You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@hive.apache.org by dj...@apache.org on 2018/06/11 00:56:34 UTC
[3/8] hive git commit: HIVE-18875 : Enable SMB Join by default in Tez
(Deepak Jaiswal, reviewed by Gunther Hagleitner)
http://git-wip-us.apache.org/repos/asf/hive/blob/0a961aa8/ql/src/test/results/clientpositive/spark/bucketmapjoin1.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/bucketmapjoin1.q.out b/ql/src/test/results/clientpositive/spark/bucketmapjoin1.q.out
index a79a8c4..82606d9 100644
--- a/ql/src/test/results/clientpositive/spark/bucketmapjoin1.q.out
+++ b/ql/src/test/results/clientpositive/spark/bucketmapjoin1.q.out
@@ -39,8 +39,6 @@ STAGE DEPENDENCIES:
STAGE PLANS:
Stage: Stage-1
Spark
- Edges:
- Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 2), Map 3 (PARTITION-LEVEL SORT, 2)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -57,75 +55,42 @@ STAGE PLANS:
expressions: key (type: int), value (type: string)
outputColumnNames: _col0, _col1
Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: int)
- null sort order: a
- sort order: +
- Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
- tag: 0
- value expressions: _col1 (type: string)
- auto parallelism: false
- Map 3
- Map Operator Tree:
- TableScan
- alias: b
- Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
- GatherStats: false
- Filter Operator
- isSamplingPred: false
- predicate: ((ds = '2008-04-08') and key is not null) (type: boolean)
- Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
- Select Operator
- expressions: key (type: int), value (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: int)
- null sort order: a
- sort order: +
- Map-reduce partition columns: _col0 (type: int)
+ Sorted Merge Bucket Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col0 (type: int)
+ 1 _col0 (type: int)
+ outputColumnNames: _col0, _col1, _col3
+ Position of Big Table: 0
Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
- tag: 1
- value expressions: _col1 (type: string)
- auto parallelism: false
- Reducer 2
- Needs Tagging: true
- Reduce Operator Tree:
- Join Operator
- condition map:
- Inner Join 0 to 1
- keys:
- 0 _col0 (type: int)
- 1 _col0 (type: int)
- outputColumnNames: _col0, _col1, _col3
- Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
- Select Operator
- expressions: _col0 (type: int), _col1 (type: string), _col3 (type: string)
- outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
- File Output Operator
- compressed: false
- GlobalTableId: 0
-#### A masked pattern was here ####
- NumFilesPerFileSink: 1
- Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
-#### A masked pattern was here ####
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- properties:
- columns _col0,_col1,_col2
- columns.types int:string:string
- escape.delim \
- hive.serialization.extend.additional.nesting.levels true
- serialization.escape.crlf true
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- TotalFiles: 1
- GatherStats: false
- MultiFileSpray: false
+ BucketMapJoin: true
+ Select Operator
+ expressions: _col0 (type: int), _col1 (type: string), _col3 (type: string)
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+#### A masked pattern was here ####
+ NumFilesPerFileSink: 1
+ Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
+#### A masked pattern was here ####
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ properties:
+ columns _col0,_col1,_col2
+ columns.types int:string:string
+ escape.delim \
+ hive.serialization.extend.additional.nesting.levels true
+ serialization.escape.crlf true
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ TotalFiles: 1
+ GatherStats: false
+ MultiFileSpray: false
Stage: Stage-0
Fetch Operator
@@ -164,8 +129,6 @@ STAGE DEPENDENCIES:
STAGE PLANS:
Stage: Stage-1
Spark
- Edges:
- Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 2), Map 3 (PARTITION-LEVEL SORT, 2)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -182,75 +145,42 @@ STAGE PLANS:
expressions: key (type: int), value (type: string)
outputColumnNames: _col0, _col1
Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: int)
- null sort order: a
- sort order: +
- Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
- tag: 0
- value expressions: _col1 (type: string)
- auto parallelism: false
- Map 3
- Map Operator Tree:
- TableScan
- alias: b
- Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
- GatherStats: false
- Filter Operator
- isSamplingPred: false
- predicate: ((ds = '2008-04-08') and key is not null) (type: boolean)
- Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
- Select Operator
- expressions: key (type: int), value (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: int)
- null sort order: a
- sort order: +
- Map-reduce partition columns: _col0 (type: int)
+ Sorted Merge Bucket Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col0 (type: int)
+ 1 _col0 (type: int)
+ outputColumnNames: _col0, _col1, _col3
+ Position of Big Table: 0
Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
- tag: 1
- value expressions: _col1 (type: string)
- auto parallelism: false
