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 2014/11/25 14:03:23 UTC
svn commit: r1641614 [38/43] - in /hive/branches/spark:
itests/src/test/resources/
ql/src/java/org/apache/hadoop/hive/ql/optimizer/physical/
ql/src/java/org/apache/hadoop/hive/ql/optimizer/spark/
ql/src/java/org/apache/hadoop/hive/ql/parse/spark/ ql/sr...
Modified: hive/branches/spark/ql/src/test/results/clientpositive/spark/smb_mapjoin_2.q.out
URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/smb_mapjoin_2.q.out?rev=1641614&r1=1641613&r2=1641614&view=diff
==============================================================================
--- hive/branches/spark/ql/src/test/results/clientpositive/spark/smb_mapjoin_2.q.out (original)
+++ hive/branches/spark/ql/src/test/results/clientpositive/spark/smb_mapjoin_2.q.out Tue Nov 25 13:03:18 2014
@@ -53,14 +53,35 @@ POSTHOOK: query: explain
select /*+mapjoin(a)*/ * from smb_bucket_1 a join smb_bucket_3 b on a.key = b.key
POSTHOOK: type: QUERY
STAGE DEPENDENCIES:
- Stage-1 is a root stage
+ Stage-3 is a root stage
+ Stage-1 depends on stages: Stage-3
Stage-0 depends on stages: Stage-1
STAGE PLANS:
+ Stage: Stage-3
+ Spark
+#### A masked pattern was here ####
+ Vertices:
+ Map 2
+ Map Operator Tree:
+ TableScan
+ alias: a
+ Statistics: Num rows: 2 Data size: 208 Basic stats: COMPLETE Column stats: NONE
+ 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}
+ 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
@@ -71,47 +92,32 @@ STAGE PLANS:
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)
- Map 3
- Map Operator Tree:
- TableScan
- alias: a
- Statistics: Num rows: 2 Data size: 208 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- predicate: key is not null (type: boolean)
- Statistics: Num rows: 1 Data size: 104 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: 104 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: 114 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: 114 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 1 Data size: 114 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
+ 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:
+ 0 Map 2
+ Statistics: Num rows: 1 Data size: 114 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: 114 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 114 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
Stage: Stage-0
Fetch Operator
@@ -138,14 +144,13 @@ POSTHOOK: query: explain
select /*+mapjoin(a)*/ * from smb_bucket_1 a left outer join smb_bucket_3 b on a.key = b.key
POSTHOOK: type: QUERY
STAGE DEPENDENCIES:
- Stage-1 is a root stage
+ Stage-3 is a root stage
+ Stage-1 depends on stages: Stage-3
Stage-0 depends on stages: Stage-1
STAGE PLANS:
- Stage: Stage-1
+ Stage: Stage-3
Spark
- Edges:
- Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 1), Map 3 (PARTITION-LEVEL SORT, 1)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -153,44 +158,51 @@ STAGE PLANS:
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)
- Map 3
+ 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
+#### A masked pattern was here ####
+ Vertices:
+ Map 2
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)
- 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: 228 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: 228 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
+ 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 1
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
+ 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: 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
Stage: Stage-0
Fetch Operator
@@ -220,14 +232,32 @@ POSTHOOK: query: explain
select /*+mapjoin(a)*/ * from smb_bucket_1 a right outer join smb_bucket_3 b on a.key = b.key
POSTHOOK: type: QUERY
STAGE DEPENDENCIES:
- Stage-1 is a root stage
+ Stage-3 is a root stage
+ Stage-1 depends on stages: Stage-3
Stage-0 depends on stages: Stage-1
STAGE PLANS:
+ Stage: Stage-3
+ Spark
+#### A masked pattern was here ####
+ Vertices:
+ Map 2
+ Map Operator Tree:
+ 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}
+ 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
@@ -235,44 +265,32 @@ STAGE PLANS:
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)
- Map 3
- 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)
- 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: 228 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: 228 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
+ 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 2
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
+ 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: 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
Stage: Stage-0
Fetch Operator
@@ -389,14 +407,35 @@ POSTHOOK: query: explain
select /*+mapjoin(b)*/ * from smb_bucket_1 a join smb_bucket_3 b on a.key = b.key
POSTHOOK: type: QUERY
STAGE DEPENDENCIES:
- Stage-1 is a root stage
+ Stage-3 is a root stage
+ Stage-1 depends on stages: Stage-3
Stage-0 depends on stages: Stage-1
STAGE PLANS:
+ Stage: Stage-3
+ Spark
+#### A masked pattern was here ####
+ Vertices:
+ Map 2
+ Map Operator Tree:
+ TableScan
+ alias: a
+ Statistics: Num rows: 2 Data size: 208 Basic stats: COMPLETE Column stats: NONE
+ 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}
