type: int), d (type: int)
outputColumnNames: a, b, c, d
- Statistics: Num rows: 7 Data size: 112 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 7 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count(DISTINCT b), count(DISTINCT c), sum(d)
keys: a (type: int), b (type: int), c (type: int)
mode: hash
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
- Statistics: Num rows: 7 Data size: 112 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 108 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int), _col1 (type: int), _col2 (type: int)
sort order: +++
Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 7 Data size: 112 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 108 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col5 (type: bigint)
Execution mode: llap
LLAP IO: all inputs
@@ -109,10 +109,10 @@ STAGE PLANS:
keys: KEY._col0 (type: int)
mode: mergepartial
outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 3 Data size: 48 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 84 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 3 Data size: 48 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 84 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -164,21 +164,21 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: abcd
- Statistics: Num rows: 7 Data size: 112 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 7 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: a (type: int), b (type: int), c (type: int), d (type: int)
outputColumnNames: a, b, c, d
- Statistics: Num rows: 7 Data size: 112 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 7 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count(), count(a), count(b), count(c), count(d), count(DISTINCT a), count(DISTINCT b), count(DISTINCT c), count(DISTINCT d), count(DISTINCT a, b), count(DISTINCT b, c), count(DISTINCT c, d), count(DISTINCT a, d), count(DISTINCT a, c), count(DISTINCT b, d), count(DISTINCT a, b, c), count(DISTINCT b, c, d), count(DISTINCT a, c, d), count(DISTINCT a, b, d), count(DISTINCT a, b, c, d)
keys: a (type: int), b (type: int), c (type: int), d (type: int)
mode: hash
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23
- Statistics: Num rows: 7 Data size: 112 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 528 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int), _col1 (type: int), _col2 (type: int), _col3 (type: int)
sort order: ++++
- Statistics: Num rows: 7 Data size: 112 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 528 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col4 (type: bigint), _col5 (type: bigint), _col6 (type: bigint), _col7 (type: bigint), _col8 (type: bigint)
Execution mode: llap
LLAP IO: all inputs
@@ -200,14 +200,14 @@ STAGE PLANS:
aggregations: count(VALUE._col0), count(VALUE._col1), count(VALUE._col2), count(VALUE._col3), count(VALUE._col4), count(DISTINCT KEY._col0:0._col0), count(DISTINCT KEY._col0:1._col0), count(DISTINCT KEY._col0:2._col0), count(DISTINCT KEY._col0:3._col0), count(DISTINCT KEY._col0:4._col0, KEY._col0:4._col1), count(DISTINCT KEY._col0:5._col0, KEY._col0:5._col1), count(DISTINCT KEY._col0:6._col0, KEY._col0:6._col1), count(DISTINCT KEY._col0:7._col0, KEY._col0:7._col1), count(DISTINCT KEY._col0:8._col0, KEY._col0:8._col1), count(DISTINCT KEY._col0:9._col0, KEY._col0:9._col1), count(DISTINCT KEY._col0:10._col0, KEY._col0:10._col1, KEY._col0:10._col2), count(DISTINCT KEY._col0:11._col0, KEY._col0:11._col1, KEY._col0:11._col2), count(DISTINCT KEY._col0:12._col0, KEY._col0:12._col1, KEY._col0:12._col2), count(DISTINCT KEY._col0:13._col0, KEY._col0:13._col1, KEY._col0:13._col2), count(DISTINCT KEY._col0:14._col0, KEY._col0:14._col1, KEY._col0:14._col2, KEY._col0:14._col3)
mode: mergepartial
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19
- Statistics: Num rows: 1 Data size: 208 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 160 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: bigint), _col0 (type: bigint), _col1 (type: bigint), _col2 (type: bigint), _col3 (type: bigint), _col4 (type: bigint), _col5 (type: bigint), _col6 (type: bigint), _col7 (type: bigint), _col8 (type: bigint), _col9 (type: bigint), _col10 (type: bigint), _col11 (type: bigint), _col12 (type: bigint), _col13 (type: bigint), _col14 (type: bigint), _col15 (type: bigint), _col16 (type: bigint), _col17 (type: bigint), _col18 (type: bigint), _col19 (type: bigint)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20
- Statistics: Num rows: 1 Data size: 208 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 168 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 208 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 168 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -256,7 +256,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: abcd
- Statistics: Num rows: 7 Data size: 112 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 7 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
Select Operator
@@ -266,7 +266,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1, 2, 3]
- Statistics: Num rows: 7 Data size: 112 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 7 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: a (type: int), b (type: int), c (type: int)
sort order: +++
@@ -276,7 +276,7 @@ STAGE PLANS:
native: false
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
nativeConditionsNotMet: No DISTINCT columns IS false
- Statistics: Num rows: 7 Data size: 112 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 7 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: d (type: int)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -302,10 +302,10 @@ STAGE PLANS:
keys: KEY._col0 (type: int)
mode: complete
outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 3 Data size: 48 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 3 Data size: 48 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -357,7 +357,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: abcd
- Statistics: Num rows: 7 Data size: 112 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 7 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
Select Operator
@@ -367,7 +367,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1, 2, 3]
- Statistics: Num rows: 7 Data size: 112 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 7 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: a (type: int), b (type: int), c (type: int), d (type: int)
sort order: ++++
@@ -376,7 +376,7 @@ STAGE PLANS:
native: false
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
nativeConditionsNotMet: No DISTINCT columns IS false
- Statistics: Num rows: 7 Data size: 112 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 7 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized, llap
LLAP IO: all inputs
Map Vectorization:
@@ -400,14 +400,14 @@ STAGE PLANS:
aggregations: count(), count(KEY._col0:0._col0), count(KEY._col0:1._col0), count(KEY._col0:2._col0), count(KEY._col0:3._col0), count(DISTINCT KEY._col0:0._col0), count(DISTINCT KEY._col0:1._col0), count(DISTINCT KEY._col0:2._col0), count(DISTINCT KEY._col0:3._col0), count(DISTINCT KEY._col0:4._col0, KEY._col0:4._col1), count(DISTINCT KEY._col0:5._col0, KEY._col0:5._col1), count(DISTINCT KEY._col0:6._col0, KEY._col0:6._col1), count(DISTINCT KEY._col0:7._col0, KEY._col0:7._col1), count(DISTINCT KEY._col0:8._col0, KEY._col0:8._col1), count(DISTINCT KEY._col0:9._col0, KEY._col0:9._col1), count(DISTINCT KEY._col0:10._col0, KEY._col0:10._col1, KEY._col0:10._col2), count(DISTINCT KEY._col0:11._col0, KEY._col0:11._col1, KEY._col0:11._col2), count(DISTINCT KEY._col0:12._col0, KEY._col0:12._col1, KEY._col0:12._col2), count(DISTINCT KEY._col0:13._col0, KEY._col0:13._col1, KEY._col0:13._col2), count(DISTINCT KEY._col0:14._col0, KEY._col0:14._col1, KEY._col0:14._col2, KEY._col0:1
4._col3)
mode: complete
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19
- Statistics: Num rows: 1 Data size: 176 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 160 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: bigint), _col0 (type: bigint), _col1 (type: bigint), _col2 (type: bigint), _col3 (type: bigint), _col4 (type: bigint), _col5 (type: bigint), _col6 (type: bigint), _col7 (type: bigint), _col8 (type: bigint), _col9 (type: bigint), _col10 (type: bigint), _col11 (type: bigint), _col12 (type: bigint), _col13 (type: bigint), _col14 (type: bigint), _col15 (type: bigint), _col16 (type: bigint), _col17 (type: bigint), _col18 (type: bigint), _col19 (type: bigint)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20
- Statistics: Num rows: 1 Data size: 176 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 168 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 176 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 168 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/llap/vector_decimal_10_0.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/vector_decimal_10_0.q.out b/ql/src/test/results/clientpositive/llap/vector_decimal_10_0.q.out
index 9f940d3..39fd39d 100644
--- a/ql/src/test/results/clientpositive/llap/vector_decimal_10_0.q.out
+++ b/ql/src/test/results/clientpositive/llap/vector_decimal_10_0.q.out
@@ -63,7 +63,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: decimal
- Statistics: Num rows: 2 Data size: 224 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 224 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:dec:decimal(10,0)/DECIMAL_64, 1:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -74,7 +74,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0]
- Statistics: Num rows: 2 Data size: 224 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 224 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: decimal(10,0))
sort order: +
@@ -83,7 +83,7 @@ STAGE PLANS:
keyColumns: 0:decimal(10,0)
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 2 Data size: 224 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 224 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized, llap
LLAP IO: all inputs
Map Vectorization:
@@ -124,13 +124,13 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0]
- Statistics: Num rows: 2 Data size: 224 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 224 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 2 Data size: 224 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 224 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/llap/vector_decimal_6.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/vector_decimal_6.q.out b/ql/src/test/results/clientpositive/llap/vector_decimal_6.q.out
index ef2d74c..ad1757c 100644
--- a/ql/src/test/results/clientpositive/llap/vector_decimal_6.q.out
+++ b/ql/src/test/results/clientpositive/llap/vector_decimal_6.q.out
@@ -652,7 +652,7 @@ PLAN VECTORIZATION:
STAGE DEPENDENCIES:
Stage-1 is a root stage
Stage-2 depends on stages: Stage-1
- Stage-4 depends on stages: Stage-2, Stage-0
+ Stage-4 depends on stages: Stage-0, Stage-2
Stage-3 depends on stages: Stage-4
Stage-0 depends on stages: Stage-1
@@ -710,40 +710,45 @@ STAGE PLANS:
partitionColumnCount: 0
scratchColumnTypeNames: [decimal(11,5)/DECIMAL_64, bigint]
Reducer 2
- Execution mode: vectorized, llap
+ Execution mode: llap
Reduce Vectorization:
enabled: true
enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true
- reduceColumnNullOrder: z
- reduceColumnSortOrder: +
- allNative: false
- usesVectorUDFAdaptor: false
- vectorized: true
- rowBatchContext:
- dataColumnCount: 2
- dataColumns: KEY.reducesinkkey0:int, VALUE._col0:decimal(11,5)
- partitionColumnCount: 0
- scratchColumnTypeNames: []
+ notVectorizedReason: Aggregation Function expression for GROUPBY operator: UDF compute_stats not supported
+ vectorized: false
Reduce Operator Tree:
Select Operator
expressions: VALUE._col0 (type: decimal(11,5)), KEY.reducesinkkey0 (type: int)
outputColumnNames: _col0, _col1
- Select Vectorization:
- className: VectorSelectOperator
- native: true
- projectedOutputColumnNums: [1, 0]
Statistics: Num rows: 27 Data size: 3132 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- File Sink Vectorization:
- className: VectorFileSinkOperator
- native: false
Statistics: Num rows: 27 Data size: 3132 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat
serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde
name: default.DECIMAL_6_3
+ Select Operator
+ expressions: _col0 (type: decimal(11,5)), _col1 (type: int)
+ outputColumnNames: col1, col2
+ Statistics: Num rows: 27 Data size: 3132 Basic stats: COMPLETE Column stats: COMPLETE
+ Group By Operator
+ aggregations: compute_stats(col1, 'hll'), compute_stats(col2, 'hll')
+ mode: complete
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 1056 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: _col0 (type: struct<columntype:string,min:decimal(11,5),max:decimal(11,5),countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col1 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 1056 Basic stats: COMPLETE Column stats: COMPLETE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 1056 Basic stats: COMPLETE Column stats: COMPLETE
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
Stage: Stage-2
Dependency Collection
@@ -760,6 +765,10 @@ STAGE PLANS:
Stage: Stage-3
Stats Work
Basic Stats Work:
+ Column Stats Desc:
+ Columns: k, v
+ Column Types: decimal(11,5), int
+ Table: default.DECIMAL_6_3
Stage: Stage-0
Move Operator
[04/35] hive git commit: HIVE-16957: Support CTAS for auto gather
column stats (Jesus Camacho Rodriguez, reviewed by Ashutosh Chauhan)
Posted by jc...@apache.org.
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/llap/vectorized_dynamic_partition_pruning.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/vectorized_dynamic_partition_pruning.q.out b/ql/src/test/results/clientpositive/llap/vectorized_dynamic_partition_pruning.q.out
index 43ccbe9..21d4e1b 100644
--- a/ql/src/test/results/clientpositive/llap/vectorized_dynamic_partition_pruning.q.out
+++ b/ql/src/test/results/clientpositive/llap/vectorized_dynamic_partition_pruning.q.out
@@ -59,7 +59,7 @@ PLAN VECTORIZATION:
STAGE DEPENDENCIES:
Stage-1 is a root stage
Stage-2 depends on stages: Stage-1
- Stage-4 depends on stages: Stage-2, Stage-0
+ Stage-4 depends on stages: Stage-0, Stage-2
Stage-3 depends on stages: Stage-4
Stage-0 depends on stages: Stage-1
@@ -69,6 +69,7 @@ STAGE PLANS:
#### A masked pattern was here ####
Edges:
Reducer 2 <- Map 1 (SIMPLE_EDGE)
+ Reducer 3 <- Reducer 2 (CUSTOM_SIMPLE_EDGE)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -102,13 +103,12 @@ STAGE PLANS:
usesVectorUDFAdaptor: false
vectorized: true
Reducer 2
- Execution mode: vectorized, llap
+ Execution mode: llap
Reduce Vectorization:
enabled: true
enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true
- allNative: false
- usesVectorUDFAdaptor: false
- vectorized: true
+ notVectorizedReason: Aggregation Function expression for GROUPBY operator: UDF compute_stats not supported
+ vectorized: false
Reduce Operator Tree:
Group By Operator
keys: KEY._col0 (type: string)
@@ -127,6 +127,39 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.srcpart_date_n8
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: string)
+ outputColumnNames: col1, col2
+ Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: COMPLETE
+ Group By Operator
+ aggregations: compute_stats(col1, 'hll'), compute_stats(col2, 'hll')
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col0 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>)
+ Reducer 3
+ Execution mode: llap
+ Reduce Vectorization:
+ enabled: true
+ enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true
+ notVectorizedReason: Aggregation Function expression for GROUPBY operator: UDF compute_stats not supported
+ vectorized: false
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
Stage: Stage-2
Dependency Collection
@@ -143,6 +176,10 @@ STAGE PLANS:
Stage: Stage-3
Stats Work
Basic Stats Work:
+ Column Stats Desc:
+ Columns: ds, date
+ Column Types: string, string
+ Table: default.srcpart_date_n8
Stage: Stage-0
Move Operator
@@ -298,33 +335,33 @@ STAGE PLANS:
TableScan
alias: srcpart_date_n8
filterExpr: ((date = '2008-04-08') and ds is not null) (type: boolean)
- Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 376 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: ((date = '2008-04-08') and ds is not null) (type: boolean)
- Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: ds (type: string)
outputColumnNames: _col0
- Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: string)
outputColumnNames: _col0
- Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
keys: _col0 (type: string)
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: COMPLETE
Dynamic Partitioning Event Operator
Target column: ds (string)
Target Input: srcpart
Partition key expr: ds
- Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: COMPLETE
Target Vertex: Map 1
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -346,15 +383,15 @@ STAGE PLANS:
keys:
0 _col0 (type: string)
1 _col0 (type: string)
- Statistics: Num rows: 2200 Data size: 404800 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1000 Data size: 8000 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count()
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: bigint)
MergeJoin Vectorization:
enabled: false
@@ -372,10 +409,10 @@ STAGE PLANS:
aggregations: count(VALUE._col0)
mode: mergepartial
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -472,19 +509,19 @@ STAGE PLANS:
TableScan
alias: srcpart_date_n8
filterExpr: ((date = '2008-04-08') and ds is not null) (type: boolean)
- Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 376 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: ((date = '2008-04-08') and ds is not null) (type: boolean)
- Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: ds (type: string)
outputColumnNames: _col0
- Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized, llap
LLAP IO: all inputs
Map Vectorization:
@@ -505,15 +542,15 @@ STAGE PLANS:
keys:
0 _col0 (type: string)
1 _col0 (type: string)
- Statistics: Num rows: 2200 Data size: 404800 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1000 Data size: 8000 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count()
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: bigint)
MergeJoin Vectorization:
enabled: false
@@ -531,10 +568,10 @@ STAGE PLANS:
aggregations: count(VALUE._col0)
mode: mergepartial
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -649,33 +686,33 @@ STAGE PLANS:
TableScan
alias: srcpart_date_n8
filterExpr: ((date = '2008-04-08') and ds is not null) (type: boolean)
- Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 376 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: ((date = '2008-04-08') and ds is not null) (type: boolean)
- Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: ds (type: string)
outputColumnNames: _col0
- Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: string)
outputColumnNames: _col0
- Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
keys: _col0 (type: string)
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: COMPLETE
Dynamic Partitioning Event Operator
Target column: ds (string)
Target Input: srcpart
Partition key expr: ds
- Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: COMPLETE
Target Vertex: Map 1
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -693,33 +730,33 @@ STAGE PLANS:
TableScan
alias: srcpart_hour_n2
filterExpr: ((UDFToDouble(hour) = 11.0D) and hr is not null) (type: boolean)
- Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 344 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: ((UDFToDouble(hour) = 11.0D) and hr is not null) (type: boolean)
- Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: hr (type: string)
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 86 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 86 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: string)
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 86 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
keys: _col0 (type: string)
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 86 Basic stats: COMPLETE Column stats: COMPLETE
Dynamic Partitioning Event Operator
Target column: hr (string)
Target Input: srcpart
Partition key expr: hr
- Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 86 Basic stats: COMPLETE Column stats: COMPLETE
Target Vertex: Map 1
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -742,12 +779,12 @@ STAGE PLANS:
0 _col0 (type: string)
1 _col0 (type: string)
outputColumnNames: _col1
- Statistics: Num rows: 2200 Data size: 809600 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1000 Data size: 184000 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col1 (type: string)
sort order: +
Map-reduce partition columns: _col1 (type: string)
- Statistics: Num rows: 2200 Data size: 809600 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1000 Data size: 184000 Basic stats: COMPLETE Column stats: COMPLETE
MergeJoin Vectorization:
enabled: false
enableConditionsNotMet: Vectorizing MergeJoin Supported IS false
@@ -760,15 +797,15 @@ STAGE PLANS:
keys:
0 _col1 (type: string)
1 _col0 (type: string)
- Statistics: Num rows: 2420 Data size: 890560 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1000 Data size: 8000 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count()
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: bigint)
MergeJoin Vectorization:
enabled: false
@@ -786,10 +823,10 @@ STAGE PLANS:
aggregations: count(VALUE._col0)
mode: mergepartial
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -896,19 +933,19 @@ STAGE PLANS:
TableScan
alias: srcpart_date_n8
filterExpr: ((date = '2008-04-08') and ds is not null) (type: boolean)
- Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 376 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: ((date = '2008-04-08') and ds is not null) (type: boolean)
- Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: ds (type: string)
outputColumnNames: _col0
- Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized, llap
LLAP IO: all inputs
Map Vectorization:
@@ -925,19 +962,19 @@ STAGE PLANS:
TableScan
alias: srcpart_hour_n2
filterExpr: ((UDFToDouble(hour) = 11.0D) and hr is not null) (type: boolean)
- Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 344 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: ((UDFToDouble(hour) = 11.0D) and hr is not null) (type: boolean)
- Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: hr (type: string)
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 86 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 86 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized, llap
LLAP IO: all inputs
Map Vectorization:
@@ -959,12 +996,12 @@ STAGE PLANS:
0 _col0 (type: string)
1 _col0 (type: string)
outputColumnNames: _col1
- Statistics: Num rows: 2200 Data size: 809600 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1000 Data size: 184000 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col1 (type: string)
sort order: +
Map-reduce partition columns: _col1 (type: string)
- Statistics: Num rows: 2200 Data size: 809600 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1000 Data size: 184000 Basic stats: COMPLETE Column stats: COMPLETE
MergeJoin Vectorization:
enabled: false
enableConditionsNotMet: Vectorizing MergeJoin Supported IS false
@@ -977,15 +1014,15 @@ STAGE PLANS:
keys:
0 _col1 (type: string)
1 _col0 (type: string)
- Statistics: Num rows: 2420 Data size: 890560 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1000 Data size: 8000 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count()
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: bigint)
MergeJoin Vectorization:
enabled: false
@@ -1003,10 +1040,10 @@ STAGE PLANS:
aggregations: count(VALUE._col0)
mode: mergepartial
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -1117,48 +1154,48 @@ STAGE PLANS:
TableScan
alias: srcpart_date_hour_n2
filterExpr: ((date = '2008-04-08') and (UDFToDouble(hour) = 11.0D) and ds is not null and hr is not null) (type: boolean)
- Statistics: Num rows: 4 Data size: 2944 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4 Data size: 1440 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: ((UDFToDouble(hour) = 11.0D) and (date = '2008-04-08') and ds is not null and hr is not null) (type: boolean)
- Statistics: Num rows: 2 Data size: 1472 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: ds (type: string), hr (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 2 Data size: 1472 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string), _col1 (type: string)
sort order: ++
Map-reduce partition columns: _col0 (type: string), _col1 (type: string)
- Statistics: Num rows: 2 Data size: 1472 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: string)
outputColumnNames: _col0
- Statistics: Num rows: 2 Data size: 1472 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
keys: _col0 (type: string)
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 2 Data size: 1472 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
Dynamic Partitioning Event Operator
Target column: ds (string)
Target Input: srcpart
Partition key expr: ds
- Statistics: Num rows: 2 Data size: 1472 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
Target Vertex: Map 1
Select Operator
expressions: _col1 (type: string)
outputColumnNames: _col0
- Statistics: Num rows: 2 Data size: 1472 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
keys: _col0 (type: string)
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 2 Data size: 1472 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
Dynamic Partitioning Event Operator
Target column: hr (string)
Target Input: srcpart
Partition key expr: hr
- Statistics: Num rows: 2 Data size: 1472 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
Target Vertex: Map 1
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -1180,15 +1217,15 @@ STAGE PLANS:
keys:
0 _col0 (type: string), _col1 (type: string)
1 _col0 (type: string), _col1 (type: string)
- Statistics: Num rows: 2200 Data size: 809600 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1000 Data size: 8000 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count()
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: bigint)
MergeJoin Vectorization:
enabled: false
@@ -1206,10 +1243,10 @@ STAGE PLANS:
aggregations: count(VALUE._col0)
mode: mergepartial
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -1306,19 +1343,19 @@ STAGE PLANS:
TableScan
alias: srcpart_date_hour_n2
filterExpr: ((date = '2008-04-08') and (UDFToDouble(hour) = 11.0D) and ds is not null and hr is not null) (type: boolean)
- Statistics: Num rows: 4 Data size: 2944 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4 Data size: 1440 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: ((UDFToDouble(hour) = 11.0D) and (date = '2008-04-08') and ds is not null and hr is not null) (type: boolean)
- Statistics: Num rows: 2 Data size: 1472 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: ds (type: string), hr (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 2 Data size: 1472 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string), _col1 (type: string)
sort order: ++
Map-reduce partition columns: _col0 (type: string), _col1 (type: string)
- Statistics: Num rows: 2 Data size: 1472 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized, llap
LLAP IO: all inputs
Map Vectorization:
@@ -1339,15 +1376,15 @@ STAGE PLANS:
keys:
0 _col0 (type: string), _col1 (type: string)
1 _col0 (type: string), _col1 (type: string)
- Statistics: Num rows: 2200 Data size: 809600 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1000 Data size: 8000 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count()
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: bigint)
MergeJoin Vectorization:
enabled: false
@@ -1365,10 +1402,10 @@ STAGE PLANS:
aggregations: count(VALUE._col0)
mode: mergepartial
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -1476,33 +1513,33 @@ STAGE PLANS:
TableScan
alias: srcpart_date_n8
filterExpr: ((date = 'I DONT EXIST') and ds is not null) (type: boolean)
- Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 376 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: ((date = 'I DONT EXIST') and ds is not null) (type: boolean)
- Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: ds (type: string)
outputColumnNames: _col0
- Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: string)
outputColumnNames: _col0
- Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
keys: _col0 (type: string)
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: COMPLETE
Dynamic Partitioning Event Operator
Target column: ds (string)
Target Input: srcpart
Partition key expr: ds
- Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: COMPLETE
Target Vertex: Map 1
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -1524,15 +1561,15 @@ STAGE PLANS:
keys:
0 _col0 (type: string)
1 _col0 (type: string)
- Statistics: Num rows: 2200 Data size: 404800 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1000 Data size: 8000 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count()
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: bigint)
MergeJoin Vectorization:
enabled: false
@@ -1550,10 +1587,10 @@ STAGE PLANS:
aggregations: count(VALUE._col0)
mode: mergepartial
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -1650,19 +1687,19 @@ STAGE PLANS:
TableScan
alias: srcpart_date_n8
filterExpr: ((date = 'I DONT EXIST') and ds is not null) (type: boolean)
- Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 376 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: ((date = 'I DONT EXIST') and ds is not null) (type: boolean)
- Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: ds (type: string)
outputColumnNames: _col0
- Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized, llap
LLAP IO: all inputs
Map Vectorization:
@@ -1683,15 +1720,15 @@ STAGE PLANS:
keys:
0 _col0 (type: string)
1 _col0 (type: string)
- Statistics: Num rows: 2200 Data size: 404800 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1000 Data size: 8000 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count()
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: bigint)
MergeJoin Vectorization:
enabled: false
@@ -1709,10 +1746,10 @@ STAGE PLANS:
aggregations: count(VALUE._col0)
mode: mergepartial
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -1818,33 +1855,33 @@ STAGE PLANS:
TableScan
alias: srcpart_double_hour_n2
filterExpr: ((UDFToDouble(hour) = 11.0D) and hr is not null) (type: boolean)
- Statistics: Num rows: 2 Data size: 384 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 188 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: ((UDFToDouble(hour) = 11.0D) and hr is not null) (type: boolean)
- Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: UDFToDouble(UDFToInteger((hr / 2.0D))) (type: double)
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: double)
sort order: +
Map-reduce partition columns: _col0 (type: double)
- Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: double)
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
keys: _col0 (type: double)
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Dynamic Partitioning Event Operator
Target column: hr (string)
Target Input: srcpart
Partition key expr: UDFToDouble(hr)
- Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Target Vertex: Map 1
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -1866,15 +1903,15 @@ STAGE PLANS:
keys:
0 _col0 (type: double)
1 _col0 (type: double)
- Statistics: Num rows: 2200 Data size: 17600 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1000 Data size: 8000 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count()
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: bigint)
MergeJoin Vectorization:
enabled: false
@@ -1892,10 +1929,10 @@ STAGE PLANS:
aggregations: count(VALUE._col0)
mode: mergepartial
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -1992,33 +2029,33 @@ STAGE PLANS:
TableScan
alias: srcpart_double_hour_n2
filterExpr: ((UDFToDouble(hour) = 11.0D) and hr is not null) (type: boolean)
- Statistics: Num rows: 2 Data size: 384 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 188 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: ((UDFToDouble(hour) = 11.0D) and hr is not null) (type: boolean)
- Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: hr (type: double)
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: double)
sort order: +
Map-reduce partition columns: _col0 (type: double)
- Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: double)
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
keys: _col0 (type: double)
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Dynamic Partitioning Event Operator
Target column: hr (string)
Target Input: srcpart
Partition key expr: (UDFToDouble(hr) * 2.0D)
- Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Target Vertex: Map 1
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -2040,15 +2077,15 @@ STAGE PLANS:
keys:
0 _col0 (type: double)
1 _col0 (type: double)
- Statistics: Num rows: 2200 Data size: 17600 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1000 Data size: 8000 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count()
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: bigint)
MergeJoin Vectorization:
enabled: false
@@ -2066,10 +2103,10 @@ STAGE PLANS:
aggregations: count(VALUE._col0)
mode: mergepartial
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -2166,19 +2203,19 @@ STAGE PLANS:
TableScan
alias: srcpart_double_hour_n2
filterExpr: ((UDFToDouble(hour) = 11.0D) and hr is not null) (type: boolean)
- Statistics: Num rows: 2 Data size: 384 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 188 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: ((UDFToDouble(hour) = 11.0D) and hr is not null) (type: boolean)
- Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: UDFToDouble(UDFToInteger((hr / 2.0D))) (type: double)
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: double)
sort order: +
Map-reduce partition columns: _col0 (type: double)
- Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized, llap
LLAP IO: all inputs
Map Vectorization:
@@ -2199,15 +2236,15 @@ STAGE PLANS:
keys:
0 _col0 (type: double)
1 _col0 (type: double)
- Statistics: Num rows: 2200 Data size: 17600 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1000 Data size: 8000 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count()
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: bigint)
MergeJoin Vectorization:
enabled: false
@@ -2225,10 +2262,10 @@ STAGE PLANS:
aggregations: count(VALUE._col0)
mode: mergepartial
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -2325,19 +2362,19 @@ STAGE PLANS:
TableScan
alias: srcpart_double_hour_n2
filterExpr: ((UDFToDouble(hour) = 11.0D) and hr is not null) (type: boolean)
- Statistics: Num rows: 2 Data size: 384 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 188 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: ((UDFToDouble(hour) = 11.0D) and hr is not null) (type: boolean)
- Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: hr (type: double)
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: double)
sort order: +
Map-reduce partition columns: _col0 (type: double)
- Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized, llap
LLAP IO: all inputs
Map Vectorization:
@@ -2358,15 +2395,15 @@ STAGE PLANS:
keys:
0 _col0 (type: double)
1 _col0 (type: double)
- Statistics: Num rows: 2200 Data size: 17600 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1000 Data size: 8000 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count()
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: bigint)
MergeJoin Vectorization:
enabled: false
@@ -2384,10 +2421,10 @@ STAGE PLANS:
aggregations: count(VALUE._col0)
mode: mergepartial
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -2497,33 +2534,33 @@ STAGE PLANS:
TableScan
alias: srcpart_double_hour_n2
filterExpr: ((UDFToDouble(hour) = 11.0D) and hr is not null) (type: boolean)
- Statistics: Num rows: 2 Data size: 384 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 188 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: ((UDFToDouble(hour) = 11.0D) and hr is not null) (type: boolean)
- Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: CAST( hr AS STRING) (type: string)
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: string)
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
keys: _col0 (type: string)
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE
Dynamic Partitioning Event Operator
Target column: hr (string)
Target Input: srcpart
Partition key expr: CAST( (UDFToDouble(hr) * 2.0D) AS STRING)
- Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE
Target Vertex: Map 1
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -2545,15 +2582,15 @@ STAGE PLANS:
keys:
0 _col0 (type: string)
1 _col0 (type: string)
- Statistics: Num rows: 2200 Data size: 404800 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1000 Data size: 8000 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count()
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: bigint)
MergeJoin Vectorization:
enabled: false
@@ -2571,10 +2608,10 @@ STAGE PLANS:
aggregations: count(VALUE._col0)
mode: mergepartial
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -2842,17 +2879,17 @@ STAGE PLANS:
TableScan
alias: srcpart_date_hour_n2
filterExpr: ((date = '2008-04-08') and (UDFToDouble(hour) = 11.0D)) (type: boolean)
- Statistics: Num rows: 4 Data size: 2944 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4 Data size: 1440 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: ((UDFToDouble(hour) = 11.0D) and (date = '2008-04-08')) (type: boolean)
- Statistics: Num rows: 2 Data size: 1472 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: ds (type: string), hr (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 2 Data size: 1472 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
- Statistics: Num rows: 2 Data size: 1472 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: string), _col1 (type: string)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -2876,17 +2913,17 @@ STAGE PLANS:
1
outputColumnNames: _col0, _col1, _col2, _col3
residual filter predicates: {((_col0 = _col2) or (_col1 = _col3))}
- Statistics: Num rows: 4000 Data size: 4420000 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2000 Data size: 1096000 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
- Statistics: Num rows: 4000 Data size: 4420000 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2000 Data size: 1096000 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count()
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: bigint)
MergeJoin Vectorization:
enabled: false
@@ -2904,10 +2941,10 @@ STAGE PLANS:
aggregations: count(VALUE._col0)
mode: mergepartial
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -3004,48 +3041,48 @@ STAGE PLANS:
TableScan
alias: srcpart_date_hour_n2
filterExpr: ((date = '2008-04-08') and (UDFToDouble(hour) = 11.0D) and ds is not null and hr is not null) (type: boolean)
- Statistics: Num rows: 4 Data size: 2944 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4 Data size: 1440 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: ((UDFToDouble(hour) = 11.0D) and (date = '2008-04-08') and ds is not null and hr is not null) (type: boolean)
- Statistics: Num rows: 2 Data size: 1472 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: ds (type: string), hr (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 2 Data size: 1472 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string), _col1 (type: string)
sort order: ++
Map-reduce partition columns: _col0 (type: string), _col1 (type: string)
- Statistics: Num rows: 2 Data size: 1472 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: string)
outputColumnNames: _col0
- Statistics: Num rows: 2 Data size: 1472 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
keys: _col0 (type: string)
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 2 Data size: 1472 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
Dynamic Partitioning Event Operator
Target column: ds (string)
Target Input: srcpart
Partition key expr: ds
- Statistics: Num rows: 2 Data size: 1472 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
Target Vertex: Map 1
Select Operator
expressions: _col1 (type: string)
outputColumnNames: _col0
- Statistics: Num rows: 2 Data size: 1472 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
keys: _col0 (type: string)
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 2 Data size: 1472 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
Dynamic Partitioning Event Operator
Target column: hr (string)
Target Input: srcpart
Partition key expr: hr
- Statistics: Num rows: 2 Data size: 1472 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
Target Vertex: Map 1
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -3067,15 +3104,15 @@ STAGE PLANS:
keys:
0 _col0 (type: string), _col1 (type: string)
1 _col0 (type: string), _col1 (type: string)
- Statistics: Num rows: 2200 Data size: 809600 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1000 Data size: 8000 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count()
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: bigint)
MergeJoin Vectorization:
enabled: false
@@ -3093,10 +3130,10 @@ STAGE PLANS:
aggregations: count(VALUE._col0)
mode: mergepartial
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -3193,33 +3230,33 @@ STAGE PLANS:
TableScan
alias: srcpart_date_n8
filterExpr: ((date = '2008-04-08') and ds is not null) (type: boolean)
- Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 376 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: ((date = '2008-04-08') and ds is not null) (type: boolean)
- Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: ds (type: string)
outputColumnNames: _col0
- Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: string)
outputColumnNames: _col0
- Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
keys: _col0 (type: string)
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: COMPLETE
Dynamic Partitioning Event Operator
Target column: ds (string)
Target Input: srcpart
Partition key expr: ds
- Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: COMPLETE
Target Vertex: Map 1
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -3241,15 +3278,15 @@ STAGE PLANS:
keys:
0 _col0 (type: string)
1 _col0 (type: string)
- Statistics: Num rows: 2200 Data size: 404800 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1000 Data size: 8000 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count()
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: bigint)
MergeJoin Vectorization:
enabled: false
@@ -3267,10 +3304,10 @@ STAGE PLANS:
aggregations: count(VALUE._col0)
mode: mergepartial
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -3322,33 +3359,33 @@ STAGE PLANS:
TableScan
alias: srcpart_date_n8
filterExpr: (date = '2008-04-08') (type: boolean)
- Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 376 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: (date = '2008-04-08') (type: boolean)
- Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: ds (type: string)
outputColumnNames: _col0
- Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: string)
outputColumnNames: _col0
- Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
keys: _col0 (type: string)
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: COMPLETE
Dynamic Partitioning Event Operator
Target column: ds (string)
Target Input: srcpart
Partition key expr: ds
- Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: COMPLETE
Target Vertex: Map 4
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -3395,15 +3432,15 @@ STAGE PLANS:
keys:
0 _col0 (type: string)
1 _col0 (type: string)
- Statistics: Num rows: 2200 Data size: 404800 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1001 Data size: 8008 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count()
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: bigint)
MergeJoin Vectorization:
enabled: false
@@ -3421,10 +3458,10 @@ STAGE PLANS:
aggregations: count(VALUE._col0)
mode: mergepartial
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -3501,33 +3538,33 @@ STAGE PLANS:
TableScan
alias: srcpart_date_n8
filterExpr: (date = '2008-04-08') (type: boolean)
- Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 376 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: (date = '2008-04-08') (type: boolean)
- Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: ds (type: string)
outputColumnNames: _col0
- Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
<TRUNCATED>
[33/35] hive git commit: HIVE-16957: Support CTAS for auto gather
column stats (Jesus Camacho Rodriguez, reviewed by Ashutosh Chauhan)
Posted by jc...@apache.org.
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/ctas_uses_database_location.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/ctas_uses_database_location.q.out b/ql/src/test/results/clientpositive/ctas_uses_database_location.q.out
index 8cf7fe1..ed7dafb 100644
--- a/ql/src/test/results/clientpositive/ctas_uses_database_location.q.out
+++ b/ql/src/test/results/clientpositive/ctas_uses_database_location.q.out
@@ -54,7 +54,32 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: db1.table_db1
- Execution mode: vectorized
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: string)
+ outputColumnNames: col1, col2
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: compute_stats(col1, 'hll'), compute_stats(col2, 'hll')
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>)
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
Stage: Stage-7
Conditional Operator
@@ -83,6 +108,10 @@ STAGE PLANS:
Stage: Stage-2
Stats Work
Basic Stats Work:
+ Column Stats Desc:
+ Columns: key, value
+ Column Types: string, string
+ Table: db1.table_db1
Stage: Stage-3
Map Reduce
@@ -143,7 +172,7 @@ Retention: 0
#### A masked pattern was here ####
Table Type: MANAGED_TABLE
Table Parameters:
- COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"key\":\"true\",\"value\":\"true\"}}
bucketing_version 2
numFiles 1
numRows 500
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/decimal_serde.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/decimal_serde.q.out b/ql/src/test/results/clientpositive/decimal_serde.q.out
index ec90dd3..81a4db8 100644
--- a/ql/src/test/results/clientpositive/decimal_serde.q.out
+++ b/ql/src/test/results/clientpositive/decimal_serde.q.out
@@ -115,7 +115,7 @@ Retention: 0
#### A masked pattern was here ####
Table Type: MANAGED_TABLE
Table Parameters:
- COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"key\":\"true\",\"value\":\"true\"}}
bucketing_version 2
numFiles 1
numRows 38
@@ -168,7 +168,7 @@ Retention: 0
#### A masked pattern was here ####
Table Type: MANAGED_TABLE
Table Parameters:
- COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"key\":\"true\",\"value\":\"true\"}}
bucketing_version 2
numFiles 1
numRows 38
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/druid/druidmini_mv.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/druid/druidmini_mv.q.out b/ql/src/test/results/clientpositive/druid/druidmini_mv.q.out
index 5aef596..0c1ca76 100644
--- a/ql/src/test/results/clientpositive/druid/druidmini_mv.q.out
+++ b/ql/src/test/results/clientpositive/druid/druidmini_mv.q.out
@@ -234,17 +234,17 @@ STAGE PLANS:
TableScan
alias: cmv_basetable_n2
filterExpr: ((a = 3) and (d = 3)) (type: boolean)
- Statistics: Num rows: 6 Data size: 96 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: ((a = 3) and (d = 3)) (type: boolean)
- Statistics: Num rows: 6 Data size: 96 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: c (type: double)
outputColumnNames: _col0
- Statistics: Num rows: 6 Data size: 96 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
- Statistics: Num rows: 6 Data size: 96 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: double)
Execution mode: vectorized, llap
LLAP IO: may be used (ACID table)
@@ -274,14 +274,14 @@ STAGE PLANS:
0
1
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 18 Data size: 522 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 63 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: _col0 (type: int), _col1 (type: double), _col0 (type: int), _col2 (type: double)
outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 18 Data size: 522 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 63 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
- Statistics: Num rows: 18 Data size: 522 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 63 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -367,17 +367,17 @@ STAGE PLANS:
TableScan
alias: cmv_basetable_n2
filterExpr: (a = 3) (type: boolean)
- Statistics: Num rows: 7 Data size: 84 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 7 Data size: 84 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: (a = 3) (type: boolean)
- Statistics: Num rows: 7 Data size: 84 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: c (type: double)
outputColumnNames: _col0
- Statistics: Num rows: 7 Data size: 84 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
- Statistics: Num rows: 7 Data size: 84 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: double)
Execution mode: vectorized, llap
LLAP IO: may be used (ACID table)
@@ -386,17 +386,17 @@ STAGE PLANS:
TableScan
alias: cmv_basetable_n2
filterExpr: ((d = 3) and (a = 3)) (type: boolean)
- Statistics: Num rows: 7 Data size: 112 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 7 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: ((a = 3) and (d = 3)) (type: boolean)
- Statistics: Num rows: 7 Data size: 112 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: c (type: double)
outputColumnNames: _col0
- Statistics: Num rows: 7 Data size: 112 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
- Statistics: Num rows: 7 Data size: 112 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: double)
Execution mode: vectorized, llap
LLAP IO: may be used (ACID table)
@@ -410,14 +410,14 @@ STAGE PLANS:
0
1
outputColumnNames: _col0, _col1
- Statistics: Num rows: 49 Data size: 1421 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: 3 (type: int), _col0 (type: double), 3 (type: int), _col1 (type: double)
outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 49 Data size: 1421 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 49 Data size: 1421 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -495,23 +495,23 @@ STAGE PLANS:
TableScan
alias: cmv_basetable_n2
filterExpr: (a = 3) (type: boolean)
- Statistics: Num rows: 7 Data size: 5124 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 7 Data size: 1652 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: (a = 3) (type: boolean)
- Statistics: Num rows: 7 Data size: 5124 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 472 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: CAST( t AS timestamp with local time zone) (type: timestamp with local time zone), 3 (type: int), b (type: varchar(256)), c (type: double), userid (type: varchar(256))
outputColumnNames: _col0, _col1, _col2, _col3, _col4
- Statistics: Num rows: 7 Data size: 5124 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 472 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: timestamp with local time zone), _col1 (type: int), _col2 (type: varchar(256)), _col3 (type: double), _col4 (type: varchar(256)), floor_hour(CAST( GenericUDFEpochMilli(_col0) AS TIMESTAMP)) (type: timestamp)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, __time_granularity
- Statistics: Num rows: 7 Data size: 5124 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 472 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: __time_granularity (type: timestamp)
sort order: +
Map-reduce partition columns: __time_granularity (type: timestamp)
- Statistics: Num rows: 7 Data size: 5124 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 472 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: timestamp with local time zone), _col1 (type: int), _col2 (type: varchar(256)), _col3 (type: double), _col4 (type: varchar(256))
Execution mode: llap
LLAP IO: may be used (ACID table)
@@ -521,11 +521,11 @@ STAGE PLANS:
Select Operator
expressions: VALUE._col0 (type: timestamp with local time zone), VALUE._col1 (type: int), VALUE._col2 (type: varchar(256)), VALUE._col3 (type: double), VALUE._col4 (type: varchar(256)), KEY.__time_granularity (type: timestamp)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, __time_granularity
- Statistics: Num rows: 7 Data size: 5124 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 472 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
Dp Sort State: PARTITION_SORTED
- Statistics: Num rows: 7 Data size: 5124 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 472 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.hive.druid.io.DruidQueryBasedInputFormat
output format: org.apache.hadoop.hive.druid.io.DruidOutputFormat
@@ -597,17 +597,17 @@ STAGE PLANS:
TableScan
alias: cmv_basetable_n2
filterExpr: ((a = 3) and (d = 3)) (type: boolean)
- Statistics: Num rows: 7 Data size: 112 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 7 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: ((a = 3) and (d = 3)) (type: boolean)
- Statistics: Num rows: 7 Data size: 112 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: c (type: double)
outputColumnNames: _col0
- Statistics: Num rows: 7 Data size: 112 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
- Statistics: Num rows: 7 Data size: 112 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: double)
Execution mode: vectorized, llap
LLAP IO: may be used (ACID table)
@@ -637,14 +637,14 @@ STAGE PLANS:
0
1
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 21 Data size: 609 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 63 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: _col0 (type: int), _col1 (type: double), _col0 (type: int), _col2 (type: double)
outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 21 Data size: 609 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 63 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
- Statistics: Num rows: 21 Data size: 609 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 63 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/explain_ddl.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/explain_ddl.q.out b/ql/src/test/results/clientpositive/explain_ddl.q.out
index 3846b2c..05a8fce 100644
--- a/ql/src/test/results/clientpositive/explain_ddl.q.out
+++ b/ql/src/test/results/clientpositive/explain_ddl.q.out
@@ -82,7 +82,32 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.M1
- Execution mode: vectorized
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: string)
+ outputColumnNames: col1, col2
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: compute_stats(col1, 'hll'), compute_stats(col2, 'hll')
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>)
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
Stage: Stage-7
Conditional Operator
@@ -111,6 +136,10 @@ STAGE PLANS:
Stage: Stage-2
Stats Work
Basic Stats Work:
+ Column Stats Desc:
+ Columns: key, value
+ Column Types: string, string
+ Table: default.M1
Stage: Stage-3
Map Reduce
@@ -182,7 +211,32 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.M1
- Execution mode: vectorized
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: string)
+ outputColumnNames: col1, col2
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: compute_stats(col1, 'hll'), compute_stats(col2, 'hll')
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>)
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
Stage: Stage-7
Conditional Operator
@@ -211,6 +265,10 @@ STAGE PLANS:
Stage: Stage-2
Stats Work
Basic Stats Work:
+ Column Stats Desc:
+ Columns: key, value
+ Column Types: string, string
+ Table: default.M1
Stage: Stage-3
Map Reduce
@@ -286,7 +344,32 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.M1
- Execution mode: vectorized
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: string)
+ outputColumnNames: col1, col2
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: compute_stats(col1, 'hll'), compute_stats(col2, 'hll')
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>)
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
Stage: Stage-7
Conditional Operator
@@ -315,6 +398,10 @@ STAGE PLANS:
Stage: Stage-2
Stats Work
Basic Stats Work:
+ Column Stats Desc:
+ Columns: key, value
+ Column Types: string, string
+ Table: default.M1
Stage: Stage-3
Map Reduce
@@ -386,7 +473,32 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.V1_n0
- Execution mode: vectorized
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: string)
+ outputColumnNames: col1, col2
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: compute_stats(col1, 'hll'), compute_stats(col2, 'hll')
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>)
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
Stage: Stage-7
Conditional Operator
@@ -415,6 +527,10 @@ STAGE PLANS:
Stage: Stage-2
Stats Work
Basic Stats Work:
+ Column Stats Desc:
+ Columns: key, value
+ Column Types: string, string
+ Table: default.V1_n0
Stage: Stage-3
Map Reduce
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/groupby_duplicate_key.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/groupby_duplicate_key.q.out b/ql/src/test/results/clientpositive/groupby_duplicate_key.q.out
index 3fe95af..59692e8 100644
--- a/ql/src/test/results/clientpositive/groupby_duplicate_key.q.out
+++ b/ql/src/test/results/clientpositive/groupby_duplicate_key.q.out
@@ -94,8 +94,9 @@ POSTHOOK: Output: default@dummy_n6
STAGE DEPENDENCIES:
Stage-1 is a root stage
Stage-0 depends on stages: Stage-1
- Stage-3 depends on stages: Stage-0
- Stage-2 depends on stages: Stage-3
+ Stage-4 depends on stages: Stage-0, Stage-3
+ Stage-2 depends on stages: Stage-4
+ Stage-3 depends on stages: Stage-1
STAGE PLANS:
Stage: Stage-1
@@ -138,6 +139,21 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.dummy_n6
+ Select Operator
+ expressions: _col0 (type: string), 'X' (type: string), 'X' (type: string)
+ outputColumnNames: col1, col2, col3
+ Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: compute_stats(col1, 'hll'), compute_stats(col2, 'hll'), compute_stats(col3, 'hll')
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
Stage: Stage-0
Move Operator
@@ -145,7 +161,7 @@ STAGE PLANS:
hdfs directory: true
#### A masked pattern was here ####
- Stage: Stage-3
+ Stage: Stage-4
Create Table Operator:
Create Table
columns: key string, dummy1 string, dummy2 string
@@ -157,6 +173,33 @@ STAGE PLANS:
Stage: Stage-2
Stats Work
Basic Stats Work:
+ Column Stats Desc:
+ Columns: key, dummy1, dummy2
+ Column Types: string, string, string
+ Table: default.dummy_n6
+
+ Stage: Stage-3
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col2 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>)
+ Execution mode: vectorized
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
PREHOOK: query: create table dummy_n6 as
select distinct key, "X" as dummy1, "X" as dummy2 from src tablesample (10 rows)
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/input1_limit.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/input1_limit.q.out b/ql/src/test/results/clientpositive/input1_limit.q.out
index ff88dec..90499f8 100644
--- a/ql/src/test/results/clientpositive/input1_limit.q.out
+++ b/ql/src/test/results/clientpositive/input1_limit.q.out
@@ -60,6 +60,7 @@ STAGE PLANS:
Reduce Output Operator
sort order:
Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE
+ TopN Hash Memory Usage: 0.1
value expressions: _col0 (type: string), _col1 (type: string)
Filter Operator
predicate: (key < 100) (type: boolean)
@@ -170,6 +171,7 @@ STAGE PLANS:
Reduce Output Operator
sort order:
Statistics: Num rows: 5 Data size: 50 Basic stats: COMPLETE Column stats: NONE
+ TopN Hash Memory Usage: 0.1
value expressions: _col0 (type: string), _col1 (type: string)
Execution mode: vectorized
Reduce Operator Tree:
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/input3_limit.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/input3_limit.q.out b/ql/src/test/results/clientpositive/input3_limit.q.out
index e0ffe19..92bec61 100644
--- a/ql/src/test/results/clientpositive/input3_limit.q.out
+++ b/ql/src/test/results/clientpositive/input3_limit.q.out
@@ -84,6 +84,7 @@ STAGE PLANS:
key expressions: _col0 (type: string), _col1 (type: string)
sort order: ++
Statistics: Num rows: 1 Data size: 116030 Basic stats: COMPLETE Column stats: NONE
+ TopN Hash Memory Usage: 0.1
Execution mode: vectorized
Reduce Operator Tree:
Select Operator
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/input_part10.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/input_part10.q.out b/ql/src/test/results/clientpositive/input_part10.q.out
index 33d4485..09ebdd1 100644
--- a/ql/src/test/results/clientpositive/input_part10.q.out
+++ b/ql/src/test/results/clientpositive/input_part10.q.out
@@ -53,6 +53,7 @@ STAGE PLANS:
Reduce Output Operator
sort order:
Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
+ TopN Hash Memory Usage: 0.1
value expressions: _col0 (type: int), _col1 (type: int)
Execution mode: vectorized
Reduce Operator Tree:
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/insert2_overwrite_partitions.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/insert2_overwrite_partitions.q.out b/ql/src/test/results/clientpositive/insert2_overwrite_partitions.q.out
index 14c0e2e..319c23f 100644
--- a/ql/src/test/results/clientpositive/insert2_overwrite_partitions.q.out
+++ b/ql/src/test/results/clientpositive/insert2_overwrite_partitions.q.out
@@ -77,6 +77,7 @@ STAGE PLANS:
key expressions: _col0 (type: string), _col1 (type: string)
sort order: --
Statistics: Num rows: 124 Data size: 60280 Basic stats: PARTIAL Column stats: NONE
+ TopN Hash Memory Usage: 0.1
Execution mode: vectorized
Reduce Operator Tree:
Select Operator
@@ -224,6 +225,7 @@ STAGE PLANS:
key expressions: _col0 (type: string), _col1 (type: string)
sort order: --
Statistics: Num rows: 124 Data size: 60280 Basic stats: PARTIAL Column stats: NONE
+ TopN Hash Memory Usage: 0.1
Execution mode: vectorized
Reduce Operator Tree:
Select Operator
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/insert_into1.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/insert_into1.q.out b/ql/src/test/results/clientpositive/insert_into1.q.out
index b700e0b..95a87ae 100644
--- a/ql/src/test/results/clientpositive/insert_into1.q.out
+++ b/ql/src/test/results/clientpositive/insert_into1.q.out
@@ -39,6 +39,7 @@ STAGE PLANS:
key expressions: _col0 (type: string)
sort order: +
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ TopN Hash Memory Usage: 0.1
value expressions: _col1 (type: string)
Execution mode: vectorized
Reduce Operator Tree:
@@ -199,6 +200,7 @@ STAGE PLANS:
key expressions: _col0 (type: string)
sort order: +
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ TopN Hash Memory Usage: 0.1
value expressions: _col1 (type: string)
Execution mode: vectorized
Reduce Operator Tree:
@@ -359,6 +361,7 @@ STAGE PLANS:
key expressions: _col0 (type: string)
sort order: +
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ TopN Hash Memory Usage: 0.1
value expressions: _col1 (type: string)
Execution mode: vectorized
Reduce Operator Tree:
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/insert_into2.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/insert_into2.q.out b/ql/src/test/results/clientpositive/insert_into2.q.out
index 65a0ea7..91c4785 100644
--- a/ql/src/test/results/clientpositive/insert_into2.q.out
+++ b/ql/src/test/results/clientpositive/insert_into2.q.out
@@ -43,6 +43,7 @@ STAGE PLANS:
key expressions: _col0 (type: string)
sort order: +
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ TopN Hash Memory Usage: 0.1
value expressions: _col1 (type: string)
Execution mode: vectorized
Reduce Operator Tree:
@@ -256,6 +257,7 @@ STAGE PLANS:
key expressions: _col0 (type: string)
sort order: +
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ TopN Hash Memory Usage: 0.1
value expressions: _col1 (type: string)
Execution mode: vectorized
Reduce Operator Tree:
@@ -434,6 +436,7 @@ STAGE PLANS:
key expressions: _col0 (type: string)
sort order: +
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ TopN Hash Memory Usage: 0.1
value expressions: _col1 (type: string)
Execution mode: vectorized
Reduce Operator Tree:
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/insert_into3.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/insert_into3.q.out b/ql/src/test/results/clientpositive/insert_into3.q.out
index f5c43bb..ee6e196 100644
--- a/ql/src/test/results/clientpositive/insert_into3.q.out
+++ b/ql/src/test/results/clientpositive/insert_into3.q.out
@@ -59,6 +59,7 @@ STAGE PLANS:
key expressions: _col0 (type: string), _col1 (type: string)
sort order: ++
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ TopN Hash Memory Usage: 0.1
Select Operator
expressions: key (type: string), value (type: string)
outputColumnNames: _col0, _col1
@@ -163,6 +164,7 @@ STAGE PLANS:
key expressions: _col0 (type: string), _col1 (type: string)
sort order: ++
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ TopN Hash Memory Usage: 0.1
Execution mode: vectorized
Reduce Operator Tree:
Select Operator
@@ -314,6 +316,7 @@ STAGE PLANS:
Reduce Output Operator
sort order:
Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE
+ TopN Hash Memory Usage: 0.1
value expressions: _col0 (type: string), _col1 (type: string)
Select Operator
expressions: key (type: string), value (type: string)
@@ -421,6 +424,7 @@ STAGE PLANS:
Reduce Output Operator
sort order:
Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE
+ TopN Hash Memory Usage: 0.1
value expressions: _col0 (type: string), _col1 (type: string)
Execution mode: vectorized
Reduce Operator Tree:
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/insert_into4.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/insert_into4.q.out b/ql/src/test/results/clientpositive/insert_into4.q.out
index 463aced..6dfc88a 100644
--- a/ql/src/test/results/clientpositive/insert_into4.q.out
+++ b/ql/src/test/results/clientpositive/insert_into4.q.out
@@ -53,6 +53,7 @@ STAGE PLANS:
Reduce Output Operator
sort order:
Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE
+ TopN Hash Memory Usage: 0.1
value expressions: _col0 (type: string), _col1 (type: string)
Execution mode: vectorized
Reduce Operator Tree:
@@ -186,6 +187,7 @@ STAGE PLANS:
Reduce Output Operator
sort order:
Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE
+ TopN Hash Memory Usage: 0.1
value expressions: _col0 (type: string), _col1 (type: string)
Execution mode: vectorized
Reduce Operator Tree:
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/insert_into5.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/insert_into5.q.out b/ql/src/test/results/clientpositive/insert_into5.q.out
index 5c964cf..08eccf1 100644
--- a/ql/src/test/results/clientpositive/insert_into5.q.out
+++ b/ql/src/test/results/clientpositive/insert_into5.q.out
@@ -53,6 +53,7 @@ STAGE PLANS:
Reduce Output Operator
sort order:
Statistics: Num rows: 10 Data size: 910 Basic stats: COMPLETE Column stats: COMPLETE
+ TopN Hash Memory Usage: 0.1
value expressions: _col0 (type: int), _col1 (type: string)
Execution mode: vectorized
Reduce Operator Tree:
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/insert_into6.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/insert_into6.q.out b/ql/src/test/results/clientpositive/insert_into6.q.out
index 035a29f..6d90dd1 100644
--- a/ql/src/test/results/clientpositive/insert_into6.q.out
+++ b/ql/src/test/results/clientpositive/insert_into6.q.out
@@ -55,6 +55,7 @@ STAGE PLANS:
Reduce Output Operator
sort order:
Statistics: Num rows: 150 Data size: 1500 Basic stats: COMPLETE Column stats: NONE
+ TopN Hash Memory Usage: 0.1
value expressions: _col0 (type: string), _col1 (type: string)
Execution mode: vectorized
Reduce Operator Tree:
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/join42.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/join42.q.out b/ql/src/test/results/clientpositive/join42.q.out
index f2985fe..f2c62c0 100644
--- a/ql/src/test/results/clientpositive/join42.q.out
+++ b/ql/src/test/results/clientpositive/join42.q.out
@@ -90,7 +90,8 @@ POSTHOOK: Output: default@acct
POSTHOOK: Lineage: acct.acc_n EXPRESSION []
POSTHOOK: Lineage: acct.aid SCRIPT []
POSTHOOK: Lineage: acct.brn EXPRESSION []
-Warning: Shuffle Join JOIN[28][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Stage-1:MAPRED' is a cross product
+Warning: Shuffle Join JOIN[30][tables = [$hdt$_0, $hdt$_1, $hdt$_2, $hdt$_3]] in Stage 'Stage-3:MAPRED' is a cross product
+Warning: Shuffle Join JOIN[20][tables = [$hdt$_4, $hdt$_5]] in Stage 'Stage-8:MAPRED' is a cross product
PREHOOK: query: explain select
acct.ACC_N,
acct.brn
@@ -133,113 +134,17 @@ POSTHOOK: Input: default@pi
#### A masked pattern was here ####
STAGE DEPENDENCIES:
Stage-1 is a root stage
- Stage-2 depends on stages: Stage-1, Stage-6
- Stage-5 is a root stage
- Stage-6 depends on stages: Stage-5
- Stage-0 depends on stages: Stage-2
+ Stage-2 depends on stages: Stage-1
+ Stage-3 depends on stages: Stage-2
+ Stage-4 depends on stages: Stage-3, Stage-8
+ Stage-8 is a root stage
+ Stage-0 depends on stages: Stage-4
STAGE PLANS:
Stage: Stage-1
Map Reduce
Map Operator Tree:
TableScan
- alias: acct
- filterExpr: (aid is not null and brn is not null) (type: boolean)
- Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- predicate: (aid is not null and brn is not null) (type: boolean)
- Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: aid (type: int), acc_n (type: int), brn (type: int)
- outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- sort order:
- Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col0 (type: int), _col1 (type: int), _col2 (type: int)
- TableScan
- alias: l
- filterExpr: (id = 4436) (type: boolean)
- Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- predicate: (id = 4436) (type: boolean)
- Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- sort order:
- Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE
- TableScan
- alias: fr
- filterExpr: (loan_id = 4436) (type: boolean)
- Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- predicate: (loan_id = 4436) (type: boolean)
- Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- sort order:
- Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE
- Reduce Operator Tree:
- Join Operator
- condition map:
- Inner Join 0 to 1
- Inner Join 0 to 2
- keys:
- 0
- 1
- 2
- outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 3 Data size: 58 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
-
- Stage: Stage-2
- Map Reduce
- Map Operator Tree:
- TableScan
- Reduce Output Operator
- key expressions: _col0 (type: int)
- sort order: +
- Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 3 Data size: 58 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col1 (type: int), _col2 (type: int)
- TableScan
- Reduce Output Operator
- key expressions: _col2 (type: int)
- sort order: +
- Map-reduce partition columns: _col2 (type: int)
- Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE
- Reduce Operator Tree:
- Join Operator
- condition map:
- Inner Join 0 to 1
- keys:
- 0 _col0 (type: int)
- 1 _col2 (type: int)
- outputColumnNames: _col1, _col2
- Statistics: Num rows: 3 Data size: 63 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col1 (type: int), _col2 (type: int)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 3 Data size: 63 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 3 Data size: 63 Basic stats: COMPLETE Column stats: NONE
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
- Stage: Stage-5
- Map Reduce
- Map Operator Tree:
- TableScan
alias: la_n11
filterExpr: ((loan_id = 4436) and aid is not null and pi_id is not null) (type: boolean)
Statistics: Num rows: 1 Data size: 14 Basic stats: COMPLETE Column stats: NONE
@@ -288,7 +193,7 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
- Stage: Stage-6
+ Stage: Stage-2
Map Reduce
Map Operator Tree:
TableScan
@@ -330,13 +235,133 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+ Stage: Stage-3
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col2 (type: int)
+ TableScan
+ alias: fr
+ filterExpr: (loan_id = 4436) (type: boolean)
+ Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: (loan_id = 4436) (type: boolean)
+ Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0
+ 1
+ outputColumnNames: _col2
+ Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+
+ Stage: Stage-4
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ Reduce Output Operator
+ key expressions: _col2 (type: int)
+ sort order: +
+ Map-reduce partition columns: _col2 (type: int)
+ Statistics: Num rows: 1 Data size: 21 Basic stats: COMPLETE Column stats: NONE
+ TableScan
+ Reduce Output Operator
+ key expressions: _col0 (type: int)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: int)
+ Statistics: Num rows: 3 Data size: 46 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col1 (type: int), _col2 (type: int)
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col2 (type: int)
+ 1 _col0 (type: int)
+ outputColumnNames: _col6, _col7
+ Statistics: Num rows: 3 Data size: 50 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col6 (type: int), _col7 (type: int)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 3 Data size: 50 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 3 Data size: 50 Basic stats: COMPLETE Column stats: NONE
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ Stage: Stage-8
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ alias: acct
+ filterExpr: (aid is not null and brn is not null) (type: boolean)
+ Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: (aid is not null and brn is not null) (type: boolean)
+ Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: aid (type: int), acc_n (type: int), brn (type: int)
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: int), _col1 (type: int), _col2 (type: int)
+ TableScan
+ alias: l
+ filterExpr: (id = 4436) (type: boolean)
+ Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: (id = 4436) (type: boolean)
+ Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0
+ 1
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 3 Data size: 46 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+
Stage: Stage-0
Fetch Operator
limit: -1
Processor Tree:
ListSink
-Warning: Shuffle Join JOIN[28][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Stage-1:MAPRED' is a cross product
+Warning: Shuffle Join JOIN[30][tables = [$hdt$_0, $hdt$_1, $hdt$_2, $hdt$_3]] in Stage 'Stage-3:MAPRED' is a cross product
+Warning: Shuffle Join JOIN[20][tables = [$hdt$_4, $hdt$_5]] in Stage 'Stage-8:MAPRED' is a cross product
PREHOOK: query: select
acct.ACC_N,
acct.brn
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/join_filters_overlap.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/join_filters_overlap.q.out b/ql/src/test/results/clientpositive/join_filters_overlap.q.out
index 847b45d..331123e 100644
--- a/ql/src/test/results/clientpositive/join_filters_overlap.q.out
+++ b/ql/src/test/results/clientpositive/join_filters_overlap.q.out
@@ -96,7 +96,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
bucketing_version 2
column.name.delimiter ,
@@ -118,7 +118,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
bucketing_version 2
column.name.delimiter ,
@@ -299,7 +299,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
bucketing_version 2
column.name.delimiter ,
@@ -321,7 +321,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
bucketing_version 2
column.name.delimiter ,
@@ -502,7 +502,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
bucketing_version 2
column.name.delimiter ,
@@ -524,7 +524,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
bucketing_version 2
column.name.delimiter ,
@@ -722,7 +722,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
bucketing_version 2
column.name.delimiter ,
@@ -744,7 +744,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
bucketing_version 2
column.name.delimiter ,
@@ -942,7 +942,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
bucketing_version 2
column.name.delimiter ,
@@ -964,7 +964,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
bucketing_version 2
column.name.delimiter ,
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/limit_pushdown_negative.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/limit_pushdown_negative.q.out b/ql/src/test/results/clientpositive/limit_pushdown_negative.q.out
index 0e2cff5..e838908 100644
--- a/ql/src/test/results/clientpositive/limit_pushdown_negative.q.out
+++ b/ql/src/test/results/clientpositive/limit_pushdown_negative.q.out
@@ -379,6 +379,7 @@ STAGE PLANS:
Reduce Output Operator
sort order:
Statistics: Num rows: 20 Data size: 200 Basic stats: COMPLETE Column stats: NONE
+ TopN Hash Memory Usage: 0.3
value expressions: _col0 (type: string), _col1 (type: double)
Execution mode: vectorized
Reduce Operator Tree:
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/llap/convert_decimal64_to_decimal.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/convert_decimal64_to_decimal.q.out b/ql/src/test/results/clientpositive/llap/convert_decimal64_to_decimal.q.out
index abed87d..0bdc5d3 100644
--- a/ql/src/test/results/clientpositive/llap/convert_decimal64_to_decimal.q.out
+++ b/ql/src/test/results/clientpositive/llap/convert_decimal64_to_decimal.q.out
@@ -161,7 +161,7 @@ STAGE PLANS:
TableScan
alias: t1
filterExpr: decimal0801_col_4 is not null (type: boolean)
- Statistics: Num rows: 1080 Data size: 115024 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1080 Data size: 109984 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:float_col_1:float, 1:varchar0037_col_2:varchar(37), 2:decimal2912_col_3:decimal(29,12), 3:decimal0801_col_4:decimal(8,1)/DECIMAL_64, 4:timestamp_col_5:timestamp, 5:boolean_col_6:boolean, 6:string_col_7:string, 7:tinyint_col_8:tinyint, 8:boolean_col_9:boolean, 9:decimal1614_col_10:decimal(16,14)/DECIMAL_64, 10:boolean_col_11:boolean, 11:float_col_12:float, 12:char0116_col_13:char(116), 13:boolean_col_14:boolean, 14:string_col_15:string, 15:double_col_16:double, 16:string_col_17:string, 17:bigint_col_18:bigint, 18:int_col_19:int, 19:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -171,7 +171,7 @@ STAGE PLANS:
native: true
predicateExpression: SelectColumnIsNotNull(col 3:decimal(8,1)/DECIMAL_64)
predicate: decimal0801_col_4 is not null (type: boolean)
- Statistics: Num rows: 1026 Data size: 109272 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 981 Data size: 99904 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: decimal0801_col_4 (type: decimal(8,1))
outputColumnNames: _col0
@@ -179,7 +179,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [3]
- Statistics: Num rows: 1026 Data size: 109272 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 981 Data size: 99904 Basic stats: COMPLETE Column stats: COMPLETE
Map Join Operator
condition map:
Inner Join 0 to 1
@@ -196,7 +196,7 @@ STAGE PLANS:
outputColumnNames: _col1
input vertices:
1 Map 3
- Statistics: Num rows: 1128 Data size: 120199 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 894 Data size: 3224 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count(_col1)
Group By Vectorization:
@@ -208,7 +208,7 @@ STAGE PLANS:
projectedOutputColumnNums: [0]
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
Reduce Sink Vectorization:
@@ -216,7 +216,7 @@ STAGE PLANS:
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
valueColumns: 0:bigint
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: bigint)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -240,7 +240,7 @@ STAGE PLANS:
TableScan
alias: t2
filterExpr: decimal0402_col_20 is not null (type: boolean)
- Statistics: Num rows: 1000 Data size: 110316 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1000 Data size: 103844 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:tinyint_col_1:tinyint, 1:float_col_2:float, 2:bigint_col_3:bigint, 3:boolean_col_4:boolean, 4:decimal0202_col_5:decimal(2,2)/DECIMAL_64, 5:decimal1612_col_6:decimal(16,12)/DECIMAL_64, 6:double_col_7:double, 7:char0205_col_8:char(205), 8:bigint_col_9:bigint, 9:decimal1202_col_10:decimal(12,2)/DECIMAL_64, 10:boolean_col_11:boolean, 11:double_col_12:double, 12:decimal2208_col_13:decimal(22,8), 13:decimal3722_col_14:decimal(37,22), 14:smallint_col_15:smallint, 15:decimal2824_col_16:decimal(28,24), 16:boolean_col_17:boolean, 17:float_col_18:float, 18:timestamp_col_19:timestamp, 19:decimal0402_col_20:decimal(4,2)/DECIMAL_64, 20:char0208_col_21:char(208), 21:char0077_col_22:char(77), 22:decimal2915_col_23:decimal(29,15), 23:char0234_col_24:char(234), 24:timestamp_col_25:timestamp, 25:tinyint_col_26:tinyint, 26:decimal3635_col_27:decimal(36,35), 27:boolean_col_28:boolean, 28:float_col_29:float, 29:smallint_col_30:smallint, 30:varchar0200_
col_31:varchar(200), 31:boolean_col_32:boolean, 32:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -250,7 +250,7 @@ STAGE PLANS:
native: true
predicateExpression: SelectColumnIsNotNull(col 19:decimal(4,2)/DECIMAL_64)
predicate: decimal0402_col_20 is not null (type: boolean)
- Statistics: Num rows: 950 Data size: 104800 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 894 Data size: 92824 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: smallint_col_15 (type: smallint), decimal0402_col_20 (type: decimal(4,2))
outputColumnNames: _col0, _col1
@@ -258,7 +258,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [14, 19]
- Statistics: Num rows: 950 Data size: 104800 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 894 Data size: 92824 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col1 (type: decimal(9,2))
sort order: +
@@ -269,7 +269,7 @@ STAGE PLANS:
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
valueColumns: 14:smallint
- Statistics: Num rows: 950 Data size: 104800 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 894 Data size: 92824 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: smallint)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -315,13 +315,13 @@ STAGE PLANS:
projectedOutputColumnNums: [0]
mode: mergepartial
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -376,7 +376,7 @@ STAGE PLANS:
TableScan
alias: t1
filterExpr: decimal0801_col_4 is not null (type: boolean)
- Statistics: Num rows: 1080 Data size: 115024 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1080 Data size: 109984 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:float_col_1:float, 1:varchar0037_col_2:varchar(37), 2:decimal2912_col_3:decimal(29,12), 3:decimal0801_col_4:decimal(8,1), 4:timestamp_col_5:timestamp, 5:boolean_col_6:boolean, 6:string_col_7:string, 7:tinyint_col_8:tinyint, 8:boolean_col_9:boolean, 9:decimal1614_col_10:decimal(16,14), 10:boolean_col_11:boolean, 11:float_col_12:float, 12:char0116_col_13:char(116), 13:boolean_col_14:boolean, 14:string_col_15:string, 15:double_col_16:double, 16:string_col_17:string, 17:bigint_col_18:bigint, 18:int_col_19:int, 19:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -386,7 +386,7 @@ STAGE PLANS:
native: true
predicateExpression: SelectColumnIsNotNull(col 3:decimal(8,1))
predicate: decimal0801_col_4 is not null (type: boolean)
- Statistics: Num rows: 1026 Data size: 109272 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 981 Data size: 99904 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: decimal0801_col_4 (type: decimal(8,1))
outputColumnNames: _col0
@@ -394,7 +394,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [3]
- Statistics: Num rows: 1026 Data size: 109272 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 981 Data size: 99904 Basic stats: COMPLETE Column stats: COMPLETE
Map Join Operator
condition map:
Inner Join 0 to 1
@@ -411,7 +411,7 @@ STAGE PLANS:
outputColumnNames: _col1
input vertices:
1 Map 3
- Statistics: Num rows: 1128 Data size: 120199 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 894 Data size: 3224 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count(_col1)
Group By Vectorization:
@@ -423,7 +423,7 @@ STAGE PLANS:
projectedOutputColumnNums: [0]
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
Reduce Sink Vectorization:
@@ -431,7 +431,7 @@ STAGE PLANS:
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
valueColumns: 0:bigint
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: bigint)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -456,7 +456,7 @@ STAGE PLANS:
TableScan
alias: t2
filterExpr: decimal0402_col_20 is not null (type: boolean)
- Statistics: Num rows: 1000 Data size: 110316 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1000 Data size: 103844 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:tinyint_col_1:tinyint, 1:float_col_2:float, 2:bigint_col_3:bigint, 3:boolean_col_4:boolean, 4:decimal0202_col_5:decimal(2,2), 5:decimal1612_col_6:decimal(16,12), 6:double_col_7:double, 7:char0205_col_8:char(205), 8:bigint_col_9:bigint, 9:decimal1202_col_10:decimal(12,2), 10:boolean_col_11:boolean, 11:double_col_12:double, 12:decimal2208_col_13:decimal(22,8), 13:decimal3722_col_14:decimal(37,22), 14:smallint_col_15:smallint, 15:decimal2824_col_16:decimal(28,24), 16:boolean_col_17:boolean, 17:float_col_18:float, 18:timestamp_col_19:timestamp, 19:decimal0402_col_20:decimal(4,2), 20:char0208_col_21:char(208), 21:char0077_col_22:char(77), 22:decimal2915_col_23:decimal(29,15), 23:char0234_col_24:char(234), 24:timestamp_col_25:timestamp, 25:tinyint_col_26:tinyint, 26:decimal3635_col_27:decimal(36,35), 27:boolean_col_28:boolean, 28:float_col_29:float, 29:smallint_col_30:smallint, 30:varchar0200_col_31:varchar(200), 31:boolean_col_32:boole
an, 32:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -466,7 +466,7 @@ STAGE PLANS:
native: true
predicateExpression: SelectColumnIsNotNull(col 19:decimal(4,2))
predicate: decimal0402_col_20 is not null (type: boolean)
- Statistics: Num rows: 950 Data size: 104800 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 894 Data size: 92824 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: smallint_col_15 (type: smallint), decimal0402_col_20 (type: decimal(4,2))
outputColumnNames: _col0, _col1
@@ -474,7 +474,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [14, 19]
- Statistics: Num rows: 950 Data size: 104800 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 894 Data size: 92824 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col1 (type: decimal(9,2))
sort order: +
@@ -485,7 +485,7 @@ STAGE PLANS:
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
valueColumns: 14:smallint
- Statistics: Num rows: 950 Data size: 104800 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 894 Data size: 92824 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: smallint)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -532,13 +532,13 @@ STAGE PLANS:
projectedOutputColumnNums: [0]
mode: mergepartial
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
[31/35] hive git commit: HIVE-16957: Support CTAS for auto gather
column stats (Jesus Camacho Rodriguez, reviewed by Ashutosh Chauhan)
Posted by jc...@apache.org.
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/llap/cross_product_check_2.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/cross_product_check_2.q.out b/ql/src/test/results/clientpositive/llap/cross_product_check_2.q.out
index f82f838..4dba867 100644
--- a/ql/src/test/results/clientpositive/llap/cross_product_check_2.q.out
+++ b/ql/src/test/results/clientpositive/llap/cross_product_check_2.q.out
@@ -55,14 +55,14 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: a_n2
- Statistics: Num rows: 500 Data size: 175168 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: key (type: string), value (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 500 Data size: 175168 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
- Statistics: Num rows: 500 Data size: 175168 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: string), _col1 (type: string)
Execution mode: vectorized, llap
LLAP IO: no inputs
@@ -70,14 +70,14 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: b_n2
- Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: key (type: string), value (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
- Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: string), _col1 (type: string)
Execution mode: vectorized, llap
LLAP IO: no inputs
@@ -91,10 +91,10 @@ STAGE PLANS:
0
1
outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 5000 Data size: 3596680 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5000 Data size: 1770000 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 5000 Data size: 3596680 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5000 Data size: 1770000 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -135,14 +135,14 @@ STAGE PLANS:
TableScan
alias: d1
filterExpr: key is not null (type: boolean)
- Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: key is not null (type: boolean)
- Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: key (type: string), value (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE
Map Join Operator
condition map:
Inner Join 0 to 1
@@ -152,10 +152,10 @@ STAGE PLANS:
outputColumnNames: _col0, _col1, _col2, _col3
input vertices:
1 Map 3
- Statistics: Num rows: 11 Data size: 4048 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 20 Data size: 7040 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
- Statistics: Num rows: 11 Data size: 4048 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 20 Data size: 7040 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string)
Execution mode: vectorized, llap
LLAP IO: no inputs
@@ -164,19 +164,19 @@ STAGE PLANS:
TableScan
alias: d2
filterExpr: key is not null (type: boolean)
- Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: key is not null (type: boolean)
- Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: key (type: string), value (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 1760 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: string)
Execution mode: vectorized, llap
LLAP IO: no inputs
@@ -184,14 +184,14 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: a_n2
- Statistics: Num rows: 500 Data size: 175168 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: key (type: string), value (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 500 Data size: 175168 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
- Statistics: Num rows: 500 Data size: 175168 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: string), _col1 (type: string)
Execution mode: vectorized, llap
LLAP IO: no inputs
@@ -205,10 +205,10 @@ STAGE PLANS:
0
1
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
- Statistics: Num rows: 5500 Data size: 3956348 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10000 Data size: 5300000 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 5500 Data size: 3956348 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10000 Data size: 5300000 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -255,14 +255,14 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: a_n2
- Statistics: Num rows: 500 Data size: 175168 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: key (type: string), value (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 500 Data size: 175168 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
- Statistics: Num rows: 500 Data size: 175168 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: string), _col1 (type: string)
Execution mode: vectorized, llap
LLAP IO: no inputs
@@ -271,14 +271,14 @@ STAGE PLANS:
TableScan
alias: d1
filterExpr: key is not null (type: boolean)
- Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 860 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: key is not null (type: boolean)
- Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 860 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: key (type: string)
outputColumnNames: _col0
- Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 860 Basic stats: COMPLETE Column stats: COMPLETE
Map Join Operator
condition map:
Inner Join 0 to 1
@@ -288,17 +288,17 @@ STAGE PLANS:
outputColumnNames: _col0
input vertices:
1 Map 5
- Statistics: Num rows: 11 Data size: 2024 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 20 Data size: 1720 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
keys: _col0 (type: string)
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 11 Data size: 2024 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 430 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 11 Data size: 2024 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 430 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized, llap
LLAP IO: no inputs
Map 5
@@ -306,19 +306,19 @@ STAGE PLANS:
TableScan
alias: d2
filterExpr: key is not null (type: boolean)
- Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 860 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: key is not null (type: boolean)
- Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 860 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: key (type: string)
outputColumnNames: _col0
- Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 860 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 860 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized, llap
LLAP IO: no inputs
Reducer 2
@@ -331,10 +331,10 @@ STAGE PLANS:
0
1
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 2500 Data size: 1338340 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2500 Data size: 660000 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 2500 Data size: 1338340 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2500 Data size: 660000 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -346,10 +346,10 @@ STAGE PLANS:
keys: KEY._col0 (type: string)
mode: mergepartial
outputColumnNames: _col0
- Statistics: Num rows: 5 Data size: 920 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 430 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
- Statistics: Num rows: 5 Data size: 920 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 430 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: string)
Stage: Stage-0
@@ -388,14 +388,14 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: a_n2
- Statistics: Num rows: 500 Data size: 175168 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: key (type: string), value (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 500 Data size: 175168 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
- Statistics: Num rows: 500 Data size: 175168 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: string), _col1 (type: string)
Execution mode: vectorized, llap
LLAP IO: no inputs
@@ -403,14 +403,14 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: d1
- Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 860 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: key (type: string)
outputColumnNames: _col0
- Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 860 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
- Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 860 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: string)
Execution mode: vectorized, llap
LLAP IO: no inputs
@@ -436,10 +436,10 @@ STAGE PLANS:
0
1
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 25000 Data size: 13508400 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2500 Data size: 660000 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 25000 Data size: 13508400 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2500 Data size: 660000 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -454,17 +454,17 @@ STAGE PLANS:
0
1
outputColumnNames: _col0
- Statistics: Num rows: 100 Data size: 18900 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 100 Data size: 8600 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
keys: _col0 (type: string)
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 100 Data size: 18900 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 430 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 100 Data size: 18900 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 430 Basic stats: COMPLETE Column stats: COMPLETE
Reducer 5
Execution mode: vectorized, llap
Reduce Operator Tree:
@@ -472,10 +472,10 @@ STAGE PLANS:
keys: KEY._col0 (type: string)
mode: mergepartial
outputColumnNames: _col0
- Statistics: Num rows: 50 Data size: 9450 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 430 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
- Statistics: Num rows: 50 Data size: 9450 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 430 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: string)
Stage: Stage-0
@@ -518,21 +518,21 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: a_n2
- Statistics: Num rows: 500 Data size: 87584 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: key (type: string)
outputColumnNames: key
- Statistics: Num rows: 500 Data size: 87584 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
keys: key (type: string)
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 500 Data size: 87584 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 250 Data size: 21750 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 500 Data size: 87584 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 250 Data size: 21750 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized, llap
LLAP IO: no inputs
Map 4
@@ -540,14 +540,14 @@ STAGE PLANS:
TableScan
alias: d1
filterExpr: key is not null (type: boolean)
- Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 860 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: key is not null (type: boolean)
- Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 860 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: key (type: string)
outputColumnNames: _col0
- Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 860 Basic stats: COMPLETE Column stats: COMPLETE
Map Join Operator
condition map:
Inner Join 0 to 1
@@ -557,17 +557,17 @@ STAGE PLANS:
outputColumnNames: _col0
input vertices:
1 Map 6
- Statistics: Num rows: 11 Data size: 2024 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 20 Data size: 1720 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
keys: _col0 (type: string)
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 11 Data size: 2024 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 430 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 11 Data size: 2024 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 430 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized, llap
LLAP IO: no inputs
Map 6
@@ -575,19 +575,19 @@ STAGE PLANS:
TableScan
alias: d2
filterExpr: key is not null (type: boolean)
- Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 860 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: key is not null (type: boolean)
- Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 860 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: key (type: string)
outputColumnNames: _col0
- Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 860 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 860 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized, llap
LLAP IO: no inputs
Reducer 2
@@ -597,10 +597,10 @@ STAGE PLANS:
keys: KEY._col0 (type: string)
mode: mergepartial
outputColumnNames: _col0
- Statistics: Num rows: 250 Data size: 43792 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 250 Data size: 21750 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
- Statistics: Num rows: 250 Data size: 43792 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 250 Data size: 21750 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: string)
Reducer 3
Execution mode: llap
@@ -612,10 +612,10 @@ STAGE PLANS:
0
1
outputColumnNames: _col0, _col1
- Statistics: Num rows: 1250 Data size: 450210 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1250 Data size: 216250 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 1250 Data size: 450210 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1250 Data size: 216250 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -627,10 +627,10 @@ STAGE PLANS:
keys: KEY._col0 (type: string)
mode: mergepartial
outputColumnNames: _col0
- Statistics: Num rows: 5 Data size: 920 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 430 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
- Statistics: Num rows: 5 Data size: 920 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 430 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: string)
Stage: Stage-0
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/llap/ctas.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/ctas.q.out b/ql/src/test/results/clientpositive/llap/ctas.q.out
index 2504b6a..c761b9d 100644
--- a/ql/src/test/results/clientpositive/llap/ctas.q.out
+++ b/ql/src/test/results/clientpositive/llap/ctas.q.out
@@ -27,7 +27,7 @@ POSTHOOK: Output: default@nzhang_CTAS1
STAGE DEPENDENCIES:
Stage-1 is a root stage
Stage-2 depends on stages: Stage-1
- Stage-4 depends on stages: Stage-2, Stage-0
+ Stage-4 depends on stages: Stage-0, Stage-2
Stage-3 depends on stages: Stage-4
Stage-0 depends on stages: Stage-1
@@ -38,6 +38,7 @@ STAGE PLANS:
Edges:
Reducer 2 <- Map 1 (SIMPLE_EDGE)
Reducer 3 <- Reducer 2 (SIMPLE_EDGE)
+ Reducer 4 <- Reducer 3 (CUSTOM_SIMPLE_EDGE)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -72,7 +73,7 @@ STAGE PLANS:
Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE
TopN Hash Memory Usage: 0.1
Reducer 3
- Execution mode: vectorized, llap
+ Execution mode: llap
Reduce Operator Tree:
Select Operator
expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string)
@@ -89,6 +90,34 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.nzhang_CTAS1
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: string)
+ outputColumnNames: col1, col2
+ Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE
+ Group By Operator
+ aggregations: compute_stats(col1, 'hll'), compute_stats(col2, 'hll')
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col0 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>)
+ Reducer 4
+ Execution mode: llap
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
Stage: Stage-2
Dependency Collection
@@ -105,6 +134,10 @@ STAGE PLANS:
Stage: Stage-3
Stats Work
Basic Stats Work:
+ Column Stats Desc:
+ Columns: k, value
+ Column Types: string, string
+ Table: default.nzhang_CTAS1
Stage: Stage-0
Move Operator
@@ -159,7 +192,7 @@ Retention: 0
#### A masked pattern was here ####
Table Type: MANAGED_TABLE
Table Parameters:
- COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"k\":\"true\",\"value\":\"true\"}}
bucketing_version 2
numFiles 1
numRows 10
@@ -190,7 +223,7 @@ POSTHOOK: Output: default@nzhang_ctas2
STAGE DEPENDENCIES:
Stage-1 is a root stage
Stage-2 depends on stages: Stage-1
- Stage-4 depends on stages: Stage-2, Stage-0
+ Stage-4 depends on stages: Stage-0, Stage-2
Stage-3 depends on stages: Stage-4
Stage-0 depends on stages: Stage-1
@@ -201,6 +234,7 @@ STAGE PLANS:
Edges:
Reducer 2 <- Map 1 (SIMPLE_EDGE)
Reducer 3 <- Reducer 2 (SIMPLE_EDGE)
+ Reducer 4 <- Reducer 3 (CUSTOM_SIMPLE_EDGE)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -235,7 +269,7 @@ STAGE PLANS:
Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE
TopN Hash Memory Usage: 0.1
Reducer 3
- Execution mode: vectorized, llap
+ Execution mode: llap
Reduce Operator Tree:
Select Operator
expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string)
@@ -252,6 +286,34 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.nzhang_ctas2
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: string)
+ outputColumnNames: col1, col2
+ Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE
+ Group By Operator
+ aggregations: compute_stats(col1, 'hll'), compute_stats(col2, 'hll')
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col0 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>)
+ Reducer 4
+ Execution mode: llap
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
Stage: Stage-2
Dependency Collection
@@ -268,6 +330,10 @@ STAGE PLANS:
Stage: Stage-3
Stats Work
Basic Stats Work:
+ Column Stats Desc:
+ Columns: key, value
+ Column Types: string, string
+ Table: default.nzhang_ctas2
Stage: Stage-0
Move Operator
@@ -322,7 +388,7 @@ Retention: 0
#### A masked pattern was here ####
Table Type: MANAGED_TABLE
Table Parameters:
- COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"key\":\"true\",\"value\":\"true\"}}
bucketing_version 2
numFiles 1
numRows 10
@@ -353,7 +419,7 @@ POSTHOOK: Output: default@nzhang_ctas3
STAGE DEPENDENCIES:
Stage-1 is a root stage
Stage-2 depends on stages: Stage-1
- Stage-4 depends on stages: Stage-2, Stage-0
+ Stage-4 depends on stages: Stage-0, Stage-2
Stage-3 depends on stages: Stage-4
Stage-0 depends on stages: Stage-1
@@ -364,6 +430,7 @@ STAGE PLANS:
Edges:
Reducer 2 <- Map 1 (SIMPLE_EDGE)
Reducer 3 <- Reducer 2 (SIMPLE_EDGE)
+ Reducer 4 <- Reducer 3 (CUSTOM_SIMPLE_EDGE)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -398,7 +465,7 @@ STAGE PLANS:
Statistics: Num rows: 10 Data size: 1920 Basic stats: COMPLETE Column stats: COMPLETE
TopN Hash Memory Usage: 0.1
Reducer 3
- Execution mode: vectorized, llap
+ Execution mode: llap
Reduce Operator Tree:
Select Operator
expressions: KEY.reducesinkkey0 (type: double), KEY.reducesinkkey1 (type: string)
@@ -415,6 +482,34 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
name: default.nzhang_ctas3
+ Select Operator
+ expressions: _col0 (type: double), _col1 (type: string)
+ outputColumnNames: col1, col2
+ Statistics: Num rows: 10 Data size: 1920 Basic stats: COMPLETE Column stats: COMPLETE
+ Group By Operator
+ aggregations: compute_stats(col1, 'hll'), compute_stats(col2, 'hll')
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col0 (type: struct<columntype:string,min:double,max:double,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>)
+ Reducer 4
+ Execution mode: llap
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
Stage: Stage-2
Dependency Collection
@@ -431,6 +526,10 @@ STAGE PLANS:
Stage: Stage-3
Stats Work
Basic Stats Work:
+ Column Stats Desc:
+ Columns: half_key, conb
+ Column Types: double, string
+ Table: default.nzhang_ctas3
Stage: Stage-0
Move Operator
@@ -485,7 +584,7 @@ Retention: 0
#### A masked pattern was here ####
Table Type: MANAGED_TABLE
Table Parameters:
- COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"conb\":\"true\",\"half_key\":\"true\"}}
bucketing_version 2
numFiles 1
numRows 10
@@ -549,7 +648,7 @@ Retention: 0
#### A masked pattern was here ####
Table Type: MANAGED_TABLE
Table Parameters:
- COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"conb\":\"true\",\"half_key\":\"true\"}}
bucketing_version 2
numFiles 1
numRows 10
@@ -580,7 +679,7 @@ POSTHOOK: Output: default@nzhang_ctas4
STAGE DEPENDENCIES:
Stage-1 is a root stage
Stage-2 depends on stages: Stage-1
- Stage-4 depends on stages: Stage-2, Stage-0
+ Stage-4 depends on stages: Stage-0, Stage-2
Stage-3 depends on stages: Stage-4
Stage-0 depends on stages: Stage-1
@@ -591,6 +690,7 @@ STAGE PLANS:
Edges:
Reducer 2 <- Map 1 (SIMPLE_EDGE)
Reducer 3 <- Reducer 2 (SIMPLE_EDGE)
+ Reducer 4 <- Reducer 3 (CUSTOM_SIMPLE_EDGE)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -625,7 +725,7 @@ STAGE PLANS:
Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE
TopN Hash Memory Usage: 0.1
Reducer 3
- Execution mode: vectorized, llap
+ Execution mode: llap
Reduce Operator Tree:
Select Operator
expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string)
@@ -642,6 +742,34 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.nzhang_ctas4
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: string)
+ outputColumnNames: col1, col2
+ Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE
+ Group By Operator
+ aggregations: compute_stats(col1, 'hll'), compute_stats(col2, 'hll')
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col0 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>)
+ Reducer 4
+ Execution mode: llap
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
Stage: Stage-2
Dependency Collection
@@ -659,6 +787,10 @@ STAGE PLANS:
Stage: Stage-3
Stats Work
Basic Stats Work:
+ Column Stats Desc:
+ Columns: key, value
+ Column Types: string, string
+ Table: default.nzhang_ctas4
Stage: Stage-0
Move Operator
@@ -713,7 +845,7 @@ Retention: 0
#### A masked pattern was here ####
Table Type: MANAGED_TABLE
Table Parameters:
- COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"key\":\"true\",\"value\":\"true\"}}
bucketing_version 2
numFiles 1
numRows 10
@@ -745,7 +877,7 @@ POSTHOOK: Output: default@nzhang_ctas5
STAGE DEPENDENCIES:
Stage-1 is a root stage
Stage-2 depends on stages: Stage-1
- Stage-4 depends on stages: Stage-2, Stage-0
+ Stage-4 depends on stages: Stage-0, Stage-2
Stage-3 depends on stages: Stage-4
Stage-0 depends on stages: Stage-1
@@ -756,6 +888,7 @@ STAGE PLANS:
Edges:
Reducer 2 <- Map 1 (SIMPLE_EDGE)
Reducer 3 <- Reducer 2 (SIMPLE_EDGE)
+ Reducer 4 <- Reducer 3 (CUSTOM_SIMPLE_EDGE)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -790,7 +923,7 @@ STAGE PLANS:
Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE
TopN Hash Memory Usage: 0.1
Reducer 3
- Execution mode: vectorized, llap
+ Execution mode: llap
Reduce Operator Tree:
Select Operator
expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string)
@@ -807,6 +940,34 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.nzhang_ctas5
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: string)
+ outputColumnNames: col1, col2
+ Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE
+ Group By Operator
+ aggregations: compute_stats(col1, 'hll'), compute_stats(col2, 'hll')
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col0 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>)
+ Reducer 4
+ Execution mode: llap
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
Stage: Stage-2
Dependency Collection
@@ -826,6 +987,10 @@ STAGE PLANS:
Stage: Stage-3
Stats Work
Basic Stats Work:
+ Column Stats Desc:
+ Columns: key, value
+ Column Types: string, string
+ Table: default.nzhang_ctas5
Stage: Stage-0
Move Operator
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/llap/dpp.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/dpp.q.out b/ql/src/test/results/clientpositive/llap/dpp.q.out
index 7305b78..9ec1639 100644
--- a/ql/src/test/results/clientpositive/llap/dpp.q.out
+++ b/ql/src/test/results/clientpositive/llap/dpp.q.out
@@ -203,6 +203,21 @@ STAGE PLANS:
sort order: +
Map-reduce partition columns: _col0 (type: string)
Statistics: Num rows: 2 Data size: 368 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: _col0 (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 2 Data size: 368 Basic stats: COMPLETE Column stats: COMPLETE
+ Group By Operator
+ keys: _col0 (type: string)
+ mode: hash
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE
+ Dynamic Partitioning Event Operator
+ Target column: dt (string)
+ Target Input: t1
+ Partition key expr: dt
+ Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE
+ Target Vertex: Map 8
Execution mode: vectorized, llap
LLAP IO: no inputs
Map 5
@@ -220,6 +235,21 @@ STAGE PLANS:
sort order: +
Map-reduce partition columns: _col0 (type: string)
Statistics: Num rows: 2 Data size: 368 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: _col0 (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 2 Data size: 368 Basic stats: COMPLETE Column stats: COMPLETE
+ Group By Operator
+ keys: _col0 (type: string)
+ mode: hash
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE
+ Dynamic Partitioning Event Operator
+ Target column: dt (string)
+ Target Input: t1
+ Partition key expr: dt
+ Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE
+ Target Vertex: Map 8
Execution mode: vectorized, llap
LLAP IO: no inputs
Map 6
@@ -227,49 +257,19 @@ STAGE PLANS:
TableScan
alias: t4
filterExpr: dt is not null (type: boolean)
- Statistics: Num rows: 5 Data size: 920 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 440 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: dt is not null (type: boolean)
- Statistics: Num rows: 5 Data size: 920 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 440 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: dt (type: string)
outputColumnNames: _col0
- Statistics: Num rows: 5 Data size: 920 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 440 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 6 Data size: 1104 Basic stats: COMPLETE Column stats: COMPLETE
- Select Operator
- expressions: _col0 (type: string)
- outputColumnNames: _col0
- Statistics: Num rows: 6 Data size: 2208 Basic stats: COMPLETE Column stats: COMPLETE
- Group By Operator
- keys: _col0 (type: string)
- mode: hash
- outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: COMPLETE
- Dynamic Partitioning Event Operator
- Target column: dt (string)
- Target Input: t2
- Partition key expr: dt
- Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: COMPLETE
- Target Vertex: Map 1
- Select Operator
- expressions: _col0 (type: string)
- outputColumnNames: _col0
- Statistics: Num rows: 6 Data size: 2208 Basic stats: COMPLETE Column stats: COMPLETE
- Group By Operator
- keys: _col0 (type: string)
- mode: hash
- outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: COMPLETE
- Dynamic Partitioning Event Operator
- Target column: dt (string)
- Target Input: t3
- Partition key expr: dt
- Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: COMPLETE
- Target Vertex: Map 5
+ Statistics: Num rows: 6 Data size: 624 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized, llap
LLAP IO: no inputs
Map 8
@@ -286,37 +286,7 @@ STAGE PLANS:
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 6 Data size: 1104 Basic stats: COMPLETE Column stats: COMPLETE
- Select Operator
- expressions: _col0 (type: string)
- outputColumnNames: _col0
- Statistics: Num rows: 6 Data size: 2208 Basic stats: COMPLETE Column stats: COMPLETE
- Group By Operator
- keys: _col0 (type: string)
- mode: hash
- outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: COMPLETE
- Dynamic Partitioning Event Operator
- Target column: dt (string)
- Target Input: t2
- Partition key expr: dt
- Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: COMPLETE
- Target Vertex: Map 1
- Select Operator
- expressions: _col0 (type: string)
- outputColumnNames: _col0
- Statistics: Num rows: 6 Data size: 2208 Basic stats: COMPLETE Column stats: COMPLETE
- Group By Operator
- keys: _col0 (type: string)
- mode: hash
- outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: COMPLETE
- Dynamic Partitioning Event Operator
- Target column: dt (string)
- Target Input: t3
- Partition key expr: dt
- Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: COMPLETE
- Target Vertex: Map 5
+ Statistics: Num rows: 6 Data size: 624 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized, llap
LLAP IO: no inputs
Reducer 3
[18/35] hive git commit: HIVE-16957: Support CTAS for auto gather
column stats (Jesus Camacho Rodriguez, reviewed by Ashutosh Chauhan)
Posted by jc...@apache.org.
