You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@hive.apache.org by xu...@apache.org on 2014/12/15 18:11:42 UTC
svn commit: r1642997 [37/42] - in /hive/branches/spark:
itests/src/test/resources/
ql/src/java/org/apache/hadoop/hive/ql/optimizer/spark/
ql/src/test/results/clientpositive/spark/
Modified: hive/branches/spark/ql/src/test/results/clientpositive/spark/smb_mapjoin_3.q.out
URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/smb_mapjoin_3.q.out?rev=1642997&r1=1642996&r2=1642997&view=diff
==============================================================================
--- hive/branches/spark/ql/src/test/results/clientpositive/spark/smb_mapjoin_3.q.out (original)
+++ hive/branches/spark/ql/src/test/results/clientpositive/spark/smb_mapjoin_3.q.out Tue Dec 2 19:57:10 2014
@@ -61,35 +61,14 @@ POSTHOOK: query: explain
select /*+mapjoin(a)*/ * from smb_bucket_2 a join smb_bucket_3 b on a.key = b.key
POSTHOOK: type: QUERY
STAGE DEPENDENCIES:
- Stage-2 is a root stage
- Stage-1 depends on stages: Stage-2
+ Stage-1 is a root stage
Stage-0 depends on stages: Stage-1
STAGE PLANS:
- Stage: Stage-2
- Spark
-#### A masked pattern was here ####
- Vertices:
- Map 2
- Map Operator Tree:
- TableScan
- alias: b
- Statistics: Num rows: 2 Data size: 222 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- predicate: key is not null (type: boolean)
- Statistics: Num rows: 1 Data size: 111 Basic stats: COMPLETE Column stats: NONE
- Spark HashTable Sink Operator
- condition expressions:
- 0 {key} {value}
- 1 {value}
- keys:
- 0 key (type: int)
- 1 key (type: int)
- Local Work:
- Map Reduce Local Work
-
Stage: Stage-1
Spark
+ Edges:
+ Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 1), Map 3 (PARTITION-LEVEL SORT, 1)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -100,32 +79,47 @@ STAGE PLANS:
Filter Operator
predicate: key is not null (type: boolean)
Statistics: Num rows: 1 Data size: 206 Basic stats: COMPLETE Column stats: NONE
- Map Join Operator
- condition map:
- Inner Join 0 to 1
- condition expressions:
- 0 {key} {value}
- 1 {key} {value}
- keys:
- 0 key (type: int)
- 1 key (type: int)
- outputColumnNames: _col0, _col1, _col5, _col6
- input vertices:
- 1 Map 2
- Statistics: Num rows: 1 Data size: 226 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col0 (type: int), _col1 (type: string), _col5 (type: int), _col6 (type: string)
- outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 1 Data size: 226 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 1 Data size: 226 Basic stats: COMPLETE Column stats: NONE
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- Local Work:
- Map Reduce Local Work
+ Reduce Output Operator
+ key expressions: key (type: int)
+ sort order: +
+ Map-reduce partition columns: key (type: int)
+ Statistics: Num rows: 1 Data size: 206 Basic stats: COMPLETE Column stats: NONE
+ value expressions: value (type: string)
+ Map 3
+ Map Operator Tree:
+ TableScan
+ alias: b
+ Statistics: Num rows: 2 Data size: 222 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: key is not null (type: boolean)
+ Statistics: Num rows: 1 Data size: 111 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: key (type: int)
+ sort order: +
+ Map-reduce partition columns: key (type: int)
+ Statistics: Num rows: 1 Data size: 111 Basic stats: COMPLETE Column stats: NONE
+ value expressions: value (type: string)
+ Reducer 2
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0 {KEY.reducesinkkey0} {VALUE._col0}
+ 1 {KEY.reducesinkkey0} {VALUE._col0}
+ outputColumnNames: _col0, _col1, _col5, _col6
+ Statistics: Num rows: 1 Data size: 226 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: int), _col1 (type: string), _col5 (type: int), _col6 (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 1 Data size: 226 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 226 Basic stats: COMPLETE Column stats: NONE
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
Stage: Stage-0
Fetch Operator
@@ -152,32 +146,14 @@ POSTHOOK: query: explain
select /*+mapjoin(a)*/ * from smb_bucket_2 a left outer join smb_bucket_3 b on a.key = b.key
POSTHOOK: type: QUERY
STAGE DEPENDENCIES:
- Stage-2 is a root stage
- Stage-1 depends on stages: Stage-2
+ Stage-1 is a root stage
Stage-0 depends on stages: Stage-1
STAGE PLANS:
- Stage: Stage-2
- Spark
-#### A masked pattern was here ####
- Vertices:
- Map 2
- Map Operator Tree:
- TableScan
- alias: b
- Statistics: Num rows: 2 Data size: 222 Basic stats: COMPLETE Column stats: NONE
- Spark HashTable Sink Operator
- condition expressions:
- 0 {key} {value}
- 1 {value}
- keys:
- 0 key (type: int)
- 1 key (type: int)
- Local Work:
- Map Reduce Local Work
-
Stage: Stage-1
Spark
+ Edges:
+ Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 3), Map 3 (PARTITION-LEVEL SORT, 3)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -185,32 +161,44 @@ STAGE PLANS:
TableScan
alias: a
Statistics: Num rows: 1 Data size: 206 Basic stats: COMPLETE Column stats: NONE
- Map Join Operator
- condition map:
- Left Outer Join0 to 1
- condition expressions:
- 0 {key} {value}
- 1 {key} {value}
- keys:
- 0 key (type: int)
- 1 key (type: int)
- outputColumnNames: _col0, _col1, _col5, _col6
- input vertices:
- 1 Map 2
+ Reduce Output Operator
+ key expressions: key (type: int)
+ sort order: +
+ Map-reduce partition columns: key (type: int)
+ Statistics: Num rows: 1 Data size: 206 Basic stats: COMPLETE Column stats: NONE
+ value expressions: value (type: string)
+ Map 3
+ Map Operator Tree:
+ TableScan
+ alias: b
+ Statistics: Num rows: 2 Data size: 222 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: key (type: int)
+ sort order: +
+ Map-reduce partition columns: key (type: int)
+ Statistics: Num rows: 2 Data size: 222 Basic stats: COMPLETE Column stats: NONE
+ value expressions: value (type: string)
+ Reducer 2
