You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@hive.apache.org by ha...@apache.org on 2017/12/12 00:00:14 UTC
[16/51] [partial] hive git commit: HIVE-13567 : Enable auto-gather
column stats by default (Zoltan Haindrich,
Pengcheng Xiong via Ashutosh Chauhan)
http://git-wip-us.apache.org/repos/asf/hive/blob/3bbc24d2/ql/src/test/results/clientpositive/llap/extrapolate_part_stats_partial_ndv.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/extrapolate_part_stats_partial_ndv.q.out b/ql/src/test/results/clientpositive/llap/extrapolate_part_stats_partial_ndv.q.out
index 1ac5977..aa44d33 100644
--- a/ql/src/test/results/clientpositive/llap/extrapolate_part_stats_partial_ndv.q.out
+++ b/ql/src/test/results/clientpositive/llap/extrapolate_part_stats_partial_ndv.q.out
@@ -269,7 +269,7 @@ STAGE PLANS:
partition values:
year 2000
properties:
- COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"cnt":"true","locid":"true","state":"true","zip":"true"}}
bucket_count -1
column.name.delimiter ,
columns state,locid,cnt,zip
@@ -404,7 +404,7 @@ STAGE PLANS:
partition values:
year 2003
properties:
- COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"cnt":"true","locid":"true","state":"true","zip":"true"}}
bucket_count -1
column.name.delimiter ,
columns state,locid,cnt,zip
@@ -1051,7 +1051,7 @@ STAGE PLANS:
year 2001
zip 43201
properties:
- COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"cnt":"true","locid":"true","state":"true"}}
bucket_count -1
column.name.delimiter ,
columns state,locid,cnt
@@ -1097,7 +1097,7 @@ STAGE PLANS:
year 2002
zip 43201
properties:
- COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"cnt":"true","locid":"true","state":"true"}}
bucket_count -1
column.name.delimiter ,
columns state,locid,cnt
@@ -1143,7 +1143,7 @@ STAGE PLANS:
year 2003
zip 43201
properties:
- COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"cnt":"true","locid":"true","state":"true"}}
bucket_count -1
column.name.delimiter ,
columns state,locid,cnt
@@ -1189,7 +1189,7 @@ STAGE PLANS:
year 2000
zip 94086
properties:
- COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"cnt":"true","locid":"true","state":"true"}}
bucket_count -1
column.name.delimiter ,
columns state,locid,cnt
@@ -1281,7 +1281,7 @@ STAGE PLANS:
year 2002
zip 94086
properties:
- COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"cnt":"true","locid":"true","state":"true"}}
bucket_count -1
column.name.delimiter ,
columns state,locid,cnt
@@ -1327,7 +1327,7 @@ STAGE PLANS:
year 2003
zip 94086
properties:
- COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"cnt":"true","locid":"true","state":"true"}}
bucket_count -1
column.name.delimiter ,
columns state,locid,cnt
@@ -1373,7 +1373,7 @@ STAGE PLANS:
year 2000
zip 94087
properties:
- COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"cnt":"true","locid":"true","state":"true"}}
bucket_count -1
column.name.delimiter ,
columns state,locid,cnt
@@ -1419,7 +1419,7 @@ STAGE PLANS:
year 2001
zip 94087
properties:
- COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"cnt":"true","locid":"true","state":"true"}}
bucket_count -1
column.name.delimiter ,
columns state,locid,cnt
@@ -1511,7 +1511,7 @@ STAGE PLANS:
year 2003
zip 94087
properties:
- COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"cnt":"true","locid":"true","state":"true"}}
bucket_count -1
column.name.delimiter ,
columns state,locid,cnt
http://git-wip-us.apache.org/repos/asf/hive/blob/3bbc24d2/ql/src/test/results/clientpositive/llap/filter_join_breaktask.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/filter_join_breaktask.q.out b/ql/src/test/results/clientpositive/llap/filter_join_breaktask.q.out
index ecc2246..f69d8a2 100644
--- a/ql/src/test/results/clientpositive/llap/filter_join_breaktask.q.out
+++ b/ql/src/test/results/clientpositive/llap/filter_join_breaktask.q.out
@@ -44,23 +44,23 @@ STAGE PLANS:
Map 1
Map Operator Tree:
TableScan
- alias: g
- Statistics: Num rows: 25 Data size: 4600 Basic stats: COMPLETE Column stats: NONE
+ alias: f
+ Statistics: Num rows: 25 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE
GatherStats: false
Filter Operator
isSamplingPred: false
- predicate: (value <> '') (type: boolean)
- Statistics: Num rows: 25 Data size: 4600 Basic stats: COMPLETE Column stats: NONE
+ predicate: key is not null (type: boolean)
+ Statistics: Num rows: 15 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
- expressions: value (type: string)
+ expressions: key (type: int)
outputColumnNames: _col0
- Statistics: Num rows: 25 Data size: 4600 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 15 Data size: 1450 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
- key expressions: _col0 (type: string)
+ key expressions: _col0 (type: int)