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/llap/unionDistinct_1.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/unionDistinct_1.q.out b/ql/src/test/results/clientpositive/llap/unionDistinct_1.q.out
index 93791ac..7f2cc85 100644
--- a/ql/src/test/results/clientpositive/llap/unionDistinct_1.q.out
+++ b/ql/src/test/results/clientpositive/llap/unionDistinct_1.q.out
@@ -5154,27 +5154,27 @@ STAGE PLANS:
TableScan
alias: src2_n2
filterExpr: (UDFToDouble(key) < 10.0D) (type: boolean)
- Statistics: Num rows: 309 Data size: 56640 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 309 Data size: 29355 Basic stats: COMPLETE Column stats: COMPLETE
GatherStats: false
Filter Operator
isSamplingPred: false
predicate: (UDFToDouble(key) < 10.0D) (type: boolean)
- Statistics: Num rows: 103 Data size: 18880 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 103 Data size: 9785 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: key (type: string), count (type: bigint)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 103 Data size: 18880 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 103 Data size: 9785 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
keys: _col0 (type: string), _col1 (type: bigint)
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 206 Data size: 37760 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 103 Data size: 9785 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string), _col1 (type: bigint)
null sort order: aa
sort order: ++
Map-reduce partition columns: _col0 (type: string), _col1 (type: bigint)
- Statistics: Num rows: 206 Data size: 37760 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 103 Data size: 9785 Basic stats: COMPLETE Column stats: COMPLETE
tag: -1
auto parallelism: true
Execution mode: vectorized
@@ -5187,7 +5187,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"count":"true","key":"true"}}
bucket_count -1
bucketing_version 2
column.name.delimiter ,
@@ -5210,7 +5210,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"count":"true","key":"true"}}
bucket_count -1
bucketing_version 2
column.name.delimiter ,
@@ -5238,24 +5238,24 @@ STAGE PLANS:
TableScan
alias: src5_n1
filterExpr: (UDFToDouble(key) < 10.0D) (type: boolean)
- Statistics: Num rows: 309 Data size: 54280 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 309 Data size: 26883 Basic stats: COMPLETE Column stats: COMPLETE
GatherStats: false
Filter Operator
isSamplingPred: false
predicate: (UDFToDouble(key) < 10.0D) (type: boolean)
- Statistics: Num rows: 103 Data size: 18093 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 103 Data size: 8961 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count()
keys: key (type: string)
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 103 Data size: 18093 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 51 Data size: 4845 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
null sort order: a
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 103 Data size: 18093 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 51 Data size: 4845 Basic stats: COMPLETE Column stats: COMPLETE
tag: -1
value expressions: _col1 (type: bigint)
auto parallelism: true
@@ -5269,7 +5269,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"count":"true","key":"true"}}
bucket_count -1
bucketing_version 2
column.name.delimiter ,
@@ -5292,7 +5292,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"count":"true","key":"true"}}
bucket_count -1
bucketing_version 2
column.name.delimiter ,
@@ -5320,27 +5320,27 @@ STAGE PLANS:
TableScan
alias: src3
filterExpr: (UDFToDouble(key) < 10.0D) (type: boolean)
- Statistics: Num rows: 309 Data size: 56640 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 309 Data size: 29355 Basic stats: COMPLETE Column stats: COMPLETE
GatherStats: false
Filter Operator
isSamplingPred: false
predicate: (UDFToDouble(key) < 10.0D) (type: boolean)
- Statistics: Num rows: 103 Data size: 18880 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 103 Data size: 9785 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: key (type: string), count (type: bigint)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 103 Data size: 18880 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 103 Data size: 9785 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
keys: _col0 (type: string), _col1 (type: bigint)
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 206 Data size: 37760 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 103 Data size: 9785 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string), _col1 (type: bigint)
null sort order: aa
sort order: ++
Map-reduce partition columns: _col0 (type: string), _col1 (type: bigint)
- Statistics: Num rows: 206 Data size: 37760 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 103 Data size: 9785 Basic stats: COMPLETE Column stats: COMPLETE
tag: -1
auto parallelism: true
Execution mode: vectorized
@@ -5353,7 +5353,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"count":"true","key":"true"}}
bucket_count -1
bucketing_version 2
column.name.delimiter ,
@@ -5376,7 +5376,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"count":"true","key":"true"}}
bucket_count -1
bucketing_version 2
column.name.delimiter ,
@@ -5404,27 +5404,27 @@ STAGE PLANS:
TableScan
alias: src4
filterExpr: (UDFToDouble(key) < 10.0D) (type: boolean)
- Statistics: Num rows: 309 Data size: 56640 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 309 Data size: 29355 Basic stats: COMPLETE Column stats: COMPLETE
GatherStats: false
Filter Operator
isSamplingPred: false
predicate: (UDFToDouble(key) < 10.0D) (type: boolean)
- Statistics: Num rows: 103 Data size: 18880 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 103 Data size: 9785 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: key (type: string), count (type: bigint)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 103 Data size: 18880 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 103 Data size: 9785 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
keys: _col0 (type: string), _col1 (type: bigint)
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 206 Data size: 37760 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 103 Data size: 9785 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string), _col1 (type: bigint)
null sort order: aa
sort order: ++
Map-reduce partition columns: _col0 (type: string), _col1 (type: bigint)
- Statistics: Num rows: 206 Data size: 37760 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 103 Data size: 9785 Basic stats: COMPLETE Column stats: COMPLETE
tag: -1
auto parallelism: true
Execution mode: vectorized
@@ -5437,7 +5437,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"count":"true","key":"true"}}
bucket_count -1
bucketing_version 2
column.name.delimiter ,
@@ -5460,7 +5460,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"count":"true","key":"true"}}
bucket_count -1
bucketing_version 2
column.name.delimiter ,
@@ -5492,79 +5492,79 @@ STAGE PLANS:
keys: KEY._col0 (type: string)
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 51 Data size: 8958 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 51 Data size: 4845 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
keys: _col0 (type: string), _col1 (type: bigint)
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 154 Data size: 27838 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 77 Data size: 7315 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string), _col1 (type: bigint)
null sort order: aa
sort order: ++
Map-reduce partition columns: _col0 (type: string), _col1 (type: bigint)
- Statistics: Num rows: 154 Data size: 27838 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 77 Data size: 7315 Basic stats: COMPLETE Column stats: COMPLETE
tag: -1
auto parallelism: true
Reducer 3
- Execution mode: vectorized
+ Execution mode: vectorized, llap
Needs Tagging: false
Reduce Operator Tree:
Group By Operator
keys: KEY._col0 (type: string), KEY._col1 (type: bigint)
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 103 Data size: 18880 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 103 Data size: 9785 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
keys: _col0 (type: string), _col1 (type: bigint)
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 206 Data size: 37760 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 103 Data size: 9785 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string), _col1 (type: bigint)
null sort order: aa
sort order: ++
Map-reduce partition columns: _col0 (type: string), _col1 (type: bigint)
- Statistics: Num rows: 206 Data size: 37760 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 103 Data size: 9785 Basic stats: COMPLETE Column stats: COMPLETE
tag: -1
auto parallelism: true
Reducer 5
- Execution mode: vectorized
+ Execution mode: vectorized, llap
Needs Tagging: false
Reduce Operator Tree:
Group By Operator
keys: KEY._col0 (type: string), KEY._col1 (type: bigint)
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 103 Data size: 18880 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 103 Data size: 9785 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
keys: _col0 (type: string), _col1 (type: bigint)
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 154 Data size: 27838 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 77 Data size: 7315 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string), _col1 (type: bigint)
null sort order: aa
sort order: ++
Map-reduce partition columns: _col0 (type: string), _col1 (type: bigint)
- Statistics: Num rows: 154 Data size: 27838 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 77 Data size: 7315 Basic stats: COMPLETE Column stats: COMPLETE
tag: -1
auto parallelism: true
Reducer 7
- Execution mode: vectorized
+ Execution mode: vectorized, llap
Needs Tagging: false
Reduce Operator Tree:
Group By Operator
keys: KEY._col0 (type: string), KEY._col1 (type: bigint)
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 77 Data size: 13919 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 77 Data size: 7315 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
GlobalTableId: 0
directory: hdfs://### HDFS PATH ###
NumFilesPerFileSink: 1
- Statistics: Num rows: 77 Data size: 13919 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 77 Data size: 7315 Basic stats: COMPLETE Column stats: COMPLETE
Stats Publishing Key Prefix: hdfs://### HDFS PATH ###
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
@@ -5624,11 +5624,11 @@ POSTHOOK: Input: default@src3
POSTHOOK: Input: default@src4
POSTHOOK: Input: default@src5_n1
POSTHOOK: Output: hdfs://### HDFS PATH ###
+5 1
0 1
0 3
2 1
4 1
-5 1
5 3
8 1
9 1
@@ -5690,9 +5690,9 @@ STAGE PLANS:
Edges:
Map 1 <- Union 2 (CONTAINS)
Map 6 <- Union 2 (CONTAINS)
+ Map 8 <- Map 7 (BROADCAST_EDGE), Union 4 (CONTAINS)
Reducer 3 <- Union 2 (SIMPLE_EDGE), Union 4 (CONTAINS)
Reducer 5 <- Union 4 (SIMPLE_EDGE)
- Reducer 8 <- Map 7 (SIMPLE_EDGE), Map 9 (SIMPLE_EDGE), Union 4 (CONTAINS)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -5700,27 +5700,27 @@ STAGE PLANS:
TableScan
alias: src2_n2
filterExpr: (UDFToDouble(key) < 10.0D) (type: boolean)
- Statistics: Num rows: 309 Data size: 56640 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 309 Data size: 29355 Basic stats: COMPLETE Column stats: COMPLETE
GatherStats: false
Filter Operator
isSamplingPred: false
predicate: (UDFToDouble(key) < 10.0D) (type: boolean)
- Statistics: Num rows: 103 Data size: 18880 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 103 Data size: 9785 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: key (type: string), count (type: bigint)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 103 Data size: 18880 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 103 Data size: 9785 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
keys: _col0 (type: string), _col1 (type: bigint)
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 206 Data size: 37760 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 103 Data size: 9785 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string), _col1 (type: bigint)
null sort order: aa
sort order: ++
Map-reduce partition columns: _col0 (type: string), _col1 (type: bigint)
- Statistics: Num rows: 206 Data size: 37760 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 103 Data size: 9785 Basic stats: COMPLETE Column stats: COMPLETE
tag: -1
auto parallelism: true
Execution mode: vectorized
@@ -5733,7 +5733,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"count":"true","key":"true"}}
bucket_count -1
bucketing_version 2
column.name.delimiter ,
@@ -5756,7 +5756,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"count":"true","key":"true"}}
bucket_count -1
bucketing_version 2
column.name.delimiter ,
@@ -5784,27 +5784,27 @@ STAGE PLANS:
TableScan
alias: src3
filterExpr: (UDFToDouble(key) < 10.0D) (type: boolean)
- Statistics: Num rows: 309 Data size: 56640 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 309 Data size: 29355 Basic stats: COMPLETE Column stats: COMPLETE
GatherStats: false
Filter Operator
isSamplingPred: false
predicate: (UDFToDouble(key) < 10.0D) (type: boolean)
- Statistics: Num rows: 103 Data size: 18880 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 103 Data size: 9785 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: key (type: string), count (type: bigint)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 103 Data size: 18880 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 103 Data size: 9785 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
keys: _col0 (type: string), _col1 (type: bigint)
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 206 Data size: 37760 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 103 Data size: 9785 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string), _col1 (type: bigint)
null sort order: aa
sort order: ++
Map-reduce partition columns: _col0 (type: string), _col1 (type: bigint)
- Statistics: Num rows: 206 Data size: 37760 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 103 Data size: 9785 Basic stats: COMPLETE Column stats: COMPLETE
tag: -1
auto parallelism: true
Execution mode: vectorized
@@ -5817,7 +5817,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"count":"true","key":"true"}}
bucket_count -1
bucketing_version 2
column.name.delimiter ,
@@ -5840,7 +5840,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"count":"true","key":"true"}}
bucket_count -1
bucketing_version 2
column.name.delimiter ,
@@ -5868,22 +5868,22 @@ STAGE PLANS:
TableScan
alias: a
filterExpr: (UDFToDouble(key) < 10.0D) (type: boolean)
- Statistics: Num rows: 309 Data size: 54280 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 309 Data size: 26883 Basic stats: COMPLETE Column stats: COMPLETE
GatherStats: false
Filter Operator
isSamplingPred: false
predicate: (UDFToDouble(key) < 10.0D) (type: boolean)
- Statistics: Num rows: 103 Data size: 18093 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 103 Data size: 8961 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: key (type: string)
outputColumnNames: _col0
- Statistics: Num rows: 103 Data size: 18093 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 103 Data size: 8961 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
null sort order: a
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 103 Data size: 18093 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 103 Data size: 8961 Basic stats: COMPLETE Column stats: COMPLETE
tag: 0
auto parallelism: true
Execution mode: vectorized
@@ -5896,7 +5896,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"count":"true","key":"true"}}
bucket_count -1
bucketing_version 2
column.name.delimiter ,
@@ -5919,7 +5919,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"count":"true","key":"true"}}
bucket_count -1
bucketing_version 2
column.name.delimiter ,
@@ -5942,30 +5942,51 @@ STAGE PLANS:
name: default.src4
Truncated Path -> Alias:
/src4 [a]
- Map 9
+ Map 8
Map Operator Tree:
TableScan
alias: b
filterExpr: (UDFToDouble(key) < 10.0D) (type: boolean)
- Statistics: Num rows: 309 Data size: 56640 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 309 Data size: 29355 Basic stats: COMPLETE Column stats: COMPLETE
GatherStats: false
Filter Operator
isSamplingPred: false
predicate: (UDFToDouble(key) < 10.0D) (type: boolean)
- Statistics: Num rows: 103 Data size: 18880 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 103 Data size: 9785 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: key (type: string), count (type: bigint)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 103 Data size: 18880 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: string)
- null sort order: a
- sort order: +
- Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 103 Data size: 18880 Basic stats: COMPLETE Column stats: NONE
- tag: 1
- value expressions: _col1 (type: bigint)
- auto parallelism: true
+ Statistics: Num rows: 103 Data size: 9785 Basic stats: COMPLETE Column stats: COMPLETE
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ Estimated key counts: Map 7 => 103
+ keys:
+ 0 _col0 (type: string)
+ 1 _col0 (type: string)
+ outputColumnNames: _col0, _col2
+ input vertices:
+ 0 Map 7
+ Position of Big Table: 1
+ Statistics: Num rows: 103 Data size: 9785 Basic stats: COMPLETE Column stats: COMPLETE
+ HybridGraceHashJoin: true
+ Select Operator
+ expressions: _col0 (type: string), _col2 (type: bigint)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 103 Data size: 9785 Basic stats: COMPLETE Column stats: COMPLETE
+ Group By Operator
+ keys: _col0 (type: string), _col1 (type: bigint)
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 103 Data size: 9785 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ key expressions: _col0 (type: string), _col1 (type: bigint)
+ null sort order: aa
+ sort order: ++
+ Map-reduce partition columns: _col0 (type: string), _col1 (type: bigint)
+ Statistics: Num rows: 103 Data size: 9785 Basic stats: COMPLETE Column stats: COMPLETE
+ tag: -1
+ auto parallelism: true
Execution mode: vectorized
Path -> Alias:
hdfs://### HDFS PATH ### [b]
@@ -5976,7 +5997,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"count":"true","key":"true"}}
bucket_count -1
bucketing_version 2
column.name.delimiter ,
@@ -5999,7 +6020,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"count":"true","key":"true"}}
bucket_count -1
bucketing_version 2
column.name.delimiter ,
@@ -6023,42 +6044,42 @@ STAGE PLANS:
Truncated Path -> Alias:
/src5_n1 [b]
Reducer 3
- Execution mode: vectorized
+ Execution mode: vectorized, llap
Needs Tagging: false
Reduce Operator Tree:
Group By Operator
keys: KEY._col0 (type: string), KEY._col1 (type: bigint)
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 103 Data size: 18880 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 103 Data size: 9785 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
keys: _col0 (type: string), _col1 (type: bigint)
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 216 Data size: 38782 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 103 Data size: 9785 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string), _col1 (type: bigint)
null sort order: aa
sort order: ++
Map-reduce partition columns: _col0 (type: string), _col1 (type: bigint)
- Statistics: Num rows: 216 Data size: 38782 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 103 Data size: 9785 Basic stats: COMPLETE Column stats: COMPLETE
tag: -1
auto parallelism: true
Reducer 5
- Execution mode: vectorized
+ Execution mode: vectorized, llap
Needs Tagging: false
Reduce Operator Tree:
Group By Operator
keys: KEY._col0 (type: string), KEY._col1 (type: bigint)
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 108 Data size: 19391 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 103 Data size: 9785 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
GlobalTableId: 0
directory: hdfs://### HDFS PATH ###
NumFilesPerFileSink: 1
- Statistics: Num rows: 108 Data size: 19391 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 103 Data size: 9785 Basic stats: COMPLETE Column stats: COMPLETE
Stats Publishing Key Prefix: hdfs://### HDFS PATH ###
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
@@ -6075,35 +6096,6 @@ STAGE PLANS:
TotalFiles: 1
GatherStats: false
MultiFileSpray: false
- Reducer 8
- Needs Tagging: false
- Reduce Operator Tree:
- Merge Join Operator
- condition map:
- Inner Join 0 to 1
- keys:
- 0 _col0 (type: string)
- 1 _col0 (type: string)
- outputColumnNames: _col0, _col2
- Position of Big Table: 1
- Statistics: Num rows: 113 Data size: 19902 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col0 (type: string), _col2 (type: bigint)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 113 Data size: 19902 Basic stats: COMPLETE Column stats: NONE
- Group By Operator
- keys: _col0 (type: string), _col1 (type: bigint)
- mode: hash
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 216 Data size: 38782 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: string), _col1 (type: bigint)
- null sort order: aa
- sort order: ++
- Map-reduce partition columns: _col0 (type: string), _col1 (type: bigint)
- Statistics: Num rows: 216 Data size: 38782 Basic stats: COMPLETE Column stats: NONE
- tag: -1
- auto parallelism: true
Union 2
Vertex: Union 2
Union 4
@@ -6206,10 +6198,10 @@ STAGE PLANS:
Edges:
Map 1 <- Union 2 (CONTAINS)
Map 6 <- Union 2 (CONTAINS)
+ Map 7 <- Map 9 (BROADCAST_EDGE)
Reducer 3 <- Union 2 (SIMPLE_EDGE), Union 4 (CONTAINS)
Reducer 5 <- Union 4 (SIMPLE_EDGE)
- Reducer 8 <- Map 10 (SIMPLE_EDGE), Map 7 (SIMPLE_EDGE)
- Reducer 9 <- Reducer 8 (SIMPLE_EDGE), Union 4 (CONTAINS)
+ Reducer 8 <- Map 7 (SIMPLE_EDGE), Union 4 (CONTAINS)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -6217,27 +6209,27 @@ STAGE PLANS:
TableScan
alias: src2_n2
filterExpr: (UDFToDouble(key) < 10.0D) (type: boolean)
- Statistics: Num rows: 309 Data size: 56640 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 309 Data size: 29355 Basic stats: COMPLETE Column stats: COMPLETE
GatherStats: false
Filter Operator
isSamplingPred: false
predicate: (UDFToDouble(key) < 10.0D) (type: boolean)
- Statistics: Num rows: 103 Data size: 18880 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 103 Data size: 9785 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: key (type: string), count (type: bigint)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 103 Data size: 18880 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 103 Data size: 9785 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
keys: _col0 (type: string), _col1 (type: bigint)
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 206 Data size: 37760 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 103 Data size: 9785 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string), _col1 (type: bigint)
null sort order: aa
sort order: ++
Map-reduce partition columns: _col0 (type: string), _col1 (type: bigint)
- Statistics: Num rows: 206 Data size: 37760 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 103 Data size: 9785 Basic stats: COMPLETE Column stats: COMPLETE
tag: -1
auto parallelism: true
Execution mode: vectorized
@@ -6250,7 +6242,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"count":"true","key":"true"}}
bucket_count -1
bucketing_version 2
column.name.delimiter ,
@@ -6273,7 +6265,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"count":"true","key":"true"}}
bucket_count -1
bucketing_version 2
column.name.delimiter ,
@@ -6296,40 +6288,45 @@ STAGE PLANS:
name: default.src2_n2
Truncated Path -> Alias:
/src2_n2 [src2_n2]
- Map 10
+ Map 6
Map Operator Tree:
TableScan
- alias: b
+ alias: src3
filterExpr: (UDFToDouble(key) < 10.0D) (type: boolean)
- Statistics: Num rows: 309 Data size: 54280 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 309 Data size: 29355 Basic stats: COMPLETE Column stats: COMPLETE
GatherStats: false
Filter Operator
isSamplingPred: false
predicate: (UDFToDouble(key) < 10.0D) (type: boolean)
- Statistics: Num rows: 103 Data size: 18093 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 103 Data size: 9785 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
- expressions: key (type: string)
- outputColumnNames: _col0
- Statistics: Num rows: 103 Data size: 18093 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: string)
- null sort order: a
- sort order: +
- Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 103 Data size: 18093 Basic stats: COMPLETE Column stats: NONE
- tag: 1
- auto parallelism: true
+ expressions: key (type: string), count (type: bigint)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 103 Data size: 9785 Basic stats: COMPLETE Column stats: COMPLETE
+ Group By Operator
+ keys: _col0 (type: string), _col1 (type: bigint)
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 103 Data size: 9785 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ key expressions: _col0 (type: string), _col1 (type: bigint)
+ null sort order: aa
+ sort order: ++
+ Map-reduce partition columns: _col0 (type: string), _col1 (type: bigint)
+ Statistics: Num rows: 103 Data size: 9785 Basic stats: COMPLETE Column stats: COMPLETE
+ tag: -1
+ auto parallelism: true
Execution mode: vectorized
Path -> Alias:
- hdfs://### HDFS PATH ### [b]
+ hdfs://### HDFS PATH ### [src3]
Path -> Partition:
hdfs://### HDFS PATH ###
Partition
- base file name: src5_n1
+ base file name: src3
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"count":"true","key":"true"}}
bucket_count -1
bucketing_version 2
column.name.delimiter ,
@@ -6338,11 +6335,11 @@ STAGE PLANS:
columns.types string:bigint
#### A masked pattern was here ####
location hdfs://### HDFS PATH ###
- name default.src5_n1
+ name default.src3
numFiles 1
numRows 309
rawDataSize 1482
- serialization.ddl struct src5_n1 { string key, i64 count}
+ serialization.ddl struct src3 { string key, i64 count}
serialization.format 1
serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
totalSize 1791
@@ -6352,7 +6349,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"count":"true","key":"true"}}
bucket_count -1
bucketing_version 2
column.name.delimiter ,
@@ -6361,59 +6358,74 @@ STAGE PLANS:
columns.types string:bigint
#### A masked pattern was here ####
location hdfs://### HDFS PATH ###
- name default.src5_n1
+ name default.src3
numFiles 1
numRows 309
rawDataSize 1482
- serialization.ddl struct src5_n1 { string key, i64 count}
+ serialization.ddl struct src3 { string key, i64 count}
serialization.format 1
serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
totalSize 1791
#### A masked pattern was here ####
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.src5_n1
- name: default.src5_n1
+ name: default.src3
+ name: default.src3
Truncated Path -> Alias:
- /src5_n1 [b]
- Map 6
+ /src3 [src3]
+ Map 7
Map Operator Tree:
TableScan
- alias: src3
+ alias: a
filterExpr: (UDFToDouble(key) < 10.0D) (type: boolean)
- Statistics: Num rows: 309 Data size: 56640 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 309 Data size: 26883 Basic stats: COMPLETE Column stats: COMPLETE
GatherStats: false
Filter Operator
isSamplingPred: false
predicate: (UDFToDouble(key) < 10.0D) (type: boolean)
- Statistics: Num rows: 103 Data size: 18880 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 103 Data size: 8961 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
- expressions: key (type: string), count (type: bigint)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 103 Data size: 18880 Basic stats: COMPLETE Column stats: NONE
- Group By Operator
- keys: _col0 (type: string), _col1 (type: bigint)
- mode: hash
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 206 Data size: 37760 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: string), _col1 (type: bigint)
- null sort order: aa
- sort order: ++
- Map-reduce partition columns: _col0 (type: string), _col1 (type: bigint)
- Statistics: Num rows: 206 Data size: 37760 Basic stats: COMPLETE Column stats: NONE
- tag: -1
- auto parallelism: true
+ expressions: key (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 103 Data size: 8961 Basic stats: COMPLETE Column stats: COMPLETE
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ Estimated key counts: Map 9 => 103
+ keys:
+ 0 _col0 (type: string)
+ 1 _col0 (type: string)
+ outputColumnNames: _col0
+ input vertices:
+ 1 Map 9
+ Position of Big Table: 0
+ Statistics: Num rows: 103 Data size: 8961 Basic stats: COMPLETE Column stats: COMPLETE
+ HybridGraceHashJoin: true
+ Group By Operator
+ aggregations: count()
+ keys: _col0 (type: string)
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 51 Data size: 4845 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ null sort order: a
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 51 Data size: 4845 Basic stats: COMPLETE Column stats: COMPLETE
+ tag: -1
+ value expressions: _col1 (type: bigint)
+ auto parallelism: true
Execution mode: vectorized
Path -> Alias:
- hdfs://### HDFS PATH ### [src3]
+ hdfs://### HDFS PATH ### [a]
Path -> Partition:
hdfs://### HDFS PATH ###
Partition
- base file name: src3
+ base file name: src4
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"count":"true","key":"true"}}
bucket_count -1
bucketing_version 2
column.name.delimiter ,
@@ -6422,11 +6434,11 @@ STAGE PLANS:
columns.types string:bigint
#### A masked pattern was here ####
location hdfs://### HDFS PATH ###
- name default.src3
+ name default.src4
numFiles 1
numRows 309
rawDataSize 1482
- serialization.ddl struct src3 { string key, i64 count}
+ serialization.ddl struct src4 { string key, i64 count}
serialization.format 1
serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
totalSize 1791
@@ -6436,7 +6448,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"count":"true","key":"true"}}
bucket_count -1
bucketing_version 2
column.name.delimiter ,
@@ -6445,54 +6457,54 @@ STAGE PLANS:
columns.types string:bigint
#### A masked pattern was here ####
location hdfs://### HDFS PATH ###
- name default.src3
+ name default.src4
numFiles 1
numRows 309
rawDataSize 1482
- serialization.ddl struct src3 { string key, i64 count}
+ serialization.ddl struct src4 { string key, i64 count}
serialization.format 1
serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
totalSize 1791
#### A masked pattern was here ####
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.src3
- name: default.src3
+ name: default.src4
+ name: default.src4
Truncated Path -> Alias:
- /src3 [src3]
- Map 7
+ /src4 [a]
+ Map 9
Map Operator Tree:
TableScan
- alias: a
+ alias: b
filterExpr: (UDFToDouble(key) < 10.0D) (type: boolean)
- Statistics: Num rows: 309 Data size: 54280 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 309 Data size: 26883 Basic stats: COMPLETE Column stats: COMPLETE
GatherStats: false
Filter Operator
isSamplingPred: false
predicate: (UDFToDouble(key) < 10.0D) (type: boolean)
- Statistics: Num rows: 103 Data size: 18093 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 103 Data size: 8961 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: key (type: string)
outputColumnNames: _col0
- Statistics: Num rows: 103 Data size: 18093 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 103 Data size: 8961 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
null sort order: a
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 103 Data size: 18093 Basic stats: COMPLETE Column stats: NONE
- tag: 0
+ Statistics: Num rows: 103 Data size: 8961 Basic stats: COMPLETE Column stats: COMPLETE
+ tag: 1
auto parallelism: true
Execution mode: vectorized
Path -> Alias:
- hdfs://### HDFS PATH ### [a]
+ hdfs://### HDFS PATH ### [b]
Path -> Partition:
hdfs://### HDFS PATH ###
Partition
- base file name: src4
+ base file name: src5_n1
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"count":"true","key":"true"}}
bucket_count -1
bucketing_version 2
column.name.delimiter ,
@@ -6501,11 +6513,11 @@ STAGE PLANS:
columns.types string:bigint
#### A masked pattern was here ####
location hdfs://### HDFS PATH ###
- name default.src4
+ name default.src5_n1
numFiles 1
numRows 309
rawDataSize 1482
- serialization.ddl struct src4 { string key, i64 count}
+ serialization.ddl struct src5_n1 { string key, i64 count}
serialization.format 1
serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
totalSize 1791
@@ -6515,7 +6527,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"count":"true","key":"true"}}
bucket_count -1
bucketing_version 2
column.name.delimiter ,
@@ -6524,57 +6536,57 @@ STAGE PLANS:
columns.types string:bigint
#### A masked pattern was here ####
location hdfs://### HDFS PATH ###
- name default.src4
+ name default.src5_n1
numFiles 1
numRows 309
rawDataSize 1482
- serialization.ddl struct src4 { string key, i64 count}
+ serialization.ddl struct src5_n1 { string key, i64 count}
serialization.format 1
serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
totalSize 1791
#### A masked pattern was here ####
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.src4
- name: default.src4
+ name: default.src5_n1
+ name: default.src5_n1
Truncated Path -> Alias:
- /src4 [a]
+ /src5_n1 [b]
Reducer 3
- Execution mode: vectorized
+ Execution mode: vectorized, llap
Needs Tagging: false
Reduce Operator Tree:
Group By Operator
keys: KEY._col0 (type: string), KEY._col1 (type: bigint)
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 103 Data size: 18880 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 103 Data size: 9785 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
keys: _col0 (type: string), _col1 (type: bigint)
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 159 Data size: 28742 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 77 Data size: 7315 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string), _col1 (type: bigint)
null sort order: aa
sort order: ++
Map-reduce partition columns: _col0 (type: string), _col1 (type: bigint)
- Statistics: Num rows: 159 Data size: 28742 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 77 Data size: 7315 Basic stats: COMPLETE Column stats: COMPLETE
tag: -1
auto parallelism: true
Reducer 5
- Execution mode: vectorized
+ Execution mode: vectorized, llap
Needs Tagging: false
Reduce Operator Tree:
Group By Operator
keys: KEY._col0 (type: string), KEY._col1 (type: bigint)
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 79 Data size: 14280 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 77 Data size: 7315 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
GlobalTableId: 0
directory: hdfs://### HDFS PATH ###
NumFilesPerFileSink: 1
- Statistics: Num rows: 79 Data size: 14280 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 77 Data size: 7315 Basic stats: COMPLETE Column stats: COMPLETE
Stats Publishing Key Prefix: hdfs://### HDFS PATH ###
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
@@ -6592,33 +6604,6 @@ STAGE PLANS:
GatherStats: false
MultiFileSpray: false
Reducer 8
- Needs Tagging: false
- Reduce Operator Tree:
- Merge Join Operator
- condition map:
- Inner Join 0 to 1
- keys:
- 0 _col0 (type: string)
- 1 _col0 (type: string)
- outputColumnNames: _col0
- Position of Big Table: 0
- Statistics: Num rows: 113 Data size: 19902 Basic stats: COMPLETE Column stats: NONE
- Group By Operator
- aggregations: count()
- keys: _col0 (type: string)
- mode: hash
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 113 Data size: 19902 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: string)
- null sort order: a
- sort order: +
- Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 113 Data size: 19902 Basic stats: COMPLETE Column stats: NONE
- tag: -1
- value expressions: _col1 (type: bigint)
- auto parallelism: true
- Reducer 9
Execution mode: vectorized
Needs Tagging: false
Reduce Operator Tree:
@@ -6627,18 +6612,18 @@ STAGE PLANS:
keys: KEY._col0 (type: string)
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 56 Data size: 9862 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 51 Data size: 4845 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
keys: _col0 (type: string), _col1 (type: bigint)
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 159 Data size: 28742 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 77 Data size: 7315 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string), _col1 (type: bigint)
null sort order: aa
sort order: ++
Map-reduce partition columns: _col0 (type: string), _col1 (type: bigint)
- Statistics: Num rows: 159 Data size: 28742 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 77 Data size: 7315 Basic stats: COMPLETE Column stats: COMPLETE
tag: -1
auto parallelism: true
Union 2
@@ -6678,11 +6663,11 @@ POSTHOOK: Input: default@src3
POSTHOOK: Input: default@src4
POSTHOOK: Input: default@src5_n1
POSTHOOK: Output: hdfs://### HDFS PATH ###
+5 1
0 1
0 3
2 1
4 1
-5 1
5 3
8 1
9 1
@@ -6759,7 +6744,7 @@ POSTHOOK: Output: default@tmp_unionall_n0
STAGE DEPENDENCIES:
Stage-1 is a root stage
Stage-2 depends on stages: Stage-1
- Stage-4 depends on stages: Stage-2, Stage-0
+ Stage-4 depends on stages: Stage-0, Stage-2
Stage-3 depends on stages: Stage-4
Stage-0 depends on stages: Stage-1
@@ -6769,10 +6754,11 @@ STAGE PLANS:
#### A masked pattern was here ####
Edges:
Map 1 <- Union 2 (CONTAINS)
- Map 4 <- Union 5 (CONTAINS)
- Map 7 <- Union 5 (CONTAINS)
+ Map 5 <- Union 6 (CONTAINS)
+ Map 8 <- Union 6 (CONTAINS)
Reducer 3 <- Union 2 (SIMPLE_EDGE)
- Reducer 6 <- Union 2 (CONTAINS), Union 5 (SIMPLE_EDGE)
+ Reducer 4 <- Reducer 3 (CUSTOM_SIMPLE_EDGE)
+ Reducer 7 <- Union 2 (CONTAINS), Union 6 (SIMPLE_EDGE)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -6796,7 +6782,7 @@ STAGE PLANS:
Map-reduce partition columns: _col0 (type: string), _col1 (type: string)
Statistics: Num rows: 408 Data size: 72624 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized
- Map 4
+ Map 5
Map Operator Tree:
TableScan
alias: a
@@ -6817,7 +6803,7 @@ STAGE PLANS:
Map-reduce partition columns: _col0 (type: string)
Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized
- Map 7
+ Map 8
Map Operator Tree:
TableScan
alias: b
@@ -6839,7 +6825,7 @@ STAGE PLANS:
Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized
Reducer 3
- Execution mode: vectorized, llap
+ Execution mode: llap
Reduce Operator Tree:
Group By Operator
keys: KEY._col0 (type: string), KEY._col1 (type: string)
@@ -6864,7 +6850,35 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.tmp_unionall_n0
- Reducer 6
+ Select Operator
+ expressions: _col0 (type: bigint), _col1 (type: string), _col2 (type: string)
+ outputColumnNames: col1, col2, col3
+ Statistics: Num rows: 408 Data size: 75888 Basic stats: COMPLETE Column stats: COMPLETE
+ Group By Operator
+ aggregations: compute_stats(col1, 'hll'), compute_stats(col2, 'hll'), compute_stats(col3, 'hll')
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 1304 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 1304 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col0 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col2 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>)
+ Reducer 4
+ Execution mode: llap
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: COMPLETE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: COMPLETE
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ Reducer 7
Execution mode: vectorized, llap
Reduce Operator Tree:
Group By Operator
@@ -6897,8 +6911,8 @@ STAGE PLANS:
Statistics: Num rows: 408 Data size: 72624 Basic stats: COMPLETE Column stats: COMPLETE
Union 2
Vertex: Union 2
- Union 5
- Vertex: Union 5
+ Union 6
+ Vertex: Union 6
Stage: Stage-2
Dependency Collection
@@ -6915,6 +6929,10 @@ STAGE PLANS:
Stage: Stage-3
Stats Work
Basic Stats Work:
+ Column Stats Desc:
+ Columns: counts, key, value
+ Column Types: bigint, string, string
+ Table: default.tmp_unionall_n0
Stage: Stage-0
Move Operator
@@ -8255,10 +8273,9 @@ STAGE PLANS:
Tez
#### A masked pattern was here ####
Edges:
- Map 3 <- Union 4 (CONTAINS)
- Map 6 <- Union 4 (CONTAINS)
- Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 5 (SIMPLE_EDGE)
- Reducer 5 <- Union 4 (SIMPLE_EDGE)
+ Map 2 <- Union 3 (CONTAINS)
+ Map 5 <- Union 3 (CONTAINS)
+ Reducer 4 <- Map 1 (BROADCAST_EDGE), Union 3 (SIMPLE_EDGE)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -8266,105 +8283,100 @@ STAGE PLANS:
TableScan
alias: a
filterExpr: (UDFToDouble(key) = 97.0D) (type: boolean)
- Statistics: Num rows: 500 Data size: 87584 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: (UDFToDouble(key) = 97.0D) (type: boolean)
- Statistics: Num rows: 250 Data size: 43792 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 250 Data size: 21750 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: key (type: string)
outputColumnNames: _col0
- Statistics: Num rows: 250 Data size: 43792 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 250 Data size: 21750 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 250 Data size: 43792 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 250 Data size: 21750 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized
- Map 3
+ Map 2
Map Operator Tree:
TableScan
alias: dim_pho
filterExpr: (UDFToDouble(key) = 97.0D) (type: boolean)
- Statistics: Num rows: 500 Data size: 175168 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: (UDFToDouble(key) = 97.0D) (type: boolean)
- Statistics: Num rows: 250 Data size: 87584 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: key (type: string), value (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 250 Data size: 87584 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
keys: _col0 (type: string), _col1 (type: string)
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 500 Data size: 175168 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string), _col1 (type: string)
sort order: ++
Map-reduce partition columns: _col0 (type: string), _col1 (type: string)
- Statistics: Num rows: 500 Data size: 175168 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized
- Map 6
+ Map 5
Map Operator Tree:
TableScan
alias: jackson_sev_add
filterExpr: (UDFToDouble(key) = 97.0D) (type: boolean)
- Statistics: Num rows: 500 Data size: 175168 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: (UDFToDouble(key) = 97.0D) (type: boolean)
- Statistics: Num rows: 250 Data size: 87584 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: key (type: string), value (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 250 Data size: 87584 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
keys: _col0 (type: string), _col1 (type: string)
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 500 Data size: 175168 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string), _col1 (type: string)
sort order: ++
Map-reduce partition columns: _col0 (type: string), _col1 (type: string)
- Statistics: Num rows: 500 Data size: 175168 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized
- Reducer 2
- Reduce Operator Tree:
- Merge Join Operator
- condition map:
- Inner Join 0 to 1
- keys:
- 0 _col0 (type: string)
- 1 _col0 (type: string)
- outputColumnNames: _col1, _col2
- Statistics: Num rows: 275 Data size: 48171 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col1 (type: string), _col2 (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 275 Data size: 48171 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 275 Data size: 48171 Basic stats: COMPLETE Column stats: NONE
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- Reducer 5
+ Reducer 4
Execution mode: vectorized
Reduce Operator Tree:
Group By Operator
keys: KEY._col0 (type: string), KEY._col1 (type: string)
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 250 Data size: 87584 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: string)
- sort order: +
- Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 250 Data size: 87584 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col1 (type: string)
- Union 4
- Vertex: Union 4
+ Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col0 (type: string)
+ 1 _col0 (type: string)
+ outputColumnNames: _col1, _col2
+ input vertices:
+ 0 Map 1
+ Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE
+ HybridGraceHashJoin: true
+ Select Operator
+ expressions: _col1 (type: string), _col2 (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ Union 3
+ Vertex: Union 3
Stage: Stage-0
Fetch Operator
@@ -9035,12 +9047,15 @@ STAGE PLANS:
Reduce Output Operator
sort order:
Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
+ TopN Hash Memory Usage: 0.1
Reduce Output Operator
sort order:
Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
+ TopN Hash Memory Usage: 0.1
Reduce Output Operator
sort order:
Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
+ TopN Hash Memory Usage: 0.1
Execution mode: vectorized
Map 11
Map Operator Tree:
@@ -9055,6 +9070,7 @@ STAGE PLANS:
Reduce Output Operator
sort order:
Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
+ TopN Hash Memory Usage: 0.1
Execution mode: vectorized
Reducer 10
Execution mode: vectorized
@@ -9745,66 +9761,67 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: t1_n93
- Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 1740 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: key (type: string), value (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 1740 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
keys: _col0 (type: string), _col1 (type: string)
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 20 Data size: 7360 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 1740 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string), _col1 (type: string)
sort order: ++
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 20 Data size: 7360 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 1740 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized
Map 7
Map Operator Tree:
TableScan
alias: t2_n58
- Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 1740 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: key (type: string), value (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 1740 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
keys: _col0 (type: string), _col1 (type: string)
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 20 Data size: 7360 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 1740 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string), _col1 (type: string)
sort order: ++
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 20 Data size: 7360 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 1740 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized
Reducer 3
+ Execution mode: llap
Reduce Operator Tree:
Group By Operator
keys: KEY._col0 (type: string), KEY._col1 (type: string)
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 1740 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: string)
outputColumnNames: _col0
- Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 1740 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count(1)
keys: _col0 (type: string)
mode: complete
outputColumnNames: _col0, _col1
- Statistics: Num rows: 5 Data size: 1840 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 558 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: string), UDFToInteger(_col1) (type: int)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 5 Data size: 1840 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 534 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 5 Data size: 1840 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 534 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
@@ -9813,61 +9830,63 @@ STAGE PLANS:
Select Operator
expressions: _col0 (type: string), _col1 (type: int)
outputColumnNames: key, cnt
- Statistics: Num rows: 5 Data size: 1840 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 534 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: compute_stats(key, 'hll'), compute_stats(cnt, 'hll')
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 1232 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
- Statistics: Num rows: 1 Data size: 1232 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>)
Select Operator
expressions: _col1 (type: string)
outputColumnNames: _col1
- Statistic
<TRUNCATED>
[35/35] hive git commit: HIVE-16957: Support CTAS for auto gather
column stats (Jesus Camacho Rodriguez, reviewed by Ashutosh Chauhan)
Posted by jc...@apache.org.
HIVE-16957: Support CTAS for auto gather column stats (Jesus Camacho Rodriguez, reviewed by Ashutosh Chauhan)
Project: http://git-wip-us.apache.org/repos/asf/hive/repo
Commit: http://git-wip-us.apache.org/repos/asf/hive/commit/138b00ca
Tree: http://git-wip-us.apache.org/repos/asf/hive/tree/138b00ca
Diff: http://git-wip-us.apache.org/repos/asf/hive/diff/138b00ca
Branch: refs/heads/master
Commit: 138b00cad8433780fb605e280121b0a9e8baeac5
Parents: 691c4cb
Author: Jesus Camacho Rodriguez <jc...@apache.org>
Authored: Tue Dec 11 17:24:21 2018 -0800
Committer: Jesus Camacho Rodriguez <jc...@apache.org>
Committed: Fri Jan 4 01:22:41 2019 +0100
----------------------------------------------------------------------
.../listener/TestDbNotificationListener.java | 6 +-
.../apache/hadoop/hive/hooks/TestHs2Hooks.java | 1 +
.../ql/optimizer/LimitPushdownOptimizer.java | 28 +-
.../hive/ql/parse/BaseSemanticAnalyzer.java | 2 +-
.../ql/parse/ColumnStatsAutoGatherContext.java | 127 +-
.../ql/parse/ColumnStatsSemanticAnalyzer.java | 121 +-
.../hadoop/hive/ql/parse/SemanticAnalyzer.java | 61 +-
.../hadoop/hive/ql/plan/CreateViewDesc.java | 7 +
.../cbo_rp_cross_product_check_2.q | 6 +-
ql/src/test/queries/clientpositive/llap_acid2.q | 17 +-
.../materialized_view_create_rewrite.q | 2 -
.../materialized_view_create_rewrite_2.q | 4 -
.../materialized_view_create_rewrite_3.q | 8 -
.../materialized_view_create_rewrite_4.q | 14 +-
.../materialized_view_create_rewrite_5.q | 7 -
.../materialized_view_create_rewrite_dummy.q | 2 -
.../materialized_view_create_rewrite_multi_db.q | 2 -
...rialized_view_create_rewrite_rebuild_dummy.q | 8 -
...terialized_view_create_rewrite_time_window.q | 6 -
...rialized_view_create_rewrite_time_window_2.q | 3 -
.../materialized_view_rewrite_1.q | 14 -
.../materialized_view_rewrite_10.q | 6 -
.../materialized_view_rewrite_2.q | 10 -
.../materialized_view_rewrite_3.q | 8 -
.../materialized_view_rewrite_4.q | 11 -
.../materialized_view_rewrite_5.q | 17 -
.../materialized_view_rewrite_6.q | 9 -
.../materialized_view_rewrite_7.q | 7 -
.../materialized_view_rewrite_8.q | 2 -
.../materialized_view_rewrite_9.q | 3 -
.../materialized_view_rewrite_empty.q | 1 -
.../materialized_view_rewrite_no_join_opt.q | 8 -
.../materialized_view_rewrite_no_join_opt_2.q | 11 -
.../materialized_view_rewrite_part_1.q | 11 -
.../materialized_view_rewrite_part_2.q | 10 -
.../materialized_view_rewrite_ssb.q | 6 -
.../materialized_view_rewrite_ssb_2.q | 6 -
.../results/clientnegative/masking_mv.q.out | 31 +-
.../alter_table_update_status.q.out | 8 +-
..._table_update_status_disable_bitvector.q.out | 4 +-
.../clientpositive/autoColumnStats_4.q.out | 1 +
.../materialized_view_create_rewrite.q.out | 14 +-
.../cbo_rp_cross_product_check_2.q.out | 44 +-
ql/src/test/results/clientpositive/ctas.q.out | 255 +-
.../results/clientpositive/ctas_colname.q.out | 339 ++-
.../ctas_uses_database_location.q.out | 33 +-
.../results/clientpositive/decimal_serde.q.out | 4 +-
.../clientpositive/druid/druidmini_mv.q.out | 64 +-
.../results/clientpositive/explain_ddl.q.out | 124 +-
.../clientpositive/groupby_duplicate_key.q.out | 49 +-
.../results/clientpositive/input1_limit.q.out | 2 +
.../results/clientpositive/input3_limit.q.out | 1 +
.../results/clientpositive/input_part10.q.out | 1 +
.../insert2_overwrite_partitions.q.out | 2 +
.../results/clientpositive/insert_into1.q.out | 3 +
.../results/clientpositive/insert_into2.q.out | 3 +
.../results/clientpositive/insert_into3.q.out | 4 +
.../results/clientpositive/insert_into4.q.out | 2 +
.../results/clientpositive/insert_into5.q.out | 1 +
.../results/clientpositive/insert_into6.q.out | 1 +
ql/src/test/results/clientpositive/join42.q.out | 233 +-
.../clientpositive/join_filters_overlap.q.out | 20 +-
.../limit_pushdown_negative.q.out | 1 +
.../llap/convert_decimal64_to_decimal.q.out | 48 +-
.../clientpositive/llap/cross_prod_1.q.out | 206 +-
.../clientpositive/llap/cross_prod_3.q.out | 14 +-
.../clientpositive/llap/cross_prod_4.q.out | 16 +-
.../llap/cross_product_check_1.q.out | 150 +-
.../llap/cross_product_check_2.q.out | 144 +-
.../test/results/clientpositive/llap/ctas.q.out | 195 +-
.../test/results/clientpositive/llap/dpp.q.out | 100 +-
.../llap/dynamic_partition_pruning.q.out | 1019 +++----
.../llap/dynamic_semijoin_reduction.q.out | 24 +-
.../llap/dynamic_semijoin_reduction_3.q.out | 48 -
.../llap/dynpart_sort_opt_vectorization.q.out | 4 +
.../llap/dynpart_sort_optimization.q.out | 5 +
.../clientpositive/llap/empty_join.q.out | 4 +-
.../llap/enforce_constraint_notnull.q.out | 122 +-
.../clientpositive/llap/explainuser_1.q.out | 118 +-
.../llap/insert1_overwrite_partitions.q.out | 3 +
.../clientpositive/llap/insert_into1.q.out | 3 +
.../clientpositive/llap/insert_into2.q.out | 3 +
.../llap/insert_into_default_keyword.q.out | 24 -
.../results/clientpositive/llap/lineage2.q.out | 10 +-
.../results/clientpositive/llap/lineage3.q.out | 2 +-
.../clientpositive/llap/llap_acid2.q.out | 570 ++--
.../clientpositive/llap/llap_nullscan.q.out | 78 +-
.../clientpositive/llap/llap_partitioned.q.out | 12 +-
.../results/clientpositive/llap/llap_udf.q.out | 39 +-
.../clientpositive/llap/llapdecider.q.out | 39 +-
.../llap/materialized_view_create.q.out | 6 +-
.../llap/materialized_view_create_rewrite.q.out | 24 +-
.../materialized_view_create_rewrite_2.q.out | 62 +-
.../materialized_view_create_rewrite_3.q.out | 109 +-
.../materialized_view_create_rewrite_4.q.out | 232 +-
.../materialized_view_create_rewrite_5.q.out | 50 +-
...materialized_view_create_rewrite_dummy.q.out | 24 +-
...erialized_view_create_rewrite_multi_db.q.out | 14 +-
...ized_view_create_rewrite_rebuild_dummy.q.out | 111 +-
...alized_view_create_rewrite_time_window.q.out | 105 +-
...ized_view_create_rewrite_time_window_2.q.out | 34 +-
.../llap/materialized_view_describe.q.out | 10 +-
.../llap/materialized_view_partitioned.q.out | 107 +-
.../llap/materialized_view_partitioned_3.q.out | 51 +-
.../llap/materialized_view_rewrite_1.q.out | 140 -
.../llap/materialized_view_rewrite_10.q.out | 60 -
.../llap/materialized_view_rewrite_2.q.out | 102 +-
.../llap/materialized_view_rewrite_3.q.out | 80 -
.../llap/materialized_view_rewrite_4.q.out | 110 -
.../llap/materialized_view_rewrite_5.q.out | 178 +-
.../llap/materialized_view_rewrite_6.q.out | 90 -
.../llap/materialized_view_rewrite_7.q.out | 70 -
.../llap/materialized_view_rewrite_8.q.out | 20 -
.../llap/materialized_view_rewrite_9.q.out | 30 -
.../llap/materialized_view_rewrite_empty.q.out | 10 -
.../materialized_view_rewrite_no_join_opt.q.out | 80 -
...aterialized_view_rewrite_no_join_opt_2.q.out | 186 --
.../llap/materialized_view_rewrite_part_1.q.out | 186 --
.../llap/materialized_view_rewrite_part_2.q.out | 138 +-
.../llap/materialized_view_rewrite_ssb.q.out | 284 +-
.../llap/materialized_view_rewrite_ssb_2.q.out | 286 +-
.../llap/multi_insert_lateral_view.q.out | 440 +--
.../llap/orc_llap_nonvector.q.out | 16 +-
.../clientpositive/llap/partition_ctas.q.out | 45 +-
.../clientpositive/llap/rcfile_createas1.q.out | 39 +-
.../clientpositive/llap/results_cache_1.q.out | 26 +-
.../llap/results_cache_invalidation2.q.out | 32 +-
.../llap/results_cache_with_masking.q.out | 24 +-
.../llap/runtime_stats_merge.q.out | 32 +-
.../results/clientpositive/llap/semijoin.q.out | 524 ++--
.../clientpositive/llap/semijoin_hint.q.out | 48 -
.../results/clientpositive/llap/sqlmerge.q.out | 24 -
.../clientpositive/llap/sqlmerge_stats.q.out | 168 --
.../clientpositive/llap/subquery_scalar.q.out | 2 +
.../clientpositive/llap/subquery_select.q.out | 26 +-
.../results/clientpositive/llap/tez_dml.q.out | 73 +-
.../clientpositive/llap/tez_nway_join.q.out | 122 +-
.../llap/tez_smb_reduce_side.q.out | 30 +-
.../clientpositive/llap/unionDistinct_1.q.out | 1048 +++----
.../clientpositive/llap/union_top_level.q.out | 85 +-
.../llap/vector_between_columns.q.out | 38 +-
.../clientpositive/llap/vector_between_in.q.out | 166 +-
.../llap/vector_case_when_1.q.out | 18 +-
.../llap/vector_char_mapjoin1.q.out | 214 +-
.../llap/vector_char_varchar_1.q.out | 136 +-
.../clientpositive/llap/vector_count.q.out | 48 +-
.../llap/vector_decimal_10_0.q.out | 10 +-
.../clientpositive/llap/vector_decimal_6.q.out | 47 +-
.../llap/vector_decimal_aggregate.q.out | 64 +-
.../llap/vector_decimal_cast.q.out | 10 +-
.../llap/vector_decimal_math_funcs.q.out | 16 +-
.../clientpositive/llap/vector_groupby4.q.out | 26 +-
.../clientpositive/llap/vector_groupby6.q.out | 26 +-
.../llap/vector_groupby_grouping_id1.q.out | 84 +-
.../llap/vector_groupby_grouping_id2.q.out | 212 +-
.../llap/vector_groupby_grouping_id3.q.out | 32 +-
.../llap/vector_groupby_grouping_sets1.q.out | 94 +-
.../llap/vector_groupby_grouping_sets2.q.out | 54 +-
.../llap/vector_groupby_grouping_sets3.q.out | 46 +-
.../vector_groupby_grouping_sets3_dec.q.out | 46 +-
.../llap/vector_groupby_grouping_sets4.q.out | 94 +-
.../llap/vector_groupby_grouping_sets5.q.out | 64 +-
.../llap/vector_groupby_grouping_sets6.q.out | 24 +-
.../vector_groupby_grouping_sets_grouping.q.out | 222 +-
.../vector_groupby_grouping_sets_limit.q.out | 128 +-
.../llap/vector_grouping_sets.q.out | 40 +-
.../clientpositive/llap/vector_if_expr_2.q.out | 10 +-
.../llap/vector_include_no_sel.q.out | 22 +-
.../llap/vector_interval_mapjoin.q.out | 20 +-
.../clientpositive/llap/vector_join30.q.out | 398 +--
.../llap/vector_join_filters.q.out | 120 +-
.../clientpositive/llap/vector_join_nulls.q.out | 110 +-
.../llap/vector_leftsemi_mapjoin.q.out | 2724 +++++++++---------
.../clientpositive/llap/vector_like_2.q.out | 10 +-
.../llap/vector_llap_io_data_conversion.q.out | 10 +-
.../llap/vector_nullsafe_join.q.out | 200 +-
.../llap/vector_number_compare_projection.q.out | 24 +-
.../llap/vector_partitioned_date_time.q.out | 60 +-
.../llap/vector_reduce_groupby_decimal.q.out | 20 +-
.../clientpositive/llap/vector_udf2.q.out | 16 +-
.../llap/vector_varchar_mapjoin1.q.out | 162 +-
.../llap/vector_windowing_navfn.q.out | 48 +-
.../llap/vector_windowing_streaming.q.out | 82 +-
.../llap/vectorization_decimal_date.q.out | 10 +-
.../llap/vectorization_short_regress.q.out | 60 +-
.../vectorized_dynamic_partition_pruning.q.out | 993 ++++---
.../vectorized_dynamic_semijoin_reduction.q.out | 266 +-
.../llap/vectorized_mapjoin3.q.out | 72 +-
.../clientpositive/load_dyn_part14.q.out | 3 +
.../results/clientpositive/masking_mv.q.out | 66 +-
ql/src/test/results/clientpositive/merge3.q.out | 57 +-
ql/src/test/results/clientpositive/merge4.q.out | 2 +
.../results/clientpositive/mm_default.q.out | 4 +-
.../clientpositive/named_column_join.q.out | 2 +-
.../results/clientpositive/nonmr_fetch.q.out | 49 +-
.../nonreserved_keywords_insert_into1.q.out | 3 +
.../results/clientpositive/nullformatCTAS.q.out | 31 +-
.../results/clientpositive/orc_createas1.q.out | 60 +
.../clientpositive/parallel_orderby.q.out | 29 +-
.../clientpositive/perf/spark/query70.q.out | 1 +
.../perf/tez/constraints/query70.q.out | 106 +-
.../clientpositive/perf/tez/query70.q.out | 142 +-
.../clientpositive/rcfile_default_format.q.out | 8 +-
.../sample_islocalmode_hook_use_metadata.q.out | 2 +-
.../show_materialized_views.q.out | 8 +-
.../clientpositive/skewjoin_noskew.q.out | 63 +-
.../clientpositive/skewjoin_onesideskew.q.out | 78 +-
.../results/clientpositive/smb_mapjoin9.q.out | 25 +
.../clientpositive/spark/subquery_scalar.q.out | 2 +
.../clientpositive/spark/subquery_select.q.out | 17 +-
ql/src/test/results/clientpositive/stats5.q.out | 2 +-
.../clientpositive/tez/explainanalyze_1.q.out | 31 +-
.../clientpositive/tez/explainanalyze_3.q.out | 39 +-
.../clientpositive/tez/explainanalyze_5.q.out | 8 +-
.../clientpositive/tez/explainuser_3.q.out | 33 +-
.../results/clientpositive/udtf_explode.q.out | 4 +
.../test/results/clientpositive/union24.q.out | 48 +-
.../test/results/clientpositive/union25.q.out | 55 +-
.../clientpositive/vector_decimal_6.q.out | 24 +
219 files changed, 9418 insertions(+), 9589 deletions(-)
----------------------------------------------------------------------
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/itests/hcatalog-unit/src/test/java/org/apache/hive/hcatalog/listener/TestDbNotificationListener.java
----------------------------------------------------------------------
diff --git a/itests/hcatalog-unit/src/test/java/org/apache/hive/hcatalog/listener/TestDbNotificationListener.java b/itests/hcatalog-unit/src/test/java/org/apache/hive/hcatalog/listener/TestDbNotificationListener.java
index be4f9ae..9eacfd8 100644
--- a/itests/hcatalog-unit/src/test/java/org/apache/hive/hcatalog/listener/TestDbNotificationListener.java
+++ b/itests/hcatalog-unit/src/test/java/org/apache/hive/hcatalog/listener/TestDbNotificationListener.java
@@ -1280,12 +1280,12 @@ public class TestDbNotificationListener {
driver.run("create table " + sourceTblName + " (c int)");
// Event 2 (alter: marker stats event), 3 (insert), 4 (alter: stats update event)
driver.run("insert into table " + sourceTblName + " values (1)");
- // Event 5, 6 (alter: stats update event)
+ // Event 5, 6 (alter), 7 (alter: stats update event)
driver.run("create table " + targetTblName + " as select c from " + sourceTblName);
// Get notifications from metastore
NotificationEventResponse rsp = msClient.getNextNotification(firstEventId, 0, null);
- assertEquals(7, rsp.getEventsSize());
+ assertEquals(8, rsp.getEventsSize());
NotificationEvent event = rsp.getEvents().get(0);
assertEquals(firstEventId + 1, event.getEventId());
assertEquals(EventType.CREATE_TABLE.toString(), event.getEventType());
@@ -1299,7 +1299,7 @@ public class TestDbNotificationListener {
event = rsp.getEvents().get(5);
assertEquals(firstEventId + 6, event.getEventId());
assertEquals(EventType.CREATE_TABLE.toString(), event.getEventType());
- testEventCounts(defaultDbName, firstEventId, null, null, 7);
+ testEventCounts(defaultDbName, firstEventId, null, null, 8);
}
@Test
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/itests/hive-unit/src/test/java/org/apache/hadoop/hive/hooks/TestHs2Hooks.java
----------------------------------------------------------------------
diff --git a/itests/hive-unit/src/test/java/org/apache/hadoop/hive/hooks/TestHs2Hooks.java b/itests/hive-unit/src/test/java/org/apache/hadoop/hive/hooks/TestHs2Hooks.java
index d26af3b..509b178 100644
--- a/itests/hive-unit/src/test/java/org/apache/hadoop/hive/hooks/TestHs2Hooks.java
+++ b/itests/hive-unit/src/test/java/org/apache/hadoop/hive/hooks/TestHs2Hooks.java
@@ -147,6 +147,7 @@ public class TestHs2Hooks {
hiveConf.setVar(ConfVars.SEMANTIC_ANALYZER_HOOK,
SemanticAnalysisHook.class.getName());
hiveConf.setBoolVar(ConfVars.HIVE_SUPPORT_CONCURRENCY, false);
+ hiveConf.setBoolVar(ConfVars.HIVESTATSCOLAUTOGATHER, false);
hiveServer2 = new HiveServer2();
hiveServer2.init(hiveConf);
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/java/org/apache/hadoop/hive/ql/optimizer/LimitPushdownOptimizer.java
----------------------------------------------------------------------
diff --git a/ql/src/java/org/apache/hadoop/hive/ql/optimizer/LimitPushdownOptimizer.java b/ql/src/java/org/apache/hadoop/hive/ql/optimizer/LimitPushdownOptimizer.java
index 859c18f..1dbe160 100644
--- a/ql/src/java/org/apache/hadoop/hive/ql/optimizer/LimitPushdownOptimizer.java
+++ b/ql/src/java/org/apache/hadoop/hive/ql/optimizer/LimitPushdownOptimizer.java
@@ -133,9 +133,17 @@ public class LimitPushdownOptimizer extends Transform {
}
}
if (rs != null) {
- if (OperatorUtils.findOperators(rs, GroupByOperator.class).size() > 1){
- // Not safe to continue for RS-GBY-GBY-LIM kind of pipelines. See HIVE-10607 for more.
- return false;
+ Operator<?> currentOp = rs;
+ boolean foundGroupByOperator = false;
+ while (currentOp != nd) { // nd = limitOp
+ if (currentOp instanceof GroupByOperator) {
+ if (foundGroupByOperator) {
+ // Not safe to continue for RS-GBY-GBY-LIM kind of pipelines. See HIVE-10607 for more.
+ return false;
+ }
+ foundGroupByOperator = true;
+ }
+ currentOp = currentOp.getChildOperators().get(0);
}
LimitOperator limit = (LimitOperator) nd;
LimitDesc limitDesc = limit.getConf();
@@ -175,9 +183,17 @@ public class LimitPushdownOptimizer extends Transform {
}
}
if (pRS != null) {
- if (OperatorUtils.findOperators(pRS, GroupByOperator.class).size() > 1){
- // Not safe to continue for RS-GBY-GBY-LIM kind of pipelines. See HIVE-10607 for more.
- return false;
+ Operator<?> currentOp = pRS;
+ boolean foundGroupByOperator = false;
+ while (currentOp != nd) { // nd = cRS
+ if (currentOp instanceof GroupByOperator) {
+ if (foundGroupByOperator) {
+ // Not safe to continue for RS-GBY-GBY-LIM kind of pipelines. See HIVE-10607 for more.
+ return false;
+ }
+ foundGroupByOperator = true;
+ }
+ currentOp = currentOp.getChildOperators().get(0);
}
List<ExprNodeDesc> cKeys = cRS.getConf().getKeyCols();
List<ExprNodeDesc> pKeys = pRS.getConf().getKeyCols();
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/java/org/apache/hadoop/hive/ql/parse/BaseSemanticAnalyzer.java
----------------------------------------------------------------------
diff --git a/ql/src/java/org/apache/hadoop/hive/ql/parse/BaseSemanticAnalyzer.java b/ql/src/java/org/apache/hadoop/hive/ql/parse/BaseSemanticAnalyzer.java
index 3a51d97..833757c 100644
--- a/ql/src/java/org/apache/hadoop/hive/ql/parse/BaseSemanticAnalyzer.java
+++ b/ql/src/java/org/apache/hadoop/hive/ql/parse/BaseSemanticAnalyzer.java
@@ -1636,7 +1636,7 @@ public abstract class BaseSemanticAnalyzer {
}
}
- public class AnalyzeRewriteContext {
+ public static class AnalyzeRewriteContext {
private String tableName;
private List<String> colName;
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/java/org/apache/hadoop/hive/ql/parse/ColumnStatsAutoGatherContext.java
----------------------------------------------------------------------
diff --git a/ql/src/java/org/apache/hadoop/hive/ql/parse/ColumnStatsAutoGatherContext.java b/ql/src/java/org/apache/hadoop/hive/ql/parse/ColumnStatsAutoGatherContext.java
index 11ccff4..acd2b6d 100644
--- a/ql/src/java/org/apache/hadoop/hive/ql/parse/ColumnStatsAutoGatherContext.java
+++ b/ql/src/java/org/apache/hadoop/hive/ql/parse/ColumnStatsAutoGatherContext.java
@@ -25,6 +25,7 @@ import java.util.List;
import java.util.Map;
import org.apache.hadoop.hive.conf.HiveConf;
+import org.apache.hadoop.hive.conf.HiveConf.ConfVars;
import org.apache.hadoop.hive.metastore.api.FieldSchema;
import org.apache.hadoop.hive.ql.Context;
import org.apache.hadoop.hive.ql.QueryState;
@@ -32,6 +33,8 @@ import org.apache.hadoop.hive.ql.exec.ColumnInfo;
import org.apache.hadoop.hive.ql.exec.Operator;
import org.apache.hadoop.hive.ql.exec.RowSchema;
import org.apache.hadoop.hive.ql.exec.SelectOperator;
+import org.apache.hadoop.hive.ql.exec.UDTFOperator;
+import org.apache.hadoop.hive.ql.exec.Utilities;
import org.apache.hadoop.hive.ql.metadata.HiveException;
import org.apache.hadoop.hive.ql.metadata.Table;
import org.apache.hadoop.hive.ql.parse.BaseSemanticAnalyzer.AnalyzeRewriteContext;
@@ -47,10 +50,9 @@ import org.apache.hadoop.hive.serde2.typeinfo.TypeInfo;
/**
* ColumnStatsAutoGatherContext: This is passed to the compiler when set
- * hive.stats.autogather=true during the INSERT OVERWRITE command.
- *
- **/
-
+ * hive.stats.autogather=true during the INSERT, INSERT OVERWRITE, or CTAS
+ * commands.
+ */
public class ColumnStatsAutoGatherContext {
public AnalyzeRewriteContext analyzeRewrite;
@@ -92,79 +94,134 @@ public class ColumnStatsAutoGatherContext {
this.analyzeRewrite = analyzeRewrite;
}
+ /**
+ * Generate the statement of analyze table [tablename] compute statistics for columns
+ * In non-partitioned table case, it will generate TS-SEL-GBY-RS-GBY-SEL-FS operator
+ * In static-partitioned table case, it will generate TS-FIL(partitionKey)-SEL-GBY(partitionKey)-RS-GBY-SEL-FS operator
+ * In dynamic-partitioned table case, it will generate TS-SEL-GBY(partitionKey)-RS-GBY-SEL-FS operator
+ * However, we do not need to specify the partition-spec because (1) the data is going to be inserted to that specific partition
+ * (2) we can compose the static/dynamic partition using a select operator in replaceSelectOperatorProcess.
+ */
public void insertAnalyzePipeline() throws SemanticException{
- // 1. Generate the statement of analyze table [tablename] compute statistics for columns
- // In non-partitioned table case, it will generate TS-SEL-GBY-RS-GBY-SEL-FS operator
- // In static-partitioned table case, it will generate TS-FIL(partitionKey)-SEL-GBY(partitionKey)-RS-GBY-SEL-FS operator
- // In dynamic-partitioned table case, it will generate TS-SEL-GBY(partitionKey)-RS-GBY-SEL-FS operator
- // However, we do not need to specify the partition-spec because (1) the data is going to be inserted to that specific partition
- // (2) we can compose the static/dynamic partition using a select operator in replaceSelectOperatorProcess..
String analyzeCommand = "analyze table `" + tbl.getDbName() + "`.`" + tbl.getTableName() + "`"
+ " compute statistics for columns ";
+ insertAnalyzePipeline(analyzeCommand, false);
+ }
- // 2. Based on the statement, generate the selectOperator
+ /**
+ * Generate the statement of SELECT compute_stats(col1) compute_stats(col2),...,
+ * similar to the one generated from ANALYZE TABLE t1 COMPUTE STATISTICS FOR COLUMNS,
+ * but t1 is replaced by a TABLE(VALUES(cast(null as int),cast(null as string))) AS t1(col1,col2).
+ *
+ * We use TABLE-VALUES statement for computing stats for CTAS statement because in those cases
+ * the table has not been created yet. Once the plan for the SELECT statement is generated,
+ * we connect it to the existing CTAS plan as we do for INSERT or INSERT OVERWRITE.
+ */
+ public void insertTableValuesAnalyzePipeline() throws SemanticException {
+ // Instead of starting from analyze statement, we just generate the Select plan
+ boolean isPartitionStats = conf.getBoolVar(ConfVars.HIVE_STATS_COLLECT_PART_LEVEL_STATS) && tbl.isPartitioned();
+ if (isPartitionStats) {
+ partSpec = new HashMap<>();
+ List<String> partKeys = Utilities.getColumnNamesFromFieldSchema(tbl.getPartitionKeys());
+ for (String partKey : partKeys) {
+ partSpec.put(partKey, null);
+ }
+ }
+ String command = ColumnStatsSemanticAnalyzer.genRewrittenQuery(
+ tbl, Utilities.getColumnNamesFromFieldSchema(tbl.getCols()), conf, partSpec, isPartitionStats, true);
+ insertAnalyzePipeline(command, true);
+ }
+
+ private void insertAnalyzePipeline(String command, boolean rewritten) throws SemanticException {
+ // 1. Based on the statement, generate the selectOperator
Operator<?> selOp = null;
try {
- selOp = genSelOpForAnalyze(analyzeCommand, origCtx);
+ selOp = genSelOp(command, rewritten, origCtx);
} catch (IOException | ParseException e) {
throw new SemanticException(e);
}
- // 3. attach this SEL to the operator right before FS
+ // 2. attach this SEL to the operator right before FS
op.getChildOperators().add(selOp);
selOp.getParentOperators().clear();
selOp.getParentOperators().add(op);
- // 4. address the colExp, colList, etc for the SEL
+ // 3. address the colExp, colList, etc for the SEL
try {
replaceSelectOperatorProcess((SelectOperator)selOp, op);
} catch (HiveException e) {
throw new SemanticException(e);
}
}
-
- @SuppressWarnings("rawtypes")
- private Operator genSelOpForAnalyze(String analyzeCommand, Context origCtx) throws IOException, ParseException, SemanticException{
- //0. initialization
+
+ private Operator genSelOp(String command, boolean rewritten, Context origCtx)
+ throws IOException, ParseException, SemanticException {
+ // 1. initialization
Context ctx = new Context(conf);
ctx.setOpContext(origCtx.getOpContext());
ctx.setExplainConfig(origCtx.getExplainConfig());
- ASTNode tree = ParseUtils.parse(analyzeCommand, ctx);
- //1. get the ColumnStatsSemanticAnalyzer
- QueryState queryState = new QueryState.Builder().withHiveConf(conf).build();
- BaseSemanticAnalyzer baseSem = SemanticAnalyzerFactory.get(queryState, tree);
- ColumnStatsSemanticAnalyzer colSem = (ColumnStatsSemanticAnalyzer) baseSem;
+ // 2. parse tree and create semantic analyzer. if we need to rewrite the analyze
+ // statement, we do it now
+ final ASTNode ast;
+ final SemanticAnalyzer sem;
+ final QueryState queryState = new QueryState.Builder().withHiveConf(conf).build();
+ if (rewritten) {
+ // Create the context object that is needed to store the column stats
+ this.analyzeRewrite = ColumnStatsSemanticAnalyzer.genAnalyzeRewriteContext(conf, tbl);
+
+ // The analyze statement has already been rewritten, we just need to create the AST
+ // and the corresponding semantic analyzer
+ ast = ParseUtils.parse(command, ctx);
+ BaseSemanticAnalyzer baseSem = SemanticAnalyzerFactory.get(queryState, ast);
+ sem = (SemanticAnalyzer) baseSem;
+ } else {
+ // We need to rewrite the analyze command and get the rewritten AST
+ ASTNode analyzeTree = ParseUtils.parse(command, ctx);
+ BaseSemanticAnalyzer baseSem = SemanticAnalyzerFactory.get(queryState, analyzeTree);
+ ColumnStatsSemanticAnalyzer colSem = (ColumnStatsSemanticAnalyzer) baseSem;
+ ast = colSem.rewriteAST(analyzeTree, this);
- //2. get the rewritten AST
- ASTNode ast = colSem.rewriteAST(tree, this);
- baseSem = SemanticAnalyzerFactory.get(queryState, ast);
- SemanticAnalyzer sem = (SemanticAnalyzer) baseSem;
+ // Obtain the context object that is needed to store the column stats
+ this.analyzeRewrite = colSem.getAnalyzeRewriteContext();
+
+ // Analyze the rewritten statement
+ baseSem = SemanticAnalyzerFactory.get(queryState, ast);
+ sem = (SemanticAnalyzer) baseSem;
+ }
QB qb = new QB(null, null, false);
ASTNode child = ast;
- ParseContext subPCtx = ((SemanticAnalyzer) sem).getParseContext();
+ ParseContext subPCtx = sem.getParseContext();
subPCtx.setContext(ctx);
- ((SemanticAnalyzer) sem).initParseCtx(subPCtx);
+ sem.initParseCtx(subPCtx);
sem.doPhase1(child, qb, sem.initPhase1Ctx(), null);
// This will trigger new calls to metastore to collect metadata
// TODO: cache the information from the metastore
sem.getMetaData(qb);
- Operator<?> operator = sem.genPlan(qb);
+ sem.genPlan(qb);
- //3. populate the load file work so that ColumnStatsTask can work
+ // 3. populate the load file work so that ColumnStatsTask can work
loadFileWork.addAll(sem.getLoadFileWork());
- //4. because there is only one TS for analyze statement, we can get it.
+ // 4. because there is only one TS for analyze statement, we can get it.
if (sem.topOps.values().size() != 1) {
throw new SemanticException(
"ColumnStatsAutoGatherContext is expecting exactly one TS, but finds "
+ sem.topOps.values().size());
}
- operator = sem.topOps.values().iterator().next();
+ Operator<?> operator = sem.topOps.values().iterator().next();
- //5. get the first SEL after TS
- while(!(operator instanceof SelectOperator)){
+ // 5. if this has been rewritten, get the SEL after UDTF;
+ // otherwise, get the first SEL after TS
+ if (rewritten) {
+ while (!(operator instanceof UDTFOperator)) {
+ operator = operator.getChildOperators().get(0);
+ }
operator = operator.getChildOperators().get(0);
+ } else {
+ while (!(operator instanceof SelectOperator)) {
+ operator = operator.getChildOperators().get(0);
+ }
}
return operator;
}
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/java/org/apache/hadoop/hive/ql/parse/ColumnStatsSemanticAnalyzer.java
----------------------------------------------------------------------
diff --git a/ql/src/java/org/apache/hadoop/hive/ql/parse/ColumnStatsSemanticAnalyzer.java b/ql/src/java/org/apache/hadoop/hive/ql/parse/ColumnStatsSemanticAnalyzer.java
index 9aff006..066807b 100644
--- a/ql/src/java/org/apache/hadoop/hive/ql/parse/ColumnStatsSemanticAnalyzer.java
+++ b/ql/src/java/org/apache/hadoop/hive/ql/parse/ColumnStatsSemanticAnalyzer.java
@@ -148,7 +148,8 @@ public class ColumnStatsSemanticAnalyzer extends SemanticAnalyzer {
}
}
- private StringBuilder genPartitionClause(Map<String, String> partSpec) throws SemanticException {
+ private static StringBuilder genPartitionClause(Table tbl, Map<String, String> partSpec)
+ throws SemanticException {
StringBuilder whereClause = new StringBuilder(" where ");
boolean predPresent = false;
StringBuilder groupByClause = new StringBuilder(" group by ");
@@ -162,7 +163,8 @@ public class ColumnStatsSemanticAnalyzer extends SemanticAnalyzer {
} else {
whereClause.append(" and ");
}
- whereClause.append("`").append(partKey).append("` = ").append(genPartValueString(getColTypeOf(partKey), value));
+ whereClause.append("`").append(partKey).append("` = ")
+ .append(genPartValueString(getColTypeOf(tbl, partKey), value));
}
}
@@ -181,8 +183,7 @@ public class ColumnStatsSemanticAnalyzer extends SemanticAnalyzer {
- private String getColTypeOf(String partKey) throws SemanticException{
-
+ private static String getColTypeOf(Table tbl, String partKey) throws SemanticException{
for (FieldSchema fs : tbl.getPartitionKeys()) {
if (partKey.equalsIgnoreCase(fs.getName())) {
return fs.getType().toLowerCase();
@@ -191,8 +192,7 @@ public class ColumnStatsSemanticAnalyzer extends SemanticAnalyzer {
throw new SemanticException("Unknown partition key : " + partKey);
}
- private List<String> getColumnTypes(List<String> colNames)
- throws SemanticException{
+ private static List<String> getColumnTypes(Table tbl, List<String> colNames) {
List<String> colTypes = new ArrayList<String>();
List<FieldSchema> cols = tbl.getCols();
List<String> copyColNames = new ArrayList<>(colNames);
@@ -215,21 +215,33 @@ public class ColumnStatsSemanticAnalyzer extends SemanticAnalyzer {
return colTypes;
}
- private String escapeBackTicks(String colName) {
+ private static String escapeBackTicks(String colName) {
return colName.replaceAll("`", "``");
}
private String genRewrittenQuery(List<String> colNames, HiveConf conf, Map<String, String> partSpec,
- boolean isPartitionStats) throws SemanticException{
+ boolean isPartitionStats, boolean useTableValues) throws SemanticException {
+ String rewrittenQuery = genRewrittenQuery(tbl, colNames, conf, partSpec, isPartitionStats, useTableValues);
+ isRewritten = true;
+ return rewrittenQuery;
+ }
+
+ public static String genRewrittenQuery(Table tbl, List<String> colNames, HiveConf conf, Map<String, String> partSpec,
+ boolean isPartitionStats, boolean useTableValues) throws SemanticException{
StringBuilder rewrittenQueryBuilder = new StringBuilder("select ");
+ StringBuilder columnNamesBuilder = new StringBuilder();
+ StringBuilder columnDummyValuesBuilder = new StringBuilder();
for (int i = 0; i < colNames.size(); i++) {
if (i > 0) {
rewrittenQueryBuilder.append(" , ");
+ columnNamesBuilder.append(" , ");
+ columnDummyValuesBuilder.append(" , ");
}
String func = HiveConf.getVar(conf, HiveConf.ConfVars.HIVE_STATS_NDV_ALGO).toLowerCase();
rewrittenQueryBuilder.append("compute_stats(`");
- rewrittenQueryBuilder.append(escapeBackTicks(colNames.get(i)));
+ final String columnName = escapeBackTicks(colNames.get(i));
+ rewrittenQueryBuilder.append(columnName);
rewrittenQueryBuilder.append("`, '" + func + "'");
if ("fm".equals(func)) {
int numBitVectors = 0;
@@ -241,23 +253,45 @@ public class ColumnStatsSemanticAnalyzer extends SemanticAnalyzer {
rewrittenQueryBuilder.append(", " + numBitVectors);
}
rewrittenQueryBuilder.append(')');
+
+ columnNamesBuilder.append("`" + columnName + "`");
+
+ columnDummyValuesBuilder.append(
+ "cast(null as " + TypeInfoUtils.getTypeInfoFromTypeString(tbl.getCols().get(i).getType()).toString() + ")");
}
if (isPartitionStats) {
for (FieldSchema fs : tbl.getPartCols()) {
- rewrittenQueryBuilder.append(" , `" + fs.getName() + "`");
+ final String partColumnName = " , `" + fs.getName() + "`";
+ rewrittenQueryBuilder.append(partColumnName);
+
+ columnNamesBuilder.append(partColumnName);
+
+ columnDummyValuesBuilder.append(
+ " , cast(null as " + TypeInfoUtils.getTypeInfoFromTypeString(fs.getType()).toString() + ")");
}
}
- rewrittenQueryBuilder.append(" from `");
- rewrittenQueryBuilder.append(tbl.getDbName());
- rewrittenQueryBuilder.append("`.");
- rewrittenQueryBuilder.append("`" + tbl.getTableName() + "`");
- isRewritten = true;
+
+ rewrittenQueryBuilder.append(" from ");
+ if (useTableValues) {
+ //TABLE(VALUES(cast(null as int),cast(null as string))) AS tablename(col1,col2)
+ rewrittenQueryBuilder.append("table(values(");
+ // Values
+ rewrittenQueryBuilder.append(columnDummyValuesBuilder.toString());
+ rewrittenQueryBuilder.append(")) as ");
+ rewrittenQueryBuilder.append("`" + tbl.getTableName() + "`");
+ rewrittenQueryBuilder.append("(");
+ // Columns
+ rewrittenQueryBuilder.append(columnNamesBuilder.toString());
+ rewrittenQueryBuilder.append(")");
+ } else {
+ rewrittenQueryBuilder.append("`" + tbl.getDbName() + "`.`" + tbl.getTableName() + "`");
+ }
// If partition level statistics is requested, add predicate and group by as needed to rewritten
// query
if (isPartitionStats) {
- rewrittenQueryBuilder.append(genPartitionClause(partSpec));
+ rewrittenQueryBuilder.append(genPartitionClause(tbl, partSpec));
}
String rewrittenQuery = rewrittenQueryBuilder.toString();
@@ -311,7 +345,7 @@ public class ColumnStatsSemanticAnalyzer extends SemanticAnalyzer {
}
}
- private void logTypeWarning(String colName, String colType) {
+ private static void logTypeWarning(String colName, String colType) {
String warning = "Only primitive type arguments are accepted but " + colType
+ " is passed for " + colName + ".";
warning = "WARNING: " + warning;
@@ -353,8 +387,8 @@ public class ColumnStatsSemanticAnalyzer extends SemanticAnalyzer {
} else {
isTableLevel = true;
}
- colType = getColumnTypes(colNames);
- rewrittenQuery = genRewrittenQuery(colNames, conf, partSpec, isPartitionStats);
+ colType = getColumnTypes(tbl, colNames);
+ rewrittenQuery = genRewrittenQuery(colNames, conf, partSpec, isPartitionStats, false);
rewrittenTree = genRewrittenTree(rewrittenQuery);
} else {
// Not an analyze table column compute statistics statement - don't do any rewrites
@@ -391,19 +425,19 @@ public class ColumnStatsSemanticAnalyzer extends SemanticAnalyzer {
/**
* @param ast
* is the original analyze ast
- * @param qb
- * is the qb that calls this function
- * @param sem
- * is the semantic analyzer that calls this function
+ * @param context
+ * the column stats auto gather context
* @return
* @throws SemanticException
*/
public ASTNode rewriteAST(ASTNode ast, ColumnStatsAutoGatherContext context)
throws SemanticException {
- tbl = AnalyzeCommandUtils.getTable(ast, this);
- colNames = getColumnName(ast);
// Save away the original AST
originalTree = ast;
+
+ tbl = AnalyzeCommandUtils.getTable(ast, this);
+
+ colNames = getColumnName(ast);
boolean isPartitionStats = AnalyzeCommandUtils.isPartitionLevelStats(ast);
Map<String, String> partSpec = null;
checkForPartitionColumns(colNames,
@@ -414,21 +448,38 @@ public class ColumnStatsSemanticAnalyzer extends SemanticAnalyzer {
}
if (isPartitionStats) {
- isTableLevel = false;
partSpec = AnalyzeCommandUtils.getPartKeyValuePairsFromAST(tbl, ast, conf);
handlePartialPartitionSpec(partSpec, context);
- } else {
- isTableLevel = true;
}
- colType = getColumnTypes(colNames);
- rewrittenQuery = genRewrittenQuery(colNames, conf, partSpec, isPartitionStats);
+
+ colType = getColumnTypes(tbl, colNames);
+
+ isTableLevel = !isPartitionStats;
+
+ rewrittenQuery = genRewrittenQuery(colNames, conf, partSpec, isPartitionStats, false);
rewrittenTree = genRewrittenTree(rewrittenQuery);
- context.analyzeRewrite = new AnalyzeRewriteContext();
- context.analyzeRewrite.setTableName(tbl.getFullyQualifiedName());
- context.analyzeRewrite.setTblLvl(isTableLevel);
- context.analyzeRewrite.setColName(colNames);
- context.analyzeRewrite.setColType(colType);
return rewrittenTree;
}
+
+ AnalyzeRewriteContext getAnalyzeRewriteContext() {
+ AnalyzeRewriteContext analyzeRewrite = new AnalyzeRewriteContext();
+ analyzeRewrite.setTableName(tbl.getFullyQualifiedName());
+ analyzeRewrite.setTblLvl(isTableLevel);
+ analyzeRewrite.setColName(colNames);
+ analyzeRewrite.setColType(colType);
+ return analyzeRewrite;
+ }
+
+ static AnalyzeRewriteContext genAnalyzeRewriteContext(HiveConf conf, Table tbl) {
+ AnalyzeRewriteContext analyzeRewrite = new AnalyzeRewriteContext();
+ analyzeRewrite.setTableName(tbl.getFullyQualifiedName());
+ analyzeRewrite.setTblLvl(!(conf.getBoolVar(ConfVars.HIVE_STATS_COLLECT_PART_LEVEL_STATS) && tbl.isPartitioned()));
+ List<String> colNames = Utilities.getColumnNamesFromFieldSchema(tbl.getCols());
+ List<String> colTypes = getColumnTypes(tbl, colNames);
+ analyzeRewrite.setColName(colNames);
+ analyzeRewrite.setColType(colTypes);
+ return analyzeRewrite;
+ }
+
}
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/java/org/apache/hadoop/hive/ql/parse/SemanticAnalyzer.java
----------------------------------------------------------------------
diff --git a/ql/src/java/org/apache/hadoop/hive/ql/parse/SemanticAnalyzer.java b/ql/src/java/org/apache/hadoop/hive/ql/parse/SemanticAnalyzer.java
index 5126a79..54f34f6 100644
--- a/ql/src/java/org/apache/hadoop/hive/ql/parse/SemanticAnalyzer.java
+++ b/ql/src/java/org/apache/hadoop/hive/ql/parse/SemanticAnalyzer.java
@@ -544,7 +544,7 @@ public class SemanticAnalyzer extends BaseSemanticAnalyzer {
return ctx.getOpContext();
}
- public String genPartValueString(String partColType, String partVal) throws SemanticException {
+ public static String genPartValueString(String partColType, String partVal) throws SemanticException {
String returnVal = partVal;
if (partColType.equals(serdeConstants.STRING_TYPE_NAME) ||
partColType.contains(serdeConstants.VARCHAR_TYPE_NAME) ||
@@ -7438,6 +7438,7 @@ public class SemanticAnalyzer extends BaseSemanticAnalyzer {
partitionColumnNames = viewDesc.getPartColNames();
fileSinkColInfos = new ArrayList<>();
destTableIsTemporary = false;
+ destTableIsMaterialization = false;
}
if (isLocal) {
@@ -7496,9 +7497,6 @@ public class SemanticAnalyzer extends BaseSemanticAnalyzer {
viewDesc.setPartCols(new ArrayList<>(partitionColumns));
}
- destTableIsTransactional = tblDesc != null && AcidUtils.isTransactionalTable(tblDesc);
- destTableIsFullAcid = tblDesc != null && AcidUtils.isFullAcidTable(tblDesc);
-
boolean isDestTempFile = true;
if (!ctx.isMRTmpFileURI(destinationPath.toUri().toString())) {
idToTableNameMap.put(String.valueOf(destTableId), destinationPath.toUri().toString());
@@ -7543,7 +7541,15 @@ public class SemanticAnalyzer extends BaseSemanticAnalyzer {
tableDescriptor = PlanUtils.getTableDesc(tblDesc, cols, colTypes);
}
- boolean isDfsDir = (destType.intValue() == QBMetaData.DEST_DFS_FILE);
+ boolean isDfsDir = (destType == QBMetaData.DEST_DFS_FILE);
+
+ try {
+ destinationTable = tblDesc != null ? tblDesc.toTable(conf) : viewDesc != null ? viewDesc.toTable(conf) : null;
+ } catch (HiveException e) {
+ throw new SemanticException(e);
+ }
+
+ destTableIsFullAcid = AcidUtils.isFullAcidTable(destinationTable);
if (isPartitioned) {
// Create a SELECT that may reorder the columns if needed
@@ -7565,12 +7571,6 @@ public class SemanticAnalyzer extends BaseSemanticAnalyzer {
.getColumnInfos()), input), rowResolver);
input.setColumnExprMap(colExprMap);
- try {
- destinationTable = tblDesc != null ? tblDesc.toTable(conf) : viewDesc.toTable(conf);
- } catch (HiveException e) {
- throw new SemanticException(e);
- }
-
// If this is a partitioned CTAS or MV statement, we are going to create a LoadTableDesc
// object. Although the table does not exist in metastore, we will swamp the CreateTableTask
// and MoveTask resulting from this LoadTable so in this specific case, first we create
@@ -7623,7 +7623,7 @@ public class SemanticAnalyzer extends BaseSemanticAnalyzer {
throw new SemanticException("Unknown destination type: " + destType);
}
- if (!(destType.intValue() == QBMetaData.DEST_DFS_FILE && qb.getIsQuery())) {
+ if (!(destType == QBMetaData.DEST_DFS_FILE && qb.getIsQuery())) {
input = genConversionSelectOperator(dest, qb, input, tableDescriptor, dpCtx);
}
@@ -7662,8 +7662,7 @@ public class SemanticAnalyzer extends BaseSemanticAnalyzer {
canBeMerged &= !destTableIsFullAcid;
// Generate the partition columns from the parent input
- if (destType.intValue() == QBMetaData.DEST_TABLE
- || destType.intValue() == QBMetaData.DEST_PARTITION) {
+ if (destType == QBMetaData.DEST_TABLE || destType == QBMetaData.DEST_PARTITION) {
genPartnCols(dest, input, qb, tableDescriptor, destinationTable, rsCtx);
}
@@ -7705,14 +7704,21 @@ public class SemanticAnalyzer extends BaseSemanticAnalyzer {
// and it is an insert overwrite or insert into table
if (conf.getBoolVar(ConfVars.HIVESTATSAUTOGATHER)
&& conf.getBoolVar(ConfVars.HIVESTATSCOLAUTOGATHER)
+ && destinationTable != null && !destinationTable.isNonNative()
+ && !destTableIsTemporary && !destTableIsMaterialization
&& ColumnStatsAutoGatherContext.canRunAutogatherStats(fso)) {
- // TODO: Column stats autogather does not work for CTAS statements
- if (destType.intValue() == QBMetaData.DEST_TABLE && !destinationTable.isNonNative()) {
- genAutoColumnStatsGatheringPipeline(qb, destinationTable, partSpec, input, qb.getParseInfo()
- .isInsertIntoTable(destinationTable.getDbName(), destinationTable.getTableName()));
- } else if (destType.intValue() == QBMetaData.DEST_PARTITION && !destinationTable.isNonNative()) {
- genAutoColumnStatsGatheringPipeline(qb, destinationTable, destinationPartition.getSpec(), input, qb
- .getParseInfo().isInsertIntoTable(destinationTable.getDbName(), destinationTable.getTableName()));
+ if (destType == QBMetaData.DEST_TABLE) {
+ genAutoColumnStatsGatheringPipeline(qb, destinationTable, partSpec, input,
+ qb.getParseInfo().isInsertIntoTable(destinationTable.getDbName(), destinationTable.getTableName()),
+ false);
+ } else if (destType == QBMetaData.DEST_PARTITION) {
+ genAutoColumnStatsGatheringPipeline(qb, destinationTable, destinationPartition.getSpec(), input,
+ qb.getParseInfo().isInsertIntoTable(destinationTable.getDbName(), destinationTable.getTableName()),
+ false);
+ } else if (destType == QBMetaData.DEST_LOCAL_FILE || destType == QBMetaData.DEST_DFS_FILE) {
+ // CTAS or CMV statement
+ genAutoColumnStatsGatheringPipeline(qb, destinationTable, null, input,
+ false, true);
}
}
return output;
@@ -8067,13 +8073,20 @@ public class SemanticAnalyzer extends BaseSemanticAnalyzer {
}
- private void genAutoColumnStatsGatheringPipeline(QB qb, Table table,
- Map<String, String> partSpec, Operator curr, boolean isInsertInto) throws SemanticException {
+ private void genAutoColumnStatsGatheringPipeline(QB qb, Table table, Map<String, String> partSpec,
+ Operator curr, boolean isInsertInto, boolean useTableValueConstructor)
+ throws SemanticException {
LOG.info("Generate an operator pipeline to autogather column stats for table " + table.getTableName()
+ " in query " + ctx.getCmd());
ColumnStatsAutoGatherContext columnStatsAutoGatherContext = null;
columnStatsAutoGatherContext = new ColumnStatsAutoGatherContext(this, conf, curr, table, partSpec, isInsertInto, ctx);
- columnStatsAutoGatherContext.insertAnalyzePipeline();
+ if (useTableValueConstructor) {
+ // Table does not exist, use table value constructor to simulate
+ columnStatsAutoGatherContext.insertTableValuesAnalyzePipeline();
+ } else {
+ // Table already exists
+ columnStatsAutoGatherContext.insertAnalyzePipeline();
+ }
columnStatsAutoGatherContexts.add(columnStatsAutoGatherContext);
}
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/java/org/apache/hadoop/hive/ql/plan/CreateViewDesc.java
----------------------------------------------------------------------
diff --git a/ql/src/java/org/apache/hadoop/hive/ql/plan/CreateViewDesc.java b/ql/src/java/org/apache/hadoop/hive/ql/plan/CreateViewDesc.java
index f0f7b18..7130aba 100644
--- a/ql/src/java/org/apache/hadoop/hive/ql/plan/CreateViewDesc.java
+++ b/ql/src/java/org/apache/hadoop/hive/ql/plan/CreateViewDesc.java
@@ -24,9 +24,11 @@ import java.util.Map;
import java.util.Set;
import org.apache.hadoop.fs.Path;
+import org.apache.hadoop.hive.common.StatsSetupConst;
import org.apache.hadoop.hive.conf.HiveConf;
import org.apache.hadoop.hive.metastore.TableType;
import org.apache.hadoop.hive.metastore.api.FieldSchema;
+import org.apache.hadoop.hive.metastore.utils.MetaStoreUtils;
import org.apache.hadoop.hive.ql.exec.DDLTask;
import org.apache.hadoop.hive.ql.exec.Utilities;
import org.apache.hadoop.hive.ql.metadata.HiveException;
@@ -410,6 +412,11 @@ public class CreateViewDesc extends DDLDesc implements Serializable {
}
}
+ // Sets the column state for the create view statement (false since it is a creation).
+ // Similar to logic in CreateTableDesc.