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Left Outer Join0 to 1
+ condition expressions:
+ 0 {KEY.reducesinkkey0} {VALUE._col0}
+ 1 {KEY.reducesinkkey0} {VALUE._col0}
+ outputColumnNames: _col0, _col1, _col5, _col6
+ Statistics: Num rows: 2 Data size: 244 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: int), _col1 (type: string), _col5 (type: int), _col6 (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 2 Data size: 244 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
Statistics: Num rows: 2 Data size: 244 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col0 (type: int), _col1 (type: string), _col5 (type: int), _col6 (type: string)
- outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 2 Data size: 244 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 2 Data size: 244 Basic stats: COMPLETE Column stats: NONE
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- Local Work:
- Map Reduce Local Work
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
Stage: Stage-0
Fetch Operator
@@ -239,13 +227,14 @@ POSTHOOK: query: explain
select /*+mapjoin(a)*/ * from smb_bucket_2 a right outer join smb_bucket_3 b on a.key = b.key
POSTHOOK: type: QUERY
STAGE DEPENDENCIES:
- Stage-2 is a root stage
- Stage-1 depends on stages: Stage-2
+ Stage-1 is a root stage
Stage-0 depends on stages: Stage-1
STAGE PLANS:
- Stage: Stage-2
+ Stage: Stage-1
Spark
+ Edges:
+ Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 3), Map 3 (PARTITION-LEVEL SORT, 3)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -253,51 +242,44 @@ STAGE PLANS:
TableScan
alias: a
Statistics: Num rows: 1 Data size: 206 Basic stats: COMPLETE Column stats: NONE
- Spark HashTable Sink Operator
- condition expressions:
- 0 {value}
- 1 {key} {value}
- keys:
- 0 key (type: int)
- 1 key (type: int)
- Local Work:
- Map Reduce Local Work
-
- Stage: Stage-1
- Spark
-#### A masked pattern was here ####
- Vertices:
- Map 2
+ Reduce Output Operator
+ key expressions: key (type: int)
+ sort order: +
+ Map-reduce partition columns: key (type: int)
+ Statistics: Num rows: 1 Data size: 206 Basic stats: COMPLETE Column stats: NONE
+ value expressions: value (type: string)
+ Map 3
Map Operator Tree:
TableScan
alias: b
Statistics: Num rows: 2 Data size: 222 Basic stats: COMPLETE Column stats: NONE
- Map Join Operator
- condition map:
- Right Outer Join0 to 1
- condition expressions:
- 0 {key} {value}
- 1 {key} {value}
- keys:
- 0 key (type: int)
- 1 key (type: int)
- outputColumnNames: _col0, _col1, _col5, _col6
- input vertices:
- 0 Map 1
+ Reduce Output Operator
+ key expressions: key (type: int)
+ sort order: +
+ Map-reduce partition columns: key (type: int)
+ Statistics: Num rows: 2 Data size: 222 Basic stats: COMPLETE Column stats: NONE
+ value expressions: value (type: string)
+ Reducer 2
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Right Outer Join0 to 1
+ condition expressions:
+ 0 {KEY.reducesinkkey0} {VALUE._col0}
+ 1 {KEY.reducesinkkey0} {VALUE._col0}
+ outputColumnNames: _col0, _col1, _col5, _col6
+ Statistics: Num rows: 2 Data size: 244 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: int), _col1 (type: string), _col5 (type: int), _col6 (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 2 Data size: 244 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
Statistics: Num rows: 2 Data size: 244 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col0 (type: int), _col1 (type: string), _col5 (type: int), _col6 (type: string)
- outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 2 Data size: 244 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 2 Data size: 244 Basic stats: COMPLETE Column stats: NONE
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- Local Work:
- Map Reduce Local Work
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
Stage: Stage-0
Fetch Operator
@@ -413,35 +395,14 @@ POSTHOOK: query: explain
select /*+mapjoin(b)*/ * from smb_bucket_2 a join smb_bucket_3 b on a.key = b.key
POSTHOOK: type: QUERY
STAGE DEPENDENCIES:
- Stage-2 is a root stage
- Stage-1 depends on stages: Stage-2
+ Stage-1 is a root stage
Stage-0 depends on stages: Stage-1
STAGE PLANS:
- Stage: Stage-2
- Spark
-#### A masked pattern was here ####
- Vertices:
- Map 2
- Map Operator Tree:
- TableScan
- alias: b
- Statistics: Num rows: 2 Data size: 222 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- predicate: key is not null (type: boolean)
- Statistics: Num rows: 1 Data size: 111 Basic stats: COMPLETE Column stats: NONE
- Spark HashTable Sink Operator
- condition expressions:
- 0 {key} {value}
- 1 {value}
- keys:
- 0 key (type: int)
- 1 key (type: int)
- Local Work:
- Map Reduce Local Work
-
Stage: Stage-1
Spark
+ Edges:
+ Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 3), Map 3 (PARTITION-LEVEL SORT, 3)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -452,32 +413,47 @@ STAGE PLANS:
Filter Operator
predicate: key is not null (type: boolean)
Statistics: Num rows: 1 Data size: 206 Basic stats: COMPLETE Column stats: NONE
- Map Join Operator
- condition map:
- Inner Join 0 to 1
- condition expressions:
- 0 {key} {value}
- 1 {key} {value}
- keys:
- 0 key (type: int)
- 1 key (type: int)
- outputColumnNames: _col0, _col1, _col5, _col6
- input vertices:
- 1 Map 2
- Statistics: Num rows: 1 Data size: 226 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col0 (type: int), _col1 (type: string), _col5 (type: int), _col6 (type: string)
- outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 1 Data size: 226 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 1 Data size: 226 Basic stats: COMPLETE Column stats: NONE
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- Local Work:
- Map Reduce Local Work
+ Reduce Output Operator
+ key expressions: key (type: int)
+ sort order: +
+ Map-reduce partition columns: key (type: int)