null sort order: a
sort order: +
- Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 25 Data size: 4600 Basic stats: COMPLETE Column stats: NONE
+ Map-reduce partition columns: _col0 (type: int)
+ Statistics: Num rows: 15 Data size: 1450 Basic stats: COMPLETE Column stats: COMPLETE
tag: 0
auto parallelism: true
Execution mode: llap
@@ -76,7 +76,7 @@ STAGE PLANS:
partition values:
ds 2008-04-08
properties:
- COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
column.name.delimiter ,
columns key,value
@@ -116,29 +116,29 @@ STAGE PLANS:
name: default.filter_join_breaktask
name: default.filter_join_breaktask
Truncated Path -> Alias:
- /filter_join_breaktask/ds=2008-04-08 [g]
+ /filter_join_breaktask/ds=2008-04-08 [f]
Map 4
Map Operator Tree:
TableScan
alias: m
- Statistics: Num rows: 25 Data size: 4700 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 25 Data size: 2289 Basic stats: COMPLETE Column stats: COMPLETE
GatherStats: false
Filter Operator
isSamplingPred: false
predicate: ((value <> '') and key is not null) (type: boolean)
- Statistics: Num rows: 24 Data size: 4512 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 15 Data size: 1375 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: key (type: int), value (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 24 Data size: 4512 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 15 Data size: 2785 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
- key expressions: _col1 (type: string)
+ key expressions: _col0 (type: int)
null sort order: a
sort order: +
- Map-reduce partition columns: _col1 (type: string)
- Statistics: Num rows: 24 Data size: 4512 Basic stats: COMPLETE Column stats: NONE
+ Map-reduce partition columns: _col0 (type: int)
+ Statistics: Num rows: 15 Data size: 2785 Basic stats: COMPLETE Column stats: COMPLETE
tag: 1
- value expressions: _col0 (type: int)
+ value expressions: _col1 (type: string)
auto parallelism: true
Execution mode: llap
LLAP IO: no inputs
@@ -153,7 +153,7 @@ STAGE PLANS:
partition values:
ds 2008-04-08
properties:
- COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
column.name.delimiter ,
columns key,value
@@ -197,23 +197,23 @@ STAGE PLANS:
Map 5
Map Operator Tree:
TableScan
- alias: f
- Statistics: Num rows: 25 Data size: 100 Basic stats: COMPLETE Column stats: NONE
+ alias: g
+ Statistics: Num rows: 25 Data size: 2225 Basic stats: COMPLETE Column stats: COMPLETE
GatherStats: false
Filter Operator
isSamplingPred: false
- predicate: key is not null (type: boolean)
- Statistics: Num rows: 24 Data size: 96 Basic stats: COMPLETE Column stats: NONE
+ predicate: (value <> '') (type: boolean)
+ Statistics: Num rows: 25 Data size: 2225 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
- expressions: key (type: int)
+ expressions: value (type: string)
outputColumnNames: _col0
- Statistics: Num rows: 24 Data size: 96 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 25 Data size: 4575 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
- key expressions: _col0 (type: int)
+ key expressions: _col0 (type: string)
null sort order: a
sort order: +
- Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 24 Data size: 96 Basic stats: COMPLETE Column stats: NONE
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 25 Data size: 4575 Basic stats: COMPLETE Column stats: COMPLETE
tag: 1
auto parallelism: true
Execution mode: llap
@@ -229,7 +229,7 @@ STAGE PLANS:
partition values:
ds 2008-04-08
properties:
- COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
column.name.delimiter ,
columns key,value
@@ -269,7 +269,7 @@ STAGE PLANS:
name: default.filter_join_breaktask
name: default.filter_join_breaktask
Truncated Path -> Alias:
- /filter_join_breaktask/ds=2008-04-08 [f]
+ /filter_join_breaktask/ds=2008-04-08 [g]
Reducer 2
Execution mode: llap
Needs Tagging: false
@@ -278,19 +278,19 @@ STAGE PLANS:
condition map:
Inner Join 0 to 1
keys:
- 0 _col0 (type: string)
- 1 _col1 (type: string)
- outputColumnNames: _col0, _col2
- Position of Big Table: 0
- Statistics: Num rows: 27 Data size: 5060 Basic stats: COMPLETE Column stats: NONE
+ 0 _col0 (type: int)
+ 1 _col0 (type: int)
+ outputColumnNames: _col0, _col3
+ Position of Big Table: 1
+ Statistics: Num rows: 25 Data size: 2305 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
- key expressions: _col2 (type: int)
+ key expressions: _col3 (type: string)
null sort order: a
sort order: +
- Map-reduce partition columns: _col2 (type: int)
- Statistics: Num rows: 27 Data size: 5060 Basic stats: COMPLETE Column stats: NONE
+ Map-reduce partition columns: _col3 (type: string)
+ Statistics: Num rows: 25 Data size: 2305 Basic stats: COMPLETE Column stats: COMPLETE
tag: 0
- value expressions: _col0 (type: string)