+ StatsSetupConst.setStatsStateForCreateTable(tbl.getTTable().getParameters(), null,
+ StatsSetupConst.FALSE);
+
return tbl;
}
}
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/queries/clientpositive/cbo_rp_cross_product_check_2.q
----------------------------------------------------------------------
diff --git a/ql/src/test/queries/clientpositive/cbo_rp_cross_product_check_2.q b/ql/src/test/queries/clientpositive/cbo_rp_cross_product_check_2.q
index 00c19c7..07c3522 100644
--- a/ql/src/test/queries/clientpositive/cbo_rp_cross_product_check_2.q
+++ b/ql/src/test/queries/clientpositive/cbo_rp_cross_product_check_2.q
@@ -4,10 +4,12 @@ set hive.cbo.returnpath.hiveop=true;
set hive.explain.user=false;
-- SORT_QUERY_RESULTS
-create table A_n18 as
+create table A_n18 (key string, value string);
+insert into A_n18
select * from src;
-create table B_n14 as
+create table B_n14 (key string, value string);
+insert into B_n14
select * from src order by key
limit 10;
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/queries/clientpositive/llap_acid2.q
----------------------------------------------------------------------
diff --git a/ql/src/test/queries/clientpositive/llap_acid2.q b/ql/src/test/queries/clientpositive/llap_acid2.q
index cd06d31..84ef485 100644
--- a/ql/src/test/queries/clientpositive/llap_acid2.q
+++ b/ql/src/test/queries/clientpositive/llap_acid2.q
@@ -40,7 +40,10 @@ select cint, cbigint, cfloat, cdouble,
cint as c1, cbigint as c2, cfloat as c3, cdouble as c4,
cint as c8, cbigint as c7, cfloat as c6, cdouble as c5,
cstring1, cfloat as c9, cast("1.123" as decimal(10,3))as c10,
- cast("1.123456789" as decimal(38,18)) as c11 from alltypesorc order by cdouble asc limit 30;
+ cast("1.123456789" as decimal(38,18)) as c11
+from alltypesorc
+order by cint, cbigint, cfloat, cdouble, cstring1
+limit 30;
alter table orc_llap_n2 set TBLPROPERTIES ('transactional'='true','orc.write.format'='0.12');
@@ -49,7 +52,10 @@ select cint, cbigint, cfloat, cdouble,
cint as c1, cbigint as c2, cfloat as c3, cdouble as c4,
cint as c8, cbigint as c7, cfloat as c6, cdouble as c5,
cstring1, cfloat as c9, cast("3.321" as decimal(10,3))as c10,
- cast("9.987654321" as decimal(38,18)) as c11 from alltypesorc order by cdouble asc limit 30;
+ cast("9.987654321" as decimal(38,18)) as c11
+from alltypesorc
+order by cint, cbigint, cfloat, cdouble, cstring1
+limit 30;
CREATE TABLE orc_llap2 (
@@ -76,7 +82,10 @@ select cint, cbigint, cfloat, cdouble,
cint as c1, cbigint as c2, cfloat as c3, cdouble as c4,
cint as c8, cbigint as c7, cfloat as c6, cdouble as c5,
cstring1, cfloat as c9, cast("1.123" as decimal(10,3))as c10,
- cast("1.123456789" as decimal(38,18)) as c11 from alltypesorc order by cdouble asc limit 30;
+ cast("1.123456789" as decimal(38,18)) as c11
+from alltypesorc
+order by cint, cbigint, cfloat, cdouble, cstring1
+limit 30;
alter table orc_llap2 set TBLPROPERTIES ('transactional'='true','orc.write.format'='0.12');
@@ -86,6 +95,8 @@ cdecimal2 = cast("9.987654321" as decimal(38,18)) where cstring1 = 'N016jPED08o
SET hive.llap.io.enabled=true;
+-- SORT_QUERY_RESULTS
+
select cstring1 from orc_llap_n2;
select cfloat2, cint from orc_llap_n2;
select * from orc_llap_n2;
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/queries/clientpositive/materialized_view_create_rewrite.q
----------------------------------------------------------------------
diff --git a/ql/src/test/queries/clientpositive/materialized_view_create_rewrite.q b/ql/src/test/queries/clientpositive/materialized_view_create_rewrite.q
index 9735e61..3b18932 100644
--- a/ql/src/test/queries/clientpositive/materialized_view_create_rewrite.q
+++ b/ql/src/test/queries/clientpositive/materialized_view_create_rewrite.q
@@ -15,8 +15,6 @@ insert into cmv_basetable_n10 values
(3, 'calvin', 978.76, 3),
(3, 'charlie', 9.8, 1);
-analyze table cmv_basetable_n10 compute statistics for columns;
-
create materialized view cmv_mat_view_n10
as select a, b, c from cmv_basetable_n10 where a = 2;
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/queries/clientpositive/materialized_view_create_rewrite_2.q
----------------------------------------------------------------------
diff --git a/ql/src/test/queries/clientpositive/materialized_view_create_rewrite_2.q b/ql/src/test/queries/clientpositive/materialized_view_create_rewrite_2.q
index 3f695d1..998aa49 100644
--- a/ql/src/test/queries/clientpositive/materialized_view_create_rewrite_2.q
+++ b/ql/src/test/queries/clientpositive/materialized_view_create_rewrite_2.q
@@ -13,8 +13,6 @@ insert into cmv_basetable_n9 values
(3, 'calvin', 978.76, 3),
(3, 'charlie', 9.8, 1);
-analyze table cmv_basetable_n9 compute statistics for columns;
-
create materialized view cmv_mat_view_n9
as select b from cmv_basetable_n9 where c > 10.0 group by a, b, c;
@@ -57,8 +55,6 @@ insert into cmv_basetable_2_n4 values
(1, 'alfred', 10.30, 2),
(3, 'calvin', 978.76, 3);
-analyze table cmv_basetable_2_n4 compute statistics for columns;
-
create materialized view cmv_mat_view_5
as select cmv_basetable_n9.a, cmv_basetable_2_n4.c
from cmv_basetable_n9 join cmv_basetable_2_n4 on (cmv_basetable_n9.a = cmv_basetable_2_n4.a)
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/queries/clientpositive/materialized_view_create_rewrite_3.q
----------------------------------------------------------------------
diff --git a/ql/src/test/queries/clientpositive/materialized_view_create_rewrite_3.q b/ql/src/test/queries/clientpositive/materialized_view_create_rewrite_3.q
index eb668a9..61d7c11 100644
--- a/ql/src/test/queries/clientpositive/materialized_view_create_rewrite_3.q
+++ b/ql/src/test/queries/clientpositive/materialized_view_create_rewrite_3.q
@@ -13,16 +13,12 @@ insert into cmv_basetable values
(3, 'calvin', 978.76, 3),
(3, 'charlie', 9.8, 1);
-analyze table cmv_basetable compute statistics for columns;
-
create table cmv_basetable_2 (a int, b varchar(256), c decimal(10,2), d int) stored as orc TBLPROPERTIES ('transactional'='true');
insert into cmv_basetable_2 values
(1, 'alfred', 10.30, 2),
(3, 'calvin', 978.76, 3);
-analyze table cmv_basetable_2 compute statistics for columns;
-
EXPLAIN
CREATE MATERIALIZED VIEW cmv_mat_view AS
SELECT cmv_basetable.a, cmv_basetable_2.c
@@ -51,8 +47,6 @@ GROUP BY cmv_basetable.a, cmv_basetable_2.c;
insert into cmv_basetable_2 values
(3, 'charlie', 15.8, 1);
-analyze table cmv_basetable_2 compute statistics for columns;
-
-- CANNOT USE THE VIEW, IT IS OUTDATED
EXPLAIN
SELECT cmv_basetable.a
@@ -119,8 +113,6 @@ insert into cmv_irrelevant_table values
(1, 'alfred', 10.30, 2),
(3, 'charlie', 9.8, 1);
-analyze table cmv_irrelevant_table compute statistics for columns;
-
-- IT CAN STILL BE USED
EXPLAIN
SELECT cmv_basetable.a
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/queries/clientpositive/materialized_view_create_rewrite_4.q
----------------------------------------------------------------------
diff --git a/ql/src/test/queries/clientpositive/materialized_view_create_rewrite_4.q b/ql/src/test/queries/clientpositive/materialized_view_create_rewrite_4.q
index f21db8a..a2754e1 100644
--- a/ql/src/test/queries/clientpositive/materialized_view_create_rewrite_4.q
+++ b/ql/src/test/queries/clientpositive/materialized_view_create_rewrite_4.q
@@ -13,16 +13,12 @@ insert into cmv_basetable_n5 values
(3, 'calvin', 978.76, 3),
(3, 'charlie', 9.8, 1);
-analyze table cmv_basetable_n5 compute statistics for columns;
-
create table cmv_basetable_2_n2 (a int, b varchar(256), c decimal(10,2), d int) stored as orc TBLPROPERTIES ('transactional'='true');
insert into cmv_basetable_2_n2 values
(1, 'alfred', 10.30, 2),
(3, 'calvin', 978.76, 3);
-analyze table cmv_basetable_2_n2 compute statistics for columns;
-
-- CREATE VIEW WITH REWRITE DISABLED
EXPLAIN
CREATE MATERIALIZED VIEW cmv_mat_view_n5 DISABLE REWRITE TBLPROPERTIES ('transactional'='true') AS
@@ -37,8 +33,6 @@ CREATE MATERIALIZED VIEW cmv_mat_view_n5 DISABLE REWRITE TBLPROPERTIES ('transac
WHERE cmv_basetable_2_n2.c > 10.0
GROUP BY cmv_basetable_n5.a, cmv_basetable_2_n2.c;
-analyze table cmv_mat_view_n5 compute statistics for columns;
-
DESCRIBE FORMATTED cmv_mat_view_n5;
-- CANNOT USE THE VIEW, IT IS DISABLED FOR REWRITE
@@ -56,8 +50,6 @@ GROUP BY cmv_basetable_n5.a, cmv_basetable_2_n2.c;
insert into cmv_basetable_2_n2 values
(3, 'charlie', 15.8, 1);
-analyze table cmv_basetable_2_n2 compute statistics for columns;
-
-- ENABLE FOR REWRITE
EXPLAIN
ALTER MATERIALIZED VIEW cmv_mat_view_n5 ENABLE REWRITE;
@@ -107,6 +99,8 @@ ALTER MATERIALIZED VIEW cmv_mat_view_n5 REBUILD;
ALTER MATERIALIZED VIEW cmv_mat_view_n5 REBUILD;
+DESCRIBE FORMATTED cmv_mat_view_n5;
+
-- MV CAN BE USED
EXPLAIN
SELECT cmv_basetable_n5.a, sum(cmv_basetable_2_n2.d)
@@ -128,6 +122,8 @@ ALTER MATERIALIZED VIEW cmv_mat_view_n5 REBUILD;
ALTER MATERIALIZED VIEW cmv_mat_view_n5 REBUILD;
+DESCRIBE FORMATTED cmv_mat_view_n5;
+
-- MV CAN BE USED
EXPLAIN
SELECT cmv_basetable_n5.a, sum(cmv_basetable_2_n2.d)
@@ -150,6 +146,8 @@ ALTER MATERIALIZED VIEW cmv_mat_view_n5 REBUILD;
ALTER MATERIALIZED VIEW cmv_mat_view_n5 REBUILD;
+DESCRIBE FORMATTED cmv_mat_view_n5;
+
-- MV CAN BE USED
EXPLAIN
SELECT cmv_basetable_n5.a, sum(cmv_basetable_2_n2.d)
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/queries/clientpositive/materialized_view_create_rewrite_5.q
----------------------------------------------------------------------
diff --git a/ql/src/test/queries/clientpositive/materialized_view_create_rewrite_5.q b/ql/src/test/queries/clientpositive/materialized_view_create_rewrite_5.q
index 3026d90..8fdc1da 100644
--- a/ql/src/test/queries/clientpositive/materialized_view_create_rewrite_5.q
+++ b/ql/src/test/queries/clientpositive/materialized_view_create_rewrite_5.q
@@ -13,28 +13,21 @@ insert into cmv_basetable_n6 values
(3, 'calvin', 978.76, 3),
(3, 'charlie', 9.8, 1);
-analyze table cmv_basetable_n6 compute statistics for columns;
-
create table cmv_basetable_2_n3 (a int, b varchar(256), c decimal(10,2), d int) stored as orc TBLPROPERTIES ('transactional'='true');
insert into cmv_basetable_2_n3 values
(1, 'alfred', 10.30, 2),
(3, 'calvin', 978.76, 3);
-analyze table cmv_basetable_2_n3 compute statistics for columns;
-
CREATE MATERIALIZED VIEW cmv_mat_view_n6
TBLPROPERTIES ('transactional'='true') AS
SELECT cmv_basetable_n6.a, cmv_basetable_2_n3.c
FROM cmv_basetable_n6 JOIN cmv_basetable_2_n3 ON (cmv_basetable_n6.a = cmv_basetable_2_n3.a)
WHERE cmv_basetable_2_n3.c > 10.0;
-analyze table cmv_mat_view_n6 compute statistics for columns;
insert into cmv_basetable_2_n3 values
(3, 'charlie', 15.8, 1);
-analyze table cmv_basetable_2_n3 compute statistics for columns;
-
-- CANNOT USE THE VIEW, IT IS OUTDATED
EXPLAIN
SELECT cmv_basetable_n6.a
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/queries/clientpositive/materialized_view_create_rewrite_dummy.q
----------------------------------------------------------------------
diff --git a/ql/src/test/queries/clientpositive/materialized_view_create_rewrite_dummy.q b/ql/src/test/queries/clientpositive/materialized_view_create_rewrite_dummy.q
index 8c9da8a..6978593 100644
--- a/ql/src/test/queries/clientpositive/materialized_view_create_rewrite_dummy.q
+++ b/ql/src/test/queries/clientpositive/materialized_view_create_rewrite_dummy.q
@@ -16,8 +16,6 @@ insert into cmv_basetable_n0 values
(3, 'calvin', 978.76, 3),
(3, 'charlie', 9.8, 1);
-analyze table cmv_basetable_n0 compute statistics for columns;
-
create materialized view cmv_mat_view_n0
as select a, b, c from cmv_basetable_n0 where a = 2;
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/queries/clientpositive/materialized_view_create_rewrite_multi_db.q
----------------------------------------------------------------------
diff --git a/ql/src/test/queries/clientpositive/materialized_view_create_rewrite_multi_db.q b/ql/src/test/queries/clientpositive/materialized_view_create_rewrite_multi_db.q
index 85d926f..6de65aa 100644
--- a/ql/src/test/queries/clientpositive/materialized_view_create_rewrite_multi_db.q
+++ b/ql/src/test/queries/clientpositive/materialized_view_create_rewrite_multi_db.q
@@ -17,8 +17,6 @@ insert into cmv_basetable_n7 values
(3, 'calvin', 978.76, 3),
(3, 'charlie', 9.8, 1);
-analyze table cmv_basetable_n7 compute statistics for columns;
-
create database db2;
use db2;
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/queries/clientpositive/materialized_view_create_rewrite_rebuild_dummy.q
----------------------------------------------------------------------
diff --git a/ql/src/test/queries/clientpositive/materialized_view_create_rewrite_rebuild_dummy.q b/ql/src/test/queries/clientpositive/materialized_view_create_rewrite_rebuild_dummy.q
index 72e3d65..e0dcf9a 100644
--- a/ql/src/test/queries/clientpositive/materialized_view_create_rewrite_rebuild_dummy.q
+++ b/ql/src/test/queries/clientpositive/materialized_view_create_rewrite_rebuild_dummy.q
@@ -13,16 +13,12 @@ insert into cmv_basetable_n1 values
(3, 'calvin', 978.76, 3),
(3, 'charlie', 9.8, 1);
-analyze table cmv_basetable_n1 compute statistics for columns;
-
create table cmv_basetable_2_n0 (a int, b varchar(256), c decimal(10,2), d int) stored as orc TBLPROPERTIES ('transactional'='true');
insert into cmv_basetable_2_n0 values
(1, 'alfred', 10.30, 2),
(3, 'calvin', 978.76, 3);
-analyze table cmv_basetable_2_n0 compute statistics for columns;
-
EXPLAIN
CREATE MATERIALIZED VIEW cmv_mat_view_n1 AS
SELECT cmv_basetable_n1.a, cmv_basetable_2_n0.c
@@ -51,8 +47,6 @@ GROUP BY cmv_basetable_n1.a, cmv_basetable_2_n0.c;
insert into cmv_basetable_2_n0 values
(3, 'charlie', 15.8, 1);
-analyze table cmv_basetable_2_n0 compute statistics for columns;
-
-- CANNOT USE THE VIEW, IT IS OUTDATED
EXPLAIN
SELECT cmv_basetable_n1.a
@@ -119,8 +113,6 @@ insert into cmv_irrelevant_table_n0 values
(1, 'alfred', 10.30, 2),
(3, 'charlie', 9.8, 1);
-analyze table cmv_irrelevant_table_n0 compute statistics for columns;
-
-- IT CAN STILL BE USED
EXPLAIN
SELECT cmv_basetable_n1.a
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/queries/clientpositive/materialized_view_create_rewrite_time_window.q
----------------------------------------------------------------------
diff --git a/ql/src/test/queries/clientpositive/materialized_view_create_rewrite_time_window.q b/ql/src/test/queries/clientpositive/materialized_view_create_rewrite_time_window.q
index 4cdb715..fa07401 100644
--- a/ql/src/test/queries/clientpositive/materialized_view_create_rewrite_time_window.q
+++ b/ql/src/test/queries/clientpositive/materialized_view_create_rewrite_time_window.q
@@ -12,16 +12,12 @@ insert into cmv_basetable_n3 values
(3, 'calvin', 978.76, 3),
(3, 'charlie', 9.8, 1);
-analyze table cmv_basetable_n3 compute statistics for columns;
-
create table cmv_basetable_2_n1 (a int, b varchar(256), c decimal(10,2), d int) stored as orc TBLPROPERTIES ('transactional'='true');
insert into cmv_basetable_2_n1 values
(1, 'alfred', 10.30, 2),
(3, 'calvin', 978.76, 3);
-analyze table cmv_basetable_2_n1 compute statistics for columns;
-
-- CREATE VIEW WITH REWRITE DISABLED
EXPLAIN
CREATE MATERIALIZED VIEW cmv_mat_view_n3 DISABLE REWRITE TBLPROPERTIES('rewriting.time.window'='5min') AS
@@ -53,8 +49,6 @@ GROUP BY cmv_basetable_n3.a, cmv_basetable_2_n1.c;
insert into cmv_basetable_2_n1 values
(3, 'charlie', 15.8, 1);
-analyze table cmv_basetable_2_n1 compute statistics for columns;
-
-- ENABLE FOR REWRITE
EXPLAIN
ALTER MATERIALIZED VIEW cmv_mat_view_n3 ENABLE REWRITE;
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/queries/clientpositive/materialized_view_create_rewrite_time_window_2.q
----------------------------------------------------------------------
diff --git a/ql/src/test/queries/clientpositive/materialized_view_create_rewrite_time_window_2.q b/ql/src/test/queries/clientpositive/materialized_view_create_rewrite_time_window_2.q
index 6873673..418ec45 100644
--- a/ql/src/test/queries/clientpositive/materialized_view_create_rewrite_time_window_2.q
+++ b/ql/src/test/queries/clientpositive/materialized_view_create_rewrite_time_window_2.q
@@ -9,13 +9,11 @@ insert into cmv_basetable_n100 values
(2, 'bonnie', 172342.2, 3),
(3, 'calvin', 978.76, 3),
(3, 'charlie', 9.8, 1);
-analyze table cmv_basetable_n100 compute statistics for columns;
create table cmv_basetable_2_n100 (a int, b varchar(256), c decimal(10,2), d int) stored as orc TBLPROPERTIES ('transactional'='true');
insert into cmv_basetable_2_n100 values
(1, 'alfred', 10.30, 2),
(3, 'calvin', 978.76, 3);
-analyze table cmv_basetable_2_n100 compute statistics for columns;
-- CREATE MATERIALIZED VIEW
CREATE MATERIALIZED VIEW cmv_mat_view_n300 AS
@@ -29,7 +27,6 @@ DESCRIBE FORMATTED cmv_mat_view_n300;
insert into cmv_basetable_2_n100 values
(3, 'charlie', 15.8, 1);
-analyze table cmv_basetable_2_n100 compute statistics for columns;
-- OUTDATED: YES
DESCRIBE FORMATTED cmv_mat_view_n300;
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/queries/clientpositive/materialized_view_rewrite_1.q
----------------------------------------------------------------------
diff --git a/ql/src/test/queries/clientpositive/materialized_view_rewrite_1.q b/ql/src/test/queries/clientpositive/materialized_view_rewrite_1.q
index 18b9f7d..ff7cefc 100644
--- a/ql/src/test/queries/clientpositive/materialized_view_rewrite_1.q
+++ b/ql/src/test/queries/clientpositive/materialized_view_rewrite_1.q
@@ -15,7 +15,6 @@ create table emps_n3 (
stored as orc TBLPROPERTIES ('transactional'='true');
insert into emps_n3 values (100, 10, 'Bill', 10000, 1000), (200, 20, 'Eric', 8000, 500),
(150, 10, 'Sebastian', 7000, null), (110, 10, 'Theodore', 10000, 250), (120, 10, 'Bill', 10000, 250);
-analyze table emps_n3 compute statistics for columns;
create table depts_n2 (
deptno int,
@@ -23,21 +22,18 @@ create table depts_n2 (
locationid int)
stored as orc TBLPROPERTIES ('transactional'='true');
insert into depts_n2 values (10, 'Sales', 10), (30, 'Marketing', null), (20, 'HR', 20);
-analyze table depts_n2 compute statistics for columns;
create table dependents_n2 (
empid int,
name varchar(256))
stored as orc TBLPROPERTIES ('transactional'='true');
insert into dependents_n2 values (10, 'Michael'), (20, 'Jane');
-analyze table dependents_n2 compute statistics for columns;
create table locations_n2 (
locationid int,
name varchar(256))
stored as orc TBLPROPERTIES ('transactional'='true');
insert into locations_n2 values (10, 'San Francisco'), (20, 'San Diego');
-analyze table locations_n2 compute statistics for columns;
alter table emps_n3 add constraint pk1 primary key (empid) disable novalidate rely;
alter table depts_n2 add constraint pk2 primary key (deptno) disable novalidate rely;
@@ -50,7 +46,6 @@ alter table depts_n2 add constraint fk2 foreign key (locationid) references loca
-- EXAMPLE 1
create materialized view mv1_n2 as
select * from emps_n3 where empid < 150;
-analyze table mv1_n2 compute statistics for columns;
explain
select *
@@ -67,7 +62,6 @@ drop materialized view mv1_n2;
create materialized view mv1_n2 as
select deptno, name, salary, commission
from emps_n3;
-analyze table mv1_n2 compute statistics for columns;
explain
select emps_n3.name, emps_n3.salary, emps_n3.commission
@@ -84,7 +78,6 @@ drop materialized view mv1_n2;
create materialized view mv1_n2 as
select empid deptno from emps_n3
join depts_n2 using (deptno);
-analyze table mv1_n2 compute statistics for columns;
explain
select empid deptno from emps_n3
@@ -98,7 +91,6 @@ drop materialized view mv1_n2;
-- EXAMPLE 4
create materialized view mv1_n2 as
select * from emps_n3 where empid < 200;
-analyze table mv1_n2 compute statistics for columns;
explain
select * from emps_n3 where empid > 120
@@ -112,7 +104,6 @@ drop materialized view mv1_n2;
-- EXAMPLE 5 - NO MV, ALREADY UNIQUE
create materialized view mv1_n2 as
select empid, deptno from emps_n3 group by empid, deptno;
-analyze table mv1_n2 compute statistics for columns;
explain
select empid, deptno from emps_n3 group by empid, deptno;
@@ -124,7 +115,6 @@ drop materialized view mv1_n2;
-- EXAMPLE 5 - NO MV, ALREADY UNIQUE
create materialized view mv1_n2 as
select empid, name from emps_n3 group by empid, name;
-analyze table mv1_n2 compute statistics for columns;
explain
select empid, name from emps_n3 group by empid, name;
@@ -136,7 +126,6 @@ drop materialized view mv1_n2;
-- EXAMPLE 5
create materialized view mv1_n2 as
select name, salary from emps_n3 group by name, salary;
-analyze table mv1_n2 compute statistics for columns;
explain
select name, salary from emps_n3 group by name, salary;
@@ -148,7 +137,6 @@ drop materialized view mv1_n2;
-- EXAMPLE 6
create materialized view mv1_n2 as
select name, salary from emps_n3 group by name, salary;
-analyze table mv1_n2 compute statistics for columns;
explain
select name from emps_n3 group by name;
@@ -160,7 +148,6 @@ drop materialized view mv1_n2;
-- EXAMPLE 7
create materialized view mv1_n2 as
select name, salary from emps_n3 where deptno = 10 group by name, salary;
-analyze table mv1_n2 compute statistics for columns;
explain
select name from emps_n3 where deptno = 10 group by name;
@@ -173,7 +160,6 @@ drop materialized view mv1_n2;
create materialized view mv1_n2 as
select name, salary, count(*) as c, sum(empid) as s
from emps_n3 group by name, salary;
-analyze table mv1_n2 compute statistics for columns;
explain
select name from emps_n3 group by name;
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/queries/clientpositive/materialized_view_rewrite_10.q
----------------------------------------------------------------------
diff --git a/ql/src/test/queries/clientpositive/materialized_view_rewrite_10.q b/ql/src/test/queries/clientpositive/materialized_view_rewrite_10.q
index 9542792..ff593a7 100644
--- a/ql/src/test/queries/clientpositive/materialized_view_rewrite_10.q
+++ b/ql/src/test/queries/clientpositive/materialized_view_rewrite_10.q
@@ -14,13 +14,11 @@ create table emps_n10 (
stored as orc TBLPROPERTIES ('transactional'='true');
insert into emps_n10 values (100, 10, 'Bill', 10000, 1000), (200, 20, 'Eric', 8000, 500),
(150, 10, 'Sebastian', 7000, null), (110, 10, 'Theodore', 10000, 250), (110, 10, 'Bill', 10000, 250);
-analyze table emps_n10 compute statistics for columns;
-- EXAMPLE 1
create materialized view mv1_n10 as
select deptno, sum(salary), count(salary) as a
from emps_n10 group by deptno;
-analyze table mv1_n10 compute statistics for columns;
explain
select deptno, avg(salary) as a
@@ -35,7 +33,6 @@ drop materialized view mv1_n10;
create materialized view mv1_n10 as
select salary, sum(salary), count(salary) as a
from emps_n10 group by salary;
-analyze table mv1_n10 compute statistics for columns;
explain
select salary, avg(salary) as a
@@ -50,7 +47,6 @@ drop materialized view mv1_n10;
create materialized view mv1_n10 as
select salary, sum(salary), count(salary) as a
from emps_n10 where salary > 0 group by salary;
-analyze table mv1_n10 compute statistics for columns;
explain
select salary, avg(salary) as a
@@ -71,12 +67,10 @@ create table emps_n10_2 (
stored as orc TBLPROPERTIES ('transactional'='true');
insert into emps_n10_2 values (100, 10, 'Bill', 1, 1000), (200, 20, 'Eric', 2, 500),
(150, 10, 'Sebastian', 2, null), (110, 10, 'Theodore', 3, 250), (110, 10, 'Bill', 0, 250);
-analyze table emps_n10_2 compute statistics for columns;
create materialized view mv1_n10 as
select salary, sum(salary), count(salary) as a
from emps_n10_2 where salary > 0 group by salary;
-analyze table mv1_n10 compute statistics for columns;
explain
select avg(salary)
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/queries/clientpositive/materialized_view_rewrite_2.q
----------------------------------------------------------------------
diff --git a/ql/src/test/queries/clientpositive/materialized_view_rewrite_2.q b/ql/src/test/queries/clientpositive/materialized_view_rewrite_2.q
index 3a447fc..feba84e 100644
--- a/ql/src/test/queries/clientpositive/materialized_view_rewrite_2.q
+++ b/ql/src/test/queries/clientpositive/materialized_view_rewrite_2.q
@@ -15,7 +15,6 @@ create table emps_n0 (
stored as orc TBLPROPERTIES ('transactional'='true');
insert into emps_n0 values (100, 10, 'Bill', 10000, 1000), (200, 20, 'Eric', 8000, 500),
(150, 10, 'Sebastian', 7000, null), (110, 10, 'Theodore', 10000, 250), (110, 10, 'Bill', 10000, 250);
-analyze table emps_n0 compute statistics for columns;
create table depts_n0 (
deptno int,
@@ -23,21 +22,18 @@ create table depts_n0 (
locationid int)
stored as orc TBLPROPERTIES ('transactional'='true');
insert into depts_n0 values (10, 'Sales', 10), (30, 'Marketing', null), (20, 'HR', 20);
-analyze table depts_n0 compute statistics for columns;
create table dependents_n0 (
empid int,
name varchar(256))
stored as orc TBLPROPERTIES ('transactional'='true');
insert into dependents_n0 values (10, 'Michael'), (10, 'Jane');
-analyze table dependents_n0 compute statistics for columns;
create table locations_n0 (
locationid int,
name varchar(256))
stored as orc TBLPROPERTIES ('transactional'='true');
insert into locations_n0 values (10, 'San Francisco'), (10, 'San Diego');
-analyze table locations_n0 compute statistics for columns;
alter table emps_n0 add constraint pk1 primary key (empid) disable novalidate rely;
alter table depts_n0 add constraint pk2 primary key (deptno) disable novalidate rely;
@@ -52,7 +48,6 @@ create materialized view mv1_n0 as
select empid, depts_n0.deptno from emps_n0
join depts_n0 using (deptno) where depts_n0.deptno > 10
group by empid, depts_n0.deptno;
-analyze table mv1_n0 compute statistics for columns;
explain
select empid from emps_n0
@@ -70,7 +65,6 @@ create materialized view mv1_n0 as
select depts_n0.deptno, empid from depts_n0
join emps_n0 using (deptno) where depts_n0.deptno > 10
group by empid, depts_n0.deptno;
-analyze table mv1_n0 compute statistics for columns;
explain
select empid from emps_n0
@@ -88,7 +82,6 @@ create materialized view mv1_n0 as
select empid, depts_n0.deptno from emps_n0
join depts_n0 using (deptno) where emps_n0.deptno > 10
group by empid, depts_n0.deptno;
-analyze table mv1_n0 compute statistics for columns;
explain
select empid from emps_n0
@@ -106,7 +99,6 @@ create materialized view mv1_n0 as
select depts_n0.deptno, emps_n0.empid from depts_n0
join emps_n0 using (deptno) where emps_n0.empid > 10
group by depts_n0.deptno, emps_n0.empid;
-analyze table mv1_n0 compute statistics for columns;
explain
select depts_n0.deptno from depts_n0
@@ -124,7 +116,6 @@ create materialized view mv1_n0 as
select depts_n0.deptno, emps_n0.empid from depts_n0
join emps_n0 using (deptno) where emps_n0.empid > 10
group by depts_n0.deptno, emps_n0.empid;
-analyze table mv1_n0 compute statistics for columns;
explain
select depts_n0.deptno from depts_n0
@@ -143,7 +134,6 @@ select depts_n0.name, dependents_n0.name as name2, emps_n0.deptno, depts_n0.dept
from depts_n0, dependents_n0, emps_n0
where depts_n0.deptno > 10
group by depts_n0.name, dependents_n0.name, emps_n0.deptno, depts_n0.deptno, dependents_n0.empid;
-analyze table mv1_n0 compute statistics for columns;
explain
select dependents_n0.empid
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/queries/clientpositive/materialized_view_rewrite_3.q
----------------------------------------------------------------------
diff --git a/ql/src/test/queries/clientpositive/materialized_view_rewrite_3.q b/ql/src/test/queries/clientpositive/materialized_view_rewrite_3.q
index 0823f59..ff02ceb 100644
--- a/ql/src/test/queries/clientpositive/materialized_view_rewrite_3.q
+++ b/ql/src/test/queries/clientpositive/materialized_view_rewrite_3.q
@@ -15,7 +15,6 @@ create table emps_n9 (
stored as orc TBLPROPERTIES ('transactional'='true');
insert into emps_n9 values (100, 10, 'Bill', 10000, 1000), (200, 20, 'Eric', 8000, 500),
(150, 10, 'Sebastian', 7000, null), (120, 10, 'Theodore', 10000, 250);
-analyze table emps_n9 compute statistics for columns;
create table depts_n7 (
deptno int,
@@ -23,21 +22,18 @@ create table depts_n7 (
locationid int)
stored as orc TBLPROPERTIES ('transactional'='true');
insert into depts_n7 values (10, 'Sales', 10), (30, 'Marketing', null), (20, 'HR', 20);
-analyze table depts_n7 compute statistics for columns;
create table dependents_n5 (
empid int,
name varchar(256))
stored as orc TBLPROPERTIES ('transactional'='true');
insert into dependents_n5 values (10, 'Michael'), (20, 'Jane');
-analyze table dependents_n5 compute statistics for columns;
create table locations_n5 (
locationid int,
name varchar(256))
stored as orc TBLPROPERTIES ('transactional'='true');
insert into locations_n5 values (10, 'San Francisco'), (20, 'San Diego');
-analyze table locations_n5 compute statistics for columns;
alter table emps_n9 add constraint pk1 primary key (empid) disable novalidate rely;
alter table depts_n7 add constraint pk2 primary key (deptno) disable novalidate rely;
@@ -51,7 +47,6 @@ alter table depts_n7 add constraint fk2 foreign key (locationid) references loca
create materialized view mv1_n5 as
select empid deptno from emps_n9
join depts_n7 using (deptno);
-analyze table mv1_n5 compute statistics for columns;
explain
select empid deptno from emps_n9
@@ -66,7 +61,6 @@ drop materialized view mv1_n5;
create materialized view mv1_n5 as
select cast(empid as BIGINT) from emps_n9
join depts_n7 using (deptno);
-analyze table mv1_n5 compute statistics for columns;
explain
select empid deptno from emps_n9
@@ -81,7 +75,6 @@ drop materialized view mv1_n5;
create materialized view mv1_n5 as
select cast(empid as BIGINT) from emps_n9
join depts_n7 using (deptno);
-analyze table mv1_n5 compute statistics for columns;
explain
select empid deptno from emps_n9
@@ -97,7 +90,6 @@ create materialized view mv1_n5 as
select depts_n7.name
from emps_n9
join depts_n7 on (emps_n9.deptno = depts_n7.deptno);
-analyze table mv1_n5 compute statistics for columns;
explain
select dependents_n5.empid
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/queries/clientpositive/materialized_view_rewrite_4.q
----------------------------------------------------------------------
diff --git a/ql/src/test/queries/clientpositive/materialized_view_rewrite_4.q b/ql/src/test/queries/clientpositive/materialized_view_rewrite_4.q
index 6724cec..08c1956 100644
--- a/ql/src/test/queries/clientpositive/materialized_view_rewrite_4.q
+++ b/ql/src/test/queries/clientpositive/materialized_view_rewrite_4.q
@@ -15,7 +15,6 @@ create table emps_n5 (
stored as orc TBLPROPERTIES ('transactional'='true');
insert into emps_n5 values (100, 10, 'Bill', 10000, 1000), (200, 20, 'Eric', 8000, 500),
(150, 10, 'Sebastian', 7000, null), (110, 10, 'Theodore', 10000, 250), (120, 10, 'Bill', 10000, 250);
-analyze table emps_n5 compute statistics for columns;
create table depts_n4 (
deptno int,
@@ -23,21 +22,18 @@ create table depts_n4 (
locationid int)
stored as orc TBLPROPERTIES ('transactional'='true');
insert into depts_n4 values (10, 'Sales', 10), (30, 'Marketing', null), (20, 'HR', 20);
-analyze table depts_n4 compute statistics for columns;
create table dependents_n3 (
empid int,
name varchar(256))
stored as orc TBLPROPERTIES ('transactional'='true');
insert into dependents_n3 values (10, 'Michael'), (20, 'Jane');
-analyze table dependents_n3 compute statistics for columns;
create table locations_n3 (
locationid int,
name varchar(256))
stored as orc TBLPROPERTIES ('transactional'='true');
insert into locations_n3 values (10, 'San Francisco'), (20, 'San Diego');
-analyze table locations_n3 compute statistics for columns;
alter table emps_n5 add constraint pk1 primary key (empid) disable novalidate rely;
alter table depts_n4 add constraint pk2 primary key (deptno) disable novalidate rely;
@@ -52,7 +48,6 @@ alter table depts_n4 add constraint fk2 foreign key (locationid) references loca
create materialized view mv1_n3 as
select name, salary, count(*) as c, sum(empid) as s
from emps_n5 group by name, salary;
-analyze table mv1_n3 compute statistics for columns;
explain
select name, count(*) as c, sum(empid) as s
@@ -67,7 +62,6 @@ drop materialized view mv1_n3;
create materialized view mv1_n3 as
select name, salary, count(*) as c, sum(empid) as s
from emps_n5 group by name, salary;
-analyze table mv1_n3 compute statistics for columns;
explain
select salary, name, sum(empid) as s, count(*) as c
@@ -84,7 +78,6 @@ create materialized view mv1_n3 as
select empid, emps_n5.deptno, count(*) as c, sum(empid) as s
from emps_n5 join depts_n4 using (deptno)
group by empid, emps_n5.deptno;
-analyze table mv1_n3 compute statistics for columns;
explain
select depts_n4.deptno, count(*) as c, sum(empid) as s
@@ -102,7 +95,6 @@ create materialized view mv1_n3 as
select empid, emps_n5.deptno, count(*) as c, sum(empid) as s
from emps_n5 join depts_n4 using (deptno)
where emps_n5.deptno >= 10 group by empid, emps_n5.deptno;
-analyze table mv1_n3 compute statistics for columns;
explain
select depts_n4.deptno, sum(empid) as s
@@ -120,7 +112,6 @@ create materialized view mv1_n3 as
select empid, depts_n4.deptno, count(*) + 1 as c, sum(empid) as s
from emps_n5 join depts_n4 using (deptno)
where depts_n4.deptno >= 10 group by empid, depts_n4.deptno;
-analyze table mv1_n3 compute statistics for columns;
explain
select depts_n4.deptno, sum(empid) + 1 as s
@@ -139,7 +130,6 @@ select depts_n4.name, sum(salary) as s
from emps_n5
join depts_n4 on (emps_n5.deptno = depts_n4.deptno)
group by depts_n4.name;
-analyze table mv1_n3 compute statistics for columns;
explain
select dependents_n3.empid, sum(salary) as s
@@ -162,7 +152,6 @@ select dependents_n3.empid, emps_n5.deptno, count(distinct salary) as s
from emps_n5
join dependents_n3 on (emps_n5.empid = dependents_n3.empid)
group by dependents_n3.empid, emps_n5.deptno;
-analyze table mv1_n3 compute statistics for columns;
explain
select emps_n5.deptno, count(distinct salary) as s
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/queries/clientpositive/materialized_view_rewrite_5.q
----------------------------------------------------------------------
diff --git a/ql/src/test/queries/clientpositive/materialized_view_rewrite_5.q b/ql/src/test/queries/clientpositive/materialized_view_rewrite_5.q
index d87928c..1e9a9b9 100644
--- a/ql/src/test/queries/clientpositive/materialized_view_rewrite_5.q
+++ b/ql/src/test/queries/clientpositive/materialized_view_rewrite_5.q
@@ -15,7 +15,6 @@ create table emps_n2 (
stored as orc TBLPROPERTIES ('transactional'='true');
insert into emps_n2 values (100, 10, 'Bill', 10000, 1000), (200, 20, 'Eric', 8000, 500),
(150, 10, 'Sebastian', 7000, null), (110, 10, 'Theodore', 10000, 250), (120, 10, 'Bill', 10000, 250);
-analyze table emps_n2 compute statistics for columns;
create table depts_n1 (
deptno int,
@@ -23,21 +22,18 @@ create table depts_n1 (
locationid int)
stored as orc TBLPROPERTIES ('transactional'='true');
insert into depts_n1 values (10, 'Sales', 10), (30, 'Marketing', null), (20, 'HR', 20);
-analyze table depts_n1 compute statistics for columns;
create table dependents_n1 (
empid int,
name varchar(256))
stored as orc TBLPROPERTIES ('transactional'='true');
insert into dependents_n1 values (10, 'Michael'), (20, 'Jane');
-analyze table dependents_n1 compute statistics for columns;
create table locations_n1 (
locationid int,
name varchar(256))
stored as orc TBLPROPERTIES ('transactional'='true');
insert into locations_n1 values (10, 'San Francisco'), (20, 'San Diego');
-analyze table locations_n1 compute statistics for columns;
alter table emps_n2 add constraint pk1 primary key (empid) disable novalidate rely;
alter table depts_n1 add constraint pk2 primary key (deptno) disable novalidate rely;
@@ -54,7 +50,6 @@ alter table depts_n1 change column locationid locationid int constraint nn2 not
-- EXAMPLE 8
create materialized view mv1_n1 as
select name, deptno, salary from emps_n2 where deptno > 15 group by name, deptno, salary;
-analyze table mv1_n1 compute statistics for columns;
explain
select name from emps_n2 where deptno >= 20 group by name;
@@ -67,7 +62,6 @@ drop materialized view mv1_n1;
create materialized view mv1_n1 as
select name, deptno, salary, count(*) as c, sum(empid) as s
from emps_n2 where deptno >= 15 group by name, deptno, salary;
-analyze table mv1_n1 compute statistics for columns;
explain
select name, sum(empid) as s
@@ -87,7 +81,6 @@ join locations_n1 on (locations_n1.name = dependents_n1.name)
join emps_n2 on (emps_n2.deptno = depts_n1.deptno)
where depts_n1.deptno > 10 and depts_n1.deptno < 20
group by depts_n1.deptno, dependents_n1.empid;
-analyze table mv1_n1 compute statistics for columns;
explain
select dependents_n1.empid
@@ -113,7 +106,6 @@ create materialized view mv1_n1 as
select empid, depts_n1.deptno, count(*) as c, sum(empid) as s
from emps_n2 join depts_n1 using (deptno)
group by empid, depts_n1.deptno;
-analyze table mv1_n1 compute statistics for columns;
explain
select deptno from emps_n2 group by deptno;
@@ -127,7 +119,6 @@ create materialized view mv1_n1 as
select empid, depts_n1.deptno, count(*) as c, sum(empid) as s
from emps_n2 join depts_n1 using (deptno)
group by empid, depts_n1.deptno;
-analyze table mv1_n1 compute statistics for columns;
explain
select deptno, empid, sum(empid) as s, count(*) as c
@@ -144,7 +135,6 @@ select dependents_n1.empid, emps_n2.deptno, sum(salary) as s
from emps_n2
join dependents_n1 on (emps_n2.empid = dependents_n1.empid)
group by dependents_n1.empid, emps_n2.deptno;
-analyze table mv1_n1 compute statistics for columns;
explain
select dependents_n1.empid, sum(salary) as s
@@ -167,7 +157,6 @@ select dependents_n1.empid, emps_n2.deptno, sum(salary) as s
from emps_n2
join dependents_n1 on (emps_n2.empid = dependents_n1.empid)
group by dependents_n1.empid, emps_n2.deptno;
-analyze table mv1_n1 compute statistics for columns;
explain
select depts_n1.name, sum(salary) as s
@@ -190,7 +179,6 @@ select a.empid deptno from
(select * from emps_n2 where empid = 1) a
join depts_n1 on (a.deptno = depts_n1.deptno)
join dependents_n1 on (a.empid = dependents_n1.empid);
-analyze table mv1_n1 compute statistics for columns;
explain
select a.empid from
@@ -209,7 +197,6 @@ select a.empid, a.deptno from
(select * from emps_n2 where empid = 1) a
join depts_n1 on (a.deptno = depts_n1.deptno)
join dependents_n1 on (a.empid = dependents_n1.empid);
-analyze table mv1_n1 compute statistics for columns;
explain
select a.empid from
@@ -227,7 +214,6 @@ create materialized view mv1_n1 as
select empid deptno from
(select * from emps_n2 where empid = 1) a
join depts_n1 on (a.deptno = depts_n1.deptno);
-analyze table mv1_n1 compute statistics for columns;
explain
select empid from emps_n2 where empid = 1;
@@ -242,7 +228,6 @@ select emps_n2.empid, emps_n2.deptno from emps_n2
join depts_n1 on (emps_n2.deptno = depts_n1.deptno)
join dependents_n1 on (emps_n2.empid = dependents_n1.empid)
where emps_n2.empid = 1;
-analyze table mv1_n1 compute statistics for columns;
explain
select emps_n2.empid from emps_n2
@@ -262,7 +247,6 @@ join depts_n1 a on (emps_n2.deptno=a.deptno)
join depts_n1 b on (emps_n2.deptno=b.deptno)
join dependents_n1 on (emps_n2.empid = dependents_n1.empid)
where emps_n2.empid = 1;
-analyze table mv1_n1 compute statistics for columns;
explain
select emps_n2.empid from emps_n2
@@ -282,7 +266,6 @@ join depts_n1 a on (emps_n2.deptno=a.deptno)
join depts_n1 b on (emps_n2.deptno=b.deptno)
join dependents_n1 on (emps_n2.empid = dependents_n1.empid)
where emps_n2.name = 'Sebastian';
-analyze table mv1_n1 compute statistics for columns;
explain
select emps_n2.empid from emps_n2
[34/35] hive git commit: HIVE-16957: Support CTAS for auto gather
column stats (Jesus Camacho Rodriguez, reviewed by Ashutosh Chauhan)
Posted by jc...@apache.org.
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/queries/clientpositive/materialized_view_rewrite_6.q
----------------------------------------------------------------------
diff --git a/ql/src/test/queries/clientpositive/materialized_view_rewrite_6.q b/ql/src/test/queries/clientpositive/materialized_view_rewrite_6.q
index 23fc3c1..5ff60bc 100644
--- a/ql/src/test/queries/clientpositive/materialized_view_rewrite_6.q
+++ b/ql/src/test/queries/clientpositive/materialized_view_rewrite_6.q
@@ -15,7 +15,6 @@ create table emps (
stored as orc TBLPROPERTIES ('transactional'='true');
insert into emps values (100, 10, 'Bill', 10000, 1000), (200, 20, 'Eric', 8000, 500),
(150, 10, 'Sebastian', 7000, null), (110, 10, 'Theodore', 10000, 250), (120, 10, 'Bill', 10000, 250);
-analyze table emps compute statistics for columns;
create table depts (
deptno int,
@@ -23,21 +22,18 @@ create table depts (
locationid int)
stored as orc TBLPROPERTIES ('transactional'='true');
insert into depts values (10, 'Sales', 10), (30, 'Marketing', null), (20, 'HR', 20);
-analyze table depts compute statistics for columns;
create table dependents (
empid int,
name varchar(256))
stored as orc TBLPROPERTIES ('transactional'='true');
insert into dependents values (10, 'Michael'), (20, 'Jane');
-analyze table dependents compute statistics for columns;
create table locations (
locationid int,
name varchar(256))
stored as orc TBLPROPERTIES ('transactional'='true');
insert into locations values (10, 'San Francisco'), (20, 'San Diego');
-analyze table locations compute statistics for columns;
alter table emps add constraint pk1 primary key (empid) disable novalidate rely;
alter table depts add constraint pk2 primary key (deptno) disable novalidate rely;
@@ -55,7 +51,6 @@ alter table depts change column locationid locationid int constraint nn2 not nul
create materialized view mv1 as
select name, deptno, salary, count(*) + 1 as c, sum(empid) as s
from emps where deptno >= 10 group by name, deptno, salary;
-analyze table mv1 compute statistics for columns;
explain
select salary, sum(empid) + 1 as s
@@ -70,7 +65,6 @@ drop materialized view mv1;
create materialized view mv1 as
select name, deptno, salary, count(*) + 1 as c, sum(empid) as s
from emps where deptno >= 15 group by name, deptno, salary;
-analyze table mv1 compute statistics for columns;
explain
select salary + 1, sum(empid) + 1 as s
@@ -86,7 +80,6 @@ create materialized view mv1 as
select depts.name
from emps
join depts on (emps.deptno = depts.deptno);
-analyze table mv1 compute statistics for columns;
explain
select dependents.empid
@@ -106,7 +99,6 @@ create materialized view mv1 as
select depts.name
from emps
join depts on (emps.deptno = depts.deptno);
-analyze table mv1 compute statistics for columns;
explain
select dependents.empid
@@ -127,7 +119,6 @@ drop materialized view mv1;
create materialized view mv1 as
select emps.empid, emps.deptno, emps.name as name1, emps.salary, emps.commission, dependents.name as name2
from emps join dependents on (emps.empid = dependents.empid);
-analyze table mv1 compute statistics for columns;
explain
select emps.empid, dependents.empid, emps.deptno
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/queries/clientpositive/materialized_view_rewrite_7.q
----------------------------------------------------------------------
diff --git a/ql/src/test/queries/clientpositive/materialized_view_rewrite_7.q b/ql/src/test/queries/clientpositive/materialized_view_rewrite_7.q
index 3d1cedc..9a0e3c8 100644
--- a/ql/src/test/queries/clientpositive/materialized_view_rewrite_7.q
+++ b/ql/src/test/queries/clientpositive/materialized_view_rewrite_7.q
@@ -15,7 +15,6 @@ create table emps_n8 (
stored as orc TBLPROPERTIES ('transactional'='true');
insert into emps_n8 values (100, 10, 'Bill', 10000, 1000), (200, 20, 'Eric', 8000, 500),
(150, 10, 'Sebastian', 7000, null), (110, 10, 'Theodore', 10000, 250);
-analyze table emps_n8 compute statistics for columns;
create table depts_n6 (
deptno int,
@@ -23,21 +22,18 @@ create table depts_n6 (
locationid int)
stored as orc TBLPROPERTIES ('transactional'='true');
insert into depts_n6 values (10, 'Sales', 10), (30, 'Marketing', null), (20, 'HR', 20);
-analyze table depts_n6 compute statistics for columns;
create table dependents_n4 (
empid int,
name varchar(256))
stored as orc TBLPROPERTIES ('transactional'='true');
insert into dependents_n4 values (10, 'Michael'), (20, 'Jane');
-analyze table dependents_n4 compute statistics for columns;
create table locations_n4 (
locationid int,
name varchar(256))
stored as orc TBLPROPERTIES ('transactional'='true');
insert into locations_n4 values (10, 'San Francisco'), (20, 'San Diego');
-analyze table locations_n4 compute statistics for columns;
alter table emps_n8 add constraint pk1 primary key (empid) disable novalidate rely;
alter table depts_n6 add constraint pk2 primary key (deptno) disable novalidate rely;
@@ -60,7 +56,6 @@ join locations_n4 on (locations_n4.name = dependents_n4.name)
join emps_n8 on (emps_n8.deptno = depts_n6.deptno)
where depts_n6.deptno > 11
group by depts_n6.deptno, dependents_n4.empid;
-analyze table mv1_n4 compute statistics for columns;
explain
select dependents_n4.empid, depts_n6.deptno
@@ -90,7 +85,6 @@ join locations_n4 on (locations_n4.name = dependents_n4.name)
join emps_n8 on (emps_n8.deptno = depts_n6.deptno)
where depts_n6.deptno > 11 and depts_n6.deptno < 19
group by depts_n6.deptno, dependents_n4.empid;
-analyze table mv1_n4 compute statistics for columns;
explain
select dependents_n4.empid, count(emps_n8.salary) + 1
@@ -119,7 +113,6 @@ from depts_n6
join dependents_n4 on (depts_n6.name = dependents_n4.name)
join emps_n8 on (emps_n8.deptno = depts_n6.deptno)
where depts_n6.deptno >= 10;
-analyze table mv1_n4 compute statistics for columns;
explain
select dependents_n4.empid
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/queries/clientpositive/materialized_view_rewrite_8.q
----------------------------------------------------------------------
diff --git a/ql/src/test/queries/clientpositive/materialized_view_rewrite_8.q b/ql/src/test/queries/clientpositive/materialized_view_rewrite_8.q
index cfcfddc..919a356 100644
--- a/ql/src/test/queries/clientpositive/materialized_view_rewrite_8.q
+++ b/ql/src/test/queries/clientpositive/materialized_view_rewrite_8.q
@@ -18,7 +18,6 @@ stored AS ORC
TBLPROPERTIES("transactional"="true");
insert into table source_table_001
values ('2010-10-10', 1, 1, 'env', 1, 1);
-analyze table source_table_001 compute statistics for columns;
CREATE MATERIALIZED VIEW source_table_001_mv AS
SELECT
@@ -27,7 +26,6 @@ SUM(A.UP_VOLUME) AS UP_VOLUME_SUM,
A.MY_DATE,A.MY_ID2,A.ENVIRONMENT
from source_table_001 AS A
group by A.MY_ID,A.MY_ID2,A.ENVIRONMENT,A.MY_DATE;
-analyze table source_table_001_mv compute statistics for columns;
explain
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/queries/clientpositive/materialized_view_rewrite_9.q
----------------------------------------------------------------------
diff --git a/ql/src/test/queries/clientpositive/materialized_view_rewrite_9.q b/ql/src/test/queries/clientpositive/materialized_view_rewrite_9.q
index 18d5cec..40c4117 100644
--- a/ql/src/test/queries/clientpositive/materialized_view_rewrite_9.q
+++ b/ql/src/test/queries/clientpositive/materialized_view_rewrite_9.q
@@ -18,7 +18,6 @@ stored AS ORC
TBLPROPERTIES("transactional"="true");
insert into table source_table_001_n0
values ('2010-10-10 00:00:00', 1, 1, 'env', 1, 1);
-analyze table source_table_001_n0 compute statistics for columns;
CREATE MATERIALIZED VIEW source_table_001_mv_n0 AS
SELECT
@@ -27,7 +26,6 @@ SUM(A.UP_VOLUME) AS UP_VOLUME_SUM,
A.MY_ID,A.MY_DATE,A.MY_ID2,A.ENVIRONMENT
from source_table_001_n0 AS A
group by A.MY_ID,A.MY_ID2,A.ENVIRONMENT,A.MY_DATE;
-analyze table source_table_001_mv_n0 compute statistics for columns;
explain
select
@@ -45,7 +43,6 @@ SUM(A.UP_VOLUME) AS UP_VOLUME_SUM,
A.MY_ID,FLOOR(A.MY_DATE to hour),A.MY_ID2,A.ENVIRONMENT
from source_table_001_n0 AS A
group by A.MY_ID,A.MY_ID2,A.ENVIRONMENT,FLOOR(A.MY_DATE to hour);
-analyze table source_table_001_mv_n0 compute statistics for columns;
explain
select
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/queries/clientpositive/materialized_view_rewrite_empty.q
----------------------------------------------------------------------
diff --git a/ql/src/test/queries/clientpositive/materialized_view_rewrite_empty.q b/ql/src/test/queries/clientpositive/materialized_view_rewrite_empty.q
index 9ae1d4e..db56a38 100644
--- a/ql/src/test/queries/clientpositive/materialized_view_rewrite_empty.q
+++ b/ql/src/test/queries/clientpositive/materialized_view_rewrite_empty.q
@@ -13,7 +13,6 @@ create table emps_mv_rewrite_empty (
salary float,
commission int)
stored as orc TBLPROPERTIES ('transactional'='true');
-analyze table emps_mv_rewrite_empty compute statistics for columns;
create materialized view emps_mv_rewrite_empty_mv1 as
select * from emps_mv_rewrite_empty where empid < 150;
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/queries/clientpositive/materialized_view_rewrite_no_join_opt.q
----------------------------------------------------------------------
diff --git a/ql/src/test/queries/clientpositive/materialized_view_rewrite_no_join_opt.q b/ql/src/test/queries/clientpositive/materialized_view_rewrite_no_join_opt.q
index 8de9c70..353cef8 100644
--- a/ql/src/test/queries/clientpositive/materialized_view_rewrite_no_join_opt.q
+++ b/ql/src/test/queries/clientpositive/materialized_view_rewrite_no_join_opt.q
@@ -15,7 +15,6 @@ create table emps_n30 (
stored as orc TBLPROPERTIES ('transactional'='true');
insert into emps_n30 values (100, 10, 'Bill', 10000, 1000), (200, 20, 'Eric', 8000, 500),
(150, 10, 'Sebastian', 7000, null), (110, 10, 'Theodore', 10000, 250), (120, 10, 'Bill', 10000, 250);
-analyze table emps_n30 compute statistics for columns;
create table depts_n20 (
deptno int,
@@ -23,21 +22,18 @@ create table depts_n20 (
locationid int)
stored as orc TBLPROPERTIES ('transactional'='true');
insert into depts_n20 values (10, 'Sales', 10), (30, 'Marketing', null), (20, 'HR', 20);
-analyze table depts_n20 compute statistics for columns;
create table dependents_n20 (
empid int,
name varchar(256))
stored as orc TBLPROPERTIES ('transactional'='true');
insert into dependents_n20 values (10, 'Michael'), (20, 'Jane');
-analyze table dependents_n20 compute statistics for columns;
create table locations_n20 (
locationid int,
name varchar(256))
stored as orc TBLPROPERTIES ('transactional'='true');
insert into locations_n20 values (10, 'San Francisco'), (20, 'San Diego');
-analyze table locations_n20 compute statistics for columns;
alter table emps_n30 add constraint pk1 primary key (empid) disable novalidate rely;
alter table depts_n20 add constraint pk2 primary key (deptno) disable novalidate rely;
@@ -51,7 +47,6 @@ alter table depts_n20 add constraint fk2 foreign key (locationid) references loc
create materialized view mv1_n20 as
select deptno, name, salary, commission
from emps_n30;
-analyze table mv1_n20 compute statistics for columns;
explain
select emps_n30.name, emps_n30.salary, emps_n30.commission
@@ -69,7 +64,6 @@ create materialized view mv1_n20 as
select empid, emps_n30.deptno, count(*) as c, sum(empid) as s
from emps_n30 join depts_n20 using (deptno)
group by empid, emps_n30.deptno;
-analyze table mv1_n20 compute statistics for columns;
explain
select depts_n20.deptno, count(*) as c, sum(empid) as s
@@ -88,7 +82,6 @@ select dependents_n20.empid, emps_n30.deptno, sum(salary) as s
from emps_n30
join dependents_n20 on (emps_n30.empid = dependents_n20.empid)
group by dependents_n20.empid, emps_n30.deptno;
-analyze table mv1_n20 compute statistics for columns;
explain
select dependents_n20.empid, sum(salary) as s
@@ -109,7 +102,6 @@ drop materialized view mv1_n20;
create materialized view mv1_n20 as
select emps_n30.empid, emps_n30.deptno, emps_n30.name as name1, emps_n30.salary, emps_n30.commission, dependents_n20.name as name2
from emps_n30 join dependents_n20 on (emps_n30.empid = dependents_n20.empid);
-analyze table mv1_n20 compute statistics for columns;
explain
select emps_n30.empid, dependents_n20.empid, emps_n30.deptno
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/queries/clientpositive/materialized_view_rewrite_no_join_opt_2.q
----------------------------------------------------------------------
diff --git a/ql/src/test/queries/clientpositive/materialized_view_rewrite_no_join_opt_2.q b/ql/src/test/queries/clientpositive/materialized_view_rewrite_no_join_opt_2.q
index a137230..a5bb2c0 100644
--- a/ql/src/test/queries/clientpositive/materialized_view_rewrite_no_join_opt_2.q
+++ b/ql/src/test/queries/clientpositive/materialized_view_rewrite_no_join_opt_2.q
@@ -15,7 +15,6 @@ create table emps_n30 (
stored as orc TBLPROPERTIES ('transactional'='true');
insert into emps_n30 values (100, 10, 'Bill', 10000, 1000), (200, 20, 'Eric', 8000, 500),
(150, 10, 'Sebastian', 7000, null), (110, 10, 'Theodore', 10000, 250), (120, 10, 'Bill', 10000, 250);
-analyze table emps_n30 compute statistics for columns;
create table depts_n20 (
deptno int,
@@ -23,21 +22,18 @@ create table depts_n20 (
locationid int)
stored as orc TBLPROPERTIES ('transactional'='true');
insert into depts_n20 values (10, 'Sales', 10), (30, 'Marketing', null), (20, 'HR', 20);
-analyze table depts_n20 compute statistics for columns;
create table dependents_n20 (
empid int,
name varchar(256))
stored as orc TBLPROPERTIES ('transactional'='true');
insert into dependents_n20 values (10, 'Michael'), (20, 'Jane');
-analyze table dependents_n20 compute statistics for columns;
create table locations_n20 (
locationid int,
name varchar(256))
stored as orc TBLPROPERTIES ('transactional'='true');
insert into locations_n20 values (10, 'San Francisco'), (20, 'San Diego');
-analyze table locations_n20 compute statistics for columns;
alter table emps_n30 add constraint pk1 primary key (empid) disable novalidate rely;
alter table depts_n20 add constraint pk2 primary key (deptno) disable novalidate rely;
@@ -50,7 +46,6 @@ alter table depts_n20 add constraint fk2 foreign key (locationid) references loc
-- EXAMPLE 1
create materialized view mv1_part_n2 partitioned on (deptno) as
select * from emps_n30 where empid < 150;
-analyze table mv1_part_n2 compute statistics for columns;
explain
select *
@@ -67,7 +62,6 @@ drop materialized view mv1_part_n2;
create materialized view mv1_part_n2 partitioned on (deptno) as
select deptno, name, salary, commission
from emps_n30;
-analyze table mv1_part_n2 compute statistics for columns;
explain
select emps_n30.name, emps_n30.salary, emps_n30.commission
@@ -83,7 +77,6 @@ drop materialized view mv1_part_n2;
-- EXAMPLE 4
create materialized view mv1_part_n2 partitioned on (deptno) as
select * from emps_n30 where empid < 200;
-analyze table mv1_part_n2 compute statistics for columns;
explain
select * from emps_n30 where empid > 120
@@ -97,7 +90,6 @@ drop materialized view mv1_part_n2;
-- EXAMPLE 5
create materialized view mv1_part_n2 partitioned on (name) as
select name, salary from emps_n30 group by name, salary;
-analyze table mv1_part_n2 compute statistics for columns;
explain
select name, salary from emps_n30 group by name, salary;
@@ -109,7 +101,6 @@ drop materialized view mv1_part_n2;
-- EXAMPLE 6
create materialized view mv1_part_n2 partitioned on (name) as
select name, salary from emps_n30 group by name, salary;
-analyze table mv1_part_n2 compute statistics for columns;
explain
select name from emps_n30 group by name;
@@ -121,7 +112,6 @@ drop materialized view mv1_part_n2;
-- EXAMPLE 7
create materialized view mv1_part_n2 partitioned on (name) as
select name, salary from emps_n30 where deptno = 10 group by name, salary;
-analyze table mv1_part_n2 compute statistics for columns;
explain
select name from emps_n30 where deptno = 10 group by name;
@@ -134,7 +124,6 @@ drop materialized view mv1_part_n2;
create materialized view mv1_part_n2 partitioned on (name) as
select name, salary, count(*) as c, sum(empid) as s
from emps_n30 group by name, salary;
-analyze table mv1_part_n2 compute statistics for columns;
explain
select name from emps_n30 group by name;
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/queries/clientpositive/materialized_view_rewrite_part_1.q
----------------------------------------------------------------------
diff --git a/ql/src/test/queries/clientpositive/materialized_view_rewrite_part_1.q b/ql/src/test/queries/clientpositive/materialized_view_rewrite_part_1.q
index e6980c0..3fecac1 100644
--- a/ql/src/test/queries/clientpositive/materialized_view_rewrite_part_1.q
+++ b/ql/src/test/queries/clientpositive/materialized_view_rewrite_part_1.q
@@ -16,7 +16,6 @@ create table emps_n30 (
stored as orc TBLPROPERTIES ('transactional'='true');
insert into emps_n30 values (100, 10, 'Bill', 10000, 1000), (200, 20, 'Eric', 8000, 500),
(150, 10, 'Sebastian', 7000, null), (110, 10, 'Theodore', 10000, 250), (120, 10, 'Bill', 10000, 250);
-analyze table emps_n30 compute statistics for columns;
create table depts_n20 (
deptno int,
@@ -24,21 +23,18 @@ create table depts_n20 (
locationid int)
stored as orc TBLPROPERTIES ('transactional'='true');
insert into depts_n20 values (10, 'Sales', 10), (30, 'Marketing', null), (20, 'HR', 20);
-analyze table depts_n20 compute statistics for columns;
create table dependents_n20 (
empid int,
name varchar(256))
stored as orc TBLPROPERTIES ('transactional'='true');
insert into dependents_n20 values (10, 'Michael'), (20, 'Jane');
-analyze table dependents_n20 compute statistics for columns;
create table locations_n20 (
locationid int,
name varchar(256))
stored as orc TBLPROPERTIES ('transactional'='true');
insert into locations_n20 values (10, 'San Francisco'), (20, 'San Diego');
-analyze table locations_n20 compute statistics for columns;
alter table emps_n30 add constraint pk1 primary key (empid) disable novalidate rely;
alter table depts_n20 add constraint pk2 primary key (deptno) disable novalidate rely;
@@ -51,7 +47,6 @@ alter table depts_n20 add constraint fk2 foreign key (locationid) references loc
-- EXAMPLE 1
create materialized view mv1_part_n2 partitioned on (deptno) as
select * from emps_n30 where empid < 150;
-analyze table mv1_part_n2 compute statistics for columns;
explain
select *
@@ -68,7 +63,6 @@ drop materialized view mv1_part_n2;
create materialized view mv1_part_n2 partitioned on (deptno) as
select deptno, name, salary, commission
from emps_n30;
-analyze table mv1_part_n2 compute statistics for columns;
explain
select emps_n30.name, emps_n30.salary, emps_n30.commission
@@ -84,7 +78,6 @@ drop materialized view mv1_part_n2;
-- EXAMPLE 4
create materialized view mv1_part_n2 partitioned on (deptno) as
select * from emps_n30 where empid < 200;
-analyze table mv1_part_n2 compute statistics for columns;
explain
select * from emps_n30 where empid > 120
@@ -98,7 +91,6 @@ drop materialized view mv1_part_n2;
-- EXAMPLE 5
create materialized view mv1_part_n2 partitioned on (name) as
select name, salary from emps_n30 group by name, salary;
-analyze table mv1_part_n2 compute statistics for columns;
explain
select name, salary from emps_n30 group by name, salary;
@@ -110,7 +102,6 @@ drop materialized view mv1_part_n2;
-- EXAMPLE 6
create materialized view mv1_part_n2 partitioned on (name) as
select name, salary from emps_n30 group by name, salary;
-analyze table mv1_part_n2 compute statistics for columns;
explain
select name from emps_n30 group by name;
@@ -122,7 +113,6 @@ drop materialized view mv1_part_n2;
-- EXAMPLE 7
create materialized view mv1_part_n2 partitioned on (name) as
select name, salary from emps_n30 where deptno = 10 group by name, salary;
-analyze table mv1_part_n2 compute statistics for columns;
explain
select name from emps_n30 where deptno = 10 group by name;
@@ -135,7 +125,6 @@ drop materialized view mv1_part_n2;
create materialized view mv1_part_n2 partitioned on (name) as
select name, salary, count(*) as c, sum(empid) as s
from emps_n30 group by name, salary;
-analyze table mv1_part_n2 compute statistics for columns;
explain
select name from emps_n30 group by name;
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/queries/clientpositive/materialized_view_rewrite_part_2.q
----------------------------------------------------------------------
diff --git a/ql/src/test/queries/clientpositive/materialized_view_rewrite_part_2.q b/ql/src/test/queries/clientpositive/materialized_view_rewrite_part_2.q
index b2e6ebd..8d6df04 100644
--- a/ql/src/test/queries/clientpositive/materialized_view_rewrite_part_2.q
+++ b/ql/src/test/queries/clientpositive/materialized_view_rewrite_part_2.q
@@ -16,7 +16,6 @@ create table emps_n00 (
stored as orc TBLPROPERTIES ('transactional'='true');
insert into emps_n00 values (100, 10, 'Bill', 10000, 1000), (200, 20, 'Eric', 8000, 500),
(150, 10, 'Sebastian', 7000, null), (110, 10, 'Theodore', 10000, 250), (110, 10, 'Bill', 10000, 250);
-analyze table emps_n00 compute statistics for columns;
create table depts_n00 (
deptno int,
@@ -24,21 +23,18 @@ create table depts_n00 (
locationid int)
stored as orc TBLPROPERTIES ('transactional'='true');
insert into depts_n00 values (10, 'Sales', 10), (30, 'Marketing', null), (20, 'HR', 20);
-analyze table depts_n00 compute statistics for columns;
create table dependents_n00 (
empid int,
name varchar(256))
stored as orc TBLPROPERTIES ('transactional'='true');
insert into dependents_n00 values (10, 'Michael'), (10, 'Jane');
-analyze table dependents_n00 compute statistics for columns;
create table locations_n00 (
locationid int,
name varchar(256))
stored as orc TBLPROPERTIES ('transactional'='true');
insert into locations_n00 values (10, 'San Francisco'), (10, 'San Diego');
-analyze table locations_n00 compute statistics for columns;
alter table emps_n00 add constraint pk1 primary key (empid) disable novalidate rely;
alter table depts_n00 add constraint pk2 primary key (deptno) disable novalidate rely;
@@ -53,7 +49,6 @@ create materialized view mv1_part_n0 partitioned on (deptno) as
select empid, depts_n00.deptno as deptno from emps_n00
join depts_n00 using (deptno) where depts_n00.deptno > 10
group by empid, depts_n00.deptno;
-analyze table mv1_part_n0 compute statistics for columns;
explain
select empid from emps_n00
@@ -71,7 +66,6 @@ create materialized view mv1_part_n0 partitioned on (deptno) as
select depts_n00.deptno as deptno, empid from depts_n00
join emps_n00 using (deptno) where depts_n00.deptno > 10
group by empid, depts_n00.deptno;
-analyze table mv1_part_n0 compute statistics for columns;
explain
select empid from emps_n00
@@ -89,7 +83,6 @@ create materialized view mv1_part_n0 partitioned on (deptno) as
select empid, depts_n00.deptno as deptno from emps_n00
join depts_n00 using (deptno) where emps_n00.deptno > 10
group by empid, depts_n00.deptno;
-analyze table mv1_part_n0 compute statistics for columns;
explain
select empid from emps_n00
@@ -107,7 +100,6 @@ create materialized view mv1_part_n0 partitioned on (deptno) as
select depts_n00.deptno as deptno, emps_n00.empid from depts_n00
join emps_n00 using (deptno) where emps_n00.empid > 10
group by depts_n00.deptno, emps_n00.empid;
-analyze table mv1_part_n0 compute statistics for columns;
explain
select depts_n00.deptno from depts_n00
@@ -125,7 +117,6 @@ create materialized view mv1_part_n0 partitioned on (deptno) as
select depts_n00.deptno as deptno, emps_n00.empid from depts_n00
join emps_n00 using (deptno) where emps_n00.empid > 10
group by depts_n00.deptno, emps_n00.empid;
-analyze table mv1_part_n0 compute statistics for columns;
explain
select depts_n00.deptno from depts_n00
@@ -144,7 +135,6 @@ select depts_n00.name, dependents_n00.name as name2, emps_n00.deptno, depts_n00.
from depts_n00, dependents_n00, emps_n00
where depts_n00.deptno > 10
group by depts_n00.name, dependents_n00.name, emps_n00.deptno, depts_n00.deptno, dependents_n00.empid;
-analyze table mv1_part_n0 compute statistics for columns;
explain
select dependents_n00.empid
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/queries/clientpositive/materialized_view_rewrite_ssb.q
----------------------------------------------------------------------
diff --git a/ql/src/test/queries/clientpositive/materialized_view_rewrite_ssb.q b/ql/src/test/queries/clientpositive/materialized_view_rewrite_ssb.q
index aed5bdb..2bd92bd 100644
--- a/ql/src/test/queries/clientpositive/materialized_view_rewrite_ssb.q
+++ b/ql/src/test/queries/clientpositive/materialized_view_rewrite_ssb.q
@@ -202,12 +202,6 @@ TBLPROPERTIES ('transactional'='true');
INSERT INTO `lineorder_n0`
SELECT * FROM `lineorder_ext_n0`;
-analyze table customer_n1 compute statistics for columns;
-analyze table dates_n0 compute statistics for columns;
-analyze table ssb_part_n0 compute statistics for columns;
-analyze table supplier_n0 compute statistics for columns;
-analyze table lineorder_n0 compute statistics for columns;
-
CREATE MATERIALIZED VIEW `ssb_mv_n0`
AS
SELECT
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/queries/clientpositive/materialized_view_rewrite_ssb_2.q
----------------------------------------------------------------------
diff --git a/ql/src/test/queries/clientpositive/materialized_view_rewrite_ssb_2.q b/ql/src/test/queries/clientpositive/materialized_view_rewrite_ssb_2.q
index 0982b66..1f4621e 100644
--- a/ql/src/test/queries/clientpositive/materialized_view_rewrite_ssb_2.q
+++ b/ql/src/test/queries/clientpositive/materialized_view_rewrite_ssb_2.q
@@ -202,12 +202,6 @@ TBLPROPERTIES ('transactional'='true');
INSERT INTO `lineorder`
SELECT * FROM `lineorder_ext`;
-analyze table customer_n0 compute statistics for columns;
-analyze table dates compute statistics for columns;
-analyze table ssb_part compute statistics for columns;
-analyze table supplier compute statistics for columns;
-analyze table lineorder compute statistics for columns;
-
CREATE MATERIALIZED VIEW `ssb_mv`
AS
SELECT
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientnegative/masking_mv.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientnegative/masking_mv.q.out b/ql/src/test/results/clientnegative/masking_mv.q.out
index 54e9843..c16631a 100644
--- a/ql/src/test/results/clientnegative/masking_mv.q.out
+++ b/ql/src/test/results/clientnegative/masking_mv.q.out
@@ -57,7 +57,32 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat
serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde
name: default.masking_test_view_n_mv
- Execution mode: vectorized
+ Select Operator
+ expressions: _col0 (type: int)
+ outputColumnNames: col1
+ Statistics: Num rows: 500 Data size: 30200 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: compute_stats(col1, 'hll')
+ mode: hash
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 424 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 424 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>)
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: compute_stats(VALUE._col0)
+ mode: mergepartial
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: NONE
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
Stage: Stage-7
Conditional Operator
@@ -86,6 +111,10 @@ STAGE PLANS:
Stage: Stage-2
Stats Work
Basic Stats Work:
+ Column Stats Desc:
+ Columns: key
+ Column Types: int
+ Table: default.masking_test_view_n_mv
Stage: Stage-9
Materialized View Work
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/alter_table_update_status.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/alter_table_update_status.q.out b/ql/src/test/results/clientpositive/alter_table_update_status.q.out
index ec8a64c..6453391 100644
--- a/ql/src/test/results/clientpositive/alter_table_update_status.q.out
+++ b/ql/src/test/results/clientpositive/alter_table_update_status.q.out
@@ -60,7 +60,7 @@ num_trues
num_falses
bitVector HL
comment from deserializer
-COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"key\":\"true\"}}
+COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"key\":\"true\",\"value\":\"true\"}}
PREHOOK: query: ALTER TABLE src_stat_n0 UPDATE STATISTICS for column key SET ('numDVs'='1111','avgColLen'='1.111')
PREHOOK: type: ALTERTABLE_UPDATETABLESTATS
PREHOOK: Input: default@src_stat_n0
@@ -87,7 +87,7 @@ num_trues
num_falses
bitVector HL
comment from deserializer
-COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"key\":\"true\"}}
+COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"key\":\"true\",\"value\":\"true\"}}
PREHOOK: query: ALTER TABLE src_stat_n0 UPDATE STATISTICS for column value SET ('numDVs'='121','numNulls'='122','avgColLen'='1.23','maxColLen'='124')
PREHOOK: type: ALTERTABLE_UPDATETABLESTATS
PREHOOK: Input: default@src_stat_n0
@@ -112,7 +112,7 @@ avg_col_len 1.23
max_col_len 124
num_trues
num_falses
-bitVector
+bitVector HL
comment from deserializer
COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"key\":\"true\",\"value\":\"true\"}}
PREHOOK: query: ANALYZE TABLE src_stat_int_n0 COMPUTE STATISTICS for columns key
@@ -234,7 +234,7 @@ avg_col_len 2.34
max_col_len 235
num_trues
num_falses
-bitVector
+bitVector HL
comment from deserializer
COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"key\":\"true\",\"value\":\"true\"}}
PREHOOK: query: use default
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/alter_table_update_status_disable_bitvector.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/alter_table_update_status_disable_bitvector.q.out b/ql/src/test/results/clientpositive/alter_table_update_status_disable_bitvector.q.out
index 1b787af..068f302 100644
--- a/ql/src/test/results/clientpositive/alter_table_update_status_disable_bitvector.q.out
+++ b/ql/src/test/results/clientpositive/alter_table_update_status_disable_bitvector.q.out
@@ -60,7 +60,7 @@ num_trues
num_falses
bitVector
comment from deserializer
-COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"key\":\"true\"}}
+COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"key\":\"true\",\"value\":\"true\"}}
PREHOOK: query: ALTER TABLE src_stat UPDATE STATISTICS for column key SET ('numDVs'='1111','avgColLen'='1.111')
PREHOOK: type: ALTERTABLE_UPDATETABLESTATS
PREHOOK: Input: default@src_stat
@@ -87,7 +87,7 @@ num_trues
num_falses
bitVector
comment from deserializer
-COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"key\":\"true\"}}
+COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"key\":\"true\",\"value\":\"true\"}}
PREHOOK: query: ALTER TABLE src_stat UPDATE STATISTICS for column value SET ('numDVs'='121','numNulls'='122','avgColLen'='1.23','maxColLen'='124')
PREHOOK: type: ALTERTABLE_UPDATETABLESTATS
PREHOOK: Input: default@src_stat
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/autoColumnStats_4.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/autoColumnStats_4.q.out b/ql/src/test/results/clientpositive/autoColumnStats_4.q.out
index 83ee0f7..bd8c5c8 100644
--- a/ql/src/test/results/clientpositive/autoColumnStats_4.q.out
+++ b/ql/src/test/results/clientpositive/autoColumnStats_4.q.out
@@ -77,6 +77,7 @@ STAGE PLANS:
key expressions: _col0 (type: int)
sort order: +
Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
+ TopN Hash Memory Usage: 0.1
value expressions: _col1 (type: varchar(128))
Execution mode: vectorized
Reduce Operator Tree:
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/beeline/materialized_view_create_rewrite.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/beeline/materialized_view_create_rewrite.q.out b/ql/src/test/results/clientpositive/beeline/materialized_view_create_rewrite.q.out
index 1976545..257dbd6 100644
--- a/ql/src/test/results/clientpositive/beeline/materialized_view_create_rewrite.q.out
+++ b/ql/src/test/results/clientpositive/beeline/materialized_view_create_rewrite.q.out
@@ -28,16 +28,6 @@ POSTHOOK: Lineage: cmv_basetable_n10.a SCRIPT []
POSTHOOK: Lineage: cmv_basetable_n10.b SCRIPT []
POSTHOOK: Lineage: cmv_basetable_n10.c SCRIPT []
POSTHOOK: Lineage: cmv_basetable_n10.d SCRIPT []
-PREHOOK: query: analyze table cmv_basetable_n10 compute statistics for columns
-PREHOOK: type: ANALYZE_TABLE
-PREHOOK: Input: default@cmv_basetable_n10
-#### A masked pattern was here ####
-PREHOOK: Output: default@cmv_basetable_n10
-POSTHOOK: query: analyze table cmv_basetable_n10 compute statistics for columns
-POSTHOOK: type: ANALYZE_TABLE
-POSTHOOK: Input: default@cmv_basetable_n10
-#### A masked pattern was here ####
-POSTHOOK: Output: default@cmv_basetable_n10
PREHOOK: query: create materialized view cmv_mat_view_n10
as select a, b, c from cmv_basetable_n10 where a = 2
PREHOOK: type: CREATE_MATERIALIZED_VIEW
@@ -64,7 +54,7 @@ PREHOOK: query: show tblproperties cmv_mat_view_n10
PREHOOK: type: SHOW_TBLPROPERTIES
POSTHOOK: query: show tblproperties cmv_mat_view_n10
POSTHOOK: type: SHOW_TBLPROPERTIES
-COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"}
+COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"a":"true","b":"true","c":"true"}}
bucketing_version 2
numFiles 1
numFilesErasureCoded 0
@@ -98,7 +88,7 @@ PREHOOK: query: show tblproperties cmv_mat_view2_n4
PREHOOK: type: SHOW_TBLPROPERTIES
POSTHOOK: query: show tblproperties cmv_mat_view2_n4
POSTHOOK: type: SHOW_TBLPROPERTIES
-COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"}
+COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"a":"true","c":"true"}}
bucketing_version 2
numFiles 1
numFilesErasureCoded 0
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/cbo_rp_cross_product_check_2.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/cbo_rp_cross_product_check_2.q.out b/ql/src/test/results/clientpositive/cbo_rp_cross_product_check_2.q.out
index a960b06..89c967b 100644
--- a/ql/src/test/results/clientpositive/cbo_rp_cross_product_check_2.q.out
+++ b/ql/src/test/results/clientpositive/cbo_rp_cross_product_check_2.q.out
@@ -1,31 +1,43 @@
-PREHOOK: query: create table A_n18 as
-select * from src
-PREHOOK: type: CREATETABLE_AS_SELECT
-PREHOOK: Input: default@src
+PREHOOK: query: create table A_n18 (key string, value string)
+PREHOOK: type: CREATETABLE
PREHOOK: Output: database:default
PREHOOK: Output: default@A_n18
-POSTHOOK: query: create table A_n18 as
-select * from src
-POSTHOOK: type: CREATETABLE_AS_SELECT
-POSTHOOK: Input: default@src
+POSTHOOK: query: create table A_n18 (key string, value string)
+POSTHOOK: type: CREATETABLE
POSTHOOK: Output: database:default
POSTHOOK: Output: default@A_n18
+PREHOOK: query: insert into A_n18
+select * from src
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+PREHOOK: Output: default@a_n18
+POSTHOOK: query: insert into A_n18
+select * from src
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+POSTHOOK: Output: default@a_n18
POSTHOOK: Lineage: a_n18.key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ]
POSTHOOK: Lineage: a_n18.value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
-PREHOOK: query: create table B_n14 as
+PREHOOK: query: create table B_n14 (key string, value string)
+PREHOOK: type: CREATETABLE
+PREHOOK: Output: database:default
+PREHOOK: Output: default@B_n14
+POSTHOOK: query: create table B_n14 (key string, value string)
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@B_n14
+PREHOOK: query: insert into B_n14
select * from src order by key
limit 10
-PREHOOK: type: CREATETABLE_AS_SELECT
+PREHOOK: type: QUERY
PREHOOK: Input: default@src
-PREHOOK: Output: database:default
-PREHOOK: Output: default@B_n14
-POSTHOOK: query: create table B_n14 as
+PREHOOK: Output: default@b_n14
+POSTHOOK: query: insert into B_n14
select * from src order by key
limit 10
-POSTHOOK: type: CREATETABLE_AS_SELECT
+POSTHOOK: type: QUERY
POSTHOOK: Input: default@src
-POSTHOOK: Output: database:default
-POSTHOOK: Output: default@B_n14
+POSTHOOK: Output: default@b_n14
POSTHOOK: Lineage: b_n14.key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ]
POSTHOOK: Lineage: b_n14.value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
Warning: Map Join MAPJOIN[8][bigTable=?] in task 'Stage-3:MAPRED' is a cross product
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/ctas.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/ctas.q.out b/ql/src/test/results/clientpositive/ctas.q.out
index f414c68..b56d4b3 100644
--- a/ql/src/test/results/clientpositive/ctas.q.out
+++ b/ql/src/test/results/clientpositive/ctas.q.out
@@ -28,8 +28,9 @@ STAGE DEPENDENCIES:
Stage-1 is a root stage
Stage-2 depends on stages: Stage-1
Stage-0 depends on stages: Stage-2
- Stage-4 depends on stages: Stage-0
- Stage-3 depends on stages: Stage-4
+ Stage-5 depends on stages: Stage-0, Stage-4
+ Stage-3 depends on stages: Stage-5
+ Stage-4 depends on stages: Stage-2
STAGE PLANS:
Stage: Stage-1
@@ -89,6 +90,21 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.nzhang_CTAS1
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: string)
+ outputColumnNames: col1, col2
+ Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: compute_stats(col1, 'hll'), compute_stats(col2, 'hll')
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
Stage: Stage-0
Move Operator
@@ -96,7 +112,7 @@ STAGE PLANS:
hdfs directory: true
#### A masked pattern was here ####
- Stage: Stage-4
+ Stage: Stage-5
Create Table Operator:
Create Table
columns: k string, value string
@@ -108,6 +124,33 @@ STAGE PLANS:
Stage: Stage-3
Stats Work
Basic Stats Work:
+ Column Stats Desc:
+ Columns: k, value
+ Column Types: string, string
+ Table: default.nzhang_CTAS1
+
+ Stage: Stage-4
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>)
+ Execution mode: vectorized
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
PREHOOK: query: create table nzhang_CTAS1 as select key k, value from src sort by k, value limit 10
PREHOOK: type: CREATETABLE_AS_SELECT
@@ -156,7 +199,7 @@ Retention: 0
#### A masked pattern was here ####
Table Type: MANAGED_TABLE
Table Parameters:
- COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"k\":\"true\",\"value\":\"true\"}}
bucketing_version 2
numFiles 1
numRows 10
@@ -188,8 +231,9 @@ STAGE DEPENDENCIES:
Stage-1 is a root stage
Stage-2 depends on stages: Stage-1
Stage-0 depends on stages: Stage-2
- Stage-4 depends on stages: Stage-0
- Stage-3 depends on stages: Stage-4
+ Stage-5 depends on stages: Stage-0, Stage-4
+ Stage-3 depends on stages: Stage-5
+ Stage-4 depends on stages: Stage-2
STAGE PLANS:
Stage: Stage-1
@@ -249,6 +293,21 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.nzhang_ctas2
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: string)
+ outputColumnNames: col1, col2
+ Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: compute_stats(col1, 'hll'), compute_stats(col2, 'hll')
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
Stage: Stage-0
Move Operator
@@ -256,7 +315,7 @@ STAGE PLANS:
hdfs directory: true
#### A masked pattern was here ####
- Stage: Stage-4
+ Stage: Stage-5
Create Table Operator:
Create Table
columns: key string, value string
@@ -268,6 +327,33 @@ STAGE PLANS:
Stage: Stage-3
Stats Work
Basic Stats Work:
+ Column Stats Desc:
+ Columns: key, value
+ Column Types: string, string
+ Table: default.nzhang_ctas2
+
+ Stage: Stage-4
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>)
+ Execution mode: vectorized
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
PREHOOK: query: create table nzhang_ctas2 as select * from src sort by key, value limit 10
PREHOOK: type: CREATETABLE_AS_SELECT
@@ -316,7 +402,7 @@ Retention: 0
#### A masked pattern was here ####
Table Type: MANAGED_TABLE
Table Parameters:
- COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"key\":\"true\",\"value\":\"true\"}}
bucketing_version 2
numFiles 1
numRows 10
@@ -348,8 +434,9 @@ STAGE DEPENDENCIES:
Stage-1 is a root stage
Stage-2 depends on stages: Stage-1
Stage-0 depends on stages: Stage-2
- Stage-4 depends on stages: Stage-0
- Stage-3 depends on stages: Stage-4
+ Stage-5 depends on stages: Stage-0, Stage-4
+ Stage-3 depends on stages: Stage-5
+ Stage-4 depends on stages: Stage-2
STAGE PLANS:
Stage: Stage-1
@@ -409,6 +496,21 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
name: default.nzhang_ctas3
+ Select Operator
+ expressions: _col0 (type: double), _col1 (type: string)
+ outputColumnNames: col1, col2
+ Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: compute_stats(col1, 'hll'), compute_stats(col2, 'hll')
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
Stage: Stage-0
Move Operator
@@ -416,7 +518,7 @@ STAGE PLANS:
hdfs directory: true
#### A masked pattern was here ####
- Stage: Stage-4
+ Stage: Stage-5
Create Table Operator:
Create Table
columns: half_key double, conb string
@@ -428,6 +530,33 @@ STAGE PLANS:
Stage: Stage-3
Stats Work
Basic Stats Work:
+ Column Stats Desc:
+ Columns: half_key, conb
+ Column Types: double, string
+ Table: default.nzhang_ctas3
+
+ Stage: Stage-4
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: struct<columntype:string,min:double,max:double,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>)
+ Execution mode: vectorized
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
PREHOOK: query: create table nzhang_ctas3 row format serde "org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe" stored as RCFile as select key/2 half_key, concat(value, "_con") conb from src sort by half_key, conb limit 10
PREHOOK: type: CREATETABLE_AS_SELECT
@@ -476,7 +605,7 @@ Retention: 0
#### A masked pattern was here ####
Table Type: MANAGED_TABLE
Table Parameters:
- COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"conb\":\"true\",\"half_key\":\"true\"}}
bucketing_version 2
numFiles 1
numRows 10
@@ -540,7 +669,7 @@ Retention: 0
#### A masked pattern was here ####
Table Type: MANAGED_TABLE
Table Parameters:
- COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"conb\":\"true\",\"half_key\":\"true\"}}
bucketing_version 2
numFiles 1
numRows 10
@@ -572,8 +701,9 @@ STAGE DEPENDENCIES:
Stage-1 is a root stage
Stage-2 depends on stages: Stage-1
Stage-0 depends on stages: Stage-2
- Stage-4 depends on stages: Stage-0
- Stage-3 depends on stages: Stage-4
+ Stage-5 depends on stages: Stage-0, Stage-4
+ Stage-3 depends on stages: Stage-5
+ Stage-4 depends on stages: Stage-2
STAGE PLANS:
Stage: Stage-1
@@ -633,6 +763,21 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.nzhang_ctas4
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: string)
+ outputColumnNames: col1, col2
+ Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: compute_stats(col1, 'hll'), compute_stats(col2, 'hll')
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
Stage: Stage-0
Move Operator
@@ -640,7 +785,7 @@ STAGE PLANS:
hdfs directory: true
#### A masked pattern was here ####
- Stage: Stage-4
+ Stage: Stage-5
Create Table Operator:
Create Table
columns: key string, value string
@@ -653,6 +798,33 @@ STAGE PLANS:
Stage: Stage-3
Stats Work
Basic Stats Work:
+ Column Stats Desc:
+ Columns: key, value
+ Column Types: string, string
+ Table: default.nzhang_ctas4
+
+ Stage: Stage-4
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>)
+ Execution mode: vectorized
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
PREHOOK: query: create table nzhang_ctas4 row format delimited fields terminated by ',' stored as textfile as select key, value from src sort by key, value limit 10
PREHOOK: type: CREATETABLE_AS_SELECT
@@ -701,7 +873,7 @@ Retention: 0
#### A masked pattern was here ####
Table Type: MANAGED_TABLE
Table Parameters:
- COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"key\":\"true\",\"value\":\"true\"}}
bucketing_version 2
numFiles 1
numRows 10
@@ -734,8 +906,9 @@ STAGE DEPENDENCIES:
Stage-1 is a root stage
Stage-2 depends on stages: Stage-1
Stage-0 depends on stages: Stage-2
- Stage-4 depends on stages: Stage-0
- Stage-3 depends on stages: Stage-4
+ Stage-5 depends on stages: Stage-0, Stage-4
+ Stage-3 depends on stages: Stage-5
+ Stage-4 depends on stages: Stage-2
STAGE PLANS:
Stage: Stage-1
@@ -795,6 +968,21 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.nzhang_ctas5
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: string)
+ outputColumnNames: col1, col2
+ Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: compute_stats(col1, 'hll'), compute_stats(col2, 'hll')
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
Stage: Stage-0
Move Operator
@@ -802,7 +990,7 @@ STAGE PLANS:
hdfs directory: true
#### A masked pattern was here ####
- Stage: Stage-4
+ Stage: Stage-5
Create Table Operator:
Create Table
columns: key string, value string
@@ -817,6 +1005,33 @@ STAGE PLANS:
Stage: Stage-3
Stats Work
Basic Stats Work:
+ Column Stats Desc:
+ Columns: key, value
+ Column Types: string, string
+ Table: default.nzhang_ctas5
+
+ Stage: Stage-4
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>)
+ Execution mode: vectorized
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
PREHOOK: query: create table nzhang_ctas5 row format delimited fields terminated by ',' lines terminated by '\012' stored as textfile as select key, value from src sort by key, value limit 10
PREHOOK: type: CREATETABLE_AS_SELECT
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/ctas_colname.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/ctas_colname.q.out b/ql/src/test/results/clientpositive/ctas_colname.q.out
index 9cc82d1..7f7465c 100644
--- a/ql/src/test/results/clientpositive/ctas_colname.q.out
+++ b/ql/src/test/results/clientpositive/ctas_colname.q.out
@@ -13,8 +13,9 @@ POSTHOOK: Output: default@summary
STAGE DEPENDENCIES:
Stage-1 is a root stage
Stage-0 depends on stages: Stage-1
- Stage-3 depends on stages: Stage-0
- Stage-2 depends on stages: Stage-3
+ Stage-4 depends on stages: Stage-0, Stage-3
+ Stage-2 depends on stages: Stage-4
+ Stage-3 depends on stages: Stage-1
STAGE PLANS:
Stage: Stage-1
@@ -52,6 +53,21 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.summary
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: string), _col2 (type: double), _col3 (type: string)
+ outputColumnNames: col1, col2, col3, col4
+ Statistics: Num rows: 20 Data size: 200 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: compute_stats(col1, 'hll'), compute_stats(col2, 'hll'), compute_stats(col3, 'hll'), compute_stats(col4, 'hll')
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 1 Data size: 1744 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
Stage: Stage-0
Move Operator
@@ -59,7 +75,7 @@ STAGE PLANS:
hdfs directory: true
#### A masked pattern was here ####
- Stage: Stage-3
+ Stage: Stage-4
Create Table Operator:
Create Table
columns: key string, value string, _c1 double, _c2 string
@@ -71,6 +87,33 @@ STAGE PLANS:
Stage: Stage-2
Stats Work
Basic Stats Work:
+ Column Stats Desc:
+ Columns: key, value, _c1, _c2
+ Column Types: string, string, double, string
+ Table: default.summary
+
+ Stage: Stage-3
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 1744 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col2 (type: struct<columntype:string,min:double,max:double,countnulls:bigint,bitvector:binary>), _col3 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>)
+ Execution mode: vectorized
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2), compute_stats(VALUE._col3)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: NONE
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
PREHOOK: query: create table summary as select *, key + 1, concat(value, value) from src limit 20
PREHOOK: type: CREATETABLE_AS_SELECT
@@ -105,7 +148,7 @@ Retention: 0
#### A masked pattern was here ####
Table Type: MANAGED_TABLE
Table Parameters:
- COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"_c1\":\"true\",\"_c2\":\"true\",\"key\":\"true\",\"value\":\"true\"}}
bucketing_version 2
numFiles 1
numRows 20
@@ -166,8 +209,9 @@ POSTHOOK: Output: default@x4
STAGE DEPENDENCIES:
Stage-1 is a root stage
Stage-0 depends on stages: Stage-1
- Stage-3 depends on stages: Stage-0
- Stage-2 depends on stages: Stage-3
+ Stage-4 depends on stages: Stage-0, Stage-3
+ Stage-2 depends on stages: Stage-4
+ Stage-3 depends on stages: Stage-1
STAGE PLANS:
Stage: Stage-1
@@ -220,6 +264,21 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.x4
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: string), _col2 (type: int)
+ outputColumnNames: col1, col2, col3
+ Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: compute_stats(col1, 'hll'), compute_stats(col2, 'hll'), compute_stats(col3, 'hll')
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 1304 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
Stage: Stage-0
Move Operator
@@ -227,7 +286,7 @@ STAGE PLANS:
hdfs directory: true
#### A masked pattern was here ####
- Stage: Stage-3
+ Stage: Stage-4
Create Table Operator:
Create Table
columns: key string, value string, rr int
@@ -239,6 +298,33 @@ STAGE PLANS:
Stage: Stage-2
Stats Work
Basic Stats Work:
+ Column Stats Desc:
+ Columns: key, value, rr
+ Column Types: string, string, int
+ Table: default.x4
+
+ Stage: Stage-3
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 1304 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col2 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>)
+ Execution mode: vectorized
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
PREHOOK: query: create table x4 as select *, rank() over(partition by key order by value) as rr from src1
PREHOOK: type: CREATETABLE_AS_SELECT
@@ -271,7 +357,7 @@ Retention: 0
#### A masked pattern was here ####
Table Type: MANAGED_TABLE
Table Parameters:
- COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"key\":\"true\",\"rr\":\"true\",\"value\":\"true\"}}
bucketing_version 2
numFiles 1
numRows 25
@@ -338,8 +424,9 @@ STAGE DEPENDENCIES:
Stage-1 is a root stage
Stage-2 depends on stages: Stage-1
Stage-0 depends on stages: Stage-2
- Stage-4 depends on stages: Stage-0
- Stage-3 depends on stages: Stage-4
+ Stage-5 depends on stages: Stage-0, Stage-4
+ Stage-3 depends on stages: Stage-5
+ Stage-4 depends on stages: Stage-2
STAGE PLANS:
Stage: Stage-1
@@ -420,6 +507,21 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.x5
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string)
+ outputColumnNames: col1, col2, col3
+ Statistics: Num rows: 20 Data size: 200 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: compute_stats(col1, 'hll'), compute_stats(col2, 'hll'), compute_stats(col3, 'hll')
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
Stage: Stage-0
Move Operator
@@ -427,7 +529,7 @@ STAGE PLANS:
hdfs directory: true
#### A masked pattern was here ####
- Stage: Stage-4
+ Stage: Stage-5
Create Table Operator:
Create Table
columns: key string, value string, lead1 string
@@ -439,6 +541,33 @@ STAGE PLANS:
Stage: Stage-3
Stats Work
Basic Stats Work:
+ Column Stats Desc:
+ Columns: key, value, lead1
+ Column Types: string, string, string
+ Table: default.x5
+
+ Stage: Stage-4
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col2 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>)
+ Execution mode: vectorized
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
PREHOOK: query: create table x5 as select *, lead(key,1) over(partition by key order by value) as lead1 from src limit 20
PREHOOK: type: CREATETABLE_AS_SELECT
@@ -471,7 +600,7 @@ Retention: 0
#### A masked pattern was here ####
Table Type: MANAGED_TABLE
Table Parameters:
- COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"key\":\"true\",\"lead1\":\"true\",\"value\":\"true\"}}
bucketing_version 2
numFiles 1
numRows 20
@@ -559,7 +688,32 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.x6
- Execution mode: vectorized
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: string), _col2 (type: double)
+ outputColumnNames: col1, col2, col3
+ Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: compute_stats(col1, 'hll'), compute_stats(col2, 'hll'), compute_stats(col3, 'hll')
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 1304 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 1304 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col2 (type: struct<columntype:string,min:double,max:double,countnulls:bigint,bitvector:binary>)
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
Stage: Stage-7
Conditional Operator
@@ -588,6 +742,10 @@ STAGE PLANS:
Stage: Stage-2
Stats Work
Basic Stats Work:
+ Column Stats Desc:
+ Columns: key, value, _c1
+ Column Types: string, string, double
+ Table: default.x6
Stage: Stage-3
Map Reduce
@@ -650,7 +808,7 @@ Retention: 0
#### A masked pattern was here ####
Table Type: MANAGED_TABLE
Table Parameters:
- COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"_c1\":\"true\",\"key\":\"true\",\"value\":\"true\"}}
bucketing_version 2
numFiles 1
numRows 25
@@ -716,8 +874,9 @@ POSTHOOK: Output: default@x7
STAGE DEPENDENCIES:
Stage-1 is a root stage
Stage-0 depends on stages: Stage-1
- Stage-3 depends on stages: Stage-0
- Stage-2 depends on stages: Stage-3
+ Stage-4 depends on stages: Stage-0, Stage-3
+ Stage-2 depends on stages: Stage-4
+ Stage-3 depends on stages: Stage-1
STAGE PLANS:
Stage: Stage-1
@@ -758,6 +917,21 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.x7
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: string), _col2 (type: bigint)
+ outputColumnNames: col1, col2, col3
+ Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: compute_stats(col1, 'hll'), compute_stats(col2, 'hll'), compute_stats(col3, 'hll')
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 1304 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
Stage: Stage-0
Move Operator
@@ -765,7 +939,7 @@ STAGE PLANS:
hdfs directory: true
#### A masked pattern was here ####
- Stage: Stage-3
+ Stage: Stage-4
Create Table Operator:
Create Table
columns: _col0 string, _col1 string, _c1 bigint
@@ -777,6 +951,33 @@ STAGE PLANS:
Stage: Stage-2
Stats Work
Basic Stats Work:
+ Column Stats Desc:
+ Columns: _col0, _col1, _c1
+ Column Types: string, string, bigint
+ Table: default.x7
+
+ Stage: Stage-3
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 1304 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col2 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>)
+ Execution mode: vectorized
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
PREHOOK: query: create table x7 as select * from (select *, count(value) from src group by key, value) a
PREHOOK: type: CREATETABLE_AS_SELECT
@@ -809,7 +1010,7 @@ Retention: 0
#### A masked pattern was here ####
Table Type: MANAGED_TABLE
Table Parameters:
- COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"_c1\":\"true\",\"_col0\":\"true\",\"_col1\":\"true\"}}
bucketing_version 2
numFiles 1
numRows 309
@@ -1159,8 +1360,9 @@ POSTHOOK: Output: default@x8
STAGE DEPENDENCIES:
Stage-1 is a root stage
Stage-0 depends on stages: Stage-1
- Stage-3 depends on stages: Stage-0
- Stage-2 depends on stages: Stage-3
+ Stage-4 depends on stages: Stage-0, Stage-3
+ Stage-2 depends on stages: Stage-4
+ Stage-3 depends on stages: Stage-1
STAGE PLANS:
Stage: Stage-1
@@ -1201,6 +1403,21 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.x8
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: string), _col2 (type: bigint)
+ outputColumnNames: col1, col2, col3
+ Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: compute_stats(col1, 'hll'), compute_stats(col2, 'hll'), compute_stats(col3, 'hll')
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 1304 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
Stage: Stage-0
Move Operator
@@ -1208,7 +1425,7 @@ STAGE PLANS:
hdfs directory: true
#### A masked pattern was here ####
- Stage: Stage-3
+ Stage: Stage-4
Create Table Operator:
Create Table
columns: _col0 string, _col1 string, _c1 bigint
@@ -1220,6 +1437,33 @@ STAGE PLANS:
Stage: Stage-2
Stats Work
Basic Stats Work:
+ Column Stats Desc:
+ Columns: _col0, _col1, _c1
+ Column Types: string, string, bigint
+ Table: default.x8
+
+ Stage: Stage-3
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 1304 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col2 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>)
+ Execution mode: vectorized
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
PREHOOK: query: create table x8 as select * from (select *, count(value) from src group by key, value having key < 9) a
PREHOOK: type: CREATETABLE_AS_SELECT
@@ -1252,7 +1496,7 @@ Retention: 0
#### A masked pattern was here ####
Table Type: MANAGED_TABLE
Table Parameters:
- COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"_c1\":\"true\",\"_col0\":\"true\",\"_col1\":\"true\"}}
bucketing_version 2
numFiles 1
numRows 5
@@ -1298,8 +1542,9 @@ POSTHOOK: Output: default@x9
STAGE DEPENDENCIES:
Stage-1 is a root stage
Stage-0 depends on stages: Stage-1
- Stage-3 depends on stages: Stage-0
- Stage-2 depends on stages: Stage-3
+ Stage-4 depends on stages: Stage-0, Stage-3
+ Stage-2 depends on stages: Stage-4
+ Stage-3 depends on stages: Stage-1
STAGE PLANS:
Stage: Stage-1
@@ -1347,6 +1592,21 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.x9
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: string)
+ outputColumnNames: col1, col2
+ Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: compute_stats(col1, 'hll'), compute_stats(col2, 'hll')
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 964 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
Stage: Stage-0
Move Operator
@@ -1354,7 +1614,7 @@ STAGE PLANS:
hdfs directory: true
#### A masked pattern was here ####
- Stage: Stage-3
+ Stage: Stage-4
Create Table Operator:
Create Table
columns: _c0 string, key string
@@ -1366,6 +1626,33 @@ STAGE PLANS:
Stage: Stage-2
Stats Work
Basic Stats Work:
+ Column Stats Desc:
+ Columns: _c0, key
+ Column Types: string, string
+ Table: default.x9
+
+ Stage: Stage-3
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 964 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>)
+ Execution mode: vectorized
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 964 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 964 Basic stats: COMPLETE Column stats: NONE
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
PREHOOK: query: create table x9 as select * from (select max(value),key from src group by key having key < 9 AND max(value) IS NOT NULL) a
PREHOOK: type: CREATETABLE_AS_SELECT
@@ -1396,7 +1683,7 @@ Retention: 0
#### A masked pattern was here ####
Table Type: MANAGED_TABLE
Table Parameters:
- COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"_c0\":\"true\",\"key\":\"true\"}}
bucketing_version 2
numFiles 1
numRows 5
[02/35] hive git commit: HIVE-16957: Support CTAS for auto gather
column stats (Jesus Camacho Rodriguez, reviewed by Ashutosh Chauhan)
Posted by jc...@apache.org.