+ Statistics: Num rows: 1 Data size: 206 Basic stats: COMPLETE Column stats: NONE
+ value expressions: value (type: string)
+ Map 3
+ Map Operator Tree:
+ TableScan
+ alias: b
+ Statistics: Num rows: 2 Data size: 222 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: key is not null (type: boolean)
+ Statistics: Num rows: 1 Data size: 111 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: key (type: int)
+ sort order: +
+ Map-reduce partition columns: key (type: int)
+ Statistics: Num rows: 1 Data size: 111 Basic stats: COMPLETE Column stats: NONE
+ value expressions: value (type: string)
+ Reducer 2
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0 {KEY.reducesinkkey0} {VALUE._col0}
+ 1 {KEY.reducesinkkey0} {VALUE._col0}
+ outputColumnNames: _col0, _col1, _col5, _col6
+ Statistics: Num rows: 1 Data size: 226 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: int), _col1 (type: string), _col5 (type: int), _col6 (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 1 Data size: 226 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 226 Basic stats: COMPLETE Column stats: NONE
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
Stage: Stage-0
Fetch Operator
@@ -504,32 +480,14 @@ POSTHOOK: query: explain
select /*+mapjoin(b)*/ * from smb_bucket_2 a left outer join smb_bucket_3 b on a.key = b.key
POSTHOOK: type: QUERY
STAGE DEPENDENCIES:
- Stage-2 is a root stage
- Stage-1 depends on stages: Stage-2
+ Stage-1 is a root stage
Stage-0 depends on stages: Stage-1
STAGE PLANS:
- Stage: Stage-2
- Spark
-#### A masked pattern was here ####
- Vertices:
- Map 2
- Map Operator Tree:
- TableScan
- alias: b
- Statistics: Num rows: 2 Data size: 222 Basic stats: COMPLETE Column stats: NONE
- Spark HashTable Sink Operator
- condition expressions:
- 0 {key} {value}
- 1 {value}
- keys:
- 0 key (type: int)
- 1 key (type: int)
- Local Work:
- Map Reduce Local Work
-
Stage: Stage-1
Spark
+ Edges:
+ Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 3), Map 3 (PARTITION-LEVEL SORT, 3)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -537,32 +495,44 @@ STAGE PLANS:
TableScan
alias: a
Statistics: Num rows: 1 Data size: 206 Basic stats: COMPLETE Column stats: NONE
- Map Join Operator
- condition map:
- Left Outer Join0 to 1
- condition expressions:
- 0 {key} {value}
- 1 {key} {value}
- keys:
- 0 key (type: int)
- 1 key (type: int)
- outputColumnNames: _col0, _col1, _col5, _col6
- input vertices:
- 1 Map 2
+ Reduce Output Operator
+ key expressions: key (type: int)
+ sort order: +
+ Map-reduce partition columns: key (type: int)
+ Statistics: Num rows: 1 Data size: 206 Basic stats: COMPLETE Column stats: NONE
+ value expressions: value (type: string)
+ Map 3
+ Map Operator Tree:
+ TableScan
+ alias: b
+ Statistics: Num rows: 2 Data size: 222 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: key (type: int)
+ sort order: +
+ Map-reduce partition columns: key (type: int)
+ Statistics: Num rows: 2 Data size: 222 Basic stats: COMPLETE Column stats: NONE
+ value expressions: value (type: string)
+ Reducer 2
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Left Outer Join0 to 1
+ condition expressions:
+ 0 {KEY.reducesinkkey0} {VALUE._col0}
+ 1 {KEY.reducesinkkey0} {VALUE._col0}
+ outputColumnNames: _col0, _col1, _col5, _col6
+ Statistics: Num rows: 2 Data size: 244 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: int), _col1 (type: string), _col5 (type: int), _col6 (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 2 Data size: 244 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
Statistics: Num rows: 2 Data size: 244 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col0 (type: int), _col1 (type: string), _col5 (type: int), _col6 (type: string)
- outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 2 Data size: 244 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 2 Data size: 244 Basic stats: COMPLETE Column stats: NONE
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- Local Work:
- Map Reduce Local Work
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
Stage: Stage-0
Fetch Operator
@@ -591,13 +561,14 @@ POSTHOOK: query: explain
select /*+mapjoin(b)*/ * from smb_bucket_2 a right outer join smb_bucket_3 b on a.key = b.key
POSTHOOK: type: QUERY
STAGE DEPENDENCIES:
- Stage-2 is a root stage
- Stage-1 depends on stages: Stage-2
+ Stage-1 is a root stage
Stage-0 depends on stages: Stage-1
STAGE PLANS:
- Stage: Stage-2
+ Stage: Stage-1
Spark
+ Edges:
+ Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 3), Map 3 (PARTITION-LEVEL SORT, 3)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -605,51 +576,44 @@ STAGE PLANS:
TableScan
alias: a
Statistics: Num rows: 1 Data size: 206 Basic stats: COMPLETE Column stats: NONE
- Spark HashTable Sink Operator
- condition expressions:
- 0 {value}
- 1 {key} {value}
- keys:
- 0 key (type: int)
- 1 key (type: int)
- Local Work:
- Map Reduce Local Work
-
- Stage: Stage-1
- Spark
-#### A masked pattern was here ####
- Vertices:
- Map 2
+ Reduce Output Operator
+ key expressions: key (type: int)
+ sort order: +
+ Map-reduce partition columns: key (type: int)
+ Statistics: Num rows: 1 Data size: 206 Basic stats: COMPLETE Column stats: NONE
+ value expressions: value (type: string)
+ Map 3
Map Operator Tree:
TableScan
alias: b
Statistics: Num rows: 2 Data size: 222 Basic stats: COMPLETE Column stats: NONE
- Map Join Operator
- condition map:
- Right Outer Join0 to 1
- condition expressions:
- 0 {key} {value}
- 1 {key} {value}
- keys:
- 0 key (type: int)
- 1 key (type: int)
- outputColumnNames: _col0, _col1, _col5, _col6
- input vertices:
- 0 Map 1
+ Reduce Output Operator
+ key expressions: key (type: int)
+ sort order: +
+ Map-reduce partition columns: key (type: int)
+ Statistics: Num rows: 2 Data size: 222 Basic stats: COMPLETE Column stats: NONE
+ value expressions: value (type: string)