+ value expressions: _col0 (type: int)
auto parallelism: true
Reducer 3
Execution mode: llap
@@ -300,21 +300,21 @@ STAGE PLANS:
condition map:
Inner Join 0 to 1
keys:
- 0 _col2 (type: int)
- 1 _col0 (type: int)
+ 0 _col3 (type: string)
+ 1 _col0 (type: string)
outputColumnNames: _col0, _col5
Position of Big Table: 0
- Statistics: Num rows: 29 Data size: 5566 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 32 Data size: 2956 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
- expressions: _col5 (type: int), _col0 (type: string)
+ expressions: _col0 (type: int), _col5 (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 29 Data size: 5566 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 32 Data size: 2956 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
GlobalTableId: 0
#### A masked pattern was here ####
NumFilesPerFileSink: 1
- Statistics: Num rows: 29 Data size: 5566 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 32 Data size: 2956 Basic stats: COMPLETE Column stats: COMPLETE
#### A masked pattern was here ####
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/3bbc24d2/ql/src/test/results/clientpositive/llap/groupby2.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/groupby2.q.out b/ql/src/test/results/clientpositive/llap/groupby2.q.out
index 5ab6235..c452719 100644
--- a/ql/src/test/results/clientpositive/llap/groupby2.q.out
+++ b/ql/src/test/results/clientpositive/llap/groupby2.q.out
@@ -27,6 +27,8 @@ STAGE PLANS:
Edges:
Reducer 2 <- Map 1 (SIMPLE_EDGE)
Reducer 3 <- Reducer 2 (SIMPLE_EDGE)
+ Reducer 4 <- Reducer 3 (CUSTOM_SIMPLE_EDGE)
+ Reducer 5 <- Reducer 4 (CUSTOM_SIMPLE_EDGE)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -81,6 +83,42 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.dest_g2
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: int), _col2 (type: string)
+ outputColumnNames: key, c1, c2
+ Statistics: Num rows: 309 Data size: 114948 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ sort order:
+ Map-reduce partition columns: rand() (type: double)
+ Statistics: Num rows: 309 Data size: 114948 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: key (type: string), c1 (type: int), c2 (type: string)
+ Reducer 4
+ Execution mode: llap
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: compute_stats(VALUE._col0, 'hll'), compute_stats(VALUE._col2, 'hll'), compute_stats(VALUE._col3, 'hll')
+ mode: partial1
+ 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,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col2 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>)
+ Reducer 5
+ Execution mode: llap
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2)
+ mode: final
+ 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
@@ -98,6 +136,10 @@ STAGE PLANS:
Stage: Stage-3
Stats Work
Basic Stats Work:
+ Column Stats Desc:
+ Columns: key, c1, c2
+ Column Types: string, int, string
+ Table: default.dest_g2
PREHOOK: query: FROM src
INSERT OVERWRITE TABLE dest_g2 SELECT substr(src.key,1,1), count(DISTINCT substr(src.value,5)), concat(substr(src.key,1,1),sum(substr(src.value,5))) GROUP BY substr(src.key,1,1)
http://git-wip-us.apache.org/repos/asf/hive/blob/3bbc24d2/ql/src/test/results/clientpositive/llap/groupby3.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/groupby3.q.out b/ql/src/test/results/clientpositive/llap/groupby3.q.out
index 897946b..d050c4e 100644
--- a/ql/src/test/results/clientpositive/llap/groupby3.q.out
+++ b/ql/src/test/results/clientpositive/llap/groupby3.q.out
@@ -45,6 +45,7 @@ STAGE PLANS:
Edges:
Reducer 2 <- Map 1 (SIMPLE_EDGE)
Reducer 3 <- Reducer 2 (CUSTOM_SIMPLE_EDGE)
+ Reducer 4 <- Reducer 3 (CUSTOM_SIMPLE_EDGE)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -73,6 +74,7 @@ STAGE PLANS:
Statistics: Num rows: 1 Data size: 1208 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
+ Map-reduce partition columns: rand() (type: double)
Statistics: Num rows: 1 Data size: 1208 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: double), _col1 (type: struct<count:bigint,sum:double,input:string>), _col2 (type: struct<count:bigint,sum:double,input:string>), _col3 (type: string), _col4 (type: string), _col5 (type: struct<count:bigint,sum:double,variance:double>), _col6 (type: struct<count:bigint,sum:double,variance:double>), _col7 (type: struct<count:bigint,sum:double,variance:double>), _col8 (type: struct<count:bigint,sum:double,variance:double>)
Reducer 3
@@ -95,6 +97,34 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.dest1
+ Select Operator
+ expressions: _col0 (type: double), _col1 (type: double), _col2 (type: double), _col3 (type: double), _col4 (type: double), _col5 (type: double), _col6 (type: double), _col7 (type: double), _col8 (type: double)