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/llap/vectorized_mapjoin3.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/vectorized_mapjoin3.q.out b/ql/src/test/results/clientpositive/llap/vectorized_mapjoin3.q.out
index fa9103f..4013b36 100644
--- a/ql/src/test/results/clientpositive/llap/vectorized_mapjoin3.q.out
+++ b/ql/src/test/results/clientpositive/llap/vectorized_mapjoin3.q.out
@@ -126,7 +126,7 @@ STAGE PLANS:
TableScan
alias: t1
filterExpr: (decimal0801_col is not null and int_col_1 is not null) (type: boolean)
- Statistics: Num rows: 5 Data size: 580 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 5 Data size: 580 Basic stats: COMPLETE Column stats: NONE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:decimal0801_col:decimal(8,1)/DECIMAL_64, 1:int_col_1:int, 2:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -136,7 +136,7 @@ STAGE PLANS:
native: true
predicateExpression: FilterExprAndExpr(children: SelectColumnIsNotNull(col 0:decimal(8,1)/DECIMAL_64), SelectColumnIsNotNull(col 1:int))
predicate: (decimal0801_col is not null and int_col_1 is not null) (type: boolean)
- Statistics: Num rows: 4 Data size: 464 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 5 Data size: 580 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: decimal0801_col (type: decimal(8,1)), int_col_1 (type: int)
outputColumnNames: _col0, _col1
@@ -144,7 +144,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1]
- Statistics: Num rows: 4 Data size: 464 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 5 Data size: 580 Basic stats: COMPLETE Column stats: NONE
Map Join Operator
condition map:
Inner Join 0 to 1
@@ -165,13 +165,13 @@ STAGE PLANS:
outputColumnNames: _col0
input vertices:
1 Reducer 3
- Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 5 Data size: 638 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 5 Data size: 638 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -197,7 +197,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: tt1
- Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:int_col_0:int, 1:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -208,7 +208,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0]
- Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: max(int_col_0)
Group By Vectorization:
@@ -220,7 +220,7 @@ STAGE PLANS:
projectedOutputColumnNums: [0]
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
sort order:
Reduce Sink Vectorization:
@@ -228,7 +228,7 @@ STAGE PLANS:
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
valueColumns: 0:int
- Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
value expressions: _col0 (type: int)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -274,14 +274,14 @@ STAGE PLANS:
projectedOutputColumnNums: [0]
mode: mergepartial
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
Filter Operator
Filter Vectorization:
className: VectorFilterOperator
native: true
predicateExpression: SelectColumnIsNotNull(col 0:int)
predicate: _col0 is not null (type: boolean)
- Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
@@ -291,7 +291,7 @@ STAGE PLANS:
keyColumns: 0:int
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
Stage: Stage-0
Fetch Operator
@@ -337,7 +337,7 @@ STAGE PLANS:
TableScan
alias: t1
filterExpr: (int_col_1 is not null and decimal0801_col is not null) (type: boolean)
- Statistics: Num rows: 5 Data size: 580 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 5 Data size: 580 Basic stats: COMPLETE Column stats: NONE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:decimal0801_col:decimal(8,1)/DECIMAL_64, 1:int_col_1:int, 2:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -347,7 +347,7 @@ STAGE PLANS:
native: true
predicateExpression: FilterExprAndExpr(children: SelectColumnIsNotNull(col 1:int), SelectColumnIsNotNull(col 0:decimal(8,1)/DECIMAL_64))
predicate: (decimal0801_col is not null and int_col_1 is not null) (type: boolean)
- Statistics: Num rows: 4 Data size: 464 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 5 Data size: 580 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: decimal0801_col (type: decimal(8,1)), int_col_1 (type: int)
outputColumnNames: _col0, _col1
@@ -355,7 +355,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1]
- Statistics: Num rows: 4 Data size: 464 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 5 Data size: 580 Basic stats: COMPLETE Column stats: NONE
Map Join Operator
condition map:
Inner Join 0 to 1
@@ -376,13 +376,13 @@ STAGE PLANS:
outputColumnNames: _col0
input vertices:
1 Reducer 3
- Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 5 Data size: 638 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 5 Data size: 638 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -408,7 +408,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: tt1
- Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:int_col_0:int, 1:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -419,7 +419,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0]
- Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: max(int_col_0)
Group By Vectorization:
@@ -431,7 +431,7 @@ STAGE PLANS:
projectedOutputColumnNums: [0]
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
sort order:
Reduce Sink Vectorization:
@@ -439,7 +439,7 @@ STAGE PLANS:
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
valueColumns: 0:int
- Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
value expressions: _col0 (type: int)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -485,14 +485,14 @@ STAGE PLANS:
projectedOutputColumnNums: [0]
mode: mergepartial
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
Filter Operator
Filter Vectorization:
className: VectorFilterOperator
native: true
predicateExpression: SelectColumnIsNotNull(col 0:int)
predicate: _col0 is not null (type: boolean)
- Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
@@ -502,7 +502,7 @@ STAGE PLANS:
keyColumns: 0:int
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
Stage: Stage-0
Fetch Operator
@@ -548,7 +548,7 @@ STAGE PLANS:
TableScan
alias: t1
filterExpr: (decimal0801_col is not null and int_col_1 is not null) (type: boolean)
- Statistics: Num rows: 5 Data size: 580 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 5 Data size: 580 Basic stats: COMPLETE Column stats: NONE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:decimal0801_col:decimal(8,1)/DECIMAL_64, 1:int_col_1:int, 2:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -558,7 +558,7 @@ STAGE PLANS:
native: true
predicateExpression: FilterExprAndExpr(children: SelectColumnIsNotNull(col 0:decimal(8,1)/DECIMAL_64), SelectColumnIsNotNull(col 1:int))
predicate: (decimal0801_col is not null and int_col_1 is not null) (type: boolean)
- Statistics: Num rows: 4 Data size: 464 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 5 Data size: 580 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: decimal0801_col (type: decimal(8,1)), int_col_1 (type: int)
outputColumnNames: _col0, _col1
@@ -566,7 +566,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1]
- Statistics: Num rows: 4 Data size: 464 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 5 Data size: 580 Basic stats: COMPLETE Column stats: NONE
Map Join Operator
condition map:
Inner Join 0 to 1
@@ -587,13 +587,13 @@ STAGE PLANS:
outputColumnNames: _col0
input vertices:
1 Reducer 3
- Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 5 Data size: 638 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 5 Data size: 638 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -619,7 +619,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: tt1
- Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:int_col_0:int, 1:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -630,7 +630,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0]
- Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: max(int_col_0)
Group By Vectorization:
@@ -642,7 +642,7 @@ STAGE PLANS:
projectedOutputColumnNums: [0]
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
sort order:
Reduce Sink Vectorization:
@@ -650,7 +650,7 @@ STAGE PLANS:
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
valueColumns: 0:int
- Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
value expressions: _col0 (type: int)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -696,14 +696,14 @@ STAGE PLANS:
projectedOutputColumnNums: [0]
mode: mergepartial
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
Filter Operator
Filter Vectorization:
className: VectorFilterOperator
native: true
predicateExpression: SelectColumnIsNotNull(col 0:int)
predicate: _col0 is not null (type: boolean)
- Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
@@ -713,7 +713,7 @@ STAGE PLANS:
keyColumns: 0:int
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
Stage: Stage-0
Fetch Operator
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/load_dyn_part14.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/load_dyn_part14.q.out b/ql/src/test/results/clientpositive/load_dyn_part14.q.out
index bc4d704..61718e6 100644
--- a/ql/src/test/results/clientpositive/load_dyn_part14.q.out
+++ b/ql/src/test/results/clientpositive/load_dyn_part14.q.out
@@ -73,6 +73,7 @@ STAGE PLANS:
Reduce Output Operator
sort order:
Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
+ TopN Hash Memory Usage: 0.1
Execution mode: vectorized
Reduce Operator Tree:
Limit
@@ -265,6 +266,7 @@ STAGE PLANS:
Reduce Output Operator
sort order:
Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
+ TopN Hash Memory Usage: 0.1
Execution mode: vectorized
Reduce Operator Tree:
Limit
@@ -295,6 +297,7 @@ STAGE PLANS:
Reduce Output Operator
sort order:
Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
+ TopN Hash Memory Usage: 0.1
Execution mode: vectorized
Reduce Operator Tree:
Limit
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/masking_mv.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/masking_mv.q.out b/ql/src/test/results/clientpositive/masking_mv.q.out
index 3da49df..105e54b 100644
--- a/ql/src/test/results/clientpositive/masking_mv.q.out
+++ b/ql/src/test/results/clientpositive/masking_mv.q.out
@@ -57,7 +57,32 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat
serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde
name: default.masking_test_view_n_mv
- Execution mode: vectorized
+ Select Operator
+ expressions: _col0 (type: int)
+ outputColumnNames: col1
+ Statistics: Num rows: 500 Data size: 30200 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: compute_stats(col1, 'hll')
+ mode: hash
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 424 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 424 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>)
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: compute_stats(VALUE._col0)
+ mode: mergepartial
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: NONE
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
Stage: Stage-7
Conditional Operator
@@ -86,6 +111,10 @@ STAGE PLANS:
Stage: Stage-2
Stats Work
Basic Stats Work:
+ Column Stats Desc:
+ Columns: key
+ Column Types: int
+ Table: default.masking_test_view_n_mv
Stage: Stage-9
Materialized View Work
@@ -138,7 +167,7 @@ Retention: 0
#### A masked pattern was here ####
Table Type: MATERIALIZED_VIEW
Table Parameters:
- COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"key\":\"true\"}}
bucketing_version 2
numFiles 1
numRows 500
@@ -695,7 +724,32 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat
serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde
name: default.masking_test_view_n_mv_2
- Execution mode: vectorized
+ Select Operator
+ expressions: _col0 (type: int)
+ outputColumnNames: col1
+ Statistics: Num rows: 500 Data size: 30200 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: compute_stats(col1, 'hll')
+ mode: hash
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 424 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 424 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>)
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: compute_stats(VALUE._col0)
+ mode: mergepartial
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: NONE
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
Stage: Stage-7
Conditional Operator
@@ -724,6 +778,10 @@ STAGE PLANS:
Stage: Stage-2
Stats Work
Basic Stats Work:
+ Column Stats Desc:
+ Columns: key
+ Column Types: int
+ Table: default.masking_test_view_n_mv_2
Stage: Stage-9
Materialized View Work
@@ -776,7 +834,7 @@ Retention: 0
#### A masked pattern was here ####
Table Type: MATERIALIZED_VIEW
Table Parameters:
- COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"key\":\"true\"}}
bucketing_version 2
numFiles 1
numRows 500
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/merge3.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/merge3.q.out b/ql/src/test/results/clientpositive/merge3.q.out
index fc115bd..fc8afcf 100644
--- a/ql/src/test/results/clientpositive/merge3.q.out
+++ b/ql/src/test/results/clientpositive/merge3.q.out
@@ -109,7 +109,22 @@ STAGE PLANS:
TotalFiles: 1
GatherStats: true
MultiFileSpray: false
- Execution mode: vectorized
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: string)
+ outputColumnNames: col1, col2
+ Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: compute_stats(col1, 'hll'), compute_stats(col2, 'hll')
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ null sort order:
+ sort order:
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE
+ tag: -1
+ value expressions: _col0 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>)
+ auto parallelism: false
Path -> Alias:
#### A masked pattern was here ####
Path -> Partition:
@@ -119,7 +134,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
bucketing_version 2
column.name.delimiter ,
@@ -141,7 +156,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
bucketing_version 2
column.name.delimiter ,
@@ -163,6 +178,35 @@ STAGE PLANS:
name: default.merge_src
Truncated Path -> Alias:
/merge_src [merge_src]
+ Needs Tagging: false
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+#### A masked pattern was here ####
+ NumFilesPerFileSink: 1
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE
+#### A masked pattern was here ####
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ properties:
+ columns _col0,_col1
+ columns.types struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>:struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>
+ escape.delim \
+ hive.serialization.extend.additional.nesting.levels true
+ serialization.escape.crlf true
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ TotalFiles: 1
+ GatherStats: false
+ MultiFileSpray: false
Stage: Stage-7
Conditional Operator
@@ -192,6 +236,11 @@ STAGE PLANS:
Stats Work
Basic Stats Work:
#### A masked pattern was here ####
+ Column Stats Desc:
+ Columns: key, value
+ Column Types: string, string
+ Table: default.merge_src2
+ Is Table Level Stats: true
Stage: Stage-3
Map Reduce
@@ -2346,7 +2395,7 @@ Retention: 0
#### A masked pattern was here ####
Table Type: MANAGED_TABLE
Table Parameters:
- COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"key\":\"true\",\"value\":\"true\"}}
bucketing_version 2
numFiles 1
numRows 2000
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/merge4.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/merge4.q.out b/ql/src/test/results/clientpositive/merge4.q.out
index 621601d..1a5dc73 100644
--- a/ql/src/test/results/clientpositive/merge4.q.out
+++ b/ql/src/test/results/clientpositive/merge4.q.out
@@ -2915,6 +2915,7 @@ STAGE PLANS:
Reduce Output Operator
sort order:
Statistics: Num rows: 1 Data size: 259 Basic stats: COMPLETE Column stats: COMPLETE
+ TopN Hash Memory Usage: 0.1
value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string)
TableScan
alias: src
@@ -2931,6 +2932,7 @@ STAGE PLANS:
Reduce Output Operator
sort order:
Statistics: Num rows: 1 Data size: 259 Basic stats: COMPLETE Column stats: COMPLETE
+ TopN Hash Memory Usage: 0.1
value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string)
Reduce Operator Tree:
Select Operator
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/mm_default.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/mm_default.q.out b/ql/src/test/results/clientpositive/mm_default.q.out
index 5a85554..70519b7 100644
--- a/ql/src/test/results/clientpositive/mm_default.q.out
+++ b/ql/src/test/results/clientpositive/mm_default.q.out
@@ -180,7 +180,7 @@ Retention: 0
#### A masked pattern was here ####
Table Type: MANAGED_TABLE
Table Parameters:
- COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"key\":\"true\"}}
bucketing_version 2
numFiles 1
numRows 1
@@ -252,7 +252,7 @@ Retention: 0
#### A masked pattern was here ####
Table Type: MANAGED_TABLE
Table Parameters:
- COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"key\":\"true\"}}
bucketing_version 2
numFiles 1
numRows 1
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/named_column_join.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/named_column_join.q.out b/ql/src/test/results/clientpositive/named_column_join.q.out
index 5e94f88..22fd7f5 100644
--- a/ql/src/test/results/clientpositive/named_column_join.q.out
+++ b/ql/src/test/results/clientpositive/named_column_join.q.out
@@ -468,7 +468,7 @@ Retention: 0
#### A masked pattern was here ####
Table Type: MANAGED_TABLE
Table Parameters:
- COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"a\":\"true\",\"b\":\"true\"}}
bucketing_version 2
numFiles 1
numRows 13
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/nonmr_fetch.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/nonmr_fetch.q.out b/ql/src/test/results/clientpositive/nonmr_fetch.q.out
index ca1bf15..7c1de88 100644
--- a/ql/src/test/results/clientpositive/nonmr_fetch.q.out
+++ b/ql/src/test/results/clientpositive/nonmr_fetch.q.out
@@ -1300,8 +1300,9 @@ POSTHOOK: Output: default@srcx
STAGE DEPENDENCIES:
Stage-1 is a root stage
Stage-0 depends on stages: Stage-1
- Stage-3 depends on stages: Stage-0
- Stage-2 depends on stages: Stage-3
+ Stage-4 depends on stages: Stage-0, Stage-3
+ Stage-2 depends on stages: Stage-4
+ Stage-3 depends on stages: Stage-1
STAGE PLANS:
Stage: Stage-1
@@ -1339,6 +1340,21 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.srcx
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: string)
+ outputColumnNames: col1, col2
+ Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: compute_stats(col1, 'hll'), compute_stats(col2, 'hll')
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
Stage: Stage-0
Move Operator
@@ -1346,7 +1362,7 @@ STAGE PLANS:
hdfs directory: true
#### A masked pattern was here ####
- Stage: Stage-3
+ Stage: Stage-4
Create Table Operator:
Create Table
columns: key string, value string
@@ -1358,6 +1374,33 @@ STAGE PLANS:
Stage: Stage-2
Stats Work
Basic Stats Work:
+ Column Stats Desc:
+ Columns: key, value
+ Column Types: string, string
+ Table: default.srcx
+
+ Stage: Stage-3
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>)
+ Execution mode: vectorized
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
PREHOOK: query: explain analyze table src compute statistics
PREHOOK: type: QUERY
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/nonreserved_keywords_insert_into1.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/nonreserved_keywords_insert_into1.q.out b/ql/src/test/results/clientpositive/nonreserved_keywords_insert_into1.q.out
index b195ad2..9557caf 100644
--- a/ql/src/test/results/clientpositive/nonreserved_keywords_insert_into1.q.out
+++ b/ql/src/test/results/clientpositive/nonreserved_keywords_insert_into1.q.out
@@ -41,6 +41,7 @@ STAGE PLANS:
Reduce Output Operator
sort order:
Statistics: Num rows: 100 Data size: 1000 Basic stats: COMPLETE Column stats: NONE
+ TopN Hash Memory Usage: 0.1
value expressions: _col0 (type: string), _col1 (type: string)
Execution mode: vectorized
Reduce Operator Tree:
@@ -174,6 +175,7 @@ STAGE PLANS:
Reduce Output Operator
sort order:
Statistics: Num rows: 100 Data size: 1000 Basic stats: COMPLETE Column stats: NONE
+ TopN Hash Memory Usage: 0.1
value expressions: _col0 (type: string), _col1 (type: string)
Execution mode: vectorized
Reduce Operator Tree:
@@ -316,6 +318,7 @@ STAGE PLANS:
Reduce Output Operator
sort order:
Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE
+ TopN Hash Memory Usage: 0.1
value expressions: _col0 (type: string), _col1 (type: string)
Execution mode: vectorized
Reduce Operator Tree:
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/nullformatCTAS.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/nullformatCTAS.q.out b/ql/src/test/results/clientpositive/nullformatCTAS.q.out
index 6fe3800..e6a7750 100644
--- a/ql/src/test/results/clientpositive/nullformatCTAS.q.out
+++ b/ql/src/test/results/clientpositive/nullformatCTAS.q.out
@@ -76,7 +76,32 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.null_tab3
- Execution mode: vectorized
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: string)
+ outputColumnNames: col1, col2
+ Statistics: Num rows: 1 Data size: 1300 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: compute_stats(col1, 'hll'), compute_stats(col2, 'hll')
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>)
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
Stage: Stage-7
Conditional Operator
@@ -105,6 +130,10 @@ STAGE PLANS:
Stage: Stage-2
Stats Work
Basic Stats Work:
+ Column Stats Desc:
+ Columns: a, b
+ Column Types: string, string
+ Table: default.null_tab3
Stage: Stage-3
Map Reduce
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/orc_createas1.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/orc_createas1.q.out b/ql/src/test/results/clientpositive/orc_createas1.q.out
index dd1986c..1019f8a 100644
--- a/ql/src/test/results/clientpositive/orc_createas1.q.out
+++ b/ql/src/test/results/clientpositive/orc_createas1.q.out
@@ -88,6 +88,32 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat
serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde
name: default.orc_createas1b
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: string)
+ outputColumnNames: col1, col2
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: compute_stats(col1, 'hll'), compute_stats(col2, 'hll')
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>)
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
Stage: Stage-7
Conditional Operator
@@ -116,6 +142,10 @@ STAGE PLANS:
Stage: Stage-2
Stats Work
Basic Stats Work:
+ Column Stats Desc:
+ Columns: key, value
+ Column Types: string, string
+ Table: default.orc_createas1b
Stage: Stage-3
Merge File Operator
@@ -269,6 +299,32 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat
serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde
name: default.orc_createas1c
+ Select Operator
+ expressions: _col0 (type: int), _col1 (type: string), _col2 (type: int)
+ outputColumnNames: col1, col2, col3
+ Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: compute_stats(col1, 'hll'), compute_stats(col2, 'hll'), compute_stats(col3, 'hll')
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 1288 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 1288 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col2 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>)
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
Stage: Stage-7
Conditional Operator
@@ -297,6 +353,10 @@ STAGE PLANS:
Stage: Stage-2
Stats Work
Basic Stats Work:
+ Column Stats Desc:
+ Columns: key, value, part
+ Column Types: int, string, int
+ Table: default.orc_createas1c
Stage: Stage-3
Merge File Operator
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/parallel_orderby.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/parallel_orderby.q.out b/ql/src/test/results/clientpositive/parallel_orderby.q.out
index 05d570d..77685ea 100644
--- a/ql/src/test/results/clientpositive/parallel_orderby.q.out
+++ b/ql/src/test/results/clientpositive/parallel_orderby.q.out
@@ -69,6 +69,26 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.total_ordered
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: string)
+ outputColumnNames: col1, col2
+ Statistics: Num rows: 1 Data size: 5600 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: compute_stats(col1, 'hll'), compute_stats(col2, 'hll')
+ mode: complete
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col1 (type: struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
Stage: Stage-0
Move Operator
@@ -88,13 +108,16 @@ STAGE PLANS:
Stage: Stage-2
Stats Work
Basic Stats Work:
+ Column Stats Desc:
+ Columns: key, value
+ Column Types: string, string
+ Table: default.total_ordered
PREHOOK: query: create table total_ordered as select * from src5_n2 order by key, value
PREHOOK: type: CREATETABLE_AS_SELECT
PREHOOK: Input: default@src5_n2
PREHOOK: Output: database:default
PREHOOK: Output: default@total_ordered
-java.lang.ClassCastException: org.apache.hadoop.hive.serde2.lazy.LazyStruct cannot be cast to org.apache.hadoop.hive.ql.exec.vector.VectorizedRowBatch
POSTHOOK: query: create table total_ordered as select * from src5_n2 order by key, value
POSTHOOK: type: CREATETABLE_AS_SELECT
POSTHOOK: Input: default@src5_n2
@@ -119,7 +142,7 @@ Retention: 0
#### A masked pattern was here ####
Table Type: MANAGED_TABLE
Table Parameters:
- COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"key\":\"true\",\"value\":\"true\"}}
bucketing_version 2
numFiles 1
numRows 48
@@ -230,7 +253,7 @@ Retention: 0
#### A masked pattern was here ####
Table Type: MANAGED_TABLE
Table Parameters:
- COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"key\":\"true\",\"value\":\"true\"}}
bucketing_version 2
numFiles 1
numRows 48
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/perf/spark/query70.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/perf/spark/query70.q.out b/ql/src/test/results/clientpositive/perf/spark/query70.q.out
index 56767af..d73e542 100644
--- a/ql/src/test/results/clientpositive/perf/spark/query70.q.out
+++ b/ql/src/test/results/clientpositive/perf/spark/query70.q.out
@@ -261,6 +261,7 @@ STAGE PLANS:
sort order: +
Map-reduce partition columns: _col0 (type: string)
Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE
+ TopN Hash Memory Usage: 0.1
value expressions: _col1 (type: decimal(17,2))
Reducer 11
Execution mode: vectorized
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/perf/tez/constraints/query70.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/perf/tez/constraints/query70.q.out b/ql/src/test/results/clientpositive/perf/tez/constraints/query70.q.out
index 17e2f99..a49314c 100644
--- a/ql/src/test/results/clientpositive/perf/tez/constraints/query70.q.out
+++ b/ql/src/test/results/clientpositive/perf/tez/constraints/query70.q.out
@@ -100,25 +100,25 @@ Stage-0
limit:-1
Stage-1
Reducer 6 vectorized
- File Output Operator [FS_170]
- Limit [LIM_169] (rows=1 width=492)
+ File Output Operator [FS_171]
+ Limit [LIM_170] (rows=1 width=492)
Number of rows:100
- Select Operator [SEL_168] (rows=1 width=492)
+ Select Operator [SEL_169] (rows=1 width=492)
Output:["_col0","_col1","_col2","_col3","_col4"]
<-Reducer 5 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_167]
- Select Operator [SEL_166] (rows=1 width=492)
+ SHUFFLE [RS_168]
+ Select Operator [SEL_167] (rows=1 width=492)
Output:["_col0","_col1","_col2","_col3","_col4","_col5"]
- PTF Operator [PTF_165] (rows=1 width=304)
+ PTF Operator [PTF_166] (rows=1 width=304)
Function definitions:[{},{"name:":"windowingtablefunction","order by:":"_col2 DESC NULLS LAST","partition by:":"(grouping(_col3, 1) + grouping(_col3, 0)), CASE WHEN ((grouping(_col3, 0) = 0)) THEN (_col0) ELSE (CAST( null AS STRING)) END"}]
- Select Operator [SEL_164] (rows=1 width=304)
+ Select Operator [SEL_165] (rows=1 width=304)
Output:["_col0","_col1","_col2","_col3"]
<-Reducer 4 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_163]
+ SHUFFLE [RS_164]
PartitionCols:(grouping(_col3, 1) + grouping(_col3, 0)), CASE WHEN ((grouping(_col3, 0) = 0)) THEN (_col0) ELSE (CAST( null AS STRING)) END
- Select Operator [SEL_162] (rows=1 width=304)
+ Select Operator [SEL_163] (rows=1 width=304)
Output:["_col0","_col1","_col2","_col3"]
- Group By Operator [GBY_161] (rows=1 width=304)
+ Group By Operator [GBY_162] (rows=1 width=304)
Output:["_col0","_col1","_col2","_col3"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2
<-Reducer 3 [SIMPLE_EDGE]
SHUFFLE [RS_50]
@@ -127,90 +127,92 @@ Stage-0
Output:["_col0","_col1","_col2","_col3"],aggregations:["sum(_col2)"],keys:_col0, _col1, 0L
Select Operator [SEL_47] (rows=1 width=296)
Output:["_col0","_col1","_col2"]
- Merge Join Operator [MERGEJOIN_136] (rows=1 width=296)
+ Merge Join Operator [MERGEJOIN_137] (rows=1 width=296)
Conds:RS_44._col1=RS_45._col0(Inner),Output:["_col2","_col6","_col7"]
<-Reducer 2 [SIMPLE_EDGE]
SHUFFLE [RS_44]
PartitionCols:_col1
- Merge Join Operator [MERGEJOIN_132] (rows=91197860 width=85)
- Conds:RS_147._col0=RS_139._col0(Inner),Output:["_col1","_col2"]
+ Merge Join Operator [MERGEJOIN_133] (rows=91197860 width=85)
+ Conds:RS_148._col0=RS_140._col0(Inner),Output:["_col1","_col2"]
<-Map 11 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_139]
+ SHUFFLE [RS_140]
PartitionCols:_col0
- Select Operator [SEL_138] (rows=317 width=8)
+ Select Operator [SEL_139] (rows=317 width=8)
Output:["_col0"]
- Filter Operator [FIL_137] (rows=317 width=8)
+ Filter Operator [FIL_138] (rows=317 width=8)
predicate:d_month_seq BETWEEN 1212 AND 1223
TableScan [TS_3] (rows=73049 width=8)
default@date_dim,d1,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_month_seq"]
<-Map 1 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_147]
+ SHUFFLE [RS_148]
PartitionCols:_col0
- Select Operator [SEL_146] (rows=525329897 width=114)
+ Select Operator [SEL_147] (rows=525329897 width=114)
Output:["_col0","_col1","_col2"]
- Filter Operator [FIL_145] (rows=525329897 width=114)
+ Filter Operator [FIL_146] (rows=525329897 width=114)
predicate:((ss_sold_date_sk BETWEEN DynamicValue(RS_42_d1_d_date_sk_min) AND DynamicValue(RS_42_d1_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_42_d1_d_date_sk_bloom_filter))) and ss_sold_date_sk is not null and ss_store_sk is not null)
TableScan [TS_0] (rows=575995635 width=114)
default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_sold_date_sk","ss_store_sk","ss_net_profit"]
<-Reducer 12 [BROADCAST_EDGE] vectorized
- BROADCAST [RS_144]
- Group By Operator [GBY_143] (rows=1 width=12)
+ BROADCAST [RS_145]
+ Group By Operator [GBY_144] (rows=1 width=12)
Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"]
<-Map 11 [CUSTOM_SIMPLE_EDGE] vectorized
- SHUFFLE [RS_142]
- Group By Operator [GBY_141] (rows=1 width=12)
+ SHUFFLE [RS_143]
+ Group By Operator [GBY_142] (rows=1 width=12)
Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"]
- Select Operator [SEL_140] (rows=317 width=4)
+ Select Operator [SEL_141] (rows=317 width=4)
Output:["_col0"]
- Please refer to the previous Select Operator [SEL_138]
+ Please refer to the previous Select Operator [SEL_139]
<-Reducer 10 [SIMPLE_EDGE]
SHUFFLE [RS_45]
PartitionCols:_col0
- Merge Join Operator [MERGEJOIN_135] (rows=556 width=188)
- Conds:RS_160._col2=RS_157._col0(Inner),Output:["_col0","_col1","_col2"]
+ Merge Join Operator [MERGEJOIN_136] (rows=556 width=188)
+ Conds:RS_161._col2=RS_158._col0(Inner),Output:["_col0","_col1","_col2"]
<-Map 13 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_160]
+ SHUFFLE [RS_161]
PartitionCols:_col2
- Select Operator [SEL_159] (rows=1704 width=188)
+ Select Operator [SEL_160] (rows=1704 width=188)
Output:["_col0","_col1","_col2"]
- Filter Operator [FIL_158] (rows=1704 width=188)
+ Filter Operator [FIL_159] (rows=1704 width=188)
predicate:s_state is not null
TableScan [TS_6] (rows=1704 width=188)
default@store,store,Tbl:COMPLETE,Col:COMPLETE,Output:["s_store_sk","s_county","s_state"]
<-Reducer 9 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_157]
+ SHUFFLE [RS_158]
PartitionCols:_col0
- Select Operator [SEL_156] (rows=16 width=86)
+ Select Operator [SEL_157] (rows=16 width=86)
Output:["_col0"]
- Filter Operator [FIL_155] (rows=16 width=198)
+ Filter Operator [FIL_156] (rows=16 width=198)
predicate:(rank_window_0 <= 5)
- PTF Operator [PTF_154] (rows=49 width=198)
+ PTF Operator [PTF_155] (rows=49 width=198)
Function definitions:[{},{"name:":"windowingtablefunction","order by:":"_col1 DESC NULLS LAST","partition by:":"_col0"}]
- Select Operator [SEL_153] (rows=49 width=198)
+ Select Operator [SEL_154] (rows=49 width=198)
Output:["_col0","_col1"]
<-Reducer 8 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_152]
+ SHUFFLE [RS_153]
PartitionCols:_col0
- Group By Operator [GBY_151] (rows=49 width=198)
+ Group By Operator [GBY_152] (rows=49 width=198)
Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0
<-Reducer 7 [SIMPLE_EDGE]
SHUFFLE [RS_26]
PartitionCols:_col0
Group By Operator [GBY_25] (rows=2989 width=198)
Output:["_col0","_col1"],aggregations:["sum(_col2)"],keys:_col5
- Merge Join Operator [MERGEJOIN_134] (rows=91197860 width=168)
- Conds:RS_21._col1=RS_150._col0(Inner),Output:["_col2","_col5"]
- <-Reducer 2 [SIMPLE_EDGE]
- SHUFFLE [RS_21]
- PartitionCols:_col1
- Please refer to the previous Merge Join Operator [MERGEJOIN_132]
- <-Map 14 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_150]
- PartitionCols:_col0
- Select Operator [SEL_149] (rows=1704 width=90)
- Output:["_col0","_col1"]
- Filter Operator [FIL_148] (rows=1704 width=90)
- predicate:s_state is not null
- TableScan [TS_15] (rows=1704 width=90)
- default@store,store,Tbl:COMPLETE,Col:COMPLETE,Output:["s_store_sk","s_state"]
+ Top N Key Operator [TNK_87] (rows=91197860 width=168)
+ keys:_col5,sort order:+,top n:6
+ Merge Join Operator [MERGEJOIN_135] (rows=91197860 width=168)
+ Conds:RS_21._col1=RS_151._col0(Inner),Output:["_col2","_col5"]
+ <-Reducer 2 [SIMPLE_EDGE]
+ SHUFFLE [RS_21]
+ PartitionCols:_col1
+ Please refer to the previous Merge Join Operator [MERGEJOIN_133]
+ <-Map 14 [SIMPLE_EDGE] vectorized
+ SHUFFLE [RS_151]
+ PartitionCols:_col0
+ Select Operator [SEL_150] (rows=1704 width=90)
+ Output:["_col0","_col1"]
+ Filter Operator [FIL_149] (rows=1704 width=90)
+ predicate:s_state is not null
+ TableScan [TS_15] (rows=1704 width=90)
+ default@store,store,Tbl:COMPLETE,Col:COMPLETE,Output:["s_store_sk","s_state"]
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/perf/tez/query70.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/perf/tez/query70.q.out b/ql/src/test/results/clientpositive/perf/tez/query70.q.out
index 6d2528e..8d9d06d 100644
--- a/ql/src/test/results/clientpositive/perf/tez/query70.q.out
+++ b/ql/src/test/results/clientpositive/perf/tez/query70.q.out
@@ -100,25 +100,25 @@ Stage-0
limit:-1
Stage-1
Reducer 7 vectorized
- File Output Operator [FS_168]
- Limit [LIM_167] (rows=100 width=492)
+ File Output Operator [FS_169]
+ Limit [LIM_168] (rows=100 width=492)
Number of rows:100
- Select Operator [SEL_166] (rows=720 width=492)
+ Select Operator [SEL_167] (rows=720 width=492)
Output:["_col0","_col1","_col2","_col3","_col4"]
<-Reducer 6 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_165]
- Select Operator [SEL_164] (rows=720 width=492)
+ SHUFFLE [RS_166]
+ Select Operator [SEL_165] (rows=720 width=492)
Output:["_col0","_col1","_col2","_col3","_col4","_col5"]
- PTF Operator [PTF_163] (rows=720 width=304)
+ PTF Operator [PTF_164] (rows=720 width=304)
Function definitions:[{},{"name:":"windowingtablefunction","order by:":"_col2 DESC NULLS LAST","partition by:":"(grouping(_col3, 1) + grouping(_col3, 0)), CASE WHEN ((grouping(_col3, 0) = 0)) THEN (_col0) ELSE (CAST( null AS STRING)) END"}]
- Select Operator [SEL_162] (rows=720 width=304)
+ Select Operator [SEL_163] (rows=720 width=304)
Output:["_col0","_col1","_col2","_col3"]
<-Reducer 5 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_161]
+ SHUFFLE [RS_162]
PartitionCols:(grouping(_col3, 1) + grouping(_col3, 0)), CASE WHEN ((grouping(_col3, 0) = 0)) THEN (_col0) ELSE (CAST( null AS STRING)) END
- Select Operator [SEL_160] (rows=720 width=304)
+ Select Operator [SEL_161] (rows=720 width=304)
Output:["_col0","_col1","_col2","_col3"]
- Group By Operator [GBY_159] (rows=720 width=304)
+ Group By Operator [GBY_160] (rows=720 width=304)
Output:["_col0","_col1","_col2","_col3"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0, KEY._col1, KEY._col2
<-Reducer 4 [SIMPLE_EDGE]
SHUFFLE [RS_49]
@@ -127,89 +127,91 @@ Stage-0
Output:["_col0","_col1","_col2","_col3"],aggregations:["sum(_col2)"],keys:_col0, _col1, 0L
Select Operator [SEL_46] (rows=29778893 width=207)
Output:["_col0","_col1","_col2"]
- Merge Join Operator [MERGEJOIN_134] (rows=29778893 width=207)
- Conds:RS_43._col7=RS_158._col0(Inner),Output:["_col2","_col6","_col7"]
+ Merge Join Operator [MERGEJOIN_135] (rows=29778893 width=207)
+ Conds:RS_43._col7=RS_159._col0(Inner),Output:["_col2","_col6","_col7"]
<-Reducer 10 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_158]
+ SHUFFLE [RS_159]
PartitionCols:_col0
- Select Operator [SEL_157] (rows=16 width=86)
+ Select Operator [SEL_158] (rows=16 width=86)
Output:["_col0"]
- Filter Operator [FIL_156] (rows=16 width=198)
+ Filter Operator [FIL_157] (rows=16 width=198)
predicate:(rank_window_0 <= 5)
- PTF Operator [PTF_155] (rows=49 width=198)
+ PTF Operator [PTF_156] (rows=49 width=198)
Function definitions:[{},{"name:":"windowingtablefunction","order by:":"_col1 DESC NULLS LAST","partition by:":"_col0"}]
- Select Operator [SEL_154] (rows=49 width=198)
+ Select Operator [SEL_155] (rows=49 width=198)
Output:["_col0","_col1"]
<-Reducer 9 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_153]
+ SHUFFLE [RS_154]
PartitionCols:_col0
- Group By Operator [GBY_152] (rows=49 width=198)
+ Group By Operator [GBY_153] (rows=49 width=198)
Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)"],keys:KEY._col0
<-Reducer 8 [SIMPLE_EDGE]
SHUFFLE [RS_26]
PartitionCols:_col0
Group By Operator [GBY_25] (rows=2989 width=198)
Output:["_col0","_col1"],aggregations:["sum(_col2)"],keys:_col5
- Merge Join Operator [MERGEJOIN_133] (rows=91197860 width=168)
- Conds:RS_21._col1=RS_151._col0(Inner),Output:["_col2","_col5"]
- <-Reducer 2 [SIMPLE_EDGE]
- SHUFFLE [RS_21]
- PartitionCols:_col1
- Merge Join Operator [MERGEJOIN_130] (rows=91197860 width=85)
- Conds:RS_145._col0=RS_137._col0(Inner),Output:["_col1","_col2"]
- <-Map 11 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_137]
- PartitionCols:_col0
- Select Operator [SEL_136] (rows=317 width=8)
- Output:["_col0"]
- Filter Operator [FIL_135] (rows=317 width=8)
- predicate:(d_date_sk is not null and d_month_seq BETWEEN 1212 AND 1223)
- TableScan [TS_3] (rows=73049 width=8)
- default@date_dim,d1,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_month_seq"]
- <-Map 1 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_145]
- PartitionCols:_col0
- Select Operator [SEL_144] (rows=525329897 width=114)
- Output:["_col0","_col1","_col2"]
- Filter Operator [FIL_143] (rows=525329897 width=114)
- predicate:((ss_sold_date_sk BETWEEN DynamicValue(RS_38_d1_d_date_sk_min) AND DynamicValue(RS_38_d1_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_38_d1_d_date_sk_bloom_filter))) and ss_sold_date_sk is not null and ss_store_sk is not null)
- TableScan [TS_0] (rows=575995635 width=114)
- default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_sold_date_sk","ss_store_sk","ss_net_profit"]
- <-Reducer 12 [BROADCAST_EDGE] vectorized
- BROADCAST [RS_142]
- Group By Operator [GBY_141] (rows=1 width=12)
- Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"]
- <-Map 11 [CUSTOM_SIMPLE_EDGE] vectorized
- SHUFFLE [RS_140]
- Group By Operator [GBY_139] (rows=1 width=12)
- Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"]
- Select Operator [SEL_138] (rows=317 width=4)
- Output:["_col0"]
- Please refer to the previous Select Operator [SEL_136]
- <-Map 14 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_151]
- PartitionCols:_col0
- Select Operator [SEL_150] (rows=1704 width=90)
- Output:["_col0","_col1"]
- Filter Operator [FIL_149] (rows=1704 width=90)
- predicate:(s_state is not null and s_store_sk is not null)
- TableScan [TS_15] (rows=1704 width=90)
- default@store,store,Tbl:COMPLETE,Col:COMPLETE,Output:["s_store_sk","s_state"]
+ Top N Key Operator [TNK_85] (rows=91197860 width=168)
+ keys:_col5,sort order:+,top n:6
+ Merge Join Operator [MERGEJOIN_134] (rows=91197860 width=168)
+ Conds:RS_21._col1=RS_152._col0(Inner),Output:["_col2","_col5"]
+ <-Reducer 2 [SIMPLE_EDGE]
+ SHUFFLE [RS_21]
+ PartitionCols:_col1
+ Merge Join Operator [MERGEJOIN_131] (rows=91197860 width=85)
+ Conds:RS_146._col0=RS_138._col0(Inner),Output:["_col1","_col2"]
+ <-Map 11 [SIMPLE_EDGE] vectorized
+ SHUFFLE [RS_138]
+ PartitionCols:_col0
+ Select Operator [SEL_137] (rows=317 width=8)
+ Output:["_col0"]
+ Filter Operator [FIL_136] (rows=317 width=8)
+ predicate:(d_date_sk is not null and d_month_seq BETWEEN 1212 AND 1223)
+ TableScan [TS_3] (rows=73049 width=8)
+ default@date_dim,d1,Tbl:COMPLETE,Col:COMPLETE,Output:["d_date_sk","d_month_seq"]
+ <-Map 1 [SIMPLE_EDGE] vectorized
+ SHUFFLE [RS_146]
+ PartitionCols:_col0
+ Select Operator [SEL_145] (rows=525329897 width=114)
+ Output:["_col0","_col1","_col2"]
+ Filter Operator [FIL_144] (rows=525329897 width=114)
+ predicate:((ss_sold_date_sk BETWEEN DynamicValue(RS_38_d1_d_date_sk_min) AND DynamicValue(RS_38_d1_d_date_sk_max) and in_bloom_filter(ss_sold_date_sk, DynamicValue(RS_38_d1_d_date_sk_bloom_filter))) and ss_sold_date_sk is not null and ss_store_sk is not null)
+ TableScan [TS_0] (rows=575995635 width=114)
+ default@store_sales,store_sales,Tbl:COMPLETE,Col:COMPLETE,Output:["ss_sold_date_sk","ss_store_sk","ss_net_profit"]
+ <-Reducer 12 [BROADCAST_EDGE] vectorized
+ BROADCAST [RS_143]
+ Group By Operator [GBY_142] (rows=1 width=12)
+ Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=1000000)"]
+ <-Map 11 [CUSTOM_SIMPLE_EDGE] vectorized
+ SHUFFLE [RS_141]
+ Group By Operator [GBY_140] (rows=1 width=12)
+ Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=1000000)"]
+ Select Operator [SEL_139] (rows=317 width=4)
+ Output:["_col0"]
+ Please refer to the previous Select Operator [SEL_137]
+ <-Map 14 [SIMPLE_EDGE] vectorized
+ SHUFFLE [RS_152]
+ PartitionCols:_col0
+ Select Operator [SEL_151] (rows=1704 width=90)
+ Output:["_col0","_col1"]
+ Filter Operator [FIL_150] (rows=1704 width=90)
+ predicate:(s_state is not null and s_store_sk is not null)
+ TableScan [TS_15] (rows=1704 width=90)
+ default@store,store,Tbl:COMPLETE,Col:COMPLETE,Output:["s_store_sk","s_state"]
<-Reducer 3 [SIMPLE_EDGE]
SHUFFLE [RS_43]
PartitionCols:_col7
- Merge Join Operator [MERGEJOIN_131] (rows=91197860 width=266)
- Conds:RS_40._col1=RS_148._col0(Inner),Output:["_col2","_col6","_col7"]
+ Merge Join Operator [MERGEJOIN_132] (rows=91197860 width=266)
+ Conds:RS_40._col1=RS_149._col0(Inner),Output:["_col2","_col6","_col7"]
<-Reducer 2 [SIMPLE_EDGE]
SHUFFLE [RS_40]
PartitionCols:_col1
- Please refer to the previous Merge Join Operator [MERGEJOIN_130]
+ Please refer to the previous Merge Join Operator [MERGEJOIN_131]
<-Map 13 [SIMPLE_EDGE] vectorized
- SHUFFLE [RS_148]
+ SHUFFLE [RS_149]
PartitionCols:_col0
- Select Operator [SEL_147] (rows=1704 width=188)
+ Select Operator [SEL_148] (rows=1704 width=188)
Output:["_col0","_col1","_col2"]
- Filter Operator [FIL_146] (rows=1704 width=188)
+ Filter Operator [FIL_147] (rows=1704 width=188)
predicate:(s_state is not null and s_store_sk is not null)
TableScan [TS_6] (rows=1704 width=188)
default@store,store,Tbl:COMPLETE,Col:COMPLETE,Output:["s_store_sk","s_county","s_state"]
[13/35] hive git commit: HIVE-16957: Support CTAS for auto gather
column stats (Jesus Camacho Rodriguez, reviewed by Ashutosh Chauhan)
Posted by jc...@apache.org.
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/llap/vector_groupby_grouping_id3.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/vector_groupby_grouping_id3.q.out b/ql/src/test/results/clientpositive/llap/vector_groupby_grouping_id3.q.out
index 214b865..d3e297d 100644
--- a/ql/src/test/results/clientpositive/llap/vector_groupby_grouping_id3.q.out
+++ b/ql/src/test/results/clientpositive/llap/vector_groupby_grouping_id3.q.out
@@ -66,7 +66,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: t1_n112
- Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:key:int, 1:value:int, 2:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -77,7 +77,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1]
- Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count()
Group By Vectorization:
@@ -91,14 +91,14 @@ STAGE PLANS:
keys: key (type: int), value (type: int), 0L (type: bigint)
mode: hash
outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 12 Data size: 96 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 140 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
Filter Vectorization:
className: VectorFilterOperator
native: true
predicateExpression: FilterLongColEqualLongScalar(col 2:bigint, val 1)
predicate: (_col2 = 1L) (type: boolean)
- Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 140 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int), _col1 (type: int), 1L (type: bigint)
sort order: +++
@@ -110,7 +110,7 @@ STAGE PLANS:
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
valueColumns: 3:bigint
- Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 140 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col3 (type: bigint)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -158,7 +158,7 @@ STAGE PLANS:
keys: KEY._col0 (type: int), KEY._col1 (type: int), 1L (type: bigint)
mode: mergepartial
outputColumnNames: _col0, _col1, _col3
- Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 140 Basic stats: COMPLETE Column stats: COMPLETE
pruneGroupingSetId: true
Select Operator
expressions: _col0 (type: int), _col1 (type: int), 1L (type: bigint), _col3 (type: bigint)
@@ -168,13 +168,13 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [0, 1, 3, 2]
selectExpressions: ConstantVectorExpression(val 1) -> 3:bigint
- Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 140 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 140 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -246,7 +246,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: t1_n112
- Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:key:int, 1:value:int, 2:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -257,7 +257,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1]
- Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count()
Group By Vectorization:
@@ -271,7 +271,7 @@ STAGE PLANS:
keys: _col0 (type: int), _col1 (type: int), 0L (type: bigint)
mode: hash
outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 12 Data size: 96 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 140 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int), _col1 (type: int), _col2 (type: bigint)
sort order: +++
@@ -282,7 +282,7 @@ STAGE PLANS:
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
valueColumns: 3:bigint
- Statistics: Num rows: 12 Data size: 96 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 140 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col3 (type: bigint)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -330,14 +330,14 @@ STAGE PLANS:
keys: KEY._col0 (type: int), KEY._col1 (type: int), KEY._col2 (type: bigint)
mode: mergepartial
outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 140 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
Filter Vectorization:
className: VectorFilterOperator
native: true
predicateExpression: FilterLongColEqualLongScalar(col 2:bigint, val 1)
predicate: (_col2 = 1L) (type: boolean)
- Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 140 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: int), _col1 (type: int), 1L (type: bigint), _col3 (type: bigint)
outputColumnNames: _col0, _col1, _col2, _col3
@@ -346,13 +346,13 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [0, 1, 4, 3]
selectExpressions: ConstantVectorExpression(val 1) -> 4:bigint
- Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 140 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 140 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/llap/vector_groupby_grouping_sets1.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/vector_groupby_grouping_sets1.q.out b/ql/src/test/results/clientpositive/llap/vector_groupby_grouping_sets1.q.out
index 6bb3c10..27e393f 100644
--- a/ql/src/test/results/clientpositive/llap/vector_groupby_grouping_sets1.q.out
+++ b/ql/src/test/results/clientpositive/llap/vector_groupby_grouping_sets1.q.out
@@ -74,7 +74,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: t1_n30
- Statistics: Num rows: 6 Data size: 2208 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 1020 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:a:string, 1:b:string, 2:c:string, 3:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -85,7 +85,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1]
- Statistics: Num rows: 6 Data size: 2208 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 1020 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count()
Group By Vectorization:
@@ -99,7 +99,7 @@ STAGE PLANS:
keys: a (type: string), b (type: string), 0L (type: bigint)
mode: hash
outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 24 Data size: 8832 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 2232 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: bigint)
sort order: +++
@@ -110,7 +110,7 @@ STAGE PLANS:
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
valueColumns: 3:bigint
- Statistics: Num rows: 24 Data size: 8832 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 2232 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col3 (type: bigint)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -158,7 +158,7 @@ STAGE PLANS:
keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: bigint)
mode: mergepartial
outputColumnNames: _col0, _col1, _col3
- Statistics: Num rows: 12 Data size: 4416 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 2232 Basic stats: COMPLETE Column stats: COMPLETE
pruneGroupingSetId: true
Select Operator
expressions: _col0 (type: string), _col1 (type: string), _col3 (type: bigint)
@@ -167,13 +167,13 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1, 2]
- Statistics: Num rows: 12 Data size: 4416 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 2136 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 12 Data size: 4416 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 2136 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -240,7 +240,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: t1_n30
- Statistics: Num rows: 6 Data size: 2208 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 1020 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:a:string, 1:b:string, 2:c:string, 3:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -251,7 +251,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1]
- Statistics: Num rows: 6 Data size: 2208 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 1020 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count()
Group By Vectorization:
@@ -265,7 +265,7 @@ STAGE PLANS:
keys: a (type: string), b (type: string), 0L (type: bigint)
mode: hash
outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 24 Data size: 8832 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 2232 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: bigint)
sort order: +++
@@ -276,7 +276,7 @@ STAGE PLANS:
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
valueColumns: 3:bigint
- Statistics: Num rows: 24 Data size: 8832 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 2232 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col3 (type: bigint)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -324,7 +324,7 @@ STAGE PLANS:
keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: bigint)
mode: mergepartial
outputColumnNames: _col0, _col1, _col3
- Statistics: Num rows: 12 Data size: 4416 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 2232 Basic stats: COMPLETE Column stats: COMPLETE
pruneGroupingSetId: true
Select Operator
expressions: _col0 (type: string), _col1 (type: string), _col3 (type: bigint)
@@ -333,13 +333,13 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1, 2]
- Statistics: Num rows: 12 Data size: 4416 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 2136 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 12 Data size: 4416 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 2136 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -406,7 +406,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: t1_n30
- Statistics: Num rows: 6 Data size: 2208 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 1020 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:a:string, 1:b:string, 2:c:string, 3:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -417,7 +417,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1]
- Statistics: Num rows: 6 Data size: 2208 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 1020 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count()
Group By Vectorization:
@@ -431,7 +431,7 @@ STAGE PLANS:
keys: a (type: string), b (type: string), 0L (type: bigint)
mode: hash
outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 24 Data size: 8832 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 2232 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: bigint)
sort order: +++
@@ -442,7 +442,7 @@ STAGE PLANS:
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
valueColumns: 3:bigint
- Statistics: Num rows: 24 Data size: 8832 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 2232 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col3 (type: bigint)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -490,7 +490,7 @@ STAGE PLANS:
keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: bigint)
mode: mergepartial
outputColumnNames: _col0, _col1, _col3
- Statistics: Num rows: 12 Data size: 4416 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 2232 Basic stats: COMPLETE Column stats: COMPLETE
pruneGroupingSetId: true
Select Operator
expressions: _col0 (type: string), _col1 (type: string), _col3 (type: bigint)
@@ -499,13 +499,13 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1, 2]
- Statistics: Num rows: 12 Data size: 4416 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 2136 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 12 Data size: 4416 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 2136 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -572,7 +572,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: t1_n30
- Statistics: Num rows: 6 Data size: 2208 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 1020 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:a:string, 1:b:string, 2:c:string, 3:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -583,7 +583,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1]
- Statistics: Num rows: 6 Data size: 2208 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 1020 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count()
Group By Vectorization:
@@ -597,7 +597,7 @@ STAGE PLANS:
keys: a (type: string), b (type: string), 0L (type: bigint)
mode: hash
outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 12 Data size: 4416 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 1116 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: bigint)
sort order: +++
@@ -608,7 +608,7 @@ STAGE PLANS:
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
valueColumns: 3:bigint
- Statistics: Num rows: 12 Data size: 4416 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 1116 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col3 (type: bigint)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -656,7 +656,7 @@ STAGE PLANS:
keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: bigint)
mode: mergepartial
outputColumnNames: _col0, _col1, _col3
- Statistics: Num rows: 6 Data size: 2208 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 1116 Basic stats: COMPLETE Column stats: COMPLETE
pruneGroupingSetId: true
Select Operator
expressions: _col0 (type: string), _col1 (type: string), _col3 (type: bigint)
@@ -665,13 +665,13 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1, 2]
- Statistics: Num rows: 6 Data size: 2208 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 1068 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 6 Data size: 2208 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 1068 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -734,7 +734,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: t1_n30
- Statistics: Num rows: 6 Data size: 3312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 1530 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:a:string, 1:b:string, 2:c:string, 3:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -745,7 +745,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1, 2]
- Statistics: Num rows: 6 Data size: 3312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 1530 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
Group By Vectorization:
className: VectorGroupByOperator
@@ -757,7 +757,7 @@ STAGE PLANS:
keys: a (type: string), b (type: string), c (type: string), 0L (type: bigint)
mode: hash
outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 18 Data size: 9936 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 9 Data size: 2367 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: bigint)
sort order: ++++
@@ -767,7 +767,7 @@ STAGE PLANS:
keyColumns: 0:string, 1:string, 2:string, 3:bigint
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 18 Data size: 9936 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 9 Data size: 2367 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized, llap
LLAP IO: all inputs
Map Vectorization:
@@ -812,7 +812,7 @@ STAGE PLANS:
keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: string), KEY._col3 (type: bigint)
mode: mergepartial
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 9 Data size: 4968 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 9 Data size: 2367 Basic stats: COMPLETE Column stats: COMPLETE
pruneGroupingSetId: true
Select Operator
expressions: _col0 (type: string)
@@ -821,13 +821,13 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0]
- Statistics: Num rows: 9 Data size: 4968 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 9 Data size: 765 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 9 Data size: 4968 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 9 Data size: 765 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -893,7 +893,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: t1_n30
- Statistics: Num rows: 6 Data size: 1104 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 510 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:a:string, 1:b:string, 2:c:string, 3:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -904,7 +904,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0]
- Statistics: Num rows: 6 Data size: 1104 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 510 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
Group By Vectorization:
className: VectorGroupByOperator
@@ -916,7 +916,7 @@ STAGE PLANS:
keys: a (type: string)
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 6 Data size: 1104 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 255 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
@@ -926,7 +926,7 @@ STAGE PLANS:
keyColumns: 0:string
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 6 Data size: 1104 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 255 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized, llap
LLAP IO: all inputs
Map Vectorization:
@@ -971,13 +971,13 @@ STAGE PLANS:
keys: KEY._col0 (type: string)
mode: mergepartial
outputColumnNames: _col0
- Statistics: Num rows: 3 Data size: 552 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 255 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 3 Data size: 552 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 255 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -1034,7 +1034,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: t1_n30
- Statistics: Num rows: 6 Data size: 2208 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 1020 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:a:string, 1:b:string, 2:c:string, 3:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -1046,7 +1046,7 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [6]
selectExpressions: DoubleColAddDoubleColumn(col 4:double, col 5:double)(children: CastStringToDouble(col 0:string) -> 4:double, CastStringToDouble(col 1:string) -> 5:double) -> 6:double
- Statistics: Num rows: 6 Data size: 2208 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 1020 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count()
Group By Vectorization:
@@ -1060,7 +1060,7 @@ STAGE PLANS:
keys: _col0 (type: double)
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 6 Data size: 2208 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: double)
sort order: +
@@ -1071,7 +1071,7 @@ STAGE PLANS:
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
valueColumns: 1:bigint
- Statistics: Num rows: 6 Data size: 2208 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: bigint)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -1119,13 +1119,13 @@ STAGE PLANS:
keys: KEY._col0 (type: double)
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 3 Data size: 1104 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 3 Data size: 1104 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/llap/vector_groupby_grouping_sets2.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/vector_groupby_grouping_sets2.q.out b/ql/src/test/results/clientpositive/llap/vector_groupby_grouping_sets2.q.out
index 135c531..4cf6c89 100644
--- a/ql/src/test/results/clientpositive/llap/vector_groupby_grouping_sets2.q.out
+++ b/ql/src/test/results/clientpositive/llap/vector_groupby_grouping_sets2.q.out
@@ -60,7 +60,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: t1_n69
- Statistics: Num rows: 6 Data size: 2208 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 1020 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:a:string, 1:b:string, 2:c:string, 3:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -71,7 +71,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1]
- Statistics: Num rows: 6 Data size: 2208 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 1020 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count()
Group By Vectorization:
@@ -85,7 +85,7 @@ STAGE PLANS:
keys: a (type: string), b (type: string)
mode: hash
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 6 Data size: 2208 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 534 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string), _col1 (type: string)
sort order: ++
@@ -96,7 +96,7 @@ STAGE PLANS:
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
valueColumns: 2:bigint
- Statistics: Num rows: 6 Data size: 2208 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 534 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col2 (type: bigint)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -144,7 +144,7 @@ STAGE PLANS:
keys: KEY._col0 (type: string), KEY._col1 (type: string), 0L (type: bigint)
mode: partials
outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 24 Data size: 8832 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 2232 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: bigint)
sort order: +++
@@ -155,7 +155,7 @@ STAGE PLANS:
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
valueColumns: 3:bigint
- Statistics: Num rows: 24 Data size: 8832 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 2232 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col3 (type: bigint)
Reducer 3
Execution mode: vectorized, llap
@@ -186,7 +186,7 @@ STAGE PLANS:
keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: bigint)
mode: final
outputColumnNames: _col0, _col1, _col3
- Statistics: Num rows: 12 Data size: 4416 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 2232 Basic stats: COMPLETE Column stats: COMPLETE
pruneGroupingSetId: true
Select Operator
expressions: _col0 (type: string), _col1 (type: string), _col3 (type: bigint)
@@ -195,13 +195,13 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1, 2]
- Statistics: Num rows: 12 Data size: 4416 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 2136 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 12 Data size: 4416 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 2136 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -245,7 +245,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: t1_n69
- Statistics: Num rows: 6 Data size: 2208 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 1020 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:a:string, 1:b:string, 2:c:string, 3:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -256,7 +256,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1]
- Statistics: Num rows: 6 Data size: 2208 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 1020 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count()
Group By Vectorization:
@@ -270,7 +270,7 @@ STAGE PLANS:
keys: a (type: string), b (type: string)
mode: hash
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 6 Data size: 2208 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 534 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string), _col1 (type: string)
sort order: ++
@@ -281,7 +281,7 @@ STAGE PLANS:
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
valueColumns: 2:bigint
- Statistics: Num rows: 6 Data size: 2208 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 534 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col2 (type: bigint)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -329,7 +329,7 @@ STAGE PLANS:
keys: KEY._col0 (type: string), KEY._col1 (type: string), 0L (type: bigint)
mode: partials
outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 24 Data size: 8832 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 2232 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: bigint)
sort order: +++
@@ -340,7 +340,7 @@ STAGE PLANS:
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
valueColumns: 3:bigint
- Statistics: Num rows: 24 Data size: 8832 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 2232 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col3 (type: bigint)
Reducer 3
Execution mode: vectorized, llap
@@ -371,7 +371,7 @@ STAGE PLANS:
keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: bigint)
mode: final
outputColumnNames: _col0, _col1, _col3
- Statistics: Num rows: 12 Data size: 4416 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 2232 Basic stats: COMPLETE Column stats: COMPLETE
pruneGroupingSetId: true
Select Operator
expressions: _col0 (type: string), _col1 (type: string), _col3 (type: bigint)
@@ -380,13 +380,13 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1, 2]
- Statistics: Num rows: 12 Data size: 4416 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 2136 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 12 Data size: 4416 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 2136 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -454,22 +454,22 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: t1_n69
- Statistics: Num rows: 6 Data size: 3312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 1530 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: a (type: string), b (type: string), c (type: string)
outputColumnNames: a, b, c
- Statistics: Num rows: 6 Data size: 3312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 1530 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: sum(c)
keys: a (type: string), b (type: string)
mode: hash
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 6 Data size: 3312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 534 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string), _col1 (type: string)
sort order: ++
Map-reduce partition columns: _col0 (type: string), _col1 (type: string)
- Statistics: Num rows: 6 Data size: 3312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 534 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col2 (type: double)
Execution mode: llap
LLAP IO: all inputs
@@ -508,7 +508,7 @@ STAGE PLANS:
keys: KEY._col0 (type: string), KEY._col1 (type: string), 0L (type: bigint)
mode: partials
outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 24 Data size: 13248 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 2232 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: bigint)
sort order: +++
@@ -519,7 +519,7 @@ STAGE PLANS:
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
valueColumns: 3:double
- Statistics: Num rows: 24 Data size: 13248 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 2232 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col3 (type: double)
Reducer 3
Execution mode: vectorized, llap
@@ -550,7 +550,7 @@ STAGE PLANS:
keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: bigint)
mode: final
outputColumnNames: _col0, _col1, _col3
- Statistics: Num rows: 12 Data size: 6624 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 2232 Basic stats: COMPLETE Column stats: COMPLETE
pruneGroupingSetId: true
Select Operator
expressions: _col0 (type: string), _col1 (type: string), _col3 (type: double)
@@ -559,13 +559,13 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1, 2]
- Statistics: Num rows: 12 Data size: 6624 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 2136 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 12 Data size: 6624 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 2136 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/llap/vector_groupby_grouping_sets3.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/vector_groupby_grouping_sets3.q.out b/ql/src/test/results/clientpositive/llap/vector_groupby_grouping_sets3.q.out
index 077f6c7..cf5e8a6 100644
--- a/ql/src/test/results/clientpositive/llap/vector_groupby_grouping_sets3.q.out
+++ b/ql/src/test/results/clientpositive/llap/vector_groupby_grouping_sets3.q.out
@@ -67,22 +67,22 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: t1_n106
- Statistics: Num rows: 12 Data size: 6624 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 3060 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: a (type: string), b (type: string), c (type: string)
outputColumnNames: a, b, c
- Statistics: Num rows: 12 Data size: 6624 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 3060 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: sum(c), count(c), count()
keys: a (type: string), b (type: string), 0L (type: bigint)
mode: hash
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
- Statistics: Num rows: 48 Data size: 26496 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 24 Data size: 4848 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: bigint)
sort order: +++
Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: bigint)
- Statistics: Num rows: 48 Data size: 26496 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 24 Data size: 4848 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col3 (type: double), _col4 (type: bigint), _col5 (type: bigint)
Execution mode: llap
LLAP IO: all inputs
@@ -121,7 +121,7 @@ STAGE PLANS:
keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: bigint)
mode: mergepartial
outputColumnNames: _col0, _col1, _col3, _col4, _col5
- Statistics: Num rows: 24 Data size: 13248 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 24 Data size: 4848 Basic stats: COMPLETE Column stats: COMPLETE
pruneGroupingSetId: true
Select Operator
expressions: _col0 (type: string), _col1 (type: string), (_col3 / _col4) (type: double), _col5 (type: bigint)
@@ -131,13 +131,13 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [0, 1, 5, 4]
selectExpressions: DoubleColDivideLongColumn(col 2:double, col 3:bigint) -> 5:double
- Statistics: Num rows: 24 Data size: 13248 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 24 Data size: 4464 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 24 Data size: 13248 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 24 Data size: 4464 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -180,22 +180,22 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: t1_n106
- Statistics: Num rows: 12 Data size: 6624 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 3060 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: a (type: string), b (type: string), c (type: string)
outputColumnNames: a, b, c
- Statistics: Num rows: 12 Data size: 6624 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 3060 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: sum(c), count(c), count()
keys: a (type: string), b (type: string), 0L (type: bigint)
mode: hash
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
- Statistics: Num rows: 48 Data size: 26496 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 24 Data size: 4848 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: bigint)
sort order: +++
Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: bigint)
- Statistics: Num rows: 48 Data size: 26496 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 24 Data size: 4848 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col3 (type: double), _col4 (type: bigint), _col5 (type: bigint)
Execution mode: llap
LLAP IO: all inputs
@@ -234,7 +234,7 @@ STAGE PLANS:
keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: bigint)
mode: mergepartial
outputColumnNames: _col0, _col1, _col3, _col4, _col5
- Statistics: Num rows: 24 Data size: 13248 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 24 Data size: 4848 Basic stats: COMPLETE Column stats: COMPLETE
pruneGroupingSetId: true
Select Operator
expressions: _col0 (type: string), _col1 (type: string), (_col3 / _col4) (type: double), _col5 (type: bigint)
@@ -244,13 +244,13 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [0, 1, 5, 4]
selectExpressions: DoubleColDivideLongColumn(col 2:double, col 3:bigint) -> 5:double
- Statistics: Num rows: 24 Data size: 13248 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 24 Data size: 4464 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 24 Data size: 13248 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 24 Data size: 4464 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -319,22 +319,22 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: t1_n106
- Statistics: Num rows: 12 Data size: 6624 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 3060 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: a (type: string), b (type: string), c (type: string)
outputColumnNames: a, b, c
- Statistics: Num rows: 12 Data size: 6624 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 3060 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: sum(c), count(c), count()
keys: a (type: string), b (type: string)
mode: hash
outputColumnNames: _col0, _col1, _col2, _col3, _col4
- Statistics: Num rows: 12 Data size: 6624 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 1164 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string), _col1 (type: string)
sort order: ++
Map-reduce partition columns: _col0 (type: string), _col1 (type: string)
- Statistics: Num rows: 12 Data size: 6624 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 1164 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col2 (type: double), _col3 (type: bigint), _col4 (type: bigint)
Execution mode: llap
LLAP IO: all inputs
@@ -373,7 +373,7 @@ STAGE PLANS:
keys: KEY._col0 (type: string), KEY._col1 (type: string), 0L (type: bigint)
mode: partials
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
- Statistics: Num rows: 48 Data size: 26496 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 24 Data size: 4848 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: bigint)
sort order: +++
@@ -384,7 +384,7 @@ STAGE PLANS:
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
valueColumns: 3:double, 4:bigint, 5:bigint
- Statistics: Num rows: 48 Data size: 26496 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 24 Data size: 4848 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col3 (type: double), _col4 (type: bigint), _col5 (type: bigint)
Reducer 3
Execution mode: vectorized, llap
@@ -415,7 +415,7 @@ STAGE PLANS:
keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: bigint)
mode: final
outputColumnNames: _col0, _col1, _col3, _col4, _col5
- Statistics: Num rows: 24 Data size: 13248 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 24 Data size: 4848 Basic stats: COMPLETE Column stats: COMPLETE
pruneGroupingSetId: true
Select Operator
expressions: _col0 (type: string), _col1 (type: string), (_col3 / _col4) (type: double), _col5 (type: bigint)
@@ -425,13 +425,13 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [0, 1, 5, 4]
selectExpressions: DoubleColDivideLongColumn(col 2:double, col 3:bigint) -> 5:double
- Statistics: Num rows: 24 Data size: 13248 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 24 Data size: 4464 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 24 Data size: 13248 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 24 Data size: 4464 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/llap/vector_groupby_grouping_sets3_dec.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/vector_groupby_grouping_sets3_dec.q.out b/ql/src/test/results/clientpositive/llap/vector_groupby_grouping_sets3_dec.q.out
index 50f9ad3..1999728 100644
--- a/ql/src/test/results/clientpositive/llap/vector_groupby_grouping_sets3_dec.q.out
+++ b/ql/src/test/results/clientpositive/llap/vector_groupby_grouping_sets3_dec.q.out
@@ -67,7 +67,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: t1_n115
- Statistics: Num rows: 12 Data size: 5760 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 3384 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:a:string, 1:b:string, 2:c_dec:decimal(10,2)/DECIMAL_64, 3:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -78,7 +78,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1, 2]
- Statistics: Num rows: 12 Data size: 5760 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 3384 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: sum(c_dec), count(c_dec), count()
Group By Vectorization:
@@ -92,7 +92,7 @@ STAGE PLANS:
keys: a (type: string), b (type: string), 0L (type: bigint)
mode: hash
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
- Statistics: Num rows: 48 Data size: 23040 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 24 Data size: 7344 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: bigint)
sort order: +++
@@ -103,7 +103,7 @@ STAGE PLANS:
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
valueColumns: 3:decimal(20,2), 4:bigint, 5:bigint
- Statistics: Num rows: 48 Data size: 23040 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 24 Data size: 7344 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col3 (type: decimal(20,2)), _col4 (type: bigint), _col5 (type: bigint)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -151,7 +151,7 @@ STAGE PLANS:
keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: bigint)
mode: mergepartial
outputColumnNames: _col0, _col1, _col3, _col4, _col5
- Statistics: Num rows: 24 Data size: 11520 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 24 Data size: 7344 Basic stats: COMPLETE Column stats: COMPLETE
pruneGroupingSetId: true
Select Operator
expressions: _col0 (type: string), _col1 (type: string), (_col3 / _col4) (type: decimal(38,20)), _col5 (type: bigint)
@@ -161,13 +161,13 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [0, 1, 6, 4]
selectExpressions: DecimalColDivideDecimalColumn(col 2:decimal(20,2), col 5:decimal(19,0))(children: CastLongToDecimal(col 3:bigint) -> 5:decimal(19,0)) -> 6:decimal(38,20)
- Statistics: Num rows: 24 Data size: 11520 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 24 Data size: 6960 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 24 Data size: 11520 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 24 Data size: 6960 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -210,7 +210,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: t1_n115
- Statistics: Num rows: 12 Data size: 5760 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 3384 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:a:string, 1:b:string, 2:c_dec:decimal(10,2)/DECIMAL_64, 3:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -221,7 +221,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1, 2]
- Statistics: Num rows: 12 Data size: 5760 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 3384 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: sum(c_dec), count(c_dec), count()
Group By Vectorization:
@@ -235,7 +235,7 @@ STAGE PLANS:
keys: a (type: string), b (type: string), 0L (type: bigint)
mode: hash
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
- Statistics: Num rows: 48 Data size: 23040 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 24 Data size: 7344 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: bigint)
sort order: +++
@@ -246,7 +246,7 @@ STAGE PLANS:
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
valueColumns: 3:decimal(20,2), 4:bigint, 5:bigint
- Statistics: Num rows: 48 Data size: 23040 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 24 Data size: 7344 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col3 (type: decimal(20,2)), _col4 (type: bigint), _col5 (type: bigint)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -294,7 +294,7 @@ STAGE PLANS:
keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: bigint)
mode: mergepartial
outputColumnNames: _col0, _col1, _col3, _col4, _col5
- Statistics: Num rows: 24 Data size: 11520 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 24 Data size: 7344 Basic stats: COMPLETE Column stats: COMPLETE
pruneGroupingSetId: true
Select Operator
expressions: _col0 (type: string), _col1 (type: string), (_col3 / _col4) (type: decimal(38,20)), _col5 (type: bigint)
@@ -304,13 +304,13 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [0, 1, 6, 4]
selectExpressions: DecimalColDivideDecimalColumn(col 2:decimal(20,2), col 5:decimal(19,0))(children: CastLongToDecimal(col 3:bigint) -> 5:decimal(19,0)) -> 6:decimal(38,20)
- Statistics: Num rows: 24 Data size: 11520 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 24 Data size: 6960 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 24 Data size: 11520 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 24 Data size: 6960 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -379,7 +379,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: t1_n115
- Statistics: Num rows: 12 Data size: 5760 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 3384 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:a:string, 1:b:string, 2:c_dec:decimal(10,2)/DECIMAL_64, 3:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -390,7 +390,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1, 2]
- Statistics: Num rows: 12 Data size: 5760 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 3384 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: sum(c_dec), count(c_dec), count()
Group By Vectorization:
@@ -404,7 +404,7 @@ STAGE PLANS:
keys: a (type: string), b (type: string)
mode: hash
outputColumnNames: _col0, _col1, _col2, _col3, _col4
- Statistics: Num rows: 12 Data size: 5760 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 1788 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string), _col1 (type: string)
sort order: ++
@@ -415,7 +415,7 @@ STAGE PLANS:
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
valueColumns: 2:decimal(20,2), 3:bigint, 4:bigint
- Statistics: Num rows: 12 Data size: 5760 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 1788 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col2 (type: decimal(20,2)), _col3 (type: bigint), _col4 (type: bigint)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -463,7 +463,7 @@ STAGE PLANS:
keys: KEY._col0 (type: string), KEY._col1 (type: string), 0L (type: bigint)
mode: partials
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
- Statistics: Num rows: 48 Data size: 23040 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 24 Data size: 7344 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: bigint)
sort order: +++
@@ -474,7 +474,7 @@ STAGE PLANS:
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
valueColumns: 3:decimal(20,2), 4:bigint, 5:bigint
- Statistics: Num rows: 48 Data size: 23040 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 24 Data size: 7344 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col3 (type: decimal(20,2)), _col4 (type: bigint), _col5 (type: bigint)
Reducer 3
Execution mode: vectorized, llap
@@ -505,7 +505,7 @@ STAGE PLANS:
keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: bigint)
mode: final
outputColumnNames: _col0, _col1, _col3, _col4, _col5
- Statistics: Num rows: 24 Data size: 11520 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 24 Data size: 7344 Basic stats: COMPLETE Column stats: COMPLETE
pruneGroupingSetId: true
Select Operator
expressions: _col0 (type: string), _col1 (type: string), (_col3 / _col4) (type: decimal(38,20)), _col5 (type: bigint)
@@ -515,13 +515,13 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [0, 1, 6, 4]
selectExpressions: DecimalColDivideDecimalColumn(col 2:decimal(20,2), col 5:decimal(19,0))(children: CastLongToDecimal(col 3:bigint) -> 5:decimal(19,0)) -> 6:decimal(38,20)
- Statistics: Num rows: 24 Data size: 11520 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 24 Data size: 6960 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 24 Data size: 11520 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 24 Data size: 6960 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
[22/35] hive git commit: HIVE-16957: Support CTAS for auto gather
column stats (Jesus Camacho Rodriguez, reviewed by Ashutosh Chauhan)
Posted by jc...@apache.org.
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/llap/multi_insert_lateral_view.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/multi_insert_lateral_view.q.out b/ql/src/test/results/clientpositive/llap/multi_insert_lateral_view.q.out
index 158d484..f631369 100644
--- a/ql/src/test/results/clientpositive/llap/multi_insert_lateral_view.q.out
+++ b/ql/src/test/results/clientpositive/llap/multi_insert_lateral_view.q.out
@@ -71,23 +71,23 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: src_10_n0
- Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 870 Basic stats: COMPLETE Column stats: COMPLETE
Lateral View Forward
- Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 870 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: key (type: string)
outputColumnNames: key
- Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 4310 Basic stats: COMPLETE Column stats: COMPLETE
Lateral View Join Operator
outputColumnNames: _col0, _col5
- Statistics: Num rows: 20 Data size: 3680 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 20 Data size: 5910 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: string), CAST( _col5 AS STRING) (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 20 Data size: 3680 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 20 Data size: 5420 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 20 Data size: 3680 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 20 Data size: 5420 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
@@ -96,33 +96,33 @@ STAGE PLANS:
Select Operator
expressions: _col0 (type: string), _col1 (type: string)
outputColumnNames: key, value
- Statistics: Num rows: 20 Data size: 3680 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 20 Data size: 5420 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll')
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 1684 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
- Statistics: Num rows: 1 Data size: 1684 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>)
Select Operator
expressions: array((key + 1),(key + 2)) (type: array<double>)
outputColumnNames: _col0
- Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 1600 Basic stats: COMPLETE Column stats: COMPLETE
UDTF Operator
- Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 1600 Basic stats: COMPLETE Column stats: COMPLETE
function name: explode
Lateral View Join Operator
outputColumnNames: _col0, _col5
- Statistics: Num rows: 20 Data size: 3680 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 20 Data size: 5910 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: string), CAST( _col5 AS STRING) (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 20 Data size: 3680 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 20 Data size: 5420 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 20 Data size: 3680 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 20 Data size: 5420 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
@@ -131,32 +131,32 @@ STAGE PLANS:
Select Operator
expressions: _col0 (type: string), _col1 (type: string)
outputColumnNames: key, value
- Statistics: Num rows: 20 Data size: 3680 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 20 Data size: 5420 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll')
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 1684 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
- Statistics: Num rows: 1 Data size: 1684 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>)
Lateral View Forward
- Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 870 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: key (type: string)
outputColumnNames: key
- Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 4310 Basic stats: COMPLETE Column stats: COMPLETE
Lateral View Join Operator
outputColumnNames: _col0, _col5
- Statistics: Num rows: 20 Data size: 3680 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 20 Data size: 5910 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: string), CAST( _col5 AS STRING) (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 20 Data size: 3680 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 20 Data size: 5420 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 20 Data size: 3680 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 20 Data size: 5420 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
@@ -165,33 +165,33 @@ STAGE PLANS:
Select Operator
expressions: _col0 (type: string), _col1 (type: string)
outputColumnNames: key, value
- Statistics: Num rows: 20 Data size: 3680 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 20 Data size: 5420 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll')
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 1684 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
- Statistics: Num rows: 1 Data size: 1684 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>)
Select Operator
expressions: array((key + 3),(key + 4)) (type: array<double>)
outputColumnNames: _col0
- Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 1600 Basic stats: COMPLETE Column stats: COMPLETE
UDTF Operator
- Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 1600 Basic stats: COMPLETE Column stats: COMPLETE
function name: explode
Lateral View Join Operator
outputColumnNames: _col0, _col5
- Statistics: Num rows: 20 Data size: 3680 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 20 Data size: 5910 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: string), CAST( _col5 AS STRING) (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 20 Data size: 3680 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 20 Data size: 5420 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 20 Data size: 3680 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 20 Data size: 5420 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
@@ -200,15 +200,15 @@ STAGE PLANS:
Select Operator
expressions: _col0 (type: string), _col1 (type: string)
outputColumnNames: key, value
- Statistics: Num rows: 20 Data size: 3680 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 20 Data size: 5420 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll')
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 1684 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
- Statistics: Num rows: 1 Data size: 1684 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>)
Execution mode: llap
LLAP IO: no inputs
@@ -219,10 +219,10 @@ STAGE PLANS:
aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1)
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 1684 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 1684 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -234,10 +234,10 @@ STAGE PLANS:
aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1)
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 1684 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 1684 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -395,92 +395,92 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: src_10_n0
- Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 870 Basic stats: COMPLETE Column stats: COMPLETE
Lateral View Forward
- Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 870 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: key (type: string)
outputColumnNames: key
- Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 4310 Basic stats: COMPLETE Column stats: COMPLETE
Lateral View Join Operator
outputColumnNames: _col0, _col5
- Statistics: Num rows: 20 Data size: 3680 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 20 Data size: 5910 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: sum(_col5)
keys: _col0 (type: string)
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 20 Data size: 3680 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 950 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 20 Data size: 3680 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 950 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: double)
Select Operator
expressions: array((key + 1),(key + 2)) (type: array<double>)
outputColumnNames: _col0
- Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 1600 Basic stats: COMPLETE Column stats: COMPLETE
UDTF Operator
- Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 1600 Basic stats: COMPLETE Column stats: COMPLETE
function name: explode
Lateral View Join Operator
outputColumnNames: _col0, _col5
- Statistics: Num rows: 20 Data size: 3680 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 20 Data size: 5910 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: sum(_col5)
keys: _col0 (type: string)
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 20 Data size: 3680 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 950 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 20 Data size: 3680 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 950 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: double)
Lateral View Forward
- Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 870 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: key (type: string)
outputColumnNames: key
- Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 4310 Basic stats: COMPLETE Column stats: COMPLETE
Lateral View Join Operator
outputColumnNames: _col0, _col5
- Statistics: Num rows: 20 Data size: 3680 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 20 Data size: 5910 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: sum(_col5)
keys: _col0 (type: string)
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 20 Data size: 3680 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 950 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 20 Data size: 3680 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 950 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: double)
Select Operator
expressions: array((key + 3),(key + 4)) (type: array<double>)
outputColumnNames: _col0
- Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 1600 Basic stats: COMPLETE Column stats: COMPLETE
UDTF Operator
- Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 1600 Basic stats: COMPLETE Column stats: COMPLETE
function name: explode
Lateral View Join Operator
outputColumnNames: _col0, _col5
- Statistics: Num rows: 20 Data size: 3680 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 20 Data size: 5910 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: sum(_col5)
keys: _col0 (type: string)
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 20 Data size: 3680 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 950 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 20 Data size: 3680 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 950 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: double)
Execution mode: llap
LLAP IO: no inputs
@@ -492,14 +492,14 @@ STAGE PLANS:
keys: KEY._col0 (type: string)
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 950 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: string), CAST( _col1 AS STRING) (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 2710 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 2710 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
@@ -508,15 +508,15 @@ STAGE PLANS:
Select Operator
expressions: _col0 (type: string), _col1 (type: string)
outputColumnNames: key, value
- Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 2710 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll')
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 1684 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
- Statistics: Num rows: 1 Data size: 1684 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>)
Reducer 3
Execution mode: llap
@@ -525,10 +525,10 @@ STAGE PLANS:
aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1)
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 1684 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 1684 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -541,14 +541,14 @@ STAGE PLANS:
keys: KEY._col0 (type: string)
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 950 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: string), CAST( _col1 AS STRING) (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 2710 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 2710 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
@@ -557,15 +557,15 @@ STAGE PLANS:
Select Operator
expressions: _col0 (type: string), _col1 (type: string)
outputColumnNames: key, value
- Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 2710 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll')
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 1684 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
- Statistics: Num rows: 1 Data size: 1684 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>)
Reducer 5
Execution mode: llap
@@ -574,10 +574,10 @@ STAGE PLANS:
aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1)
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 1684 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 1684 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -722,58 +722,58 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: src_10_n0
- Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE
Lateral View Forward
- Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: key (type: string)
outputColumnNames: key
- Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 5220 Basic stats: COMPLETE Column stats: COMPLETE
Lateral View Join Operator
outputColumnNames: _col0, _col5
- Statistics: Num rows: 20 Data size: 7360 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 20 Data size: 6820 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: sum(_col5)
keys: _col0 (type: string)
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 20 Data size: 7360 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 950 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 20 Data size: 7360 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 950 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: double)
Select Operator
expressions: array((key + 1),(key + 2)) (type: array<double>)
outputColumnNames: _col0
- Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 1600 Basic stats: COMPLETE Column stats: COMPLETE
UDTF Operator
- Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 1600 Basic stats: COMPLETE Column stats: COMPLETE
function name: explode
Lateral View Join Operator
outputColumnNames: _col0, _col5
- Statistics: Num rows: 20 Data size: 7360 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 20 Data size: 6820 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: sum(_col5)
keys: _col0 (type: string)
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 20 Data size: 7360 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 950 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 20 Data size: 7360 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 950 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: double)
Filter Operator
predicate: ((key < 200) or (key > 200)) (type: boolean)
- Statistics: Num rows: 6 Data size: 2208 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 1068 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: key (type: string)
sort order: +
Map-reduce partition columns: key (type: string)
- Statistics: Num rows: 6 Data size: 2208 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 1068 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: value (type: string)
Execution mode: llap
LLAP IO: no inputs
@@ -785,14 +785,14 @@ STAGE PLANS:
keys: KEY._col0 (type: string)
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 950 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: string), CAST( _col1 AS STRING) (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 2710 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 2710 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
@@ -801,15 +801,15 @@ STAGE PLANS:
Select Operator
expressions: _col0 (type: string), _col1 (type: string)
outputColumnNames: key, value
- Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 2710 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll')
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 1952 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
- Statistics: Num rows: 1 Data size: 1952 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>)
Reducer 3
Execution mode: llap
@@ -818,10 +818,10 @@ STAGE PLANS:
aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1)
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 1952 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 1952 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -830,23 +830,23 @@ STAGE PLANS:
Execution mode: llap
Reduce Operator Tree:
Forward
- Statistics: Num rows: 6 Data size: 2208 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 1068 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: (KEY._col0 > 200) (type: boolean)
- Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count(VALUE._col0)
keys: KEY._col0 (type: string)
mode: complete
outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 190 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: string), CAST( _col1 AS STRING) (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 542 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 542 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
@@ -855,32 +855,32 @@ STAGE PLANS:
Select Operator
expressions: _col0 (type: string), _col1 (type: string)
outputColumnNames: key, value
- Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 542 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll')
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 1248 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
- Statistics: Num rows: 1 Data size: 1248 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>)
Filter Operator
predicate: (KEY._col0 < 200) (type: boolean)
- Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count(VALUE._col0)
keys: KEY._col0 (type: string)
mode: complete
outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 190 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: string), CAST( _col1 AS STRING) (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 542 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 542 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
@@ -889,15 +889,15 @@ STAGE PLANS:
Select Operator
expressions: _col0 (type: string), _col1 (type: string)
outputColumnNames: key, value
- Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 542 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll')
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 1248 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
- Statistics: Num rows: 1 Data size: 1248 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>)
Reducer 5
Execution mode: llap
@@ -906,10 +906,10 @@ STAGE PLANS:
aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1)
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 1248 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 1248 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -921,10 +921,10 @@ STAGE PLANS:
aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1)
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 1248 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 1248 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -1102,104 +1102,104 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: src_10_n0
- Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE
Lateral View Forward
- Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: key (type: string)
outputColumnNames: key
- Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 5220 Basic stats: COMPLETE Column stats: COMPLETE
Lateral View Join Operator
outputColumnNames: _col0, _col5
- Statistics: Num rows: 20 Data size: 7360 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 20 Data size: 6820 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: sum(DISTINCT _col0)
keys: _col5 (type: double), _col0 (type: string)
mode: hash
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 20 Data size: 7360 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 950 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: double), _col1 (type: string)
sort order: ++
Map-reduce partition columns: _col0 (type: double)
- Statistics: Num rows: 20 Data size: 7360 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 950 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: array((key + 1),(key + 2)) (type: array<double>)
outputColumnNames: _col0
- Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 1600 Basic stats: COMPLETE Column stats: COMPLETE
UDTF Operator
- Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 1600 Basic stats: COMPLETE Column stats: COMPLETE
function name: explode
Lateral View Join Operator
outputColumnNames: _col0, _col5
- Statistics: Num rows: 20 Data size: 7360 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 20 Data size: 6820 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: sum(DISTINCT _col0)
keys: _col5 (type: double), _col0 (type: string)
mode: hash
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 20 Data size: 7360 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 950 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: double), _col1 (type: string)
sort order: ++
Map-reduce partition columns: _col0 (type: double)
- Statistics: Num rows: 20 Data size: 7360 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 950 Basic stats: COMPLETE Column stats: COMPLETE
Lateral View Forward
- Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: key (type: string)
outputColumnNames: key
- Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 5220 Basic stats: COMPLETE Column stats: COMPLETE
Lateral View Join Operator
outputColumnNames: _col0, _col5
- Statistics: Num rows: 20 Data size: 7360 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 20 Data size: 6820 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: sum(DISTINCT _col0)
keys: _col5 (type: double), _col0 (type: string)
mode: hash
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 20 Data size: 7360 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 950 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: double), _col1 (type: string)
sort order: ++
Map-reduce partition columns: _col0 (type: double)
- Statistics: Num rows: 20 Data size: 7360 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 950 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: array((key + 3),(key + 4)) (type: array<double>)
outputColumnNames: _col0
- Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 1600 Basic stats: COMPLETE Column stats: COMPLETE
UDTF Operator
- Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 1600 Basic stats: COMPLETE Column stats: COMPLETE
function name: explode
Lateral View Join Operator
outputColumnNames: _col0, _col5
- Statistics: Num rows: 20 Data size: 7360 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 20 Data size: 6820 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: sum(DISTINCT _col0)
keys: _col5 (type: double), _col0 (type: string)
mode: hash
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 20 Data size: 7360 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 950 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: double), _col1 (type: string)
sort order: ++
Map-reduce partition columns: _col0 (type: double)
- Statistics: Num rows: 20 Data size: 7360 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 950 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: key (type: string), value (type: string)
outputColumnNames: key, value
- Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: sum(DISTINCT key)
keys: value (type: string), key (type: string)
mode: hash
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 930 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string), _col1 (type: string)
sort order: ++
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 930 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: llap
LLAP IO: no inputs
Reducer 2
@@ -1210,14 +1210,14 @@ STAGE PLANS:
keys: KEY._col0 (type: double)
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: CAST( _col0 AS STRING) (type: string), CAST( _col1 AS STRING) (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
@@ -1226,15 +1226,15 @@ STAGE PLANS:
Select Operator
expressions: _col0 (type: string), _col1 (type: string)
outputColumnNames: key, value
- Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll')
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 1952 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
- Statistics: Num rows: 1 Data size: 1952 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>)
Reducer 3
Execution mode: llap
@@ -1243,10 +1243,10 @@ STAGE PLANS:
aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1)
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 1952 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 1952 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -1259,14 +1259,14 @@ STAGE PLANS:
keys: KEY._col0 (type: double)
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: CAST( _col0 AS STRING) (type: string), CAST( _col1 AS STRING) (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
@@ -1275,15 +1275,15 @@ STAGE PLANS:
Select Operator
expressions: _col0 (type: string), _col1 (type: string)
outputColumnNames: key, value
- Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll')
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 1952 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
- Statistics: Num rows: 1 Data size: 1952 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>)
Reducer 5
Execution mode: llap
@@ -1292,10 +1292,10 @@ STAGE PLANS:
aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1)
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 1952 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 1952 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -1308,14 +1308,14 @@ STAGE PLANS:
keys: KEY._col0 (type: string)
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 5 Data size: 1840 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 495 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: string), CAST( _col1 AS STRING) (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 5 Data size: 1840 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 1375 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 5 Data size: 1840 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 1375 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
@@ -1324,15 +1324,15 @@ STAGE PLANS:
Select Operator
expressions: _col0 (type: string), _col1 (type: string)
outputColumnNames: key, value
- Statistics: Num rows: 5 Data size: 1840 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 1375 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll')
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 1256 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
- Statistics: Num rows: 1 Data size: 1256 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>)
Reducer 7
Execution mode: llap
@@ -1341,10 +1341,10 @@ STAGE PLANS:
aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1)
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 1256 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 1256 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -1567,97 +1567,97 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: src_10_n0
- Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE
Lateral View Forward
- Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: key (type: string)
outputColumnNames: key
- Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 5220 Basic stats: COMPLETE Column stats: COMPLETE
Lateral View Join Operator
outputColumnNames: _col0, _col5
- Statistics: Num rows: 20 Data size: 7360 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 20 Data size: 6820 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: sum(DISTINCT _col5)
keys: _col0 (type: string), _col5 (type: double)
mode: hash
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 20 Data size: 7360 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 950 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string), _col1 (type: double)
sort order: ++
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 20 Data size: 7360 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 950 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: array((key + 1),(key + 2)) (type: array<double>)
outputColumnNames: _col0
- Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 1600 Basic stats: COMPLETE Column stats: COMPLETE
UDTF Operator
- Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 1600 Basic stats: COMPLETE Column stats: COMPLETE
function name: explode
Lateral View Join Operator
outputColumnNames: _col0, _col5
- Statistics: Num rows: 20 Data size: 7360 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 20 Data size: 6820 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: sum(DISTINCT _col5)
keys: _col0 (type: string), _col5 (type: double)
mode: hash
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 20 Data size: 7360 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 950 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string), _col1 (type: double)
sort order: ++
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 20 Data size: 7360 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 950 Basic stats: COMPLETE Column stats: COMPLETE
Lateral View Forward
- Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: key (type: string)
outputColumnNames: key
- Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 5220 Basic stats: COMPLETE Column stats: COMPLETE
Lateral View Join Operator
outputColumnNames: _col0, _col5
- Statistics: Num rows: 20 Data size: 7360 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 20 Data size: 6820 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: sum(DISTINCT _col5)
keys: _col0 (type: string), _col5 (type: double)
mode: hash
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 20 Data size: 7360 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 950 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string), _col1 (type: double)
sort order: ++
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 20 Data size: 7360 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 950 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: array((key + 3),(key + 4)) (type: array<double>)
outputColumnNames: _col0
- Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 1600 Basic stats: COMPLETE Column stats: COMPLETE
UDTF Operator
- Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 1600 Basic stats: COMPLETE Column stats: COMPLETE
function name: explode
Lateral View Join Operator
outputColumnNames: _col0, _col5
- Statistics: Num rows: 20 Data size: 7360 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 20 Data size: 6820 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: sum(DISTINCT _col5)
keys: _col0 (type: string), _col5 (type: double)
mode: hash
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 20 Data size: 7360 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 950 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string), _col1 (type: double)
sort order: ++
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 20 Data size: 7360 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 950 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: ((key < 200) or (key > 200)) (type: boolean)
- Statistics: Num rows: 6 Data size: 2208 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 1068 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: value (type: string), key (type: string)
sort order: ++
Map-reduce partition columns: value (type: string)
- Statistics: Num rows: 6 Data size: 2208 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 1068 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: llap
LLAP IO: no inputs
Reducer 2
@@ -1668,14 +1668,14 @@ STAGE PLANS:
keys: KEY._col0 (type: string)
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 950 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: string), CAST( _col1 AS STRING) (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 2710 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 2710 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
@@ -1684,15 +1684,15 @@ STAGE PLANS:
Select Operator
expressions: _col0 (type: string), _col1 (type: string)
outputColumnNames: key, value
- Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 2710 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll')
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 1952 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
- Statistics: Num rows: 1 Data size: 1952 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>)
Reducer 3
Execution mode: llap
@@ -1701,10 +1701,10 @@ STAGE PLANS:
aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1)
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 1952 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 1952 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -1717,14 +1717,14 @@ STAGE PLANS:
keys: KEY._col0 (type: string)
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 950 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: string), CAST( _col1 AS STRING) (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 2710 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 2710 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
@@ -1733,15 +1733,15 @@ STAGE PLANS:
Select Operator
expressions: _col0 (type: string), _col1 (type: string)
outputColumnNames: key, value
- Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 2710 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll')
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 1952 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
- Statistics: Num rows: 1 Data size: 1952 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>)
Reducer 5
Execution mode: llap
@@ -1750,10 +1750,10 @@ STAGE PLANS:
aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1)
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 1952 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 1952 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -1762,23 +1762,23 @@ STAGE PLANS:
Execution mode: llap
Reduce Operator Tree:
Forward
- Statistics: Num rows: 6 Data size: 2208 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 1068 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: (KEY._col1:0._col0 > 200) (type: boolean)
- Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 182 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: sum(DISTINCT KEY._col1:0._col0)
keys: KEY._col0 (type: string)
mode: complete
outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 198 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: string), CAST( _col1 AS STRING) (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 550 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 550 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
@@ -1787,32 +1787,32 @@ STAGE PLANS:
Select Operator
expressions: _col0 (type: string), _col1 (type: string)
outputColumnNames: key, value
- Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 550 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll')
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 1248 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE
<TRUNCATED>
[11/35] hive git commit: HIVE-16957: Support CTAS for auto gather
column stats (Jesus Camacho Rodriguez, reviewed by Ashutosh Chauhan)
Posted by jc...@apache.org.