+ Reducer 2
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Right Outer Join0 to 1
+ condition expressions:
+ 0 {KEY.reducesinkkey0} {VALUE._col0}
+ 1 {KEY.reducesinkkey0} {VALUE._col0}
+ outputColumnNames: _col0, _col1, _col5, _col6
+ Statistics: Num rows: 2 Data size: 244 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: int), _col1 (type: string), _col5 (type: int), _col6 (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 2 Data size: 244 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
Statistics: Num rows: 2 Data size: 244 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col0 (type: int), _col1 (type: string), _col5 (type: int), _col6 (type: string)
- outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 2 Data size: 244 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 2 Data size: 244 Basic stats: COMPLETE Column stats: NONE
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- Local Work:
- Map Reduce Local Work
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
Stage: Stage-0
Fetch Operator
Modified: hive/branches/spark/ql/src/test/results/clientpositive/spark/smb_mapjoin_4.q.out
URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/smb_mapjoin_4.q.out?rev=1642997&r1=1642996&r2=1642997&view=diff
==============================================================================
--- hive/branches/spark/ql/src/test/results/clientpositive/spark/smb_mapjoin_4.q.out (original)
+++ hive/branches/spark/ql/src/test/results/clientpositive/spark/smb_mapjoin_4.q.out Tue Dec 2 19:57:10 2014
@@ -57,13 +57,14 @@ explain
select /*+mapjoin(a,b)*/ * from smb_bucket_1 a join smb_bucket_2 b on a.key = b.key join smb_bucket_3 c on b.key=c.key
POSTHOOK: type: QUERY
STAGE DEPENDENCIES:
- Stage-2 is a root stage
- Stage-1 depends on stages: Stage-2
+ Stage-1 is a root stage
Stage-0 depends on stages: Stage-1
STAGE PLANS:
- Stage: Stage-2
+ Stage: Stage-1
Spark
+ Edges:
+ Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 1), Map 3 (PARTITION-LEVEL SORT, 1), Map 4 (PARTITION-LEVEL SORT, 1)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -74,79 +75,63 @@ STAGE PLANS:
Filter Operator
predicate: key is not null (type: boolean)
Statistics: Num rows: 1 Data size: 104 Basic stats: COMPLETE Column stats: NONE
- Spark HashTable Sink Operator
- condition expressions:
- 0 {value}
- 1 {key} {value}
- 2 {key} {value}
- keys:
- 0 key (type: int)
- 1 key (type: int)
- 2 key (type: int)
- Local Work:
- Map Reduce Local Work
+ Reduce Output Operator
+ key expressions: key (type: int)
+ sort order: +
+ Map-reduce partition columns: key (type: int)
+ Statistics: Num rows: 1 Data size: 104 Basic stats: COMPLETE Column stats: NONE
+ value expressions: value (type: string)
Map 3
Map Operator Tree:
TableScan
- alias: c
- Statistics: Num rows: 2 Data size: 222 Basic stats: COMPLETE Column stats: NONE
+ alias: b
+ Statistics: Num rows: 1 Data size: 206 Basic stats: COMPLETE Column stats: NONE
Filter Operator
predicate: key is not null (type: boolean)
- Statistics: Num rows: 1 Data size: 111 Basic stats: COMPLETE Column stats: NONE
- Spark HashTable Sink Operator
- condition expressions:
- 0 {key} {value}
- 1 {key} {value}
- 2 {value}
- keys:
- 0 key (type: int)
- 1 key (type: int)
- 2 key (type: int)
- Local Work:
- Map Reduce Local Work
-
- Stage: Stage-1
- Spark
-#### A masked pattern was here ####
- Vertices:
- Map 2
+ Statistics: Num rows: 1 Data size: 206 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: key (type: int)
+ sort order: +
+ Map-reduce partition columns: key (type: int)
+ Statistics: Num rows: 1 Data size: 206 Basic stats: COMPLETE Column stats: NONE
+ value expressions: value (type: string)
+ Map 4
Map Operator Tree:
TableScan
- alias: b
- Statistics: Num rows: 1 Data size: 206 Basic stats: COMPLETE Column stats: NONE
+ alias: c
+ Statistics: Num rows: 2 Data size: 222 Basic stats: COMPLETE Column stats: NONE
Filter Operator
predicate: key is not null (type: boolean)
- Statistics: Num rows: 1 Data size: 206 Basic stats: COMPLETE Column stats: NONE
- Map Join Operator
- condition map:
- Inner Join 0 to 1
- Inner Join 1 to 2
- condition expressions:
- 0 {key} {value}
- 1 {key} {value}
- 2 {key} {value}
- keys:
- 0 key (type: int)
- 1 key (type: int)
- 2 key (type: int)
- outputColumnNames: _col0, _col1, _col5, _col6, _col10, _col11
- input vertices:
- 0 Map 1
- 2 Map 3
- Statistics: Num rows: 2 Data size: 228 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col0 (type: int), _col1 (type: string), _col5 (type: int), _col6 (type: string), _col10 (type: int), _col11 (type: string)
- outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
- Statistics: Num rows: 2 Data size: 228 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 2 Data size: 228 Basic stats: COMPLETE Column stats: NONE
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- Local Work:
- Map Reduce Local Work
+ Statistics: Num rows: 1 Data size: 111 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: key (type: int)
+ sort order: +
+ Map-reduce partition columns: key (type: int)
+ Statistics: Num rows: 1 Data size: 111 Basic stats: COMPLETE Column stats: NONE
+ value expressions: value (type: string)
+ Reducer 2
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ Inner Join 1 to 2
+ condition expressions:
+ 0 {KEY.reducesinkkey0} {VALUE._col0}
+ 1 {KEY.reducesinkkey0} {VALUE._col0}
+ 2 {KEY.reducesinkkey0} {VALUE._col0}
+ outputColumnNames: _col0, _col1, _col5, _col6, _col10, _col11
+ Statistics: Num rows: 2 Data size: 228 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: int), _col1 (type: string), _col5 (type: int), _col6 (type: string), _col10 (type: int), _col11 (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
+ Statistics: Num rows: 2 Data size: 228 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 2 Data size: 228 Basic stats: COMPLETE Column stats: NONE