+ outputColumnNames: c1, c2, c3, c4, c5, c6, c7, c8, c9
+ Statistics: Num rows: 1 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE
+ Group By Operator
+ aggregations: compute_stats(c1, 'hll'), compute_stats(c2, 'hll'), compute_stats(c3, 'hll'), compute_stats(c4, 'hll'), compute_stats(c5, 'hll'), compute_stats(c6, 'hll'), compute_stats(c7, 'hll'), compute_stats(c8, 'hll'), compute_stats(c9, 'hll')
+ mode: complete
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8
+ Statistics: Num rows: 1 Data size: 3816 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 3816 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,min:double,max:double,countnulls:bigint,bitvector:binary>), _col2 (type: struct<columntype:string,min:double,max:double,countnulls:bigint,bitvector:binary>), _col3 (type: struct<columntype:string,min:double,max:double,countnulls:bigint,bitvector:binary>), _col4 (type: struct<columntype:string,min:double,max:double,countnulls:bigint,bitvector:binary>), _col5 (type: struct<columntype:string,min:double,max:double,countnulls:bigint,bitvector:binary>), _col6 (type: struct<columntype:string,min:double,max:double,countnulls:bigint,bitvector:binary>), _col7 (type: struct<columntype:string,min:double,max:double,countnulls:bigint,bitvector:binary>), _col8 (type: struct<columntype:string,min:double,max:double,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), compute_stats(VALUE._col3), compute_stats(VALUE._col4), compute_stats(VALUE._col5), compute_stats(VALUE._col6), compute_stats(VALUE._col7), compute_stats(VALUE._col8)
+ mode: final
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8
+ Statistics: Num rows: 1 Data size: 3960 Basic stats: COMPLETE Column stats: COMPLETE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 3960 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
@@ -112,6 +142,10 @@ STAGE PLANS:
Stage: Stage-3
Stats Work
Basic Stats Work:
+ Column Stats Desc:
+ Columns: c1, c2, c3, c4, c5, c6, c7, c8, c9
+ Column Types: double, double, double, double, double, double, double, double, double
+ Table: default.dest1
PREHOOK: query: FROM src
INSERT OVERWRITE TABLE dest1 SELECT
http://git-wip-us.apache.org/repos/asf/hive/blob/3bbc24d2/ql/src/test/results/clientpositive/llap/infer_bucket_sort_bucketed_table.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/infer_bucket_sort_bucketed_table.q.out b/ql/src/test/results/clientpositive/llap/infer_bucket_sort_bucketed_table.q.out
index 876c858..1520232 100644
--- a/ql/src/test/results/clientpositive/llap/infer_bucket_sort_bucketed_table.q.out
+++ b/ql/src/test/results/clientpositive/llap/infer_bucket_sort_bucketed_table.q.out
@@ -40,7 +40,7 @@ Database: default
Table: test_table_bucketed
#### A masked pattern was here ####
Partition Parameters:
- COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"key\":\"true\",\"value\":\"true\"}}
numFiles 3
numRows 309
rawDataSize 1482
http://git-wip-us.apache.org/repos/asf/hive/blob/3bbc24d2/ql/src/test/results/clientpositive/llap/insert1.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/insert1.q.out b/ql/src/test/results/clientpositive/llap/insert1.q.out
index bc62682..315c660 100644
--- a/ql/src/test/results/clientpositive/llap/insert1.q.out
+++ b/ql/src/test/results/clientpositive/llap/insert1.q.out
@@ -38,6 +38,9 @@ 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:
@@ -59,8 +62,36 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.insert1
+ Select Operator
+ expressions: _col0 (type: int), _col1 (type: string)
+ outputColumnNames: key, value
+ Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll')
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 1052 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 1052 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
+ Reducer 2
+ 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: 1068 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 1068 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
@@ -78,6 +109,10 @@ STAGE PLANS:
Stage: Stage-3
Stats Work
Basic Stats Work:
+ Column Stats Desc:
+ Columns: key, value
+ Column Types: int, string
+ Table: default.insert1
PREHOOK: query: explain insert into table INSERT1 select a.key, a.value from insert2 a WHERE (a.key=-1)
PREHOOK: type: QUERY
@@ -93,6 +128,9 @@ 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:
@@ -114,8 +152,36 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.insert1
+ Select Operator
+ expressions: _col0 (type: int), _col1 (type: string)
+ outputColumnNames: key, value
+ Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll')
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 1052 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 1052 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