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/llap/vector_groupby_grouping_sets_grouping.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/vector_groupby_grouping_sets_grouping.q.out b/ql/src/test/results/clientpositive/llap/vector_groupby_grouping_sets_grouping.q.out
index ab33222..1799c00 100644
--- a/ql/src/test/results/clientpositive/llap/vector_groupby_grouping_sets_grouping.q.out
+++ b/ql/src/test/results/clientpositive/llap/vector_groupby_grouping_sets_grouping.q.out
@@ -62,7 +62,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: t1_n47
- Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:key:int, 1:value:int, 2:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -73,7 +73,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1]
- Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
Group By Vectorization:
className: VectorGroupByOperator
@@ -85,7 +85,7 @@ STAGE PLANS:
keys: _col0 (type: int), _col1 (type: int), 0L (type: bigint)
mode: hash
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 18 Data size: 144 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 9 Data size: 136 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int), _col1 (type: int), _col2 (type: bigint)
sort order: +++
@@ -95,7 +95,7 @@ STAGE PLANS:
keyColumns: 0:int, 1:int, 2:bigint
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 18 Data size: 144 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 9 Data size: 136 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized, llap
LLAP IO: all inputs
Map Vectorization:
@@ -140,7 +140,7 @@ STAGE PLANS:
keys: KEY._col0 (type: int), KEY._col1 (type: int), KEY._col2 (type: bigint)
mode: mergepartial
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 9 Data size: 72 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 9 Data size: 136 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: int), _col1 (type: int), _col2 (type: bigint), grouping(_col2, 1) (type: bigint), grouping(_col2, 0) (type: bigint)
outputColumnNames: _col0, _col1, _col2, _col3, _col4
@@ -149,13 +149,13 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [0, 1, 2, 3, 4]
selectExpressions: GroupingColumn(col 2, mask 2) -> 3:bigint, GroupingColumn(col 2, mask 1) -> 4:bigint
- Statistics: Num rows: 9 Data size: 72 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 9 Data size: 280 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 9 Data size: 72 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 9 Data size: 280 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -226,7 +226,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: t1_n47
- Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:key:int, 1:value:int, 2:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -237,7 +237,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1]
- Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
Group By Vectorization:
className: VectorGroupByOperator
@@ -249,7 +249,7 @@ STAGE PLANS:
keys: _col0 (type: int), _col1 (type: int), 0L (type: bigint)
mode: hash
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 24 Data size: 192 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int), _col1 (type: int), _col2 (type: bigint)
sort order: +++
@@ -259,7 +259,7 @@ STAGE PLANS:
keyColumns: 0:int, 1:int, 2:bigint
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 24 Data size: 192 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized, llap
LLAP IO: all inputs
Map Vectorization:
@@ -304,7 +304,7 @@ STAGE PLANS:
keys: KEY._col0 (type: int), KEY._col1 (type: int), KEY._col2 (type: bigint)
mode: mergepartial
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 12 Data size: 96 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: int), _col1 (type: int), _col2 (type: bigint), grouping(_col2, 1) (type: bigint), grouping(_col2, 0) (type: bigint)
outputColumnNames: _col0, _col1, _col2, _col3, _col4
@@ -313,13 +313,13 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [0, 1, 2, 3, 4]
selectExpressions: GroupingColumn(col 2, mask 2) -> 3:bigint, GroupingColumn(col 2, mask 1) -> 4:bigint
- Statistics: Num rows: 12 Data size: 96 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 372 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 12 Data size: 96 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 372 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -397,7 +397,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: t1_n47
- Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:key:int, 1:value:int, 2:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -408,7 +408,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1]
- Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
Group By Vectorization:
className: VectorGroupByOperator
@@ -420,7 +420,7 @@ STAGE PLANS:
keys: _col0 (type: int), _col1 (type: int), 0L (type: bigint)
mode: hash
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 24 Data size: 192 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int), _col1 (type: int), _col2 (type: bigint)
sort order: +++
@@ -430,7 +430,7 @@ STAGE PLANS:
keyColumns: 0:int, 1:int, 2:bigint
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 24 Data size: 192 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized, llap
LLAP IO: all inputs
Map Vectorization:
@@ -475,14 +475,14 @@ STAGE PLANS:
keys: KEY._col0 (type: int), KEY._col1 (type: int), KEY._col2 (type: bigint)
mode: mergepartial
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 12 Data size: 96 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
Filter Vectorization:
className: VectorFilterOperator
native: true
predicateExpression: FilterLongColEqualLongScalar(col 3:bigint, val 1)(children: GroupingColumn(col 2, mask 2) -> 3:bigint)
predicate: (grouping(_col2, 1) = 1) (type: boolean)
- Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 92 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: int), _col1 (type: int)
outputColumnNames: _col0, _col1
@@ -490,13 +490,13 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1]
- Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -569,7 +569,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: t1_n47
- Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:key:int, 1:value:int, 2:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -580,7 +580,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1]
- Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
Group By Vectorization:
className: VectorGroupByOperator
@@ -592,7 +592,7 @@ STAGE PLANS:
keys: _col0 (type: int), _col1 (type: int), 0L (type: bigint)
mode: hash
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 24 Data size: 192 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int), _col1 (type: int), _col2 (type: bigint)
sort order: +++
@@ -602,7 +602,7 @@ STAGE PLANS:
keyColumns: 0:int, 1:int, 2:bigint
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 24 Data size: 192 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized, llap
LLAP IO: all inputs
Map Vectorization:
@@ -647,14 +647,14 @@ STAGE PLANS:
keys: KEY._col0 (type: int), KEY._col1 (type: int), KEY._col2 (type: bigint)
mode: mergepartial
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 12 Data size: 96 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
Filter Vectorization:
className: VectorFilterOperator
native: true
predicateExpression: FilterExprOrExpr(children: FilterLongColEqualLongScalar(col 3:bigint, val 1)(children: GroupingColumn(col 2, mask 2) -> 3:bigint), FilterLongColEqualLongScalar(col 4:bigint, val 1)(children: GroupingColumn(col 2, mask 1) -> 4:bigint))
predicate: ((grouping(_col2, 0) = 1) or (grouping(_col2, 1) = 1)) (type: boolean)
- Statistics: Num rows: 12 Data size: 96 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: int), _col1 (type: int), (grouping(_col2, 1) + grouping(_col2, 0)) (type: bigint), CASE WHEN (((grouping(_col2, 1) + grouping(_col2, 0)) = 1)) THEN (_col0) ELSE (null) END (type: int)
outputColumnNames: _col0, _col1, _col2, _col3
@@ -663,7 +663,7 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [0, 1, 7, 12]
selectExpressions: LongColAddLongColumn(col 5:bigint, col 6:bigint)(children: GroupingColumn(col 2, mask 2) -> 5:bigint, GroupingColumn(col 2, mask 1) -> 6:bigint) -> 7:bigint, IfExprColumnNull(col 11:boolean, col 0:int, null)(children: LongColEqualLongScalar(col 10:bigint, val 1)(children: LongColAddLongColumn(col 8:bigint, col 9:bigint)(children: GroupingColumn(col 2, mask 2) -> 8:bigint, GroupingColumn(col 2, mask 1) -> 9:bigint) -> 10:bigint) -> 11:boolean, col 0:int) -> 12:int
- Statistics: Num rows: 12 Data size: 96 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 228 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col2 (type: bigint), _col3 (type: int)
sort order: -+
@@ -673,7 +673,7 @@ STAGE PLANS:
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
valueColumns: 0:int, 1:int
- Statistics: Num rows: 12 Data size: 96 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 228 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: int), _col1 (type: int)
Reducer 3
Execution mode: vectorized, llap
@@ -698,13 +698,13 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [2, 3, 0]
- Statistics: Num rows: 12 Data size: 96 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 12 Data size: 96 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -778,7 +778,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: t1_n47
- Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:key:int, 1:value:int, 2:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -789,7 +789,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1]
- Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
Group By Vectorization:
className: VectorGroupByOperator
@@ -801,7 +801,7 @@ STAGE PLANS:
keys: key (type: int), value (type: int), 0L (type: bigint)
mode: hash
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 18 Data size: 144 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 9 Data size: 136 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int), _col1 (type: int), _col2 (type: bigint)
sort order: +++
@@ -811,7 +811,7 @@ STAGE PLANS:
keyColumns: 0:int, 1:int, 2:bigint
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 18 Data size: 144 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 9 Data size: 136 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized, llap
LLAP IO: all inputs
Map Vectorization:
@@ -856,7 +856,7 @@ STAGE PLANS:
keys: KEY._col0 (type: int), KEY._col1 (type: int), KEY._col2 (type: bigint)
mode: mergepartial
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 9 Data size: 72 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 9 Data size: 136 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: int), _col1 (type: int), _col2 (type: bigint), grouping(_col2, 1L) (type: bigint), grouping(_col2, 0L) (type: bigint)
outputColumnNames: _col0, _col1, _col2, _col3, _col4
@@ -865,13 +865,13 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [0, 1, 2, 3, 4]
selectExpressions: GroupingColumn(col 2, mask 2) -> 3:bigint, GroupingColumn(col 2, mask 1) -> 4:bigint
- Statistics: Num rows: 9 Data size: 72 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 9 Data size: 280 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 9 Data size: 72 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 9 Data size: 280 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -942,7 +942,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: t1_n47
- Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:key:int, 1:value:int, 2:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -953,7 +953,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1]
- Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
Group By Vectorization:
className: VectorGroupByOperator
@@ -965,7 +965,7 @@ STAGE PLANS:
keys: key (type: int), value (type: int), 0L (type: bigint)
mode: hash
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 24 Data size: 192 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int), _col1 (type: int), _col2 (type: bigint)
sort order: +++
@@ -975,7 +975,7 @@ STAGE PLANS:
keyColumns: 0:int, 1:int, 2:bigint
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 24 Data size: 192 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized, llap
LLAP IO: all inputs
Map Vectorization:
@@ -1020,7 +1020,7 @@ STAGE PLANS:
keys: KEY._col0 (type: int), KEY._col1 (type: int), KEY._col2 (type: bigint)
mode: mergepartial
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 12 Data size: 96 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: int), _col1 (type: int), _col2 (type: bigint), grouping(_col2, 1L) (type: bigint), grouping(_col2, 0L) (type: bigint)
outputColumnNames: _col0, _col1, _col2, _col3, _col4
@@ -1029,13 +1029,13 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [0, 1, 2, 3, 4]
selectExpressions: GroupingColumn(col 2, mask 2) -> 3:bigint, GroupingColumn(col 2, mask 1) -> 4:bigint
- Statistics: Num rows: 12 Data size: 96 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 372 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 12 Data size: 96 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 372 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -1113,7 +1113,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: t1_n47
- Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:key:int, 1:value:int, 2:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -1124,7 +1124,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1]
- Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
Group By Vectorization:
className: VectorGroupByOperator
@@ -1136,14 +1136,14 @@ STAGE PLANS:
keys: key (type: int), value (type: int), 0L (type: bigint)
mode: hash
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 24 Data size: 192 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
Filter Vectorization:
className: VectorFilterOperator
native: true
predicateExpression: FilterLongColEqualLongScalar(col 3:bigint, val 1)(children: GroupingColumn(col 2, mask 2) -> 3:bigint)
predicate: (grouping(_col2, 1L) = 1) (type: boolean)
- Statistics: Num rows: 12 Data size: 96 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 92 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int), _col1 (type: int), _col2 (type: bigint)
sort order: +++
@@ -1153,7 +1153,7 @@ STAGE PLANS:
keyColumns: 0:int, 1:int, 2:bigint
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 12 Data size: 96 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 92 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized, llap
LLAP IO: all inputs
Map Vectorization:
@@ -1198,14 +1198,14 @@ STAGE PLANS:
keys: KEY._col0 (type: int), KEY._col1 (type: int), KEY._col2 (type: bigint)
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 92 Basic stats: COMPLETE Column stats: COMPLETE
pruneGroupingSetId: true
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 92 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -1278,7 +1278,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: t1_n47
- Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:key:int, 1:value:int, 2:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -1289,7 +1289,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1]
- Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
Group By Vectorization:
className: VectorGroupByOperator
@@ -1301,14 +1301,14 @@ STAGE PLANS:
keys: key (type: int), value (type: int), 0L (type: bigint)
mode: hash
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 24 Data size: 192 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
Filter Vectorization:
className: VectorFilterOperator
native: true
predicateExpression: FilterExprOrExpr(children: FilterLongColEqualLongScalar(col 3:bigint, val 1)(children: GroupingColumn(col 2, mask 2) -> 3:bigint), FilterLongColEqualLongScalar(col 4:bigint, val 1)(children: GroupingColumn(col 2, mask 1) -> 4:bigint))
predicate: ((grouping(_col2, 0L) = 1) or (grouping(_col2, 1L) = 1)) (type: boolean)
- Statistics: Num rows: 24 Data size: 192 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int), _col1 (type: int), _col2 (type: bigint)
sort order: +++
@@ -1318,7 +1318,7 @@ STAGE PLANS:
keyColumns: 0:int, 1:int, 2:bigint
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 24 Data size: 192 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized, llap
LLAP IO: all inputs
Map Vectorization:
@@ -1363,7 +1363,7 @@ STAGE PLANS:
keys: KEY._col0 (type: int), KEY._col1 (type: int), KEY._col2 (type: bigint)
mode: mergepartial
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 12 Data size: 96 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: int), _col1 (type: int), (grouping(_col2, 1L) + grouping(_col2, 0L)) (type: bigint)
outputColumnNames: _col0, _col1, _col2
@@ -1372,7 +1372,7 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [0, 1, 5]
selectExpressions: LongColAddLongColumn(col 3:bigint, col 4:bigint)(children: GroupingColumn(col 2, mask 2) -> 3:bigint, GroupingColumn(col 2, mask 1) -> 4:bigint) -> 5:bigint
- Statistics: Num rows: 12 Data size: 96 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col2 (type: bigint), CASE WHEN ((_col2 = 1L)) THEN (_col0) END (type: int)
sort order: -+
@@ -1383,7 +1383,7 @@ STAGE PLANS:
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
valueColumns: 0:int, 1:int
- Statistics: Num rows: 12 Data size: 96 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: int), _col1 (type: int)
Reducer 3
Execution mode: vectorized, llap
@@ -1408,13 +1408,13 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [2, 3, 0]
- Statistics: Num rows: 12 Data size: 96 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 12 Data size: 96 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -1488,7 +1488,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: t1_n47
- Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:key:int, 1:value:int, 2:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -1499,7 +1499,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1]
- Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
Group By Vectorization:
className: VectorGroupByOperator
@@ -1511,7 +1511,7 @@ STAGE PLANS:
keys: key (type: int), value (type: int)
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int), _col1 (type: int)
sort order: ++
@@ -1521,7 +1521,7 @@ STAGE PLANS:
keyColumns: 0:int, 1:int
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized, llap
LLAP IO: all inputs
Map Vectorization:
@@ -1566,7 +1566,7 @@ STAGE PLANS:
keys: KEY._col0 (type: int), KEY._col1 (type: int)
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: int), _col1 (type: int), 0L (type: bigint), 0L (type: bigint)
outputColumnNames: _col0, _col1, _col2, _col3
@@ -1575,13 +1575,13 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [0, 1, 2, 3]
selectExpressions: ConstantVectorExpression(val 0) -> 2:bigint, ConstantVectorExpression(val 0) -> 3:bigint
- Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -1647,7 +1647,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: t1_n47
- Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:key:int, 1:value:int, 2:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -1658,7 +1658,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1]
- Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
Group By Vectorization:
className: VectorGroupByOperator
@@ -1670,7 +1670,7 @@ STAGE PLANS:
keys: key (type: int), value (type: int)
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int), _col1 (type: int)
sort order: ++
@@ -1680,7 +1680,7 @@ STAGE PLANS:
keyColumns: 0:int, 1:int
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized, llap
LLAP IO: all inputs
Map Vectorization:
@@ -1725,7 +1725,7 @@ STAGE PLANS:
keys: KEY._col0 (type: int), KEY._col1 (type: int)
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: int), _col1 (type: int), 0L (type: bigint)
outputColumnNames: _col0, _col1, _col2
@@ -1734,13 +1734,13 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [0, 1, 2]
selectExpressions: ConstantVectorExpression(val 0) -> 2:bigint
- Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -1808,7 +1808,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: t1_n47
- Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:key:int, 1:value:int, 2:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -1819,7 +1819,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1]
- Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
Group By Vectorization:
className: VectorGroupByOperator
@@ -1831,7 +1831,7 @@ STAGE PLANS:
keys: key (type: int), value (type: int)
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int), _col1 (type: int)
sort order: ++
@@ -1841,7 +1841,7 @@ STAGE PLANS:
keyColumns: 0:int, 1:int
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized, llap
LLAP IO: all inputs
Map Vectorization:
@@ -1886,13 +1886,13 @@ STAGE PLANS:
keys: KEY._col0 (type: int), KEY._col1 (type: int)
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -1960,7 +1960,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: t1_n47
- Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:key:int, 1:value:int, 2:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -1971,7 +1971,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1]
- Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
Group By Vectorization:
className: VectorGroupByOperator
@@ -1983,7 +1983,7 @@ STAGE PLANS:
keys: key (type: int), value (type: int), 0L (type: bigint)
mode: hash
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 24 Data size: 192 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int), _col1 (type: int), _col2 (type: bigint)
sort order: +++
@@ -1993,7 +1993,7 @@ STAGE PLANS:
keyColumns: 0:int, 1:int, 2:bigint
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 24 Data size: 192 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized, llap
LLAP IO: all inputs
Map Vectorization:
@@ -2038,7 +2038,7 @@ STAGE PLANS:
keys: KEY._col0 (type: int), KEY._col1 (type: int), KEY._col2 (type: bigint)
mode: mergepartial
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 12 Data size: 96 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: int), _col1 (type: int), _col2 (type: bigint), grouping(_col2, 1L, 0L) (type: bigint)
outputColumnNames: _col0, _col1, _col2, _col3
@@ -2047,13 +2047,13 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [0, 1, 2, 3]
selectExpressions: GroupingColumns(col 2, masks [2, 1]) -> 3:bigint
- Statistics: Num rows: 12 Data size: 96 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 276 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 12 Data size: 96 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 276 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -2129,7 +2129,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: t1_n47
- Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:key:int, 1:value:int, 2:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -2140,7 +2140,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1]
- Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
Group By Vectorization:
className: VectorGroupByOperator
@@ -2152,7 +2152,7 @@ STAGE PLANS:
keys: key (type: int), value (type: int), 0L (type: bigint)
mode: hash
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 24 Data size: 192 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int), _col1 (type: int), _col2 (type: bigint)
sort order: +++
@@ -2162,7 +2162,7 @@ STAGE PLANS:
keyColumns: 0:int, 1:int, 2:bigint
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 24 Data size: 192 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized, llap
LLAP IO: all inputs
Map Vectorization:
@@ -2207,7 +2207,7 @@ STAGE PLANS:
keys: KEY._col0 (type: int), KEY._col1 (type: int), KEY._col2 (type: bigint)
mode: mergepartial
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 12 Data size: 96 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: int), _col1 (type: int), _col2 (type: bigint), grouping(_col2, 0L, 1L) (type: bigint)
outputColumnNames: _col0, _col1, _col2, _col3
@@ -2216,13 +2216,13 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [0, 1, 2, 3]
selectExpressions: GroupingColumns(col 2, masks [1, 2]) -> 3:bigint
- Statistics: Num rows: 12 Data size: 96 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 276 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 12 Data size: 96 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 276 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -2298,7 +2298,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: t1_n47
- Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:key:int, 1:value:int, 2:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -2309,7 +2309,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1]
- Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
Group By Vectorization:
className: VectorGroupByOperator
@@ -2321,7 +2321,7 @@ STAGE PLANS:
keys: key (type: int), value (type: int), 0L (type: bigint)
mode: hash
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 18 Data size: 144 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 9 Data size: 136 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int), _col1 (type: int), _col2 (type: bigint)
sort order: +++
@@ -2331,7 +2331,7 @@ STAGE PLANS:
keyColumns: 0:int, 1:int, 2:bigint
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 18 Data size: 144 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 9 Data size: 136 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized, llap
LLAP IO: all inputs
Map Vectorization:
@@ -2376,7 +2376,7 @@ STAGE PLANS:
keys: KEY._col0 (type: int), KEY._col1 (type: int), KEY._col2 (type: bigint)
mode: mergepartial
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 9 Data size: 72 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 9 Data size: 136 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: int), _col1 (type: int), _col2 (type: bigint), grouping(_col2, 1L, 0L) (type: bigint)
outputColumnNames: _col0, _col1, _col2, _col3
@@ -2385,13 +2385,13 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [0, 1, 2, 3]
selectExpressions: GroupingColumns(col 2, masks [2, 1]) -> 3:bigint
- Statistics: Num rows: 9 Data size: 72 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 9 Data size: 208 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 9 Data size: 72 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 9 Data size: 208 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -2462,7 +2462,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: t1_n47
- Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:key:int, 1:value:int, 2:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -2473,7 +2473,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1]
- Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
Group By Vectorization:
className: VectorGroupByOperator
@@ -2485,7 +2485,7 @@ STAGE PLANS:
keys: key (type: int), value (type: int), 0L (type: bigint)
mode: hash
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 18 Data size: 144 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 9 Data size: 136 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int), _col1 (type: int), _col2 (type: bigint)
sort order: +++
@@ -2495,7 +2495,7 @@ STAGE PLANS:
keyColumns: 0:int, 1:int, 2:bigint
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 18 Data size: 144 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 9 Data size: 136 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized, llap
LLAP IO: all inputs
Map Vectorization:
@@ -2540,7 +2540,7 @@ STAGE PLANS:
keys: KEY._col0 (type: int), KEY._col1 (type: int), KEY._col2 (type: bigint)
mode: mergepartial
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 9 Data size: 72 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 9 Data size: 136 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: int), _col1 (type: int), _col2 (type: bigint), grouping(_col2, 0L, 1L) (type: bigint)
outputColumnNames: _col0, _col1, _col2, _col3
@@ -2549,13 +2549,13 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [0, 1, 2, 3]
selectExpressions: GroupingColumns(col 2, masks [1, 2]) -> 3:bigint
- Statistics: Num rows: 9 Data size: 72 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 9 Data size: 208 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 9 Data size: 72 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 9 Data size: 208 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
[05/35] hive git commit: HIVE-16957: Support CTAS for auto gather
column stats (Jesus Camacho Rodriguez, reviewed by Ashutosh Chauhan)
Posted by jc...@apache.org.
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/llap/vector_reduce_groupby_decimal.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/vector_reduce_groupby_decimal.q.out b/ql/src/test/results/clientpositive/llap/vector_reduce_groupby_decimal.q.out
index 62887c4..a0051f1 100644
--- a/ql/src/test/results/clientpositive/llap/vector_reduce_groupby_decimal.q.out
+++ b/ql/src/test/results/clientpositive/llap/vector_reduce_groupby_decimal.q.out
@@ -54,7 +54,7 @@ STAGE PLANS:
TableScan
alias: decimal_test_n2
filterExpr: (cdecimal1 is not null and cdecimal2 is not null) (type: boolean)
- Statistics: Num rows: 6102 Data size: 1368328 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6102 Data size: 1440072 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
Filter Operator
@@ -63,11 +63,11 @@ STAGE PLANS:
native: true
predicateExpression: FilterExprAndExpr(children: SelectColumnIsNotNull(col 2:decimal(20,10)), SelectColumnIsNotNull(col 3:decimal(23,14)))
predicate: (cdecimal1 is not null and cdecimal2 is not null) (type: boolean)
- Statistics: Num rows: 5492 Data size: 1231540 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6102 Data size: 1440072 Basic stats: COMPLETE Column stats: COMPLETE
Top N Key Operator
sort order: ++++
keys: cint (type: int), cdouble (type: double), cdecimal1 (type: decimal(20,10)), cdecimal2 (type: decimal(23,14))
- Statistics: Num rows: 5492 Data size: 1231540 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6102 Data size: 1440072 Basic stats: COMPLETE Column stats: COMPLETE
top n: 50
Top N Key Vectorization:
className: VectorTopNKeyOperator
@@ -86,7 +86,7 @@ STAGE PLANS:
keys: cint (type: int), cdouble (type: double), cdecimal1 (type: decimal(20,10)), cdecimal2 (type: decimal(23,14))
mode: hash
outputColumnNames: _col0, _col1, _col2, _col3, _col4
- Statistics: Num rows: 5492 Data size: 1231540 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6102 Data size: 2123496 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int), _col1 (type: double), _col2 (type: decimal(20,10)), _col3 (type: decimal(23,14))
sort order: ++++
@@ -95,7 +95,7 @@ STAGE PLANS:
className: VectorReduceSinkMultiKeyOperator
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 5492 Data size: 1231540 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6102 Data size: 2123496 Basic stats: COMPLETE Column stats: COMPLETE
TopN Hash Memory Usage: 0.1
value expressions: _col4 (type: decimal(20,10))
Execution mode: vectorized, llap
@@ -131,7 +131,7 @@ STAGE PLANS:
keys: KEY._col0 (type: int), KEY._col1 (type: double), KEY._col2 (type: decimal(20,10)), KEY._col3 (type: decimal(23,14))
mode: mergepartial
outputColumnNames: _col0, _col1, _col2, _col3, _col4
- Statistics: Num rows: 2746 Data size: 615770 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6102 Data size: 2123496 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int), _col1 (type: double), _col2 (type: decimal(20,10)), _col3 (type: decimal(23,14))
sort order: ++++
@@ -139,7 +139,7 @@ STAGE PLANS:
className: VectorReduceSinkObjectHashOperator
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 2746 Data size: 615770 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6102 Data size: 2123496 Basic stats: COMPLETE Column stats: COMPLETE
TopN Hash Memory Usage: 0.1
value expressions: _col4 (type: decimal(20,10))
Reducer 3
@@ -158,19 +158,19 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1, 2, 3, 4]
- Statistics: Num rows: 2746 Data size: 615770 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6102 Data size: 2123496 Basic stats: COMPLETE Column stats: COMPLETE
Limit
Number of rows: 50
Limit Vectorization:
className: VectorLimitOperator
native: true
- Statistics: Num rows: 50 Data size: 11200 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 50 Data size: 17400 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 50 Data size: 11200 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 50 Data size: 17400 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/llap/vector_udf2.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/vector_udf2.q.out b/ql/src/test/results/clientpositive/llap/vector_udf2.q.out
index 0e1ab60..266211c 100644
--- a/ql/src/test/results/clientpositive/llap/vector_udf2.q.out
+++ b/ql/src/test/results/clientpositive/llap/vector_udf2.q.out
@@ -187,7 +187,7 @@ STAGE PLANS:
TableScan
alias: hive_14349
filterExpr: (a like 'XYZ%a%') (type: boolean)
- Statistics: Num rows: 2 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 2 Data size: 368 Basic stats: COMPLETE Column stats: NONE
TableScan Vectorization:
native: true
Filter Operator
@@ -196,7 +196,7 @@ STAGE PLANS:
native: true
predicateExpression: FilterStringColLikeStringScalar(col 0:string, pattern XYZ%a%)
predicate: (a like 'XYZ%a%') (type: boolean)
- Statistics: Num rows: 1 Data size: 90 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: a (type: string)
outputColumnNames: _col0
@@ -204,13 +204,13 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0]
- Statistics: Num rows: 1 Data size: 90 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 1 Data size: 90 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -279,7 +279,7 @@ STAGE PLANS:
TableScan
alias: hive_14349
filterExpr: (a like 'XYZ%a_') (type: boolean)
- Statistics: Num rows: 6 Data size: 552 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 6 Data size: 1104 Basic stats: COMPLETE Column stats: NONE
TableScan Vectorization:
native: true
Filter Operator
@@ -288,7 +288,7 @@ STAGE PLANS:
native: true
predicateExpression: FilterStringColLikeStringScalar(col 0:string, pattern XYZ%a_)
predicate: (a like 'XYZ%a_') (type: boolean)
- Statistics: Num rows: 3 Data size: 276 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 3 Data size: 552 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: a (type: string)
outputColumnNames: _col0
@@ -296,13 +296,13 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0]
- Statistics: Num rows: 3 Data size: 276 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 3 Data size: 552 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 3 Data size: 276 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 3 Data size: 552 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/llap/vector_varchar_mapjoin1.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/vector_varchar_mapjoin1.q.out b/ql/src/test/results/clientpositive/llap/vector_varchar_mapjoin1.q.out
index 0cfd81c..f8b3223 100644
--- a/ql/src/test/results/clientpositive/llap/vector_varchar_mapjoin1.q.out
+++ b/ql/src/test/results/clientpositive/llap/vector_varchar_mapjoin1.q.out
@@ -154,14 +154,14 @@ STAGE PLANS:
TableScan
alias: a
filterExpr: c2 is not null (type: boolean)
- Statistics: Num rows: 3 Data size: 294 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 276 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: c2 is not null (type: boolean)
- Statistics: Num rows: 3 Data size: 294 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 276 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: c1 (type: int), c2 (type: varchar(10))
outputColumnNames: _col0, _col1
- Statistics: Num rows: 3 Data size: 294 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 276 Basic stats: COMPLETE Column stats: COMPLETE
Map Join Operator
condition map:
Inner Join 0 to 1
@@ -171,11 +171,11 @@ STAGE PLANS:
outputColumnNames: _col0, _col1, _col2, _col3
input vertices:
1 Map 3
- Statistics: Num rows: 3 Data size: 323 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 552 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
- Statistics: Num rows: 3 Data size: 323 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 552 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: varchar(10)), _col2 (type: int), _col3 (type: varchar(10))
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -193,19 +193,19 @@ STAGE PLANS:
TableScan
alias: b
filterExpr: c2 is not null (type: boolean)
- Statistics: Num rows: 3 Data size: 294 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 276 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: c2 is not null (type: boolean)
- Statistics: Num rows: 3 Data size: 294 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 276 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: c1 (type: int), c2 (type: varchar(10))
outputColumnNames: _col0, _col1
- Statistics: Num rows: 3 Data size: 294 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 276 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col1 (type: varchar(10))
sort order: +
Map-reduce partition columns: _col1 (type: varchar(10))
- Statistics: Num rows: 3 Data size: 294 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 276 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: int)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -230,10 +230,10 @@ STAGE PLANS:
Select Operator
expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: varchar(10)), VALUE._col1 (type: int), VALUE._col2 (type: varchar(10))
outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 3 Data size: 323 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 552 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 3 Data size: 323 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 552 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -279,8 +279,8 @@ STAGE PLANS:
Tez
#### A masked pattern was here ####
Edges:
- Map 2 <- Map 1 (BROADCAST_EDGE)
- Reducer 3 <- Map 2 (SIMPLE_EDGE)
+ Map 1 <- Map 3 (BROADCAST_EDGE)
+ Reducer 2 <- Map 1 (SIMPLE_EDGE)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -288,20 +288,29 @@ STAGE PLANS:
TableScan
alias: a
filterExpr: c2 is not null (type: boolean)
- Statistics: Num rows: 3 Data size: 294 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 276 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: c2 is not null (type: boolean)
- Statistics: Num rows: 3 Data size: 294 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 276 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: c1 (type: int), c2 (type: varchar(10))
outputColumnNames: _col0, _col1
- Statistics: Num rows: 3 Data size: 294 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col1 (type: varchar(20))
- sort order: +
- Map-reduce partition columns: _col1 (type: varchar(20))
- Statistics: Num rows: 3 Data size: 294 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col0 (type: int)
+ Statistics: Num rows: 3 Data size: 276 Basic stats: COMPLETE Column stats: COMPLETE
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col1 (type: varchar(20))
+ 1 _col1 (type: varchar(20))
+ outputColumnNames: _col0, _col1, _col2, _col3
+ input vertices:
+ 1 Map 3
+ Statistics: Num rows: 3 Data size: 552 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ key expressions: _col0 (type: int)
+ sort order: +
+ Statistics: Num rows: 3 Data size: 552 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col1 (type: varchar(10)), _col2 (type: int), _col3 (type: varchar(20))
Execution mode: vectorized, llap
LLAP IO: all inputs
Map Vectorization:
@@ -313,34 +322,25 @@ STAGE PLANS:
allNative: true
usesVectorUDFAdaptor: false
vectorized: true
- Map 2
+ Map 3
Map Operator Tree:
TableScan
alias: b
filterExpr: c2 is not null (type: boolean)
- Statistics: Num rows: 3 Data size: 324 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 276 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: c2 is not null (type: boolean)
- Statistics: Num rows: 3 Data size: 324 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 276 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: c1 (type: int), c2 (type: varchar(20))
outputColumnNames: _col0, _col1
- Statistics: Num rows: 3 Data size: 324 Basic stats: COMPLETE Column stats: NONE
- Map Join Operator
- condition map:
- Inner Join 0 to 1
- keys:
- 0 _col1 (type: varchar(20))
- 1 _col1 (type: varchar(20))
- outputColumnNames: _col0, _col1, _col2, _col3
- input vertices:
- 0 Map 1
- Statistics: Num rows: 3 Data size: 323 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: int)
- sort order: +
- Statistics: Num rows: 3 Data size: 323 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col1 (type: varchar(10)), _col2 (type: int), _col3 (type: varchar(20))
+ Statistics: Num rows: 3 Data size: 276 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ key expressions: _col1 (type: varchar(20))
+ sort order: +
+ Map-reduce partition columns: _col1 (type: varchar(20))
+ Statistics: Num rows: 3 Data size: 276 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col0 (type: int)
Execution mode: vectorized, llap
LLAP IO: all inputs
Map Vectorization:
@@ -352,7 +352,7 @@ STAGE PLANS:
allNative: true
usesVectorUDFAdaptor: false
vectorized: true
- Reducer 3
+ Reducer 2
Execution mode: vectorized, llap
Reduce Vectorization:
enabled: true
@@ -364,10 +364,10 @@ STAGE PLANS:
Select Operator
expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: varchar(10)), VALUE._col1 (type: int), VALUE._col2 (type: varchar(20))
outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 3 Data size: 323 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 552 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 3 Data size: 323 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 552 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -415,8 +415,8 @@ STAGE PLANS:
Tez
#### A masked pattern was here ####
Edges:
- Map 2 <- Map 1 (BROADCAST_EDGE)
- Reducer 3 <- Map 2 (SIMPLE_EDGE)
+ Map 1 <- Map 3 (BROADCAST_EDGE)
+ Reducer 2 <- Map 1 (SIMPLE_EDGE)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -424,20 +424,33 @@ STAGE PLANS:
TableScan
alias: a
filterExpr: c2 is not null (type: boolean)
- Statistics: Num rows: 3 Data size: 294 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 276 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: c2 is not null (type: boolean)
- Statistics: Num rows: 3 Data size: 294 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 276 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: c1 (type: int), c2 (type: varchar(10)), CAST( c2 AS STRING) (type: string)
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 3 Data size: 294 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col2 (type: string)
- sort order: +
- Map-reduce partition columns: _col2 (type: string)
- Statistics: Num rows: 3 Data size: 294 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col0 (type: int), _col1 (type: varchar(10))
+ Statistics: Num rows: 3 Data size: 828 Basic stats: COMPLETE Column stats: COMPLETE
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col2 (type: string)
+ 1 _col1 (type: string)
+ outputColumnNames: _col0, _col1, _col3, _col4
+ input vertices:
+ 1 Map 3
+ Statistics: Num rows: 3 Data size: 552 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: _col0 (type: int), _col1 (type: varchar(10)), _col3 (type: int), _col4 (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 3 Data size: 552 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ key expressions: _col0 (type: int)
+ sort order: +
+ Statistics: Num rows: 3 Data size: 552 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col1 (type: varchar(10)), _col2 (type: int), _col3 (type: string)
Execution mode: vectorized, llap
LLAP IO: all inputs
Map Vectorization:
@@ -449,38 +462,25 @@ STAGE PLANS:
allNative: true
usesVectorUDFAdaptor: false
vectorized: true
- Map 2
+ Map 3
Map Operator Tree:
TableScan
alias: b
filterExpr: c2 is not null (type: boolean)
- Statistics: Num rows: 3 Data size: 564 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 276 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: c2 is not null (type: boolean)
- Statistics: Num rows: 3 Data size: 564 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 276 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: c1 (type: int), c2 (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 3 Data size: 564 Basic stats: COMPLETE Column stats: NONE
- Map Join Operator
- condition map:
- Inner Join 0 to 1
- keys:
- 0 _col2 (type: string)
- 1 _col1 (type: string)
- outputColumnNames: _col0, _col1, _col3, _col4
- input vertices:
- 0 Map 1
- Statistics: Num rows: 3 Data size: 323 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col0 (type: int), _col1 (type: varchar(10)), _col3 (type: int), _col4 (type: string)
- outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 3 Data size: 323 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: int)
- sort order: +
- Statistics: Num rows: 3 Data size: 323 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col1 (type: varchar(10)), _col2 (type: int), _col3 (type: string)
+ Statistics: Num rows: 3 Data size: 276 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ key expressions: _col1 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col1 (type: string)
+ Statistics: Num rows: 3 Data size: 276 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col0 (type: int)
Execution mode: vectorized, llap
LLAP IO: all inputs
Map Vectorization:
@@ -492,7 +492,7 @@ STAGE PLANS:
allNative: true
usesVectorUDFAdaptor: false
vectorized: true
- Reducer 3
+ Reducer 2
Execution mode: vectorized, llap
Reduce Vectorization:
enabled: true
@@ -504,10 +504,10 @@ STAGE PLANS:
Select Operator
expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: varchar(10)), VALUE._col1 (type: int), VALUE._col2 (type: string)
outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 3 Data size: 323 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 552 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 3 Data size: 323 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 552 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/llap/vector_windowing_navfn.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/vector_windowing_navfn.q.out b/ql/src/test/results/clientpositive/llap/vector_windowing_navfn.q.out
index c69beb9..2af57ed 100644
--- a/ql/src/test/results/clientpositive/llap/vector_windowing_navfn.q.out
+++ b/ql/src/test/results/clientpositive/llap/vector_windowing_navfn.q.out
@@ -1641,7 +1641,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: wtest
- Statistics: Num rows: 15 Data size: 120 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 15 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:a:int, 1:b:int, 2:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -1655,7 +1655,7 @@ STAGE PLANS:
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
partitionColumns: 0:int
- Statistics: Num rows: 15 Data size: 120 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 15 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized, llap
LLAP IO: no inputs
Map Vectorization:
@@ -1684,7 +1684,7 @@ STAGE PLANS:
Select Operator
expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: int)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 15 Data size: 120 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 15 Data size: 4116 Basic stats: COMPLETE Column stats: COMPLETE
PTF Operator
Function definitions:
Input definition
@@ -1722,14 +1722,14 @@ STAGE PLANS:
name: first_value
window function: GenericUDAFFirstValueEvaluator
window frame: ROWS PRECEDING(MAX)~FOLLOWING(1)
- Statistics: Num rows: 15 Data size: 120 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 15 Data size: 4116 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: int), _col1 (type: int), first_value_window_0 (type: int), first_value_window_1 (type: int), first_value_window_2 (type: int), first_value_window_3 (type: int)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
- Statistics: Num rows: 15 Data size: 120 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 15 Data size: 308 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 15 Data size: 120 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 15 Data size: 308 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -1816,7 +1816,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: wtest
- Statistics: Num rows: 15 Data size: 120 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 15 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:a:int, 1:b:int, 2:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -1830,7 +1830,7 @@ STAGE PLANS:
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
partitionColumns: 0:int
- Statistics: Num rows: 15 Data size: 120 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 15 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized, llap
LLAP IO: no inputs
Map Vectorization:
@@ -1859,7 +1859,7 @@ STAGE PLANS:
Select Operator
expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: int)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 15 Data size: 120 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 15 Data size: 4116 Basic stats: COMPLETE Column stats: COMPLETE
PTF Operator
Function definitions:
Input definition
@@ -1897,14 +1897,14 @@ STAGE PLANS:
name: first_value
window function: GenericUDAFFirstValueEvaluator
window frame: ROWS PRECEDING(MAX)~FOLLOWING(1)
- Statistics: Num rows: 15 Data size: 120 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 15 Data size: 4116 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: int), _col1 (type: int), first_value_window_0 (type: int), first_value_window_1 (type: int), first_value_window_2 (type: int), first_value_window_3 (type: int)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
- Statistics: Num rows: 15 Data size: 120 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 15 Data size: 308 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 15 Data size: 120 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 15 Data size: 308 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -1991,7 +1991,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: wtest
- Statistics: Num rows: 15 Data size: 120 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 15 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:a:int, 1:b:int, 2:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -2005,7 +2005,7 @@ STAGE PLANS:
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
partitionColumns: 0:int
- Statistics: Num rows: 15 Data size: 120 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 15 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized, llap
LLAP IO: no inputs
Map Vectorization:
@@ -2034,7 +2034,7 @@ STAGE PLANS:
Select Operator
expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: int)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 15 Data size: 120 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 15 Data size: 4116 Basic stats: COMPLETE Column stats: COMPLETE
PTF Operator
Function definitions:
Input definition
@@ -2072,14 +2072,14 @@ STAGE PLANS:
name: last_value
window function: GenericUDAFLastValueEvaluator
window frame: ROWS PRECEDING(MAX)~FOLLOWING(1)
- Statistics: Num rows: 15 Data size: 120 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 15 Data size: 4116 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: int), _col1 (type: int), last_value_window_0 (type: int), last_value_window_1 (type: int), last_value_window_2 (type: int), last_value_window_3 (type: int)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
- Statistics: Num rows: 15 Data size: 120 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 15 Data size: 308 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 15 Data size: 120 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 15 Data size: 308 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -2166,7 +2166,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: wtest
- Statistics: Num rows: 15 Data size: 120 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 15 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:a:int, 1:b:int, 2:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -2180,7 +2180,7 @@ STAGE PLANS:
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
partitionColumns: 0:int
- Statistics: Num rows: 15 Data size: 120 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 15 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized, llap
LLAP IO: no inputs
Map Vectorization:
@@ -2209,7 +2209,7 @@ STAGE PLANS:
Select Operator
expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: int)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 15 Data size: 120 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 15 Data size: 4116 Basic stats: COMPLETE Column stats: COMPLETE
PTF Operator
Function definitions:
Input definition
@@ -2247,14 +2247,14 @@ STAGE PLANS:
name: last_value
window function: GenericUDAFLastValueEvaluator
window frame: ROWS PRECEDING(MAX)~FOLLOWING(1)
- Statistics: Num rows: 15 Data size: 120 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 15 Data size: 4116 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: int), _col1 (type: int), last_value_window_0 (type: int), last_value_window_1 (type: int), last_value_window_2 (type: int), last_value_window_3 (type: int)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
- Statistics: Num rows: 15 Data size: 120 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 15 Data size: 308 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 15 Data size: 120 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 15 Data size: 308 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/llap/vector_windowing_streaming.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/vector_windowing_streaming.q.out b/ql/src/test/results/clientpositive/llap/vector_windowing_streaming.q.out
index f81d927..41d12ba 100644
--- a/ql/src/test/results/clientpositive/llap/vector_windowing_streaming.q.out
+++ b/ql/src/test/results/clientpositive/llap/vector_windowing_streaming.q.out
@@ -798,7 +798,7 @@ PLAN VECTORIZATION:
STAGE DEPENDENCIES:
Stage-1 is a root stage
Stage-2 depends on stages: Stage-1
- Stage-4 depends on stages: Stage-2, Stage-0
+ Stage-4 depends on stages: Stage-0, Stage-2
Stage-3 depends on stages: Stage-4
Stage-0 depends on stages: Stage-1
@@ -808,6 +808,7 @@ STAGE PLANS:
#### A masked pattern was here ####
Edges:
Reducer 2 <- Map 1 (SIMPLE_EDGE)
+ Reducer 3 <- Reducer 2 (CUSTOM_SIMPLE_EDGE)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -847,28 +848,16 @@ STAGE PLANS:
partitionColumnCount: 0
scratchColumnTypeNames: []
Reducer 2
- Execution mode: vectorized, llap
+ Execution mode: llap
Reduce Vectorization:
enabled: true
enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true
- reduceColumnNullOrder: az
- reduceColumnSortOrder: ++
- allNative: false
- usesVectorUDFAdaptor: false
- vectorized: true
- rowBatchContext:
- dataColumnCount: 2
- dataColumns: KEY.reducesinkkey0:tinyint, KEY.reducesinkkey1:double
- partitionColumnCount: 0
- scratchColumnTypeNames: [bigint]
+ notVectorizedReason: Aggregation Function expression for GROUPBY operator: UDF compute_stats not supported
+ vectorized: false
Reduce Operator Tree:
Select Operator
expressions: KEY.reducesinkkey0 (type: tinyint), KEY.reducesinkkey1 (type: double)
outputColumnNames: _col0, _col5
- Select Vectorization:
- className: VectorSelectOperator
- native: true
- projectedOutputColumnNums: [0, 1]
Statistics: Num rows: 12288 Data size: 3403280 Basic stats: COMPLETE Column stats: COMPLETE
PTF Operator
Function definitions:
@@ -890,46 +879,55 @@ STAGE PLANS:
window function: GenericUDAFRankEvaluator
window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX)
isPivotResult: true
- PTF Vectorization:
- className: VectorPTFOperator
- evaluatorClasses: [VectorPTFEvaluatorRank]
- functionInputExpressions: [col 1:double]
- functionNames: [rank]
- keyInputColumns: [0, 1]
- native: true
- nonKeyInputColumns: []
- orderExpressions: [col 1:double]
- outputColumns: [2, 0, 1]
- outputTypes: [int, tinyint, double]
- partitionExpressions: [col 0:tinyint]
- streamingColumns: [2]
Statistics: Num rows: 12288 Data size: 3403280 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
- Filter Vectorization:
- className: VectorFilterOperator
- native: true
- predicateExpression: FilterLongColLessLongScalar(col 2:int, val 5)
predicate: (rank_window_0 < 5) (type: boolean)
Statistics: Num rows: 4096 Data size: 1121976 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: tinyint), _col5 (type: double), rank_window_0 (type: int)
outputColumnNames: _col0, _col1, _col2
- Select Vectorization:
- className: VectorSelectOperator
- native: true
- projectedOutputColumnNums: [0, 1, 2]
Statistics: Num rows: 4096 Data size: 40632 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- File Sink Vectorization:
- className: VectorFileSinkOperator
- native: false
Statistics: Num rows: 4096 Data size: 40632 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.sD
+ Select Operator
+ expressions: _col0 (type: tinyint), _col1 (type: double), _col2 (type: int)
+ outputColumnNames: col1, col2, col3
+ Statistics: Num rows: 4096 Data size: 40632 Basic stats: COMPLETE Column stats: COMPLETE
+ Group By Operator
+ aggregations: compute_stats(col1, 'hll'), compute_stats(col2, 'hll'), compute_stats(col3, 'hll')
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 1272 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 1272 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col0 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,min:double,max:double,countnulls:bigint,bitvector:binary>), _col2 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>)
+ Reducer 3
+ Execution mode: llap
+ Reduce Vectorization:
+ enabled: true
+ enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true
+ notVectorizedReason: Aggregation Function expression for GROUPBY operator: UDF compute_stats not supported
+ vectorized: false
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: COMPLETE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: COMPLETE
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
Stage: Stage-2
Dependency Collection
@@ -947,6 +945,10 @@ STAGE PLANS:
Stage: Stage-3
Stats Work
Basic Stats Work:
+ Column Stats Desc:
+ Columns: ctinyint, cdouble, r
+ Column Types: tinyint, double, int
+ Table: default.sD
Stage: Stage-0
Move Operator
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/llap/vectorization_decimal_date.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/vectorization_decimal_date.q.out b/ql/src/test/results/clientpositive/llap/vectorization_decimal_date.q.out
index 6502ff5..a68b9e0 100644
--- a/ql/src/test/results/clientpositive/llap/vectorization_decimal_date.q.out
+++ b/ql/src/test/results/clientpositive/llap/vectorization_decimal_date.q.out
@@ -38,7 +38,7 @@ STAGE PLANS:
TableScan
alias: date_decimal_test
filterExpr: (cint is not null and cdouble is not null) (type: boolean)
- Statistics: Num rows: 12288 Data size: 2101500 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 1651440 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
Filter Operator
@@ -47,7 +47,7 @@ STAGE PLANS:
native: true
predicateExpression: FilterExprAndExpr(children: SelectColumnIsNotNull(col 0:int), SelectColumnIsNotNull(col 1:double))
predicate: (cdouble is not null and cint is not null) (type: boolean)
- Statistics: Num rows: 11060 Data size: 1891486 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6848 Data size: 920460 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: cdate (type: date), cint (type: int), cdecimal (type: decimal(20,10))
outputColumnNames: _col0, _col1, _col2
@@ -55,19 +55,19 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [2, 0, 3]
- Statistics: Num rows: 11060 Data size: 1891486 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6848 Data size: 879548 Basic stats: COMPLETE Column stats: COMPLETE
Limit
Number of rows: 10
Limit Vectorization:
className: VectorLimitOperator
native: true
- Statistics: Num rows: 10 Data size: 1710 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 1376 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 10 Data size: 1710 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 1376 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/llap/vectorization_short_regress.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/vectorization_short_regress.q.out b/ql/src/test/results/clientpositive/llap/vectorization_short_regress.q.out
index 10de402..19fd205 100644
--- a/ql/src/test/results/clientpositive/llap/vectorization_short_regress.q.out
+++ b/ql/src/test/results/clientpositive/llap/vectorization_short_regress.q.out
@@ -3915,7 +3915,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: alltypesnullorc
- Statistics: Num rows: 12288 Data size: 46700 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
Select Operator
@@ -3925,7 +3925,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0]
- Statistics: Num rows: 12288 Data size: 46700 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count(ctinyint)
Group By Vectorization:
@@ -3937,14 +3937,14 @@ STAGE PLANS:
projectedOutputColumnNums: [0]
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
Reduce Sink Vectorization:
className: VectorReduceSinkEmptyKeyOperator
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: bigint)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -3977,13 +3977,13 @@ STAGE PLANS:
projectedOutputColumnNums: [0]
mode: mergepartial
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -4034,7 +4034,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: alltypesnullorc
- Statistics: Num rows: 12288 Data size: 46700 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
Select Operator
@@ -4044,7 +4044,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [2]
- Statistics: Num rows: 12288 Data size: 46700 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count(cint)
Group By Vectorization:
@@ -4056,14 +4056,14 @@ STAGE PLANS:
projectedOutputColumnNums: [0]
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
Reduce Sink Vectorization:
className: VectorReduceSinkEmptyKeyOperator
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: bigint)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -4096,13 +4096,13 @@ STAGE PLANS:
projectedOutputColumnNums: [0]
mode: mergepartial
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -4153,7 +4153,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: alltypesnullorc
- Statistics: Num rows: 12288 Data size: 46700 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
Select Operator
@@ -4163,7 +4163,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [4]
- Statistics: Num rows: 12288 Data size: 46700 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count(cfloat)
Group By Vectorization:
@@ -4175,14 +4175,14 @@ STAGE PLANS:
projectedOutputColumnNums: [0]
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
Reduce Sink Vectorization:
className: VectorReduceSinkEmptyKeyOperator
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: bigint)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -4215,13 +4215,13 @@ STAGE PLANS:
projectedOutputColumnNums: [0]
mode: mergepartial
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -4272,7 +4272,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: alltypesnullorc
- Statistics: Num rows: 12288 Data size: 2148200 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 84 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
Select Operator
@@ -4282,7 +4282,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [6]
- Statistics: Num rows: 12288 Data size: 2148200 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 84 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count(cstring1)
Group By Vectorization:
@@ -4294,14 +4294,14 @@ STAGE PLANS:
projectedOutputColumnNums: [0]
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
Reduce Sink Vectorization:
className: VectorReduceSinkEmptyKeyOperator
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: bigint)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -4334,13 +4334,13 @@ STAGE PLANS:
projectedOutputColumnNums: [0]
mode: mergepartial
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -4391,7 +4391,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: alltypesnullorc
- Statistics: Num rows: 12288 Data size: 46700 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
Select Operator
@@ -4401,7 +4401,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [10]
- Statistics: Num rows: 12288 Data size: 46700 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count(cboolean1)
Group By Vectorization:
@@ -4413,14 +4413,14 @@ STAGE PLANS:
projectedOutputColumnNums: [0]
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
Reduce Sink Vectorization:
className: VectorReduceSinkEmptyKeyOperator
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: bigint)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -4453,13 +4453,13 @@ STAGE PLANS:
projectedOutputColumnNums: [0]
mode: mergepartial
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
[15/35] hive git commit: HIVE-16957: Support CTAS for auto gather
column stats (Jesus Camacho Rodriguez, reviewed by Ashutosh Chauhan)
Posted by jc...@apache.org.
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/llap/vector_decimal_aggregate.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/vector_decimal_aggregate.q.out b/ql/src/test/results/clientpositive/llap/vector_decimal_aggregate.q.out
index c585eb1..f3f5f51 100644
--- a/ql/src/test/results/clientpositive/llap/vector_decimal_aggregate.q.out
+++ b/ql/src/test/results/clientpositive/llap/vector_decimal_aggregate.q.out
@@ -72,7 +72,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: decimal_vgby
- Statistics: Num rows: 12289 Data size: 2662128 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12289 Data size: 2091896 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:cdouble:double, 1:cdecimal1:decimal(20,10), 2:cdecimal2:decimal(23,14), 3:cint:int, 4:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -83,7 +83,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [1, 2, 3]
- Statistics: Num rows: 12289 Data size: 2662128 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12289 Data size: 2091896 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count(cdecimal1), max(cdecimal1), min(cdecimal1), sum(cdecimal1), count(cdecimal2), max(cdecimal2), min(cdecimal2), sum(cdecimal2), count()
Group By Vectorization:
@@ -97,7 +97,7 @@ STAGE PLANS:
keys: cint (type: int)
mode: hash
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9
- Statistics: Num rows: 12289 Data size: 2662128 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6105 Data size: 4267312 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
@@ -108,7 +108,7 @@ STAGE PLANS:
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
valueColumns: 1:bigint, 2:decimal(20,10), 3:decimal(20,10), 4:decimal(30,10), 5:bigint, 6:decimal(23,14), 7:decimal(23,14), 8:decimal(33,14), 9:bigint
- Statistics: Num rows: 12289 Data size: 2662128 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6105 Data size: 4267312 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: bigint), _col2 (type: decimal(20,10)), _col3 (type: decimal(20,10)), _col4 (type: decimal(30,10)), _col5 (type: bigint), _col6 (type: decimal(23,14)), _col7 (type: decimal(23,14)), _col8 (type: decimal(33,14)), _col9 (type: bigint)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -156,14 +156,14 @@ STAGE PLANS:
keys: KEY._col0 (type: int)
mode: mergepartial
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9
- Statistics: Num rows: 6144 Data size: 1330955 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6105 Data size: 4267312 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
Filter Vectorization:
className: VectorFilterOperator
native: true
predicateExpression: FilterLongColGreaterLongScalar(col 9:bigint, val 1)
predicate: (_col9 > 1L) (type: boolean)
- Statistics: Num rows: 2048 Data size: 443651 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2035 Data size: 1422440 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: int), _col1 (type: bigint), _col2 (type: decimal(20,10)), _col3 (type: decimal(20,10)), _col4 (type: decimal(30,10)), _col5 (type: bigint), _col6 (type: decimal(23,14)), _col7 (type: decimal(23,14)), _col8 (type: decimal(33,14))
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8
@@ -171,13 +171,13 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1, 2, 3, 4, 5, 6, 7, 8]
- Statistics: Num rows: 2048 Data size: 443651 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2035 Data size: 1406160 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 2048 Data size: 443651 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2035 Data size: 1406160 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -255,7 +255,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: decimal_vgby
- Statistics: Num rows: 12289 Data size: 2662128 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12289 Data size: 2091896 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:cdouble:double, 1:cdecimal1:decimal(20,10), 2:cdecimal2:decimal(23,14), 3:cint:int, 4:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -267,7 +267,7 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [3, 1, 2, 5, 8, 9, 12]
selectExpressions: CastDecimalToDouble(col 1:decimal(20,10)) -> 5:double, DoubleColMultiplyDoubleColumn(col 6:double, col 7:double)(children: CastDecimalToDouble(col 1:decimal(20,10)) -> 6:double, CastDecimalToDouble(col 1:decimal(20,10)) -> 7:double) -> 8:double, CastDecimalToDouble(col 2:decimal(23,14)) -> 9:double, DoubleColMultiplyDoubleColumn(col 10:double, col 11:double)(children: CastDecimalToDouble(col 2:decimal(23,14)) -> 10:double, CastDecimalToDouble(col 2:decimal(23,14)) -> 11:double) -> 12:double
- Statistics: Num rows: 12289 Data size: 2662128 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12289 Data size: 2091896 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count(_col1), max(_col1), min(_col1), sum(_col1), sum(_col4), sum(_col3), count(_col2), max(_col2), min(_col2), sum(_col2), sum(_col6), sum(_col5), count()
Group By Vectorization:
@@ -281,7 +281,7 @@ STAGE PLANS:
keys: _col0 (type: int)
mode: hash
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13
- Statistics: Num rows: 12289 Data size: 2662128 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6105 Data size: 4462672 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
@@ -292,7 +292,7 @@ STAGE PLANS:
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
valueColumns: 1:bigint, 2:decimal(20,10), 3:decimal(20,10), 4:decimal(30,10), 5:double, 6:double, 7:bigint, 8:decimal(23,14), 9:decimal(23,14), 10:decimal(33,14), 11:double, 12:double, 13:bigint
- Statistics: Num rows: 12289 Data size: 2662128 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6105 Data size: 4462672 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: bigint), _col2 (type: decimal(20,10)), _col3 (type: decimal(20,10)), _col4 (type: decimal(30,10)), _col5 (type: double), _col6 (type: double), _col7 (type: bigint), _col8 (type: decimal(23,14)), _col9 (type: decimal(23,14)), _col10 (type: decimal(33,14)), _col11 (type: double), _col12 (type: double), _col13 (type: bigint)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -340,14 +340,14 @@ STAGE PLANS:
keys: KEY._col0 (type: int)
mode: mergepartial
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13
- Statistics: Num rows: 6144 Data size: 1330955 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6105 Data size: 4462672 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
Filter Vectorization:
className: VectorFilterOperator
native: true
predicateExpression: FilterLongColGreaterLongScalar(col 13:bigint, val 1)
predicate: (_col13 > 1L) (type: boolean)
- Statistics: Num rows: 2048 Data size: 443651 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2035 Data size: 1487560 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: int), _col1 (type: bigint), _col2 (type: decimal(20,10)), _col3 (type: decimal(20,10)), _col4 (type: decimal(30,10)), (CAST( _col4 AS decimal(24,14)) / _col1) (type: decimal(38,28)), power(((_col5 - ((_col6 * _col6) / _col1)) / _col1), 0.5) (type: double), power(((_col5 - ((_col6 * _col6) / _col1)) / CASE WHEN ((_col1 = 1L)) THEN (null) ELSE ((_col1 - 1)) END), 0.5) (type: double), _col7 (type: bigint), _col8 (type: decimal(23,14)), _col9 (type: decimal(23,14)), _col10 (type: decimal(33,14)), (CAST( _col10 AS decimal(27,18)) / _col7) (type: decimal(38,29)), power(((_col11 - ((_col12 * _col12) / _col7)) / _col7), 0.5) (type: double), power(((_col11 - ((_col12 * _col12) / _col7)) / CASE WHEN ((_col7 = 1L)) THEN (null) ELSE ((_col7 - 1)) END), 0.5) (type: double)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14
@@ -356,13 +356,13 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [0, 1, 2, 3, 4, 16, 21, 29, 7, 8, 9, 10, 32, 37, 45]
selectExpressions: DecimalColDivideDecimalColumn(col 14:decimal(24,14), col 15:decimal(19,0))(children: CastDecimalToDecimal(col 4:decimal(30,10)) -> 14:decimal(24,14), CastLongToDecimal(col 1:bigint) -> 15:decimal(19,0)) -> 16:decimal(38,28), FuncPowerDoubleToDouble(col 20:double)(children: DoubleColDivideLongColumn(col 19:double, col 1:bigint)(children: DoubleColSubtractDoubleColumn(col 5:double, col 18:double)(children: DoubleColDivideLongColumn(col 17:double, col 1:bigint)(children: DoubleColMultiplyDoubleColumn(col 6:double, col 6:double) -> 17:double) -> 18:double) -> 19:double) -> 20:double) -> 21:double, FuncPowerDoubleToDouble(col 28:double)(children: DoubleColDivideLongColumn(col 24:double, col 27:bigint)(children: DoubleColSubtractDoubleColumn(col 5:double, col 23:double)(children: DoubleColDivideLongColumn(col 22:double, col 1:bigint)(children: DoubleColMultiplyDoubleColumn(col 6:double, col 6:double) -> 22:double) -> 23:double) -> 24:double, IfEx
prNullCondExpr(col 25:boolean, null, col 26:bigint)(children: LongColEqualLongScalar(col 1:bigint, val 1) -> 25:boolean, LongColSubtractLongScalar(col 1:bigint, val 1) -> 26:bigint) -> 27:bigint) -> 28:double) -> 29:double, DecimalColDivideDecimalColumn(col 30:decimal(27,18), col 31:decimal(19,0))(children: CastDecimalToDecimal(col 10:decimal(33,14)) -> 30:decimal(27,18), CastLongToDecimal(col 7:bigint) -> 31:decimal(19,0)) -> 32:decimal(38,29), FuncPowerDoubleToDouble(col 36:double)(children: DoubleColDivideLongColumn(col 35:double, col 7:bigint)(children: DoubleColSubtractDoubleColumn(col 11:double, col 34:double)(children: DoubleColDivideLongColumn(col 33:double, col 7:bigint)(children: DoubleColMultiplyDoubleColumn(col 12:double, col 12:double) -> 33:double) -> 34:double) -> 35:double) -> 36:double) -> 37:double, FuncPowerDoubleToDouble(col 44:double)(children: DoubleColDivideLongColumn(col 40:double, col 43:bigint)(children: DoubleColSubtractDoubleColumn(col 11:double, col 39:d
ouble)(children: DoubleColDivideLongColumn(col 38:double, col 7:bigint)(children: DoubleColMultiplyDoubleColumn(col 12:double, col 12:double) -> 38:double) -> 39:double) -> 40:double, IfExprNullCondExpr(col 41:boolean, null, col 42:bigint)(children: LongColEqualLongScalar(col 7:bigint, val 1) -> 41:boolean, LongColSubtractLongScalar(col 7:bigint, val 1) -> 42:bigint) -> 43:bigint) -> 44:double) -> 45:double
- Statistics: Num rows: 2048 Data size: 443651 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2035 Data size: 1927120 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 2048 Data size: 443651 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2035 Data size: 1927120 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -474,7 +474,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: decimal_vgby_small
- Statistics: Num rows: 12289 Data size: 2662128 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12289 Data size: 2091336 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:cdouble:double, 1:cdecimal1:decimal(11,5)/DECIMAL_64, 2:cdecimal2:decimal(16,0)/DECIMAL_64, 3:cint:int, 4:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -485,7 +485,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [1, 2, 3]
- Statistics: Num rows: 12289 Data size: 2662128 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12289 Data size: 2091336 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count(cdecimal1), max(cdecimal1), min(cdecimal1), sum(cdecimal1), count(cdecimal2), max(cdecimal2), min(cdecimal2), sum(cdecimal2), count()
Group By Vectorization:
@@ -499,7 +499,7 @@ STAGE PLANS:
keys: cint (type: int)
mode: hash
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9
- Statistics: Num rows: 12289 Data size: 2662128 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6105 Data size: 4267312 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
@@ -510,7 +510,7 @@ STAGE PLANS:
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
valueColumns: 1:bigint, 2:decimal(11,5), 3:decimal(11,5), 4:decimal(21,5), 5:bigint, 6:decimal(16,0), 7:decimal(16,0), 8:decimal(26,0), 9:bigint
- Statistics: Num rows: 12289 Data size: 2662128 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6105 Data size: 4267312 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: bigint), _col2 (type: decimal(11,5)), _col3 (type: decimal(11,5)), _col4 (type: decimal(21,5)), _col5 (type: bigint), _col6 (type: decimal(16,0)), _col7 (type: decimal(16,0)), _col8 (type: decimal(26,0)), _col9 (type: bigint)
Execution mode: vectorized, llap
LLAP IO: no inputs
@@ -558,14 +558,14 @@ STAGE PLANS:
keys: KEY._col0 (type: int)
mode: mergepartial
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9
- Statistics: Num rows: 6144 Data size: 1330955 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6105 Data size: 4267312 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
Filter Vectorization:
className: VectorFilterOperator
native: true
predicateExpression: FilterLongColGreaterLongScalar(col 9:bigint, val 1)
predicate: (_col9 > 1L) (type: boolean)
- Statistics: Num rows: 2048 Data size: 443651 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2035 Data size: 1422440 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: int), _col1 (type: bigint), _col2 (type: decimal(11,5)), _col3 (type: decimal(11,5)), _col4 (type: decimal(21,5)), _col5 (type: bigint), _col6 (type: decimal(16,0)), _col7 (type: decimal(16,0)), _col8 (type: decimal(26,0))
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8
@@ -573,13 +573,13 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1, 2, 3, 4, 5, 6, 7, 8]
- Statistics: Num rows: 2048 Data size: 443651 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2035 Data size: 1406160 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 2048 Data size: 443651 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2035 Data size: 1406160 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -676,7 +676,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: decimal_vgby_small
- Statistics: Num rows: 12289 Data size: 2662128 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12289 Data size: 2091336 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:cdouble:double, 1:cdecimal1:decimal(11,5)/DECIMAL_64, 2:cdecimal2:decimal(16,0)/DECIMAL_64, 3:cint:int, 4:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -688,7 +688,7 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [3, 1, 2, 6, 11, 13, 18]
selectExpressions: CastDecimalToDouble(col 5:decimal(11,5))(children: ConvertDecimal64ToDecimal(col 1:decimal(11,5)/DECIMAL_64) -> 5:decimal(11,5)) -> 6:double, DoubleColMultiplyDoubleColumn(col 8:double, col 10:double)(children: CastDecimalToDouble(col 7:decimal(11,5))(children: ConvertDecimal64ToDecimal(col 1:decimal(11,5)/DECIMAL_64) -> 7:decimal(11,5)) -> 8:double, CastDecimalToDouble(col 9:decimal(11,5))(children: ConvertDecimal64ToDecimal(col 1:decimal(11,5)/DECIMAL_64) -> 9:decimal(11,5)) -> 10:double) -> 11:double, CastDecimalToDouble(col 12:decimal(16,0))(children: ConvertDecimal64ToDecimal(col 2:decimal(16,0)/DECIMAL_64) -> 12:decimal(16,0)) -> 13:double, DoubleColMultiplyDoubleColumn(col 15:double, col 17:double)(children: CastDecimalToDouble(col 14:decimal(16,0))(children: ConvertDecimal64ToDecimal(col 2:decimal(16,0)/DECIMAL_64) -> 14:decimal(16,0)) -> 15:double, CastDecimalToDouble(col 16:decimal(16,0))(children: ConvertDecimal64ToDecimal(col 2:
decimal(16,0)/DECIMAL_64) -> 16:decimal(16,0)) -> 17:double) -> 18:double
- Statistics: Num rows: 12289 Data size: 2662128 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12289 Data size: 2091336 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count(_col1), max(_col1), min(_col1), sum(_col1), sum(_col4), sum(_col3), count(_col2), max(_col2), min(_col2), sum(_col2), sum(_col6), sum(_col5), count()
Group By Vectorization:
@@ -702,7 +702,7 @@ STAGE PLANS:
keys: _col0 (type: int)
mode: hash
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13
- Statistics: Num rows: 12289 Data size: 2662128 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6105 Data size: 4462672 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
@@ -713,7 +713,7 @@ STAGE PLANS:
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
valueColumns: 1:bigint, 2:decimal(11,5), 3:decimal(11,5), 4:decimal(21,5), 5:double, 6:double, 7:bigint, 8:decimal(16,0), 9:decimal(16,0), 10:decimal(26,0), 11:double, 12:double, 13:bigint
- Statistics: Num rows: 12289 Data size: 2662128 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6105 Data size: 4462672 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: bigint), _col2 (type: decimal(11,5)), _col3 (type: decimal(11,5)), _col4 (type: decimal(21,5)), _col5 (type: double), _col6 (type: double), _col7 (type: bigint), _col8 (type: decimal(16,0)), _col9 (type: decimal(16,0)), _col10 (type: decimal(26,0)), _col11 (type: double), _col12 (type: double), _col13 (type: bigint)
Execution mode: vectorized, llap
LLAP IO: no inputs
@@ -761,14 +761,14 @@ STAGE PLANS:
keys: KEY._col0 (type: int)
mode: mergepartial
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13
- Statistics: Num rows: 6144 Data size: 1330955 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6105 Data size: 4462672 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
Filter Vectorization:
className: VectorFilterOperator
native: true
predicateExpression: FilterLongColGreaterLongScalar(col 13:bigint, val 1)
predicate: (_col13 > 1L) (type: boolean)
- Statistics: Num rows: 2048 Data size: 443651 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2035 Data size: 1487560 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: int), _col1 (type: bigint), _col2 (type: decimal(11,5)), _col3 (type: decimal(11,5)), _col4 (type: decimal(21,5)), (CAST( _col4 AS decimal(15,9)) / _col1) (type: decimal(35,29)), power(((_col5 - ((_col6 * _col6) / _col1)) / _col1), 0.5) (type: double), power(((_col5 - ((_col6 * _col6) / _col1)) / CASE WHEN ((_col1 = 1L)) THEN (null) ELSE ((_col1 - 1)) END), 0.5) (type: double), _col7 (type: bigint), _col8 (type: decimal(16,0)), _col9 (type: decimal(16,0)), _col10 (type: decimal(26,0)), CAST( (CAST( _col10 AS decimal(20,4)) / _col7) AS decimal(20,4)) (type: decimal(20,4)), power(((_col11 - ((_col12 * _col12) / _col7)) / _col7), 0.5) (type: double), power(((_col11 - ((_col12 * _col12) / _col7)) / CASE WHEN ((_col7 = 1L)) THEN (null) ELSE ((_col7 - 1)) END), 0.5) (type: double)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14
@@ -777,13 +777,13 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [0, 1, 2, 3, 4, 16, 21, 29, 7, 8, 9, 10, 33, 38, 46]
selectExpressions: DecimalColDivideDecimalColumn(col 14:decimal(15,9), col 15:decimal(19,0))(children: CastDecimalToDecimal(col 4:decimal(21,5)) -> 14:decimal(15,9), CastLongToDecimal(col 1:bigint) -> 15:decimal(19,0)) -> 16:decimal(35,29), FuncPowerDoubleToDouble(col 20:double)(children: DoubleColDivideLongColumn(col 19:double, col 1:bigint)(children: DoubleColSubtractDoubleColumn(col 5:double, col 18:double)(children: DoubleColDivideLongColumn(col 17:double, col 1:bigint)(children: DoubleColMultiplyDoubleColumn(col 6:double, col 6:double) -> 17:double) -> 18:double) -> 19:double) -> 20:double) -> 21:double, FuncPowerDoubleToDouble(col 28:double)(children: DoubleColDivideLongColumn(col 24:double, col 27:bigint)(children: DoubleColSubtractDoubleColumn(col 5:double, col 23:double)(children: DoubleColDivideLongColumn(col 22:double, col 1:bigint)(children: DoubleColMultiplyDoubleColumn(col 6:double, col 6:double) -> 22:double) -> 23:double) -> 24:double, IfExprN
ullCondExpr(col 25:boolean, null, col 26:bigint)(children: LongColEqualLongScalar(col 1:bigint, val 1) -> 25:boolean, LongColSubtractLongScalar(col 1:bigint, val 1) -> 26:bigint) -> 27:bigint) -> 28:double) -> 29:double, CastDecimalToDecimal(col 32:decimal(38,22))(children: DecimalColDivideDecimalColumn(col 30:decimal(20,4), col 31:decimal(19,0))(children: CastDecimalToDecimal(col 10:decimal(26,0)) -> 30:decimal(20,4), CastLongToDecimal(col 7:bigint) -> 31:decimal(19,0)) -> 32:decimal(38,22)) -> 33:decimal(20,4), FuncPowerDoubleToDouble(col 37:double)(children: DoubleColDivideLongColumn(col 36:double, col 7:bigint)(children: DoubleColSubtractDoubleColumn(col 11:double, col 35:double)(children: DoubleColDivideLongColumn(col 34:double, col 7:bigint)(children: DoubleColMultiplyDoubleColumn(col 12:double, col 12:double) -> 34:double) -> 35:double) -> 36:double) -> 37:double) -> 38:double, FuncPowerDoubleToDouble(col 45:double)(children: DoubleColDivideLongColumn(col 41:double, col 44:bi
gint)(children: DoubleColSubtractDoubleColumn(col 11:double, col 40:double)(children: DoubleColDivideLongColumn(col 39:double, col 7:bigint)(children: DoubleColMultiplyDoubleColumn(col 12:double, col 12:double) -> 39:double) -> 40:double) -> 41:double, IfExprNullCondExpr(col 42:boolean, null, col 43:bigint)(children: LongColEqualLongScalar(col 7:bigint, val 1) -> 42:boolean, LongColSubtractLongScalar(col 7:bigint, val 1) -> 43:bigint) -> 44:bigint) -> 45:double) -> 46:double
- Statistics: Num rows: 2048 Data size: 443651 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2035 Data size: 1927120 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 2048 Data size: 443651 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2035 Data size: 1927120 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/llap/vector_decimal_cast.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/vector_decimal_cast.q.out b/ql/src/test/results/clientpositive/llap/vector_decimal_cast.q.out
index 9c21718..fb5fd32 100644
--- a/ql/src/test/results/clientpositive/llap/vector_decimal_cast.q.out
+++ b/ql/src/test/results/clientpositive/llap/vector_decimal_cast.q.out
@@ -152,7 +152,7 @@ STAGE PLANS:
TableScan
alias: alltypes_small
filterExpr: (cdouble is not null and cint is not null and cboolean1 is not null and ctimestamp1 is not null) (type: boolean)
- Statistics: Num rows: 12288 Data size: 653800 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 638316 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:ctinyint:tinyint, 1:csmallint:smallint, 2:cint:int, 3:cbigint:bigint, 4:cfloat:float, 5:cdouble:double, 6:cstring1:string, 7:cstring2:string, 8:ctimestamp1:timestamp, 9:ctimestamp2:timestamp, 10:cboolean1:boolean, 11:cboolean2:boolean, 12:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -162,7 +162,7 @@ STAGE PLANS:
native: true
predicateExpression: FilterExprAndExpr(children: SelectColumnIsNotNull(col 5:double), SelectColumnIsNotNull(col 2:int), SelectColumnIsNotNull(col 10:boolean), SelectColumnIsNotNull(col 8:timestamp))
predicate: (cboolean1 is not null and cdouble is not null and cint is not null and ctimestamp1 is not null) (type: boolean)
- Statistics: Num rows: 9832 Data size: 523125 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5112 Data size: 265564 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: cdouble (type: double), cint (type: int), cboolean1 (type: boolean), ctimestamp1 (type: timestamp), CAST( cdouble AS decimal(20,10)) (type: decimal(20,10)), CAST( cint AS decimal(23,14)) (type: decimal(23,14)), CAST( cboolean1 AS decimal(5,2)) (type: decimal(5,2)), CAST( ctimestamp1 AS decimal(15,0)) (type: decimal(15,0))
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7
@@ -171,19 +171,19 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [5, 2, 10, 8, 13, 14, 15, 16]
selectExpressions: CastDoubleToDecimal(col 5:double) -> 13:decimal(20,10), CastLongToDecimal(col 2:int) -> 14:decimal(23,14), CastLongToDecimal(col 10:boolean) -> 15:decimal(5,2), CastTimestampToDecimal(col 8:timestamp) -> 16:decimal(15,0)
- Statistics: Num rows: 9832 Data size: 523125 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5112 Data size: 2410700 Basic stats: COMPLETE Column stats: COMPLETE
Limit
Number of rows: 10
Limit Vectorization:
className: VectorLimitOperator
native: true
- Statistics: Num rows: 10 Data size: 530 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 4784 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 10 Data size: 530 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 4784 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/llap/vector_decimal_math_funcs.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/vector_decimal_math_funcs.q.out b/ql/src/test/results/clientpositive/llap/vector_decimal_math_funcs.q.out
index a8a83bd..b26fb62 100644
--- a/ql/src/test/results/clientpositive/llap/vector_decimal_math_funcs.q.out
+++ b/ql/src/test/results/clientpositive/llap/vector_decimal_math_funcs.q.out
@@ -120,7 +120,7 @@ STAGE PLANS:
TableScan
alias: decimal_test_n0
filterExpr: (((cbigint % 500) = 0) and (sin(cdecimal1) >= -1.0D)) (type: boolean)
- Statistics: Num rows: 12289 Data size: 1401120 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12289 Data size: 1100992 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:cbigint:bigint, 1:cdouble:double, 2:cdecimal1:decimal(20,10), 3:cdecimal2:decimal(23,14), 4:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -130,7 +130,7 @@ STAGE PLANS:
native: true
predicateExpression: FilterExprAndExpr(children: FilterLongColEqualLongScalar(col 5:bigint, val 0)(children: LongColModuloLongScalar(col 0:bigint, val 500) -> 5:bigint), FilterDoubleColGreaterEqualDoubleScalar(col 7:double, val -1.0)(children: FuncSinDoubleToDouble(col 6:double)(children: CastDecimalToDouble(col 2:decimal(20,10)) -> 6:double) -> 7:double))
predicate: (((cbigint % 500) = 0) and (sin(cdecimal1) >= -1.0D)) (type: boolean)
- Statistics: Num rows: 2048 Data size: 233500 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2048 Data size: 183600 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: cdecimal1 (type: decimal(20,10)), round(cdecimal1, 2) (type: decimal(13,2)), round(cdecimal1) (type: decimal(11,0)), floor(cdecimal1) (type: decimal(11,0)), ceil(cdecimal1) (type: decimal(11,0)), round(exp(cdecimal1), 58) (type: double), ln(cdecimal1) (type: double), log10(cdecimal1) (type: double), log2(cdecimal1) (type: double), log2((cdecimal1 - 15601)) (type: double), log(2, cdecimal1) (type: double), power(log2(cdecimal1), 2) (type: double), power(log2(cdecimal1), 2) (type: double), sqrt(cdecimal1) (type: double), abs(cdecimal1) (type: decimal(20,10)), sin(cdecimal1) (type: double), asin(cdecimal1) (type: double), cos(cdecimal1) (type: double), acos(cdecimal1) (type: double), atan(cdecimal1) (type: double), degrees(cdecimal1) (type: double), radians(cdecimal1) (type: double), cdecimal1 (type: decimal(20,10)), (- cdecimal1) (type: decimal(20,10)), sign(cdecimal1) (type: int), cos(((- sin(log(cdecimal1))) + 3.14159D)) (type: double)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25
@@ -139,13 +139,13 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [2, 8, 9, 10, 11, 14, 16, 18, 20, 23, 25, 28, 31, 33, 34, 36, 38, 40, 42, 44, 46, 48, 2, 49, 50, 56]
selectExpressions: FuncRoundWithNumDigitsDecimalToDecimal(col 2:decimal(20,10), decimalPlaces 2) -> 8:decimal(13,2), FuncRoundDecimalToDecimal(col 2:decimal(20,10)) -> 9:decimal(11,0), FuncFloorDecimalToDecimal(col 2:decimal(20,10)) -> 10:decimal(11,0), FuncCeilDecimalToDecimal(col 2:decimal(20,10)) -> 11:decimal(11,0), RoundWithNumDigitsDoubleToDouble(col 13, decimalPlaces 58)(children: FuncExpDoubleToDouble(col 12:double)(children: CastDecimalToDouble(col 2:decimal(20,10)) -> 12:double) -> 13:double) -> 14:double, FuncLnDoubleToDouble(col 15:double)(children: CastDecimalToDouble(col 2:decimal(20,10)) -> 15:double) -> 16:double, FuncLog10DoubleToDouble(col 17:double)(children: CastDecimalToDouble(col 2:decimal(20,10)) -> 17:double) -> 18:double, FuncLog2DoubleToDouble(col 19:double)(children: CastDecimalToDouble(col 2:decimal(20,10)) -> 19:double) -> 20:double, FuncLog2DoubleToDouble(col 22:double)(children: CastDecimalToDouble(col 21:decimal(21,10))(child
ren: DecimalColSubtractDecimalScalar(col 2:decimal(20,10), val 15601) -> 21:decimal(21,10)) -> 22:double) -> 23:double, FuncLogWithBaseDoubleToDouble(col 24:double)(children: CastDecimalToDouble(col 2:decimal(20,10)) -> 24:double) -> 25:double, FuncPowerDoubleToDouble(col 27:double)(children: FuncLog2DoubleToDouble(col 26:double)(children: CastDecimalToDouble(col 2:decimal(20,10)) -> 26:double) -> 27:double) -> 28:double, FuncPowerDoubleToDouble(col 30:double)(children: FuncLog2DoubleToDouble(col 29:double)(children: CastDecimalToDouble(col 2:decimal(20,10)) -> 29:double) -> 30:double) -> 31:double, FuncSqrtDoubleToDouble(col 32:double)(children: CastDecimalToDouble(col 2:decimal(20,10)) -> 32:double) -> 33:double, FuncAbsDecimalToDecimal(col 2:decimal(20,10)) -> 34:decimal(20,10), FuncSinDoubleToDouble(col 35:double)(children: CastDecimalToDouble(col 2:decimal(20,10)) -> 35:double) -> 36:double, FuncASinDoubleToDouble(col 37:double)(children: CastDecimalToDouble(col 2:decimal(20,10
)) -> 37:double) -> 38:double, FuncCosDoubleToDouble(col 39:double)(children: CastDecimalToDouble(col 2:decimal(20,10)) -> 39:double) -> 40:double, FuncACosDoubleToDouble(col 41:double)(children: CastDecimalToDouble(col 2:decimal(20,10)) -> 41:double) -> 42:double, FuncATanDoubleToDouble(col 43:double)(children: CastDecimalToDouble(col 2:decimal(20,10)) -> 43:double) -> 44:double, FuncDegreesDoubleToDouble(col 45:double)(children: CastDecimalToDouble(col 2:decimal(20,10)) -> 45:double) -> 46:double, FuncRadiansDoubleToDouble(col 47:double)(children: CastDecimalToDouble(col 2:decimal(20,10)) -> 47:double) -> 48:double, FuncNegateDecimalToDecimal(col 2:decimal(20,10)) -> 49:decimal(20,10), FuncSignDecimalToLong(col 2:decimal(20,10)) -> 50:int, FuncCosDoubleToDouble(col 55:double)(children: DoubleColAddDoubleScalar(col 54:double, val 3.14159)(children: DoubleColUnaryMinus(col 53:double)(children: FuncSinDoubleToDouble(col 52:double)(children: FuncLnDoubleToDouble(col 51:double)(childre
n: CastDecimalToDouble(col 2:decimal(20,10)) -> 51:double) -> 52:double) -> 53:double) -> 54:double) -> 55:double) -> 56:double
- Statistics: Num rows: 2048 Data size: 233500 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2048 Data size: 2005696 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 2048 Data size: 233500 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2048 Data size: 2005696 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -371,7 +371,7 @@ STAGE PLANS:
TableScan
alias: decimal_test_small
filterExpr: (((cbigint % 500) = 0) and (sin(cdecimal1) >= -1.0D)) (type: boolean)
- Statistics: Num rows: 12288 Data size: 1401000 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 1100992 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:cbigint:bigint, 1:cdouble:double, 2:cdecimal1:decimal(12,4)/DECIMAL_64, 3:cdecimal2:decimal(14,8)/DECIMAL_64, 4:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -381,7 +381,7 @@ STAGE PLANS:
native: true
predicateExpression: FilterExprAndExpr(children: FilterLongColEqualLongScalar(col 5:bigint, val 0)(children: LongColModuloLongScalar(col 0:bigint, val 500) -> 5:bigint), FilterDoubleColGreaterEqualDoubleScalar(col 8:double, val -1.0)(children: FuncSinDoubleToDouble(col 7:double)(children: CastDecimalToDouble(col 6:decimal(12,4))(children: ConvertDecimal64ToDecimal(col 2:decimal(12,4)/DECIMAL_64) -> 6:decimal(12,4)) -> 7:double) -> 8:double))
predicate: (((cbigint % 500) = 0) and (sin(cdecimal1) >= -1.0D)) (type: boolean)
- Statistics: Num rows: 2048 Data size: 233500 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2048 Data size: 183600 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: cdecimal1 (type: decimal(12,4)), round(cdecimal1, 2) (type: decimal(11,2)), round(cdecimal1) (type: decimal(9,0)), floor(cdecimal1) (type: decimal(9,0)), ceil(cdecimal1) (type: decimal(9,0)), round(exp(cdecimal1), 58) (type: double), ln(cdecimal1) (type: double), log10(cdecimal1) (type: double), log2(cdecimal1) (type: double), log2((cdecimal1 - 15601)) (type: double), log(2, cdecimal1) (type: double), power(log2(cdecimal1), 2) (type: double), power(log2(cdecimal1), 2) (type: double), sqrt(cdecimal1) (type: double), abs(cdecimal1) (type: decimal(12,4)), sin(cdecimal1) (type: double), asin(cdecimal1) (type: double), cos(cdecimal1) (type: double), acos(cdecimal1) (type: double), atan(cdecimal1) (type: double), degrees(cdecimal1) (type: double), radians(cdecimal1) (type: double), cdecimal1 (type: decimal(12,4)), (- cdecimal1) (type: decimal(12,4)), sign(cdecimal1) (type: int), cos(((- sin(log(cdecimal1))) + 3.14159D)) (type: double)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25
@@ -390,13 +390,13 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [2, 10, 12, 14, 16, 20, 23, 26, 29, 32, 35, 39, 43, 46, 48, 51, 54, 57, 60, 63, 66, 69, 2, 71, 73, 80]
selectExpressions: FuncRoundWithNumDigitsDecimalToDecimal(col 9:decimal(12,4), decimalPlaces 2)(children: ConvertDecimal64ToDecimal(col 2:decimal(12,4)/DECIMAL_64) -> 9:decimal(12,4)) -> 10:decimal(11,2), FuncRoundDecimalToDecimal(col 11:decimal(12,4))(children: ConvertDecimal64ToDecimal(col 2:decimal(12,4)/DECIMAL_64) -> 11:decimal(12,4)) -> 12:decimal(9,0), FuncFloorDecimalToDecimal(col 13:decimal(12,4))(children: ConvertDecimal64ToDecimal(col 2:decimal(12,4)/DECIMAL_64) -> 13:decimal(12,4)) -> 14:decimal(9,0), FuncCeilDecimalToDecimal(col 15:decimal(12,4))(children: ConvertDecimal64ToDecimal(col 2:decimal(12,4)/DECIMAL_64) -> 15:decimal(12,4)) -> 16:decimal(9,0), RoundWithNumDigitsDoubleToDouble(col 19, decimalPlaces 58)(children: FuncExpDoubleToDouble(col 18:double)(children: CastDecimalToDouble(col 17:decimal(12,4))(children: ConvertDecimal64ToDecimal(col 2:decimal(12,4)/DECIMAL_64) -> 17:decimal(12,4)) -> 18:double) -> 19:double) -> 20:double, FuncLnD
oubleToDouble(col 22:double)(children: CastDecimalToDouble(col 21:decimal(12,4))(children: ConvertDecimal64ToDecimal(col 2:decimal(12,4)/DECIMAL_64) -> 21:decimal(12,4)) -> 22:double) -> 23:double, FuncLog10DoubleToDouble(col 25:double)(children: CastDecimalToDouble(col 24:decimal(12,4))(children: ConvertDecimal64ToDecimal(col 2:decimal(12,4)/DECIMAL_64) -> 24:decimal(12,4)) -> 25:double) -> 26:double, FuncLog2DoubleToDouble(col 28:double)(children: CastDecimalToDouble(col 27:decimal(12,4))(children: ConvertDecimal64ToDecimal(col 2:decimal(12,4)/DECIMAL_64) -> 27:decimal(12,4)) -> 28:double) -> 29:double, FuncLog2DoubleToDouble(col 31:double)(children: CastDecimalToDouble(col 81:decimal(13,4))(children: ConvertDecimal64ToDecimal(col 30:decimal(13,4)/DECIMAL_64)(children: Decimal64ColSubtractDecimal64Scalar(col 2:decimal(12,4)/DECIMAL_64, decimal64Val 156010000, decimalVal 15601) -> 30:decimal(13,4)/DECIMAL_64) -> 81:decimal(13,4)) -> 31:double) -> 32:double, FuncLogWithBaseDoubleToD
ouble(col 34:double)(children: CastDecimalToDouble(col 33:decimal(12,4))(children: ConvertDecimal64ToDecimal(col 2:decimal(12,4)/DECIMAL_64) -> 33:decimal(12,4)) -> 34:double) -> 35:double, FuncPowerDoubleToDouble(col 38:double)(children: FuncLog2DoubleToDouble(col 37:double)(children: CastDecimalToDouble(col 36:decimal(12,4))(children: ConvertDecimal64ToDecimal(col 2:decimal(12,4)/DECIMAL_64) -> 36:decimal(12,4)) -> 37:double) -> 38:double) -> 39:double, FuncPowerDoubleToDouble(col 42:double)(children: FuncLog2DoubleToDouble(col 41:double)(children: CastDecimalToDouble(col 40:decimal(12,4))(children: ConvertDecimal64ToDecimal(col 2:decimal(12,4)/DECIMAL_64) -> 40:decimal(12,4)) -> 41:double) -> 42:double) -> 43:double, FuncSqrtDoubleToDouble(col 45:double)(children: CastDecimalToDouble(col 44:decimal(12,4))(children: ConvertDecimal64ToDecimal(col 2:decimal(12,4)/DECIMAL_64) -> 44:decimal(12,4)) -> 45:double) -> 46:double, FuncAbsDecimalToDecimal(col 47:decimal(12,4))(children: Conv
ertDecimal64ToDecimal(col 2:decimal(12,4)/DECIMAL_64) -> 47:decimal(12,4)) -> 48:decimal(12,4), FuncSinDoubleToDouble(col 50:double)(children: CastDecimalToDouble(col 49:decimal(12,4))(children: ConvertDecimal64ToDecimal(col 2:decimal(12,4)/DECIMAL_64) -> 49:decimal(12,4)) -> 50:double) -> 51:double, FuncASinDoubleToDouble(col 53:double)(children: CastDecimalToDouble(col 52:decimal(12,4))(children: ConvertDecimal64ToDecimal(col 2:decimal(12,4)/DECIMAL_64) -> 52:decimal(12,4)) -> 53:double) -> 54:double, FuncCosDoubleToDouble(col 56:double)(children: CastDecimalToDouble(col 55:decimal(12,4))(children: ConvertDecimal64ToDecimal(col 2:decimal(12,4)/DECIMAL_64) -> 55:decimal(12,4)) -> 56:double) -> 57:double, FuncACosDoubleToDouble(col 59:double)(children: CastDecimalToDouble(col 58:decimal(12,4))(children: ConvertDecimal64ToDecimal(col 2:decimal(12,4)/DECIMAL_64) -> 58:decimal(12,4)) -> 59:double) -> 60:double, FuncATanDoubleToDouble(col 62:double)(children: CastDecimalToDouble(col 61:
decimal(12,4))(children: ConvertDecimal64ToDecimal(col 2:decimal(12,4)/DECIMAL_64) -> 61:decimal(12,4)) -> 62:double) -> 63:double, FuncDegreesDoubleToDouble(col 65:double)(children: CastDecimalToDouble(col 64:decimal(12,4))(children: ConvertDecimal64ToDecimal(col 2:decimal(12,4)/DECIMAL_64) -> 64:decimal(12,4)) -> 65:double) -> 66:double, FuncRadiansDoubleToDouble(col 68:double)(children: CastDecimalToDouble(col 67:decimal(12,4))(children: ConvertDecimal64ToDecimal(col 2:decimal(12,4)/DECIMAL_64) -> 67:decimal(12,4)) -> 68:double) -> 69:double, FuncNegateDecimalToDecimal(col 70:decimal(12,4))(children: ConvertDecimal64ToDecimal(col 2:decimal(12,4)/DECIMAL_64) -> 70:decimal(12,4)) -> 71:decimal(12,4), FuncSignDecimalToLong(col 72:decimal(12,4))(children: ConvertDecimal64ToDecimal(col 2:decimal(12,4)/DECIMAL_64) -> 72:decimal(12,4)) -> 73:int, FuncCosDoubleToDouble(col 79:double)(children: DoubleColAddDoubleScalar(col 78:double, val 3.14159)(children: DoubleColUnaryMinus(col 77:doubl
e)(children: FuncSinDoubleToDouble(col 76:double)(children: FuncLnDoubleToDouble(col 75:double)(children: CastDecimalToDouble(col 74:decimal(12,4))(children: ConvertDecimal64ToDecimal(col 2:decimal(12,4)/DECIMAL_64) -> 74:decimal(12,4)) -> 75:double) -> 76:double) -> 77:double) -> 78:double) -> 79:double) -> 80:double
- Statistics: Num rows: 2048 Data size: 233500 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2048 Data size: 2005696 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 2048 Data size: 233500 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2048 Data size: 2005696 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/llap/vector_groupby4.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/vector_groupby4.q.out b/ql/src/test/results/clientpositive/llap/vector_groupby4.q.out
index 24df11f..f7c121d 100644
--- a/ql/src/test/results/clientpositive/llap/vector_groupby4.q.out
+++ b/ql/src/test/results/clientpositive/llap/vector_groupby4.q.out
@@ -55,7 +55,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: srcorc_n1
- Statistics: Num rows: 500 Data size: 87584 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
Select Operator
@@ -66,7 +66,7 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [3]
selectExpressions: StringSubstrColStartLen(col 0:string, start 0, length 1) -> 3:string
- Statistics: Num rows: 500 Data size: 87584 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
@@ -75,7 +75,7 @@ STAGE PLANS:
className: VectorReduceSinkObjectHashOperator
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 500 Data size: 87584 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized, llap
LLAP IO: all inputs
Map Vectorization:
@@ -107,7 +107,7 @@ STAGE PLANS:
keys: KEY._col0 (type: string)
mode: partial1
outputColumnNames: _col0
- Statistics: Num rows: 500 Data size: 87584 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 92000 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
@@ -116,7 +116,7 @@ STAGE PLANS:
className: VectorReduceSinkStringOperator
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 500 Data size: 87584 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 92000 Basic stats: COMPLETE Column stats: COMPLETE
Reducer 3
Execution mode: vectorized, llap
Reduce Vectorization:
@@ -137,13 +137,13 @@ STAGE PLANS:
keys: KEY._col0 (type: string)
mode: final
outputColumnNames: _col0
- Statistics: Num rows: 250 Data size: 43792 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 316 Data size: 58144 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 250 Data size: 43792 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 316 Data size: 58144 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat
@@ -156,7 +156,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0]
- Statistics: Num rows: 250 Data size: 43792 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 316 Data size: 58144 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
Map-reduce partition columns: rand() (type: double)
@@ -164,7 +164,7 @@ STAGE PLANS:
className: VectorReduceSinkObjectHashOperator
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 250 Data size: 43792 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 316 Data size: 58144 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: c1 (type: string)
Reducer 4
Execution mode: llap
@@ -178,10 +178,10 @@ STAGE PLANS:
aggregations: compute_stats(VALUE._col0, 'hll')
mode: partial1
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 624 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
- Statistics: Num rows: 1 Data size: 624 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>)
Reducer 5
Execution mode: llap
@@ -195,10 +195,10 @@ STAGE PLANS:
aggregations: compute_stats(VALUE._col0)
mode: final
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 624 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 624 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/llap/vector_groupby6.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/vector_groupby6.q.out b/ql/src/test/results/clientpositive/llap/vector_groupby6.q.out
index 88f8036..e7d6979 100644
--- a/ql/src/test/results/clientpositive/llap/vector_groupby6.q.out
+++ b/ql/src/test/results/clientpositive/llap/vector_groupby6.q.out
@@ -55,7 +55,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: srcorc_n0
- Statistics: Num rows: 500 Data size: 87584 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
Select Operator
@@ -66,7 +66,7 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [3]
selectExpressions: StringSubstrColStartLen(col 1:string, start 4, length 1) -> 3:string
- Statistics: Num rows: 500 Data size: 87584 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
@@ -75,7 +75,7 @@ STAGE PLANS:
className: VectorReduceSinkObjectHashOperator
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 500 Data size: 87584 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized, llap
LLAP IO: all inputs
Map Vectorization:
@@ -107,7 +107,7 @@ STAGE PLANS:
keys: KEY._col0 (type: string)
mode: partial1
outputColumnNames: _col0
- Statistics: Num rows: 500 Data size: 87584 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 92000 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
@@ -116,7 +116,7 @@ STAGE PLANS:
className: VectorReduceSinkStringOperator
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 500 Data size: 87584 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 92000 Basic stats: COMPLETE Column stats: COMPLETE
Reducer 3
Execution mode: vectorized, llap
Reduce Vectorization:
@@ -137,13 +137,13 @@ STAGE PLANS:
keys: KEY._col0 (type: string)
mode: final
outputColumnNames: _col0
- Statistics: Num rows: 250 Data size: 43792 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 307 Data size: 56488 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 250 Data size: 43792 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 307 Data size: 56488 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat
@@ -156,7 +156,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0]
- Statistics: Num rows: 250 Data size: 43792 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 307 Data size: 56488 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
Map-reduce partition columns: rand() (type: double)
@@ -164,7 +164,7 @@ STAGE PLANS:
className: VectorReduceSinkObjectHashOperator
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 250 Data size: 43792 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 307 Data size: 56488 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: c1 (type: string)
Reducer 4
Execution mode: llap
@@ -178,10 +178,10 @@ STAGE PLANS:
aggregations: compute_stats(VALUE._col0, 'hll')
mode: partial1
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 624 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
- Statistics: Num rows: 1 Data size: 624 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>)
Reducer 5
Execution mode: llap
@@ -195,10 +195,10 @@ STAGE PLANS:
aggregations: compute_stats(VALUE._col0)
mode: final
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 624 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 624 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 440 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
[23/35] hive git commit: HIVE-16957: Support CTAS for auto gather
column stats (Jesus Camacho Rodriguez, reviewed by Ashutosh Chauhan)
Posted by jc...@apache.org.
