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 [40/42] - 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/temp_table_join1.q.out
URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/temp_table_join1.q.out?rev=1642997&r1=1642996&r2=1642997&view=diff
==============================================================================
--- hive/branches/spark/ql/src/test/results/clientpositive/spark/temp_table_join1.q.out (original)
+++ hive/branches/spark/ql/src/test/results/clientpositive/spark/temp_table_join1.q.out Tue Dec 2 19:57:10 2014
@@ -33,71 +33,64 @@ FROM src_nontemp src1 JOIN src_nontemp s
SELECT src1.key, src2.value
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 2
+ Map 1
Map Operator Tree:
TableScan
- alias: src2
+ alias: src1
Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE
Filter Operator
predicate: key is not null (type: boolean)
Statistics: Num rows: 5 Data size: 52 Basic stats: COMPLETE Column stats: NONE
- Spark HashTable Sink Operator
- condition expressions:
- 0 {key}
- 1 {value}
- keys:
- 0 key (type: string)
- 1 key (type: string)
- Local Work:
- Map Reduce Local Work
-
- Stage: Stage-1
- Spark
-#### A masked pattern was here ####
- Vertices:
- Map 1
+ Reduce Output Operator
+ key expressions: key (type: string)
+ sort order: +
+ Map-reduce partition columns: key (type: string)
+ Statistics: Num rows: 5 Data size: 52 Basic stats: COMPLETE Column stats: NONE
+ Map 3
Map Operator Tree:
TableScan
- alias: src1
+ alias: src2
Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE
Filter Operator
predicate: key is not null (type: boolean)
Statistics: Num rows: 5 Data size: 52 Basic stats: COMPLETE Column stats: NONE
- Map Join Operator
- condition map:
- Inner Join 0 to 1
- condition expressions:
- 0 {key}
- 1 {value}
- keys:
- 0 key (type: string)
- 1 key (type: string)
- outputColumnNames: _col0, _col6
- input vertices:
- 1 Map 2
- Statistics: Num rows: 5 Data size: 57 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col0 (type: string), _col6 (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 5 Data size: 57 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 5 Data size: 57 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: string)
+ sort order: +
+ Map-reduce partition columns: key (type: string)
+ Statistics: Num rows: 5 Data size: 52 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}
+ 1 {VALUE._col0}
+ outputColumnNames: _col0, _col6
+ Statistics: Num rows: 5 Data size: 57 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: string), _col6 (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 5 Data size: 57 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 5 Data size: 57 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
@@ -136,71 +129,64 @@ FROM src_nontemp src1 JOIN src_temp src2
SELECT src1.key, src2.value
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 2
+ Map 1
Map Operator Tree:
TableScan
- alias: src2
+ alias: src1
Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE
Filter Operator
predicate: key is not null (type: boolean)
Statistics: Num rows: 5 Data size: 52 Basic stats: COMPLETE Column stats: NONE
- Spark HashTable Sink Operator
- condition expressions:
- 0 {key}
- 1 {value}
- keys:
- 0 key (type: string)
- 1 key (type: string)
- Local Work:
- Map Reduce Local Work
-
- Stage: Stage-1
- Spark
-#### A masked pattern was here ####
- Vertices:
- Map 1
+ Reduce Output Operator
+ key expressions: key (type: string)
+ sort order: +
+ Map-reduce partition columns: key (type: string)
+ Statistics: Num rows: 5 Data size: 52 Basic stats: COMPLETE Column stats: NONE
+ Map 3
Map Operator Tree:
TableScan
- alias: src1
+ alias: src2
Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE
Filter Operator
predicate: key is not null (type: boolean)
Statistics: Num rows: 5 Data size: 52 Basic stats: COMPLETE Column stats: NONE
- Map Join Operator
- condition map:
- Inner Join 0 to 1
- condition expressions:
- 0 {key}
- 1 {value}
- keys:
- 0 key (type: string)
- 1 key (type: string)
- outputColumnNames: _col0, _col6
- input vertices:
- 1 Map 2
- Statistics: Num rows: 5 Data size: 57 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col0 (type: string), _col6 (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 5 Data size: 57 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 5 Data size: 57 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: string)
+ sort order: +
+ Map-reduce partition columns: key (type: string)
+ Statistics: Num rows: 5 Data size: 52 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}
+ 1 {VALUE._col0}
+ outputColumnNames: _col0, _col6
+ Statistics: Num rows: 5 Data size: 57 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: string), _col6 (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 5 Data size: 57 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 5 Data size: 57 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
@@ -241,71 +227,64 @@ FROM src_temp src1 JOIN src_temp src2 ON
SELECT src1.key, src2.value
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 2
+ Map 1
Map Operator Tree:
TableScan
- alias: src2
+ alias: src1
Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE
Filter Operator
predicate: key is not null (type: boolean)
Statistics: Num rows: 5 Data size: 52 Basic stats: COMPLETE Column stats: NONE
- Spark HashTable Sink Operator
- condition expressions:
- 0 {key}
- 1 {value}
- keys:
- 0 key (type: string)
- 1 key (type: string)
- Local Work:
- Map Reduce Local Work
-
- Stage: Stage-1
- Spark
-#### A masked pattern was here ####
- Vertices:
- Map 1
+ Reduce Output Operator
+ key expressions: key (type: string)
+ sort order: +
+ Map-reduce partition columns: key (type: string)
+ Statistics: Num rows: 5 Data size: 52 Basic stats: COMPLETE Column stats: NONE
+ Map 3
Map Operator Tree:
TableScan
- alias: src1
+ alias: src2
Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE
Filter Operator
predicate: key is not null (type: boolean)
Statistics: Num rows: 5 Data size: 52 Basic stats: COMPLETE Column stats: NONE
- Map Join Operator
- condition map:
- Inner Join 0 to 1
- condition expressions:
- 0 {key}
- 1 {value}
- keys:
- 0 key (type: string)
- 1 key (type: string)
- outputColumnNames: _col0, _col6
- input vertices:
- 1 Map 2
- Statistics: Num rows: 5 Data size: 57 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col0 (type: string), _col6 (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 5 Data size: 57 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 5 Data size: 57 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: string)
+ sort order: +
+ Map-reduce partition columns: key (type: string)
+ Statistics: Num rows: 5 Data size: 52 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}
+ 1 {VALUE._col0}
+ outputColumnNames: _col0, _col6
+ Statistics: Num rows: 5 Data size: 57 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: string), _col6 (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 5 Data size: 57 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 5 Data size: 57 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
Modified: hive/branches/spark/ql/src/test/results/clientpositive/spark/tez_join_tests.q.out
URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/tez_join_tests.q.out?rev=1642997&r1=1642996&r2=1642997&view=diff
==============================================================================
--- hive/branches/spark/ql/src/test/results/clientpositive/spark/tez_join_tests.q.out (original)
+++ hive/branches/spark/ql/src/test/results/clientpositive/spark/tez_join_tests.q.out Tue Dec 2 19:57:10 2014
@@ -9,35 +9,17 @@ explain
select * from (select b.key, b.value from src1 a left outer join src b on (a.key = b.key) order by b.key) x right outer join src c on (x.value = c.value) order by x.key
POSTHOOK: type: QUERY
STAGE DEPENDENCIES:
- Stage-3 is a root stage
- Stage-2 depends on stages: Stage-3
- Stage-1 depends on stages: Stage-2
+ Stage-1 is a root stage
Stage-0 depends on stages: Stage-1
STAGE PLANS:
- Stage: Stage-3
- Spark
-#### A masked pattern was here ####
- Vertices:
- Map 3
- Map Operator Tree:
- TableScan
- alias: b
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- Spark HashTable Sink Operator
- condition expressions:
- 0
- 1 {value}
- keys:
- 0 key (type: string)
- 1 key (type: string)
- Local Work:
- Map Reduce Local Work
-
- Stage: Stage-2
+ Stage: Stage-1
Spark
Edges:
- Reducer 2 <- Map 1 (SORT, 1)
+ Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 1), Map 6 (PARTITION-LEVEL SORT, 1)
+ Reducer 4 <- Map 7 (PARTITION-LEVEL SORT, 1), Reducer 3 (PARTITION-LEVEL SORT, 1)
+ Reducer 3 <- Reducer 2 (SORT, 1)
+ Reducer 5 <- Reducer 4 (SORT, 1)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -45,77 +27,79 @@ STAGE PLANS:
TableScan
alias: a
Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE
- Map Join Operator
- condition map:
- Left Outer Join0 to 1
- condition expressions:
- 0
- 1 {key} {value}
- keys:
- 0 key (type: string)
- 1 key (type: string)
- outputColumnNames: _col5, _col6
- input vertices:
- 1 Map 3
- Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col5 (type: string), _col6 (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: string)
- sort order: +
- Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col1 (type: string)
- Local Work:
- Map Reduce Local Work
+ Reduce Output Operator
+ key expressions: key (type: string)
+ sort order: +
+ Map-reduce partition columns: key (type: string)
+ Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE
+ Map 6
+ Map Operator Tree:
+ TableScan
+ alias: b
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: key (type: string)
+ sort order: +
+ Map-reduce partition columns: key (type: string)
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ value expressions: value (type: string)
+ Map 7
+ Map Operator Tree:
+ TableScan
+ alias: c
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: value (type: string)
+ sort order: +
+ Map-reduce partition columns: value (type: string)
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ value expressions: key (type: string)
Reducer 2
- Local Work:
- Map Reduce Local Work
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Left Outer Join0 to 1
+ condition expressions:
+ 0
+ 1 {KEY.reducesinkkey0} {VALUE._col0}
+ outputColumnNames: _col5, _col6
+ Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col5 (type: string), _col6 (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ sort order: +
+ Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col1 (type: string)
+ Reducer 3
Reduce Operator Tree:
Select Operator
expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string)
outputColumnNames: _col0, _col1
Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
- Spark HashTable Sink Operator
- condition expressions:
- 0 {_col0}
- 1 {key} {value}
- keys:
- 0 _col1 (type: string)
- 1 value (type: string)
-
- Stage: Stage-1
- Spark
- Edges:
- Reducer 5 <- Map 4 (SORT, 1)
-#### A masked pattern was here ####
- Vertices:
- Map 4
- Map Operator Tree:
- TableScan
- alias: c
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- Map Join Operator
- condition map:
- Right Outer Join0 to 1
- condition expressions:
- 0 {_col0} {_col1}
- 1 {key} {value}
- keys:
- 0 _col1 (type: string)
- 1 value (type: string)
- outputColumnNames: _col0, _col1, _col2, _col3
- input vertices:
- 0 Reducer 2
- Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: string)
- sort order: +
- Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col1 (type: string), _col2 (type: string), _col3 (type: string)
- Local Work:
- Map Reduce Local Work
+ Reduce Output Operator
+ key expressions: _col1 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col1 (type: string)
+ Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: string)
+ Reducer 4
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Right Outer Join0 to 1
+ condition expressions:
+ 0 {VALUE._col0} {KEY.reducesinkkey0}
+ 1 {VALUE._col0} {KEY.reducesinkkey0}
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ sort order: +
+ Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col1 (type: string), _col2 (type: string), _col3 (type: string)
Reducer 5
Reduce Operator Tree:
Select Operator
Modified: hive/branches/spark/ql/src/test/results/clientpositive/spark/tez_joins_explain.q.out
URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/tez_joins_explain.q.out?rev=1642997&r1=1642996&r2=1642997&view=diff
==============================================================================
--- hive/branches/spark/ql/src/test/results/clientpositive/spark/tez_joins_explain.q.out (original)
+++ hive/branches/spark/ql/src/test/results/clientpositive/spark/tez_joins_explain.q.out Tue Dec 2 19:57:10 2014
@@ -9,35 +9,17 @@ explain
select * from (select b.key, b.value from src1 a left outer join src b on (a.key = b.key) order by b.key) x right outer join src c on (x.value = c.value) order by x.key
POSTHOOK: type: QUERY
STAGE DEPENDENCIES:
- Stage-3 is a root stage
- Stage-2 depends on stages: Stage-3
- Stage-1 depends on stages: Stage-2
+ Stage-1 is a root stage
Stage-0 depends on stages: Stage-1
STAGE PLANS:
- Stage: Stage-3
- Spark
-#### A masked pattern was here ####
- Vertices:
- Map 3
- Map Operator Tree:
- TableScan
- alias: b
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- Spark HashTable Sink Operator
- condition expressions:
- 0
- 1 {value}
- keys:
- 0 key (type: string)
- 1 key (type: string)
- Local Work:
- Map Reduce Local Work
-
- Stage: Stage-2
+ Stage: Stage-1
Spark
Edges:
- Reducer 2 <- Map 1 (SORT, 1)
+ Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 1), Map 6 (PARTITION-LEVEL SORT, 1)
+ Reducer 4 <- Map 7 (PARTITION-LEVEL SORT, 1), Reducer 3 (PARTITION-LEVEL SORT, 1)
+ Reducer 3 <- Reducer 2 (SORT, 1)
+ Reducer 5 <- Reducer 4 (SORT, 1)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -45,77 +27,79 @@ STAGE PLANS:
TableScan
alias: a
Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE
- Map Join Operator
- condition map:
- Left Outer Join0 to 1
- condition expressions:
- 0
- 1 {key} {value}
- keys:
- 0 key (type: string)
- 1 key (type: string)
- outputColumnNames: _col5, _col6
- input vertices:
- 1 Map 3
- Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col5 (type: string), _col6 (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: string)
- sort order: +
- Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col1 (type: string)
- Local Work:
- Map Reduce Local Work
+ Reduce Output Operator
+ key expressions: key (type: string)
+ sort order: +
+ Map-reduce partition columns: key (type: string)
+ Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE
+ Map 6
+ Map Operator Tree:
+ TableScan
+ alias: b
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: key (type: string)
+ sort order: +
+ Map-reduce partition columns: key (type: string)
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ value expressions: value (type: string)
+ Map 7
+ Map Operator Tree:
+ TableScan
+ alias: c
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: value (type: string)
+ sort order: +
+ Map-reduce partition columns: value (type: string)
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ value expressions: key (type: string)
Reducer 2
- Local Work:
- Map Reduce Local Work
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Left Outer Join0 to 1
+ condition expressions:
+ 0
+ 1 {KEY.reducesinkkey0} {VALUE._col0}
+ outputColumnNames: _col5, _col6
+ Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col5 (type: string), _col6 (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ sort order: +
+ Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col1 (type: string)
+ Reducer 3
Reduce Operator Tree:
Select Operator
expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string)
outputColumnNames: _col0, _col1
Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
- Spark HashTable Sink Operator
- condition expressions:
- 0 {_col0}
- 1 {key} {value}
- keys:
- 0 _col1 (type: string)
- 1 value (type: string)
-
- Stage: Stage-1
- Spark
- Edges:
- Reducer 5 <- Map 4 (SORT, 1)
-#### A masked pattern was here ####
- Vertices:
- Map 4
- Map Operator Tree:
- TableScan
- alias: c
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- Map Join Operator
- condition map:
- Right Outer Join0 to 1
- condition expressions:
- 0 {_col0} {_col1}
- 1 {key} {value}
- keys:
- 0 _col1 (type: string)
- 1 value (type: string)
- outputColumnNames: _col0, _col1, _col2, _col3
- input vertices:
- 0 Reducer 2
- Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: string)
- sort order: +
- Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col1 (type: string), _col2 (type: string), _col3 (type: string)
- Local Work:
- Map Reduce Local Work
+ Reduce Output Operator
+ key expressions: _col1 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col1 (type: string)
+ Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: string)
+ Reducer 4
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Right Outer Join0 to 1
+ condition expressions:
+ 0 {VALUE._col0} {KEY.reducesinkkey0}
+ 1 {VALUE._col0} {KEY.reducesinkkey0}
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ sort order: +
+ Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col1 (type: string), _col2 (type: string), _col3 (type: string)
Reducer 5
Reduce Operator Tree:
Select Operator
Modified: hive/branches/spark/ql/src/test/results/clientpositive/spark/vectorized_bucketmapjoin1.q.out
URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/vectorized_bucketmapjoin1.q.out?rev=1642997&r1=1642996&r2=1642997&view=diff
==============================================================================
--- hive/branches/spark/ql/src/test/results/clientpositive/spark/vectorized_bucketmapjoin1.q.out (original)
+++ hive/branches/spark/ql/src/test/results/clientpositive/spark/vectorized_bucketmapjoin1.q.out Tue Dec 2 19:57:10 2014
@@ -101,72 +101,67 @@ POSTHOOK: query: explain
select /*+MAPJOIN(a)*/ * from vsmb_bucket_1 a join vsmb_bucket_2 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 2
+ Map 1
Map Operator Tree:
TableScan
- alias: b
+ 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 {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 1
+ 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)
+ Execution mode: vectorized
+ Map 3
Map Operator Tree:
TableScan
- alias: a
+ alias: b
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
- 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: 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
+ 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)
Execution mode: vectorized
+ 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
Stage: Stage-0
Fetch Operator
@@ -195,35 +190,14 @@ POSTHOOK: query: explain
select /*+MAPJOIN(b)*/ * from vsmb_bucket_1 a join vsmb_bucket_RC 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: 50 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- predicate: key is not null (type: boolean)
- Statistics: Num rows: 1 Data size: 25 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
@@ -234,33 +208,48 @@ STAGE PLANS:
Filter Operator
predicate: key is not null (type: boolean)
Statistics: Num rows: 1 Data size: 104 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: 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
+ 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)
Execution mode: vectorized
+ Map 3
+ Map Operator Tree:
+ TableScan
+ alias: b
+ Statistics: Num rows: 2 Data size: 50 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: key is not null (type: boolean)
+ Statistics: Num rows: 1 Data size: 25 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: 25 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
Stage: Stage-0
Fetch Operator
@@ -299,35 +288,14 @@ explain
select /*+MAPJOIN(b)*/ * from vsmb_bucket_1 a join vsmb_bucket_TXT 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: 52 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- predicate: key is not null (type: boolean)
- Statistics: Num rows: 1 Data size: 26 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
@@ -338,33 +306,48 @@ STAGE PLANS:
Filter Operator
predicate: key is not null (type: boolean)
Statistics: Num rows: 1 Data size: 104 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: 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
+ 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)
Execution mode: vectorized
+ Map 3
+ Map Operator Tree:
+ TableScan
+ alias: b
+ Statistics: Num rows: 2 Data size: 52 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: key is not null (type: boolean)
+ Statistics: Num rows: 1 Data size: 26 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: 26 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
Stage: Stage-0
Fetch Operator