+ Reducer 2
+ 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: 1068 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 1068 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
@@ -133,6 +199,10 @@ STAGE PLANS:
Stage: Stage-3
Stats Work
Basic Stats Work:
+ Column Stats Desc:
+ Columns: key, value
+ Column Types: int, string
+ Table: default.insert1
PREHOOK: query: create database x
PREHOOK: type: CREATEDATABASE
@@ -162,6 +232,9 @@ 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:
@@ -183,8 +256,36 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: x.insert1
+ Select Operator
+ expressions: _col0 (type: int), _col1 (type: string)
+ outputColumnNames: key, value
+ Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll')
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 1052 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 1052 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
+ Reducer 2
+ 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: 1068 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 1068 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
@@ -202,6 +303,10 @@ STAGE PLANS:
Stage: Stage-3
Stats Work
Basic Stats Work:
+ Column Stats Desc:
+ Columns: key, value
+ Column Types: int, string
+ Table: x.insert1
PREHOOK: query: explain insert into table default.INSERT1 select a.key, a.value from insert2 a WHERE (a.key=-1)
PREHOOK: type: QUERY
@@ -217,6 +322,9 @@ 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:
@@ -238,8 +346,36 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.insert1
+ Select Operator
+ expressions: _col0 (type: int), _col1 (type: string)
+ outputColumnNames: key, value
+ Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll')
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 1052 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 1052 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
+ Reducer 2
+ 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: 1068 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 1068 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
@@ -257,6 +393,10 @@ STAGE PLANS:
Stage: Stage-3
Stats Work
Basic Stats Work:
+ Column Stats Desc:
+ Columns: key, value
+ Column Types: int, string
+ Table: default.insert1
PREHOOK: query: explain
from insert2
@@ -280,6 +420,10 @@ STAGE PLANS:
Stage: Stage-2
Tez
#### A masked pattern was here ####
+ Edges:
+ Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE)
+ Reducer 3 <- Map 1 (CUSTOM_SIMPLE_EDGE)
+#### A masked pattern was here ####
Vertices:
Map 1
Map Operator Tree:
@@ -301,6 +445,19 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.insert1
+ Select Operator
+ expressions: _col0 (type: int), _col1 (type: string)
+ outputColumnNames: key, value
+ Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll')
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 1052 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 1052 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>)
Filter Operator
predicate: ((key < 20) and (key > 10)) (type: boolean)
Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE
@@ -316,8 +473,51 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: x.insert1
+ Select Operator
+ expressions: _col0 (type: int), _col1 (type: string)
+ outputColumnNames: key, value
+ Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll')
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 1052 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 1052 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
+ Reducer 2
+ 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: 1068 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 1068 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 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: 1068 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 1068 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
@@ -335,6 +535,10 @@ STAGE PLANS:
Stage: Stage-4
Stats Work
Basic Stats Work:
+ Column Stats Desc:
+ Columns: key, value
+ Column Types: int, string
+ Table: default.insert1
Stage: Stage-1
Move Operator
@@ -349,6 +553,10 @@ STAGE PLANS:
Stage: Stage-5
Stats Work
Basic Stats Work:
+ Column Stats Desc:
+ Columns: key, value
+ Column Types: int, string
+ Table: x.insert1
PREHOOK: query: CREATE DATABASE db2
PREHOOK: type: CREATEDATABASE
http://git-wip-us.apache.org/repos/asf/hive/blob/3bbc24d2/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 61297f0..0506404 100644
--- a/ql/src/test/results/clientpositive/llap/insert_into1.q.out
+++ b/ql/src/test/results/clientpositive/llap/insert_into1.q.out
@@ -26,6 +26,7 @@ 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
@@ -41,7 +42,6 @@ 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: llap