- Reducer 2
- Needs Tagging: true
- Reduce Operator Tree:
- Join Operator
- condition map:
- Inner Join 0 to 1
- keys:
- 0 _col0 (type: int)
- 1 _col0 (type: int)
- outputColumnNames: _col0, _col1, _col3
- Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
- Select Operator
- expressions: _col0 (type: int), _col1 (type: string), _col3 (type: string)
- outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
- File Output Operator
- compressed: false
- GlobalTableId: 0
-#### A masked pattern was here ####
- NumFilesPerFileSink: 1
- Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
-#### A masked pattern was here ####
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- properties:
- columns _col0,_col1,_col2
- columns.types int:string:string
- escape.delim \
- hive.serialization.extend.additional.nesting.levels true
- serialization.escape.crlf true
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- TotalFiles: 1
- GatherStats: false
- MultiFileSpray: false
+ BucketMapJoin: true
+ Select Operator
+ expressions: _col0 (type: int), _col1 (type: string), _col3 (type: string)
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+#### A masked pattern was here ####
+ NumFilesPerFileSink: 1
+ Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
+#### A masked pattern was here ####
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ properties:
+ columns _col0,_col1,_col2
+ columns.types int:string:string
+ escape.delim \
+ hive.serialization.extend.additional.nesting.levels true
+ serialization.escape.crlf true
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ TotalFiles: 1
+ GatherStats: false
+ MultiFileSpray: false
Stage: Stage-0
Fetch Operator
http://git-wip-us.apache.org/repos/asf/hive/blob/0a961aa8/ql/src/test/results/clientpositive/spark/smb_mapjoin_14.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/smb_mapjoin_14.q.out b/ql/src/test/results/clientpositive/spark/smb_mapjoin_14.q.out
index 1fd4490..f2782cf 100644
--- a/ql/src/test/results/clientpositive/spark/smb_mapjoin_14.q.out
+++ b/ql/src/test/results/clientpositive/spark/smb_mapjoin_14.q.out
@@ -56,8 +56,7 @@ STAGE PLANS:
Stage: Stage-1
Spark
Edges:
- Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 1), Map 4 (PARTITION-LEVEL SORT, 1)
- Reducer 3 <- Reducer 2 (GROUP, 1)
+ Reducer 2 <- Map 1 (GROUP, 1)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -72,49 +71,23 @@ STAGE PLANS:
expressions: key (type: int)
outputColumnNames: _col0
Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: int)
- sort order: +
- Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE
- Execution mode: vectorized
- Map 4
- Map Operator Tree:
- TableScan
- alias: b
- Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- predicate: key is not null (type: boolean)
- Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: key (type: int)
- outputColumnNames: _col0
- Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: int)
- sort order: +
- Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE
- Execution mode: vectorized
+ Sorted Merge Bucket Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col0 (type: int)
+ 1 _col0 (type: int)
+ Statistics: Num rows: 11 Data size: 77 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: count()
+ mode: hash
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: bigint)
Reducer 2
- Reduce Operator Tree:
- Join Operator
- condition map:
- Inner Join 0 to 1
- keys:
- 0 _col0 (type: int)
- 1 _col0 (type: int)
- Statistics: Num rows: 11 Data size: 77 Basic stats: COMPLETE Column stats: NONE
- Group By Operator
- aggregations: count()
- mode: hash
- outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- sort order:
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col0 (type: bigint)
- Reducer 3
Execution mode: vectorized
Reduce Operator Tree:
Group By Operator
@@ -175,9 +148,8 @@ STAGE PLANS:
Stage: Stage-1
Spark
Edges:
- Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 1), Map 5 (PARTITION-LEVEL SORT, 1)
- Reducer 3 <- Reducer 2 (GROUP, 1)
- Reducer 4 <- Reducer 3 (SORT, 1)
+ Reducer 2 <- Map 1 (GROUP, 1)
+ Reducer 3 <- Reducer 2 (SORT, 1)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -192,53 +164,27 @@ STAGE PLANS:
expressions: key (type: int)
outputColumnNames: _col0
Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: int)
- sort order: +
- Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE
- Execution mode: vectorized
- Map 5
- Map Operator Tree:
- TableScan
- alias: b
- Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- predicate: key is not null (type: boolean)
- Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: key (type: int)
- outputColumnNames: _col0
- Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: int)
- sort order: +
- Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE
- Execution mode: vectorized
+ Sorted Merge Bucket Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col0 (type: int)
+ 1 _col0 (type: int)
+ outputColumnNames: _col0
+ Statistics: Num rows: 11 Data size: 77 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: count()
+ keys: _col0 (type: int)