+ 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
@@ -407,47 +446,32 @@ STAGE PLANS:
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)
- Map 3
- Map Operator Tree:
- TableScan
- alias: a
- Statistics: Num rows: 2 Data size: 208 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- predicate: key is not null (type: boolean)
- Statistics: Num rows: 1 Data size: 104 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: 104 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: 114 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: 114 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 1 Data size: 114 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
+ 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:
+ 0 Map 2
+ Statistics: Num rows: 1 Data size: 114 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: 114 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 114 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
Stage: Stage-0
Fetch Operator
@@ -474,14 +498,13 @@ POSTHOOK: query: explain
select /*+mapjoin(b)*/ * from smb_bucket_1 a left outer join smb_bucket_3 b on a.key = b.key
POSTHOOK: type: QUERY
STAGE DEPENDENCIES:
- Stage-1 is a root stage
+ Stage-3 is a root stage
+ Stage-1 depends on stages: Stage-3
Stage-0 depends on stages: Stage-1
STAGE PLANS:
- Stage: Stage-1
+ Stage: Stage-3
Spark
- Edges:
- Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 1), Map 3 (PARTITION-LEVEL SORT, 1)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -489,44 +512,51 @@ STAGE PLANS:
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)
- Map 3
+ 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
+#### A masked pattern was here ####
+ Vertices:
+ Map 2
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)
- 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: 228 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: 228 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
+ 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 1
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
+ 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: 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
Stage: Stage-0
Fetch Operator
@@ -556,14 +586,32 @@ POSTHOOK: query: explain
select /*+mapjoin(b)*/ * from smb_bucket_1 a right outer join smb_bucket_3 b on a.key = b.key
POSTHOOK: type: QUERY
STAGE DEPENDENCIES:
- Stage-1 is a root stage
+ Stage-3 is a root stage
+ Stage-1 depends on stages: Stage-3
Stage-0 depends on stages: Stage-1
STAGE PLANS:
+ Stage: Stage-3
+ Spark
+#### A masked pattern was here ####
+ Vertices:
+ Map 2
+ Map Operator Tree:
+ 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}
+ 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
@@ -571,44 +619,32 @@ STAGE PLANS:
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)
- Map 3
- 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)
- 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: 228 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: 228 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
+ 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 2
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
+ 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: 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
Stage: Stage-0
Fetch Operator
Modified: hive/branches/spark/ql/src/test/results/clientpositive/spark/smb_mapjoin_25.q.out
URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/smb_mapjoin_25.q.out?rev=1641614&r1=1641613&r2=1641614&view=diff
==============================================================================
--- hive/branches/spark/ql/src/test/results/clientpositive/spark/smb_mapjoin_25.q.out (original)
+++ hive/branches/spark/ql/src/test/results/clientpositive/spark/smb_mapjoin_25.q.out Tue Nov 25 13:03:18 2014
@@ -53,43 +53,56 @@ POSTHOOK: query: explain
select * from (select a.key from smb_bucket_1 a join smb_bucket_2 b on (a.key = b.key) where a.key = 5) t1 left outer join (select c.key from smb_bucket_2 c join smb_bucket_3 d on (c.key = d.key) where c.key=5) t2 on (t1.key=t2.key) where t2.key=5
POSTHOOK: type: QUERY
STAGE DEPENDENCIES:
- Stage-1 is a root stage
+ Stage-4 is a root stage
+ Stage-3 depends on stages: Stage-4
+ Stage-1 depends on stages: Stage-3
Stage-0 depends on stages: Stage-1
STAGE PLANS:
- Stage: Stage-1
+ Stage: Stage-4
Spark
- Edges:
- Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 1), Map 4 (PARTITION-LEVEL SORT, 1)
- Reducer 6 <- Map 5 (PARTITION-LEVEL SORT, 1), Map 7 (PARTITION-LEVEL SORT, 1)
- Reducer 3 <- Reducer 2 (PARTITION-LEVEL SORT, 1), Reducer 6 (PARTITION-LEVEL SORT, 1)
#### A masked pattern was here ####
Vertices:
- Map 1
+ Map 4
Map Operator Tree:
TableScan
- alias: b
+ alias: c
Statistics: Num rows: 51 Data size: 206 Basic stats: COMPLETE Column stats: NONE
Filter Operator
predicate: (key = 5) (type: boolean)
Statistics: Num rows: 25 Data size: 100 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: 5 (type: int)
- sort order: +
- Statistics: Num rows: 25 Data size: 100 Basic stats: COMPLETE Column stats: NONE
- Map 4
+ Spark HashTable Sink Operator
+ condition expressions:
+ 0
+ 1
+ keys:
+ 0 5 (type: int)
+ 1 5 (type: int)
+ Local Work:
+ Map Reduce Local Work
+
+ Stage: Stage-3
+ Spark
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
