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 00:24:32 UTC
[33/35] hive git commit: HIVE-16957: Support CTAS for auto gather
column stats (Jesus Camacho Rodriguez, reviewed by Ashutosh Chauhan)
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