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 11 Data size: 77 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: int)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: int)
+ Statistics: Num rows: 11 Data size: 77 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col1 (type: bigint)
Reducer 2
- Reduce Operator Tree:
- Join Operator
- condition map:
- Inner Join 0 to 1
- keys:
- 0 _col0 (type: int)
- 1 _col0 (type: int)
- outputColumnNames: _col0
- Statistics: Num rows: 11 Data size: 77 Basic stats: COMPLETE Column stats: NONE
- Group By Operator
- aggregations: count()
- keys: _col0 (type: int)
- mode: hash
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 11 Data size: 77 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: int)
- sort order: +
- Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 11 Data size: 77 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col1 (type: bigint)
- Reducer 3
Execution mode: vectorized
Reduce Operator Tree:
Group By Operator
@@ -252,7 +198,7 @@ STAGE PLANS:
sort order: +
Statistics: Num rows: 5 Data size: 35 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: bigint)
- Reducer 4
+ Reducer 3
Execution mode: vectorized
Reduce Operator Tree:
Select Operator
@@ -327,9 +273,8 @@ STAGE PLANS:
Stage: Stage-1
Spark
Edges:
- Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 1), Map 5 (PARTITION-LEVEL SORT, 1)
+ Reducer 2 <- Map 1 (GROUP, 1)
Reducer 3 <- Reducer 2 (GROUP, 1)
- Reducer 4 <- Reducer 3 (GROUP, 1)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -344,51 +289,25 @@ STAGE PLANS:
expressions: key (type: int)
outputColumnNames: _col0
Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: int)
- sort order: +
- Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE
- Execution mode: vectorized
- Map 5
- Map Operator Tree:
- TableScan
- alias: b
- Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- predicate: key is not null (type: boolean)
- Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: key (type: int)
- outputColumnNames: _col0
- Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: int)
- sort order: +
- Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE
- Execution mode: vectorized
+ Sorted Merge Bucket Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col0 (type: int)
+ 1 _col0 (type: int)
+ outputColumnNames: _col0
+ Statistics: Num rows: 11 Data size: 77 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ keys: _col0 (type: int)
+ mode: hash
+ outputColumnNames: _col0
+ Statistics: Num rows: 11 Data size: 77 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: int)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: int)
+ Statistics: Num rows: 11 Data size: 77 Basic stats: COMPLETE Column stats: NONE
Reducer 2
- Reduce Operator Tree:
- Join Operator
- condition map:
- Inner Join 0 to 1
- keys:
- 0 _col0 (type: int)
- 1 _col0 (type: int)
- outputColumnNames: _col0
- Statistics: Num rows: 11 Data size: 77 Basic stats: COMPLETE Column stats: NONE
- Group By Operator
- keys: _col0 (type: int)
- mode: hash
- outputColumnNames: _col0
- Statistics: Num rows: 11 Data size: 77 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: int)
- sort order: +
- Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 11 Data size: 77 Basic stats: COMPLETE Column stats: NONE
- Reducer 3
Execution mode: vectorized
Reduce Operator Tree:
Group By Operator
@@ -407,7 +326,7 @@ STAGE PLANS:
sort order:
Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
value expressions: _col0 (type: bigint)
- Reducer 4
+ Reducer 3
Execution mode: vectorized
Reduce Operator Tree:
Group By Operator
@@ -476,8 +395,7 @@ STAGE PLANS:
Stage: Stage-1
Spark
Edges:
- Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 1), Map 4 (PARTITION-LEVEL SORT, 1)
- Reducer 3 <- Reducer 2 (GROUP, 1)
+ Reducer 2 <- Map 1 (GROUP, 1)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -492,49 +410,23 @@ STAGE PLANS:
expressions: key (type: int)
outputColumnNames: _col0
Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: int)
- sort order: +
- Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE
- Execution mode: vectorized
- Map 4
- Map Operator Tree:
- TableScan
- alias: a
- Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- predicate: (key < 6) (type: boolean)
- Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: key (type: int)
- outputColumnNames: _col0
- Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: int)
- sort order: +
- Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE
- Execution mode: vectorized
+ Sorted Merge Bucket Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col0 (type: int)
+ 1 _col0 (type: int)
+ Statistics: Num rows: 3 Data size: 23 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: count()
+ mode: hash
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: bigint)
Reducer 2
- Reduce Operator Tree:
- Join Operator
- condition map:
- Inner Join 0 to 1
- keys:
- 0 _col0 (type: int)
- 1 _col0 (type: int)
- Statistics: Num rows: 3 Data size: 23 Basic stats: COMPLETE Column stats: NONE
- Group By Operator