Map Operator Tree:
TableScan
- alias: a
- Statistics: Num rows: 52 Data size: 208 Basic stats: COMPLETE Column stats: NONE
+ alias: b
+ Statistics: Num rows: 51 Data size: 206 Basic stats: COMPLETE Column stats: NONE
Filter Operator
predicate: (key = 5) (type: boolean)
- Statistics: Num rows: 26 Data size: 104 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: 5 (type: int)
- sort order: +
- Statistics: Num rows: 26 Data size: 104 Basic stats: COMPLETE Column stats: NONE
- Map 5
+ Statistics: Num rows: 25 Data size: 100 Basic stats: COMPLETE Column stats: NONE
+ Spark HashTable Sink Operator
+ condition expressions:
+ 0
+ 1
+ keys:
+ 0 5 (type: int)
+ 1 5 (type: int)
+ Local Work:
+ Map Reduce Local Work
+ Map 3
Map Operator Tree:
TableScan
alias: d
@@ -97,82 +110,89 @@ STAGE PLANS:
Filter Operator
predicate: (key = 5) (type: boolean)
Statistics: Num rows: 27 Data size: 108 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: 5 (type: int)
- sort order: +
- Statistics: Num rows: 27 Data size: 108 Basic stats: COMPLETE Column stats: NONE
- Map 7
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0
+ 1
+ keys:
+ 0 5 (type: int)
+ 1 5 (type: int)
+ input vertices:
+ 0 Map 4
+ Statistics: Num rows: 29 Data size: 118 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: 5 (type: int)
+ outputColumnNames: _col0
+ Statistics: Num rows: 29 Data size: 118 Basic stats: COMPLETE Column stats: NONE
+ Spark HashTable Sink Operator
+ condition expressions:
+ 0 {_col0}
+ 1
+ keys:
+ 0 _col0 (type: int)
+ 1 _col0 (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: c
- Statistics: Num rows: 51 Data size: 206 Basic stats: COMPLETE Column stats: NONE
+ alias: a
+ Statistics: Num rows: 52 Data size: 208 Basic stats: COMPLETE Column stats: NONE
Filter Operator
predicate: (key = 5) (type: boolean)
- Statistics: Num rows: 25 Data size: 100 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: 5 (type: int)
- sort order: +
- Statistics: Num rows: 25 Data size: 100 Basic stats: COMPLETE Column stats: NONE
- Reducer 2
- Reduce Operator Tree:
- Join Operator
- condition map:
- Inner Join 0 to 1
- condition expressions:
- 0
- 1
- Statistics: Num rows: 28 Data size: 114 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: 5 (type: int)
- outputColumnNames: _col0
- Statistics: Num rows: 28 Data size: 114 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: 28 Data size: 114 Basic stats: COMPLETE Column stats: NONE
- Reducer 3
- Reduce Operator Tree:
- Join Operator
- condition map:
- Left Outer Join0 to 1
- condition expressions:
- 0 {KEY.reducesinkkey0}
- 1 {KEY.reducesinkkey0}
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 31 Data size: 129 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- predicate: (_col1 = 5) (type: boolean)
- Statistics: Num rows: 15 Data size: 62 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col0 (type: int), 5 (type: int)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 15 Data size: 62 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 15 Data size: 62 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
- Reducer 6
- Reduce Operator Tree:
- Join Operator
- condition map:
- Inner Join 0 to 1
- condition expressions:
- 0
- 1
- Statistics: Num rows: 29 Data size: 118 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: 5 (type: int)
- outputColumnNames: _col0
- Statistics: Num rows: 29 Data size: 118 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: 29 Data size: 118 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 26 Data size: 104 Basic stats: COMPLETE Column stats: NONE
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0
+ 1
+ keys:
+ 0 5 (type: int)
+ 1 5 (type: int)
+ input vertices:
+ 1 Map 1
+ Statistics: Num rows: 28 Data size: 114 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: 5 (type: int)
+ outputColumnNames: _col0
+ Statistics: Num rows: 28 Data size: 114 Basic stats: COMPLETE Column stats: NONE
+ Map Join Operator
+ condition map:
+ Left Outer Join0 to 1
+ condition expressions:
+ 0 {_col0}
+ 1 {_col0}
+ keys:
+ 0 _col0 (type: int)
+ 1 _col0 (type: int)
+ outputColumnNames: _col0, _col1
+ input vertices:
+ 1 Map 3
+ Statistics: Num rows: 31 Data size: 129 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: (_col1 = 5) (type: boolean)
+ Statistics: Num rows: 15 Data size: 62 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: int), 5 (type: int)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 15 Data size: 62 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 15 Data size: 62 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
Stage: Stage-0
Fetch Operator
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=1641614&r1=1641613&r2=1641614&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 Nov 25 13:03:18 2014
@@ -53,14 +53,13 @@ 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-1 is a root stage
+ Stage-3 is a root stage
+ Stage-1 depends on stages: Stage-3
Stage-0 depends on stages: Stage-1
STAGE PLANS:
- Stage: Stage-1
+ Stage: Stage-3
Spark
- Edges:
- Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 1), Map 3 (PARTITION-LEVEL SORT, 1)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -71,13 +70,21 @@ STAGE PLANS:
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)
- Map 3