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
Stage: Stage-0
Fetch Operator
@@ -173,87 +158,72 @@ POSTHOOK: query: explain
select /*+mapjoin(a,b)*/ * from smb_bucket_1 a left outer join smb_bucket_2 b on a.key = b.key join smb_bucket_3 c on b.key=c.key
POSTHOOK: type: QUERY
STAGE DEPENDENCIES:
- Stage-2 is a root stage
- Stage-1 depends on stages: Stage-2
+ Stage-1 is a root stage
Stage-0 depends on stages: Stage-1
STAGE PLANS:
- Stage: Stage-2
+ Stage: Stage-1
Spark
+ Edges:
+ Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 3), Map 3 (PARTITION-LEVEL SORT, 3), Map 4 (PARTITION-LEVEL SORT, 3)
#### A masked pattern was here ####
Vertices:
- Map 2
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: a
+ Statistics: Num rows: 2 Data size: 208 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: key (type: int)
+ sort order: +
+ Map-reduce partition columns: key (type: int)
+ Statistics: Num rows: 2 Data size: 208 Basic stats: COMPLETE Column stats: NONE
+ value expressions: value (type: string)
+ Map 3
Map Operator Tree:
TableScan
alias: b
Statistics: Num rows: 1 Data size: 206 Basic stats: COMPLETE Column stats: NONE
- Spark HashTable Sink Operator
- condition expressions:
- 0 {key} {value}
- 1 {value}
- 2 {key} {value}
- keys:
- 0 key (type: int)
- 1 key (type: int)
- 2 key (type: int)
- Local Work:
- Map Reduce Local Work
- Map 3
+ Reduce Output Operator
+ key expressions: key (type: int)
+ sort order: +
+ Map-reduce partition columns: key (type: int)
+ Statistics: Num rows: 1 Data size: 206 Basic stats: COMPLETE Column stats: NONE
+ value expressions: value (type: string)
+ Map 4
Map Operator Tree:
TableScan
alias: c
Statistics: Num rows: 2 Data size: 222 Basic stats: COMPLETE Column stats: NONE
- Spark HashTable Sink Operator
- condition expressions:
- 0 {key} {value}
- 1 {key} {value}
- 2 {value}
- keys:
- 0 key (type: int)
- 1 key (type: int)
- 2 key (type: int)
- Local Work:
- Map Reduce Local Work
-
- Stage: Stage-1
- Spark
-#### A masked pattern was here ####
- Vertices:
- Map 1
- Map Operator Tree:
- TableScan
- alias: a
- Statistics: Num rows: 2 Data size: 208 Basic stats: COMPLETE Column stats: NONE
- Map Join Operator
- condition map:
- Left Outer Join0 to 1
- Inner Join 1 to 2
- condition expressions:
- 0 {key} {value}
- 1 {key} {value}
- 2 {key} {value}
- keys:
- 0 key (type: int)
- 1 key (type: int)
- 2 key (type: int)
- outputColumnNames: _col0, _col1, _col5, _col6, _col10, _col11
- input vertices:
- 1 Map 2
- 2 Map 3
+ Reduce Output Operator
+ key expressions: key (type: int)
+ sort order: +
+ Map-reduce partition columns: key (type: int)
+ Statistics: Num rows: 2 Data size: 222 Basic stats: COMPLETE Column stats: NONE
+ value expressions: value (type: string)
+ Reducer 2
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Left Outer Join0 to 1
+ Inner Join 1 to 2
+ condition expressions:
+ 0 {KEY.reducesinkkey0} {VALUE._col0}
+ 1 {KEY.reducesinkkey0} {VALUE._col0}
+ 2 {KEY.reducesinkkey0} {VALUE._col0}
+ outputColumnNames: _col0, _col1, _col5, _col6, _col10, _col11
+ Statistics: Num rows: 4 Data size: 457 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: int), _col1 (type: string), _col5 (type: int), _col6 (type: string), _col10 (type: int), _col11 (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
+ Statistics: Num rows: 4 Data size: 457 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
Statistics: Num rows: 4 Data size: 457 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col0 (type: int), _col1 (type: string), _col5 (type: int), _col6 (type: string), _col10 (type: int), _col11 (type: string)
- outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
- Statistics: Num rows: 4 Data size: 457 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 4 Data size: 457 Basic stats: COMPLETE Column stats: NONE
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- Local Work:
- Map Reduce Local Work
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
Stage: Stage-0
Fetch Operator
@@ -280,87 +250,72 @@ POSTHOOK: query: explain
select /*+mapjoin(a,b)*/ * from smb_bucket_1 a left outer join smb_bucket_2 b on a.key = b.key left outer join smb_bucket_3 c on b.key=c.key
POSTHOOK: type: QUERY
STAGE DEPENDENCIES:
- Stage-2 is a root stage
- Stage-1 depends on stages: Stage-2
+ Stage-1 is a root stage
Stage-0 depends on stages: Stage-1
STAGE PLANS:
- Stage: Stage-2
+ Stage: Stage-1
Spark
+ Edges:
+ Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 3), Map 3 (PARTITION-LEVEL SORT, 3), Map 4 (PARTITION-LEVEL SORT, 3)
#### A masked pattern was here ####
Vertices:
- Map 2
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: a
+ Statistics: Num rows: 2 Data size: 208 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: key (type: int)
+ sort order: +
+ Map-reduce partition columns: key (type: int)
+ Statistics: Num rows: 2 Data size: 208 Basic stats: COMPLETE Column stats: NONE
+ value expressions: value (type: string)
+ Map 3
Map Operator Tree:
TableScan
alias: b
Statistics: Num rows: 1 Data size: 206 Basic stats: COMPLETE Column stats: NONE
- Spark HashTable Sink Operator
- condition expressions:
- 0 {key} {value}
- 1 {value}
- 2 {key} {value}
- keys:
- 0 key (type: int)
- 1 key (type: int)
- 2 key (type: int)
- Local Work:
- Map Reduce Local Work
- Map 3
+ Reduce Output Operator
+ key expressions: key (type: int)
+ sort order: +
+ Map-reduce partition columns: key (type: int)
+ Statistics: Num rows: 1 Data size: 206 Basic stats: COMPLETE Column stats: NONE
+ value expressions: value (type: string)
+ Map 4
Map Operator Tree:
TableScan
alias: c
Statistics: Num rows: 2 Data size: 222 Basic stats: COMPLETE Column stats: NONE
- Spark HashTable Sink Operator
- condition expressions:
- 0 {key} {value}
- 1 {key} {value}
- 2 {value}
- keys:
- 0 key (type: int)