- aggregations: count()
- mode: hash
- outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- sort order:
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col0 (type: bigint)
- Reducer 3
Execution mode: vectorized
Reduce Operator Tree:
Group By Operator
@@ -607,8 +499,7 @@ STAGE PLANS:
Stage: Stage-1
Spark
Edges:
- Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 1), Map 4 (PARTITION-LEVEL SORT, 1)
- Reducer 3 <- Reducer 2 (GROUP, 1)
+ Reducer 2 <- Map 1 (GROUP, 1)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -623,49 +514,23 @@ STAGE PLANS:
expressions: key (type: int)
outputColumnNames: _col0
Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: int)
- sort order: +
- Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE
- Execution mode: vectorized
- Map 4
- Map Operator Tree:
- TableScan
- alias: b
- Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- predicate: (key < 6) (type: boolean)
- Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: key (type: int)
- outputColumnNames: _col0
- Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: int)
- sort order: +
- Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE
- Execution mode: vectorized
+ Sorted Merge Bucket Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col0 (type: int)
+ 1 _col0 (type: int)
+ Statistics: Num rows: 3 Data size: 23 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: count()
+ mode: hash
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: bigint)
Reducer 2
- Reduce Operator Tree:
- Join Operator
- condition map:
- Inner Join 0 to 1
- keys:
- 0 _col0 (type: int)
- 1 _col0 (type: int)
- Statistics: Num rows: 3 Data size: 23 Basic stats: COMPLETE Column stats: NONE
- Group By Operator
- aggregations: count()
- mode: hash
- outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- sort order:
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col0 (type: bigint)
- Reducer 3
Execution mode: vectorized
Reduce Operator Tree:
Group By Operator
@@ -762,8 +627,7 @@ STAGE PLANS:
Stage: Stage-1
Spark
Edges:
- Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 1), Map 4 (PARTITION-LEVEL SORT, 1)
- Reducer 3 <- Reducer 2 (GROUP, 1)
+ Reducer 2 <- Map 1 (GROUP, 1)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -778,49 +642,23 @@ STAGE PLANS:
expressions: key (type: int)
outputColumnNames: _col0
Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: int)
- sort order: +
- Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE
- Execution mode: vectorized
- Map 4
- Map Operator Tree:
- TableScan
- alias: a
- Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- predicate: (key < 6) (type: boolean)
- Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: key (type: int)
- outputColumnNames: _col0
- Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: int)
- sort order: +
- Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE
- Execution mode: vectorized
+ Sorted Merge Bucket Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col0 (type: int)
+ 1 _col0 (type: int)
+ Statistics: Num rows: 3 Data size: 23 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: count()
+ mode: hash
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: bigint)
Reducer 2
- Reduce Operator Tree:
- Join Operator
- condition map:
- Inner Join 0 to 1
- keys:
- 0 _col0 (type: int)
- 1 _col0 (type: int)
- Statistics: Num rows: 3 Data size: 23 Basic stats: COMPLETE Column stats: NONE
- Group By Operator
- aggregations: count()
- mode: hash
- outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- sort order:
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col0 (type: bigint)
- Reducer 3
Execution mode: vectorized
Reduce Operator Tree:
Group By Operator
@@ -905,8 +743,7 @@ STAGE PLANS:
Stage: Stage-1
Spark
Edges:
- Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 1), Map 4 (PARTITION-LEVEL SORT, 1)
- Reducer 3 <- Reducer 2 (GROUP, 1)
+ Reducer 2 <- Map 1 (GROUP, 1)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -921,49 +758,23 @@ STAGE PLANS:
expressions: key (type: int)
outputColumnNames: _col0
Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: int)
- sort order: +
- Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE
- Execution mode: vectorized
- Map 4
- Map Operator Tree:
- TableScan
- alias: a
- Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- predicate: (key < 8) (type: boolean)
- Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: key (type: int)
- outputColumnNames: _col0
- Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: int)
- sort order: +
- Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE
- Execution mode: vectorized
+ Sorted Merge Bucket Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col0 (type: int)
+ 1 _col0 (type: int)
+ Statistics: Num rows: 3 Data size: 23 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: count()
+ mode: hash
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: bigint)
Reducer 2
- Reduce Operator Tree:
- Join Operator
- condition map:
- Inner Join 0 to 1
- keys:
- 0 _col0 (type: int)
- 1 _col0 (type: int)
- Statistics: Num rows: 3 Data size: 23 Basic stats: COMPLETE Column stats: NONE