+ 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
+#### A masked pattern was here ####
+ Vertices:
+ Map 2
Map Operator Tree:
TableScan
alias: a
@@ -85,33 +92,32 @@ STAGE PLANS:
Filter Operator
predicate: key is not null (type: boolean)
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)
- 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
+ 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 1
+ 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
Stage: Stage-0
Fetch Operator
@@ -138,14 +144,13 @@ 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-1 is a root stage
+ Stage-3 is a root stage
+ Stage-1 depends on stages: Stage-3
Stage-0 depends on stages: Stage-1
STAGE PLANS:
- Stage: Stage-1
+ Stage: Stage-3
Spark
- Edges:
- Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 1), Map 3 (PARTITION-LEVEL SORT, 1)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -153,44 +158,51 @@ STAGE PLANS:
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)
- Map 3
+ 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
+#### A masked pattern was here ####
+ Vertices:
+ Map 2
Map Operator Tree:
TableScan
alias: a
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)
- 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
+ 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 1
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
+ 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
Stage: Stage-0
Fetch Operator
@@ -219,14 +231,32 @@ 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-1 is a root stage
+ Stage-3 is a root stage
+ Stage-1 depends on stages: Stage-3
Stage-0 depends on stages: Stage-1
STAGE PLANS:
+ Stage: Stage-3
+ Spark
+#### A masked pattern was here ####
+ Vertices:
+ Map 2
+ Map Operator Tree:
+ 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
- Edges:
- Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 1), Map 3 (PARTITION-LEVEL SORT, 1)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -234,44 +264,32 @@ STAGE PLANS:
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)
- Map 3
- Map Operator Tree:
- TableScan
- alias: a
- 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)
- 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
+ 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 2
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
+ 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
Stage: Stage-0
Fetch Operator
@@ -387,14 +405,13 @@ 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-1 is a root stage
+ Stage-3 is a root stage
+ Stage-1 depends on stages: Stage-3
Stage-0 depends on stages: Stage-1
STAGE PLANS:
- Stage: Stage-1
+ Stage: Stage-3
Spark
- Edges:
- Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 1), Map 3 (PARTITION-LEVEL SORT, 1)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -405,13 +422,21 @@ STAGE PLANS:
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)
- Map 3
+ 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
+#### A masked pattern was here ####
+ Vertices:
+ Map 2
Map Operator Tree:
TableScan
alias: a
@@ -419,33 +444,32 @@ STAGE PLANS:
Filter Operator
predicate: key is not null (type: boolean)
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)
- 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
+ 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 1
+ 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
Stage: Stage-0
Fetch Operator
@@ -472,14 +496,13 @@ 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-1 is a root stage
+ Stage-3 is a root stage
+ Stage-1 depends on stages: Stage-3
Stage-0 depends on stages: Stage-1
STAGE PLANS:
- Stage: Stage-1
+ Stage: Stage-3
Spark
- Edges:
- Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 1), Map 3 (PARTITION-LEVEL SORT, 1)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -487,44 +510,51 @@ STAGE PLANS:
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)
- Map 3
+ 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
+#### A masked pattern was here ####
+ Vertices:
+ Map 2
Map Operator Tree:
TableScan
alias: a
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)
- 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
+ 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 1
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
+ 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
Stage: Stage-0
Fetch Operator
@@ -553,14 +583,32 @@ 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-1 is a root stage
+ Stage-3 is a root stage
+ Stage-1 depends on stages: Stage-3
Stage-0 depends on stages: Stage-1
STAGE PLANS:
+ Stage: Stage-3
+ Spark
+#### A masked pattern was here ####
+ Vertices:
+ Map 2
+ Map Operator Tree:
+ 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
- Edges:
- Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 1), Map 3 (PARTITION-LEVEL SORT, 1)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -568,44 +616,32 @@ STAGE PLANS:
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)
- Map 3
- Map Operator Tree:
- TableScan
- alias: a
- 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)
- 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
+ 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 2
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
+ 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
Stage: Stage-0
Fetch Operator