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/llap/materialized_view_rewrite_ssb_2.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/materialized_view_rewrite_ssb_2.q.out b/ql/src/test/results/clientpositive/llap/materialized_view_rewrite_ssb_2.q.out
index 6f7dcdb..abefa7e 100644
--- a/ql/src/test/results/clientpositive/llap/materialized_view_rewrite_ssb_2.q.out
+++ b/ql/src/test/results/clientpositive/llap/materialized_view_rewrite_ssb_2.q.out
@@ -528,56 +528,6 @@ POSTHOOK: Lineage: lineorder.lo_shippriority SIMPLE [(lineorder_ext)lineorder_ex
POSTHOOK: Lineage: lineorder.lo_suppkey SIMPLE [(lineorder_ext)lineorder_ext.FieldSchema(name:lo_suppkey, type:bigint, comment:null), ]
POSTHOOK: Lineage: lineorder.lo_supplycost SIMPLE [(lineorder_ext)lineorder_ext.FieldSchema(name:lo_supplycost, type:double, comment:null), ]
POSTHOOK: Lineage: lineorder.lo_tax SIMPLE [(lineorder_ext)lineorder_ext.FieldSchema(name:lo_tax, type:double, comment:null), ]
-PREHOOK: query: analyze table customer_n0 compute statistics for columns
-PREHOOK: type: ANALYZE_TABLE
-PREHOOK: Input: default@customer_n0
-PREHOOK: Output: default@customer_n0
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table customer_n0 compute statistics for columns
-POSTHOOK: type: ANALYZE_TABLE
-POSTHOOK: Input: default@customer_n0
-POSTHOOK: Output: default@customer_n0
-#### A masked pattern was here ####
-PREHOOK: query: analyze table dates compute statistics for columns
-PREHOOK: type: ANALYZE_TABLE
-PREHOOK: Input: default@dates
-PREHOOK: Output: default@dates
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table dates compute statistics for columns
-POSTHOOK: type: ANALYZE_TABLE
-POSTHOOK: Input: default@dates
-POSTHOOK: Output: default@dates
-#### A masked pattern was here ####
-PREHOOK: query: analyze table ssb_part compute statistics for columns
-PREHOOK: type: ANALYZE_TABLE
-PREHOOK: Input: default@ssb_part
-PREHOOK: Output: default@ssb_part
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table ssb_part compute statistics for columns
-POSTHOOK: type: ANALYZE_TABLE
-POSTHOOK: Input: default@ssb_part
-POSTHOOK: Output: default@ssb_part
-#### A masked pattern was here ####
-PREHOOK: query: analyze table supplier compute statistics for columns
-PREHOOK: type: ANALYZE_TABLE
-PREHOOK: Input: default@supplier
-PREHOOK: Output: default@supplier
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table supplier compute statistics for columns
-POSTHOOK: type: ANALYZE_TABLE
-POSTHOOK: Input: default@supplier
-POSTHOOK: Output: default@supplier
-#### A masked pattern was here ####
-PREHOOK: query: analyze table lineorder compute statistics for columns
-PREHOOK: type: ANALYZE_TABLE
-PREHOOK: Input: default@lineorder
-PREHOOK: Output: default@lineorder
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table lineorder compute statistics for columns
-POSTHOOK: type: ANALYZE_TABLE
-POSTHOOK: Input: default@lineorder
-POSTHOOK: Output: default@lineorder
-#### A masked pattern was here ####
PREHOOK: query: CREATE MATERIALIZED VIEW `ssb_mv`
AS
SELECT
@@ -699,22 +649,22 @@ STAGE PLANS:
TableScan
alias: default.ssb_mv
filterExpr: ((UDFToInteger(d_year) = 1993) and (UDFToDouble(lo_quantity) < 25.0D) and UDFToDouble(lo_discount) BETWEEN 1.0D AND 3.0D) (type: boolean)
- Statistics: Num rows: 1 Data size: 560 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 260 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: ((UDFToDouble(lo_quantity) < 25.0D) and (UDFToInteger(d_year) = 1993) and UDFToDouble(lo_discount) BETWEEN 1.0D AND 3.0D) (type: boolean)
- Statistics: Num rows: 1 Data size: 560 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 260 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: discounted_price (type: double)
outputColumnNames: discounted_price
- Statistics: Num rows: 1 Data size: 560 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 260 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: sum(discounted_price)
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 568 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
- Statistics: Num rows: 1 Data size: 568 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: double)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -725,10 +675,10 @@ STAGE PLANS:
aggregations: sum(VALUE._col0)
mode: mergepartial
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 568 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 568 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -787,22 +737,22 @@ STAGE PLANS:
TableScan
alias: default.ssb_mv
filterExpr: ((UDFToInteger(d_yearmonthnum) = 199401) and UDFToDouble(lo_discount) BETWEEN 4.0D AND 6.0D and UDFToDouble(lo_quantity) BETWEEN 26.0D AND 35.0D) (type: boolean)
- Statistics: Num rows: 1 Data size: 560 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 260 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: ((UDFToInteger(d_yearmonthnum) = 199401) and UDFToDouble(lo_discount) BETWEEN 4.0D AND 6.0D and UDFToDouble(lo_quantity) BETWEEN 26.0D AND 35.0D) (type: boolean)
- Statistics: Num rows: 1 Data size: 560 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 260 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: discounted_price (type: double)
outputColumnNames: discounted_price
- Statistics: Num rows: 1 Data size: 560 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 260 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: sum(discounted_price)
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 568 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
- Statistics: Num rows: 1 Data size: 568 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: double)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -813,10 +763,10 @@ STAGE PLANS:
aggregations: sum(VALUE._col0)
mode: mergepartial
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 568 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 568 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -877,22 +827,22 @@ STAGE PLANS:
TableScan
alias: default.ssb_mv
filterExpr: ((UDFToInteger(d_year) = 1994) and (UDFToInteger(d_weeknuminyear) = 6) and UDFToDouble(lo_discount) BETWEEN 5.0D AND 7.0D and UDFToDouble(lo_quantity) BETWEEN 26.0D AND 35.0D) (type: boolean)
- Statistics: Num rows: 1 Data size: 744 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 344 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: ((UDFToInteger(d_weeknuminyear) = 6) and (UDFToInteger(d_year) = 1994) and UDFToDouble(lo_discount) BETWEEN 5.0D AND 7.0D and UDFToDouble(lo_quantity) BETWEEN 26.0D AND 35.0D) (type: boolean)
- Statistics: Num rows: 1 Data size: 744 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 344 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: discounted_price (type: double)
outputColumnNames: discounted_price
- Statistics: Num rows: 1 Data size: 744 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 344 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: sum(discounted_price)
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 752 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
- Statistics: Num rows: 1 Data size: 752 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: double)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -903,10 +853,10 @@ STAGE PLANS:
aggregations: sum(VALUE._col0)
mode: mergepartial
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 752 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 752 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -980,25 +930,25 @@ STAGE PLANS:
TableScan
alias: default.ssb_mv
filterExpr: ((p_category = 'MFGR#12') and (s_region = 'AMERICA')) (type: boolean)
- Statistics: Num rows: 1 Data size: 744 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 344 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: ((p_category = 'MFGR#12') and (s_region = 'AMERICA')) (type: boolean)
- Statistics: Num rows: 1 Data size: 744 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 344 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: UDFToInteger(d_year) (type: int), p_brand1 (type: string), lo_revenue (type: double)
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 1 Data size: 744 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 344 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: sum(_col2)
keys: _col0 (type: int), _col1 (type: string)
mode: hash
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 1 Data size: 744 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int), _col1 (type: string)
sort order: ++
Map-reduce partition columns: _col0 (type: int), _col1 (type: string)
- Statistics: Num rows: 1 Data size: 744 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col2 (type: double)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -1010,15 +960,15 @@ STAGE PLANS:
keys: KEY._col0 (type: int), KEY._col1 (type: string)
mode: mergepartial
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 1 Data size: 744 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col2 (type: double), _col0 (type: int), _col1 (type: string)
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 1 Data size: 744 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col1 (type: int), _col2 (type: string)
sort order: ++
- Statistics: Num rows: 1 Data size: 744 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: double)
Reducer 3
Execution mode: vectorized, llap
@@ -1026,10 +976,10 @@ STAGE PLANS:
Select Operator
expressions: VALUE._col0 (type: double), KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: string)
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 1 Data size: 744 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 744 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -1103,25 +1053,25 @@ STAGE PLANS:
TableScan
alias: default.ssb_mv
filterExpr: ((s_region = 'ASIA') and p_brand1 BETWEEN 'MFGR#2221' AND 'MFGR#2228') (type: boolean)
- Statistics: Num rows: 1 Data size: 560 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 260 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: ((s_region = 'ASIA') and p_brand1 BETWEEN 'MFGR#2221' AND 'MFGR#2228') (type: boolean)
- Statistics: Num rows: 1 Data size: 560 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 260 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: UDFToInteger(d_year) (type: int), p_brand1 (type: string), lo_revenue (type: double)
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 1 Data size: 560 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 260 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: sum(_col2)
keys: _col0 (type: int), _col1 (type: string)
mode: hash
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 1 Data size: 560 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int), _col1 (type: string)
sort order: ++
Map-reduce partition columns: _col0 (type: int), _col1 (type: string)
- Statistics: Num rows: 1 Data size: 560 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col2 (type: double)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -1133,15 +1083,15 @@ STAGE PLANS:
keys: KEY._col0 (type: int), KEY._col1 (type: string)
mode: mergepartial
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 1 Data size: 560 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col2 (type: double), _col0 (type: int), _col1 (type: string)
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 1 Data size: 560 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col1 (type: int), _col2 (type: string)
sort order: ++
- Statistics: Num rows: 1 Data size: 560 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: double)
Reducer 3
Execution mode: vectorized, llap
@@ -1149,10 +1099,10 @@ STAGE PLANS:
Select Operator
expressions: VALUE._col0 (type: double), KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: string)
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 1 Data size: 560 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 560 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -1226,25 +1176,25 @@ STAGE PLANS:
TableScan
alias: default.ssb_mv
filterExpr: ((p_brand1 = 'MFGR#2239') and (s_region = 'EUROPE')) (type: boolean)
- Statistics: Num rows: 1 Data size: 560 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 260 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: ((p_brand1 = 'MFGR#2239') and (s_region = 'EUROPE')) (type: boolean)
- Statistics: Num rows: 1 Data size: 560 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 260 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: UDFToInteger(d_year) (type: int), lo_revenue (type: double)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 560 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 260 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: sum(_col1)
keys: _col0 (type: int)
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 560 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 1 Data size: 560 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: double)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -1256,15 +1206,15 @@ STAGE PLANS:
keys: KEY._col0 (type: int)
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 560 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col1 (type: double), _col0 (type: int)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 560 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col1 (type: int)
sort order: +
- Statistics: Num rows: 1 Data size: 560 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: double)
Reducer 3
Execution mode: vectorized, llap
@@ -1272,10 +1222,10 @@ STAGE PLANS:
Select Operator
expressions: VALUE._col0 (type: double), KEY.reducesinkkey0 (type: int), 'MFGR#2239' (type: string)
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 1 Data size: 560 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 105 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 560 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 105 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -1353,25 +1303,25 @@ STAGE PLANS:
TableScan
alias: default.ssb_mv
filterExpr: ((UDFToInteger(d_year) >= 1992) and (c_region = 'ASIA') and (s_region = 'ASIA') and (UDFToInteger(d_year) <= 1997)) (type: boolean)
- Statistics: Num rows: 1 Data size: 928 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 428 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: ((UDFToInteger(d_year) <= 1997) and (UDFToInteger(d_year) >= 1992) and (c_region = 'ASIA') and (s_region = 'ASIA')) (type: boolean)
- Statistics: Num rows: 1 Data size: 928 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 428 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: c_nation (type: string), s_nation (type: string), UDFToInteger(d_year) (type: int), lo_revenue (type: double)
outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 1 Data size: 928 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 428 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: sum(_col3)
keys: _col2 (type: int), _col0 (type: string), _col1 (type: string)
mode: hash
outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 1 Data size: 928 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string)
sort order: +++
Map-reduce partition columns: _col0 (type: int), _col1 (type: string), _col2 (type: string)
- Statistics: Num rows: 1 Data size: 928 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col3 (type: double)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -1383,15 +1333,15 @@ STAGE PLANS:
keys: KEY._col0 (type: int), KEY._col1 (type: string), KEY._col2 (type: string)
mode: mergepartial
outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 1 Data size: 928 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col1 (type: string), _col2 (type: string), _col0 (type: int), _col3 (type: double)
outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 1 Data size: 928 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col2 (type: int), _col3 (type: double)
sort order: +-
- Statistics: Num rows: 1 Data size: 928 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: string), _col1 (type: string)
Reducer 3
Execution mode: vectorized, llap
@@ -1399,10 +1349,10 @@ STAGE PLANS:
Select Operator
expressions: VALUE._col0 (type: string), VALUE._col1 (type: string), KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: double)
outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 1 Data size: 928 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 928 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -1478,25 +1428,25 @@ STAGE PLANS:
TableScan
alias: default.ssb_mv
filterExpr: ((UDFToInteger(d_year) >= 1992) and (c_nation = 'UNITED STATES') and (s_nation = 'UNITED STATES') and (UDFToInteger(d_year) <= 1997)) (type: boolean)
- Statistics: Num rows: 1 Data size: 928 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 428 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: ((UDFToInteger(d_year) <= 1997) and (UDFToInteger(d_year) >= 1992) and (c_nation = 'UNITED STATES') and (s_nation = 'UNITED STATES')) (type: boolean)
- Statistics: Num rows: 1 Data size: 928 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 428 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: c_city (type: string), s_city (type: string), UDFToInteger(d_year) (type: int), lo_revenue (type: double)
outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 1 Data size: 928 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 428 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: sum(_col3)
keys: _col2 (type: int), _col0 (type: string), _col1 (type: string)
mode: hash
outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 1 Data size: 928 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string)
sort order: +++
Map-reduce partition columns: _col0 (type: int), _col1 (type: string), _col2 (type: string)
- Statistics: Num rows: 1 Data size: 928 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col3 (type: double)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -1508,15 +1458,15 @@ STAGE PLANS:
keys: KEY._col0 (type: int), KEY._col1 (type: string), KEY._col2 (type: string)
mode: mergepartial
outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 1 Data size: 928 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col1 (type: string), _col2 (type: string), _col0 (type: int), _col3 (type: double)
outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 1 Data size: 928 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col2 (type: int), _col3 (type: double)
sort order: +-
- Statistics: Num rows: 1 Data size: 928 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: string), _col1 (type: string)
Reducer 3
Execution mode: vectorized, llap
@@ -1524,10 +1474,10 @@ STAGE PLANS:
Select Operator
expressions: VALUE._col0 (type: string), VALUE._col1 (type: string), KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: double)
outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 1 Data size: 928 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 928 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -1603,25 +1553,25 @@ STAGE PLANS:
TableScan
alias: default.ssb_mv
filterExpr: ((c_city) IN ('UNITED KI1', 'UNITED KI5') and (s_city) IN ('UNITED KI1', 'UNITED KI5') and (UDFToInteger(d_year) >= 1992) and (UDFToInteger(d_year) <= 1997)) (type: boolean)
- Statistics: Num rows: 1 Data size: 560 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 260 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: ((UDFToInteger(d_year) <= 1997) and (UDFToInteger(d_year) >= 1992) and (c_city) IN ('UNITED KI1', 'UNITED KI5') and (s_city) IN ('UNITED KI1', 'UNITED KI5')) (type: boolean)
- Statistics: Num rows: 1 Data size: 560 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 260 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: c_city (type: string), s_city (type: string), UDFToInteger(d_year) (type: int), lo_revenue (type: double)
outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 1 Data size: 560 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 260 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: sum(_col3)
keys: _col2 (type: int), _col0 (type: string), _col1 (type: string)
mode: hash
outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 1 Data size: 560 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string)
sort order: +++
Map-reduce partition columns: _col0 (type: int), _col1 (type: string), _col2 (type: string)
- Statistics: Num rows: 1 Data size: 560 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col3 (type: double)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -1633,15 +1583,15 @@ STAGE PLANS:
keys: KEY._col0 (type: int), KEY._col1 (type: string), KEY._col2 (type: string)
mode: mergepartial
outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 1 Data size: 560 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col1 (type: string), _col2 (type: string), _col0 (type: int), _col3 (type: double)
outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 1 Data size: 560 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col2 (type: int), _col3 (type: double)
sort order: +-
- Statistics: Num rows: 1 Data size: 560 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: string), _col1 (type: string)
Reducer 3
Execution mode: vectorized, llap
@@ -1649,10 +1599,10 @@ STAGE PLANS:
Select Operator
expressions: VALUE._col0 (type: string), VALUE._col1 (type: string), KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: double)
outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 1 Data size: 560 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 560 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -1728,25 +1678,25 @@ STAGE PLANS:
TableScan
alias: default.ssb_mv
filterExpr: ((c_city) IN ('UNITED KI1', 'UNITED KI5') and (s_city) IN ('UNITED KI1', 'UNITED KI5') and (d_yearmonth = 'Dec1997')) (type: boolean)
- Statistics: Num rows: 1 Data size: 744 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 344 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: ((c_city) IN ('UNITED KI1', 'UNITED KI5') and (d_yearmonth = 'Dec1997') and (s_city) IN ('UNITED KI1', 'UNITED KI5')) (type: boolean)
- Statistics: Num rows: 1 Data size: 744 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 344 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: c_city (type: string), s_city (type: string), UDFToInteger(d_year) (type: int), lo_revenue (type: double)
outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 1 Data size: 744 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 344 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: sum(_col3)
keys: _col2 (type: int), _col0 (type: string), _col1 (type: string)
mode: hash
outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 1 Data size: 744 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string)
sort order: +++
Map-reduce partition columns: _col0 (type: int), _col1 (type: string), _col2 (type: string)
- Statistics: Num rows: 1 Data size: 744 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col3 (type: double)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -1758,15 +1708,15 @@ STAGE PLANS:
keys: KEY._col0 (type: int), KEY._col1 (type: string), KEY._col2 (type: string)
mode: mergepartial
outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 1 Data size: 744 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col1 (type: string), _col2 (type: string), _col0 (type: int), _col3 (type: double)
outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 1 Data size: 744 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col2 (type: int), _col3 (type: double)
sort order: +-
- Statistics: Num rows: 1 Data size: 744 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: string), _col1 (type: string)
Reducer 3
Execution mode: vectorized, llap
@@ -1774,10 +1724,10 @@ STAGE PLANS:
Select Operator
expressions: VALUE._col0 (type: string), VALUE._col1 (type: string), KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: double)
outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 1 Data size: 744 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 744 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -1859,25 +1809,25 @@ STAGE PLANS:
TableScan
alias: default.ssb_mv
filterExpr: ((p_mfgr) IN ('MFGR#1', 'MFGR#2') and (c_region = 'AMERICA') and (s_region = 'AMERICA')) (type: boolean)
- Statistics: Num rows: 1 Data size: 928 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 428 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: ((c_region = 'AMERICA') and (p_mfgr) IN ('MFGR#1', 'MFGR#2') and (s_region = 'AMERICA')) (type: boolean)
- Statistics: Num rows: 1 Data size: 928 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 428 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: UDFToInteger(d_year) (type: int), c_nation (type: string), net_revenue (type: double)
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 1 Data size: 928 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 428 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: sum(_col2)
keys: _col0 (type: int), _col1 (type: string)
mode: hash
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 1 Data size: 928 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int), _col1 (type: string)
sort order: ++
Map-reduce partition columns: _col0 (type: int), _col1 (type: string)
- Statistics: Num rows: 1 Data size: 928 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col2 (type: double)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -1889,11 +1839,11 @@ STAGE PLANS:
keys: KEY._col0 (type: int), KEY._col1 (type: string)
mode: mergepartial
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 1 Data size: 928 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int), _col1 (type: string)
sort order: ++
- Statistics: Num rows: 1 Data size: 928 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col2 (type: double)
Reducer 3
Execution mode: vectorized, llap
@@ -1901,10 +1851,10 @@ STAGE PLANS:
Select Operator
expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: string), VALUE._col0 (type: double)
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 1 Data size: 928 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 928 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -1988,25 +1938,25 @@ STAGE PLANS:
TableScan
alias: default.ssb_mv
filterExpr: ((UDFToInteger(d_year)) IN (1997, 1998) and (p_mfgr) IN ('MFGR#1', 'MFGR#2') and (c_region = 'AMERICA') and (s_region = 'AMERICA')) (type: boolean)
- Statistics: Num rows: 1 Data size: 1112 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 512 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: ((UDFToInteger(d_year)) IN (1997, 1998) and (c_region = 'AMERICA') and (p_mfgr) IN ('MFGR#1', 'MFGR#2') and (s_region = 'AMERICA')) (type: boolean)
- Statistics: Num rows: 1 Data size: 1112 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 512 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: UDFToInteger(d_year) (type: int), s_nation (type: string), p_category (type: string), net_revenue (type: double)
outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 1 Data size: 1112 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 512 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: sum(_col3)
keys: _col0 (type: int), _col1 (type: string), _col2 (type: string)
mode: hash
outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 1 Data size: 1112 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string)
sort order: +++
Map-reduce partition columns: _col0 (type: int), _col1 (type: string), _col2 (type: string)
- Statistics: Num rows: 1 Data size: 1112 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col3 (type: double)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -2018,11 +1968,11 @@ STAGE PLANS:
keys: KEY._col0 (type: int), KEY._col1 (type: string), KEY._col2 (type: string)
mode: mergepartial
outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 1 Data size: 1112 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string)
sort order: +++
- Statistics: Num rows: 1 Data size: 1112 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col3 (type: double)
Reducer 3
Execution mode: vectorized, llap
@@ -2030,10 +1980,10 @@ STAGE PLANS:
Select Operator
expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string), VALUE._col0 (type: double)
outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 1 Data size: 1112 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 1112 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -2117,25 +2067,25 @@ STAGE PLANS:
TableScan
alias: default.ssb_mv
filterExpr: ((UDFToInteger(d_year)) IN (1997, 1998) and (c_region = 'AMERICA') and (p_category = 'MFGR#14') and (s_nation = 'UNITED STATES')) (type: boolean)
- Statistics: Num rows: 1 Data size: 1112 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 512 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: ((UDFToInteger(d_year)) IN (1997, 1998) and (c_region = 'AMERICA') and (p_category = 'MFGR#14') and (s_nation = 'UNITED STATES')) (type: boolean)
- Statistics: Num rows: 1 Data size: 1112 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 512 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: UDFToInteger(d_year) (type: int), s_city (type: string), p_brand1 (type: string), net_revenue (type: double)
outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 1 Data size: 1112 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 512 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: sum(_col3)
keys: _col0 (type: int), _col1 (type: string), _col2 (type: string)
mode: hash
outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 1 Data size: 1112 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string)
sort order: +++
Map-reduce partition columns: _col0 (type: int), _col1 (type: string), _col2 (type: string)
- Statistics: Num rows: 1 Data size: 1112 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col3 (type: double)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -2147,11 +2097,11 @@ STAGE PLANS:
keys: KEY._col0 (type: int), KEY._col1 (type: string), KEY._col2 (type: string)
mode: mergepartial
outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 1 Data size: 1112 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string)
sort order: +++
- Statistics: Num rows: 1 Data size: 1112 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col3 (type: double)
Reducer 3
Execution mode: vectorized, llap
@@ -2159,10 +2109,10 @@ STAGE PLANS:
Select Operator
expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string), VALUE._col0 (type: double)
outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 1 Data size: 1112 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 1112 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
[12/35] hive git commit: HIVE-16957: Support CTAS for auto gather
column stats (Jesus Camacho Rodriguez, reviewed by Ashutosh Chauhan)
Posted by jc...@apache.org.
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/llap/vector_groupby_grouping_sets4.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/vector_groupby_grouping_sets4.q.out b/ql/src/test/results/clientpositive/llap/vector_groupby_grouping_sets4.q.out
index 4b736dd..c4e8ac7 100644
--- a/ql/src/test/results/clientpositive/llap/vector_groupby_grouping_sets4.q.out
+++ b/ql/src/test/results/clientpositive/llap/vector_groupby_grouping_sets4.q.out
@@ -70,7 +70,7 @@ STAGE PLANS:
TableScan
alias: t1_n161
filterExpr: (UDFToDouble(a) < 3.0D) (type: boolean)
- Statistics: Num rows: 6 Data size: 2208 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 1020 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:a:string, 1:b:string, 2:c:string, 3:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -80,7 +80,7 @@ STAGE PLANS:
native: true
predicateExpression: FilterDoubleColLessDoubleScalar(col 4:double, val 3.0)(children: CastStringToDouble(col 0:string) -> 4:double)
predicate: (UDFToDouble(a) < 3.0D) (type: boolean)
- Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 340 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count()
Group By Vectorization:
@@ -94,7 +94,7 @@ STAGE PLANS:
keys: a (type: string), b (type: string), 0L (type: bigint)
mode: hash
outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 8 Data size: 2944 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4 Data size: 744 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: bigint)
sort order: +++
@@ -105,7 +105,7 @@ STAGE PLANS:
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
valueColumns: 3:bigint
- Statistics: Num rows: 8 Data size: 2944 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4 Data size: 744 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col3 (type: bigint)
Reduce Output Operator
key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: bigint)
@@ -117,7 +117,7 @@ STAGE PLANS:
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
valueColumns: 3:bigint
- Statistics: Num rows: 8 Data size: 2944 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4 Data size: 744 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col3 (type: bigint)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -165,7 +165,7 @@ STAGE PLANS:
keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: bigint)
mode: mergepartial
outputColumnNames: _col0, _col1, _col3
- Statistics: Num rows: 4 Data size: 1472 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4 Data size: 744 Basic stats: COMPLETE Column stats: COMPLETE
pruneGroupingSetId: true
Filter Operator
Filter Vectorization:
@@ -173,7 +173,7 @@ STAGE PLANS:
native: true
predicateExpression: SelectColumnIsNotNull(col 0:string)
predicate: _col0 is not null (type: boolean)
- Statistics: Num rows: 4 Data size: 1472 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4 Data size: 744 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: string), _col1 (type: string), _col3 (type: bigint)
outputColumnNames: _col0, _col1, _col2
@@ -181,7 +181,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1, 2]
- Statistics: Num rows: 4 Data size: 1472 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4 Data size: 712 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
@@ -192,7 +192,7 @@ STAGE PLANS:
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
valueColumns: 1:string, 2:bigint
- Statistics: Num rows: 4 Data size: 1472 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4 Data size: 712 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: string), _col2 (type: bigint)
Reducer 3
Execution mode: llap
@@ -204,10 +204,10 @@ STAGE PLANS:
0 _col0 (type: string)
1 _col0 (type: string)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
- Statistics: Num rows: 4 Data size: 1619 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 8 Data size: 2848 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 4 Data size: 1619 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 8 Data size: 2848 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -244,7 +244,7 @@ STAGE PLANS:
keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: bigint)
mode: mergepartial
outputColumnNames: _col0, _col1, _col3
- Statistics: Num rows: 4 Data size: 1472 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4 Data size: 744 Basic stats: COMPLETE Column stats: COMPLETE
pruneGroupingSetId: true
Filter Operator
Filter Vectorization:
@@ -252,7 +252,7 @@ STAGE PLANS:
native: true
predicateExpression: SelectColumnIsNotNull(col 0:string)
predicate: _col0 is not null (type: boolean)
- Statistics: Num rows: 4 Data size: 1472 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4 Data size: 744 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: string), _col1 (type: string), _col3 (type: bigint)
outputColumnNames: _col0, _col1, _col2
@@ -260,7 +260,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1, 2]
- Statistics: Num rows: 4 Data size: 1472 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4 Data size: 712 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
@@ -271,7 +271,7 @@ STAGE PLANS:
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
valueColumns: 1:string, 2:bigint
- Statistics: Num rows: 4 Data size: 1472 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4 Data size: 712 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: string), _col2 (type: bigint)
Stage: Stage-0
@@ -322,7 +322,7 @@ STAGE PLANS:
TableScan
alias: t1_n161
filterExpr: (UDFToDouble(a) < 3.0D) (type: boolean)
- Statistics: Num rows: 6 Data size: 2208 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 1020 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:a:string, 1:b:string, 2:c:string, 3:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -332,7 +332,7 @@ STAGE PLANS:
native: true
predicateExpression: FilterDoubleColLessDoubleScalar(col 4:double, val 3.0)(children: CastStringToDouble(col 0:string) -> 4:double)
predicate: (UDFToDouble(a) < 3.0D) (type: boolean)
- Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 340 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count()
Group By Vectorization:
@@ -346,7 +346,7 @@ STAGE PLANS:
keys: a (type: string), b (type: string), 0L (type: bigint)
mode: hash
outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 8 Data size: 2944 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4 Data size: 744 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: bigint)
sort order: +++
@@ -357,7 +357,7 @@ STAGE PLANS:
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
valueColumns: 3:bigint
- Statistics: Num rows: 8 Data size: 2944 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4 Data size: 744 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col3 (type: bigint)
Reduce Output Operator
key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: bigint)
@@ -369,7 +369,7 @@ STAGE PLANS:
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
valueColumns: 3:bigint
- Statistics: Num rows: 8 Data size: 2944 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4 Data size: 744 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col3 (type: bigint)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -417,7 +417,7 @@ STAGE PLANS:
keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: bigint)
mode: mergepartial
outputColumnNames: _col0, _col1, _col3
- Statistics: Num rows: 4 Data size: 1472 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4 Data size: 744 Basic stats: COMPLETE Column stats: COMPLETE
pruneGroupingSetId: true
Filter Operator
Filter Vectorization:
@@ -425,7 +425,7 @@ STAGE PLANS:
native: true
predicateExpression: SelectColumnIsNotNull(col 0:string)
predicate: _col0 is not null (type: boolean)
- Statistics: Num rows: 4 Data size: 1472 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4 Data size: 744 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: string), _col1 (type: string), _col3 (type: bigint)
outputColumnNames: _col0, _col1, _col2
@@ -433,7 +433,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1, 2]
- Statistics: Num rows: 4 Data size: 1472 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4 Data size: 712 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
@@ -444,7 +444,7 @@ STAGE PLANS:
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
valueColumns: 1:string, 2:bigint
- Statistics: Num rows: 4 Data size: 1472 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4 Data size: 712 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: string), _col2 (type: bigint)
Reducer 3
Execution mode: llap
@@ -456,10 +456,10 @@ STAGE PLANS:
0 _col0 (type: string)
1 _col0 (type: string)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
- Statistics: Num rows: 4 Data size: 1619 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 8 Data size: 2848 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 4 Data size: 1619 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 8 Data size: 2848 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -496,7 +496,7 @@ STAGE PLANS:
keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: bigint)
mode: mergepartial
outputColumnNames: _col0, _col1, _col3
- Statistics: Num rows: 4 Data size: 1472 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4 Data size: 744 Basic stats: COMPLETE Column stats: COMPLETE
pruneGroupingSetId: true
Filter Operator
Filter Vectorization:
@@ -504,7 +504,7 @@ STAGE PLANS:
native: true
predicateExpression: SelectColumnIsNotNull(col 0:string)
predicate: _col0 is not null (type: boolean)
- Statistics: Num rows: 4 Data size: 1472 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4 Data size: 744 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: string), _col1 (type: string), _col3 (type: bigint)
outputColumnNames: _col0, _col1, _col2
@@ -512,7 +512,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1, 2]
- Statistics: Num rows: 4 Data size: 1472 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4 Data size: 712 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
@@ -523,7 +523,7 @@ STAGE PLANS:
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
valueColumns: 1:string, 2:bigint
- Statistics: Num rows: 4 Data size: 1472 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4 Data size: 712 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: string), _col2 (type: bigint)
Stage: Stage-0
@@ -605,7 +605,7 @@ STAGE PLANS:
TableScan
alias: t1_n161
filterExpr: (UDFToDouble(a) < 3.0D) (type: boolean)
- Statistics: Num rows: 6 Data size: 2208 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 1020 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:a:string, 1:b:string, 2:c:string, 3:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -615,7 +615,7 @@ STAGE PLANS:
native: true
predicateExpression: FilterDoubleColLessDoubleScalar(col 4:double, val 3.0)(children: CastStringToDouble(col 0:string) -> 4:double)
predicate: (UDFToDouble(a) < 3.0D) (type: boolean)
- Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 340 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count()
Group By Vectorization:
@@ -629,7 +629,7 @@ STAGE PLANS:
keys: a (type: string), b (type: string)
mode: hash
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string), _col1 (type: string)
sort order: ++
@@ -640,7 +640,7 @@ STAGE PLANS:
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
valueColumns: 2:bigint
- Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col2 (type: bigint)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -688,7 +688,7 @@ STAGE PLANS:
keys: KEY._col0 (type: string), KEY._col1 (type: string), 0L (type: bigint)
mode: partials
outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 8 Data size: 2944 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4 Data size: 744 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: bigint)
sort order: +++
@@ -699,7 +699,7 @@ STAGE PLANS:
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
valueColumns: 3:bigint
- Statistics: Num rows: 8 Data size: 2944 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4 Data size: 744 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col3 (type: bigint)
Reduce Output Operator
key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: bigint)
@@ -711,7 +711,7 @@ STAGE PLANS:
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
valueColumns: 3:bigint
- Statistics: Num rows: 8 Data size: 2944 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4 Data size: 744 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col3 (type: bigint)
Reducer 3
Execution mode: vectorized, llap
@@ -742,7 +742,7 @@ STAGE PLANS:
keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: bigint)
mode: final
outputColumnNames: _col0, _col1, _col3
- Statistics: Num rows: 4 Data size: 1472 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4 Data size: 744 Basic stats: COMPLETE Column stats: COMPLETE
pruneGroupingSetId: true
Filter Operator
Filter Vectorization:
@@ -750,7 +750,7 @@ STAGE PLANS:
native: true
predicateExpression: SelectColumnIsNotNull(col 0:string)
predicate: _col0 is not null (type: boolean)
- Statistics: Num rows: 4 Data size: 1472 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4 Data size: 744 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: string), _col1 (type: string), _col3 (type: bigint)
outputColumnNames: _col0, _col1, _col2
@@ -758,7 +758,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1, 2]
- Statistics: Num rows: 4 Data size: 1472 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4 Data size: 712 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
@@ -769,7 +769,7 @@ STAGE PLANS:
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
valueColumns: 1:string, 2:bigint
- Statistics: Num rows: 4 Data size: 1472 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4 Data size: 712 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: string), _col2 (type: bigint)
Reducer 4
Execution mode: llap
@@ -781,10 +781,10 @@ STAGE PLANS:
0 _col0 (type: string)
1 _col0 (type: string)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
- Statistics: Num rows: 4 Data size: 1619 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 16 Data size: 5696 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 4 Data size: 1619 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 16 Data size: 5696 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -821,7 +821,7 @@ STAGE PLANS:
keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: bigint)
mode: final
outputColumnNames: _col0, _col1, _col3
- Statistics: Num rows: 4 Data size: 1472 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4 Data size: 744 Basic stats: COMPLETE Column stats: COMPLETE
pruneGroupingSetId: true
Filter Operator
Filter Vectorization:
@@ -829,7 +829,7 @@ STAGE PLANS:
native: true
predicateExpression: SelectColumnIsNotNull(col 0:string)
predicate: _col0 is not null (type: boolean)
- Statistics: Num rows: 4 Data size: 1472 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4 Data size: 744 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: string), _col1 (type: string), _col3 (type: bigint)
outputColumnNames: _col0, _col1, _col2
@@ -837,7 +837,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1, 2]
- Statistics: Num rows: 4 Data size: 1472 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4 Data size: 712 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
@@ -848,7 +848,7 @@ STAGE PLANS:
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
valueColumns: 1:string, 2:bigint
- Statistics: Num rows: 4 Data size: 1472 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4 Data size: 712 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: string), _col2 (type: bigint)
Stage: Stage-0
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/llap/vector_groupby_grouping_sets5.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/vector_groupby_grouping_sets5.q.out b/ql/src/test/results/clientpositive/llap/vector_groupby_grouping_sets5.q.out
index ff43724..eadcb6e 100644
--- a/ql/src/test/results/clientpositive/llap/vector_groupby_grouping_sets5.q.out
+++ b/ql/src/test/results/clientpositive/llap/vector_groupby_grouping_sets5.q.out
@@ -62,7 +62,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: t1_n33
- Statistics: Num rows: 6 Data size: 2208 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 1020 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:a:string, 1:b:string, 2:c:string, 3:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -73,7 +73,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1]
- Statistics: Num rows: 6 Data size: 2208 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 1020 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
Group By Vectorization:
className: VectorGroupByOperator
@@ -85,7 +85,7 @@ STAGE PLANS:
keys: a (type: string), b (type: string)
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 6 Data size: 2208 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 510 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string), _col1 (type: string)
sort order: ++
@@ -95,7 +95,7 @@ STAGE PLANS:
keyColumns: 0:string, 1:string
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 6 Data size: 2208 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 510 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized, llap
LLAP IO: all inputs
Map Vectorization:
@@ -140,7 +140,7 @@ STAGE PLANS:
keys: KEY._col0 (type: string), KEY._col1 (type: string)
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 3 Data size: 1104 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 510 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count()
Group By Vectorization:
@@ -154,7 +154,7 @@ STAGE PLANS:
keys: _col0 (type: string), _col1 (type: string), 0L (type: bigint)
mode: hash
outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 12 Data size: 4416 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 1116 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: bigint)
sort order: +++
@@ -165,7 +165,7 @@ STAGE PLANS:
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
valueColumns: 3:bigint
- Statistics: Num rows: 12 Data size: 4416 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 1116 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col3 (type: bigint)
Reducer 3
Execution mode: vectorized, llap
@@ -196,7 +196,7 @@ STAGE PLANS:
keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: bigint)
mode: mergepartial
outputColumnNames: _col0, _col1, _col3
- Statistics: Num rows: 6 Data size: 2208 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 1116 Basic stats: COMPLETE Column stats: COMPLETE
pruneGroupingSetId: true
Select Operator
expressions: _col0 (type: string), _col1 (type: string), _col3 (type: bigint)
@@ -205,13 +205,13 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1, 2]
- Statistics: Num rows: 6 Data size: 2208 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 1068 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 6 Data size: 2208 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 1068 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -257,7 +257,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: t1_n33
- Statistics: Num rows: 6 Data size: 2208 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 1020 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:a:string, 1:b:string, 2:c:string, 3:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -268,7 +268,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1]
- Statistics: Num rows: 6 Data size: 2208 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 1020 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
Group By Vectorization:
className: VectorGroupByOperator
@@ -280,7 +280,7 @@ STAGE PLANS:
keys: a (type: string), b (type: string)
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 6 Data size: 2208 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 510 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string), _col1 (type: string)
sort order: ++
@@ -290,7 +290,7 @@ STAGE PLANS:
keyColumns: 0:string, 1:string
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 6 Data size: 2208 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 510 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized, llap
LLAP IO: all inputs
Map Vectorization:
@@ -335,7 +335,7 @@ STAGE PLANS:
keys: KEY._col0 (type: string), KEY._col1 (type: string)
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 3 Data size: 1104 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 510 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count()
Group By Vectorization:
@@ -349,7 +349,7 @@ STAGE PLANS:
keys: _col0 (type: string), _col1 (type: string), 0L (type: bigint)
mode: hash
outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 12 Data size: 4416 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 1116 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: bigint)
sort order: +++
@@ -360,7 +360,7 @@ STAGE PLANS:
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
valueColumns: 3:bigint
- Statistics: Num rows: 12 Data size: 4416 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 1116 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col3 (type: bigint)
Reducer 3
Execution mode: vectorized, llap
@@ -391,7 +391,7 @@ STAGE PLANS:
keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: bigint)
mode: mergepartial
outputColumnNames: _col0, _col1, _col3
- Statistics: Num rows: 6 Data size: 2208 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 1116 Basic stats: COMPLETE Column stats: COMPLETE
pruneGroupingSetId: true
Select Operator
expressions: _col0 (type: string), _col1 (type: string), _col3 (type: bigint)
@@ -400,13 +400,13 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1, 2]
- Statistics: Num rows: 6 Data size: 2208 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 1068 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 6 Data size: 2208 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 1068 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -479,7 +479,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: t1_n33
- Statistics: Num rows: 6 Data size: 2208 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 1020 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:a:string, 1:b:string, 2:c:string, 3:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -490,7 +490,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1]
- Statistics: Num rows: 6 Data size: 2208 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 1020 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
Group By Vectorization:
className: VectorGroupByOperator
@@ -502,7 +502,7 @@ STAGE PLANS:
keys: a (type: string), b (type: string)
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 6 Data size: 2208 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 510 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string), _col1 (type: string)
sort order: ++
@@ -512,7 +512,7 @@ STAGE PLANS:
keyColumns: 0:string, 1:string
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 6 Data size: 2208 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 510 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized, llap
LLAP IO: all inputs
Map Vectorization:
@@ -557,7 +557,7 @@ STAGE PLANS:
keys: KEY._col0 (type: string), KEY._col1 (type: string)
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 3 Data size: 1104 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 510 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count()
Group By Vectorization:
@@ -571,7 +571,7 @@ STAGE PLANS:
keys: _col0 (type: string), _col1 (type: string)
mode: hash
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 3 Data size: 1104 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string), _col1 (type: string)
sort order: ++
@@ -582,7 +582,7 @@ STAGE PLANS:
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
valueColumns: 2:bigint
- Statistics: Num rows: 3 Data size: 1104 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col2 (type: bigint)
Reducer 3
Execution mode: vectorized, llap
@@ -613,7 +613,7 @@ STAGE PLANS:
keys: KEY._col0 (type: string), KEY._col1 (type: string), 0L (type: bigint)
mode: partials
outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 12 Data size: 4416 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4 Data size: 744 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: bigint)
sort order: +++
@@ -624,7 +624,7 @@ STAGE PLANS:
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
valueColumns: 3:bigint
- Statistics: Num rows: 12 Data size: 4416 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4 Data size: 744 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col3 (type: bigint)
Reducer 4
Execution mode: vectorized, llap
@@ -655,7 +655,7 @@ STAGE PLANS:
keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: bigint)
mode: final
outputColumnNames: _col0, _col1, _col3
- Statistics: Num rows: 6 Data size: 2208 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4 Data size: 744 Basic stats: COMPLETE Column stats: COMPLETE
pruneGroupingSetId: true
Select Operator
expressions: _col0 (type: string), _col1 (type: string), _col3 (type: bigint)
@@ -664,13 +664,13 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1, 2]
- Statistics: Num rows: 6 Data size: 2208 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4 Data size: 712 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 6 Data size: 2208 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4 Data size: 712 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/llap/vector_groupby_grouping_sets6.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/vector_groupby_grouping_sets6.q.out b/ql/src/test/results/clientpositive/llap/vector_groupby_grouping_sets6.q.out
index 946abaf..a516ae4 100644
--- a/ql/src/test/results/clientpositive/llap/vector_groupby_grouping_sets6.q.out
+++ b/ql/src/test/results/clientpositive/llap/vector_groupby_grouping_sets6.q.out
@@ -63,7 +63,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: t1_n84
- Statistics: Num rows: 6 Data size: 2208 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 1020 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:a:string, 1:b:string, 2:c:string, 3:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -73,7 +73,7 @@ STAGE PLANS:
native: true
predicateExpression: FilterDoubleColEqualDoubleScalar(col 4:double, val 5.0)(children: CastStringToDouble(col 0:string) -> 4:double)
predicate: (UDFToDouble(a) = 5.0D) (type: boolean)
- Statistics: Num rows: 3 Data size: 1104 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 510 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
Group By Vectorization:
className: VectorGroupByOperator
@@ -85,7 +85,7 @@ STAGE PLANS:
keys: a (type: string), b (type: string), 0L (type: bigint)
mode: hash
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 6 Data size: 2208 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 534 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: bigint)
sort order: +++
@@ -95,7 +95,7 @@ STAGE PLANS:
keyColumns: 0:string, 1:string, 2:bigint
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 6 Data size: 2208 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 534 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized, llap
LLAP IO: all inputs
Map Vectorization:
@@ -140,14 +140,14 @@ STAGE PLANS:
keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: bigint)
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 3 Data size: 1104 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 534 Basic stats: COMPLETE Column stats: COMPLETE
pruneGroupingSetId: true
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 3 Data size: 1104 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 534 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -209,7 +209,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: t1_n84
- Statistics: Num rows: 6 Data size: 2208 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 1020 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:a:string, 1:b:string, 2:c:string, 3:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -219,7 +219,7 @@ STAGE PLANS:
native: true
predicateExpression: FilterDoubleColEqualDoubleScalar(col 4:double, val 5.0)(children: CastStringToDouble(col 0:string) -> 4:double)
predicate: (UDFToDouble(a) = 5.0D) (type: boolean)
- Statistics: Num rows: 3 Data size: 1104 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 510 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
Group By Vectorization:
className: VectorGroupByOperator
@@ -231,7 +231,7 @@ STAGE PLANS:
keys: a (type: string), b (type: string), 0L (type: bigint)
mode: hash
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 6 Data size: 2208 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 534 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: bigint)
sort order: +++
@@ -241,7 +241,7 @@ STAGE PLANS:
keyColumns: 0:string, 1:string, 2:bigint
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 6 Data size: 2208 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 534 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized, llap
LLAP IO: all inputs
Map Vectorization:
@@ -286,14 +286,14 @@ STAGE PLANS:
keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: bigint)
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 3 Data size: 1104 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 534 Basic stats: COMPLETE Column stats: COMPLETE
pruneGroupingSetId: true
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 3 Data size: 1104 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 534 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
[32/35] hive git commit: HIVE-16957: Support CTAS for auto gather
column stats (Jesus Camacho Rodriguez, reviewed by Ashutosh Chauhan)
Posted by jc...@apache.org.
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/llap/cross_prod_1.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/cross_prod_1.q.out b/ql/src/test/results/clientpositive/llap/cross_prod_1.q.out
index ac1f4ea..f900a01 100644
--- a/ql/src/test/results/clientpositive/llap/cross_prod_1.q.out
+++ b/ql/src/test/results/clientpositive/llap/cross_prod_1.q.out
@@ -38,14 +38,14 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: a
- Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: key (type: string), value (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
- Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: string), _col1 (type: string)
Execution mode: vectorized, llap
LLAP IO: no inputs
@@ -53,14 +53,14 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: b
- Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: key (type: string), value (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
- Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: string), _col1 (type: string)
Execution mode: vectorized, llap
LLAP IO: no inputs
@@ -74,11 +74,11 @@ STAGE PLANS:
0
1
outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 100 Data size: 73700 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 100 Data size: 35600 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string), _col2 (type: string)
sort order: ++
- Statistics: Num rows: 100 Data size: 73700 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 100 Data size: 35600 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: string), _col3 (type: string)
Reducer 3
Execution mode: vectorized, llap
@@ -86,10 +86,10 @@ STAGE PLANS:
Select Operator
expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string), KEY.reducesinkkey1 (type: string), VALUE._col1 (type: string)
outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 100 Data size: 73700 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 100 Data size: 35600 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 100 Data size: 73700 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 100 Data size: 35600 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -235,14 +235,14 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: a
- Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: key (type: string), value (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
- Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: string), _col1 (type: string)
Execution mode: vectorized, llap
LLAP IO: no inputs
@@ -250,14 +250,14 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: b
- Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: key (type: string), value (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
- Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: string), _col1 (type: string)
Execution mode: vectorized, llap
LLAP IO: no inputs
@@ -272,10 +272,10 @@ STAGE PLANS:
1
outputColumnNames: _col0, _col1, _col2, _col3
residual filter predicates: {(_col0 < _col2)}
- Statistics: Num rows: 33 Data size: 24321 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 33 Data size: 11748 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 33 Data size: 24321 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 33 Data size: 11748 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -367,17 +367,17 @@ STAGE PLANS:
TableScan
alias: a
filterExpr: key BETWEEN '103' AND '105' (type: boolean)
- Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: key BETWEEN '103' AND '105' (type: boolean)
- Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: key (type: string), value (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
- Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: string), _col1 (type: string)
Execution mode: vectorized, llap
LLAP IO: no inputs
@@ -385,14 +385,14 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: b
- Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: key (type: string), value (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
- Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: string), _col1 (type: string)
Execution mode: vectorized, llap
LLAP IO: no inputs
@@ -406,10 +406,10 @@ STAGE PLANS:
0
1
outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 10 Data size: 7370 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 3560 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 10 Data size: 7370 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 3560 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -485,14 +485,14 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: a
- Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: key (type: string), value (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
- Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: string), _col1 (type: string)
Execution mode: vectorized, llap
LLAP IO: no inputs
@@ -500,14 +500,14 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: c
- Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: key (type: string), value (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
- Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: string), _col1 (type: string)
Execution mode: vectorized, llap
LLAP IO: no inputs
@@ -515,14 +515,14 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: b
- Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: key (type: string), value (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
- Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: string), _col1 (type: string)
Execution mode: vectorized, llap
LLAP IO: no inputs
@@ -538,14 +538,14 @@ STAGE PLANS:
1
2
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
- Statistics: Num rows: 1000 Data size: 1105000 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1000 Data size: 534000 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: string), _col1 (type: string), _col4 (type: string), _col5 (type: string), _col2 (type: string), _col3 (type: string)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
- Statistics: Num rows: 1000 Data size: 1105000 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1000 Data size: 534000 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 1000 Data size: 1105000 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1000 Data size: 534000 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -1592,17 +1592,17 @@ STAGE PLANS:
TableScan
alias: a
filterExpr: (key) IN ('103', '104', '105') (type: boolean)
- Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: (key) IN ('103', '104', '105') (type: boolean)
- Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 534 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: key (type: string), value (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 534 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
- Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 534 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: string), _col1 (type: string)
Execution mode: vectorized, llap
LLAP IO: no inputs
@@ -1610,14 +1610,14 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: b
- Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: key (type: string), value (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
- Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: string), _col1 (type: string)
Execution mode: vectorized, llap
LLAP IO: no inputs
@@ -1631,10 +1631,10 @@ STAGE PLANS:
0
1
outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 100 Data size: 73700 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 30 Data size: 10680 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 100 Data size: 73700 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 30 Data size: 10680 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -1711,14 +1711,14 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: a
- Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 870 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: key (type: string)
outputColumnNames: _col0
- Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 870 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
- Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 870 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: string)
Execution mode: vectorized, llap
LLAP IO: no inputs
@@ -1744,18 +1744,18 @@ STAGE PLANS:
0
1
outputColumnNames: _col0
- Statistics: Num rows: 100 Data size: 18900 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 100 Data size: 8700 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count()
keys: _col0 (type: string)
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 100 Data size: 18900 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 950 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 100 Data size: 18900 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 950 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: bigint)
Reducer 3
Execution mode: vectorized, llap
@@ -1765,10 +1765,10 @@ STAGE PLANS:
keys: KEY._col0 (type: string)
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 50 Data size: 9450 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 950 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 50 Data size: 9450 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 950 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -1824,14 +1824,14 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: a
- Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: key (type: string), value (type: string), value BETWEEN 'val_103' AND 'val_105' (type: boolean)
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 1820 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
- Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 1820 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: boolean)
Execution mode: vectorized, llap
LLAP IO: no inputs
@@ -1839,14 +1839,14 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: b
- Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: key (type: string), value (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
- Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: string), _col1 (type: string)
Execution mode: vectorized, llap
LLAP IO: no inputs
@@ -1861,14 +1861,14 @@ STAGE PLANS:
1
outputColumnNames: _col0, _col1, _col2, _col3, _col4
residual filter predicates: {((_col0 = _col3) or _col2)}
- Statistics: Num rows: 100 Data size: 73700 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 100 Data size: 36000 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: string), _col1 (type: string), _col3 (type: string), _col4 (type: string)
outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 100 Data size: 73700 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 100 Data size: 35600 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 100 Data size: 73700 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 100 Data size: 35600 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -1905,14 +1905,14 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: a
- Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: key (type: string), value (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
- Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: string), _col1 (type: string)
Execution mode: vectorized, llap
LLAP IO: no inputs
@@ -1920,14 +1920,14 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: b
- Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: key (type: string), value (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
- Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: string), _col1 (type: string)
Execution mode: vectorized, llap
LLAP IO: no inputs
@@ -1942,10 +1942,10 @@ STAGE PLANS:
1
outputColumnNames: _col0, _col1, _col2, _col3
residual filter predicates: {((_col0 = _col2) or _col1 BETWEEN 'val_103' AND 'val_105')}
- Statistics: Num rows: 100 Data size: 73700 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 100 Data size: 35600 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 100 Data size: 73700 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 100 Data size: 35600 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -1982,14 +1982,14 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: a
- Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: key (type: string), value (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
- Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: string), _col1 (type: string)
Execution mode: vectorized, llap
LLAP IO: no inputs
@@ -1997,14 +1997,14 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: b
- Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: key (type: string), value (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
- Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: string), _col1 (type: string)
Execution mode: vectorized, llap
LLAP IO: no inputs
@@ -2019,10 +2019,10 @@ STAGE PLANS:
1
outputColumnNames: _col0, _col1, _col2, _col3
residual filter predicates: {((_col0 = _col2) or _col1 BETWEEN 'val_103' AND 'val_105')}
- Statistics: Num rows: 100 Data size: 73700 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 100 Data size: 35600 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 100 Data size: 73700 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 100 Data size: 35600 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -2061,28 +2061,28 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: x_n0
- Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 870 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: key (type: string)
outputColumnNames: key
- Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 870 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count()
keys: key (type: string)
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 475 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 475 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: bigint)
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 475 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: bigint)
Execution mode: vectorized, llap
LLAP IO: no inputs
@@ -2094,10 +2094,10 @@ STAGE PLANS:
keys: KEY._col0 (type: string)
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 5 Data size: 920 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 475 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
- Statistics: Num rows: 5 Data size: 920 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 475 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: string), _col1 (type: bigint)
Reducer 3
Execution mode: llap
@@ -2109,10 +2109,10 @@ STAGE PLANS:
0
1
outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 25 Data size: 9225 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 25 Data size: 4750 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 25 Data size: 9225 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 25 Data size: 4750 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -2125,10 +2125,10 @@ STAGE PLANS:
keys: KEY._col0 (type: string)
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 5 Data size: 920 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 475 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
- Statistics: Num rows: 5 Data size: 920 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 475 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: string), _col1 (type: bigint)
Stage: Stage-0
@@ -2273,14 +2273,14 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: x_n0
- Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: key (type: string), value (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
- Statistics: Num rows: 20 Data size: 7360 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 20 Data size: 3560 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: string), _col1 (type: string)
Execution mode: vectorized, llap
LLAP IO: no inputs
@@ -2288,14 +2288,14 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: y
- Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: key (type: string), value (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
- Statistics: Num rows: 20 Data size: 7360 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 20 Data size: 3560 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: string), _col1 (type: string)
Execution mode: vectorized, llap
LLAP IO: no inputs
@@ -2303,14 +2303,14 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: x_n0
- Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: key (type: string), value (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
- Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: string), _col1 (type: string)
Execution mode: vectorized, llap
LLAP IO: no inputs
@@ -2324,10 +2324,10 @@ STAGE PLANS:
0
1
outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 200 Data size: 147400 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 200 Data size: 71200 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 200 Data size: 147400 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 200 Data size: 71200 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/llap/cross_prod_3.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/cross_prod_3.q.out b/ql/src/test/results/clientpositive/llap/cross_prod_3.q.out
index 672ff7b..9b2db3a 100644
--- a/ql/src/test/results/clientpositive/llap/cross_prod_3.q.out
+++ b/ql/src/test/results/clientpositive/llap/cross_prod_3.q.out
@@ -77,14 +77,14 @@ STAGE PLANS:
input vertices:
1 Map 2
2 Map 3
- Statistics: Num rows: 22 Data size: 3916 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 530 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col2 (type: string), _col3 (type: string), _col0 (type: string), _col1 (type: string), _col4 (type: string), _col5 (type: string)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
- Statistics: Num rows: 22 Data size: 3916 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 530 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 22 Data size: 3916 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 530 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -96,19 +96,19 @@ STAGE PLANS:
TableScan
alias: y_n0
filterExpr: key is not null (type: boolean)
- Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 174 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: key is not null (type: boolean)
- Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 174 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: key (type: string), value (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 174 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 174 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: string)
Execution mode: vectorized, llap
LLAP IO: no inputs
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/llap/cross_prod_4.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/cross_prod_4.q.out b/ql/src/test/results/clientpositive/llap/cross_prod_4.q.out
index 910976f..310a0fa 100644
--- a/ql/src/test/results/clientpositive/llap/cross_prod_4.q.out
+++ b/ql/src/test/results/clientpositive/llap/cross_prod_4.q.out
@@ -37,14 +37,14 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: a
- Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: key (type: string), value (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
- Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: string), _col1 (type: string)
Execution mode: vectorized, llap
LLAP IO: no inputs
@@ -52,14 +52,14 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: b
- Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: key (type: string), value (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
- Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: string), _col1 (type: string)
Execution mode: vectorized, llap
LLAP IO: no inputs
@@ -73,10 +73,10 @@ STAGE PLANS:
0
1
outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 100 Data size: 73700 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 100 Data size: 35600 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 100 Data size: 73700 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 100 Data size: 35600 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/llap/cross_product_check_1.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/cross_product_check_1.q.out b/ql/src/test/results/clientpositive/llap/cross_product_check_1.q.out
index 1dfc35e..6833de0 100644
--- a/ql/src/test/results/clientpositive/llap/cross_product_check_1.q.out
+++ b/ql/src/test/results/clientpositive/llap/cross_product_check_1.q.out
@@ -55,14 +55,14 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: a_n8
- Statistics: Num rows: 500 Data size: 175168 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: key (type: string), value (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 500 Data size: 175168 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
- Statistics: Num rows: 500 Data size: 175168 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: string), _col1 (type: string)
Execution mode: vectorized, llap
LLAP IO: no inputs
@@ -70,14 +70,14 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: b_n6
- Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: key (type: string), value (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
- Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: string), _col1 (type: string)
Execution mode: vectorized, llap
LLAP IO: no inputs
@@ -91,10 +91,10 @@ STAGE PLANS:
0
1
outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 5000 Data size: 3596680 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5000 Data size: 1780000 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 5000 Data size: 3596680 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5000 Data size: 1780000 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -135,19 +135,19 @@ STAGE PLANS:
TableScan
alias: d1
filterExpr: key is not null (type: boolean)
- Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: key is not null (type: boolean)
- Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: key (type: string), value (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: string)
Execution mode: vectorized, llap
LLAP IO: no inputs
@@ -156,19 +156,19 @@ STAGE PLANS:
TableScan
alias: d2
filterExpr: key is not null (type: boolean)
- Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: key is not null (type: boolean)
- Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: key (type: string), value (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: string)
Execution mode: vectorized, llap
LLAP IO: no inputs
@@ -176,14 +176,14 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: a_n8
- Statistics: Num rows: 500 Data size: 175168 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: key (type: string), value (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 500 Data size: 175168 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
- Statistics: Num rows: 500 Data size: 175168 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: string), _col1 (type: string)
Execution mode: vectorized, llap
LLAP IO: no inputs
@@ -197,10 +197,10 @@ STAGE PLANS:
0 _col0 (type: string)
1 _col0 (type: string)
outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 11 Data size: 4048 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 3560 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
- Statistics: Num rows: 11 Data size: 4048 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 3560 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string)
Reducer 3
Execution mode: llap
@@ -212,10 +212,10 @@ STAGE PLANS:
0
1
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
- Statistics: Num rows: 5500 Data size: 3956348 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5000 Data size: 2670000 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 5500 Data size: 3956348 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5000 Data size: 2670000 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -262,14 +262,14 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: a_n8
- Statistics: Num rows: 500 Data size: 175168 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: key (type: string), value (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 500 Data size: 175168 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
- Statistics: Num rows: 500 Data size: 175168 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: string), _col1 (type: string)
Execution mode: vectorized, llap
LLAP IO: no inputs
@@ -278,19 +278,19 @@ STAGE PLANS:
TableScan
alias: d1
filterExpr: key is not null (type: boolean)
- Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 870 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: key is not null (type: boolean)
- Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 870 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: key (type: string)
outputColumnNames: _col0
- Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 870 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 870 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized, llap
LLAP IO: no inputs
Map 6
@@ -298,19 +298,19 @@ STAGE PLANS:
TableScan
alias: d2
filterExpr: key is not null (type: boolean)
- Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 870 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: key is not null (type: boolean)
- Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 870 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: key (type: string)
outputColumnNames: _col0
- Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 870 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 870 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized, llap
LLAP IO: no inputs
Reducer 2
@@ -323,10 +323,10 @@ STAGE PLANS:
0
1
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 2500 Data size: 1338340 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2500 Data size: 662500 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 2500 Data size: 1338340 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2500 Data size: 662500 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -341,17 +341,17 @@ STAGE PLANS:
0 _col0 (type: string)
1 _col0 (type: string)
outputColumnNames: _col0
- Statistics: Num rows: 11 Data size: 2024 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 870 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
keys: _col0 (type: string)
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 11 Data size: 2024 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 435 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 11 Data size: 2024 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 435 Basic stats: COMPLETE Column stats: COMPLETE
Reducer 5
Execution mode: vectorized, llap
Reduce Operator Tree:
@@ -359,10 +359,10 @@ STAGE PLANS:
keys: KEY._col0 (type: string)
mode: mergepartial
outputColumnNames: _col0
- Statistics: Num rows: 5 Data size: 920 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 435 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
- Statistics: Num rows: 5 Data size: 920 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 435 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: string)
Stage: Stage-0
@@ -401,14 +401,14 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: a_n8
- Statistics: Num rows: 500 Data size: 175168 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: key (type: string), value (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 500 Data size: 175168 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
- Statistics: Num rows: 500 Data size: 175168 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: string), _col1 (type: string)
Execution mode: vectorized, llap
LLAP IO: no inputs
@@ -416,14 +416,14 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: d1
- Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 870 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: key (type: string)
outputColumnNames: _col0
- Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 870 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
- Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 870 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: string)
Execution mode: vectorized, llap
LLAP IO: no inputs
@@ -449,10 +449,10 @@ STAGE PLANS:
0
1
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 25000 Data size: 13508400 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5000 Data size: 1325000 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 25000 Data size: 13508400 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5000 Data size: 1325000 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -467,17 +467,17 @@ STAGE PLANS:
0
1
outputColumnNames: _col0
- Statistics: Num rows: 100 Data size: 18900 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 100 Data size: 8700 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
keys: _col0 (type: string)
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 100 Data size: 18900 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 870 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 100 Data size: 18900 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 870 Basic stats: COMPLETE Column stats: COMPLETE
Reducer 5
Execution mode: vectorized, llap
Reduce Operator Tree:
@@ -485,10 +485,10 @@ STAGE PLANS:
keys: KEY._col0 (type: string)
mode: mergepartial
outputColumnNames: _col0
- Statistics: Num rows: 50 Data size: 9450 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 870 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
- Statistics: Num rows: 50 Data size: 9450 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 870 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: string)
Stage: Stage-0
@@ -531,21 +531,21 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: a_n8
- Statistics: Num rows: 500 Data size: 87584 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: key (type: string)
outputColumnNames: key
- Statistics: Num rows: 500 Data size: 87584 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
keys: key (type: string)
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 500 Data size: 87584 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 250 Data size: 21750 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 500 Data size: 87584 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 250 Data size: 21750 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized, llap
LLAP IO: no inputs
Map 4
@@ -553,19 +553,19 @@ STAGE PLANS:
TableScan
alias: d1
filterExpr: key is not null (type: boolean)
- Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 870 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: key is not null (type: boolean)
- Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 870 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: key (type: string)
outputColumnNames: _col0
- Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 870 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 870 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized, llap
LLAP IO: no inputs
Map 7
@@ -573,19 +573,19 @@ STAGE PLANS:
TableScan
alias: d2
filterExpr: key is not null (type: boolean)
- Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 870 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: key is not null (type: boolean)
- Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 870 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: key (type: string)
outputColumnNames: _col0
- Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 870 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 870 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized, llap
LLAP IO: no inputs
Reducer 2
@@ -595,10 +595,10 @@ STAGE PLANS:
keys: KEY._col0 (type: string)
mode: mergepartial
outputColumnNames: _col0
- Statistics: Num rows: 250 Data size: 43792 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 250 Data size: 21750 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
- Statistics: Num rows: 250 Data size: 43792 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 250 Data size: 21750 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: string)
Reducer 3
Execution mode: llap
@@ -610,10 +610,10 @@ STAGE PLANS:
0
1
outputColumnNames: _col0, _col1
- Statistics: Num rows: 1250 Data size: 450210 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1250 Data size: 217500 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 1250 Data size: 450210 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1250 Data size: 217500 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -628,17 +628,17 @@ STAGE PLANS:
0 _col0 (type: string)
1 _col0 (type: string)
outputColumnNames: _col0
- Statistics: Num rows: 11 Data size: 2024 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 870 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
keys: _col0 (type: string)
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 11 Data size: 2024 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 435 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 11 Data size: 2024 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 435 Basic stats: COMPLETE Column stats: COMPLETE
Reducer 6
Execution mode: vectorized, llap
Reduce Operator Tree:
@@ -646,10 +646,10 @@ STAGE PLANS:
keys: KEY._col0 (type: string)
mode: mergepartial
outputColumnNames: _col0
- Statistics: Num rows: 5 Data size: 920 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 435 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
- Statistics: Num rows: 5 Data size: 920 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 435 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: string)
Stage: Stage-0
[21/35] hive git commit: HIVE-16957: Support CTAS for auto gather
column stats (Jesus Camacho Rodriguez, reviewed by Ashutosh Chauhan)
Posted by jc...@apache.org.
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/llap/orc_llap_nonvector.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/orc_llap_nonvector.q.out b/ql/src/test/results/clientpositive/llap/orc_llap_nonvector.q.out
index f25f09e..472b310 100644
--- a/ql/src/test/results/clientpositive/llap/orc_llap_nonvector.q.out
+++ b/ql/src/test/results/clientpositive/llap/orc_llap_nonvector.q.out
@@ -88,17 +88,17 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: orc_llap_nonvector
- Statistics: Num rows: 12288 Data size: 5790800 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 3191474 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: ctinyint (type: tinyint), csmallint (type: smallint), cint (type: int), cbigint (type: bigint), cfloat (type: float), cdouble (type: double), cstring1 (type: string), cstring2 (type: string), ctimestamp1 (type: timestamp), ctimestamp2 (type: timestamp), cboolean1 (type: boolean), cboolean2 (type: boolean), rdm (type: double)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12
- Statistics: Num rows: 12288 Data size: 5790800 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 3191474 Basic stats: COMPLETE Column stats: COMPLETE
Limit
Number of rows: 100
- Statistics: Num rows: 100 Data size: 47100 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 100 Data size: 26280 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 100 Data size: 47100 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 100 Data size: 26280 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -243,17 +243,17 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: orc_llap_nonvector
- Statistics: Num rows: 12288 Data size: 2194900 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 899146 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: cint (type: int), cstring1 (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 12288 Data size: 2194900 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 899146 Basic stats: COMPLETE Column stats: COMPLETE
Limit
Number of rows: 1025
- Statistics: Num rows: 1025 Data size: 182450 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1025 Data size: 75068 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 1025 Data size: 182450 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1025 Data size: 75068 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/llap/partition_ctas.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/partition_ctas.q.out b/ql/src/test/results/clientpositive/llap/partition_ctas.q.out
index cf83638..3e290b3 100644
--- a/ql/src/test/results/clientpositive/llap/partition_ctas.q.out
+++ b/ql/src/test/results/clientpositive/llap/partition_ctas.q.out
@@ -24,6 +24,9 @@ STAGE PLANS:
Stage: Stage-1
Tez
#### A masked pattern was here ####
+ Edges:
+ Reducer 2 <- Map 1 (SIMPLE_EDGE)
+#### A masked pattern was here ####
Vertices:
Map 1
Map Operator Tree:
@@ -46,8 +49,44 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.partition_ctas_1
- Execution mode: vectorized, llap
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: string)
+ outputColumnNames: col1, col2
+ Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE
+ Group By Operator
+ aggregations: compute_stats(col1, 'hll')
+ keys: col2 (type: string)
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 27 Data size: 14229 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 27 Data size: 14229 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col1 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>)
+ Execution mode: llap
LLAP IO: no inputs
+ Reducer 2
+ Execution mode: llap
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: compute_stats(VALUE._col0)
+ keys: KEY._col0 (type: string)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 27 Data size: 14229 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: _col1 (type: struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col0 (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 27 Data size: 14229 Basic stats: COMPLETE Column stats: COMPLETE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 27 Data size: 14229 Basic stats: COMPLETE Column stats: COMPLETE
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
Stage: Stage-2
Dependency Collection
@@ -77,6 +116,10 @@ STAGE PLANS:
Stage: Stage-3
Stats Work
Basic Stats Work:
+ Column Stats Desc:
+ Columns: value
+ Column Types: string
+ Table: default.partition_ctas_1
PREHOOK: query: CREATE TABLE partition_ctas_1 PARTITIONED BY (key) AS
SELECT value, key FROM src where key > 200 and key < 300
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/llap/rcfile_createas1.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/rcfile_createas1.q.out b/ql/src/test/results/clientpositive/llap/rcfile_createas1.q.out
index f6f47bb..4f1a479 100644
--- a/ql/src/test/results/clientpositive/llap/rcfile_createas1.q.out
+++ b/ql/src/test/results/clientpositive/llap/rcfile_createas1.q.out
@@ -65,7 +65,7 @@ POSTHOOK: Output: default@rcfile_createas1b
STAGE DEPENDENCIES:
Stage-1 is a root stage
Stage-2 depends on stages: Stage-1
- Stage-4 depends on stages: Stage-2, Stage-0
+ Stage-4 depends on stages: Stage-0, Stage-2
Stage-3 depends on stages: Stage-4
Stage-0 depends on stages: Stage-1
@@ -73,6 +73,9 @@ STAGE PLANS:
Stage: Stage-1
Tez
#### A masked pattern was here ####
+ Edges:
+ Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE)
+#### A masked pattern was here ####
Vertices:
Map 1
Map Operator Tree:
@@ -91,8 +94,36 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
name: default.rcfile_createas1b
- Execution mode: vectorized, llap
+ Select Operator
+ expressions: _col0 (type: int), _col1 (type: string), _col2 (type: int)
+ outputColumnNames: col1, col2, col3
+ Statistics: Num rows: 1000 Data size: 99000 Basic stats: COMPLETE Column stats: COMPLETE
+ Group By Operator
+ aggregations: compute_stats(col1, 'hll'), compute_stats(col2, 'hll'), compute_stats(col3, 'hll')
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 1288 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 1288 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col0 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col2 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>)
+ Execution mode: llap
LLAP IO: no inputs
+ Reducer 2
+ Execution mode: llap
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: COMPLETE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: COMPLETE
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
Stage: Stage-2
Dependency Collection
@@ -109,6 +140,10 @@ STAGE PLANS:
Stage: Stage-3
Stats Work
Basic Stats Work:
+ Column Stats Desc:
+ Columns: key, value, part
+ Column Types: int, string, int
+ Table: default.rcfile_createas1b
Stage: Stage-0
Move Operator
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/llap/results_cache_1.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/results_cache_1.q.out b/ql/src/test/results/clientpositive/llap/results_cache_1.q.out
index d148c82..3ffbcd4 100644
--- a/ql/src/test/results/clientpositive/llap/results_cache_1.q.out
+++ b/ql/src/test/results/clientpositive/llap/results_cache_1.q.out
@@ -296,19 +296,19 @@ STAGE PLANS:
TableScan
alias: a
filterExpr: key is not null (type: boolean)
- Statistics: Num rows: 500 Data size: 87584 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: key is not null (type: boolean)
- Statistics: Num rows: 475 Data size: 83204 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: key (type: string)
outputColumnNames: _col0
- Statistics: Num rows: 475 Data size: 83204 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 475 Data size: 83204 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized, llap
LLAP IO: no inputs
Map 4
@@ -316,19 +316,19 @@ STAGE PLANS:
TableScan
alias: b
filterExpr: key is not null (type: boolean)
- Statistics: Num rows: 500 Data size: 87584 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: key is not null (type: boolean)
- Statistics: Num rows: 475 Data size: 83204 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: key (type: string)
outputColumnNames: _col0
- Statistics: Num rows: 475 Data size: 83204 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 475 Data size: 83204 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized, llap
LLAP IO: no inputs
Reducer 2
@@ -340,15 +340,15 @@ STAGE PLANS:
keys:
0 _col0 (type: string)
1 _col0 (type: string)
- Statistics: Num rows: 522 Data size: 91524 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 791 Data size: 6328 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count()
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: bigint)
Reducer 3
Execution mode: vectorized, llap
@@ -357,10 +357,10 @@ STAGE PLANS:
aggregations: count(VALUE._col0)
mode: mergepartial
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/llap/results_cache_invalidation2.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/results_cache_invalidation2.q.out b/ql/src/test/results/clientpositive/llap/results_cache_invalidation2.q.out
index e363683..05d8396 100644
--- a/ql/src/test/results/clientpositive/llap/results_cache_invalidation2.q.out
+++ b/ql/src/test/results/clientpositive/llap/results_cache_invalidation2.q.out
@@ -208,20 +208,20 @@ STAGE PLANS:
TableScan
alias: tab1
filterExpr: (UDFToDouble(key) > 0.0D) (type: boolean)
- Statistics: Num rows: 1500 Data size: 262384 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1500 Data size: 130500 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: (UDFToDouble(key) > 0.0D) (type: boolean)
- Statistics: Num rows: 500 Data size: 87461 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
- Statistics: Num rows: 500 Data size: 87461 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count()
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
- Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: bigint)
Execution mode: vectorized, llap
LLAP IO: no inputs
@@ -232,10 +232,10 @@ STAGE PLANS:
aggregations: count(VALUE._col0)
mode: mergepartial
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -287,19 +287,19 @@ STAGE PLANS:
TableScan
alias: tab1
filterExpr: key is not null (type: boolean)
- Statistics: Num rows: 1500 Data size: 262384 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1500 Data size: 130500 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: key is not null (type: boolean)
- Statistics: Num rows: 1425 Data size: 249264 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1500 Data size: 130500 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: key (type: string)
outputColumnNames: _col0
- Statistics: Num rows: 1425 Data size: 249264 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1500 Data size: 130500 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 1425 Data size: 249264 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1500 Data size: 130500 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized, llap
LLAP IO: no inputs
Map 4
@@ -331,15 +331,15 @@ STAGE PLANS:
keys:
0 _col0 (type: string)
1 _col0 (type: string)
- Statistics: Num rows: 1567 Data size: 274190 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2373 Data size: 18984 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count()
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: bigint)
Reducer 3
Execution mode: vectorized, llap
@@ -348,10 +348,10 @@ STAGE PLANS:
aggregations: count(VALUE._col0)
mode: mergepartial
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/llap/results_cache_with_masking.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/results_cache_with_masking.q.out b/ql/src/test/results/clientpositive/llap/results_cache_with_masking.q.out
index 4f50ae2..6999617 100644
--- a/ql/src/test/results/clientpositive/llap/results_cache_with_masking.q.out
+++ b/ql/src/test/results/clientpositive/llap/results_cache_with_masking.q.out
@@ -37,21 +37,21 @@ STAGE PLANS:
TableScan
alias: masking_test_n7
filterExpr: (((key % 2) = 0) and (key < 10)) (type: boolean)
- Statistics: Num rows: 500 Data size: 1904 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: (((key % 2) = 0) and (key < 10)) (type: boolean)
- Statistics: Num rows: 250 Data size: 952 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 83 Data size: 332 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count()
keys: key (type: int)
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 250 Data size: 952 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 41 Data size: 492 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 250 Data size: 952 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 41 Data size: 492 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: bigint)
Execution mode: vectorized, llap
LLAP IO: no inputs
@@ -63,10 +63,10 @@ STAGE PLANS:
keys: KEY._col0 (type: int)
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 125 Data size: 476 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 41 Data size: 492 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 125 Data size: 476 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 41 Data size: 492 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -117,21 +117,21 @@ STAGE PLANS:
TableScan
alias: masking_test_n7
filterExpr: (((key % 2) = 0) and (key < 10)) (type: boolean)
- Statistics: Num rows: 500 Data size: 1904 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: (((key % 2) = 0) and (key < 10)) (type: boolean)
- Statistics: Num rows: 250 Data size: 952 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 83 Data size: 332 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count()
keys: key (type: int)
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 250 Data size: 952 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 41 Data size: 492 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 250 Data size: 952 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 41 Data size: 492 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: bigint)
Execution mode: vectorized, llap
LLAP IO: no inputs
@@ -143,10 +143,10 @@ STAGE PLANS:
keys: KEY._col0 (type: int)
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 125 Data size: 476 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 41 Data size: 492 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 125 Data size: 476 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 41 Data size: 492 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/llap/runtime_stats_merge.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/runtime_stats_merge.q.out b/ql/src/test/results/clientpositive/llap/runtime_stats_merge.q.out
index 9a0f6f4..e1a747d 100644
--- a/ql/src/test/results/clientpositive/llap/runtime_stats_merge.q.out
+++ b/ql/src/test/results/clientpositive/llap/runtime_stats_merge.q.out
@@ -121,29 +121,29 @@ Stage-4
Dependency Collection{}
Stage-2
Reducer 3 vectorized, llap
- File Output Operator [FS_61]
+ File Output Operator [FS_54]
table:{"name:":"default.lineitem2"}
- Select Operator [SEL_60] (runtime: rows=1 width=76)
+ Select Operator [SEL_53] (runtime: rows=1 width=76)
Output:["_col0"]
<-Map 2 [SIMPLE_EDGE] llap
SHUFFLE [RS_10]
PartitionCols:UDFToInteger(_col0)
Select Operator [SEL_9] (runtime: rows=1 width=76)
Output:["_col0"]
- Filter Operator [FIL_32] (runtime: rows=1 width=84)
+ Filter Operator [FIL_25] (runtime: rows=1 width=84)
predicate:(_col4 = _col0)
- Map Join Operator [MAPJOIN_48] (runtime: rows=1 width=84)
- Conds:FIL_36.l_orderkey=RS_52._col0(Inner),Output:["_col0","_col3","_col4"]
+ Map Join Operator [MAPJOIN_41] (runtime: rows=1 width=84)
+ Conds:FIL_29.l_orderkey=RS_45._col0(Inner),Output:["_col0","_col3","_col4"]
<-Map 1 [BROADCAST_EDGE] vectorized, llap
- BROADCAST [RS_52]
+ BROADCAST [RS_45]
PartitionCols:_col0
- Select Operator [SEL_51] (runtime: rows=1 width=4)
+ Select Operator [SEL_44] (runtime: rows=1 width=4)
Output:["_col0"]
- Filter Operator [FIL_50] (runtime: rows=1 width=4)
+ Filter Operator [FIL_43] (runtime: rows=1 width=4)
predicate:l_orderkey is not null
TableScan [TS_0] (runtime: rows=1 width=4)
default@lineitem_stage,lineitem_stage, ACID table,Tbl:COMPLETE,Col:COMPLETE,Output:["l_orderkey"]
- <-Filter Operator [FIL_36] (runtime: rows=3 width=4)
+ <-Filter Operator [FIL_29] (runtime: rows=3 width=4)
predicate:l_orderkey is not null
TableScan [TS_2] (runtime: rows=3 width=4)
default@lineitem2,lineitem2, ACID table,Tbl:COMPLETE,Col:COMPLETE,Output:["l_orderkey"]
@@ -152,7 +152,7 @@ Stage-4
table:{"name:":"default.merge_tmp_table"}
Select Operator [SEL_21] (runtime: rows=0 width=-1)
Output:["_col0"]
- Filter Operator [FIL_33] (runtime: rows=0 width=-1)
+ Filter Operator [FIL_26] (runtime: rows=0 width=-1)
predicate:(_col1 > 1L)
Group By Operator [GBY_19] (runtime: rows=1 width=84)
Output:["_col0","_col1"],aggregations:["count(VALUE._col0)"],keys:KEY._col0
@@ -163,17 +163,9 @@ Stage-4
Output:["_col0","_col1"],aggregations:["count()"],keys:_col3
Select Operator [SEL_16] (runtime: rows=1 width=84)
Output:["_col3"]
- Filter Operator [FIL_34] (runtime: rows=1 width=84)
+ Filter Operator [FIL_27] (runtime: rows=1 width=84)
predicate:(_col4 = _col0)
- Please refer to the previous Map Join Operator [MAPJOIN_48]
- File Output Operator [FS_29]
- Select Operator [SEL_28] (runtime: rows=1 width=424)
- Output:["_col0"]
- Group By Operator [GBY_27] (runtime: rows=1 width=424)
- Output:["_col0"],aggregations:["compute_stats(val, 'hll')"]
- Select Operator [SEL_24] (runtime: rows=0 width=-1)
- Output:["val"]
- Please refer to the previous Select Operator [SEL_21]
+ Please refer to the previous Map Join Operator [MAPJOIN_41]
Stage-5
Stats Work{}
Stage-1
[17/35] hive git commit: HIVE-16957: Support CTAS for auto gather
column stats (Jesus Camacho Rodriguez, reviewed by Ashutosh Chauhan)
Posted by jc...@apache.org.
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/llap/union_top_level.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/union_top_level.q.out b/ql/src/test/results/clientpositive/llap/union_top_level.q.out
index 5083678..8fc40fc 100644
--- a/ql/src/test/results/clientpositive/llap/union_top_level.q.out
+++ b/ql/src/test/results/clientpositive/llap/union_top_level.q.out
@@ -419,7 +419,7 @@ POSTHOOK: Output: default@union_top
STAGE DEPENDENCIES:
Stage-1 is a root stage
Stage-2 depends on stages: Stage-1
- Stage-4 depends on stages: Stage-2, Stage-0
+ Stage-4 depends on stages: Stage-0, Stage-2
Stage-3 depends on stages: Stage-4
Stage-0 depends on stages: Stage-1
@@ -429,8 +429,9 @@ STAGE PLANS:
#### A masked pattern was here ####
Edges:
Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE), Union 3 (CONTAINS)
- Reducer 5 <- Map 4 (CUSTOM_SIMPLE_EDGE), Union 3 (CONTAINS)
- Reducer 7 <- Map 6 (CUSTOM_SIMPLE_EDGE), Union 3 (CONTAINS)
+ Reducer 4 <- Union 3 (CUSTOM_SIMPLE_EDGE)
+ Reducer 6 <- Map 5 (CUSTOM_SIMPLE_EDGE), Union 3 (CONTAINS)
+ Reducer 8 <- Map 7 (CUSTOM_SIMPLE_EDGE), Union 3 (CONTAINS)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -456,7 +457,7 @@ STAGE PLANS:
value expressions: _col0 (type: string)
Execution mode: vectorized, llap
LLAP IO: no inputs
- Map 4
+ Map 5
Map Operator Tree:
TableScan
alias: src
@@ -479,7 +480,7 @@ STAGE PLANS:
value expressions: _col0 (type: string)
Execution mode: vectorized, llap
LLAP IO: no inputs
- Map 6
+ Map 7
Map Operator Tree:
TableScan
alias: src
@@ -503,7 +504,7 @@ STAGE PLANS:
Execution mode: vectorized, llap
LLAP IO: no inputs
Reducer 2
- Execution mode: vectorized, llap
+ Execution mode: llap
Reduce Operator Tree:
Select Operator
expressions: VALUE._col0 (type: string)
@@ -524,8 +525,36 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.union_top
- Reducer 5
- Execution mode: vectorized, llap
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: int)
+ outputColumnNames: col1, col2
+ Statistics: Num rows: 9 Data size: 819 Basic stats: COMPLETE Column stats: COMPLETE
+ Group By Operator
+ aggregations: compute_stats(col1, 'hll'), compute_stats(col2, 'hll')
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col0 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>)
+ Reducer 4
+ Execution mode: llap
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ Reducer 6
+ Execution mode: llap
Reduce Operator Tree:
Select Operator
expressions: VALUE._col0 (type: string)
@@ -546,8 +575,21 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.union_top
- Reducer 7
- Execution mode: vectorized, llap
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: int)
+ outputColumnNames: col1, col2
+ Statistics: Num rows: 9 Data size: 819 Basic stats: COMPLETE Column stats: COMPLETE
+ Group By Operator
+ aggregations: compute_stats(col1, 'hll'), compute_stats(col2, 'hll')
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col0 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>)
+ Reducer 8
+ Execution mode: llap
Reduce Operator Tree:
Select Operator
expressions: VALUE._col0 (type: string)
@@ -568,6 +610,19 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.union_top
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: int)
+ outputColumnNames: col1, col2
+ Statistics: Num rows: 9 Data size: 819 Basic stats: COMPLETE Column stats: COMPLETE
+ Group By Operator
+ aggregations: compute_stats(col1, 'hll'), compute_stats(col2, 'hll')
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col0 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>)
Union 3
Vertex: Union 3
@@ -586,6 +641,10 @@ STAGE PLANS:
Stage: Stage-3
Stats Work
Basic Stats Work:
+ Column Stats Desc:
+ Columns: key, value
+ Column Types: string, int
+ Table: default.union_top
Stage: Stage-0
Move Operator
@@ -694,6 +753,7 @@ STAGE PLANS:
Reduce Output Operator
sort order:
Statistics: Num rows: 3 Data size: 261 Basic stats: COMPLETE Column stats: COMPLETE
+ TopN Hash Memory Usage: 0.1
value expressions: _col0 (type: string)
Execution mode: vectorized, llap
LLAP IO: no inputs
@@ -716,6 +776,7 @@ STAGE PLANS:
Reduce Output Operator
sort order:
Statistics: Num rows: 3 Data size: 261 Basic stats: COMPLETE Column stats: COMPLETE
+ TopN Hash Memory Usage: 0.1
value expressions: _col0 (type: string)
Execution mode: vectorized, llap
LLAP IO: no inputs
@@ -738,6 +799,7 @@ STAGE PLANS:
Reduce Output Operator
sort order:
Statistics: Num rows: 3 Data size: 261 Basic stats: COMPLETE Column stats: COMPLETE
+ TopN Hash Memory Usage: 0.1
value expressions: _col0 (type: string)
Execution mode: vectorized, llap
LLAP IO: no inputs
@@ -978,6 +1040,7 @@ STAGE PLANS:
Reduce Output Operator
sort order:
Statistics: Num rows: 3 Data size: 261 Basic stats: COMPLETE Column stats: COMPLETE
+ TopN Hash Memory Usage: 0.1
value expressions: _col0 (type: string)
Execution mode: vectorized, llap
LLAP IO: no inputs
@@ -1000,6 +1063,7 @@ STAGE PLANS:
Reduce Output Operator
sort order:
Statistics: Num rows: 3 Data size: 261 Basic stats: COMPLETE Column stats: COMPLETE
+ TopN Hash Memory Usage: 0.1
value expressions: _col0 (type: string)
Execution mode: vectorized, llap
LLAP IO: no inputs
@@ -1022,6 +1086,7 @@ STAGE PLANS:
Reduce Output Operator
sort order:
Statistics: Num rows: 3 Data size: 261 Basic stats: COMPLETE Column stats: COMPLETE
+ TopN Hash Memory Usage: 0.1
value expressions: _col0 (type: string)
Execution mode: vectorized, llap
LLAP IO: no inputs
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/llap/vector_between_columns.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/vector_between_columns.q.out b/ql/src/test/results/clientpositive/llap/vector_between_columns.q.out
index fca136b..a91a36b 100644
--- a/ql/src/test/results/clientpositive/llap/vector_between_columns.q.out
+++ b/ql/src/test/results/clientpositive/llap/vector_between_columns.q.out
@@ -116,7 +116,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: tint
- Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
Select Operator
@@ -126,14 +126,14 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1]
- Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
Reduce Sink Vectorization:
className: VectorReduceSinkEmptyKeyOperator
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: int), _col1 (type: int)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -150,7 +150,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: tsint
- Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
Select Operator
@@ -160,14 +160,14 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1, 1]
- Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
Reduce Sink Vectorization:
className: VectorReduceSinkEmptyKeyOperator
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: int), _col1 (type: smallint), _col2 (type: int)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -190,14 +190,14 @@ STAGE PLANS:
0
1
outputColumnNames: _col0, _col1, _col2, _col3, _col4
- Statistics: Num rows: 36 Data size: 612 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 36 Data size: 708 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: int), _col2 (type: int), _col1 (type: int), _col3 (type: smallint), CASE WHEN (_col1 BETWEEN _col4 AND _col4) THEN ('Ok') ELSE ('NoOk') END (type: string)
outputColumnNames: _col0, _col1, _col2, _col3, _col4
- Statistics: Num rows: 36 Data size: 612 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 36 Data size: 7192 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 36 Data size: 612 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 36 Data size: 7192 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -294,7 +294,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: tint
- Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
Select Operator
@@ -304,14 +304,14 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1]
- Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
Reduce Sink Vectorization:
className: VectorReduceSinkEmptyKeyOperator
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: int), _col1 (type: int)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -328,7 +328,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: tsint
- Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
Select Operator
@@ -338,14 +338,14 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1, 1]
- Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
Reduce Sink Vectorization:
className: VectorReduceSinkEmptyKeyOperator
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: int), _col1 (type: smallint), _col2 (type: int)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -368,17 +368,17 @@ STAGE PLANS:
0
1
outputColumnNames: _col0, _col1, _col2, _col3, _col4
- Statistics: Num rows: 36 Data size: 612 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 36 Data size: 708 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: _col1 BETWEEN _col4 AND _col4 (type: boolean)
- Statistics: Num rows: 4 Data size: 68 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4 Data size: 80 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: int), _col2 (type: int), _col1 (type: int), _col3 (type: smallint)
outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 4 Data size: 68 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 4 Data size: 68 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/llap/vector_between_in.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/vector_between_in.q.out b/ql/src/test/results/clientpositive/llap/vector_between_in.q.out
index 1271193..14ec9e2 100644
--- a/ql/src/test/results/clientpositive/llap/vector_between_in.q.out
+++ b/ql/src/test/results/clientpositive/llap/vector_between_in.q.out
@@ -53,7 +53,7 @@ STAGE PLANS:
TableScan
alias: decimal_date_test
filterExpr: (cdate) IN (DATE'1969-10-26', DATE'1969-07-14') (type: boolean)
- Statistics: Num rows: 12289 Data size: 653856 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12289 Data size: 339304 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
Filter Operator
@@ -62,7 +62,7 @@ STAGE PLANS:
native: true
predicateExpression: FilterLongColumnInList(col 3:date, values [-67, -171])
predicate: (cdate) IN (DATE'1969-10-26', DATE'1969-07-14') (type: boolean)
- Statistics: Num rows: 1 Data size: 53 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12289 Data size: 339304 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: cdate (type: date)
outputColumnNames: _col0
@@ -70,7 +70,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [3]
- Statistics: Num rows: 1 Data size: 53 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12289 Data size: 339304 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: date)
sort order: +
@@ -78,7 +78,7 @@ STAGE PLANS:
className: VectorReduceSinkObjectHashOperator
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 1 Data size: 53 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12289 Data size: 339304 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized, llap
LLAP IO: all inputs
Map Vectorization:
@@ -106,13 +106,13 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0]
- Statistics: Num rows: 1 Data size: 53 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12289 Data size: 339304 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 1 Data size: 53 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12289 Data size: 339304 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -153,7 +153,7 @@ STAGE PLANS:
TableScan
alias: decimal_date_test
filterExpr: ((cdate <> DATE'1969-10-26') and (cdate <> DATE'1969-07-14') and (cdate <> DATE'1970-01-21')) (type: boolean)
- Statistics: Num rows: 12289 Data size: 653856 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12289 Data size: 339304 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
Filter Operator
@@ -162,13 +162,13 @@ STAGE PLANS:
native: true
predicateExpression: FilterExprAndExpr(children: FilterDateColNotEqualDateScalar(col 3:date, val -67), FilterDateColNotEqualDateScalar(col 3:date, val -171), FilterDateColNotEqualDateScalar(col 3:date, val 20))
predicate: ((cdate <> DATE'1969-07-14') and (cdate <> DATE'1969-10-26') and (cdate <> DATE'1970-01-21')) (type: boolean)
- Statistics: Num rows: 12289 Data size: 653856 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12289 Data size: 339304 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
Select Vectorization:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: []
- Statistics: Num rows: 12289 Data size: 653856 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12289 Data size: 339304 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count()
Group By Vectorization:
@@ -180,14 +180,14 @@ STAGE PLANS:
projectedOutputColumnNums: [0]
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 64 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
Reduce Sink Vectorization:
className: VectorReduceSinkEmptyKeyOperator
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 1 Data size: 64 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: bigint)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -220,13 +220,13 @@ STAGE PLANS:
projectedOutputColumnNums: [0]
mode: mergepartial
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 64 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 1 Data size: 64 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -267,7 +267,7 @@ STAGE PLANS:
TableScan
alias: decimal_date_test
filterExpr: (cdecimal1) IN (2365.8945945946, 881.0135135135, -3367.6517567568) (type: boolean)
- Statistics: Num rows: 12289 Data size: 1307712 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12289 Data size: 1027600 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
Filter Operator
@@ -276,7 +276,7 @@ STAGE PLANS:
native: true
predicateExpression: FilterDecimalColumnInList(col 1:decimal(20,10), values [2365.8945945946, 881.0135135135, -3367.6517567568])
predicate: (cdecimal1) IN (2365.8945945946, 881.0135135135, -3367.6517567568) (type: boolean)
- Statistics: Num rows: 15 Data size: 1596 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 560 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: cdecimal1 (type: decimal(20,10))
outputColumnNames: _col0
@@ -284,7 +284,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [1]
- Statistics: Num rows: 15 Data size: 1596 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 560 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: decimal(20,10))
sort order: +
@@ -292,7 +292,7 @@ STAGE PLANS:
className: VectorReduceSinkObjectHashOperator
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 15 Data size: 1596 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 560 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized, llap
LLAP IO: all inputs
Map Vectorization:
@@ -320,13 +320,13 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0]
- Statistics: Num rows: 15 Data size: 1596 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 560 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 15 Data size: 1596 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 560 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -367,7 +367,7 @@ STAGE PLANS:
TableScan
alias: decimal_date_test
filterExpr: ((cdecimal1 <> 2365.8945945946) and (cdecimal1 <> 881.0135135135) and (cdecimal1 <> -3367.6517567568)) (type: boolean)
- Statistics: Num rows: 12289 Data size: 1307712 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12289 Data size: 1027600 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
Filter Operator
@@ -376,13 +376,13 @@ STAGE PLANS:
native: true
predicateExpression: FilterExprAndExpr(children: FilterDecimalColNotEqualDecimalScalar(col 1:decimal(20,10), val 2365.8945945946), FilterDecimalColNotEqualDecimalScalar(col 1:decimal(20,10), val 881.0135135135), FilterDecimalColNotEqualDecimalScalar(col 1:decimal(20,10), val -3367.6517567568))
predicate: ((cdecimal1 <> -3367.6517567568) and (cdecimal1 <> 2365.8945945946) and (cdecimal1 <> 881.0135135135)) (type: boolean)
- Statistics: Num rows: 12289 Data size: 1307712 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12289 Data size: 1027600 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
Select Vectorization:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: []
- Statistics: Num rows: 12289 Data size: 1307712 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12289 Data size: 1027600 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count()
Group By Vectorization:
@@ -394,14 +394,14 @@ STAGE PLANS:
projectedOutputColumnNums: [0]
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 120 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
Reduce Sink Vectorization:
className: VectorReduceSinkEmptyKeyOperator
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 1 Data size: 120 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: bigint)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -434,13 +434,13 @@ STAGE PLANS:
projectedOutputColumnNums: [0]
mode: mergepartial
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 120 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 1 Data size: 120 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -481,7 +481,7 @@ STAGE PLANS:
TableScan
alias: decimal_date_test
filterExpr: cdate BETWEEN DATE'1969-12-30' AND DATE'1970-01-02' (type: boolean)
- Statistics: Num rows: 12289 Data size: 653856 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12289 Data size: 339304 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
Filter Operator
@@ -490,7 +490,7 @@ STAGE PLANS:
native: true
predicateExpression: FilterLongColumnBetween(col 3:date, left -2, right 1)
predicate: cdate BETWEEN DATE'1969-12-30' AND DATE'1970-01-02' (type: boolean)
- Statistics: Num rows: 4096 Data size: 217934 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1365 Data size: 37744 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: cdate (type: date)
outputColumnNames: _col0
@@ -498,7 +498,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [3]
- Statistics: Num rows: 4096 Data size: 217934 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1365 Data size: 37744 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: date)
sort order: +
@@ -506,7 +506,7 @@ STAGE PLANS:
className: VectorReduceSinkObjectHashOperator
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 4096 Data size: 217934 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1365 Data size: 37744 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized, llap
LLAP IO: all inputs
Map Vectorization:
@@ -534,13 +534,13 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0]
- Statistics: Num rows: 4096 Data size: 217934 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1365 Data size: 37744 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 4096 Data size: 217934 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1365 Data size: 37744 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -581,7 +581,7 @@ STAGE PLANS:
TableScan
alias: decimal_date_test
filterExpr: cdate NOT BETWEEN DATE'1968-05-01' AND DATE'1971-09-01' (type: boolean)
- Statistics: Num rows: 12289 Data size: 653856 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12289 Data size: 339304 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
Filter Operator
@@ -590,7 +590,7 @@ STAGE PLANS:
native: true
predicateExpression: FilterLongColumnNotBetween(col 3:date, left -610, right 608)
predicate: cdate NOT BETWEEN DATE'1968-05-01' AND DATE'1971-09-01' (type: boolean)
- Statistics: Num rows: 8193 Data size: 435921 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10924 Data size: 301616 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: cdate (type: date)
outputColumnNames: _col0
@@ -598,7 +598,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [3]
- Statistics: Num rows: 8193 Data size: 435921 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10924 Data size: 301616 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: date)
sort order: +
@@ -606,7 +606,7 @@ STAGE PLANS:
className: VectorReduceSinkObjectHashOperator
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 8193 Data size: 435921 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10924 Data size: 301616 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized, llap
LLAP IO: all inputs
Map Vectorization:
@@ -634,13 +634,13 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0]
- Statistics: Num rows: 8193 Data size: 435921 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10924 Data size: 301616 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 8193 Data size: 435921 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10924 Data size: 301616 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -681,7 +681,7 @@ STAGE PLANS:
TableScan
alias: decimal_date_test
filterExpr: cdecimal1 BETWEEN -20 AND 45.9918918919 (type: boolean)
- Statistics: Num rows: 12289 Data size: 1307712 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12289 Data size: 1027600 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
Filter Operator
@@ -690,7 +690,7 @@ STAGE PLANS:
native: true
predicateExpression: FilterDecimalColumnBetween(col 1:decimal(20,10), left -20, right 45.9918918919)
predicate: cdecimal1 BETWEEN -20 AND 45.9918918919 (type: boolean)
- Statistics: Num rows: 1365 Data size: 145254 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1365 Data size: 114240 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: cdecimal1 (type: decimal(20,10))
outputColumnNames: _col0
@@ -698,7 +698,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [1]
- Statistics: Num rows: 1365 Data size: 145254 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1365 Data size: 114240 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: decimal(20,10))
sort order: +
@@ -706,7 +706,7 @@ STAGE PLANS:
className: VectorReduceSinkObjectHashOperator
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 1365 Data size: 145254 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1365 Data size: 114240 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized, llap
LLAP IO: all inputs
Map Vectorization:
@@ -734,13 +734,13 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0]
- Statistics: Num rows: 1365 Data size: 145254 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1365 Data size: 114240 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 1365 Data size: 145254 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1365 Data size: 114240 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -781,7 +781,7 @@ STAGE PLANS:
TableScan
alias: decimal_date_test
filterExpr: cdecimal1 NOT BETWEEN -2000 AND 4390.1351351351 (type: boolean)
- Statistics: Num rows: 12289 Data size: 1307712 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12289 Data size: 1027600 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
Filter Operator
@@ -790,13 +790,13 @@ STAGE PLANS:
native: true
predicateExpression: FilterDecimalColumnNotBetween(col 1:decimal(20,10), left -2000, right 4390.1351351351)
predicate: cdecimal1 NOT BETWEEN -2000 AND 4390.1351351351 (type: boolean)
- Statistics: Num rows: 10924 Data size: 1162457 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10924 Data size: 913472 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
Select Vectorization:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: []
- Statistics: Num rows: 10924 Data size: 1162457 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10924 Data size: 913472 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count()
Group By Vectorization:
@@ -808,14 +808,14 @@ STAGE PLANS:
projectedOutputColumnNums: [0]
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 120 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
Reduce Sink Vectorization:
className: VectorReduceSinkEmptyKeyOperator
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 1 Data size: 120 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: bigint)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -848,13 +848,13 @@ STAGE PLANS:
projectedOutputColumnNums: [0]
mode: mergepartial
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 120 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 1 Data size: 120 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -1140,7 +1140,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: decimal_date_test
- Statistics: Num rows: 12289 Data size: 653856 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12289 Data size: 339304 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
Select Operator
@@ -1151,7 +1151,7 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [5]
selectExpressions: LongColumnInList(col 3, values [-67, -171]) -> 5:boolean
- Statistics: Num rows: 12289 Data size: 653856 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12289 Data size: 339304 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count()
Group By Vectorization:
@@ -1165,7 +1165,7 @@ STAGE PLANS:
keys: _col0 (type: boolean)
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 12289 Data size: 653856 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6144 Data size: 73728 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: boolean)
sort order: +
@@ -1174,7 +1174,7 @@ STAGE PLANS:
className: VectorReduceSinkLongOperator
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 12289 Data size: 653856 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6144 Data size: 73728 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: bigint)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -1209,7 +1209,7 @@ STAGE PLANS:
keys: KEY._col0 (type: boolean)
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 6144 Data size: 326901 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3072 Data size: 36864 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: boolean)
sort order: +
@@ -1217,7 +1217,7 @@ STAGE PLANS:
className: VectorReduceSinkObjectHashOperator
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 6144 Data size: 326901 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3072 Data size: 36864 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: bigint)
Reducer 3
Execution mode: vectorized, llap
@@ -1235,13 +1235,13 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1]
- Statistics: Num rows: 6144 Data size: 326901 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3072 Data size: 36864 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 6144 Data size: 326901 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3072 Data size: 36864 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -1282,7 +1282,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: decimal_date_test
- Statistics: Num rows: 12289 Data size: 1307712 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12289 Data size: 1027600 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
Select Operator
@@ -1293,7 +1293,7 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [5]
selectExpressions: DecimalColumnInList(col 1:decimal(20,10), values [2365.8945945946, 881.0135135135, -3367.6517567568]) -> 5:boolean
- Statistics: Num rows: 12289 Data size: 1307712 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12289 Data size: 1027600 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count()
Group By Vectorization:
@@ -1307,7 +1307,7 @@ STAGE PLANS:
keys: _col0 (type: boolean)
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 12289 Data size: 1307712 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5871 Data size: 70452 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: boolean)
sort order: +
@@ -1316,7 +1316,7 @@ STAGE PLANS:
className: VectorReduceSinkLongOperator
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 12289 Data size: 1307712 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5871 Data size: 70452 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: bigint)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -1351,7 +1351,7 @@ STAGE PLANS:
keys: KEY._col0 (type: boolean)
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 6144 Data size: 653802 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5871 Data size: 70452 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: boolean)
sort order: +
@@ -1359,7 +1359,7 @@ STAGE PLANS:
className: VectorReduceSinkObjectHashOperator
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 6144 Data size: 653802 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5871 Data size: 70452 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: bigint)
Reducer 3
Execution mode: vectorized, llap
@@ -1377,13 +1377,13 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1]
- Statistics: Num rows: 6144 Data size: 653802 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5871 Data size: 70452 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 6144 Data size: 653802 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5871 Data size: 70452 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -1424,7 +1424,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: decimal_date_test
- Statistics: Num rows: 12289 Data size: 653856 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12289 Data size: 339304 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
Select Operator
@@ -1435,7 +1435,7 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [5]
selectExpressions: LongColumnBetween(col 3:date, left -2, right 1) -> 5:boolean
- Statistics: Num rows: 12289 Data size: 653856 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12289 Data size: 339304 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count()
Group By Vectorization:
@@ -1449,7 +1449,7 @@ STAGE PLANS:
keys: _col0 (type: boolean)
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 12289 Data size: 653856 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: boolean)
sort order: +
@@ -1458,7 +1458,7 @@ STAGE PLANS:
className: VectorReduceSinkLongOperator
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 12289 Data size: 653856 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: bigint)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -1493,7 +1493,7 @@ STAGE PLANS:
keys: KEY._col0 (type: boolean)
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 6144 Data size: 326901 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: boolean)
sort order: +
@@ -1501,7 +1501,7 @@ STAGE PLANS:
className: VectorReduceSinkObjectHashOperator
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 6144 Data size: 326901 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: bigint)
Reducer 3
Execution mode: vectorized, llap
@@ -1519,13 +1519,13 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1]
- Statistics: Num rows: 6144 Data size: 326901 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 6144 Data size: 326901 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -1566,7 +1566,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: decimal_date_test
- Statistics: Num rows: 12289 Data size: 1307712 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12289 Data size: 1027600 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
Select Operator
@@ -1577,7 +1577,7 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [5]
selectExpressions: DecimalColumnNotBetween(col 1:decimal(20,10), left -2000, right 4390.1351351351) -> 5:boolean
- Statistics: Num rows: 12289 Data size: 1307712 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12289 Data size: 1027600 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count()
Group By Vectorization:
@@ -1591,7 +1591,7 @@ STAGE PLANS:
keys: _col0 (type: boolean)
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 12289 Data size: 1307712 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: boolean)
sort order: +
@@ -1600,7 +1600,7 @@ STAGE PLANS:
className: VectorReduceSinkLongOperator
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 12289 Data size: 1307712 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: bigint)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -1635,7 +1635,7 @@ STAGE PLANS:
keys: KEY._col0 (type: boolean)
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 6144 Data size: 653802 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: boolean)
sort order: +
@@ -1643,7 +1643,7 @@ STAGE PLANS:
className: VectorReduceSinkObjectHashOperator
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 6144 Data size: 653802 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: bigint)
Reducer 3
Execution mode: vectorized, llap
@@ -1661,13 +1661,13 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1]
- Statistics: Num rows: 6144 Data size: 653802 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 6144 Data size: 653802 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
[07/35] hive git commit: HIVE-16957: Support CTAS for auto gather
column stats (Jesus Camacho Rodriguez, reviewed by Ashutosh Chauhan)
Posted by jc...@apache.org.