LLAP IO: no inputs
@@ -67,6 +67,34 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.insert_into1
+ Select Operator
+ expressions: _col0 (type: int), _col1 (type: string)
+ outputColumnNames: key, value
+ Statistics: Num rows: 100 Data size: 9500 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: 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:bigint,max: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
@@ -84,6 +112,10 @@ STAGE PLANS:
Stage: Stage-3
Stats Work
Basic Stats Work:
+ Column Stats Desc:
+ Columns: key, value
+ Column Types: int, string
+ Table: default.insert_into1
PREHOOK: query: INSERT INTO TABLE insert_into1 SELECT * from src ORDER BY key LIMIT 100
PREHOOK: type: QUERY
@@ -149,6 +181,7 @@ 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
@@ -164,7 +197,6 @@ 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: llap
LLAP IO: no inputs
@@ -190,6 +222,34 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.insert_into1
+ Select Operator
+ expressions: _col0 (type: int), _col1 (type: string)
+ outputColumnNames: key, value
+ Statistics: Num rows: 100 Data size: 9500 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: 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:bigint,max: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
@@ -207,6 +267,10 @@ STAGE PLANS:
Stage: Stage-3
Stats Work
Basic Stats Work:
+ Column Stats Desc:
+ Columns: key, value
+ Column Types: int, string
+ Table: default.insert_into1
PREHOOK: query: INSERT INTO TABLE insert_into1 SELECT * FROM src ORDER BY key LIMIT 100
PREHOOK: type: QUERY
@@ -272,6 +336,7 @@ 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
@@ -287,7 +352,6 @@ 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: llap
LLAP IO: no inputs
@@ -313,6 +377,34 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.insert_into1
+ Select Operator
+ expressions: _col0 (type: int), _col1 (type: string)
+ outputColumnNames: key, value
+ Statistics: Num rows: 10 Data size: 950 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: 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:bigint,max: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
@@ -330,6 +422,10 @@ STAGE PLANS:
Stage: Stage-3
Stats Work
Basic Stats Work:
+ Column Stats Desc:
+ Columns: key, value
+ Column Types: int, string
+ Table: default.insert_into1
PREHOOK: query: INSERT OVERWRITE TABLE insert_into1 SELECT * FROM src ORDER BY key LIMIT 10
PREHOOK: type: QUERY
@@ -393,6 +489,9 @@ 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:
@@ -412,8 +511,36 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.insert_into1
+ Select Operator
+ expressions: _col0 (type: int), _col1 (type: string)
+ outputColumnNames: key, value
+ Statistics: Num rows: 1 Data size: 89 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: 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: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
+ Reducer 2
+ 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 +558,10 @@ STAGE PLANS:
Stage: Stage-3
Stats Work
Basic Stats Work:
+ Column Stats Desc:
+ Columns: key, value
+ Column Types: int, string
+ Table: default.insert_into1
PREHOOK: query: insert overwrite table insert_into1 select 1, 'a'
PREHOOK: type: QUERY
@@ -456,6 +587,9 @@ 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:
@@ -475,8 +609,36 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.insert_into1
+ Select Operator
+ expressions: _col0 (type: int), _col1 (type: string)
+ outputColumnNames: key, value
+ Statistics: Num rows: 1 Data size: 89 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: 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: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
+ Reducer 2
+ 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
@@ -494,6 +656,10 @@ STAGE PLANS:
Stage: Stage-3
Stats Work
Basic Stats Work:
+ Column Stats Desc:
+ Columns: key, value
+ Column Types: int, string
+ Table: default.insert_into1
PREHOOK: query: insert into insert_into1 select 2, 'b'
PREHOOK: type: QUERY
http://git-wip-us.apache.org/repos/asf/hive/blob/3bbc24d2/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 ef2b875..83f0e3d 100644
--- a/ql/src/test/results/clientpositive/llap/insert_into2.q.out
+++ b/ql/src/test/results/clientpositive/llap/insert_into2.q.out
@@ -30,6 +30,7 @@ STAGE PLANS:
#### A masked pattern was here ####
Edges:
Reducer 2 <- Map 1 (SIMPLE_EDGE)
+ Reducer 3 <- Reducer 2 (SIMPLE_EDGE)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -45,7 +46,6 @@ 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: llap
LLAP IO: no inputs
@@ -71,6 +71,42 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.insert_into2
+ Select Operator