- 1 key (type: int)
- 2 key (type: int)
- Local Work:
- Map Reduce Local Work
-
- Stage: Stage-1
- Spark
-#### A masked pattern was here ####
- Vertices:
- Map 1
- Map Operator Tree:
- TableScan
- alias: a
- Statistics: Num rows: 2 Data size: 208 Basic stats: COMPLETE Column stats: NONE
- Map Join Operator
- condition map:
- Left Outer Join0 to 1
- Left Outer Join1 to 2
- condition expressions:
- 0 {key} {value}
- 1 {key} {value}
- 2 {key} {value}
- keys:
- 0 key (type: int)
- 1 key (type: int)
- 2 key (type: int)
- outputColumnNames: _col0, _col1, _col5, _col6, _col10, _col11
- input vertices:
- 1 Map 2
- 2 Map 3
+ Reduce Output Operator
+ key expressions: key (type: int)
+ sort order: +
+ Map-reduce partition columns: key (type: int)
+ Statistics: Num rows: 2 Data size: 222 Basic stats: COMPLETE Column stats: NONE
+ value expressions: value (type: string)
+ Reducer 2
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Left Outer Join0 to 1
+ Left Outer Join1 to 2
+ condition expressions:
+ 0 {KEY.reducesinkkey0} {VALUE._col0}
+ 1 {KEY.reducesinkkey0} {VALUE._col0}
+ 2 {KEY.reducesinkkey0} {VALUE._col0}
+ outputColumnNames: _col0, _col1, _col5, _col6, _col10, _col11
+ Statistics: Num rows: 4 Data size: 457 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: int), _col1 (type: string), _col5 (type: int), _col6 (type: string), _col10 (type: int), _col11 (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
+ Statistics: Num rows: 4 Data size: 457 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
Statistics: Num rows: 4 Data size: 457 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col0 (type: int), _col1 (type: string), _col5 (type: int), _col6 (type: string), _col10 (type: int), _col11 (type: string)
- outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
- Statistics: Num rows: 4 Data size: 457 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 4 Data size: 457 Basic stats: COMPLETE Column stats: NONE
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- Local Work:
- Map Reduce Local Work
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
Stage: Stage-0
Fetch Operator
@@ -392,13 +347,14 @@ POSTHOOK: query: explain
select /*+mapjoin(a,b)*/ * from smb_bucket_1 a left outer join smb_bucket_2 b on a.key = b.key right outer join smb_bucket_3 c on b.key=c.key
POSTHOOK: type: QUERY
STAGE DEPENDENCIES:
- Stage-2 is a root stage
- Stage-1 depends on stages: Stage-2
+ Stage-1 is a root stage
Stage-0 depends on stages: Stage-1
STAGE PLANS:
- Stage: Stage-2
+ Stage: Stage-1
Spark
+ Edges:
+ Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 3), Map 3 (PARTITION-LEVEL SORT, 3), Map 4 (PARTITION-LEVEL SORT, 3)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -406,73 +362,57 @@ STAGE PLANS:
TableScan
alias: a
Statistics: Num rows: 2 Data size: 208 Basic stats: COMPLETE Column stats: NONE
- Spark HashTable Sink Operator
- condition expressions:
- 0 {value}
- 1 {key} {value}
- 2 {key} {value}
- keys:
- 0 key (type: int)
- 1 key (type: int)
- 2 key (type: int)
- Local Work:
- Map Reduce Local Work
- Map 2
+ Reduce Output Operator
+ key expressions: key (type: int)
+ sort order: +
+ Map-reduce partition columns: key (type: int)
+ Statistics: Num rows: 2 Data size: 208 Basic stats: COMPLETE Column stats: NONE
+ value expressions: value (type: string)
+ Map 3
Map Operator Tree:
TableScan
alias: b
Statistics: Num rows: 1 Data size: 206 Basic stats: COMPLETE Column stats: NONE
- Spark HashTable Sink Operator
- condition expressions:
- 0 {key} {value}
- 1 {value}
- 2 {key} {value}
- keys:
- 0 key (type: int)
- 1 key (type: int)
- 2 key (type: int)
- Local Work:
- Map Reduce Local Work
-
- Stage: Stage-1
- Spark
-#### A masked pattern was here ####
- Vertices:
- Map 3
+ Reduce Output Operator
+ key expressions: key (type: int)
+ sort order: +
+ Map-reduce partition columns: key (type: int)
+ Statistics: Num rows: 1 Data size: 206 Basic stats: COMPLETE Column stats: NONE
+ value expressions: value (type: string)
+ Map 4
Map Operator Tree:
TableScan
alias: c
Statistics: Num rows: 2 Data size: 222 Basic stats: COMPLETE Column stats: NONE
- Map Join Operator
- condition map:
- Left Outer Join0 to 1
- Right Outer Join1 to 2
- condition expressions:
- 0 {key} {value}
- 1 {key} {value}
- 2 {key} {value}
- keys:
- 0 key (type: int)
- 1 key (type: int)
- 2 key (type: int)
- outputColumnNames: _col0, _col1, _col5, _col6, _col10, _col11
- input vertices:
- 0 Map 1
- 1 Map 2
+ Reduce Output Operator
+ key expressions: key (type: int)
+ sort order: +
+ Map-reduce partition columns: key (type: int)
+ Statistics: Num rows: 2 Data size: 222 Basic stats: COMPLETE Column stats: NONE
+ value expressions: value (type: string)
+ Reducer 2
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Left Outer Join0 to 1
+ Right Outer Join1 to 2
+ condition expressions:
+ 0 {KEY.reducesinkkey0} {VALUE._col0}
+ 1 {KEY.reducesinkkey0} {VALUE._col0}
+ 2 {KEY.reducesinkkey0} {VALUE._col0}
+ outputColumnNames: _col0, _col1, _col5, _col6, _col10, _col11
+ Statistics: Num rows: 4 Data size: 457 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: int), _col1 (type: string), _col5 (type: int), _col6 (type: string), _col10 (type: int), _col11 (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
+ Statistics: Num rows: 4 Data size: 457 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
Statistics: Num rows: 4 Data size: 457 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col0 (type: int), _col1 (type: string), _col5 (type: int), _col6 (type: string), _col10 (type: int), _col11 (type: string)
- outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
- Statistics: Num rows: 4 Data size: 457 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 4 Data size: 457 Basic stats: COMPLETE Column stats: NONE
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- Local Work:
- Map Reduce Local Work
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
Stage: Stage-0
Fetch Operator
@@ -608,13 +548,14 @@ POSTHOOK: query: explain
select /*+mapjoin(a,b)*/ * from smb_bucket_1 a right outer join smb_bucket_2 b on a.key = b.key join smb_bucket_3 c on b.key=c.key
POSTHOOK: type: QUERY
STAGE DEPENDENCIES:
- Stage-2 is a root stage
- Stage-1 depends on stages: Stage-2
+ Stage-1 is a root stage
Stage-0 depends on stages: Stage-1
STAGE PLANS:
- Stage: Stage-2
+ Stage: Stage-1
Spark
+ Edges:
+ Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 3), Map 3 (PARTITION-LEVEL SORT, 3), Map 4 (PARTITION-LEVEL SORT, 3)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -622,73 +563,57 @@ STAGE PLANS:
TableScan
alias: a
Statistics: Num rows: 2 Data size: 208 Basic stats: COMPLETE Column stats: NONE
- Spark HashTable Sink Operator
- condition expressions:
- 0 {value}
- 1 {key} {value}
- 2 {key} {value}
- keys:
- 0 key (type: int)
- 1 key (type: int)
- 2 key (type: int)
- Local Work:
- Map Reduce Local Work
- Map 2
+ Reduce Output Operator
+ key expressions: key (type: int)
+ sort order: +
+ Map-reduce partition columns: key (type: int)
+ Statistics: Num rows: 2 Data size: 208 Basic stats: COMPLETE Column stats: NONE
+ value expressions: value (type: string)
+ Map 3
Map Operator Tree:
TableScan
alias: b
Statistics: Num rows: 1 Data size: 206 Basic stats: COMPLETE Column stats: NONE
- Spark HashTable Sink Operator
- condition expressions:
- 0 {key} {value}
- 1 {value}
- 2 {key} {value}
- keys:
- 0 key (type: int)
- 1 key (type: int)
- 2 key (type: int)
- Local Work:
- Map Reduce Local Work
-
- Stage: Stage-1
- Spark
-#### A masked pattern was here ####
- Vertices:
- Map 3
+ Reduce Output Operator
+ key expressions: key (type: int)
+ sort order: +
+ Map-reduce partition columns: key (type: int)
+ Statistics: Num rows: 1 Data size: 206 Basic stats: COMPLETE Column stats: NONE
+ value expressions: value (type: string)
+ Map 4
Map Operator Tree:
TableScan
alias: c
Statistics: Num rows: 2 Data size: 222 Basic stats: COMPLETE Column stats: NONE
- Map Join Operator
- condition map:
- Right Outer Join0 to 1
- Inner Join 1 to 2
- condition expressions:
- 0 {key} {value}
- 1 {key} {value}
- 2 {key} {value}
- keys:
- 0 key (type: int)
- 1 key (type: int)
- 2 key (type: int)
- outputColumnNames: _col0, _col1, _col5, _col6, _col10, _col11
- input vertices:
- 0 Map 1
- 1 Map 2
+ Reduce Output Operator
+ key expressions: key (type: int)
+ sort order: +
+ Map-reduce partition columns: key (type: int)
+ Statistics: Num rows: 2 Data size: 222 Basic stats: COMPLETE Column stats: NONE
+ value expressions: value (type: string)
+ Reducer 2
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Right Outer Join0 to 1
+ Inner Join 1 to 2
+ condition expressions:
+ 0 {KEY.reducesinkkey0} {VALUE._col0}
+ 1 {KEY.reducesinkkey0} {VALUE._col0}
+ 2 {KEY.reducesinkkey0} {VALUE._col0}
+ outputColumnNames: _col0, _col1, _col5, _col6, _col10, _col11
+ Statistics: Num rows: 4 Data size: 457 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: int), _col1 (type: string), _col5 (type: int), _col6 (type: string), _col10 (type: int), _col11 (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
+ Statistics: Num rows: 4 Data size: 457 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
Statistics: Num rows: 4 Data size: 457 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col0 (type: int), _col1 (type: string), _col5 (type: int), _col6 (type: string), _col10 (type: int), _col11 (type: string)
- outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
- Statistics: Num rows: 4 Data size: 457 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 4 Data size: 457 Basic stats: COMPLETE Column stats: NONE
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- Local Work:
- Map Reduce Local Work
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
Stage: Stage-0
Fetch Operator
@@ -717,13 +642,14 @@ POSTHOOK: query: explain
select /*+mapjoin(a,b)*/ * from smb_bucket_1 a right outer join smb_bucket_2 b on a.key = b.key left outer join smb_bucket_3 c on b.key=c.key
POSTHOOK: type: QUERY
STAGE DEPENDENCIES:
- Stage-2 is a root stage
- Stage-1 depends on stages: Stage-2
+ Stage-1 is a root stage
Stage-0 depends on stages: Stage-1
STAGE PLANS:
- Stage: Stage-2
+ Stage: Stage-1
Spark
+ Edges:
+ Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 3), Map 3 (PARTITION-LEVEL SORT, 3), Map 4 (PARTITION-LEVEL SORT, 3)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -731,73 +657,57 @@ STAGE PLANS:
TableScan
alias: a
Statistics: Num rows: 2 Data size: 208 Basic stats: COMPLETE Column stats: NONE
- Spark HashTable Sink Operator
- condition expressions:
- 0 {value}
- 1 {key} {value}
- 2 {key} {value}
- keys:
- 0 key (type: int)
- 1 key (type: int)
- 2 key (type: int)
- Local Work:
- Map Reduce Local Work
+ Reduce Output Operator
+ key expressions: key (type: int)
+ sort order: +
+ Map-reduce partition columns: key (type: int)
+ Statistics: Num rows: 2 Data size: 208 Basic stats: COMPLETE Column stats: NONE
+ value expressions: value (type: string)
Map 3
Map Operator Tree:
TableScan
- alias: c
- Statistics: Num rows: 2 Data size: 222 Basic stats: COMPLETE Column stats: NONE
- Spark HashTable Sink Operator
- condition expressions:
- 0 {key} {value}
- 1 {key} {value}
- 2 {value}
- keys:
- 0 key (type: int)
- 1 key (type: int)
- 2 key (type: int)
- Local Work:
- Map Reduce Local Work
-
- Stage: Stage-1
- Spark
-#### A masked pattern was here ####
- Vertices:
- Map 2
- Map Operator Tree:
- TableScan
alias: b
Statistics: Num rows: 1 Data size: 206 Basic stats: COMPLETE Column stats: NONE
- Map Join Operator
- condition map:
- Right Outer Join0 to 1
- Left Outer Join1 to 2
- condition expressions:
- 0 {key} {value}
- 1 {key} {value}
- 2 {key} {value}
- keys:
- 0 key (type: int)