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/llap/vector_leftsemi_mapjoin.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/vector_leftsemi_mapjoin.q.out b/ql/src/test/results/clientpositive/llap/vector_leftsemi_mapjoin.q.out
index 31d7074..af585a7 100644
--- a/ql/src/test/results/clientpositive/llap/vector_leftsemi_mapjoin.q.out
+++ b/ql/src/test/results/clientpositive/llap/vector_leftsemi_mapjoin.q.out
@@ -162,10 +162,10 @@ STAGE PLANS:
TableScan
alias: a
filterExpr: key is not null (type: boolean)
- Statistics: Num rows: 11 Data size: 2068 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 1023 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: key is not null (type: boolean)
- Statistics: Num rows: 11 Data size: 2068 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 1023 Basic stats: COMPLETE Column stats: COMPLETE
Map Join Operator
condition map:
Left Semi Join 0 to 1
@@ -175,11 +175,11 @@ STAGE PLANS:
outputColumnNames: _col0, _col1
input vertices:
1 Map 3
- Statistics: Num rows: 12 Data size: 2274 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 7 Data size: 651 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int), _col1 (type: string)
sort order: ++
- Statistics: Num rows: 12 Data size: 2274 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 7 Data size: 651 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: llap
LLAP IO: all inputs
Map 3
@@ -187,24 +187,24 @@ STAGE PLANS:
TableScan
alias: b
filterExpr: key is not null (type: boolean)
- Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: key is not null (type: boolean)
- Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: key (type: int)
outputColumnNames: _col0
- Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
keys: _col0 (type: int)
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: llap
LLAP IO: all inputs
Reducer 2
@@ -213,10 +213,10 @@ STAGE PLANS:
Select Operator
expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 12 Data size: 2274 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 7 Data size: 651 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 12 Data size: 2274 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 7 Data size: 651 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -278,10 +278,10 @@ STAGE PLANS:
TableScan
alias: a
filterExpr: key is not null (type: boolean)
- Statistics: Num rows: 11 Data size: 2068 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 1023 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: key is not null (type: boolean)
- Statistics: Num rows: 11 Data size: 2068 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 1023 Basic stats: COMPLETE Column stats: COMPLETE
Map Join Operator
condition map:
Left Semi Join 0 to 1
@@ -291,11 +291,11 @@ STAGE PLANS:
outputColumnNames: _col0, _col1
input vertices:
1 Map 3
- Statistics: Num rows: 12 Data size: 2274 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 7 Data size: 651 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int), _col1 (type: string)
sort order: ++
- Statistics: Num rows: 12 Data size: 2274 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 7 Data size: 651 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: llap
LLAP IO: all inputs
Map 3
@@ -303,24 +303,24 @@ STAGE PLANS:
TableScan
alias: b
filterExpr: key is not null (type: boolean)
- Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: key is not null (type: boolean)
- Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: key (type: int)
outputColumnNames: _col0
- Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
keys: _col0 (type: int)
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: llap
LLAP IO: all inputs
Reducer 2
@@ -329,10 +329,10 @@ STAGE PLANS:
Select Operator
expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 12 Data size: 2274 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 7 Data size: 651 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 12 Data size: 2274 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 7 Data size: 651 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -396,10 +396,10 @@ STAGE PLANS:
TableScan
alias: a
filterExpr: key is not null (type: boolean)
- Statistics: Num rows: 11 Data size: 2068 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 1023 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: key is not null (type: boolean)
- Statistics: Num rows: 11 Data size: 2068 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 1023 Basic stats: COMPLETE Column stats: COMPLETE
Map Join Operator
condition map:
Left Semi Join 0 to 1
@@ -409,11 +409,11 @@ STAGE PLANS:
outputColumnNames: _col0, _col1
input vertices:
1 Map 3
- Statistics: Num rows: 12 Data size: 2274 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 1125 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: int), _col1 (type: string)
sort order: ++
- Statistics: Num rows: 12 Data size: 2274 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 1125 Basic stats: COMPLETE Column stats: NONE
Execution mode: llap
LLAP IO: all inputs
Map 3
@@ -447,10 +447,10 @@ STAGE PLANS:
Select Operator
expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 12 Data size: 2274 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 1125 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
- Statistics: Num rows: 12 Data size: 2274 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 1125 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -506,10 +506,10 @@ STAGE PLANS:
TableScan
alias: a
filterExpr: key is not null (type: boolean)
- Statistics: Num rows: 11 Data size: 2068 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 1023 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: key is not null (type: boolean)
- Statistics: Num rows: 11 Data size: 2068 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 1023 Basic stats: COMPLETE Column stats: COMPLETE
Map Join Operator
condition map:
Left Semi Join 0 to 1
@@ -519,15 +519,15 @@ STAGE PLANS:
outputColumnNames: _col1
input vertices:
1 Map 3
- Statistics: Num rows: 24 Data size: 96 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col1 (type: string)
outputColumnNames: _col0
- Statistics: Num rows: 24 Data size: 96 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
- Statistics: Num rows: 24 Data size: 96 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: llap
LLAP IO: all inputs
Map 3
@@ -535,24 +535,24 @@ STAGE PLANS:
TableScan
alias: b
filterExpr: (key < 15) (type: boolean)
- Statistics: Num rows: 22 Data size: 88 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 22 Data size: 88 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: (key < 15) (type: boolean)
- Statistics: Num rows: 22 Data size: 88 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: key (type: int)
outputColumnNames: _col1
- Statistics: Num rows: 22 Data size: 88 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 7 Data size: 56 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
keys: _col1 (type: int), _col1 (type: int)
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 22 Data size: 88 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col1 (type: int)
sort order: +
Map-reduce partition columns: _col1 (type: int)
- Statistics: Num rows: 22 Data size: 88 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: llap
LLAP IO: all inputs
Reducer 2
@@ -561,10 +561,10 @@ STAGE PLANS:
Select Operator
expressions: KEY.reducesinkkey0 (type: string)
outputColumnNames: _col0
- Statistics: Num rows: 24 Data size: 96 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 24 Data size: 96 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -631,10 +631,10 @@ STAGE PLANS:
TableScan
alias: a
filterExpr: key is not null (type: boolean)
- Statistics: Num rows: 11 Data size: 2068 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 1023 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: key is not null (type: boolean)
- Statistics: Num rows: 11 Data size: 2068 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 1023 Basic stats: COMPLETE Column stats: COMPLETE
Map Join Operator
condition map:
Left Semi Join 0 to 1
@@ -644,11 +644,11 @@ STAGE PLANS:
outputColumnNames: _col0, _col1
input vertices:
1 Map 3
- Statistics: Num rows: 12 Data size: 2274 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int), _col1 (type: string)
sort order: ++
- Statistics: Num rows: 12 Data size: 2274 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: llap
LLAP IO: all inputs
Map 3
@@ -656,24 +656,24 @@ STAGE PLANS:
TableScan
alias: b
filterExpr: ((value < 'val_10') and key is not null) (type: boolean)
- Statistics: Num rows: 11 Data size: 2068 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 1023 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: ((value < 'val_10') and key is not null) (type: boolean)
- Statistics: Num rows: 3 Data size: 564 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 279 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: key (type: int), value (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 3 Data size: 564 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 279 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
keys: _col0 (type: int), _col1 (type: string)
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 3 Data size: 564 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 3 Data size: 564 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: llap
LLAP IO: all inputs
Reducer 2
@@ -682,10 +682,10 @@ STAGE PLANS:
Select Operator
expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 12 Data size: 2274 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 12 Data size: 2274 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -744,24 +744,24 @@ STAGE PLANS:
TableScan
alias: t3_n35
filterExpr: (key > 5) (type: boolean)
- Statistics: Num rows: 22 Data size: 88 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 22 Data size: 88 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: (key > 5) (type: boolean)
- Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: key (type: int)
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
keys: _col0 (type: int)
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: llap
LLAP IO: all inputs
Map 2
@@ -769,10 +769,10 @@ STAGE PLANS:
TableScan
alias: a
filterExpr: key is not null (type: boolean)
- Statistics: Num rows: 11 Data size: 2068 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 1023 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: key is not null (type: boolean)
- Statistics: Num rows: 11 Data size: 2068 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 1023 Basic stats: COMPLETE Column stats: COMPLETE
Map Join Operator
condition map:
Left Semi Join 0 to 1
@@ -782,15 +782,15 @@ STAGE PLANS:
outputColumnNames: _col1
input vertices:
1 Map 1
- Statistics: Num rows: 12 Data size: 2274 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col1 (type: string)
outputColumnNames: _col0
- Statistics: Num rows: 12 Data size: 2274 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
- Statistics: Num rows: 12 Data size: 2274 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: llap
LLAP IO: all inputs
Reducer 3
@@ -799,10 +799,10 @@ STAGE PLANS:
Select Operator
expressions: KEY.reducesinkkey0 (type: string)
outputColumnNames: _col0
- Statistics: Num rows: 12 Data size: 2274 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 12 Data size: 2274 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -861,24 +861,24 @@ STAGE PLANS:
TableScan
alias: t2_n87
filterExpr: ((key > 5) and (value <= 'val_20')) (type: boolean)
- Statistics: Num rows: 11 Data size: 2068 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 1023 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: ((key > 5) and (value <= 'val_20')) (type: boolean)
- Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: key (type: int), value (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
keys: _col0 (type: int), _col1 (type: string)
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: llap
LLAP IO: all inputs
Map 2
@@ -886,10 +886,10 @@ STAGE PLANS:
TableScan
alias: a
filterExpr: key is not null (type: boolean)
- Statistics: Num rows: 11 Data size: 2068 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 1023 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: key is not null (type: boolean)
- Statistics: Num rows: 11 Data size: 2068 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 1023 Basic stats: COMPLETE Column stats: COMPLETE
Map Join Operator
condition map:
Left Semi Join 0 to 1
@@ -899,15 +899,15 @@ STAGE PLANS:
outputColumnNames: _col1
input vertices:
1 Map 1
- Statistics: Num rows: 12 Data size: 2274 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 89 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col1 (type: string)
outputColumnNames: _col0
- Statistics: Num rows: 12 Data size: 2274 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 89 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
- Statistics: Num rows: 12 Data size: 2274 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 89 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: llap
LLAP IO: all inputs
Reducer 3
@@ -916,10 +916,10 @@ STAGE PLANS:
Select Operator
expressions: KEY.reducesinkkey0 (type: string)
outputColumnNames: _col0
- Statistics: Num rows: 12 Data size: 2274 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 89 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 12 Data size: 2274 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 89 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -975,24 +975,24 @@ STAGE PLANS:
TableScan
alias: t1_n148
filterExpr: (key > 2) (type: boolean)
- Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: (key > 2) (type: boolean)
- Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: key (type: int)
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
keys: _col0 (type: int)
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: llap
LLAP IO: all inputs
Map 2
@@ -1000,10 +1000,10 @@ STAGE PLANS:
TableScan
alias: a
filterExpr: key is not null (type: boolean)
- Statistics: Num rows: 11 Data size: 2068 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 1023 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: key is not null (type: boolean)
- Statistics: Num rows: 11 Data size: 2068 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 1023 Basic stats: COMPLETE Column stats: COMPLETE
Map Join Operator
condition map:
Left Semi Join 0 to 1
@@ -1013,11 +1013,11 @@ STAGE PLANS:
outputColumnNames: _col0, _col1
input vertices:
1 Map 1
- Statistics: Num rows: 12 Data size: 2274 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int), _col1 (type: string)
sort order: ++
- Statistics: Num rows: 12 Data size: 2274 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: llap
LLAP IO: all inputs
Reducer 3
@@ -1026,10 +1026,10 @@ STAGE PLANS:
Select Operator
expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 12 Data size: 2274 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 12 Data size: 2274 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -1090,10 +1090,10 @@ STAGE PLANS:
TableScan
alias: a
filterExpr: key is not null (type: boolean)
- Statistics: Num rows: 22 Data size: 88 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 22 Data size: 88 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: key is not null (type: boolean)
- Statistics: Num rows: 21 Data size: 84 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 22 Data size: 88 Basic stats: COMPLETE Column stats: COMPLETE
Map Join Operator
condition map:
Left Semi Join 0 to 1
@@ -1103,11 +1103,11 @@ STAGE PLANS:
outputColumnNames: _col0
input vertices:
1 Map 3
- Statistics: Num rows: 23 Data size: 92 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
- Statistics: Num rows: 23 Data size: 92 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: llap
LLAP IO: all inputs
Map 3
@@ -1115,24 +1115,24 @@ STAGE PLANS:
TableScan
alias: b
filterExpr: key is not null (type: boolean)
- Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: key is not null (type: boolean)
- Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: key (type: int)
outputColumnNames: _col0
- Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
keys: _col0 (type: int)
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: llap
LLAP IO: all inputs
Reducer 2
@@ -1141,10 +1141,10 @@ STAGE PLANS:
Select Operator
expressions: KEY.reducesinkkey0 (type: int)
outputColumnNames: _col0
- Statistics: Num rows: 23 Data size: 92 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 23 Data size: 92 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -1219,10 +1219,10 @@ STAGE PLANS:
TableScan
alias: a
filterExpr: key is not null (type: boolean)
- Statistics: Num rows: 11 Data size: 2068 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 1023 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: key is not null (type: boolean)
- Statistics: Num rows: 11 Data size: 2068 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 1023 Basic stats: COMPLETE Column stats: COMPLETE
Map Join Operator
condition map:
Left Semi Join 0 to 1
@@ -1232,11 +1232,11 @@ STAGE PLANS:
outputColumnNames: _col0, _col1
input vertices:
1 Map 3
- Statistics: Num rows: 12 Data size: 2274 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 7 Data size: 651 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int), _col1 (type: string)
sort order: ++
- Statistics: Num rows: 12 Data size: 2274 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 7 Data size: 651 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: llap
LLAP IO: all inputs
Map 3
@@ -1244,24 +1244,24 @@ STAGE PLANS:
TableScan
alias: b
filterExpr: (2 * key) is not null (type: boolean)
- Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: (2 * key) is not null (type: boolean)
- Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: key (type: int)
outputColumnNames: _col0
- Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
keys: _col0 (type: int)
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: (2 * _col0) (type: int)
sort order: +
Map-reduce partition columns: (2 * _col0) (type: int)
- Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: llap
LLAP IO: all inputs
Reducer 2
@@ -1270,10 +1270,10 @@ STAGE PLANS:
Select Operator
expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 12 Data size: 2274 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 7 Data size: 651 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 12 Data size: 2274 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 7 Data size: 651 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -1335,10 +1335,10 @@ STAGE PLANS:
TableScan
alias: a
filterExpr: key is not null (type: boolean)
- Statistics: Num rows: 11 Data size: 2068 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 1023 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: key is not null (type: boolean)
- Statistics: Num rows: 11 Data size: 2068 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 1023 Basic stats: COMPLETE Column stats: COMPLETE
Map Join Operator
condition map:
Inner Join 0 to 1
@@ -1348,7 +1348,7 @@ STAGE PLANS:
outputColumnNames: _col0, _col1, _col5, _col6
input vertices:
1 Map 3
- Statistics: Num rows: 12 Data size: 2274 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 17 Data size: 3162 Basic stats: COMPLETE Column stats: COMPLETE
Map Join Operator
condition map:
Left Semi Join 0 to 1
@@ -1358,15 +1358,15 @@ STAGE PLANS:
outputColumnNames: _col0, _col1, _col5, _col6
input vertices:
1 Map 4
- Statistics: Num rows: 23 Data size: 92 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 17 Data size: 3162 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: int), _col1 (type: string), _col5 (type: int), _col6 (type: string)
outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 23 Data size: 92 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 17 Data size: 3162 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int), _col1 (type: string)
sort order: ++
- Statistics: Num rows: 23 Data size: 92 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 17 Data size: 3162 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col2 (type: int), _col3 (type: string)
Execution mode: llap
LLAP IO: all inputs
@@ -1375,15 +1375,15 @@ STAGE PLANS:
TableScan
alias: b
filterExpr: key is not null (type: boolean)
- Statistics: Num rows: 11 Data size: 2068 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 1023 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: key is not null (type: boolean)
- Statistics: Num rows: 11 Data size: 2068 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 1023 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: key (type: int)
sort order: +
Map-reduce partition columns: key (type: int)
- Statistics: Num rows: 11 Data size: 2068 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 1023 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: value (type: string)
Execution mode: llap
LLAP IO: all inputs
@@ -1392,24 +1392,24 @@ STAGE PLANS:
TableScan
alias: c
filterExpr: key is not null (type: boolean)
- Statistics: Num rows: 22 Data size: 88 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 22 Data size: 88 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: key is not null (type: boolean)
- Statistics: Num rows: 21 Data size: 84 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 22 Data size: 88 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: key (type: int)
outputColumnNames: _col0
- Statistics: Num rows: 21 Data size: 84 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 22 Data size: 88 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
keys: _col0 (type: int)
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 21 Data size: 84 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 21 Data size: 84 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: llap
LLAP IO: all inputs
Reducer 2
@@ -1418,10 +1418,10 @@ STAGE PLANS:
Select Operator
expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: string), VALUE._col0 (type: int), VALUE._col1 (type: string)
outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 23 Data size: 92 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 17 Data size: 3162 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 23 Data size: 92 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 17 Data size: 3162 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -1493,10 +1493,10 @@ STAGE PLANS:
TableScan
alias: a
filterExpr: (key is not null and value is not null) (type: boolean)
- Statistics: Num rows: 22 Data size: 4136 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 22 Data size: 2046 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: (key is not null and value is not null) (type: boolean)
- Statistics: Num rows: 20 Data size: 3760 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 22 Data size: 2046 Basic stats: COMPLETE Column stats: COMPLETE
Map Join Operator
condition map:
Left Semi Join 0 to 1
@@ -1506,11 +1506,11 @@ STAGE PLANS:
outputColumnNames: _col0, _col1
input vertices:
1 Map 3
- Statistics: Num rows: 22 Data size: 4136 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 1023 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int), _col1 (type: string)
sort order: ++
- Statistics: Num rows: 22 Data size: 4136 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 1023 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: llap
LLAP IO: all inputs
Map 3
@@ -1518,24 +1518,24 @@ STAGE PLANS:
TableScan
alias: b
filterExpr: (key is not null and value is not null) (type: boolean)
- Statistics: Num rows: 11 Data size: 2068 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 1023 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: (key is not null and value is not null) (type: boolean)
- Statistics: Num rows: 11 Data size: 2068 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 1023 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: key (type: int), value (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 11 Data size: 2068 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 1023 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
keys: _col0 (type: int), _col1 (type: string)
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 11 Data size: 2068 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 465 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int), _col1 (type: string)
sort order: ++
Map-reduce partition columns: _col0 (type: int), _col1 (type: string)
- Statistics: Num rows: 11 Data size: 2068 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 465 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: llap
LLAP IO: all inputs
Reducer 2
@@ -1544,10 +1544,10 @@ STAGE PLANS:
Select Operator
expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 22 Data size: 4136 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 1023 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 22 Data size: 4136 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 1023 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -1619,10 +1619,10 @@ STAGE PLANS:
TableScan
alias: a
filterExpr: key is not null (type: boolean)
- Statistics: Num rows: 22 Data size: 88 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 22 Data size: 88 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: key is not null (type: boolean)
- Statistics: Num rows: 21 Data size: 84 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 22 Data size: 88 Basic stats: COMPLETE Column stats: COMPLETE
Map Join Operator
condition map:
Left Semi Join 0 to 1
@@ -1632,7 +1632,7 @@ STAGE PLANS:
outputColumnNames: _col0
input vertices:
1 Map 3
- Statistics: Num rows: 23 Data size: 92 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
Map Join Operator
condition map:
Left Semi Join 0 to 1
@@ -1642,11 +1642,11 @@ STAGE PLANS:
outputColumnNames: _col0
input vertices:
1 Map 4
- Statistics: Num rows: 25 Data size: 101 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
- Statistics: Num rows: 25 Data size: 101 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: llap
LLAP IO: all inputs
Map 3
@@ -1654,24 +1654,24 @@ STAGE PLANS:
TableScan
alias: b
filterExpr: key is not null (type: boolean)
- Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: key is not null (type: boolean)
- Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: key (type: int)
outputColumnNames: _col0
- Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
keys: _col0 (type: int)
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: llap
LLAP IO: all inputs
Map 4
@@ -1679,24 +1679,24 @@ STAGE PLANS:
TableScan
alias: c
filterExpr: key is not null (type: boolean)
- Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: key is not null (type: boolean)
- Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: key (type: int)
outputColumnNames: _col0
- Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
keys: _col0 (type: int)
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: llap
LLAP IO: all inputs
Reducer 2
@@ -1705,10 +1705,10 @@ STAGE PLANS:
Select Operator
expressions: KEY.reducesinkkey0 (type: int)
outputColumnNames: _col0
- Statistics: Num rows: 25 Data size: 101 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 25 Data size: 101 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -1781,7 +1781,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: a
- Statistics: Num rows: 22 Data size: 88 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 22 Data size: 88 Basic stats: COMPLETE Column stats: COMPLETE
Map Join Operator
condition map:
Left Outer Join 0 to 1
@@ -1791,10 +1791,10 @@ STAGE PLANS:
outputColumnNames: _col0, _col5
input vertices:
1 Map 3
- Statistics: Num rows: 24 Data size: 96 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 46 Data size: 284 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: _col5 is not null (type: boolean)
- Statistics: Num rows: 24 Data size: 96 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 24 Data size: 152 Basic stats: COMPLETE Column stats: COMPLETE
Map Join Operator
condition map:
Left Semi Join 0 to 1
@@ -1804,23 +1804,23 @@ STAGE PLANS:
outputColumnNames: _col0
input vertices:
1 Map 4
- Statistics: Num rows: 26 Data size: 105 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 24 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
- Statistics: Num rows: 26 Data size: 105 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 24 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: llap
LLAP IO: all inputs
Map 3
Map Operator Tree:
TableScan
alias: b
- Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: key (type: int)
sort order: +
Map-reduce partition columns: key (type: int)
- Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: llap
LLAP IO: all inputs
Map 4
@@ -1828,24 +1828,24 @@ STAGE PLANS:
TableScan
alias: c
filterExpr: key is not null (type: boolean)
- Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: key is not null (type: boolean)
- Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: key (type: int)
outputColumnNames: _col0
- Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
keys: _col0 (type: int)
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: llap
LLAP IO: all inputs
Reducer 2
@@ -1854,10 +1854,10 @@ STAGE PLANS:
Select Operator
expressions: KEY.reducesinkkey0 (type: int)
outputColumnNames: _col0
- Statistics: Num rows: 26 Data size: 105 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 24 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 26 Data size: 105 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 24 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -1942,24 +1942,24 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: a
- Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: key (type: int)
sort order: +
Map-reduce partition columns: key (type: int)
- Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: llap
LLAP IO: all inputs
Map 4
Map Operator Tree:
TableScan
alias: b
- Statistics: Num rows: 22 Data size: 88 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 22 Data size: 88 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: key (type: int)
sort order: +
Map-reduce partition columns: key (type: int)
- Statistics: Num rows: 22 Data size: 88 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 22 Data size: 88 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: llap
LLAP IO: all inputs
Map 5
@@ -1967,24 +1967,24 @@ STAGE PLANS:
TableScan
alias: c
filterExpr: key is not null (type: boolean)
- Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: key is not null (type: boolean)
- Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: key (type: int)
outputColumnNames: _col0
- Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
keys: _col0 (type: int)
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: llap
LLAP IO: all inputs
Reducer 2
@@ -1997,10 +1997,10 @@ STAGE PLANS:
0 key (type: int)
1 key (type: int)
outputColumnNames: _col0, _col5
- Statistics: Num rows: 24 Data size: 96 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 57 Data size: 200 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: _col5 is not null (type: boolean)
- Statistics: Num rows: 24 Data size: 96 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 24 Data size: 88 Basic stats: COMPLETE Column stats: COMPLETE
Map Join Operator
condition map:
Left Semi Join 0 to 1
@@ -2010,21 +2010,21 @@ STAGE PLANS:
outputColumnNames: _col0
input vertices:
1 Map 5
- Statistics: Num rows: 26 Data size: 105 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 24 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
- Statistics: Num rows: 26 Data size: 105 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 24 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
Reducer 3
Execution mode: llap
Reduce Operator Tree:
Select Operator
expressions: KEY.reducesinkkey0 (type: int)
outputColumnNames: _col0
- Statistics: Num rows: 26 Data size: 105 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 24 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 26 Data size: 105 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 24 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -2112,24 +2112,24 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: a
- Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: key (type: int)
sort order: +
Map-reduce partition columns: key (type: int)
- Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: llap
LLAP IO: all inputs
Map 4
Map Operator Tree:
TableScan
alias: b
- Statistics: Num rows: 22 Data size: 88 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 22 Data size: 88 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: key (type: int)
sort order: +
Map-reduce partition columns: key (type: int)
- Statistics: Num rows: 22 Data size: 88 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 22 Data size: 88 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: llap
LLAP IO: all inputs
Map 5
@@ -2137,24 +2137,24 @@ STAGE PLANS:
TableScan
alias: c
filterExpr: key is not null (type: boolean)
- Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: key is not null (type: boolean)
- Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: key (type: int)
outputColumnNames: _col0
- Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
keys: _col0 (type: int)
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: llap
LLAP IO: all inputs
Reducer 2
@@ -2167,10 +2167,10 @@ STAGE PLANS:
0 key (type: int)
1 key (type: int)
outputColumnNames: _col0, _col5
- Statistics: Num rows: 24 Data size: 96 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 57 Data size: 200 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: _col5 is not null (type: boolean)
- Statistics: Num rows: 24 Data size: 96 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 24 Data size: 88 Basic stats: COMPLETE Column stats: COMPLETE
Map Join Operator
condition map:
Left Semi Join 0 to 1
@@ -2180,21 +2180,21 @@ STAGE PLANS:
outputColumnNames: _col0
input vertices:
1 Map 5
- Statistics: Num rows: 26 Data size: 105 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 24 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
- Statistics: Num rows: 26 Data size: 105 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 24 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
Reducer 3
Execution mode: llap
Reduce Operator Tree:
Select Operator
expressions: KEY.reducesinkkey0 (type: int)
outputColumnNames: _col0
- Statistics: Num rows: 26 Data size: 105 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 24 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 26 Data size: 105 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 24 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -2282,45 +2282,45 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: a
- Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: key (type: int)
sort order: +
Map-reduce partition columns: key (type: int)
- Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: llap
LLAP IO: all inputs
Map 4
Map Operator Tree:
TableScan
alias: b
- Statistics: Num rows: 22 Data size: 88 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 22 Data size: 88 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: key (type: int)
sort order: +
Map-reduce partition columns: key (type: int)
- Statistics: Num rows: 22 Data size: 88 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 22 Data size: 88 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: llap
LLAP IO: all inputs
Map 5
Map Operator Tree:
TableScan
alias: c
- Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: key (type: int)
outputColumnNames: _col0
- Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
keys: _col0 (type: int)
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: llap
LLAP IO: all inputs
Reducer 2
@@ -2335,21 +2335,21 @@ STAGE PLANS:
1 key (type: int)
2 _col0 (type: int)
outputColumnNames: _col0
- Statistics: Num rows: 48 Data size: 193 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 17 Data size: 68 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
- Statistics: Num rows: 48 Data size: 193 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 17 Data size: 68 Basic stats: COMPLETE Column stats: COMPLETE
Reducer 3
Execution mode: llap
Reduce Operator Tree:
Select Operator
expressions: KEY.reducesinkkey0 (type: int)
outputColumnNames: _col0
- Statistics: Num rows: 48 Data size: 193 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 17 Data size: 68 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 48 Data size: 193 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 17 Data size: 68 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -2438,10 +2438,10 @@ STAGE PLANS:
TableScan
alias: a
filterExpr: key is not null (type: boolean)
- Statistics: Num rows: 22 Data size: 88 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 22 Data size: 88 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: key is not null (type: boolean)
- Statistics: Num rows: 21 Data size: 84 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 22 Data size: 88 Basic stats: COMPLETE Column stats: COMPLETE
Map Join Operator
condition map:
Left Semi Join 0 to 1
@@ -2451,7 +2451,7 @@ STAGE PLANS:
outputColumnNames: _col0
input vertices:
1 Map 3
- Statistics: Num rows: 23 Data size: 92 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
Map Join Operator
condition map:
Left Outer Join 0 to 1
@@ -2461,11 +2461,11 @@ STAGE PLANS:
outputColumnNames: _col0
input vertices:
1 Map 4
- Statistics: Num rows: 25 Data size: 101 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 28 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
- Statistics: Num rows: 25 Data size: 101 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 28 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: llap
LLAP IO: all inputs
Map 3
@@ -2473,36 +2473,36 @@ STAGE PLANS:
TableScan
alias: b
filterExpr: key is not null (type: boolean)
- Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: key is not null (type: boolean)
- Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: key (type: int)
outputColumnNames: _col0
- Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
keys: _col0 (type: int)
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: llap
LLAP IO: all inputs
Map 4
Map Operator Tree:
TableScan
alias: c
- Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: key (type: int)
sort order: +
Map-reduce partition columns: key (type: int)
- Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size
<TRUNCATED>
[28/35] hive git commit: HIVE-16957: Support CTAS for auto gather
column stats (Jesus Camacho Rodriguez, reviewed by Ashutosh Chauhan)
Posted by jc...@apache.org.
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/llap/llap_acid2.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/llap_acid2.q.out b/ql/src/test/results/clientpositive/llap/llap_acid2.q.out
index c3e9c2a..eaae3e8 100644
--- a/ql/src/test/results/clientpositive/llap/llap_acid2.q.out
+++ b/ql/src/test/results/clientpositive/llap/llap_acid2.q.out
@@ -49,7 +49,10 @@ select cint, cbigint, cfloat, cdouble,
cint as c1, cbigint as c2, cfloat as c3, cdouble as c4,
cint as c8, cbigint as c7, cfloat as c6, cdouble as c5,
cstring1, cfloat as c9, cast("1.123" as decimal(10,3))as c10,
- cast("1.123456789" as decimal(38,18)) as c11 from alltypesorc order by cdouble asc limit 30
+ cast("1.123456789" as decimal(38,18)) as c11
+from alltypesorc
+order by cint, cbigint, cfloat, cdouble, cstring1
+limit 30
PREHOOK: type: QUERY
PREHOOK: Input: default@alltypesorc
PREHOOK: Output: default@orc_llap_n2
@@ -58,7 +61,10 @@ select cint, cbigint, cfloat, cdouble,
cint as c1, cbigint as c2, cfloat as c3, cdouble as c4,
cint as c8, cbigint as c7, cfloat as c6, cdouble as c5,
cstring1, cfloat as c9, cast("1.123" as decimal(10,3))as c10,
- cast("1.123456789" as decimal(38,18)) as c11 from alltypesorc order by cdouble asc limit 30
+ cast("1.123456789" as decimal(38,18)) as c11
+from alltypesorc
+order by cint, cbigint, cfloat, cdouble, cstring1
+limit 30
POSTHOOK: type: QUERY
POSTHOOK: Input: default@alltypesorc
POSTHOOK: Output: default@orc_llap_n2
@@ -91,7 +97,10 @@ select cint, cbigint, cfloat, cdouble,
cint as c1, cbigint as c2, cfloat as c3, cdouble as c4,
cint as c8, cbigint as c7, cfloat as c6, cdouble as c5,
cstring1, cfloat as c9, cast("3.321" as decimal(10,3))as c10,
- cast("9.987654321" as decimal(38,18)) as c11 from alltypesorc order by cdouble asc limit 30
+ cast("9.987654321" as decimal(38,18)) as c11
+from alltypesorc
+order by cint, cbigint, cfloat, cdouble, cstring1
+limit 30
PREHOOK: type: QUERY
PREHOOK: Input: default@alltypesorc
PREHOOK: Output: default@orc_llap_n2
@@ -100,7 +109,10 @@ select cint, cbigint, cfloat, cdouble,
cint as c1, cbigint as c2, cfloat as c3, cdouble as c4,
cint as c8, cbigint as c7, cfloat as c6, cdouble as c5,
cstring1, cfloat as c9, cast("3.321" as decimal(10,3))as c10,
- cast("9.987654321" as decimal(38,18)) as c11 from alltypesorc order by cdouble asc limit 30
+ cast("9.987654321" as decimal(38,18)) as c11
+from alltypesorc
+order by cint, cbigint, cfloat, cdouble, cstring1
+limit 30
POSTHOOK: type: QUERY
POSTHOOK: Input: default@alltypesorc
POSTHOOK: Output: default@orc_llap_n2
@@ -167,7 +179,10 @@ select cint, cbigint, cfloat, cdouble,
cint as c1, cbigint as c2, cfloat as c3, cdouble as c4,
cint as c8, cbigint as c7, cfloat as c6, cdouble as c5,
cstring1, cfloat as c9, cast("1.123" as decimal(10,3))as c10,
- cast("1.123456789" as decimal(38,18)) as c11 from alltypesorc order by cdouble asc limit 30
+ cast("1.123456789" as decimal(38,18)) as c11
+from alltypesorc
+order by cint, cbigint, cfloat, cdouble, cstring1
+limit 30
PREHOOK: type: QUERY
PREHOOK: Input: default@alltypesorc
PREHOOK: Output: default@orc_llap2
@@ -176,7 +191,10 @@ select cint, cbigint, cfloat, cdouble,
cint as c1, cbigint as c2, cfloat as c3, cdouble as c4,
cint as c8, cbigint as c7, cfloat as c6, cdouble as c5,
cstring1, cfloat as c9, cast("1.123" as decimal(10,3))as c10,
- cast("1.123456789" as decimal(38,18)) as c11 from alltypesorc order by cdouble asc limit 30
+ cast("1.123456789" as decimal(38,18)) as c11
+from alltypesorc
+order by cint, cbigint, cfloat, cdouble, cstring1
+limit 30
POSTHOOK: type: QUERY
POSTHOOK: Input: default@alltypesorc
POSTHOOK: Output: default@orc_llap2
@@ -222,66 +240,66 @@ POSTHOOK: query: select cstring1 from orc_llap_n2
POSTHOOK: type: QUERY
POSTHOOK: Input: default@orc_llap_n2
#### A masked pattern was here ####
-N016jPED08o
-Q1JAdUlCVORmR0Q5X5Vf5u6
-eNsh5tYa
-5j7GJ8OCXgMVIcK7
-uJGHsW3cd073NGFITyQ
-G1u0pUmU6ehCm
-mk6lShdOa8kXT8i7mLd3fK
-u5C7glqT5XqtO0JE2686lk1
-h4omSc1jcLLwW
-tFY2ng51v
-vmAT10eeE47fgH20pLi
-uN803aW
-qqbDw46IgGds4
-32v414p63Jv1B4tO1xy
-73xdw4X
-d3o1712a03n20qvi62U7
-eQ80MW0h728I204P87YXc
-KHtD2A2hp6OjFgS73gdgE
-nI30tm7U55O0gI
-LSJtFA66
-mby00c
-meGb5
-pM6Gt05s1YJeii
-LR2AKy0dPt8vFdIV5760jriw
-1B3WMD5LSk65B2Moa
-xTlDv24JYv4s
-28Oe6r21yux7Lk47
-7wH3hBKdO55Xq3gEEe0
-5QLs0LVK1g
-ET3d4F2I4lV
-N016jPED08o
-Q1JAdUlCVORmR0Q5X5Vf5u6
-eNsh5tYa
-5j7GJ8OCXgMVIcK7
-uJGHsW3cd073NGFITyQ
-G1u0pUmU6ehCm
-mk6lShdOa8kXT8i7mLd3fK
-u5C7glqT5XqtO0JE2686lk1
-h4omSc1jcLLwW
-tFY2ng51v
-vmAT10eeE47fgH20pLi
-uN803aW
-qqbDw46IgGds4
-32v414p63Jv1B4tO1xy
-73xdw4X
-d3o1712a03n20qvi62U7
-eQ80MW0h728I204P87YXc
-KHtD2A2hp6OjFgS73gdgE
-nI30tm7U55O0gI
-LSJtFA66
-mby00c
-meGb5
-pM6Gt05s1YJeii
-LR2AKy0dPt8vFdIV5760jriw
-1B3WMD5LSk65B2Moa
-xTlDv24JYv4s
-28Oe6r21yux7Lk47
-7wH3hBKdO55Xq3gEEe0
-5QLs0LVK1g
-ET3d4F2I4lV
+0RrH6XDA1
+0RrH6XDA1
+0iqrc5
+0iqrc5
+0ruyd6Y50JpdGRf6HqD
+0ruyd6Y50JpdGRf6HqD
+2W4Kg220OcCy065HG60k6e
+2W4Kg220OcCy065HG60k6e
+2uLyD28144vklju213J1mr
+2uLyD28144vklju213J1mr
+41A0nYX72UOSfxO4053xy
+41A0nYX72UOSfxO4053xy
+47INeW44yvsne46Mu
+47INeW44yvsne46Mu
+8GIqX3tvNqrgH
+8GIqX3tvNqrgH
+8u8tR858jC01y8Ft66nYRnb6
+8u8tR858jC01y8Ft66nYRnb6
+8x6mobxQl6Ef0Hl1
+8x6mobxQl6Ef0Hl1
+A34p7oRr2WvUJNf
+A34p7oRr2WvUJNf
+Anj0oF
+Anj0oF
+B553840U1H2b1M06l6N81
+B553840U1H2b1M06l6N81
+F3u1yJaQywofxCCM4v4jScY
+F3u1yJaQywofxCCM4v4jScY
+HBtg2r6pR16VC73
+HBtg2r6pR16VC73
+IbgbUvP5
+IbgbUvP5
+PUn1YVC
+PUn1YVC
+aD88uS2N8DmqPlvjOa7F46i7
+aD88uS2N8DmqPlvjOa7F46i7
+aY3tpnr6wfvmWMG0U881
+aY3tpnr6wfvmWMG0U881
+aw724t8c5558x2xneC624
+aw724t8c5558x2xneC624
+dPbX4jd1v47r1bB6506si
+dPbX4jd1v47r1bB6506si
+dPkN74F7
+dPkN74F7
+iUR3Q
+iUR3Q
+jWVP6gOkq12mdh
+jWVP6gOkq12mdh
+k17Am8uPHWk02cEf1jet
+k17Am8uPHWk02cEf1jet
+k7i5RkMq88H0s
+k7i5RkMq88H0s
+oj1YrV5Wa
+oj1YrV5Wa
+s5O357fO5pF0
+s5O357fO5pF0
+us1gH35lcpND
+us1gH35lcpND
+vW36C22KS75R
+vW36C22KS75R
PREHOOK: query: select cfloat2, cint from orc_llap_n2
PREHOOK: type: QUERY
PREHOOK: Input: default@orc_llap_n2
@@ -290,66 +308,66 @@ POSTHOOK: query: select cfloat2, cint from orc_llap_n2
POSTHOOK: type: QUERY
POSTHOOK: Input: default@orc_llap_n2
#### A masked pattern was here ####
-NULL -838810013
-NULL 246423894
-NULL 708885482
-NULL 186967185
-NULL -595277064
-NULL 584923170
-NULL 518213127
-NULL -334595454
-NULL 241008004
-NULL 185212032
-NULL -738747840
-NULL -971543377
-NULL 940448896
-NULL -324030556
-NULL -899422227
-11.0 835111400
-11.0 -775326158
-11.0 653630202
-11.0 779427499
-11.0 797003983
-11.0 31832752
-11.0 783790031
-11.0 -898241885
-11.0 NULL
-11.0 -646295381
-11.0 130912195
-11.0 -391573084
-11.0 385623629
-11.0 681126962
-11.0 25892751
-NULL -838810013
-NULL 246423894
-NULL 708885482
-NULL 186967185
-NULL -595277064
-NULL 584923170
-NULL 518213127
-NULL -334595454
-NULL 241008004
-NULL 185212032
-NULL -738747840
-NULL -971543377
-NULL 940448896
-NULL -324030556
-NULL -899422227
-11.0 835111400
-11.0 -775326158
-11.0 653630202
-11.0 779427499
-11.0 797003983
-11.0 31832752
-11.0 783790031
-11.0 -898241885
-11.0 NULL
-11.0 -646295381
-11.0 130912195
-11.0 -391573084
-11.0 385623629
-11.0 681126962
-11.0 25892751
+-51.0 -1064718136
+-51.0 -1064718136
+-51.0 -1064981602
+-51.0 -1064981602
+-51.0 -1065775394
+-51.0 -1065775394
+-51.0 -1066684273
+-51.0 -1066684273
+-51.0 -1067683781
+-51.0 -1067683781
+-51.0 -1071480828
+-51.0 -1071480828
+11.0 -1064623720
+11.0 -1064623720
+11.0 -1067874703
+11.0 -1067874703
+11.0 -1068336533
+11.0 -1068336533
+11.0 -1069097390
+11.0 -1069097390
+11.0 -1069103950
+11.0 -1069103950
+11.0 -1069736047
+11.0 -1069736047
+11.0 -1072910839
+11.0 -1072910839
+11.0 -1073279343
+11.0 -1073279343
+8.0 -1068206466
+8.0 -1068206466
+8.0 -1068247011
+8.0 -1068247011
+8.0 -1071363017
+8.0 -1071363017
+NULL -1064949302
+NULL -1064949302
+NULL -1065117869
+NULL -1065117869
+NULL -1066226047
+NULL -1066226047
+NULL -1066922682
+NULL -1066922682
+NULL -1067386090
+NULL -1067386090
+NULL -1068623584
+NULL -1068623584
+NULL -1069109166
+NULL -1069109166
+NULL -1069512165
+NULL -1069512165
+NULL -1070551679
+NULL -1070551679
+NULL -1070883071
+NULL -1070883071
+NULL -1072076362
+NULL -1072076362
+NULL -1072081801
+NULL -1072081801
+NULL -1073051226
+NULL -1073051226
PREHOOK: query: select * from orc_llap_n2
PREHOOK: type: QUERY
PREHOOK: Input: default@orc_llap_n2
@@ -358,66 +376,66 @@ POSTHOOK: query: select * from orc_llap_n2
POSTHOOK: type: QUERY
POSTHOOK: Input: default@orc_llap_n2
#### A masked pattern was here ####
--838810013 1864027286 NULL NULL -838810013 1864027286 NULL NULL -838810013 1864027286 NULL NULL N016jPED08o NULL 3.321 9.9876543210
-246423894 -1645852809 NULL NULL 246423894 -1645852809 NULL NULL 246423894 -1645852809 NULL NULL Q1JAdUlCVORmR0Q5X5Vf5u6 NULL 3.321 9.9876543210
-708885482 -1645852809 NULL NULL 708885482 -1645852809 NULL NULL 708885482 -1645852809 NULL NULL eNsh5tYa NULL 3.321 9.9876543210
-186967185 -1645852809 NULL NULL 186967185 -1645852809 NULL NULL 186967185 -1645852809 NULL NULL 5j7GJ8OCXgMVIcK7 NULL 3.321 9.9876543210
--595277064 -1645852809 NULL NULL -595277064 -1645852809 NULL NULL -595277064 -1645852809 NULL NULL uJGHsW3cd073NGFITyQ NULL 3.321 9.9876543210
-584923170 -1645852809 NULL NULL 584923170 -1645852809 NULL NULL 584923170 -1645852809 NULL NULL G1u0pUmU6ehCm NULL 3.321 9.9876543210
-518213127 -1645852809 NULL NULL 518213127 -1645852809 NULL NULL 518213127 -1645852809 NULL NULL mk6lShdOa8kXT8i7mLd3fK NULL 3.321 9.9876543210
--334595454 -1645852809 NULL NULL -334595454 -1645852809 NULL NULL -334595454 -1645852809 NULL NULL u5C7glqT5XqtO0JE2686lk1 NULL 3.321 9.9876543210
-241008004 -1645852809 NULL NULL 241008004 -1645852809 NULL NULL 241008004 -1645852809 NULL NULL h4omSc1jcLLwW NULL 3.321 9.9876543210
-185212032 -1645852809 NULL NULL 185212032 -1645852809 NULL NULL 185212032 -1645852809 NULL NULL tFY2ng51v NULL 3.321 9.9876543210
--738747840 -1645852809 NULL NULL -738747840 -1645852809 NULL NULL -738747840 -1645852809 NULL NULL vmAT10eeE47fgH20pLi NULL 3.321 9.9876543210
--971543377 -1645852809 NULL NULL -971543377 -1645852809 NULL NULL -971543377 -1645852809 NULL NULL uN803aW NULL 3.321 9.9876543210
-940448896 -1645852809 NULL NULL 940448896 -1645852809 NULL NULL 940448896 -1645852809 NULL NULL qqbDw46IgGds4 NULL 3.321 9.9876543210
--324030556 -1645852809 NULL NULL -324030556 -1645852809 NULL NULL -324030556 -1645852809 NULL NULL 32v414p63Jv1B4tO1xy NULL 3.321 9.9876543210
--899422227 -1645852809 NULL NULL -899422227 -1645852809 NULL NULL -899422227 -1645852809 NULL NULL 73xdw4X NULL 3.321 9.9876543210
-835111400 1964238982 11.0 NULL 835111400 1964238982 11.0 NULL 835111400 1964238982 11.0 NULL d3o1712a03n20qvi62U7 11.0 3.321 9.9876543210
--775326158 -1289793978 11.0 NULL -775326158 -1289793978 11.0 NULL -775326158 -1289793978 11.0 NULL eQ80MW0h728I204P87YXc 11.0 3.321 9.9876543210
-653630202 1281184487 11.0 NULL 653630202 1281184487 11.0 NULL 653630202 1281184487 11.0 NULL KHtD2A2hp6OjFgS73gdgE 11.0 3.321 9.9876543210
-779427499 1326393090 11.0 NULL 779427499 1326393090 11.0 NULL 779427499 1326393090 11.0 NULL nI30tm7U55O0gI 11.0 3.321 9.9876543210
-797003983 1186689849 11.0 NULL 797003983 1186689849 11.0 NULL 797003983 1186689849 11.0 NULL LSJtFA66 11.0 3.321 9.9876543210
-31832752 1854212271 11.0 NULL 31832752 1854212271 11.0 NULL 31832752 1854212271 11.0 NULL mby00c 11.0 3.321 9.9876543210
-783790031 -1482854823 11.0 NULL 783790031 -1482854823 11.0 NULL 783790031 -1482854823 11.0 NULL meGb5 11.0 3.321 9.9876543210
--898241885 -1785664982 11.0 NULL -898241885 -1785664982 11.0 NULL -898241885 -1785664982 11.0 NULL pM6Gt05s1YJeii 11.0 3.321 9.9876543210
-NULL -1083386085 11.0 NULL NULL -1083386085 11.0 NULL NULL -1083386085 11.0 NULL LR2AKy0dPt8vFdIV5760jriw 11.0 3.321 9.9876543210
--646295381 -1654635859 11.0 NULL -646295381 -1654635859 11.0 NULL -646295381 -1654635859 11.0 NULL 1B3WMD5LSk65B2Moa 11.0 3.321 9.9876543210
-130912195 -1286145901 11.0 NULL 130912195 -1286145901 11.0 NULL 130912195 -1286145901 11.0 NULL xTlDv24JYv4s 11.0 3.321 9.9876543210
--391573084 -236100834 11.0 NULL -391573084 -236100834 11.0 NULL -391573084 -236100834 11.0 NULL 28Oe6r21yux7Lk47 11.0 3.321 9.9876543210
-385623629 236101682 11.0 NULL 385623629 236101682 11.0 NULL 385623629 236101682 11.0 NULL 7wH3hBKdO55Xq3gEEe0 11.0 3.321 9.9876543210
-681126962 993392163 11.0 NULL 681126962 993392163 11.0 NULL 681126962 993392163 11.0 NULL 5QLs0LVK1g 11.0 3.321 9.9876543210
-25892751 -1978674520 11.0 NULL 25892751 -1978674520 11.0 NULL 25892751 -1978674520 11.0 NULL ET3d4F2I4lV 11.0 3.321 9.9876543210
--838810013 1864027286 NULL NULL -838810013 1864027286 NULL NULL -838810013 1864027286 NULL NULL N016jPED08o NULL 1.123 1.1234567890
-246423894 -1645852809 NULL NULL 246423894 -1645852809 NULL NULL 246423894 -1645852809 NULL NULL Q1JAdUlCVORmR0Q5X5Vf5u6 NULL 1.123 1.1234567890
-708885482 -1645852809 NULL NULL 708885482 -1645852809 NULL NULL 708885482 -1645852809 NULL NULL eNsh5tYa NULL 1.123 1.1234567890
-186967185 -1645852809 NULL NULL 186967185 -1645852809 NULL NULL 186967185 -1645852809 NULL NULL 5j7GJ8OCXgMVIcK7 NULL 1.123 1.1234567890
--595277064 -1645852809 NULL NULL -595277064 -1645852809 NULL NULL -595277064 -1645852809 NULL NULL uJGHsW3cd073NGFITyQ NULL 1.123 1.1234567890
-584923170 -1645852809 NULL NULL 584923170 -1645852809 NULL NULL 584923170 -1645852809 NULL NULL G1u0pUmU6ehCm NULL 1.123 1.1234567890
-518213127 -1645852809 NULL NULL 518213127 -1645852809 NULL NULL 518213127 -1645852809 NULL NULL mk6lShdOa8kXT8i7mLd3fK NULL 1.123 1.1234567890
--334595454 -1645852809 NULL NULL -334595454 -1645852809 NULL NULL -334595454 -1645852809 NULL NULL u5C7glqT5XqtO0JE2686lk1 NULL 1.123 1.1234567890
-241008004 -1645852809 NULL NULL 241008004 -1645852809 NULL NULL 241008004 -1645852809 NULL NULL h4omSc1jcLLwW NULL 1.123 1.1234567890
-185212032 -1645852809 NULL NULL 185212032 -1645852809 NULL NULL 185212032 -1645852809 NULL NULL tFY2ng51v NULL 1.123 1.1234567890
--738747840 -1645852809 NULL NULL -738747840 -1645852809 NULL NULL -738747840 -1645852809 NULL NULL vmAT10eeE47fgH20pLi NULL 1.123 1.1234567890
--971543377 -1645852809 NULL NULL -971543377 -1645852809 NULL NULL -971543377 -1645852809 NULL NULL uN803aW NULL 1.123 1.1234567890
-940448896 -1645852809 NULL NULL 940448896 -1645852809 NULL NULL 940448896 -1645852809 NULL NULL qqbDw46IgGds4 NULL 1.123 1.1234567890
--324030556 -1645852809 NULL NULL -324030556 -1645852809 NULL NULL -324030556 -1645852809 NULL NULL 32v414p63Jv1B4tO1xy NULL 1.123 1.1234567890
--899422227 -1645852809 NULL NULL -899422227 -1645852809 NULL NULL -899422227 -1645852809 NULL NULL 73xdw4X NULL 1.123 1.1234567890
-835111400 1964238982 11.0 NULL 835111400 1964238982 11.0 NULL 835111400 1964238982 11.0 NULL d3o1712a03n20qvi62U7 11.0 1.123 1.1234567890
--775326158 -1289793978 11.0 NULL -775326158 -1289793978 11.0 NULL -775326158 -1289793978 11.0 NULL eQ80MW0h728I204P87YXc 11.0 1.123 1.1234567890
-653630202 1281184487 11.0 NULL 653630202 1281184487 11.0 NULL 653630202 1281184487 11.0 NULL KHtD2A2hp6OjFgS73gdgE 11.0 1.123 1.1234567890
-779427499 1326393090 11.0 NULL 779427499 1326393090 11.0 NULL 779427499 1326393090 11.0 NULL nI30tm7U55O0gI 11.0 1.123 1.1234567890
-797003983 1186689849 11.0 NULL 797003983 1186689849 11.0 NULL 797003983 1186689849 11.0 NULL LSJtFA66 11.0 1.123 1.1234567890
-31832752 1854212271 11.0 NULL 31832752 1854212271 11.0 NULL 31832752 1854212271 11.0 NULL mby00c 11.0 1.123 1.1234567890
-783790031 -1482854823 11.0 NULL 783790031 -1482854823 11.0 NULL 783790031 -1482854823 11.0 NULL meGb5 11.0 1.123 1.1234567890
--898241885 -1785664982 11.0 NULL -898241885 -1785664982 11.0 NULL -898241885 -1785664982 11.0 NULL pM6Gt05s1YJeii 11.0 1.123 1.1234567890
-NULL -1083386085 11.0 NULL NULL -1083386085 11.0 NULL NULL -1083386085 11.0 NULL LR2AKy0dPt8vFdIV5760jriw 11.0 1.123 1.1234567890
--646295381 -1654635859 11.0 NULL -646295381 -1654635859 11.0 NULL -646295381 -1654635859 11.0 NULL 1B3WMD5LSk65B2Moa 11.0 1.123 1.1234567890
-130912195 -1286145901 11.0 NULL 130912195 -1286145901 11.0 NULL 130912195 -1286145901 11.0 NULL xTlDv24JYv4s 11.0 1.123 1.1234567890
--391573084 -236100834 11.0 NULL -391573084 -236100834 11.0 NULL -391573084 -236100834 11.0 NULL 28Oe6r21yux7Lk47 11.0 1.123 1.1234567890
-385623629 236101682 11.0 NULL 385623629 236101682 11.0 NULL 385623629 236101682 11.0 NULL 7wH3hBKdO55Xq3gEEe0 11.0 1.123 1.1234567890
-681126962 993392163 11.0 NULL 681126962 993392163 11.0 NULL 681126962 993392163 11.0 NULL 5QLs0LVK1g 11.0 1.123 1.1234567890
-25892751 -1978674520 11.0 NULL 25892751 -1978674520 11.0 NULL 25892751 -1978674520 11.0 NULL ET3d4F2I4lV 11.0 1.123 1.1234567890
+-1064623720 -1894858490 11.0 NULL -1064623720 -1894858490 11.0 NULL -1064623720 -1894858490 11.0 NULL 47INeW44yvsne46Mu 11.0 1.123 1.1234567890
+-1064623720 -1894858490 11.0 NULL -1064623720 -1894858490 11.0 NULL -1064623720 -1894858490 11.0 NULL 47INeW44yvsne46Mu 11.0 3.321 9.9876543210
+-1064718136 156403402 -51.0 NULL -1064718136 156403402 -51.0 NULL -1064718136 156403402 -51.0 NULL k7i5RkMq88H0s -51.0 1.123 1.1234567890
+-1064718136 156403402 -51.0 NULL -1064718136 156403402 -51.0 NULL -1064718136 156403402 -51.0 NULL k7i5RkMq88H0s -51.0 3.321 9.9876543210
+-1064949302 -1645852809 NULL 6454.0 -1064949302 -1645852809 NULL 6454.0 -1064949302 -1645852809 NULL 6454.0 8u8tR858jC01y8Ft66nYRnb6 NULL 1.123 1.1234567890
+-1064949302 -1645852809 NULL 6454.0 -1064949302 -1645852809 NULL 6454.0 -1064949302 -1645852809 NULL 6454.0 8u8tR858jC01y8Ft66nYRnb6 NULL 3.321 9.9876543210
+-1064981602 -1444011153 -51.0 NULL -1064981602 -1444011153 -51.0 NULL -1064981602 -1444011153 -51.0 NULL aY3tpnr6wfvmWMG0U881 -51.0 1.123 1.1234567890
+-1064981602 -1444011153 -51.0 NULL -1064981602 -1444011153 -51.0 NULL -1064981602 -1444011153 -51.0 NULL aY3tpnr6wfvmWMG0U881 -51.0 3.321 9.9876543210
+-1065117869 -1887561756 NULL 2538.0 -1065117869 -1887561756 NULL 2538.0 -1065117869 -1887561756 NULL 2538.0 jWVP6gOkq12mdh NULL 1.123 1.1234567890
+-1065117869 -1887561756 NULL 2538.0 -1065117869 -1887561756 NULL 2538.0 -1065117869 -1887561756 NULL 2538.0 jWVP6gOkq12mdh NULL 3.321 9.9876543210
+-1065775394 -1331703092 -51.0 NULL -1065775394 -1331703092 -51.0 NULL -1065775394 -1331703092 -51.0 NULL aD88uS2N8DmqPlvjOa7F46i7 -51.0 1.123 1.1234567890
+-1065775394 -1331703092 -51.0 NULL -1065775394 -1331703092 -51.0 NULL -1065775394 -1331703092 -51.0 NULL aD88uS2N8DmqPlvjOa7F46i7 -51.0 3.321 9.9876543210
+-1066226047 1864027286 NULL -9439.0 -1066226047 1864027286 NULL -9439.0 -1066226047 1864027286 NULL -9439.0 8GIqX3tvNqrgH NULL 1.123 1.1234567890
+-1066226047 1864027286 NULL -9439.0 -1066226047 1864027286 NULL -9439.0 -1066226047 1864027286 NULL -9439.0 8GIqX3tvNqrgH NULL 3.321 9.9876543210
+-1066684273 2034191923 -51.0 NULL -1066684273 2034191923 -51.0 NULL -1066684273 2034191923 -51.0 NULL 2W4Kg220OcCy065HG60k6e -51.0 1.123 1.1234567890
+-1066684273 2034191923 -51.0 NULL -1066684273 2034191923 -51.0 NULL -1066684273 2034191923 -51.0 NULL 2W4Kg220OcCy065HG60k6e -51.0 3.321 9.9876543210
+-1066922682 -1645852809 NULL -9987.0 -1066922682 -1645852809 NULL -9987.0 -1066922682 -1645852809 NULL -9987.0 0RrH6XDA1 NULL 1.123 1.1234567890
+-1066922682 -1645852809 NULL -9987.0 -1066922682 -1645852809 NULL -9987.0 -1066922682 -1645852809 NULL -9987.0 0RrH6XDA1 NULL 3.321 9.9876543210
+-1067386090 -1887561756 NULL -3977.0 -1067386090 -1887561756 NULL -3977.0 -1067386090 -1887561756 NULL -3977.0 HBtg2r6pR16VC73 NULL 1.123 1.1234567890
+-1067386090 -1887561756 NULL -3977.0 -1067386090 -1887561756 NULL -3977.0 -1067386090 -1887561756 NULL -3977.0 HBtg2r6pR16VC73 NULL 3.321 9.9876543210
+-1067683781 1750003656 -51.0 NULL -1067683781 1750003656 -51.0 NULL -1067683781 1750003656 -51.0 NULL IbgbUvP5 -51.0 1.123 1.1234567890
+-1067683781 1750003656 -51.0 NULL -1067683781 1750003656 -51.0 NULL -1067683781 1750003656 -51.0 NULL IbgbUvP5 -51.0 3.321 9.9876543210
+-1067874703 -1742615956 11.0 NULL -1067874703 -1742615956 11.0 NULL -1067874703 -1742615956 11.0 NULL us1gH35lcpND 11.0 1.123 1.1234567890
+-1067874703 -1742615956 11.0 NULL -1067874703 -1742615956 11.0 NULL -1067874703 -1742615956 11.0 NULL us1gH35lcpND 11.0 3.321 9.9876543210
+-1068206466 1240583144 8.0 NULL -1068206466 1240583144 8.0 NULL -1068206466 1240583144 8.0 NULL F3u1yJaQywofxCCM4v4jScY 8.0 1.123 1.1234567890
+-1068206466 1240583144 8.0 NULL -1068206466 1240583144 8.0 NULL -1068206466 1240583144 8.0 NULL F3u1yJaQywofxCCM4v4jScY 8.0 3.321 9.9876543210
+-1068247011 -729456614 8.0 NULL -1068247011 -729456614 8.0 NULL -1068247011 -729456614 8.0 NULL dPbX4jd1v47r1bB6506si 8.0 1.123 1.1234567890
+-1068247011 -729456614 8.0 NULL -1068247011 -729456614 8.0 NULL -1068247011 -729456614 8.0 NULL dPbX4jd1v47r1bB6506si 8.0 3.321 9.9876543210
+-1068336533 925708299 11.0 NULL -1068336533 925708299 11.0 NULL -1068336533 925708299 11.0 NULL PUn1YVC 11.0 1.123 1.1234567890
+-1068336533 925708299 11.0 NULL -1068336533 925708299 11.0 NULL -1068336533 925708299 11.0 NULL PUn1YVC 11.0 3.321 9.9876543210
+-1068623584 -1887561756 NULL -14005.0 -1068623584 -1887561756 NULL -14005.0 -1068623584 -1887561756 NULL -14005.0 s5O357fO5pF0 NULL 1.123 1.1234567890
+-1068623584 -1887561756 NULL -14005.0 -1068623584 -1887561756 NULL -14005.0 -1068623584 -1887561756 NULL -14005.0 s5O357fO5pF0 NULL 3.321 9.9876543210
+-1069097390 -1858556598 11.0 NULL -1069097390 -1858556598 11.0 NULL -1069097390 -1858556598 11.0 NULL B553840U1H2b1M06l6N81 11.0 1.123 1.1234567890
+-1069097390 -1858556598 11.0 NULL -1069097390 -1858556598 11.0 NULL -1069097390 -1858556598 11.0 NULL B553840U1H2b1M06l6N81 11.0 3.321 9.9876543210
+-1069103950 -927759444 11.0 NULL -1069103950 -927759444 11.0 NULL -1069103950 -927759444 11.0 NULL 41A0nYX72UOSfxO4053xy 11.0 1.123 1.1234567890
+-1069103950 -927759444 11.0 NULL -1069103950 -927759444 11.0 NULL -1069103950 -927759444 11.0 NULL 41A0nYX72UOSfxO4053xy 11.0 3.321 9.9876543210
+-1069109166 -1645852809 NULL 8390.0 -1069109166 -1645852809 NULL 8390.0 -1069109166 -1645852809 NULL 8390.0 vW36C22KS75R NULL 1.123 1.1234567890
+-1069109166 -1645852809 NULL 8390.0 -1069109166 -1645852809 NULL 8390.0 -1069109166 -1645852809 NULL 8390.0 vW36C22KS75R NULL 3.321 9.9876543210
+-1069512165 -1645852809 NULL 11417.0 -1069512165 -1645852809 NULL 11417.0 -1069512165 -1645852809 NULL 11417.0 8x6mobxQl6Ef0Hl1 NULL 1.123 1.1234567890
+-1069512165 -1645852809 NULL 11417.0 -1069512165 -1645852809 NULL 11417.0 -1069512165 -1645852809 NULL 11417.0 8x6mobxQl6Ef0Hl1 NULL 3.321 9.9876543210
+-1069736047 -453772520 11.0 NULL -1069736047 -453772520 11.0 NULL -1069736047 -453772520 11.0 NULL k17Am8uPHWk02cEf1jet 11.0 1.123 1.1234567890
+-1069736047 -453772520 11.0 NULL -1069736047 -453772520 11.0 NULL -1069736047 -453772520 11.0 NULL k17Am8uPHWk02cEf1jet 11.0 3.321 9.9876543210
+-1070551679 1864027286 NULL -947.0 -1070551679 1864027286 NULL -947.0 -1070551679 1864027286 NULL -947.0 iUR3Q NULL 1.123 1.1234567890
+-1070551679 1864027286 NULL -947.0 -1070551679 1864027286 NULL -947.0 -1070551679 1864027286 NULL -947.0 iUR3Q NULL 3.321 9.9876543210
+-1070883071 -1645852809 NULL -741.0 -1070883071 -1645852809 NULL -741.0 -1070883071 -1645852809 NULL -741.0 0ruyd6Y50JpdGRf6HqD NULL 1.123 1.1234567890
+-1070883071 -1645852809 NULL -741.0 -1070883071 -1645852809 NULL -741.0 -1070883071 -1645852809 NULL -741.0 0ruyd6Y50JpdGRf6HqD NULL 3.321 9.9876543210
+-1071363017 1349676361 8.0 NULL -1071363017 1349676361 8.0 NULL -1071363017 1349676361 8.0 NULL Anj0oF 8.0 1.123 1.1234567890
+-1071363017 1349676361 8.0 NULL -1071363017 1349676361 8.0 NULL -1071363017 1349676361 8.0 NULL Anj0oF 8.0 3.321 9.9876543210
+-1071480828 -1401575336 -51.0 NULL -1071480828 -1401575336 -51.0 NULL -1071480828 -1401575336 -51.0 NULL aw724t8c5558x2xneC624 -51.0 1.123 1.1234567890
+-1071480828 -1401575336 -51.0 NULL -1071480828 -1401575336 -51.0 NULL -1071480828 -1401575336 -51.0 NULL aw724t8c5558x2xneC624 -51.0 3.321 9.9876543210
+-1072076362 1864027286 NULL -5470.0 -1072076362 1864027286 NULL -5470.0 -1072076362 1864027286 NULL -5470.0 2uLyD28144vklju213J1mr NULL 1.123 1.1234567890
+-1072076362 1864027286 NULL -5470.0 -1072076362 1864027286 NULL -5470.0 -1072076362 1864027286 NULL -5470.0 2uLyD28144vklju213J1mr NULL 3.321 9.9876543210
+-1072081801 1864027286 NULL 8373.0 -1072081801 1864027286 NULL 8373.0 -1072081801 1864027286 NULL 8373.0 dPkN74F7 NULL 1.123 1.1234567890
+-1072081801 1864027286 NULL 8373.0 -1072081801 1864027286 NULL 8373.0 -1072081801 1864027286 NULL 8373.0 dPkN74F7 NULL 3.321 9.9876543210
+-1072910839 2048385991 11.0 NULL -1072910839 2048385991 11.0 NULL -1072910839 2048385991 11.0 NULL 0iqrc5 11.0 1.123 1.1234567890
+-1072910839 2048385991 11.0 NULL -1072910839 2048385991 11.0 NULL -1072910839 2048385991 11.0 NULL 0iqrc5 11.0 3.321 9.9876543210
+-1073051226 -1887561756 NULL -7382.0 -1073051226 -1887561756 NULL -7382.0 -1073051226 -1887561756 NULL -7382.0 A34p7oRr2WvUJNf NULL 1.123 1.1234567890
+-1073051226 -1887561756 NULL -7382.0 -1073051226 -1887561756 NULL -7382.0 -1073051226 -1887561756 NULL -7382.0 A34p7oRr2WvUJNf NULL 3.321 9.9876543210
+-1073279343 -1595604468 11.0 NULL -1073279343 -1595604468 11.0 NULL -1073279343 -1595604468 11.0 NULL oj1YrV5Wa 11.0 1.123 1.1234567890
+-1073279343 -1595604468 11.0 NULL -1073279343 -1595604468 11.0 NULL -1073279343 -1595604468 11.0 NULL oj1YrV5Wa 11.0 3.321 9.9876543210
PREHOOK: query: select cstring1 from orc_llap2
PREHOOK: type: QUERY
PREHOOK: Input: default@orc_llap2
@@ -426,36 +444,36 @@ POSTHOOK: query: select cstring1 from orc_llap2
POSTHOOK: type: QUERY
POSTHOOK: Input: default@orc_llap2
#### A masked pattern was here ####
-Q1JAdUlCVORmR0Q5X5Vf5u6
-eNsh5tYa
-5j7GJ8OCXgMVIcK7
-uJGHsW3cd073NGFITyQ
-G1u0pUmU6ehCm
-mk6lShdOa8kXT8i7mLd3fK
-u5C7glqT5XqtO0JE2686lk1
-h4omSc1jcLLwW
-tFY2ng51v
-vmAT10eeE47fgH20pLi
-uN803aW
-qqbDw46IgGds4
-32v414p63Jv1B4tO1xy
-73xdw4X
-d3o1712a03n20qvi62U7
-eQ80MW0h728I204P87YXc
-KHtD2A2hp6OjFgS73gdgE
-nI30tm7U55O0gI
-LSJtFA66
-mby00c
-meGb5
-pM6Gt05s1YJeii
-LR2AKy0dPt8vFdIV5760jriw
-1B3WMD5LSk65B2Moa
-xTlDv24JYv4s
-28Oe6r21yux7Lk47
-7wH3hBKdO55Xq3gEEe0
-5QLs0LVK1g
-ET3d4F2I4lV
-testvalue
+0RrH6XDA1
+0iqrc5
+0ruyd6Y50JpdGRf6HqD
+2W4Kg220OcCy065HG60k6e
+2uLyD28144vklju213J1mr
+41A0nYX72UOSfxO4053xy
+47INeW44yvsne46Mu
+8GIqX3tvNqrgH
+8u8tR858jC01y8Ft66nYRnb6
+8x6mobxQl6Ef0Hl1
+A34p7oRr2WvUJNf
+Anj0oF
+B553840U1H2b1M06l6N81
+F3u1yJaQywofxCCM4v4jScY
+HBtg2r6pR16VC73
+IbgbUvP5
+PUn1YVC
+aD88uS2N8DmqPlvjOa7F46i7
+aY3tpnr6wfvmWMG0U881
+aw724t8c5558x2xneC624
+dPbX4jd1v47r1bB6506si
+dPkN74F7
+iUR3Q
+jWVP6gOkq12mdh
+k17Am8uPHWk02cEf1jet
+k7i5RkMq88H0s
+oj1YrV5Wa
+s5O357fO5pF0
+us1gH35lcpND
+vW36C22KS75R
PREHOOK: query: select cfloat2, cint from orc_llap2
PREHOOK: type: QUERY
PREHOOK: Input: default@orc_llap2
@@ -464,36 +482,36 @@ POSTHOOK: query: select cfloat2, cint from orc_llap2
POSTHOOK: type: QUERY
POSTHOOK: Input: default@orc_llap2
#### A masked pattern was here ####
-NULL 246423894
-NULL 708885482
-NULL 186967185
-NULL -595277064
-NULL 584923170
-NULL 518213127
-NULL -334595454
-NULL 241008004
-NULL 185212032
-NULL -738747840
-NULL -971543377
-NULL 940448896
-NULL -324030556
-NULL -899422227
-11.0 835111400
-11.0 -775326158
-11.0 653630202
-11.0 779427499
-11.0 797003983
-11.0 31832752
-11.0 783790031
-11.0 -898241885
-11.0 NULL
-11.0 -646295381
-11.0 130912195
-11.0 -391573084
-11.0 385623629
-11.0 681126962
-11.0 25892751
-NULL -838810013
+-51.0 -1064718136
+-51.0 -1064981602
+-51.0 -1065775394
+-51.0 -1066684273
+-51.0 -1067683781
+-51.0 -1071480828
+11.0 -1064623720
+11.0 -1067874703
+11.0 -1068336533
+11.0 -1069097390
+11.0 -1069103950
+11.0 -1069736047
+11.0 -1072910839
+11.0 -1073279343
+8.0 -1068206466
+8.0 -1068247011
+8.0 -1071363017
+NULL -1064949302
+NULL -1065117869
+NULL -1066226047
+NULL -1066922682
+NULL -1067386090
+NULL -1068623584
+NULL -1069109166
+NULL -1069512165
+NULL -1070551679
+NULL -1070883071
+NULL -1072076362
+NULL -1072081801
+NULL -1073051226
PREHOOK: query: select * from orc_llap2
PREHOOK: type: QUERY
PREHOOK: Input: default@orc_llap2
@@ -502,36 +520,36 @@ POSTHOOK: query: select * from orc_llap2
POSTHOOK: type: QUERY
POSTHOOK: Input: default@orc_llap2
#### A masked pattern was here ####
-246423894 -1645852809 NULL NULL 246423894 -1645852809 NULL NULL 246423894 -1645852809 NULL NULL Q1JAdUlCVORmR0Q5X5Vf5u6 NULL 1.123 1.1234567890
-708885482 -1645852809 NULL NULL 708885482 -1645852809 NULL NULL 708885482 -1645852809 NULL NULL eNsh5tYa NULL 1.123 1.1234567890
-186967185 -1645852809 NULL NULL 186967185 -1645852809 NULL NULL 186967185 -1645852809 NULL NULL 5j7GJ8OCXgMVIcK7 NULL 1.123 1.1234567890
--595277064 -1645852809 NULL NULL -595277064 -1645852809 NULL NULL -595277064 -1645852809 NULL NULL uJGHsW3cd073NGFITyQ NULL 1.123 1.1234567890
-584923170 -1645852809 NULL NULL 584923170 -1645852809 NULL NULL 584923170 -1645852809 NULL NULL G1u0pUmU6ehCm NULL 1.123 1.1234567890
-518213127 -1645852809 NULL NULL 518213127 -1645852809 NULL NULL 518213127 -1645852809 NULL NULL mk6lShdOa8kXT8i7mLd3fK NULL 1.123 1.1234567890
--334595454 -1645852809 NULL NULL -334595454 -1645852809 NULL NULL -334595454 -1645852809 NULL NULL u5C7glqT5XqtO0JE2686lk1 NULL 1.123 1.1234567890
-241008004 -1645852809 NULL NULL 241008004 -1645852809 NULL NULL 241008004 -1645852809 NULL NULL h4omSc1jcLLwW NULL 1.123 1.1234567890
-185212032 -1645852809 NULL NULL 185212032 -1645852809 NULL NULL 185212032 -1645852809 NULL NULL tFY2ng51v NULL 1.123 1.1234567890
--738747840 -1645852809 NULL NULL -738747840 -1645852809 NULL NULL -738747840 -1645852809 NULL NULL vmAT10eeE47fgH20pLi NULL 1.123 1.1234567890
--971543377 -1645852809 NULL NULL -971543377 -1645852809 NULL NULL -971543377 -1645852809 NULL NULL uN803aW NULL 1.123 1.1234567890
-940448896 -1645852809 NULL NULL 940448896 -1645852809 NULL NULL 940448896 -1645852809 NULL NULL qqbDw46IgGds4 NULL 1.123 1.1234567890
--324030556 -1645852809 NULL NULL -324030556 -1645852809 NULL NULL -324030556 -1645852809 NULL NULL 32v414p63Jv1B4tO1xy NULL 1.123 1.1234567890
--899422227 -1645852809 NULL NULL -899422227 -1645852809 NULL NULL -899422227 -1645852809 NULL NULL 73xdw4X NULL 1.123 1.1234567890
-835111400 1964238982 11.0 NULL 835111400 1964238982 11.0 NULL 835111400 1964238982 11.0 NULL d3o1712a03n20qvi62U7 11.0 1.123 1.1234567890
--775326158 -1289793978 11.0 NULL -775326158 -1289793978 11.0 NULL -775326158 -1289793978 11.0 NULL eQ80MW0h728I204P87YXc 11.0 1.123 1.1234567890
-653630202 1281184487 11.0 NULL 653630202 1281184487 11.0 NULL 653630202 1281184487 11.0 NULL KHtD2A2hp6OjFgS73gdgE 11.0 1.123 1.1234567890
-779427499 1326393090 11.0 NULL 779427499 1326393090 11.0 NULL 779427499 1326393090 11.0 NULL nI30tm7U55O0gI 11.0 1.123 1.1234567890
-797003983 1186689849 11.0 NULL 797003983 1186689849 11.0 NULL 797003983 1186689849 11.0 NULL LSJtFA66 11.0 1.123 1.1234567890
-31832752 1854212271 11.0 NULL 31832752 1854212271 11.0 NULL 31832752 1854212271 11.0 NULL mby00c 11.0 1.123 1.1234567890
-783790031 -1482854823 11.0 NULL 783790031 -1482854823 11.0 NULL 783790031 -1482854823 11.0 NULL meGb5 11.0 1.123 1.1234567890
--898241885 -1785664982 11.0 NULL -898241885 -1785664982 11.0 NULL -898241885 -1785664982 11.0 NULL pM6Gt05s1YJeii 11.0 1.123 1.1234567890
-NULL -1083386085 11.0 NULL NULL -1083386085 11.0 NULL NULL -1083386085 11.0 NULL LR2AKy0dPt8vFdIV5760jriw 11.0 1.123 1.1234567890
--646295381 -1654635859 11.0 NULL -646295381 -1654635859 11.0 NULL -646295381 -1654635859 11.0 NULL 1B3WMD5LSk65B2Moa 11.0 1.123 1.1234567890
-130912195 -1286145901 11.0 NULL 130912195 -1286145901 11.0 NULL 130912195 -1286145901 11.0 NULL xTlDv24JYv4s 11.0 1.123 1.1234567890
--391573084 -236100834 11.0 NULL -391573084 -236100834 11.0 NULL -391573084 -236100834 11.0 NULL 28Oe6r21yux7Lk47 11.0 1.123 1.1234567890
-385623629 236101682 11.0 NULL 385623629 236101682 11.0 NULL 385623629 236101682 11.0 NULL 7wH3hBKdO55Xq3gEEe0 11.0 1.123 1.1234567890
-681126962 993392163 11.0 NULL 681126962 993392163 11.0 NULL 681126962 993392163 11.0 NULL 5QLs0LVK1g 11.0 1.123 1.1234567890
-25892751 -1978674520 11.0 NULL 25892751 -1978674520 11.0 NULL 25892751 -1978674520 11.0 NULL ET3d4F2I4lV 11.0 1.123 1.1234567890
--838810013 1864027286 NULL NULL -838810013 1864027286 NULL NULL -838810013 1864027286 NULL NULL testvalue NULL 3.321 9.9876543210
+-1064623720 -1894858490 11.0 NULL -1064623720 -1894858490 11.0 NULL -1064623720 -1894858490 11.0 NULL 47INeW44yvsne46Mu 11.0 1.123 1.1234567890
+-1064718136 156403402 -51.0 NULL -1064718136 156403402 -51.0 NULL -1064718136 156403402 -51.0 NULL k7i5RkMq88H0s -51.0 1.123 1.1234567890
+-1064949302 -1645852809 NULL 6454.0 -1064949302 -1645852809 NULL 6454.0 -1064949302 -1645852809 NULL 6454.0 8u8tR858jC01y8Ft66nYRnb6 NULL 1.123 1.1234567890
+-1064981602 -1444011153 -51.0 NULL -1064981602 -1444011153 -51.0 NULL -1064981602 -1444011153 -51.0 NULL aY3tpnr6wfvmWMG0U881 -51.0 1.123 1.1234567890
+-1065117869 -1887561756 NULL 2538.0 -1065117869 -1887561756 NULL 2538.0 -1065117869 -1887561756 NULL 2538.0 jWVP6gOkq12mdh NULL 1.123 1.1234567890
+-1065775394 -1331703092 -51.0 NULL -1065775394 -1331703092 -51.0 NULL -1065775394 -1331703092 -51.0 NULL aD88uS2N8DmqPlvjOa7F46i7 -51.0 1.123 1.1234567890
+-1066226047 1864027286 NULL -9439.0 -1066226047 1864027286 NULL -9439.0 -1066226047 1864027286 NULL -9439.0 8GIqX3tvNqrgH NULL 1.123 1.1234567890
+-1066684273 2034191923 -51.0 NULL -1066684273 2034191923 -51.0 NULL -1066684273 2034191923 -51.0 NULL 2W4Kg220OcCy065HG60k6e -51.0 1.123 1.1234567890
+-1066922682 -1645852809 NULL -9987.0 -1066922682 -1645852809 NULL -9987.0 -1066922682 -1645852809 NULL -9987.0 0RrH6XDA1 NULL 1.123 1.1234567890
+-1067386090 -1887561756 NULL -3977.0 -1067386090 -1887561756 NULL -3977.0 -1067386090 -1887561756 NULL -3977.0 HBtg2r6pR16VC73 NULL 1.123 1.1234567890
+-1067683781 1750003656 -51.0 NULL -1067683781 1750003656 -51.0 NULL -1067683781 1750003656 -51.0 NULL IbgbUvP5 -51.0 1.123 1.1234567890
+-1067874703 -1742615956 11.0 NULL -1067874703 -1742615956 11.0 NULL -1067874703 -1742615956 11.0 NULL us1gH35lcpND 11.0 1.123 1.1234567890
+-1068206466 1240583144 8.0 NULL -1068206466 1240583144 8.0 NULL -1068206466 1240583144 8.0 NULL F3u1yJaQywofxCCM4v4jScY 8.0 1.123 1.1234567890
+-1068247011 -729456614 8.0 NULL -1068247011 -729456614 8.0 NULL -1068247011 -729456614 8.0 NULL dPbX4jd1v47r1bB6506si 8.0 1.123 1.1234567890
+-1068336533 925708299 11.0 NULL -1068336533 925708299 11.0 NULL -1068336533 925708299 11.0 NULL PUn1YVC 11.0 1.123 1.1234567890
+-1068623584 -1887561756 NULL -14005.0 -1068623584 -1887561756 NULL -14005.0 -1068623584 -1887561756 NULL -14005.0 s5O357fO5pF0 NULL 1.123 1.1234567890
+-1069097390 -1858556598 11.0 NULL -1069097390 -1858556598 11.0 NULL -1069097390 -1858556598 11.0 NULL B553840U1H2b1M06l6N81 11.0 1.123 1.1234567890
+-1069103950 -927759444 11.0 NULL -1069103950 -927759444 11.0 NULL -1069103950 -927759444 11.0 NULL 41A0nYX72UOSfxO4053xy 11.0 1.123 1.1234567890
+-1069109166 -1645852809 NULL 8390.0 -1069109166 -1645852809 NULL 8390.0 -1069109166 -1645852809 NULL 8390.0 vW36C22KS75R NULL 1.123 1.1234567890
+-1069512165 -1645852809 NULL 11417.0 -1069512165 -1645852809 NULL 11417.0 -1069512165 -1645852809 NULL 11417.0 8x6mobxQl6Ef0Hl1 NULL 1.123 1.1234567890
+-1069736047 -453772520 11.0 NULL -1069736047 -453772520 11.0 NULL -1069736047 -453772520 11.0 NULL k17Am8uPHWk02cEf1jet 11.0 1.123 1.1234567890
+-1070551679 1864027286 NULL -947.0 -1070551679 1864027286 NULL -947.0 -1070551679 1864027286 NULL -947.0 iUR3Q NULL 1.123 1.1234567890
+-1070883071 -1645852809 NULL -741.0 -1070883071 -1645852809 NULL -741.0 -1070883071 -1645852809 NULL -741.0 0ruyd6Y50JpdGRf6HqD NULL 1.123 1.1234567890
+-1071363017 1349676361 8.0 NULL -1071363017 1349676361 8.0 NULL -1071363017 1349676361 8.0 NULL Anj0oF 8.0 1.123 1.1234567890
+-1071480828 -1401575336 -51.0 NULL -1071480828 -1401575336 -51.0 NULL -1071480828 -1401575336 -51.0 NULL aw724t8c5558x2xneC624 -51.0 1.123 1.1234567890
+-1072076362 1864027286 NULL -5470.0 -1072076362 1864027286 NULL -5470.0 -1072076362 1864027286 NULL -5470.0 2uLyD28144vklju213J1mr NULL 1.123 1.1234567890
+-1072081801 1864027286 NULL 8373.0 -1072081801 1864027286 NULL 8373.0 -1072081801 1864027286 NULL 8373.0 dPkN74F7 NULL 1.123 1.1234567890
+-1072910839 2048385991 11.0 NULL -1072910839 2048385991 11.0 NULL -1072910839 2048385991 11.0 NULL 0iqrc5 11.0 1.123 1.1234567890
+-1073051226 -1887561756 NULL -7382.0 -1073051226 -1887561756 NULL -7382.0 -1073051226 -1887561756 NULL -7382.0 A34p7oRr2WvUJNf NULL 1.123 1.1234567890
+-1073279343 -1595604468 11.0 NULL -1073279343 -1595604468 11.0 NULL -1073279343 -1595604468 11.0 NULL oj1YrV5Wa 11.0 1.123 1.1234567890
PREHOOK: query: DROP TABLE orc_llap_n2
PREHOOK: type: DROPTABLE
PREHOOK: Input: default@orc_llap_n2
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/llap/llap_nullscan.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/llap_nullscan.q.out b/ql/src/test/results/clientpositive/llap/llap_nullscan.q.out
index 515b340..3404cdb 100644
--- a/ql/src/test/results/clientpositive/llap/llap_nullscan.q.out
+++ b/ql/src/test/results/clientpositive/llap/llap_nullscan.q.out
@@ -47,22 +47,22 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: src_orc_n1
- Statistics: Num rows: 10 Data size: 7360 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 3580 Basic stats: COMPLETE Column stats: COMPLETE
GatherStats: false
Filter Operator
isSamplingPred: false
predicate: false (type: boolean)
- Statistics: Num rows: 1 Data size: 736 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: key (type: string), value (type: string), ds (type: string), hr (type: string)
outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 1 Data size: 736 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
GlobalTableId: 0
directory: hdfs://### HDFS PATH ###
NumFilesPerFileSink: 1
- Statistics: Num rows: 1 Data size: 736 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE
Stats Publishing Key Prefix: hdfs://### HDFS PATH ###
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
@@ -89,7 +89,7 @@ STAGE PLANS:
input format: org.apache.hadoop.hive.ql.io.OneNullRowInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"ds":"true","hr":"true","key":"true","value":"true"}}
bucket_count -1
bucketing_version 2
column.name.delimiter ,
@@ -112,7 +112,7 @@ STAGE PLANS:
input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat
properties:
- COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"ds":"true","hr":"true","key":"true","value":"true"}}
bucket_count -1
bucketing_version 2
column.name.delimiter ,
@@ -177,29 +177,29 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: src_orc_n1
- Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 870 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: false (type: boolean)
- Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 87 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: key (type: string)
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 87 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 87 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: key (type: string)
outputColumnNames: _col0
- Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 870 Basic stats: COMPLETE Column stats: COMPLETE
Limit
Number of rows: 0
- Statistics: Num rows: 0 Data size: 0 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 87 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
- Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 87 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: string)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -213,10 +213,10 @@ STAGE PLANS:
0 _col0 (type: string)
1 _col0 (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 202 Basic stats: PARTIAL Column stats: NONE
+ Statistics: Num rows: 1 Data size: 174 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 202 Basic stats: PARTIAL Column stats: NONE
+ Statistics: Num rows: 1 Data size: 174 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -227,15 +227,15 @@ STAGE PLANS:
Select Operator
expressions: VALUE._col0 (type: string)
outputColumnNames: _col0
- Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 87 Basic stats: COMPLETE Column stats: COMPLETE
Limit
Number of rows: 0
- Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 87 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 87 Basic stats: COMPLETE Column stats: COMPLETE
Stage: Stage-0
Fetch Operator
@@ -278,18 +278,18 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: src_orc_n1
- Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 870 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: false (type: boolean)
- Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 87 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count(key)
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
- Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: bigint)
Execution mode: vectorized, llap
LLAP IO: no inputs
@@ -297,19 +297,19 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: src_orc_n1
- Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 870 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: key (type: string)
outputColumnNames: key
- Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 870 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count(key)
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
- Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: bigint)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -320,10 +320,10 @@ STAGE PLANS:
aggregations: count(VALUE._col0)
mode: mergepartial
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 2 Data size: 384 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -335,10 +335,10 @@ STAGE PLANS:
aggregations: count(VALUE._col0)
mode: mergepartial
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 2 Data size: 384 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -388,15 +388,15 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: s1
- Statistics: Num rows: 10 Data size: 7360 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 3580 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: false (type: boolean)
- Statistics: Num rows: 1 Data size: 736 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: value (type: string)
sort order: +
Map-reduce partition columns: value (type: string)
- Statistics: Num rows: 1 Data size: 736 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: key (type: string), ds (type: string), hr (type: string)
Execution mode: vectorized, llap
LLAP IO: no inputs
@@ -404,15 +404,15 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: s2
- Statistics: Num rows: 10 Data size: 7360 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 3580 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: false (type: boolean)
- Statistics: Num rows: 1 Data size: 736 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: value (type: string)
sort order: +
Map-reduce partition columns: value (type: string)
- Statistics: Num rows: 1 Data size: 736 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: key (type: string), ds (type: string), hr (type: string)
Execution mode: vectorized, llap
LLAP IO: no inputs
@@ -426,14 +426,14 @@ STAGE PLANS:
0 value (type: string)
1 value (type: string)
outputColumnNames: _col0, _col1, _col2, _col3, _col7, _col8, _col9, _col10
- Statistics: Num rows: 1 Data size: 809 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 716 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col7 (type: string), _col8 (type: string), _col9 (type: string), _col10 (type: string)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7
- Statistics: Num rows: 1 Data size: 809 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 716 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 809 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 716 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/llap/llap_partitioned.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/llap_partitioned.q.out b/ql/src/test/results/clientpositive/llap/llap_partitioned.q.out
index 7e6e88b..529543c 100644
--- a/ql/src/test/results/clientpositive/llap/llap_partitioned.q.out
+++ b/ql/src/test/results/clientpositive/llap/llap_partitioned.q.out
@@ -2374,7 +2374,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: llap_temp_table_n0
- Statistics: Num rows: 1509 Data size: 984410 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1509 Data size: 250448 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:ctinyint:tinyint, 1:cint:int, 2:cchar1:char(255), 3:cvchar1:varchar(255), 4:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -2385,7 +2385,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1, 2, 3]
- Statistics: Num rows: 1509 Data size: 984410 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1509 Data size: 250448 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: sum(hash(ctinyint,cint,cchar1,cvchar1))
Group By Vectorization:
@@ -2397,7 +2397,7 @@ STAGE PLANS:
projectedOutputColumnNums: [0]
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 694 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
Reduce Sink Vectorization:
@@ -2405,7 +2405,7 @@ STAGE PLANS:
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
valueColumns: 0:bigint
- Statistics: Num rows: 1 Data size: 694 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: bigint)
Execution mode: vectorized, llap
LLAP IO: no inputs
@@ -2451,13 +2451,13 @@ STAGE PLANS:
projectedOutputColumnNums: [0]
mode: mergepartial
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 694 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 1 Data size: 694 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/llap/llap_udf.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/llap_udf.q.out b/ql/src/test/results/clientpositive/llap/llap_udf.q.out
index 292c0f9..62f9cd2 100644
--- a/ql/src/test/results/clientpositive/llap/llap_udf.q.out
+++ b/ql/src/test/results/clientpositive/llap/llap_udf.q.out
@@ -41,14 +41,14 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: src_orc_n0
- Statistics: Num rows: 500 Data size: 87584 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: evaluate_npe(key) (type: string)
outputColumnNames: _col0
- Statistics: Num rows: 500 Data size: 87584 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 92000 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 500 Data size: 87584 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 92000 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -108,14 +108,14 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: src_orc_n0
- Statistics: Num rows: 500 Data size: 87584 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: GenericUDFTestGetJavaString(key) (type: string), GenericUDFTestGetJavaString(key) (type: string), evaluate_npe(key) (type: string)
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 500 Data size: 87584 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 276000 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 500 Data size: 87584 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 276000 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -152,19 +152,20 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: src_orc_n0
- Statistics: Num rows: 500 Data size: 87584 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: evaluate_npe(key) (type: string)
outputColumnNames: _col0
- Statistics: Num rows: 500 Data size: 87584 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 92000 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 500 Data size: 87584 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 92000 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- Execution mode: vectorized
+ Execution mode: vectorized, llap
+ LLAP IO: all inputs
Stage: Stage-0
Fetch Operator
@@ -203,14 +204,14 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: src_orc_n0
- Statistics: Num rows: 500 Data size: 87584 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: GenericUDFTestGetJavaString(key) (type: string), evaluate_npe(key) (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 500 Data size: 87584 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 184000 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 500 Data size: 87584 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 184000 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -255,14 +256,14 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: src_orc_n0
- Statistics: Num rows: 500 Data size: 87584 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: evaluate_npe(key) (type: string)
outputColumnNames: _col0
- Statistics: Num rows: 500 Data size: 87584 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 92000 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 500 Data size: 87584 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 92000 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -298,14 +299,14 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: src_orc_n0
- Statistics: Num rows: 500 Data size: 87584 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: GenericUDFTestGetJavaString(key) (type: string)
outputColumnNames: _col0
- Statistics: Num rows: 500 Data size: 87584 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 92000 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 500 Data size: 87584 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 92000 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/llap/llapdecider.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/llapdecider.q.out b/ql/src/test/results/clientpositive/llap/llapdecider.q.out
index 8f482a7..228520c 100644
--- a/ql/src/test/results/clientpositive/llap/llapdecider.q.out
+++ b/ql/src/test/results/clientpositive/llap/llapdecider.q.out
@@ -113,48 +113,49 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: src_orc_n2
- Statistics: Num rows: 500 Data size: 175168 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: key (type: string), value (type: string)
outputColumnNames: key, value
- Statistics: Num rows: 500 Data size: 175168 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count(value)
keys: key (type: string)
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 500 Data size: 175168 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 500 Data size: 175168 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: bigint)
- Execution mode: vectorized
+ Execution mode: vectorized, llap
+ LLAP IO: all inputs
Reducer 2
- Execution mode: vectorized
+ Execution mode: vectorized, llap
Reduce Operator Tree:
Group By Operator
aggregations: count(VALUE._col0)
keys: KEY._col0 (type: string)
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 250 Data size: 87584 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col1 (type: bigint)
sort order: +
- Statistics: Num rows: 250 Data size: 87584 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: string)
Reducer 3
- Execution mode: vectorized
+ Execution mode: vectorized, llap
Reduce Operator Tree:
Select Operator
expressions: VALUE._col0 (type: string), KEY.reducesinkkey0 (type: bigint)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 250 Data size: 87584 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 250 Data size: 87584 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -191,22 +192,22 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: src_orc_n2
- Statistics: Num rows: 500 Data size: 175168 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: key (type: string), value (type: string)
outputColumnNames: key, value
- Statistics: Num rows: 500 Data size: 175168 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count(value)
keys: key (type: string)
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 500 Data size: 175168 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 500 Data size: 175168 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: bigint)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -218,11 +219,11 @@ STAGE PLANS:
keys: KEY._col0 (type: string)
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 250 Data size: 87584 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col1 (type: bigint)
sort order: +
- Statistics: Num rows: 250 Data size: 87584 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: string)
Reducer 3
Execution mode: vectorized, llap
@@ -230,10 +231,10 @@ STAGE PLANS:
Select Operator
expressions: VALUE._col0 (type: string), KEY.reducesinkkey0 (type: bigint)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 250 Data size: 87584 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 250 Data size: 87584 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 250 Data size: 23750 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/llap/materialized_view_create.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/materialized_view_create.q.out b/ql/src/test/results/clientpositive/llap/materialized_view_create.q.out
index 14bf676..1540483 100644
--- a/ql/src/test/results/clientpositive/llap/materialized_view_create.q.out
+++ b/ql/src/test/results/clientpositive/llap/materialized_view_create.q.out
@@ -45,7 +45,7 @@ Retention: 0
#### A masked pattern was here ####
Table Type: MATERIALIZED_VIEW
Table Parameters:
- COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"a\":\"true\",\"b\":\"true\",\"c\":\"true\"}}
bucketing_version 2
numFiles 1
numRows 5
@@ -107,7 +107,7 @@ Retention: 0
#### A masked pattern was here ####
Table Type: MATERIALIZED_VIEW
Table Parameters:
- COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"a\":\"true\",\"c\":\"true\"}}
bucketing_version 2
numFiles 1
numRows 5
@@ -243,7 +243,7 @@ PREHOOK: query: show tblproperties cmv_mat_view5
PREHOOK: type: SHOW_TBLPROPERTIES
POSTHOOK: query: show tblproperties cmv_mat_view5
POSTHOOK: type: SHOW_TBLPROPERTIES
-COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"}
+COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"a":"true","b":"true","c":"true","d":"true","f":"true"}}
bucketing_version 2
key value
numFiles 1
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/llap/materialized_view_create_rewrite.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/materialized_view_create_rewrite.q.out b/ql/src/test/results/clientpositive/llap/materialized_view_create_rewrite.q.out
index 69bdbea..6bf9ee5 100644
--- a/ql/src/test/results/clientpositive/llap/materialized_view_create_rewrite.q.out
+++ b/ql/src/test/results/clientpositive/llap/materialized_view_create_rewrite.q.out
@@ -28,16 +28,6 @@ POSTHOOK: Lineage: cmv_basetable_n10.a SCRIPT []
POSTHOOK: Lineage: cmv_basetable_n10.b SCRIPT []
POSTHOOK: Lineage: cmv_basetable_n10.c SCRIPT []
POSTHOOK: Lineage: cmv_basetable_n10.d SCRIPT []
-PREHOOK: query: analyze table cmv_basetable_n10 compute statistics for columns
-PREHOOK: type: ANALYZE_TABLE
-PREHOOK: Input: default@cmv_basetable_n10
-PREHOOK: Output: default@cmv_basetable_n10
-#### A masked pattern was here ####
-POSTHOOK: query: analyze table cmv_basetable_n10 compute statistics for columns
-POSTHOOK: type: ANALYZE_TABLE
-POSTHOOK: Input: default@cmv_basetable_n10
-POSTHOOK: Output: default@cmv_basetable_n10
-#### A masked pattern was here ####
PREHOOK: query: create materialized view cmv_mat_view_n10
as select a, b, c from cmv_basetable_n10 where a = 2
PREHOOK: type: CREATE_MATERIALIZED_VIEW
@@ -64,7 +54,7 @@ PREHOOK: query: show tblproperties cmv_mat_view_n10
PREHOOK: type: SHOW_TBLPROPERTIES
POSTHOOK: query: show tblproperties cmv_mat_view_n10
POSTHOOK: type: SHOW_TBLPROPERTIES
-COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"}
+COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"a":"true","b":"true","c":"true"}}
bucketing_version 2
numFiles 1
numFilesErasureCoded 0
@@ -98,7 +88,7 @@ PREHOOK: query: show tblproperties cmv_mat_view2_n4
PREHOOK: type: SHOW_TBLPROPERTIES
POSTHOOK: query: show tblproperties cmv_mat_view2_n4
POSTHOOK: type: SHOW_TBLPROPERTIES
-COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"}
+COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"a":"true","c":"true"}}
bucketing_version 2
numFiles 1
numFilesErasureCoded 0
@@ -354,10 +344,10 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: default.cmv_mat_view2_n4
- Statistics: Num rows: 2 Data size: 232 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 232 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
- Statistics: Num rows: 2 Data size: 232 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 232 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: a (type: int), c (type: decimal(10,2))
Execution mode: llap
LLAP IO: all inputs
@@ -371,14 +361,14 @@ STAGE PLANS:
0
1
outputColumnNames: _col0, _col1, _col5
- Statistics: Num rows: 2 Data size: 458 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 456 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: int), _col1 (type: decimal(10,2)), _col0 (type: int), _col5 (type: decimal(10,2))
outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 2 Data size: 458 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 464 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 2 Data size: 458 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 464 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
[29/35] hive git commit: HIVE-16957: Support CTAS for auto gather
column stats (Jesus Camacho Rodriguez, reviewed by Ashutosh Chauhan)
Posted by jc...@apache.org.