+ expressions: _col0 (type: int), _col1 (type: string), '1' (type: string)
+ outputColumnNames: key, value, ds
+ Statistics: Num rows: 100 Data size: 18000 Basic stats: COMPLETE Column stats: COMPLETE
+ Group By Operator
+ aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll')
+ keys: ds (type: string)
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 949 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: 949 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col1 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col2 (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)
+ keys: KEY._col0 (type: string)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 965 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: _col1 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col2 (type: struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col0 (type: string)
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 965 Basic stats: COMPLETE Column stats: COMPLETE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 965 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
@@ -90,6 +126,10 @@ STAGE PLANS:
Stage: Stage-3
Stats Work
Basic Stats Work:
+ Column Stats Desc:
+ Columns: key, value
+ Column Types: int, string
+ Table: default.insert_into2
PREHOOK: query: INSERT INTO TABLE insert_into2 PARTITION (ds='1') SELECT * FROM src order by key limit 100
PREHOOK: type: QUERY
@@ -194,6 +234,7 @@ STAGE PLANS:
#### A masked pattern was here ####
Edges:
Reducer 2 <- Map 1 (SIMPLE_EDGE)
+ Reducer 3 <- Reducer 2 (SIMPLE_EDGE)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -209,7 +250,6 @@ 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: llap
LLAP IO: no inputs
@@ -235,6 +275,42 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.insert_into2
+ Select Operator
+ expressions: _col0 (type: int), _col1 (type: string), '2' (type: string)
+ outputColumnNames: key, value, ds
+ Statistics: Num rows: 100 Data size: 18000 Basic stats: COMPLETE Column stats: COMPLETE
+ Group By Operator
+ aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll')
+ keys: ds (type: string)
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 949 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: 949 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col1 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col2 (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)
+ keys: KEY._col0 (type: string)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 965 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: _col1 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col2 (type: struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col0 (type: string)
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 965 Basic stats: COMPLETE Column stats: COMPLETE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 965 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
@@ -254,6 +330,10 @@ STAGE PLANS:
Stage: Stage-3
Stats Work
Basic Stats Work:
+ Column Stats Desc:
+ Columns: key, value
+ Column Types: int, string
+ Table: default.insert_into2
PREHOOK: query: INSERT OVERWRITE TABLE insert_into2 PARTITION (ds='2')
SELECT * FROM src order by key LIMIT 100
@@ -327,6 +407,7 @@ STAGE PLANS:
#### A masked pattern was here ####
Edges:
Reducer 2 <- Map 1 (SIMPLE_EDGE)
+ Reducer 3 <- Reducer 2 (SIMPLE_EDGE)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -342,7 +423,6 @@ 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: llap
LLAP IO: no inputs
@@ -368,6 +448,42 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.insert_into2
+ Select Operator
+ expressions: _col0 (type: int), _col1 (type: string), '2' (type: string)
+ outputColumnNames: key, value, ds
+ Statistics: Num rows: 50 Data size: 9000 Basic stats: COMPLETE Column stats: COMPLETE
+ Group By Operator
+ aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll')
+ keys: ds (type: string)
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 949 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: 949 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col1 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col2 (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)
+ keys: KEY._col0 (type: string)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 965 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: _col1 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col2 (type: struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col0 (type: string)
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 965 Basic stats: COMPLETE Column stats: COMPLETE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 965 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
@@ -387,6 +503,10 @@ STAGE PLANS:
Stage: Stage-3
Stats Work
Basic Stats Work:
+ Column Stats Desc:
+ Columns: key, value
+ Column Types: int, string
+ Table: default.insert_into2
PREHOOK: query: INSERT OVERWRITE TABLE insert_into2 PARTITION (ds='2')
SELECT * FROM src order by key LIMIT 50
http://git-wip-us.apache.org/repos/asf/hive/blob/3bbc24d2/ql/src/test/results/clientpositive/llap/insert_values_orig_table_use_metadata.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/insert_values_orig_table_use_metadata.q.out b/ql/src/test/results/clientpositive/llap/insert_values_orig_table_use_metadata.q.out
index 143742b..d135f08 100644
--- a/ql/src/test/results/clientpositive/llap/insert_values_orig_table_use_metadata.q.out
+++ b/ql/src/test/results/clientpositive/llap/insert_values_orig_table_use_metadata.q.out
@@ -167,7 +167,6 @@ Retention: 0
#### A masked pattern was here ####
Table Type: MANAGED_TABLE
Table Parameters:
- COLUMN_STATS_ACCURATE {}
numFiles 1
numRows 0
rawDataSize 0
@@ -371,7 +370,6 @@ Retention: 0
#### A masked pattern was here ####
Table Type: MANAGED_TABLE
Table Parameters:
- COLUMN_STATS_ACCURATE {}
numFiles 1
numRows 0
rawDataSize 0
@@ -504,7 +502,6 @@ Retention: 0
#### A masked pattern was here ####
Table Type: MANAGED_TABLE
Table Parameters:
- COLUMN_STATS_ACCURATE {}
numFiles 2
numRows 0
rawDataSize 0
@@ -635,7 +632,6 @@ Retention: 0
#### A masked pattern was here ####
Table Type: MANAGED_TABLE
Table Parameters:
- COLUMN_STATS_ACCURATE {}
numFiles 3
numRows 0
rawDataSize 0
@@ -787,7 +783,7 @@ 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\"}}
numFiles 1
numRows 500
rawDataSize 5312
@@ -985,7 +981,6 @@ Database: default
Table: sp
#### A masked pattern was here ####
Partition Parameters:
- COLUMN_STATS_ACCURATE {}
numFiles 2
numRows 0
rawDataSize 0
http://git-wip-us.apache.org/repos/asf/hive/blob/3bbc24d2/ql/src/test/results/clientpositive/llap/intersect_all.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/intersect_all.q.out b/ql/src/test/results/clientpositive/llap/intersect_all.q.out
index 69be5e3..1aef092 100644
--- a/ql/src/test/results/clientpositive/llap/intersect_all.q.out
+++ b/ql/src/test/results/clientpositive/llap/intersect_all.q.out
@@ -1551,42 +1551,42 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: a
- Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: value (type: int)
outputColumnNames: value
- Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
keys: value (type: int)
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 4 Data size: 16 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: +
Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: llap
LLAP IO: no inputs
Map 5
Map Operator Tree:
TableScan
alias: b
- Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: key (type: int)
outputColumnNames: key
- Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
keys: key (type: int)
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 2 Data size: 8 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: 8 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
@@ -1596,24 +1596,24 @@ STAGE PLANS:
keys: KEY._col0 (type: int)
mode: mergepartial
outputColumnNames: _col0
- Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count()
keys: _col0 (type: int)
mode: complete
outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: min(_col1), count(_col1)
keys: _col0 (type: int)
mode: hash
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 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: 2 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: bigint), _col2 (type: bigint)
Reducer 4
Execution mode: llap
@@ -1623,24 +1623,24 @@ STAGE PLANS:
keys: KEY._col0 (type: int)
mode: mergepartial
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: (_col2 = 2) (type: boolean)
- Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col1 (type: bigint), _col0 (type: int)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE
UDTF Operator
- Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE
function name: UDTFReplicateRows
Select Operator
expressions: col1 (type: int)
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 4 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: 4 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
@@ -1652,24 +1652,24 @@ STAGE PLANS:
keys: KEY._col0 (type: int)
mode: mergepartial
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
Group By Operator
aggregations: count()
keys: _col0 (type: int)
mode: complete
outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: min(_col1), count(_col1)
keys: _col0 (type: int)
mode: hash
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 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: 2 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: bigint), _col2 (type: bigint)
Union 3
Vertex: Union 3