- Group By Operator
- aggregations: count()
- mode: hash
- outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- sort order:
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col0 (type: bigint)
- Reducer 3
Execution mode: vectorized
Reduce Operator Tree:
Group By Operator
@@ -1143,8 +954,7 @@ STAGE PLANS:
Stage: Stage-1
Spark
Edges:
- Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 1), Map 4 (PARTITION-LEVEL SORT, 1)
- Reducer 3 <- Reducer 2 (GROUP, 1)
+ Reducer 2 <- Map 1 (GROUP, 1)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -1159,49 +969,23 @@ STAGE PLANS:
expressions: key (type: int)
outputColumnNames: _col0
Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: int)
- sort order: +
- Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE
- Execution mode: vectorized
- Map 4
- Map Operator Tree:
- TableScan
- alias: a
- Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- predicate: (key < 6) (type: boolean)
- Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: key (type: int)
- outputColumnNames: _col0
- Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: int)
- sort order: +
- Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE
- Execution mode: vectorized
+ Sorted Merge Bucket Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col0 (type: int)
+ 1 _col0 (type: int)
+ Statistics: Num rows: 3 Data size: 23 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: count()
+ mode: hash
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: bigint)
Reducer 2
- Reduce Operator Tree:
- Join Operator
- condition map:
- Inner Join 0 to 1
- keys:
- 0 _col0 (type: int)
- 1 _col0 (type: int)
- Statistics: Num rows: 3 Data size: 23 Basic stats: COMPLETE Column stats: NONE
- Group By Operator
- aggregations: count()
- mode: hash
- outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- sort order:
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col0 (type: bigint)
- Reducer 3
Execution mode: vectorized
Reduce Operator Tree:
Group By Operator
@@ -1256,8 +1040,7 @@ STAGE PLANS:
Stage: Stage-1
Spark
Edges:
- Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 1), Map 4 (PARTITION-LEVEL SORT, 1)
- Reducer 3 <- Reducer 2 (GROUP, 1)
+ Reducer 2 <- Map 1 (GROUP, 1)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -1272,49 +1055,23 @@ STAGE PLANS:
expressions: key (type: int)
outputColumnNames: _col0
Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: int)
- sort order: +
- Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE
- Execution mode: vectorized
- Map 4
- Map Operator Tree:
- TableScan
- alias: a
- Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- predicate: (key < 6) (type: boolean)
- Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: key (type: int)
- outputColumnNames: _col0
- Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: int)
- sort order: +
- Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE
- Execution mode: vectorized
+ Sorted Merge Bucket Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col0 (type: int)
+ 1 _col0 (type: int)
+ Statistics: Num rows: 3 Data size: 23 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: count()
+ mode: hash
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: bigint)
Reducer 2
- Reduce Operator Tree:
- Join Operator
- condition map:
- Inner Join 0 to 1
- keys:
- 0 _col0 (type: int)
- 1 _col0 (type: int)
- Statistics: Num rows: 3 Data size: 23 Basic stats: COMPLETE Column stats: NONE
- Group By Operator
- aggregations: count()
- mode: hash
- outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- sort order:
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col0 (type: bigint)
- Reducer 3
Execution mode: vectorized
Reduce Operator Tree:
Group By Operator
@@ -1379,8 +1136,7 @@ STAGE PLANS:
Stage: Stage-1
Spark
Edges:
- Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 1), Map 4 (PARTITION-LEVEL SORT, 1), Map 5 (PARTITION-LEVEL SORT, 1)
- Reducer 3 <- Reducer 2 (GROUP, 1)
+ Reducer 2 <- Map 1 (GROUP, 1)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -1395,69 +1151,25 @@ STAGE PLANS:
expressions: key (type: int)
outputColumnNames: _col0
Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: int)
- sort order: +
- Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE
- Execution mode: vectorized
- Map 4
- Map Operator Tree:
- TableScan
- alias: a
- Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- predicate: (key < 6) (type: boolean)
- Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: key (type: int)
- outputColumnNames: _col0
- Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: int)
- sort order: +
- Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE
- Execution mode: vectorized
- Map 5
- Map Operator Tree:
- TableScan
- alias: a
- Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- predicate: (key < 6) (type: boolean)
- Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: key (type: int)
- outputColumnNames: _col0
- Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: int)
- sort order: +
- Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE
- Execution mode: vectorized
+ Sorted Merge Bucket Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ Inner Join 0 to 2
+ keys:
+ 0 _col0 (type: int)
+ 1 _col0 (type: int)
+ 2 _col0 (type: int)
+ Statistics: Num rows: 6 Data size: 46 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: count()
+ mode: hash
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: bigint)
Reducer 2
- Reduce Operator Tree:
- Join Operator
- condition map:
- Inner Join 0 to 1
- Inner Join 0 to 2
- keys:
- 0 _col0 (type: int)
- 1 _col0 (type: int)
- 2 _col0 (type: int)
- Statistics: Num rows: 6 Data size: 46 Basic stats: COMPLETE Column stats: NONE
- Group By Operator
- aggregations: count()
- mode: hash
- outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- sort order:
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col0 (type: bigint)
- Reducer 3
Execution mode: vectorized
Reduce Operator Tree:
Group By Operator
@@ -1538,8 +1250,7 @@ STAGE PLANS:
Stage: Stage-1
Spark
Edges:
- Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 1), Map 4 (PARTITION-LEVEL SORT, 1)
- Reducer 3 <- Reducer 2 (GROUP, 1)
+ Reducer 2 <- Map 1 (GROUP, 1)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -1554,49 +1265,23 @@ STAGE PLANS:
expressions: key (type: int)
outputColumnNames: _col0
Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: int)
- sort order: +
- Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE
- Execution mode: vectorized
- Map 4
- Map Operator Tree:
- TableScan
- alias: b
- Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- predicate: (key < 6) (type: boolean)
- Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: key (type: int)
- outputColumnNames: _col0
- Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: int)
- sort order: +
- Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE
- Execution mode: vectorized
+ Sorted Merge Bucket Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col0 (type: int)
+ 1 _col0 (type: int)
+ Statistics: Num rows: 3 Data size: 23 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: count()
+ mode: hash
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: bigint)
Reducer 2
- Reduce Operator Tree:
- Join Operator
- condition map:
- Inner Join 0 to 1
- keys:
- 0 _col0 (type: int)
- 1 _col0 (type: int)
- Statistics: Num rows: 3 Data size: 23 Basic stats: COMPLETE Column stats: NONE
- Group By Operator
- aggregations: count()
- mode: hash
- outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- sort order:
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col0 (type: bigint)
- Reducer 3
Execution mode: vectorized
Reduce Operator Tree:
Group By Operator
http://git-wip-us.apache.org/repos/asf/hive/blob/0a961aa8/ql/src/test/results/clientpositive/spark/smb_mapjoin_15.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/smb_mapjoin_15.q.out b/ql/src/test/results/clientpositive/spark/smb_mapjoin_15.q.out
index 6ca577f..d442e17 100644
--- a/ql/src/test/results/clientpositive/spark/smb_mapjoin_15.q.out
+++ b/ql/src/test/results/clientpositive/spark/smb_mapjoin_15.q.out
@@ -46,8 +46,7 @@ STAGE PLANS:
Stage: Stage-1
Spark
Edges:
- Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 1), Map 4 (PARTITION-LEVEL SORT, 1)
- Reducer 3 <- Reducer 2 (SORT, 1)
+ Reducer 2 <- Map 1 (SORT, 1)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -64,16 +63,26 @@ STAGE PLANS:
expressions: key (type: int), value (type: string)
outputColumnNames: _col0, _col1
Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: int)
- null sort order: a
- sort order: +
- Map-reduce partition columns: _col0 (type: int)
+ Sorted Merge Bucket Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col0 (type: int)
+ 1 _col0 (type: int)
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Position of Big Table: 0
Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE
- tag: 0
- value expressions: _col1 (type: string)
- auto parallelism: false
- Execution mode: vectorized
+ BucketMapJoin: true
+ Reduce Output Operator
+ key expressions: _col0 (type: int)
+ null sort order: a
+ sort order: +
+ Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE
+ tag: -1
+ TopN: 10
+ TopN Hash Memory Usage: 0.1
+ value expressions: _col1 (type: string), _col2 (type: int), _col3 (type: string)
+ auto parallelism: false
Path -> Alias:
#### A masked pattern was here ####
Path -> Partition:
@@ -131,109 +140,7 @@ STAGE PLANS:
name: default.test_table1_n4
Truncated Path -> Alias:
/test_table1_n4 [$hdt$_0:a]
- Map 4
- Map Operator Tree:
- TableScan
- alias: b
- Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE
- GatherStats: false
- Filter Operator
- isSamplingPred: false
- predicate: key is not null (type: boolean)
- Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: key (type: int), value (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: int)
- null sort order: a
- sort order: +
- Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE
- tag: 1
- value expressions: _col1 (type: string)
- auto parallelism: false
- Execution mode: vectorized
- Path -> Alias:
-#### A masked pattern was here ####
- Path -> Partition:
-#### A masked pattern was here ####
- Partition
- base file name: test_table2_n4
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"}
- SORTBUCKETCOLSPREFIX TRUE
- bucket_count 16
- bucket_field_name key
- bucketing_version 2
- column.name.delimiter ,
- columns key,value
- columns.comments
- columns.types int:string
-#### A masked pattern was here ####
- name default.test_table2_n4
- numFiles 16
- numRows 500
- rawDataSize 5312
- serialization.ddl struct test_table2_n4 { i32 key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 5812
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"}
- SORTBUCKETCOLSPREFIX TRUE
- bucket_count 16
- bucket_field_name key
- bucketing_version 2
- column.name.delimiter ,
- columns key,value
- columns.comments
- columns.types int:string
-#### A masked pattern was here ####
- name default.test_table2_n4
- numFiles 16
- numRows 500
- rawDataSize 5312
- serialization.ddl struct test_table2_n4 { i32 key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 5812
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.test_table2_n4
- name: default.test_table2_n4
- Truncated Path -> Alias:
- /test_table2_n4 [$hdt$_1:b]
Reducer 2
- Needs Tagging: true
- Reduce Operator Tree:
- Join Operator
- condition map:
- Inner Join 0 to 1
- keys:
- 0 _col0 (type: int)
- 1 _col0 (type: int)
- outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: int)
- null sort order: a
- sort order: +
- Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE
- tag: -1
- TopN: 10
- TopN Hash Memory Usage: 0.1
- value expressions: _col1 (type: string), _col2 (type: int), _col3 (type: string)
- auto parallelism: false
- Reducer 3
Execution mode: vectorized
Needs Tagging: false
Reduce Operator Tree:
@@ -359,8 +266,7 @@ STAGE PLANS:
Stage: Stage-1
Spark
Edges:
- Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 1), Map 4 (PARTITION-LEVEL SORT, 1)
- Reducer 3 <- Reducer 2 (SORT, 1)
+ Reducer 2 <- Map 1 (SORT, 1)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -377,16 +283,26 @@ STAGE PLANS:
expressions: key (type: int), key2 (type: int), value (type: string)
outputColumnNames: _col0, _col1, _col2
Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: int), _col1 (type: int)
- null sort order: aa
- sort order: ++
- Map-reduce partition columns: _col0 (type: int), _col1 (type: int)
+ Sorted Merge Bucket Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col0 (type: int), _col1 (type: int)
+ 1 _col0 (type: int), _col1 (type: int)
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
+ Position of Big Table: 0
Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE
- tag: 0
- value expressions: _col2 (type: string)
- auto parallelism: false
- Execution mode: vectorized
+ BucketMapJoin: true
+ Reduce Output Operator
+ key expressions: _col0 (type: int)
+ null sort order: a
+ sort order: +
+ Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE
+ tag: -1
+ TopN: 10
+ TopN Hash Memory Usage: 0.1
+ value expressions: _col1 (type: int), _col2 (type: string), _col3 (type: int), _col4 (type: int), _col5 (type: string)
+ auto parallelism: false
Path -> Alias:
#### A masked pattern was here ####
Path -> Partition:
@@ -444,109 +360,7 @@ STAGE PLANS:
name: default.test_table1_n4
Truncated Path -> Alias:
/test_table1_n4 [$hdt$_0:a]
- Map 4
- Map Operator Tree:
- TableScan
- alias: b
- Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE
- GatherStats: false
- Filter Operator
- isSamplingPred: false
- predicate: (key is not null and key2 is not null) (type: boolean)
- Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: key (type: int), key2 (type: int), value (type: string)
- outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: int), _col1 (type: int)
- null sort order: aa
- sort order: ++
- Map-reduce partition columns: _col0 (type: int), _col1 (type: int)
- Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE
- tag: 1
- value expressions: _col2 (type: string)
- auto parallelism: false
- Execution mode: vectorized
- Path -> Alias:
-#### A masked pattern was here ####
- Path -> Partition:
-#### A masked pattern was here ####
- Partition
- base file name: test_table2_n4
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"}
- SORTBUCKETCOLSPREFIX TRUE
- bucket_count 16
- bucket_field_name key
- bucketing_version 2
- column.name.delimiter ,
- columns key,key2,value
- columns.comments
- columns.types int:int:string
-#### A masked pattern was here ####
- name default.test_table2_n4
- numFiles 16
- numRows 500
- rawDataSize 7218
- serialization.ddl struct test_table2_n4 { i32 key, i32 key2, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 7718
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"}
- SORTBUCKETCOLSPREFIX TRUE
- bucket_count 16
- bucket_field_name key
- bucketing_version 2
- column.name.delimiter ,
- columns key,key2,value
- columns.comments
- columns.types int:int:string
-#### A masked pattern was here ####
- name default.test_table2_n4
- numFiles 16
- numRows 500
- rawDataSize 7218
- serialization.ddl struct test_table2_n4 { i32 key, i32 key2, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 7718