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/llap/dynamic_semijoin_reduction.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/dynamic_semijoin_reduction.q.out b/ql/src/test/results/clientpositive/llap/dynamic_semijoin_reduction.q.out
index 940c036..4304d9e 100644
--- a/ql/src/test/results/clientpositive/llap/dynamic_semijoin_reduction.q.out
+++ b/ql/src/test/results/clientpositive/llap/dynamic_semijoin_reduction.q.out
@@ -2988,7 +2988,7 @@ STAGE PLANS:
outputColumnNames: _col1
input vertices:
1 Map 3
- Statistics: Num rows: 2200 Data size: 605000 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 260 Data size: 47840 Basic stats: COMPLETE Column stats: COMPLETE
Map Join Operator
condition map:
Inner Join 0 to 1
@@ -2997,7 +2997,7 @@ STAGE PLANS:
1 _col0 (type: string)
input vertices:
1 Map 4
- Statistics: Num rows: 2420 Data size: 665500 Basic stats: PARTIAL Column stats: NONE
+ Statistics: Num rows: 286 Data size: 52624 Basic stats: PARTIAL Column stats: NONE
Group By Operator
aggregations: count()
mode: hash
@@ -3014,19 +3014,19 @@ STAGE PLANS:
TableScan
alias: alltypesorc_int40
filterExpr: cstring is not null (type: boolean)
- Statistics: Num rows: 40 Data size: 7176 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 40 Data size: 4000 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: cstring is not null (type: boolean)
- Statistics: Num rows: 38 Data size: 6817 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 40 Data size: 4000 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: cstring (type: string)
outputColumnNames: _col0
- Statistics: Num rows: 38 Data size: 6817 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 40 Data size: 4000 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 38 Data size: 6817 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 40 Data size: 4000 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized, llap
LLAP IO: no inputs
Map 4
@@ -3159,7 +3159,7 @@ STAGE PLANS:
outputColumnNames: _col1
input vertices:
1 Map 3
- Statistics: Num rows: 2200 Data size: 605000 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 260 Data size: 47840 Basic stats: COMPLETE Column stats: COMPLETE
Map Join Operator
condition map:
Inner Join 0 to 1
@@ -3168,7 +3168,7 @@ STAGE PLANS:
1 _col0 (type: string)
input vertices:
1 Map 4
- Statistics: Num rows: 2420 Data size: 665500 Basic stats: PARTIAL Column stats: NONE
+ Statistics: Num rows: 286 Data size: 52624 Basic stats: PARTIAL Column stats: NONE
Group By Operator
aggregations: count()
mode: hash
@@ -3185,19 +3185,19 @@ STAGE PLANS:
TableScan
alias: alltypesorc_int40
filterExpr: cstring is not null (type: boolean)
- Statistics: Num rows: 40 Data size: 7176 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 40 Data size: 4000 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: cstring is not null (type: boolean)
- Statistics: Num rows: 38 Data size: 6817 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 40 Data size: 4000 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: cstring (type: string)
outputColumnNames: _col0
- Statistics: Num rows: 38 Data size: 6817 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 40 Data size: 4000 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 38 Data size: 6817 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 40 Data size: 4000 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized, llap
LLAP IO: no inputs
Map 4
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/llap/dynamic_semijoin_reduction_3.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/dynamic_semijoin_reduction_3.q.out b/ql/src/test/results/clientpositive/llap/dynamic_semijoin_reduction_3.q.out
index ecf6323..96c390c 100644
--- a/ql/src/test/results/clientpositive/llap/dynamic_semijoin_reduction_3.q.out
+++ b/ql/src/test/results/clientpositive/llap/dynamic_semijoin_reduction_3.q.out
@@ -228,26 +228,6 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.merge_tmp_table
- Select Operator
- expressions: _col0 (type: int)
- outputColumnNames: val
- Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE
- Group By Operator
- aggregations: compute_stats(val, 'hll')
- mode: complete
- outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 432 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col0 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>)
- outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 432 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 1 Data size: 432 Basic stats: COMPLETE Column stats: NONE
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
Reducer 6
Execution mode: llap
Reduce Operator Tree:
@@ -351,10 +331,6 @@ STAGE PLANS:
Stage: Stage-8
Stats Work
Basic Stats Work:
- Column Stats Desc:
- Columns: val
- Column Types: int
- Table: default.merge_tmp_table
Stage: Stage-1
Move Operator
@@ -783,26 +759,6 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.merge_tmp_table
- Select Operator
- expressions: _col0 (type: int)
- outputColumnNames: val
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
- Group By Operator
- aggregations: compute_stats(val, 'hll')
- mode: complete
- outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 432 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col0 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>)
- outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 432 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 1 Data size: 432 Basic stats: COMPLETE Column stats: NONE
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
Reducer 7
Execution mode: llap
Reduce Operator Tree:
@@ -896,10 +852,6 @@ STAGE PLANS:
Stage: Stage-8
Stats Work
Basic Stats Work:
- Column Stats Desc:
- Columns: val
- Column Types: int
- Table: default.merge_tmp_table
Stage: Stage-1
Move Operator
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/llap/dynpart_sort_opt_vectorization.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/dynpart_sort_opt_vectorization.q.out b/ql/src/test/results/clientpositive/llap/dynpart_sort_opt_vectorization.q.out
index cf6c335..53337fe 100644
--- a/ql/src/test/results/clientpositive/llap/dynpart_sort_opt_vectorization.q.out
+++ b/ql/src/test/results/clientpositive/llap/dynpart_sort_opt_vectorization.q.out
@@ -274,6 +274,7 @@ STAGE PLANS:
Reduce Output Operator
sort order:
Statistics: Num rows: 10 Data size: 240 Basic stats: COMPLETE Column stats: COMPLETE
+ TopN Hash Memory Usage: 0.1
value expressions: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float), _col4 (type: tinyint)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -719,6 +720,7 @@ STAGE PLANS:
Reduce Output Operator
sort order:
Statistics: Num rows: 10 Data size: 240 Basic stats: COMPLETE Column stats: COMPLETE
+ TopN Hash Memory Usage: 0.1
value expressions: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float), _col4 (type: tinyint)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -1662,6 +1664,7 @@ STAGE PLANS:
key expressions: _col2 (type: int)
sort order: +
Statistics: Num rows: 1049 Data size: 25160 Basic stats: COMPLETE Column stats: COMPLETE
+ TopN Hash Memory Usage: 0.1
value expressions: _col0 (type: tinyint), _col1 (type: smallint), _col3 (type: bigint), _col4 (type: float)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -2992,6 +2995,7 @@ STAGE PLANS:
Reduce Output Operator
sort order:
Statistics: Num rows: 10 Data size: 816 Basic stats: COMPLETE Column stats: COMPLETE
+ TopN Hash Memory Usage: 0.1
value expressions: _col0 (type: int), _col1 (type: smallint), _col2 (type: string)
Execution mode: vectorized, llap
LLAP IO: all inputs
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/llap/dynpart_sort_optimization.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/dynpart_sort_optimization.q.out b/ql/src/test/results/clientpositive/llap/dynpart_sort_optimization.q.out
index 95c3aed..cb3704f 100644
--- a/ql/src/test/results/clientpositive/llap/dynpart_sort_optimization.q.out
+++ b/ql/src/test/results/clientpositive/llap/dynpart_sort_optimization.q.out
@@ -268,6 +268,7 @@ STAGE PLANS:
Reduce Output Operator
sort order:
Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE
+ TopN Hash Memory Usage: 0.1
value expressions: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float), _col4 (type: tinyint)
Execution mode: llap
LLAP IO: no inputs
@@ -750,6 +751,7 @@ STAGE PLANS:
Reduce Output Operator
sort order:
Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE
+ TopN Hash Memory Usage: 0.1
value expressions: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float), _col4 (type: tinyint)
Execution mode: llap
LLAP IO: no inputs
@@ -1693,6 +1695,7 @@ STAGE PLANS:
key expressions: _col2 (type: int)
sort order: +
Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE
+ TopN Hash Memory Usage: 0.1
value expressions: _col0 (type: tinyint), _col1 (type: smallint), _col3 (type: bigint), _col4 (type: float)
Execution mode: llap
LLAP IO: no inputs
@@ -4174,6 +4177,7 @@ STAGE PLANS:
Reduce Output Operator
sort order:
Statistics: Num rows: 10 Data size: 240 Basic stats: COMPLETE Column stats: COMPLETE
+ TopN Hash Memory Usage: 0.1
value expressions: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float), _col4 (type: tinyint)
Execution mode: llap
LLAP IO: no inputs
@@ -4415,6 +4419,7 @@ STAGE PLANS:
Reduce Output Operator
sort order:
Statistics: Num rows: 10 Data size: 240 Basic stats: COMPLETE Column stats: COMPLETE
+ TopN Hash Memory Usage: 0.1
value expressions: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float), _col4 (type: tinyint)
Execution mode: llap
LLAP IO: no inputs
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/llap/empty_join.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/empty_join.q.out b/ql/src/test/results/clientpositive/llap/empty_join.q.out
index 44fe8a9..f65c8bd 100644
--- a/ql/src/test/results/clientpositive/llap/empty_join.q.out
+++ b/ql/src/test/results/clientpositive/llap/empty_join.q.out
@@ -90,13 +90,13 @@ Stage-0
Filter Operator [FIL_40] (rows=1 width=4)
predicate:id is not null
TableScan [TS_6] (rows=1 width=4)
- default@test_3_n0,t3,Tbl:COMPLETE,Col:NONE,Output:["id"]
+ default@test_3_n0,t3,Tbl:COMPLETE,Col:COMPLETE,Output:["id"]
<-Select Operator [SEL_44] (rows=1 width=4)
Output:["_col0"]
Filter Operator [FIL_43] (rows=1 width=4)
predicate:id is not null
TableScan [TS_0] (rows=1 width=4)
- default@test_1_n2,t1,Tbl:COMPLETE,Col:NONE,Output:["id"]
+ default@test_1_n2,t1,Tbl:COMPLETE,Col:COMPLETE,Output:["id"]
PREHOOK: query: SELECT t1.id, t2.id, t3.id
FROM test_1_n2 t1
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/llap/enforce_constraint_notnull.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/enforce_constraint_notnull.q.out b/ql/src/test/results/clientpositive/llap/enforce_constraint_notnull.q.out
index dca0ebd..6989934 100644
--- a/ql/src/test/results/clientpositive/llap/enforce_constraint_notnull.q.out
+++ b/ql/src/test/results/clientpositive/llap/enforce_constraint_notnull.q.out
@@ -2793,6 +2793,7 @@ STAGE PLANS:
Reduce Output Operator
sort order:
Statistics: Num rows: 2 Data size: 414 Basic stats: COMPLETE Column stats: COMPLETE
+ TopN Hash Memory Usage: 0.1
value expressions: _col0 (type: int), _col1 (type: decimal(5,2)), _col2 (type: string)
Execution mode: vectorized, llap
LLAP IO: no inputs
@@ -2920,6 +2921,7 @@ STAGE PLANS:
key expressions: _col0 (type: int)
sort order: +
Statistics: Num rows: 500 Data size: 103500 Basic stats: COMPLETE Column stats: COMPLETE
+ TopN Hash Memory Usage: 0.1
value expressions: _col1 (type: decimal(5,2)), _col2 (type: string)
Execution mode: vectorized, llap
LLAP IO: no inputs
@@ -3043,16 +3045,22 @@ STAGE PLANS:
expressions: key (type: string), value (type: string)
outputColumnNames: key, value
Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
- Group By Operator
+ Top N Key Operator
+ sort order: ++
keys: key (type: string), value (type: string)
- mode: hash
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE
- Reduce Output Operator
- key expressions: _col0 (type: string), _col1 (type: string)
- sort order: ++
- Map-reduce partition columns: _col0 (type: string), _col1 (type: string)
+ Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
+ top n: 2
+ Group By Operator
+ keys: key (type: string), value (type: string)
+ mode: hash
+ outputColumnNames: _col0, _col1
Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ key expressions: _col0 (type: string), _col1 (type: string)
+ sort order: ++
+ Map-reduce partition columns: _col0 (type: string), _col1 (type: string)
+ Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE
+ TopN Hash Memory Usage: 0.1
Execution mode: vectorized, llap
LLAP IO: no inputs
Reducer 2
@@ -3803,6 +3811,7 @@ STAGE PLANS:
Reduce Output Operator
sort order:
Statistics: Num rows: 10 Data size: 3600 Basic stats: COMPLETE Column stats: COMPLETE
+ TopN Hash Memory Usage: 0.1
value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: int)
Execution mode: vectorized, llap
LLAP IO: no inputs
@@ -4637,26 +4646,6 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.merge_tmp_table
- Select Operator
- expressions: _col0 (type: int)
- outputColumnNames: val
- Statistics: Num rows: 1 Data size: 206 Basic stats: COMPLETE Column stats: NONE
- Group By Operator
- aggregations: compute_stats(val, 'hll')
- mode: complete
- outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 432 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col0 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>)
- outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 432 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 1 Data size: 432 Basic stats: COMPLETE Column stats: NONE
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
Reducer 6
Execution mode: llap
Reduce Operator Tree:
@@ -4748,10 +4737,6 @@ STAGE PLANS:
Stage: Stage-8
Stats Work
Basic Stats Work:
- Column Stats Desc:
- Columns: val
- Column Types: int
- Table: default.merge_tmp_table
Stage: Stage-1
Move Operator
@@ -4932,26 +4917,6 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.merge_tmp_table
- Select Operator
- expressions: _col0 (type: int)
- outputColumnNames: val
- Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE
- Group By Operator
- aggregations: compute_stats(val, 'hll')
- mode: complete
- outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 432 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col0 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>)
- outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 432 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 1 Data size: 432 Basic stats: COMPLETE Column stats: NONE
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
Reducer 5
Execution mode: llap
Reduce Operator Tree:
@@ -5028,10 +4993,6 @@ STAGE PLANS:
Stage: Stage-6
Stats Work
Basic Stats Work:
- Column Stats Desc:
- Columns: val
- Column Types: int
- Table: default.merge_tmp_table
Stage: Stage-1
Move Operator
@@ -5213,26 +5174,6 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.merge_tmp_table
- Select Operator
- expressions: _col0 (type: int)
- outputColumnNames: val
- Statistics: Num rows: 1 Data size: 206 Basic stats: COMPLETE Column stats: NONE
- Group By Operator
- aggregations: compute_stats(val, 'hll')
- mode: complete
- outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 432 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col0 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>)
- outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 432 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 1 Data size: 432 Basic stats: COMPLETE Column stats: NONE
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
Reducer 5
Execution mode: llap
Reduce Operator Tree:
@@ -5309,10 +5250,6 @@ STAGE PLANS:
Stage: Stage-6
Stats Work
Basic Stats Work:
- Column Stats Desc:
- Columns: val
- Column Types: int
- Table: default.merge_tmp_table
Stage: Stage-0
Move Operator
@@ -5480,26 +5417,6 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.merge_tmp_table
- Select Operator
- expressions: _col0 (type: int)
- outputColumnNames: val
- Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE
- Group By Operator
- aggregations: compute_stats(val, 'hll')
- mode: complete
- outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 432 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col0 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>)
- outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 432 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 1 Data size: 432 Basic stats: COMPLETE Column stats: NONE
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
Stage: Stage-3
Dependency Collection
@@ -5532,10 +5449,6 @@ STAGE PLANS:
Stage: Stage-5
Stats Work
Basic Stats Work:
- Column Stats Desc:
- Columns: val
- Column Types: int
- Table: default.merge_tmp_table
PREHOOK: query: DROP TABLE masking_test_n4
PREHOOK: type: DROPTABLE
@@ -6030,6 +5943,7 @@ STAGE PLANS:
key expressions: _col1 (type: string)
sort order: +
Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
+ TopN Hash Memory Usage: 0.1
value expressions: _col0 (type: string)
Execution mode: vectorized, llap
LLAP IO: no inputs
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/llap/explainuser_1.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/explainuser_1.q.out b/ql/src/test/results/clientpositive/llap/explainuser_1.q.out
index dfbbeb6..2bb6352 100644
--- a/ql/src/test/results/clientpositive/llap/explainuser_1.q.out
+++ b/ql/src/test/results/clientpositive/llap/explainuser_1.q.out
@@ -1608,7 +1608,7 @@ Stage-0
Output:["_col0","_col1","_col2"],aggregations:["count()"],keys:_col4, _col7
Select Operator [SEL_33] (rows=2 width=28)
Output:["_col4","_col7"]
- Merge Join Operator [MERGEJOIN_64] (rows=2 width=28)
+ Merge Join Operator [MERGEJOIN_65] (rows=2 width=28)
Conds:RS_29._col0=RS_30._col0(Inner),RS_30._col0=RS_31._col0(Inner),Output:["_col1","_col3","_col4","_col5","_col7","_col8"],residual filter predicates:{((_col3 + _col1) >= 0)} {(_col5 or _col8)}
<-Map 10 [SIMPLE_EDGE] llap
SHUFFLE [RS_31]
@@ -1665,10 +1665,12 @@ Stage-0
PartitionCols:_col0, _col1, _col2
Group By Operator [GBY_16] (rows=3 width=101)
Output:["_col0","_col1","_col2","_col3"],aggregations:["sum(c_int)"],keys:key, c_int, c_float
- Filter Operator [FIL_52] (rows=6 width=93)
- predicate:(((c_int + 1) >= 0) and ((c_int > 0) or (c_float >= 0.0)))
- TableScan [TS_13] (rows=20 width=88)
- default@cbo_t1,cbo_t1,Tbl:COMPLETE,Col:COMPLETE,Output:["key","c_int","c_float"]
+ Top N Key Operator [TNK_54] (rows=6 width=93)
+ keys:key, c_int, c_float,sort order:+++,top n:5
+ Filter Operator [FIL_52] (rows=6 width=93)
+ predicate:(((c_int + 1) >= 0) and ((c_int > 0) or (c_float >= 0.0)))
+ TableScan [TS_13] (rows=20 width=88)
+ default@cbo_t1,cbo_t1,Tbl:COMPLETE,Col:COMPLETE,Output:["key","c_int","c_float"]
PREHOOK: query: explain select cbo_t1.c_int from cbo_t1 left semi join cbo_t2 on cbo_t1.key=cbo_t2.key where (cbo_t1.c_int + 1 == 2) and (cbo_t1.c_int > 0 or cbo_t1.c_float >= 0)
PREHOOK: type: QUERY
@@ -3649,36 +3651,45 @@ Plan not optimized by CBO because the statement has sort by
Vertex dependency in root stage
Reducer 2 <- Map 1 (SIMPLE_EDGE)
Reducer 3 <- Reducer 2 (SIMPLE_EDGE)
+Reducer 4 <- Reducer 3 (CUSTOM_SIMPLE_EDGE)
Stage-3
Stats Work{}
Stage-4
Create Table Operator:
name:default.nzhang_CTAS1_n1
- Stage-2
- Dependency Collection{}
- Stage-1
- Reducer 3 llap
- File Output Operator [FS_8]
- table:{"name:":"default.nzhang_CTAS1_n1"}
- Limit [LIM_7] (rows=10 width=178)
- Number of rows:10
- Select Operator [SEL_6] (rows=10 width=178)
- Output:["_col0","_col1"]
- <-Reducer 2 [SIMPLE_EDGE] llap
- SHUFFLE [RS_5]
- Limit [LIM_4] (rows=10 width=178)
- Number of rows:10
- Select Operator [SEL_3] (rows=500 width=178)
- Output:["_col0","_col1"]
- <-Map 1 [SIMPLE_EDGE] llap
- SHUFFLE [RS_2]
- Select Operator [SEL_1] (rows=500 width=178)
- Output:["_col0","_col1"]
- TableScan [TS_0] (rows=500 width=178)
- default@src,src,Tbl:COMPLETE,Col:COMPLETE,Output:["key","value"]
Stage-0
Move Operator
+ Stage-1
+ Reducer 4 llap
+ File Output Operator [FS_17]
+ Group By Operator [GBY_15] (rows=1 width=880)
+ Output:["_col0","_col1"],aggregations:["compute_stats(VALUE._col0, 'hll')","compute_stats(VALUE._col2, 'hll')"]
+ <-Reducer 3 [CUSTOM_SIMPLE_EDGE] llap
+ File Output Operator [FS_8]
+ table:{"name:":"default.nzhang_CTAS1_n1"}
+ Limit [LIM_7] (rows=10 width=178)
+ Number of rows:10
+ Select Operator [SEL_6] (rows=10 width=178)
+ Output:["_col0","_col1"]
+ <-Reducer 2 [SIMPLE_EDGE] llap
+ SHUFFLE [RS_5]
+ Limit [LIM_4] (rows=10 width=178)
+ Number of rows:10
+ Select Operator [SEL_3] (rows=500 width=178)
+ Output:["_col0","_col1"]
+ <-Map 1 [SIMPLE_EDGE] llap
+ SHUFFLE [RS_2]
+ Select Operator [SEL_1] (rows=500 width=178)
+ Output:["_col0","_col1"]
+ TableScan [TS_0] (rows=500 width=178)
+ default@src,src,Tbl:COMPLETE,Col:COMPLETE,Output:["key","value"]
+ PARTITION_ONLY_SHUFFLE [RS_14]
+ Select Operator [SEL_13] (rows=10 width=178)
+ Output:["col1","col2"]
+ Please refer to the previous Limit [LIM_7]
+ Stage-2
+ Dependency Collection{}
Please refer to the previous Stage-1
PREHOOK: query: create table nzhang_CTAS1_n1 as select key k, value from src sort by k, value limit 10
@@ -3708,36 +3719,45 @@ Plan not optimized by CBO because the statement has sort by
Vertex dependency in root stage
Reducer 2 <- Map 1 (SIMPLE_EDGE)
Reducer 3 <- Reducer 2 (SIMPLE_EDGE)
+Reducer 4 <- Reducer 3 (CUSTOM_SIMPLE_EDGE)
Stage-3
Stats Work{}
Stage-4
Create Table Operator:
name:default.nzhang_ctas3_n1
- Stage-2
- Dependency Collection{}
- Stage-1
- Reducer 3 llap
- File Output Operator [FS_8]
- table:{"name:":"default.nzhang_ctas3_n1"}
- Limit [LIM_7] (rows=10 width=192)
- Number of rows:10
- Select Operator [SEL_6] (rows=10 width=192)
- Output:["_col0","_col1"]
- <-Reducer 2 [SIMPLE_EDGE] llap
- SHUFFLE [RS_5]
- Limit [LIM_4] (rows=10 width=192)
- Number of rows:10
- Select Operator [SEL_3] (rows=500 width=192)
- Output:["_col0","_col1"]
- <-Map 1 [SIMPLE_EDGE] llap
- SHUFFLE [RS_2]
- Select Operator [SEL_1] (rows=500 width=192)
- Output:["_col0","_col1"]
- TableScan [TS_0] (rows=500 width=178)
- default@src,src,Tbl:COMPLETE,Col:COMPLETE,Output:["key","value"]
Stage-0
Move Operator
+ Stage-1
+ Reducer 4 llap
+ File Output Operator [FS_17]
+ Group By Operator [GBY_15] (rows=1 width=880)
+ Output:["_col0","_col1"],aggregations:["compute_stats(VALUE._col0, 'hll')","compute_stats(VALUE._col2, 'hll')"]
+ <-Reducer 3 [CUSTOM_SIMPLE_EDGE] llap
+ File Output Operator [FS_8]
+ table:{"name:":"default.nzhang_ctas3_n1"}
+ Limit [LIM_7] (rows=10 width=192)
+ Number of rows:10
+ Select Operator [SEL_6] (rows=10 width=192)
+ Output:["_col0","_col1"]
+ <-Reducer 2 [SIMPLE_EDGE] llap
+ SHUFFLE [RS_5]
+ Limit [LIM_4] (rows=10 width=192)
+ Number of rows:10
+ Select Operator [SEL_3] (rows=500 width=192)
+ Output:["_col0","_col1"]
+ <-Map 1 [SIMPLE_EDGE] llap
+ SHUFFLE [RS_2]
+ Select Operator [SEL_1] (rows=500 width=192)
+ Output:["_col0","_col1"]
+ TableScan [TS_0] (rows=500 width=178)
+ default@src,src,Tbl:COMPLETE,Col:COMPLETE,Output:["key","value"]
+ PARTITION_ONLY_SHUFFLE [RS_14]
+ Select Operator [SEL_13] (rows=10 width=192)
+ Output:["col1","col2"]
+ Please refer to the previous Limit [LIM_7]
+ Stage-2
+ Dependency Collection{}
Please refer to the previous Stage-1
PREHOOK: query: create table nzhang_ctas3_n1 row format serde "org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe" stored as RCFile as select key/2 half_key, concat(value, "_con") conb from src sort by half_key, conb limit 10
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/llap/insert1_overwrite_partitions.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/insert1_overwrite_partitions.q.out b/ql/src/test/results/clientpositive/llap/insert1_overwrite_partitions.q.out
index 9b35dbd..760dcb4 100644
--- a/ql/src/test/results/clientpositive/llap/insert1_overwrite_partitions.q.out
+++ b/ql/src/test/results/clientpositive/llap/insert1_overwrite_partitions.q.out
@@ -73,6 +73,7 @@ STAGE PLANS:
key expressions: _col0 (type: string), _col1 (type: string)
sort order: --
Statistics: Num rows: 99 Data size: 93448 Basic stats: PARTIAL Column stats: NONE
+ TopN Hash Memory Usage: 0.1
Execution mode: vectorized, llap
LLAP IO: no inputs
Reducer 2
@@ -268,6 +269,7 @@ STAGE PLANS:
key expressions: _col0 (type: string), _col1 (type: string)
sort order: --
Statistics: Num rows: 99 Data size: 93448 Basic stats: PARTIAL Column stats: NONE
+ TopN Hash Memory Usage: 0.1
Execution mode: vectorized, llap
LLAP IO: no inputs
Reducer 2
@@ -432,6 +434,7 @@ STAGE PLANS:
key expressions: _col0 (type: string), _col1 (type: string)
sort order: --
Statistics: Num rows: 99 Data size: 93448 Basic stats: PARTIAL Column stats: NONE
+ TopN Hash Memory Usage: 0.1
Execution mode: vectorized, llap
LLAP IO: no inputs
Reducer 2
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/llap/insert_into1.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/insert_into1.q.out b/ql/src/test/results/clientpositive/llap/insert_into1.q.out
index c203b6b..6d48df5 100644
--- a/ql/src/test/results/clientpositive/llap/insert_into1.q.out
+++ b/ql/src/test/results/clientpositive/llap/insert_into1.q.out
@@ -46,6 +46,7 @@ STAGE PLANS:
key expressions: _col0 (type: string)
sort order: +
Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
+ TopN Hash Memory Usage: 0.1
value expressions: _col1 (type: string)
Execution mode: vectorized, llap
LLAP IO: no inputs
@@ -209,6 +210,7 @@ STAGE PLANS:
key expressions: _col0 (type: string)
sort order: +
Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
+ TopN Hash Memory Usage: 0.1
value expressions: _col1 (type: string)
Execution mode: vectorized, llap
LLAP IO: no inputs
@@ -372,6 +374,7 @@ STAGE PLANS:
key expressions: _col0 (type: string)
sort order: +
Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
+ TopN Hash Memory Usage: 0.1
value expressions: _col1 (type: string)
Execution mode: vectorized, llap
LLAP IO: no inputs
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/llap/insert_into2.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/insert_into2.q.out b/ql/src/test/results/clientpositive/llap/insert_into2.q.out
index 69264f0..10609d3 100644
--- a/ql/src/test/results/clientpositive/llap/insert_into2.q.out
+++ b/ql/src/test/results/clientpositive/llap/insert_into2.q.out
@@ -50,6 +50,7 @@ STAGE PLANS:
key expressions: _col0 (type: string)
sort order: +
Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
+ TopN Hash Memory Usage: 0.1
value expressions: _col1 (type: string)
Execution mode: vectorized, llap
LLAP IO: no inputs
@@ -266,6 +267,7 @@ STAGE PLANS:
key expressions: _col0 (type: string)
sort order: +
Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
+ TopN Hash Memory Usage: 0.1
value expressions: _col1 (type: string)
Execution mode: vectorized, llap
LLAP IO: no inputs
@@ -447,6 +449,7 @@ STAGE PLANS:
key expressions: _col0 (type: string)
sort order: +
Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
+ TopN Hash Memory Usage: 0.1
value expressions: _col1 (type: string)
Execution mode: vectorized, llap
LLAP IO: no inputs
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/llap/insert_into_default_keyword.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/insert_into_default_keyword.q.out b/ql/src/test/results/clientpositive/llap/insert_into_default_keyword.q.out
index 79b8fb4..faaf8ad 100644
--- a/ql/src/test/results/clientpositive/llap/insert_into_default_keyword.q.out
+++ b/ql/src/test/results/clientpositive/llap/insert_into_default_keyword.q.out
@@ -2949,26 +2949,6 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.merge_tmp_table
- Select Operator
- expressions: _col0 (type: int)
- outputColumnNames: val
- Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE
- Group By Operator
- aggregations: compute_stats(val, 'hll')
- mode: complete
- outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 424 Basic stats: COMPLETE Column stats: COMPLETE
- Select Operator
- expressions: _col0 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>)
- outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 424 Basic stats: COMPLETE Column stats: COMPLETE
- File Output Operator
- compressed: false
- Statistics: Num rows: 1 Data size: 424 Basic stats: COMPLETE Column stats: COMPLETE
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
Reducer 6
Execution mode: llap
Reduce Operator Tree:
@@ -3060,10 +3040,6 @@ STAGE PLANS:
Stage: Stage-8
Stats Work
Basic Stats Work:
- Column Stats Desc:
- Columns: val
- Column Types: int
- Table: default.merge_tmp_table
Stage: Stage-1
Move Operator
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/llap/lineage2.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/lineage2.q.out b/ql/src/test/results/clientpositive/llap/lineage2.q.out
index 1cb0cc7..8f266f8 100644
--- a/ql/src/test/results/clientpositive/llap/lineage2.q.out
+++ b/ql/src/test/results/clientpositive/llap/lineage2.q.out
@@ -5,7 +5,7 @@ PREHOOK: type: CREATETABLE_AS_SELECT
PREHOOK: Input: default@src1
PREHOOK: Output: database:default
PREHOOK: Output: default@src2
-{"version":"1.0","engine":"tez","database":"default","hash":"87921246fb098d44c05e0ccd9ecb0676","queryText":"create table src2 as select key key2, value value2 from src1","edges":[{"sources":[2],"targets":[0],"edgeType":"PROJECTION"},{"sources":[3],"targets":[1],"edgeType":"PROJECTION"}],"vertices":[{"id":0,"vertexType":"COLUMN","vertexId":"default.src2.key2"},{"id":1,"vertexType":"COLUMN","vertexId":"default.src2.value2"},{"id":2,"vertexType":"COLUMN","vertexId":"default.src1.key"},{"id":3,"vertexType":"COLUMN","vertexId":"default.src1.value"}]}
+{"version":"1.0","engine":"tez","database":"default","hash":"87921246fb098d44c05e0ccd9ecb0676","queryText":"create table src2 as select key key2, value value2 from src1","edges":[{"sources":[2],"targets":[0],"edgeType":"PROJECTION"},{"sources":[3],"targets":[1],"edgeType":"PROJECTION"},{"sources":[2],"targets":[0],"expression":"compute_stats(default.src1.key, 'hll')","edgeType":"PROJECTION"},{"sources":[3],"targets":[1],"expression":"compute_stats(default.src1.value, 'hll')","edgeType":"PROJECTION"}],"vertices":[{"id":0,"vertexType":"COLUMN","vertexId":"default.src2.key2"},{"id":1,"vertexType":"COLUMN","vertexId":"default.src2.value2"},{"id":2,"vertexType":"COLUMN","vertexId":"default.src1.key"},{"id":3,"vertexType":"COLUMN","vertexId":"default.src1.value"}]}
PREHOOK: query: select * from src1 where key is not null and value is not null limit 3
PREHOOK: type: QUERY
PREHOOK: Input: default@src1
@@ -31,7 +31,7 @@ PREHOOK: type: CREATETABLE_AS_SELECT
PREHOOK: Input: default@src1
PREHOOK: Output: database:default
PREHOOK: Output: default@dest1_n56
-{"version":"1.0","engine":"tez","database":"default","hash":"01251b1a2a539f7bb1d533cf6a9de47d","queryText":"create table dest1_n56 as select * from src1","edges":[{"sources":[2],"targets":[0],"edgeType":"PROJECTION"},{"sources":[3],"targets":[1],"edgeType":"PROJECTION"}],"vertices":[{"id":0,"vertexType":"COLUMN","vertexId":"default.dest1_n56.key"},{"id":1,"vertexType":"COLUMN","vertexId":"default.dest1_n56.value"},{"id":2,"vertexType":"COLUMN","vertexId":"default.src1.key"},{"id":3,"vertexType":"COLUMN","vertexId":"default.src1.value"}]}
+{"version":"1.0","engine":"tez","database":"default","hash":"01251b1a2a539f7bb1d533cf6a9de47d","queryText":"create table dest1_n56 as select * from src1","edges":[{"sources":[2],"targets":[0],"edgeType":"PROJECTION"},{"sources":[3],"targets":[1],"edgeType":"PROJECTION"},{"sources":[2],"targets":[0],"expression":"compute_stats(default.src1.key, 'hll')","edgeType":"PROJECTION"},{"sources":[3],"targets":[1],"expression":"compute_stats(default.src1.value, 'hll')","edgeType":"PROJECTION"}],"vertices":[{"id":0,"vertexType":"COLUMN","vertexId":"default.dest1_n56.key"},{"id":1,"vertexType":"COLUMN","vertexId":"default.dest1_n56.value"},{"id":2,"vertexType":"COLUMN","vertexId":"default.src1.key"},{"id":3,"vertexType":"COLUMN","vertexId":"default.src1.value"}]}
PREHOOK: query: insert into table dest1_n56 select * from src2
PREHOOK: type: QUERY
PREHOOK: Input: default@src2
@@ -461,7 +461,7 @@ PREHOOK: Input: default@src1
PREHOOK: Input: default@src2
PREHOOK: Output: database:default
PREHOOK: Output: default@dest2_n11
-{"version":"1.0","engine":"tez","database":"default","hash":"7e2a275cdee3a519d901b7b178eefcd7","queryText":"create table dest2_n11 as select * from src1 JOIN src2 ON src1.key = src2.key2","edges":[{"sources":[4],"targets":[0],"edgeType":"PROJECTION"},{"sources":[5],"targets":[1],"edgeType":"PROJECTION"},{"sources":[6],"targets":[2],"edgeType":"PROJECTION"},{"sources":[7],"targets":[3],"edgeType":"PROJECTION"},{"sources":[4],"targets":[0,1,2,3],"expression":"src1.key is not null","edgeType":"PREDICATE"},{"sources":[4,6],"targets":[0,1,2,3],"expression":"(src1.key = src2.key2)","edgeType":"PREDICATE"},{"sources":[6],"targets":[0,1,2,3],"expression":"src2.key2 is not null","edgeType":"PREDICATE"}],"vertices":[{"id":0,"vertexType":"COLUMN","vertexId":"default.dest2_n11.key"},{"id":1,"vertexType":"COLUMN","vertexId":"default.dest2_n11.value"},{"id":2,"vertexType":"COLUMN","vertexId":"default.dest2_n11.key2"},{"id":3,"vertexType":"COLUMN","vertexId":"default.dest2_n11.value2"},{"id":4,"ve
rtexType":"COLUMN","vertexId":"default.src1.key"},{"id":5,"vertexType":"COLUMN","vertexId":"default.src1.value"},{"id":6,"vertexType":"COLUMN","vertexId":"default.src2.key2"},{"id":7,"vertexType":"COLUMN","vertexId":"default.src2.value2"}]}
+{"version":"1.0","engine":"tez","database":"default","hash":"7e2a275cdee3a519d901b7b178eefcd7","queryText":"create table dest2_n11 as select * from src1 JOIN src2 ON src1.key = src2.key2","edges":[{"sources":[4],"targets":[0],"edgeType":"PROJECTION"},{"sources":[5],"targets":[1],"edgeType":"PROJECTION"},{"sources":[6],"targets":[2],"edgeType":"PROJECTION"},{"sources":[7],"targets":[3],"edgeType":"PROJECTION"},{"sources":[4],"targets":[0,1,2,3],"expression":"src1.key is not null","edgeType":"PREDICATE"},{"sources":[4,6],"targets":[0,1,2,3],"expression":"(src1.key = src2.key2)","edgeType":"PREDICATE"},{"sources":[6],"targets":[0,1,2,3],"expression":"src2.key2 is not null","edgeType":"PREDICATE"},{"sources":[4],"targets":[0],"expression":"compute_stats(default.src1.key, 'hll')","edgeType":"PROJECTION"},{"sources":[5],"targets":[1],"expression":"compute_stats(default.src1.value, 'hll')","edgeType":"PROJECTION"},{"sources":[6],"targets":[2],"expression":"compute_stats(default.src2.key2,
'hll')","edgeType":"PROJECTION"},{"sources":[7],"targets":[3],"expression":"compute_stats(default.src2.value2, 'hll')","edgeType":"PROJECTION"}],"vertices":[{"id":0,"vertexType":"COLUMN","vertexId":"default.dest2_n11.key"},{"id":1,"vertexType":"COLUMN","vertexId":"default.dest2_n11.value"},{"id":2,"vertexType":"COLUMN","vertexId":"default.dest2_n11.key2"},{"id":3,"vertexType":"COLUMN","vertexId":"default.dest2_n11.value2"},{"id":4,"vertexType":"COLUMN","vertexId":"default.src1.key"},{"id":5,"vertexType":"COLUMN","vertexId":"default.src1.value"},{"id":6,"vertexType":"COLUMN","vertexId":"default.src2.key2"},{"id":7,"vertexType":"COLUMN","vertexId":"default.src2.value2"}]}
PREHOOK: query: insert overwrite table dest2_n11 select * from src1 JOIN src2 ON src1.key = src2.key2
PREHOOK: type: QUERY
PREHOOK: Input: default@src1
@@ -523,7 +523,7 @@ PREHOOK: Input: default@src1
PREHOOK: Input: default@src2
PREHOOK: Output: database:default
PREHOOK: Output: default@dest3_n0
-{"version":"1.0","engine":"tez","database":"default","hash":"04c85db3424d79a3663c0532bc1e0a35","queryText":"create table dest3_n0 as\n select * from src1 JOIN src2 ON src1.key = src2.key2 WHERE length(key) > 1","edges":[{"sources":[4],"targets":[0],"edgeType":"PROJECTION"},{"sources":[5],"targets":[1],"edgeType":"PROJECTION"},{"sources":[6],"targets":[2],"edgeType":"PROJECTION"},{"sources":[7],"targets":[3],"edgeType":"PROJECTION"},{"sources":[4],"targets":[0,1,2,3],"expression":"((length(src1.key) > 1) and src1.key is not null)","edgeType":"PREDICATE"},{"sources":[4,6],"targets":[0,1,2,3],"expression":"(src1.key = src2.key2)","edgeType":"PREDICATE"},{"sources":[6],"targets":[0,1,2,3],"expression":"((length(src2.key2) > 1) and src2.key2 is not null)","edgeType":"PREDICATE"}],"vertices":[{"id":0,"vertexType":"COLUMN","vertexId":"default.dest3_n0.key"},{"id":1,"vertexType":"COLUMN","vertexId":"default.dest3_n0.value"},{"id":2,"vertexType":"COLUMN","vertexId":"default.dest3_n0.key2"},
{"id":3,"vertexType":"COLUMN","vertexId":"default.dest3_n0.value2"},{"id":4,"vertexType":"COLUMN","vertexId":"default.src1.key"},{"id":5,"vertexType":"COLUMN","vertexId":"default.src1.value"},{"id":6,"vertexType":"COLUMN","vertexId":"default.src2.key2"},{"id":7,"vertexType":"COLUMN","vertexId":"default.src2.value2"}]}
+{"version":"1.0","engine":"tez","database":"default","hash":"04c85db3424d79a3663c0532bc1e0a35","queryText":"create table dest3_n0 as\n select * from src1 JOIN src2 ON src1.key = src2.key2 WHERE length(key) > 1","edges":[{"sources":[4],"targets":[0],"edgeType":"PROJECTION"},{"sources":[5],"targets":[1],"edgeType":"PROJECTION"},{"sources":[6],"targets":[2],"edgeType":"PROJECTION"},{"sources":[7],"targets":[3],"edgeType":"PROJECTION"},{"sources":[4],"targets":[0,1,2,3],"expression":"((length(src1.key) > 1) and src1.key is not null)","edgeType":"PREDICATE"},{"sources":[4,6],"targets":[0,1,2,3],"expression":"(src1.key = src2.key2)","edgeType":"PREDICATE"},{"sources":[6],"targets":[0,1,2,3],"expression":"((length(src2.key2) > 1) and src2.key2 is not null)","edgeType":"PREDICATE"},{"sources":[4],"targets":[0],"expression":"compute_stats(default.src1.key, 'hll')","edgeType":"PROJECTION"},{"sources":[5],"targets":[1],"expression":"compute_stats(default.src1.value, 'hll')","edgeType":"PROJEC
TION"},{"sources":[6],"targets":[2],"expression":"compute_stats(default.src2.key2, 'hll')","edgeType":"PROJECTION"},{"sources":[7],"targets":[3],"expression":"compute_stats(default.src2.value2, 'hll')","edgeType":"PROJECTION"}],"vertices":[{"id":0,"vertexType":"COLUMN","vertexId":"default.dest3_n0.key"},{"id":1,"vertexType":"COLUMN","vertexId":"default.dest3_n0.value"},{"id":2,"vertexType":"COLUMN","vertexId":"default.dest3_n0.key2"},{"id":3,"vertexType":"COLUMN","vertexId":"default.dest3_n0.value2"},{"id":4,"vertexType":"COLUMN","vertexId":"default.src1.key"},{"id":5,"vertexType":"COLUMN","vertexId":"default.src1.value"},{"id":6,"vertexType":"COLUMN","vertexId":"default.src2.key2"},{"id":7,"vertexType":"COLUMN","vertexId":"default.src2.value2"}]}
PREHOOK: query: insert overwrite table dest2_n11
select * from src1 JOIN src2 ON src1.key = src2.key2 WHERE length(key) > 3
PREHOOK: type: QUERY
@@ -659,7 +659,7 @@ PREHOOK: Input: default@dest_l2
PREHOOK: Input: default@dest_l3
PREHOOK: Output: database:default
PREHOOK: Output: default@t_n10
-{"version":"1.0","engine":"tez","database":"default","hash":"1a18373814a0ccf82ee1409db6a912b5","queryText":"create table t_n10 as\nselect distinct a.c2, a.c3 from dest_l2 a\ninner join dest_l3 b on (a.id = b.id)\nwhere a.id > 0 and b.c3 = 15","edges":[{"sources":[2],"targets":[0],"edgeType":"PROJECTION"},{"sources":[3],"targets":[1],"edgeType":"PROJECTION"},{"sources":[4],"targets":[0,1],"expression":"(a.id > 0)","edgeType":"PREDICATE"},{"sources":[4,5],"targets":[0,1],"expression":"(a.id = b.id)","edgeType":"PREDICATE"},{"sources":[6,5],"targets":[0,1],"expression":"((b.c3 = 15) and (b.id > 0))","edgeType":"PREDICATE"}],"vertices":[{"id":0,"vertexType":"COLUMN","vertexId":"default.t_n10.c2"},{"id":1,"vertexType":"COLUMN","vertexId":"default.t_n10.c3"},{"id":2,"vertexType":"COLUMN","vertexId":"default.dest_l2.c2"},{"id":3,"vertexType":"COLUMN","vertexId":"default.dest_l2.c3"},{"id":4,"vertexType":"COLUMN","vertexId":"default.dest_l2.id"},{"id":5,"vertexType":"COLUMN","vertexId":"def
ault.dest_l3.id"},{"id":6,"vertexType":"COLUMN","vertexId":"default.dest_l3.c3"}]}
+{"version":"1.0","engine":"tez","database":"default","hash":"1a18373814a0ccf82ee1409db6a912b5","queryText":"create table t_n10 as\nselect distinct a.c2, a.c3 from dest_l2 a\ninner join dest_l3 b on (a.id = b.id)\nwhere a.id > 0 and b.c3 = 15","edges":[{"sources":[2],"targets":[0],"edgeType":"PROJECTION"},{"sources":[3],"targets":[1],"edgeType":"PROJECTION"},{"sources":[4],"targets":[0,1],"expression":"(a.id > 0)","edgeType":"PREDICATE"},{"sources":[4,5],"targets":[0,1],"expression":"(a.id = b.id)","edgeType":"PREDICATE"},{"sources":[6,5],"targets":[0,1],"expression":"((b.c3 = 15) and (b.id > 0))","edgeType":"PREDICATE"},{"sources":[2],"targets":[0],"expression":"compute_stats(default.dest_l2.c2, 'hll')","edgeType":"PROJECTION"},{"sources":[3],"targets":[1],"expression":"compute_stats(default.dest_l2.c3, 'hll')","edgeType":"PROJECTION"}],"vertices":[{"id":0,"vertexType":"COLUMN","vertexId":"default.t_n10.c2"},{"id":1,"vertexType":"COLUMN","vertexId":"default.t_n10.c3"},{"id":2,"verte
xType":"COLUMN","vertexId":"default.dest_l2.c2"},{"id":3,"vertexType":"COLUMN","vertexId":"default.dest_l2.c3"},{"id":4,"vertexType":"COLUMN","vertexId":"default.dest_l2.id"},{"id":5,"vertexType":"COLUMN","vertexId":"default.dest_l3.id"},{"id":6,"vertexType":"COLUMN","vertexId":"default.dest_l3.c3"}]}
PREHOOK: query: SELECT substr(src1.key,1,1), count(DISTINCT substr(src1.value,5)),
concat(substr(src1.key,1,1),sum(substr(src1.value,5)))
from src1
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/llap/lineage3.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/lineage3.q.out b/ql/src/test/results/clientpositive/llap/lineage3.q.out
index bfd82cd..11e6904 100644
--- a/ql/src/test/results/clientpositive/llap/lineage3.q.out
+++ b/ql/src/test/results/clientpositive/llap/lineage3.q.out
@@ -36,7 +36,7 @@ PREHOOK: type: CREATETABLE_AS_SELECT
PREHOOK: Input: default@src1
PREHOOK: Output: database:default
PREHOOK: Output: default@t_n20
-{"version":"1.0","engine":"tez","database":"default","hash":"5a2daa3d8508025880412b524351c849","queryText":"create table t_n20 as\nselect * from\n (select * from\n (select key from src1 limit 1) v1) v2","edges":[{"sources":[1],"targets":[0],"edgeType":"PROJECTION"}],"vertices":[{"id":0,"vertexType":"COLUMN","vertexId":"default.t_n20.key"},{"id":1,"vertexType":"COLUMN","vertexId":"default.src1.key"}]}
+{"version":"1.0","engine":"tez","database":"default","hash":"5a2daa3d8508025880412b524351c849","queryText":"create table t_n20 as\nselect * from\n (select * from\n (select key from src1 limit 1) v1) v2","edges":[{"sources":[1],"targets":[0],"edgeType":"PROJECTION"},{"sources":[1],"targets":[0],"expression":"compute_stats(default.src1.key, 'hll')","edgeType":"PROJECTION"}],"vertices":[{"id":0,"vertexType":"COLUMN","vertexId":"default.t_n20.key"},{"id":1,"vertexType":"COLUMN","vertexId":"default.src1.key"}]}
PREHOOK: query: drop table if exists dest_l1_n2
PREHOOK: type: DROPTABLE
PREHOOK: query: create table dest_l1_n2(a int, b varchar(128))
[08/35] hive git commit: HIVE-16957: Support CTAS for auto gather
column stats (Jesus Camacho Rodriguez, reviewed by Ashutosh Chauhan)
Posted by jc...@apache.org.
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/llap/vector_join_filters.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/vector_join_filters.q.out b/ql/src/test/results/clientpositive/llap/vector_join_filters.q.out
index def06a5..a86df68 100644
--- a/ql/src/test/results/clientpositive/llap/vector_join_filters.q.out
+++ b/ql/src/test/results/clientpositive/llap/vector_join_filters.q.out
@@ -79,7 +79,7 @@ STAGE PLANS:
TableScan
alias: a
filterExpr: ((key > 40) and (value > 50) and (key = value)) (type: boolean)
- Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
Filter Operator
@@ -87,21 +87,21 @@ STAGE PLANS:
className: VectorFilterOperator
native: true
predicate: ((key = value) and (key > 40) and (value > 50)) (type: boolean)
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: key (type: int), value (type: int)
outputColumnNames: _col0, _col1
Select Vectorization:
className: VectorSelectOperator
native: true
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
Reduce Sink Vectorization:
className: VectorReduceSinkEmptyKeyOperator
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: int), _col1 (type: int)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -118,7 +118,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: b
- Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
Select Operator
@@ -128,7 +128,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
selectExpressions: VectorUDFAdaptor(((key > 40) and (value > 50) and (key = value)))(children: LongColGreaterLongScalar(col 0:int, val 40) -> 3:boolean, LongColGreaterLongScalar(col 1:int, val 50) -> 4:boolean, LongColEqualLongColumn(col 0:int, col 1:int) -> 5:boolean) -> 6:boolean
- Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE
Map Join Operator
condition map:
Right Outer Join 0 to 1
@@ -146,7 +146,7 @@ STAGE PLANS:
outputColumnNames: _col0, _col1, _col2, _col3
input vertices:
0 Map 1
- Statistics: Num rows: 4 Data size: 68 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: hash(_col0,_col1,_col2,_col3) (type: int)
outputColumnNames: _col0
@@ -154,7 +154,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
selectExpressions: VectorUDFAdaptor(hash(_col0,_col1,_col2,_col3)) -> 4:int
- Statistics: Num rows: 4 Data size: 68 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: sum(_col0)
Group By Vectorization:
@@ -164,14 +164,14 @@ STAGE PLANS:
vectorProcessingMode: HASH
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
Reduce Sink Vectorization:
className: VectorReduceSinkEmptyKeyOperator
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: bigint)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -202,13 +202,13 @@ STAGE PLANS:
vectorProcessingMode: GLOBAL
mode: mergepartial
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -324,7 +324,7 @@ STAGE PLANS:
TableScan
alias: a
filterExpr: ((key > 40) and (value > 50) and (key = value)) (type: boolean)
- Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
Filter Operator
@@ -332,14 +332,14 @@ STAGE PLANS:
className: VectorFilterOperator
native: true
predicate: ((key = value) and (key > 40) and (value > 50)) (type: boolean)
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: key (type: int), value (type: int)
outputColumnNames: _col0, _col1
Select Vectorization:
className: VectorSelectOperator
native: true
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
@@ -348,7 +348,7 @@ STAGE PLANS:
className: VectorReduceSinkLongOperator
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: int)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -365,7 +365,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: b
- Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
Select Operator
@@ -375,7 +375,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
selectExpressions: LongColGreaterLongScalar(col 0:int, val 40) -> 3:boolean, LongColGreaterLongScalar(col 1:int, val 50) -> 4:boolean, LongColEqualLongColumn(col 0:int, col 1:int) -> 5:boolean
- Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4 Data size: 80 Basic stats: COMPLETE Column stats: COMPLETE
Map Join Operator
condition map:
Right Outer Join 0 to 1
@@ -392,7 +392,7 @@ STAGE PLANS:
outputColumnNames: _col0, _col1, _col2, _col3
input vertices:
0 Map 1
- Statistics: Num rows: 4 Data size: 35 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 56 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: hash(_col0,_col1,_col2,_col3) (type: int)
outputColumnNames: _col0
@@ -400,7 +400,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
selectExpressions: VectorUDFAdaptor(hash(_col0,_col1,_col2,_col3)) -> 8:int
- Statistics: Num rows: 4 Data size: 35 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 56 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: sum(_col0)
Group By Vectorization:
@@ -410,14 +410,14 @@ STAGE PLANS:
vectorProcessingMode: HASH
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
Reduce Sink Vectorization:
className: VectorReduceSinkEmptyKeyOperator
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: bigint)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -448,13 +448,13 @@ STAGE PLANS:
vectorProcessingMode: GLOBAL
mode: mergepartial
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -498,7 +498,7 @@ STAGE PLANS:
TableScan
alias: a
filterExpr: ((key > 40) and (value > 50) and (key = value)) (type: boolean)
- Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
Filter Operator
@@ -506,14 +506,14 @@ STAGE PLANS:
className: VectorFilterOperator
native: true
predicate: ((key = value) and (key > 40) and (value > 50)) (type: boolean)
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: key (type: int), value (type: int)
outputColumnNames: _col0, _col1
Select Vectorization:
className: VectorSelectOperator
native: true
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
@@ -522,7 +522,7 @@ STAGE PLANS:
className: VectorReduceSinkLongOperator
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: int)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -539,7 +539,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: b
- Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
Select Operator
@@ -549,7 +549,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
selectExpressions: LongColGreaterLongScalar(col 0:int, val 40) -> 3:boolean, LongColGreaterLongScalar(col 1:int, val 50) -> 4:boolean, LongColEqualLongColumn(col 0:int, col 1:int) -> 5:boolean
- Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4 Data size: 80 Basic stats: COMPLETE Column stats: COMPLETE
Map Join Operator
condition map:
Right Outer Join 0 to 1
@@ -566,7 +566,7 @@ STAGE PLANS:
outputColumnNames: _col0, _col1, _col2, _col3
input vertices:
0 Map 1
- Statistics: Num rows: 4 Data size: 35 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 56 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: hash(_col0,_col1,_col2,_col3) (type: int)
outputColumnNames: _col0
@@ -574,7 +574,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
selectExpressions: VectorUDFAdaptor(hash(_col0,_col1,_col2,_col3)) -> 8:int
- Statistics: Num rows: 4 Data size: 35 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 56 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: sum(_col0)
Group By Vectorization:
@@ -584,14 +584,14 @@ STAGE PLANS:
vectorProcessingMode: HASH
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
Reduce Sink Vectorization:
className: VectorReduceSinkEmptyKeyOperator
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: bigint)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -622,13 +622,13 @@ STAGE PLANS:
vectorProcessingMode: GLOBAL
mode: mergepartial
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -672,7 +672,7 @@ STAGE PLANS:
TableScan
alias: a
filterExpr: ((key > 40) and (value > 50) and (key = value)) (type: boolean)
- Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
Filter Operator
@@ -680,14 +680,14 @@ STAGE PLANS:
className: VectorFilterOperator
native: true
predicate: ((key = value) and (key > 40) and (value > 50)) (type: boolean)
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: key (type: int), value (type: int)
outputColumnNames: _col0, _col1
Select Vectorization:
className: VectorSelectOperator
native: true
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col1 (type: int)
sort order: +
@@ -696,7 +696,7 @@ STAGE PLANS:
className: VectorReduceSinkLongOperator
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: int)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -713,7 +713,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: b
- Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
Select Operator
@@ -723,7 +723,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
selectExpressions: LongColGreaterLongScalar(col 0:int, val 40) -> 3:boolean, LongColGreaterLongScalar(col 1:int, val 50) -> 4:boolean, LongColEqualLongColumn(col 0:int, col 1:int) -> 5:boolean
- Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4 Data size: 80 Basic stats: COMPLETE Column stats: COMPLETE
Map Join Operator
condition map:
Right Outer Join 0 to 1
@@ -740,7 +740,7 @@ STAGE PLANS:
outputColumnNames: _col0, _col1, _col2, _col3
input vertices:
0 Map 1
- Statistics: Num rows: 4 Data size: 35 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 56 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: hash(_col0,_col1,_col2,_col3) (type: int)
outputColumnNames: _col0
@@ -748,7 +748,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
selectExpressions: VectorUDFAdaptor(hash(_col0,_col1,_col2,_col3)) -> 8:int
- Statistics: Num rows: 4 Data size: 35 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 56 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: sum(_col0)
Group By Vectorization:
@@ -758,14 +758,14 @@ STAGE PLANS:
vectorProcessingMode: HASH
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
Reduce Sink Vectorization:
className: VectorReduceSinkEmptyKeyOperator
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: bigint)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -796,13 +796,13 @@ STAGE PLANS:
vectorProcessingMode: GLOBAL
mode: mergepartial
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -846,7 +846,7 @@ STAGE PLANS:
TableScan
alias: a
filterExpr: ((key > 40) and (value > 50) and (key = value)) (type: boolean)
- Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
Filter Operator
@@ -854,14 +854,14 @@ STAGE PLANS:
className: VectorFilterOperator
native: true
predicate: ((key = value) and (key > 40) and (value > 50)) (type: boolean)
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: key (type: int), value (type: int)
outputColumnNames: _col0, _col1
Select Vectorization:
className: VectorSelectOperator
native: true
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int), _col1 (type: int)
sort order: ++
@@ -870,7 +870,7 @@ STAGE PLANS:
className: VectorReduceSinkMultiKeyOperator
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized, llap
LLAP IO: all inputs
Map Vectorization:
@@ -886,7 +886,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: b
- Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
Select Operator
@@ -896,7 +896,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
selectExpressions: LongColGreaterLongScalar(col 0:int, val 40) -> 3:boolean, LongColGreaterLongScalar(col 1:int, val 50) -> 4:boolean, LongColEqualLongColumn(col 0:int, col 1:int) -> 5:boolean
- Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4 Data size: 80 Basic stats: COMPLETE Column stats: COMPLETE
Map Join Operator
condition map:
Right Outer Join 0 to 1
@@ -913,7 +913,7 @@ STAGE PLANS:
outputColumnNames: _col0, _col1, _col2, _col3
input vertices:
0 Map 1
- Statistics: Num rows: 4 Data size: 35 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 56 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: hash(_col0,_col1,_col2,_col3) (type: int)
outputColumnNames: _col0
@@ -921,7 +921,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
selectExpressions: VectorUDFAdaptor(hash(_col0,_col1,_col2,_col3)) -> 8:int
- Statistics: Num rows: 4 Data size: 35 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 56 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: sum(_col0)
Group By Vectorization:
@@ -931,14 +931,14 @@ STAGE PLANS:
vectorProcessingMode: HASH
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
Reduce Sink Vectorization:
className: VectorReduceSinkEmptyKeyOperator
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: bigint)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -969,13 +969,13 @@ STAGE PLANS:
vectorProcessingMode: GLOBAL
mode: mergepartial
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/llap/vector_join_nulls.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/vector_join_nulls.q.out b/ql/src/test/results/clientpositive/llap/vector_join_nulls.q.out
index 67108fe..ae5879e 100644
--- a/ql/src/test/results/clientpositive/llap/vector_join_nulls.q.out
+++ b/ql/src/test/results/clientpositive/llap/vector_join_nulls.q.out
@@ -78,7 +78,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: a
- Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
Select Operator
@@ -87,14 +87,14 @@ STAGE PLANS:
Select Vectorization:
className: VectorSelectOperator
native: true
- Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
Reduce Sink Vectorization:
className: VectorReduceSinkEmptyKeyOperator
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: int), _col1 (type: int)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -111,7 +111,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: b
- Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
Select Operator
@@ -120,7 +120,7 @@ STAGE PLANS:
Select Vectorization:
className: VectorSelectOperator
native: true
- Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE
Map Join Operator
condition map:
Right Outer Join 0 to 1
@@ -138,7 +138,7 @@ STAGE PLANS:
outputColumnNames: _col0, _col1, _col2, _col3
input vertices:
0 Map 1
- Statistics: Num rows: 9 Data size: 153 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 9 Data size: 144 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: hash(_col0,_col1,_col2,_col3) (type: int)
outputColumnNames: _col0
@@ -146,7 +146,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
selectExpressions: VectorUDFAdaptor(hash(_col0,_col1,_col2,_col3)) -> 4:int
- Statistics: Num rows: 9 Data size: 153 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 9 Data size: 144 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: sum(_col0)
Group By Vectorization:
@@ -156,14 +156,14 @@ STAGE PLANS:
vectorProcessingMode: HASH
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
Reduce Sink Vectorization:
className: VectorReduceSinkEmptyKeyOperator
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: bigint)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -194,13 +194,13 @@ STAGE PLANS:
vectorProcessingMode: GLOBAL
mode: mergepartial
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -315,7 +315,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: a
- Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
Select Operator
@@ -324,7 +324,7 @@ STAGE PLANS:
Select Vectorization:
className: VectorSelectOperator
native: true
- Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
@@ -333,7 +333,7 @@ STAGE PLANS:
className: VectorReduceSinkLongOperator
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: int)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -350,7 +350,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: b
- Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
Select Operator
@@ -359,7 +359,7 @@ STAGE PLANS:
Select Vectorization:
className: VectorSelectOperator
native: true
- Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE
Map Join Operator
condition map:
Right Outer Join 0 to 1
@@ -373,7 +373,7 @@ STAGE PLANS:
outputColumnNames: _col0, _col1, _col2, _col3
input vertices:
0 Map 1
- Statistics: Num rows: 3 Data size: 26 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: hash(_col0,_col1,_col2,_col3) (type: int)
outputColumnNames: _col0
@@ -381,7 +381,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
selectExpressions: VectorUDFAdaptor(hash(_col0,_col1,_col2,_col3)) -> 5:int
- Statistics: Num rows: 3 Data size: 26 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: sum(_col0)
Group By Vectorization:
@@ -391,14 +391,14 @@ STAGE PLANS:
vectorProcessingMode: HASH
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
Reduce Sink Vectorization:
className: VectorReduceSinkEmptyKeyOperator
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: bigint)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -429,13 +429,13 @@ STAGE PLANS:
vectorProcessingMode: GLOBAL
mode: mergepartial
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -478,7 +478,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: a
- Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
Select Operator
@@ -487,7 +487,7 @@ STAGE PLANS:
Select Vectorization:
className: VectorSelectOperator
native: true
- Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
@@ -496,7 +496,7 @@ STAGE PLANS:
className: VectorReduceSinkLongOperator
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: int)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -513,7 +513,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: b
- Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
Select Operator
@@ -522,7 +522,7 @@ STAGE PLANS:
Select Vectorization:
className: VectorSelectOperator
native: true
- Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE
Map Join Operator
condition map:
Right Outer Join 0 to 1
@@ -536,7 +536,7 @@ STAGE PLANS:
outputColumnNames: _col0, _col1, _col2, _col3
input vertices:
0 Map 1
- Statistics: Num rows: 3 Data size: 26 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: hash(_col0,_col1,_col2,_col3) (type: int)
outputColumnNames: _col0
@@ -544,7 +544,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
selectExpressions: VectorUDFAdaptor(hash(_col0,_col1,_col2,_col3)) -> 5:int
- Statistics: Num rows: 3 Data size: 26 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: sum(_col0)
Group By Vectorization:
@@ -554,14 +554,14 @@ STAGE PLANS:
vectorProcessingMode: HASH
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
Reduce Sink Vectorization:
className: VectorReduceSinkEmptyKeyOperator
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: bigint)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -592,13 +592,13 @@ STAGE PLANS:
vectorProcessingMode: GLOBAL
mode: mergepartial
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -641,7 +641,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: a
- Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
Select Operator
@@ -650,7 +650,7 @@ STAGE PLANS:
Select Vectorization:
className: VectorSelectOperator
native: true
- Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col1 (type: int)
sort order: +
@@ -659,7 +659,7 @@ STAGE PLANS:
className: VectorReduceSinkLongOperator
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: int)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -676,7 +676,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: b
- Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
Select Operator
@@ -685,7 +685,7 @@ STAGE PLANS:
Select Vectorization:
className: VectorSelectOperator
native: true
- Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE
Map Join Operator
condition map:
Right Outer Join 0 to 1
@@ -699,7 +699,7 @@ STAGE PLANS:
outputColumnNames: _col0, _col1, _col2, _col3
input vertices:
0 Map 1
- Statistics: Num rows: 3 Data size: 26 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: hash(_col0,_col1,_col2,_col3) (type: int)
outputColumnNames: _col0
@@ -707,7 +707,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
selectExpressions: VectorUDFAdaptor(hash(_col0,_col1,_col2,_col3)) -> 5:int
- Statistics: Num rows: 3 Data size: 26 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: sum(_col0)
Group By Vectorization:
@@ -717,14 +717,14 @@ STAGE PLANS:
vectorProcessingMode: HASH
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
Reduce Sink Vectorization:
className: VectorReduceSinkEmptyKeyOperator
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: bigint)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -755,13 +755,13 @@ STAGE PLANS:
vectorProcessingMode: GLOBAL
mode: mergepartial
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -806,7 +806,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: a
- Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
Select Operator
@@ -815,7 +815,7 @@ STAGE PLANS:
Select Vectorization:
className: VectorSelectOperator
native: true
- Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int), _col1 (type: int)
sort order: ++
@@ -824,7 +824,7 @@ STAGE PLANS:
className: VectorReduceSinkMultiKeyOperator
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized, llap
LLAP IO: all inputs
Map Vectorization:
@@ -840,7 +840,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: b
- Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
Select Operator
@@ -849,7 +849,7 @@ STAGE PLANS:
Select Vectorization:
className: VectorSelectOperator
native: true
- Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE
Map Join Operator
condition map:
Right Outer Join 0 to 1
@@ -863,7 +863,7 @@ STAGE PLANS:
outputColumnNames: _col0, _col1, _col2, _col3
input vertices:
0 Map 1
- Statistics: Num rows: 3 Data size: 26 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: hash(_col0,_col1,_col2,_col3) (type: int)
outputColumnNames: _col0
@@ -871,7 +871,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
selectExpressions: VectorUDFAdaptor(hash(_col0,_col1,_col2,_col3)) -> 5:int
- Statistics: Num rows: 3 Data size: 26 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: sum(_col0)
Group By Vectorization:
@@ -881,14 +881,14 @@ STAGE PLANS:
vectorProcessingMode: HASH
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
Reduce Sink Vectorization:
className: VectorReduceSinkEmptyKeyOperator
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: bigint)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -919,13 +919,13 @@ STAGE PLANS:
vectorProcessingMode: GLOBAL
mode: mergepartial
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
[20/35] hive git commit: HIVE-16957: Support CTAS for auto gather
column stats (Jesus Camacho Rodriguez, reviewed by Ashutosh Chauhan)
Posted by jc...@apache.org.
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/llap/semijoin.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/semijoin.q.out b/ql/src/test/results/clientpositive/llap/semijoin.q.out
index 63a270e..00bc6ce 100644
--- a/ql/src/test/results/clientpositive/llap/semijoin.q.out
+++ b/ql/src/test/results/clientpositive/llap/semijoin.q.out
@@ -148,15 +148,15 @@ STAGE PLANS:
TableScan
alias: a
filterExpr: key is not null (type: boolean)
- Statistics: Num rows: 11 Data size: 2068 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 1023 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: key is not null (type: boolean)
- Statistics: Num rows: 11 Data size: 2068 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 1023 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: key (type: int)
sort order: +
Map-reduce partition columns: key (type: int)
- Statistics: Num rows: 11 Data size: 2068 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 1023 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: value (type: string)
Execution mode: llap
LLAP IO: no inputs
@@ -165,24 +165,24 @@ STAGE PLANS:
TableScan
alias: b
filterExpr: key is not null (type: boolean)
- Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: key is not null (type: boolean)
- Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: key (type: int)
outputColumnNames: _col0
- Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
keys: _col0 (type: int)
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: llap
LLAP IO: no inputs
Reducer 2
@@ -195,21 +195,21 @@ STAGE PLANS:
0 key (type: int)
1 _col0 (type: int)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 12 Data size: 2274 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 7 Data size: 651 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int), _col1 (type: string)
sort order: ++
- Statistics: Num rows: 12 Data size: 2274 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 7 Data size: 651 Basic stats: COMPLETE Column stats: COMPLETE
Reducer 3
Execution mode: llap
Reduce Operator Tree:
Select Operator
expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 12 Data size: 2274 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 7 Data size: 651 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 12 Data size: 2274 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 7 Data size: 651 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -265,15 +265,15 @@ STAGE PLANS:
TableScan
alias: a
filterExpr: key is not null (type: boolean)
- Statistics: Num rows: 11 Data size: 2068 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 1023 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: key is not null (type: boolean)
- Statistics: Num rows: 11 Data size: 2068 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 1023 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: key (type: int)
sort order: +
Map-reduce partition columns: key (type: int)
- Statistics: Num rows: 11 Data size: 2068 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 1023 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: value (type: string)
Execution mode: llap
LLAP IO: no inputs
@@ -282,24 +282,24 @@ STAGE PLANS:
TableScan
alias: b
filterExpr: key is not null (type: boolean)
- Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: key is not null (type: boolean)
- Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: key (type: int)
outputColumnNames: _col0
- Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
keys: _col0 (type: int)
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: llap
LLAP IO: no inputs
Reducer 2
@@ -312,21 +312,21 @@ STAGE PLANS:
0 key (type: int)
1 _col0 (type: int)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 12 Data size: 2274 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 7 Data size: 651 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int), _col1 (type: string)
sort order: ++
- Statistics: Num rows: 12 Data size: 2274 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 7 Data size: 651 Basic stats: COMPLETE Column stats: COMPLETE
Reducer 3
Execution mode: llap
Reduce Operator Tree:
Select Operator
expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 12 Data size: 2274 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 7 Data size: 651 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 12 Data size: 2274 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 7 Data size: 651 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -384,15 +384,15 @@ STAGE PLANS:
TableScan
alias: a
filterExpr: key is not null (type: boolean)
- Statistics: Num rows: 11 Data size: 2068 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 1023 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: key is not null (type: boolean)
- Statistics: Num rows: 11 Data size: 2068 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 1023 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: key (type: int)
sort order: +
Map-reduce partition columns: key (type: int)
- Statistics: Num rows: 11 Data size: 2068 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 1023 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: value (type: string)
Execution mode: llap
LLAP IO: no inputs
@@ -431,21 +431,21 @@ STAGE PLANS:
0 key (type: int)
1 _col0 (type: int)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 12 Data size: 2274 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 1125 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: int), _col1 (type: string)
sort order: ++
- Statistics: Num rows: 12 Data size: 2274 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 1125 Basic stats: COMPLETE Column stats: NONE
Reducer 3
Execution mode: llap
Reduce Operator Tree:
Select Operator
expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 12 Data size: 2274 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 1125 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
- Statistics: Num rows: 12 Data size: 2274 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 1125 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -495,15 +495,15 @@ STAGE PLANS:
TableScan
alias: a
filterExpr: key is not null (type: boolean)
- Statistics: Num rows: 11 Data size: 2068 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 1023 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: key is not null (type: boolean)
- Statistics: Num rows: 11 Data size: 2068 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 1023 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: key (type: int)
sort order: +
Map-reduce partition columns: key (type: int)
- Statistics: Num rows: 11 Data size: 2068 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 1023 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: value (type: string)
Execution mode: llap
LLAP IO: no inputs
@@ -512,24 +512,24 @@ STAGE PLANS:
TableScan
alias: b
filterExpr: (key < 15) (type: boolean)
- Statistics: Num rows: 22 Data size: 88 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 22 Data size: 88 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: (key < 15) (type: boolean)
- Statistics: Num rows: 22 Data size: 88 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: key (type: int)
outputColumnNames: _col1
- Statistics: Num rows: 22 Data size: 88 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 7 Data size: 56 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
keys: _col1 (type: int), _col1 (type: int)
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 22 Data size: 88 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col1 (type: int)
sort order: +
Map-reduce partition columns: _col1 (type: int)
- Statistics: Num rows: 22 Data size: 88 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: llap
LLAP IO: no inputs
Reducer 2
@@ -542,25 +542,25 @@ STAGE PLANS:
0 key (type: int)
1 _col1 (type: int)
outputColumnNames: _col1
- Statistics: Num rows: 24 Data size: 96 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col1 (type: string)
outputColumnNames: _col0
- Statistics: Num rows: 24 Data size: 96 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
- Statistics: Num rows: 24 Data size: 96 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE
Reducer 3
Execution mode: llap
Reduce Operator Tree:
Select Operator
expressions: KEY.reducesinkkey0 (type: string)
outputColumnNames: _col0
- Statistics: Num rows: 24 Data size: 96 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 24 Data size: 96 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -621,15 +621,15 @@ STAGE PLANS:
TableScan
alias: a
filterExpr: key is not null (type: boolean)
- Statistics: Num rows: 11 Data size: 2068 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 1023 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: key is not null (type: boolean)
- Statistics: Num rows: 11 Data size: 2068 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 1023 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: key (type: int)
sort order: +
Map-reduce partition columns: key (type: int)
- Statistics: Num rows: 11 Data size: 2068 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 1023 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: value (type: string)
Execution mode: llap
LLAP IO: no inputs
@@ -638,24 +638,24 @@ STAGE PLANS:
TableScan
alias: b
filterExpr: ((value < 'val_10') and key is not null) (type: boolean)
- Statistics: Num rows: 11 Data size: 2068 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 1023 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: ((value < 'val_10') and key is not null) (type: boolean)
- Statistics: Num rows: 3 Data size: 564 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 279 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: key (type: int), value (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 3 Data size: 564 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 279 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
keys: _col0 (type: int), _col1 (type: string)
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 3 Data size: 564 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 3 Data size: 564 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: llap
LLAP IO: no inputs
Reducer 2
@@ -668,21 +668,21 @@ STAGE PLANS:
0 key (type: int)
1 _col0 (type: int)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 12 Data size: 2274 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int), _col1 (type: string)
sort order: ++
- Statistics: Num rows: 12 Data size: 2274 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE
Reducer 3
Execution mode: llap
Reduce Operator Tree:
Select Operator
expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 12 Data size: 2274 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 12 Data size: 2274 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -735,24 +735,24 @@ STAGE PLANS:
TableScan
alias: t3_n12
filterExpr: (key > 5) (type: boolean)
- Statistics: Num rows: 22 Data size: 88 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 22 Data size: 88 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: (key > 5) (type: boolean)
- Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: key (type: int)
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 7 Data size: 28 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
keys: _col0 (type: int)
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: llap
LLAP IO: no inputs
Map 4
@@ -760,15 +760,15 @@ STAGE PLANS:
TableScan
alias: a
filterExpr: key is not null (type: boolean)
- Statistics: Num rows: 11 Data size: 2068 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 1023 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: key is not null (type: boolean)
- Statistics: Num rows: 11 Data size: 2068 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 1023 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: key (type: int)
sort order: +
Map-reduce partition columns: key (type: int)
- Statistics: Num rows: 11 Data size: 2068 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 1023 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: value (type: string)
Execution mode: llap
LLAP IO: no inputs
@@ -782,25 +782,25 @@ STAGE PLANS:
0 key (type: int)
1 _col0 (type: int)
outputColumnNames: _col1
- Statistics: Num rows: 12 Data size: 2274 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col1 (type: string)
outputColumnNames: _col0
- Statistics: Num rows: 12 Data size: 2274 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
- Statistics: Num rows: 12 Data size: 2274 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE
Reducer 3
Execution mode: llap
Reduce Operator Tree:
Select Operator
expressions: KEY.reducesinkkey0 (type: string)
outputColumnNames: _col0
- Statistics: Num rows: 12 Data size: 2274 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 12 Data size: 2274 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -853,24 +853,24 @@ STAGE PLANS:
TableScan
alias: t2_n33
filterExpr: ((key > 5) and (value <= 'val_20')) (type: boolean)
- Statistics: Num rows: 11 Data size: 2068 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 1023 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: ((key > 5) and (value <= 'val_20')) (type: boolean)
- Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: key (type: int), value (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
keys: _col0 (type: int), _col1 (type: string)
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: llap
LLAP IO: no inputs
Map 4
@@ -878,15 +878,15 @@ STAGE PLANS:
TableScan
alias: a
filterExpr: key is not null (type: boolean)
- Statistics: Num rows: 11 Data size: 2068 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 1023 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: key is not null (type: boolean)
- Statistics: Num rows: 11 Data size: 2068 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 1023 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: key (type: int)
sort order: +
Map-reduce partition columns: key (type: int)
- Statistics: Num rows: 11 Data size: 2068 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 1023 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: value (type: string)
Execution mode: llap
LLAP IO: no inputs
@@ -900,25 +900,25 @@ STAGE PLANS:
0 key (type: int)
1 _col0 (type: int)
outputColumnNames: _col1
- Statistics: Num rows: 12 Data size: 2274 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 89 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col1 (type: string)
outputColumnNames: _col0
- Statistics: Num rows: 12 Data size: 2274 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 89 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
- Statistics: Num rows: 12 Data size: 2274 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 89 Basic stats: COMPLETE Column stats: COMPLETE
Reducer 3
Execution mode: llap
Reduce Operator Tree:
Select Operator
expressions: KEY.reducesinkkey0 (type: string)
outputColumnNames: _col0
- Statistics: Num rows: 12 Data size: 2274 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 89 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 12 Data size: 2274 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 89 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -968,24 +968,24 @@ STAGE PLANS:
TableScan
alias: t1_n55
filterExpr: (key > 2) (type: boolean)
- Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: (key > 2) (type: boolean)
- Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: key (type: int)
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
keys: _col0 (type: int)
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: llap
LLAP IO: no inputs
Map 4
@@ -993,15 +993,15 @@ STAGE PLANS:
TableScan
alias: a
filterExpr: key is not null (type: boolean)
- Statistics: Num rows: 11 Data size: 2068 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 1023 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: key is not null (type: boolean)
- Statistics: Num rows: 11 Data size: 2068 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 1023 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: key (type: int)
sort order: +
Map-reduce partition columns: key (type: int)
- Statistics: Num rows: 11 Data size: 2068 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 1023 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: value (type: string)
Execution mode: llap
LLAP IO: no inputs
@@ -1015,21 +1015,21 @@ STAGE PLANS:
0 key (type: int)
1 _col0 (type: int)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 12 Data size: 2274 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int), _col1 (type: string)
sort order: ++
- Statistics: Num rows: 12 Data size: 2274 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE
Reducer 3
Execution mode: llap
Reduce Operator Tree:
Select Operator
expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 12 Data size: 2274 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 12 Data size: 2274 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -1084,15 +1084,15 @@ STAGE PLANS:
TableScan
alias: a
filterExpr: key is not null (type: boolean)
- Statistics: Num rows: 22 Data size: 88 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 22 Data size: 88 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: key is not null (type: boolean)
- Statistics: Num rows: 21 Data size: 84 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 22 Data size: 88 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: key (type: int)
sort order: +
Map-reduce partition columns: key (type: int)
- Statistics: Num rows: 21 Data size: 84 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 22 Data size: 88 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: llap
LLAP IO: no inputs
Map 4
@@ -1100,24 +1100,24 @@ STAGE PLANS:
TableScan
alias: b
filterExpr: key is not null (type: boolean)
- Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: key is not null (type: boolean)
- Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: key (type: int)
outputColumnNames: _col0
- Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
keys: _col0 (type: int)
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: llap
LLAP IO: no inputs
Reducer 2
@@ -1130,21 +1130,21 @@ STAGE PLANS:
0 key (type: int)
1 _col0 (type: int)
outputColumnNames: _col0
- Statistics: Num rows: 23 Data size: 92 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
- Statistics: Num rows: 23 Data size: 92 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
Reducer 3
Execution mode: llap
Reduce Operator Tree:
Select Operator
expressions: KEY.reducesinkkey0 (type: int)
outputColumnNames: _col0
- Statistics: Num rows: 23 Data size: 92 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 23 Data size: 92 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -1213,15 +1213,15 @@ STAGE PLANS:
TableScan
alias: a
filterExpr: key is not null (type: boolean)
- Statistics: Num rows: 11 Data size: 2068 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 1023 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: key is not null (type: boolean)
- Statistics: Num rows: 11 Data size: 2068 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 1023 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: key (type: int)
sort order: +
Map-reduce partition columns: key (type: int)
- Statistics: Num rows: 11 Data size: 2068 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 1023 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: value (type: string)
Execution mode: llap
LLAP IO: no inputs
@@ -1230,24 +1230,24 @@ STAGE PLANS:
TableScan
alias: b
filterExpr: (2 * key) is not null (type: boolean)
- Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: (2 * key) is not null (type: boolean)
- Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: key (type: int)
outputColumnNames: _col0
- Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
keys: _col0 (type: int)
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: (2 * _col0) (type: int)
sort order: +
Map-reduce partition columns: (2 * _col0) (type: int)
- Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: llap
LLAP IO: no inputs
Reducer 2
@@ -1260,21 +1260,21 @@ STAGE PLANS:
0 key (type: int)
1 (2 * _col0) (type: int)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 12 Data size: 2274 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 7 Data size: 651 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int), _col1 (type: string)
sort order: ++
- Statistics: Num rows: 12 Data size: 2274 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 7 Data size: 651 Basic stats: COMPLETE Column stats: COMPLETE
Reducer 3
Execution mode: llap
Reduce Operator Tree:
Select Operator
expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 12 Data size: 2274 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 7 Data size: 651 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 12 Data size: 2274 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 7 Data size: 651 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -1330,15 +1330,15 @@ STAGE PLANS:
TableScan
alias: a
filterExpr: key is not null (type: boolean)
- Statistics: Num rows: 11 Data size: 2068 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 1023 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: key is not null (type: boolean)
- Statistics: Num rows: 11 Data size: 2068 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 1023 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: key (type: int)
sort order: +
Map-reduce partition columns: key (type: int)
- Statistics: Num rows: 11 Data size: 2068 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 1023 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: value (type: string)
Execution mode: llap
LLAP IO: no inputs
@@ -1347,15 +1347,15 @@ STAGE PLANS:
TableScan
alias: b
filterExpr: key is not null (type: boolean)
- Statistics: Num rows: 11 Data size: 2068 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 1023 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: key is not null (type: boolean)
- Statistics: Num rows: 11 Data size: 2068 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 1023 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: key (type: int)
sort order: +
Map-reduce partition columns: key (type: int)
- Statistics: Num rows: 11 Data size: 2068 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 1023 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: value (type: string)
Execution mode: llap
LLAP IO: no inputs
@@ -1364,24 +1364,24 @@ STAGE PLANS:
TableScan
alias: c
filterExpr: key is not null (type: boolean)
- Statistics: Num rows: 22 Data size: 88 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 22 Data size: 88 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: key is not null (type: boolean)
- Statistics: Num rows: 21 Data size: 84 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 22 Data size: 88 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: key (type: int)
outputColumnNames: _col0
- Statistics: Num rows: 21 Data size: 84 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 22 Data size: 88 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
keys: _col0 (type: int)
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 21 Data size: 84 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 21 Data size: 84 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: llap
LLAP IO: no inputs
Reducer 2
@@ -1396,15 +1396,15 @@ STAGE PLANS:
1 key (type: int)
2 _col0 (type: int)
outputColumnNames: _col0, _col1, _col5, _col6
- Statistics: Num rows: 46 Data size: 184 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 17 Data size: 3162 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: int), _col1 (type: string), _col5 (type: int), _col6 (type: string)
outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 46 Data size: 184 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 17 Data size: 3162 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int), _col1 (type: string)
sort order: ++
- Statistics: Num rows: 46 Data size: 184 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 17 Data size: 3162 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col2 (type: int), _col3 (type: string)
Reducer 3
Execution mode: llap
@@ -1412,10 +1412,10 @@ STAGE PLANS:
Select Operator
expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: string), VALUE._col0 (type: int), VALUE._col1 (type: string)
outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 46 Data size: 184 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 17 Data size: 3162 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 46 Data size: 184 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 17 Data size: 3162 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -1481,15 +1481,15 @@ STAGE PLANS:
TableScan
alias: a
filterExpr: (key is not null and value is not null) (type: boolean)
- Statistics: Num rows: 22 Data size: 4136 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 22 Data size: 2046 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: (key is not null and value is not null) (type: boolean)
- Statistics: Num rows: 20 Data size: 3760 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 22 Data size: 2046 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: key (type: int), value (type: string)
sort order: ++
Map-reduce partition columns: key (type: int), value (type: string)
- Statistics: Num rows: 20 Data size: 3760 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 22 Data size: 2046 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: llap
LLAP IO: no inputs
Map 4
@@ -1497,24 +1497,24 @@ STAGE PLANS:
TableScan
alias: b
filterExpr: (key is not null and value is not null) (type: boolean)
- Statistics: Num rows: 11 Data size: 2068 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 1023 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: (key is not null and value is not null) (type: boolean)
- Statistics: Num rows: 11 Data size: 2068 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 1023 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: key (type: int), value (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 11 Data size: 2068 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 1023 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
keys: _col0 (type: int), _col1 (type: string)
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 11 Data size: 2068 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 465 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int), _col1 (type: string)
sort order: ++
Map-reduce partition columns: _col0 (type: int), _col1 (type: string)
- Statistics: Num rows: 11 Data size: 2068 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 465 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: llap
LLAP IO: no inputs
Reducer 2
@@ -1527,21 +1527,21 @@ STAGE PLANS:
0 key (type: int), value (type: string)
1 _col0 (type: int), _col1 (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 22 Data size: 4136 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 1023 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int), _col1 (type: string)
sort order: ++
- Statistics: Num rows: 22 Data size: 4136 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 1023 Basic stats: COMPLETE Column stats: COMPLETE
Reducer 3
Execution mode: llap
Reduce Operator Tree:
Select Operator
expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 22 Data size: 4136 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 1023 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 22 Data size: 4136 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 1023 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -1607,15 +1607,15 @@ STAGE PLANS:
TableScan
alias: a
filterExpr: key is not null (type: boolean)
- Statistics: Num rows: 22 Data size: 88 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 22 Data size: 88 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: key is not null (type: boolean)
- Statistics: Num rows: 21 Data size: 84 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 22 Data size: 88 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: key (type: int)
sort order: +
Map-reduce partition columns: key (type: int)
- Statistics: Num rows: 21 Data size: 84 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 22 Data size: 88 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: llap
LLAP IO: no inputs
Map 4
@@ -1623,24 +1623,24 @@ STAGE PLANS:
TableScan
alias: b
filterExpr: key is not null (type: boolean)
- Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: key is not null (type: boolean)
- Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: key (type: int)
outputColumnNames: _col0
- Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
keys: _col0 (type: int)
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: llap
LLAP IO: no inputs
Map 5
@@ -1648,24 +1648,24 @@ STAGE PLANS:
TableScan
alias: c
filterExpr: key is not null (type: boolean)
- Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: key is not null (type: boolean)
- Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: key (type: int)
outputColumnNames: _col0
- Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
keys: _col0 (type: int)
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: llap
LLAP IO: no inputs
Reducer 2
@@ -1680,21 +1680,21 @@ STAGE PLANS:
1 _col0 (type: int)
2 _col0 (type: int)
outputColumnNames: _col0
- Statistics: Num rows: 46 Data size: 184 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
- Statistics: Num rows: 46 Data size: 184 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
Reducer 3
Execution mode: llap
Reduce Operator Tree:
Select Operator
expressions: KEY.reducesinkkey0 (type: int)
outputColumnNames: _col0
- Statistics: Num rows: 46 Data size: 184 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 46 Data size: 184 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -1761,45 +1761,45 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: a
- Statistics: Num rows: 22 Data size: 88 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 22 Data size: 88 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: key (type: int)
sort order: +
Map-reduce partition columns: key (type: int)
- Statistics: Num rows: 22 Data size: 88 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 22 Data size: 88 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: llap
LLAP IO: no inputs
Map 4
Map Operator Tree:
TableScan
alias: b
- Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: key (type: int)
sort order: +
Map-reduce partition columns: key (type: int)
- Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: llap
LLAP IO: no inputs
Map 5
Map Operator Tree:
TableScan
alias: c
- Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: key (type: int)
outputColumnNames: _col0
- Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
keys: _col0 (type: int)
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: llap
LLAP IO: no inputs
Reducer 2
@@ -1814,21 +1814,21 @@ STAGE PLANS:
1 key (type: int)
2 _col0 (type: int)
outputColumnNames: _col0
- Statistics: Num rows: 48 Data size: 193 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 17 Data size: 68 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
- Statistics: Num rows: 48 Data size: 193 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 17 Data size: 68 Basic stats: COMPLETE Column stats: COMPLETE
Reducer 3
Execution mode: llap
Reduce Operator Tree:
Select Operator
expressions: KEY.reducesinkkey0 (type: int)
outputColumnNames: _col0
- Statistics: Num rows: 48 Data size: 193 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 17 Data size: 68 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 48 Data size: 193 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 17 Data size: 68 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -1907,45 +1907,45 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: a
- Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: key (type: int)
sort order: +
Map-reduce partition columns: key (type: int)
- Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: llap
LLAP IO: no inputs
Map 4
Map Operator Tree:
TableScan
alias: b
- Statistics: Num rows: 22 Data size: 88 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 22 Data size: 88 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: key (type: int)
sort order: +
Map-reduce partition columns: key (type: int)
- Statistics: Num rows: 22 Data size: 88 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 22 Data size: 88 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: llap
LLAP IO: no inputs
Map 5
Map Operator Tree:
TableScan
alias: c
- Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: key (type: int)
outputColumnNames: _col0
- Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
keys: _col0 (type: int)
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: llap
LLAP IO: no inputs
Reducer 2
@@ -1960,21 +1960,21 @@ STAGE PLANS:
1 key (type: int)
2 _col0 (type: int)
outputColumnNames: _col0
- Statistics: Num rows: 48 Data size: 193 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 17 Data size: 68 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
- Statistics: Num rows: 48 Data size: 193 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 17 Data size: 68 Basic stats: COMPLETE Column stats: COMPLETE
Reducer 3
Execution mode: llap
Reduce Operator Tree:
Select Operator
expressions: KEY.reducesinkkey0 (type: int)
outputColumnNames: _col0
- Statistics: Num rows: 48 Data size: 193 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 17 Data size: 68 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 48 Data size: 193 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 17 Data size: 68 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -2056,45 +2056,45 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: a
- Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: key (type: int)
sort order: +
Map-reduce partition columns: key (type: int)
- Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: llap
LLAP IO: no inputs
Map 4
Map Operator Tree:
TableScan
alias: b
- Statistics: Num rows: 22 Data size: 88 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 22 Data size: 88 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: key (type: int)
sort order: +
Map-reduce partition columns: key (type: int)
- Statistics: Num rows: 22 Data size: 88 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 22 Data size: 88 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: llap
LLAP IO: no inputs
Map 5
Map Operator Tree:
TableScan
alias: c
- Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: key (type: int)
outputColumnNames: _col0
- Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
keys: _col0 (type: int)
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: llap
LLAP IO: no inputs
Reducer 2
@@ -2109,21 +2109,21 @@ STAGE PLANS:
1 key (type: int)
2 _col0 (type: int)
outputColumnNames: _col0
- Statistics: Num rows: 48 Data size: 193 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 17 Data size: 68 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
- Statistics: Num rows: 48 Data size: 193 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 17 Data size: 68 Basic stats: COMPLETE Column stats: COMPLETE
Reducer 3
Execution mode: llap
Reduce Operator Tree:
Select Operator
expressions: KEY.reducesinkkey0 (type: int)
outputColumnNames: _col0
- Statistics: Num rows: 48 Data size: 193 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 17 Data size: 68 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 48 Data size: 193 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 17 Data size: 68 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -2205,45 +2205,45 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: a
- Statistics: Num rows: 22 Data size: 88 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 22 Data size: 88 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: key (type: int)
sort order: +
Map-reduce partition columns: key (type: int)
- Statistics: Num rows: 22 Data size: 88 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 22 Data size: 88 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: llap
LLAP IO: no inputs
Map 4
Map Operator Tree:
TableScan
alias: b
- Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: key (type: int)
outputColumnNames: _col0
- Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
keys: _col0 (type: int)
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: llap
LLAP IO: no inputs
Map 5
Map Operator Tree:
TableScan
alias: c
- Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: key (type: int)
sort order: +
Map-reduce partition columns: key (type: int)
- Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: llap
LLAP IO: no inputs
Reducer 2
@@ -2258,21 +2258,21 @@ STAGE PLANS:
1 _col0 (type: int)
2 key (type: int)
outputColumnNames: _col0
- Statistics: Num rows: 48 Data size: 193 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 17 Data size: 68 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
- Statistics: Num rows: 48 Data size: 193 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 17 Data size: 68 Basic stats: COMPLETE Column stats: COMPLETE
Reducer 3
Execution mode: llap
Reduce Operator Tree:
Select Operator
expressions: KEY.reducesinkkey0 (type: int)
outputColumnNames: _col0
- Statistics: Num rows: 48 Data size: 193 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 17 Data size: 68 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 48 Data size: 193 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 17 Data size: 68 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -2354,45 +2354,45 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: a
- Statistics: Num rows: 22 Data size: 88 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 22 Data size: 88 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: key (type: int)
sort order: +
Map-reduce partition columns: key (type: int)
- Statistics: Num rows: 22 Data size: 88 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 22 Data size: 88 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: llap
LLAP IO: no inputs
Map 4
Map Operator Tree:
TableScan
alias: b
- Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: key (type: int)
outputColumnNames: _col0
- Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
keys: _col0 (type: int)
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: llap
LLAP IO: no inputs
Map 5
Map Operator Tree:
TableScan
alias: c
- Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: key (type: int)
sort order: +
Map-reduce partition columns: key (type: int)
- Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: llap
LLAP IO: no inputs
Reducer 2
@@ -2407,21 +2407,21 @@ STAGE PLANS:
1 _col0 (type: int)
2 key (type: int)
outputColumnNames: _col0
- Statistics: Num rows: 48 Data size: 193 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 17 Data size: 68 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
- Statistics: Num rows: 48 Data size: 193 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 17 Data size: 68 Basic stats: COMPLETE Column stats: COMPLETE
Reducer 3
Execution mode: llap
Reduce Operator Tree:
Select Operator
expressions: KEY.reducesinkkey0 (type: int)
outputColumnNames: _col0
- Statistics: Num rows: 48 Data size: 193 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 17 Data size: 68 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 48 Data size: 193 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 17 Data size: 68 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -2505,45 +2505,45 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: a
- Statistics: Num rows: 22 Data
<TRUNCATED>