- 1 key (type: int)
- 2 key (type: int)
- outputColumnNames: _col0, _col1, _col5, _col6, _col10, _col11
- input vertices:
- 0 Map 1
- 2 Map 3
+ Reduce Output Operator
+ key expressions: key (type: int)
+ sort order: +
+ Map-reduce partition columns: key (type: int)
+ Statistics: Num rows: 1 Data size: 206 Basic stats: COMPLETE Column stats: NONE
+ value expressions: value (type: string)
+ Map 4
+ Map Operator Tree:
+ TableScan
+ alias: c
+ Statistics: Num rows: 2 Data size: 222 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: key (type: int)
+ sort order: +
+ Map-reduce partition columns: key (type: int)
+ Statistics: Num rows: 2 Data size: 222 Basic stats: COMPLETE Column stats: NONE
+ value expressions: value (type: string)
+ Reducer 2
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Right Outer Join0 to 1
+ Left Outer Join1 to 2
+ condition expressions:
+ 0 {KEY.reducesinkkey0} {VALUE._col0}
+ 1 {KEY.reducesinkkey0} {VALUE._col0}
+ 2 {KEY.reducesinkkey0} {VALUE._col0}
+ outputColumnNames: _col0, _col1, _col5, _col6, _col10, _col11
+ Statistics: Num rows: 4 Data size: 457 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: int), _col1 (type: string), _col5 (type: int), _col6 (type: string), _col10 (type: int), _col11 (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
+ Statistics: Num rows: 4 Data size: 457 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
Statistics: Num rows: 4 Data size: 457 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col0 (type: int), _col1 (type: string), _col5 (type: int), _col6 (type: string), _col10 (type: int), _col11 (type: string)
- outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
- Statistics: Num rows: 4 Data size: 457 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 4 Data size: 457 Basic stats: COMPLETE Column stats: NONE
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- Local Work:
- Map Reduce Local Work
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
Stage: Stage-0
Fetch Operator
@@ -828,13 +738,14 @@ POSTHOOK: query: explain
select /*+mapjoin(a,b)*/ * from smb_bucket_1 a right outer join smb_bucket_2 b on a.key = b.key right outer join smb_bucket_3 c on b.key=c.key
POSTHOOK: type: QUERY
STAGE DEPENDENCIES:
- Stage-2 is a root stage
- Stage-1 depends on stages: Stage-2
+ Stage-1 is a root stage
Stage-0 depends on stages: Stage-1
STAGE PLANS:
- Stage: Stage-2
+ Stage: Stage-1
Spark
+ Edges:
+ Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 3), Map 3 (PARTITION-LEVEL SORT, 3), Map 4 (PARTITION-LEVEL SORT, 3)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -842,73 +753,57 @@ STAGE PLANS:
TableScan
alias: a
Statistics: Num rows: 2 Data size: 208 Basic stats: COMPLETE Column stats: NONE
- Spark HashTable Sink Operator
- condition expressions:
- 0 {value}
- 1 {key} {value}
- 2 {key} {value}
- keys:
- 0 key (type: int)
- 1 key (type: int)
- 2 key (type: int)
- Local Work:
- Map Reduce Local Work
- Map 2
+ Reduce Output Operator
+ key expressions: key (type: int)
+ sort order: +
+ Map-reduce partition columns: key (type: int)
+ Statistics: Num rows: 2 Data size: 208 Basic stats: COMPLETE Column stats: NONE
+ value expressions: value (type: string)
+ Map 3
Map Operator Tree:
TableScan
alias: b
Statistics: Num rows: 1 Data size: 206 Basic stats: COMPLETE Column stats: NONE
- Spark HashTable Sink Operator
- condition expressions:
- 0 {key} {value}
- 1 {value}
- 2 {key} {value}
- keys:
- 0 key (type: int)
- 1 key (type: int)
- 2 key (type: int)
- Local Work:
- Map Reduce Local Work
-
- Stage: Stage-1
- Spark
-#### A masked pattern was here ####
- Vertices:
- Map 3
+ Reduce Output Operator
+ key expressions: key (type: int)
+ sort order: +
+ Map-reduce partition columns: key (type: int)
+ Statistics: Num rows: 1 Data size: 206 Basic stats: COMPLETE Column stats: NONE
+ value expressions: value (type: string)
+ Map 4
Map Operator Tree:
TableScan
alias: c
Statistics: Num rows: 2 Data size: 222 Basic stats: COMPLETE Column stats: NONE
- Map Join Operator
- condition map:
- Right Outer Join0 to 1
- Right Outer Join1 to 2
- condition expressions:
- 0 {key} {value}
- 1 {key} {value}
- 2 {key} {value}
- keys:
- 0 key (type: int)
- 1 key (type: int)
- 2 key (type: int)
- outputColumnNames: _col0, _col1, _col5, _col6, _col10, _col11
- input vertices:
- 0 Map 1
- 1 Map 2
+ Reduce Output Operator
+ key expressions: key (type: int)
+ sort order: +
+ Map-reduce partition columns: key (type: int)
+ Statistics: Num rows: 2 Data size: 222 Basic stats: COMPLETE Column stats: NONE
+ value expressions: value (type: string)
+ Reducer 2
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Right Outer Join0 to 1
+ Right Outer Join1 to 2
+ condition expressions:
+ 0 {KEY.reducesinkkey0} {VALUE._col0}
+ 1 {KEY.reducesinkkey0} {VALUE._col0}
+ 2 {KEY.reducesinkkey0} {VALUE._col0}
+ outputColumnNames: _col0, _col1, _col5, _col6, _col10, _col11
+ Statistics: Num rows: 4 Data size: 457 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: int), _col1 (type: string), _col5 (type: int), _col6 (type: string), _col10 (type: int), _col11 (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
+ Statistics: Num rows: 4 Data size: 457 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
Statistics: Num rows: 4 Data size: 457 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col0 (type: int), _col1 (type: string), _col5 (type: int), _col6 (type: string), _col10 (type: int), _col11 (type: string)
- outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
- Statistics: Num rows: 4 Data size: 457 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 4 Data size: 457 Basic stats: COMPLETE Column stats: NONE
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- Local Work:
- Map Reduce Local Work
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
Stage: Stage-0
Fetch Operator