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.test_table2_n4
- name: default.test_table2_n4
- Truncated Path -> Alias:
- /test_table2_n4 [$hdt$_1:b]
Reducer 2
- Needs Tagging: true
- Reduce Operator Tree:
- Join Operator
- condition map:
- Inner Join 0 to 1
- keys:
- 0 _col0 (type: int), _col1 (type: int)
- 1 _col0 (type: int), _col1 (type: int)
- outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
- Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: int)
- null sort order: a
- sort order: +
- Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE
- tag: -1
- TopN: 10
- TopN Hash Memory Usage: 0.1
- value expressions: _col1 (type: int), _col2 (type: string), _col3 (type: int), _col4 (type: int), _col5 (type: string)
- auto parallelism: false
- Reducer 3
Execution mode: vectorized
Needs Tagging: false
Reduce Operator Tree:
@@ -620,8 +434,7 @@ STAGE PLANS:
Stage: Stage-1
Spark
Edges:
- Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 1), Map 4 (PARTITION-LEVEL SORT, 1)
- Reducer 3 <- Reducer 2 (SORT, 1)
+ Reducer 2 <- Map 1 (SORT, 1)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -638,16 +451,26 @@ STAGE PLANS:
expressions: key (type: int), key2 (type: int), value (type: string)
outputColumnNames: _col0, _col1, _col2
Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: int), _col1 (type: int)
- null sort order: aa
- sort order: ++
- Map-reduce partition columns: _col0 (type: int), _col1 (type: int)
+ Sorted Merge Bucket Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col0 (type: int), _col1 (type: int)
+ 1 _col0 (type: int), _col1 (type: int)
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
+ Position of Big Table: 0
Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE
- tag: 0
- value expressions: _col2 (type: string)
- auto parallelism: false
- Execution mode: vectorized
+ BucketMapJoin: true
+ Reduce Output Operator
+ key expressions: _col0 (type: int)
+ null sort order: a
+ sort order: +
+ Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE
+ tag: -1
+ TopN: 10
+ TopN Hash Memory Usage: 0.1
+ value expressions: _col1 (type: int), _col2 (type: string), _col3 (type: int), _col4 (type: int), _col5 (type: string)
+ auto parallelism: false
Path -> Alias:
#### A masked pattern was here ####
Path -> Partition:
@@ -705,109 +528,7 @@ STAGE PLANS:
name: default.test_table1_n4
Truncated Path -> Alias:
/test_table1_n4 [$hdt$_0:a]
- Map 4
- Map Operator Tree:
- TableScan
- alias: b
- Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE
- GatherStats: false
- Filter Operator
- isSamplingPred: false
- predicate: (key is not null and key2 is not null) (type: boolean)
- Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: key (type: int), key2 (type: int), value (type: string)
- outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: int), _col1 (type: int)
- null sort order: aa
- sort order: ++
- Map-reduce partition columns: _col0 (type: int), _col1 (type: int)
- Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE
- tag: 1
- value expressions: _col2 (type: string)
- auto parallelism: false
- Execution mode: vectorized
- Path -> Alias:
-#### A masked pattern was here ####
- Path -> Partition:
-#### A masked pattern was here ####
- Partition
- base file name: test_table2_n4
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"}
- SORTBUCKETCOLSPREFIX TRUE
- bucket_count 16
- bucket_field_name key
- bucketing_version 2
- column.name.delimiter ,
- columns key,key2,value
- columns.comments
- columns.types int:int:string
-#### A masked pattern was here ####
- name default.test_table2_n4
- numFiles 16
- numRows 500
- rawDataSize 7218
- serialization.ddl struct test_table2_n4 { i32 key, i32 key2, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 7718
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"}
- SORTBUCKETCOLSPREFIX TRUE
- bucket_count 16
- bucket_field_name key
- bucketing_version 2
- column.name.delimiter ,
- columns key,key2,value
- columns.comments
- columns.types int:int:string
-#### A masked pattern was here ####
- name default.test_table2_n4
- numFiles 16
- numRows 500
- rawDataSize 7218
- serialization.ddl struct test_table2_n4 { i32 key, i32 key2, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 7718
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.test_table2_n4
- name: default.test_table2_n4
- Truncated Path -> Alias:
- /test_table2_n4 [$hdt$_1:b]
Reducer 2
- Needs Tagging: true
- Reduce Operator Tree:
- Join Operator
- condition map:
- Inner Join 0 to 1
- keys:
- 0 _col0 (type: int), _col1 (type: int)
- 1 _col0 (type: int), _col1 (type: int)
- outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
- Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: int)
- null sort order: a
- sort order: +
- Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: NONE
- tag: -1
- TopN: 10
- TopN Hash Memory Usage: 0.1
- value expressions: _col1 (type: int), _col2 (type: string), _col3 (type: int), _col4 (type: int), _col5 (type: string)
- auto parallelism: false
- Reducer 3
Execution mode: vectorized
Needs Tagging: false
Reduce Operator Tree: