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 [8/42] - 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/column_access_stats.q.out
URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/column_access_stats.q.out?rev=1642997&r1=1642996&r2=1642997&view=diff
==============================================================================
--- hive/branches/spark/ql/src/test/results/clientpositive/spark/column_access_stats.q.out (original)
+++ hive/branches/spark/ql/src/test/results/clientpositive/spark/column_access_stats.q.out Tue Dec 2 19:57:10 2014
@@ -372,71 +372,63 @@ FROM T1 JOIN T2
ON T1.key = T2.key
PREHOOK: 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: t2
- Statistics: Num rows: 0 Data size: 20 Basic stats: PARTIAL Column stats: NONE
+ alias: t1
+ Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE
Filter Operator
predicate: key is not null (type: boolean)
Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
- Spark HashTable Sink Operator
- condition expressions:
- 0 {key}
- 1
- 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: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+ Map 3
Map Operator Tree:
TableScan
- alias: t1
- Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE
+ alias: t2
+ Statistics: Num rows: 0 Data size: 20 Basic stats: PARTIAL Column stats: NONE
Filter Operator
predicate: key is not null (type: boolean)
Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
- Map Join Operator
- condition map:
- Inner Join 0 to 1
- condition expressions:
- 0 {key}
- 1
- keys:
- 0 key (type: string)
- 1 key (type: string)
- outputColumnNames: _col0
- input vertices:
- 1 Map 2
+ Reduce Output Operator
+ key expressions: key (type: string)
+ sort order: +
+ Map-reduce partition columns: key (type: string)
Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
- Select Operator
- expressions: _col0 (type: string)
- outputColumnNames: _col0
- Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 0 Data size: 0 Basic stats: NONE 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
+ Reducer 2
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0 {KEY.reducesinkkey0}
+ 1
+ outputColumnNames: _col0
+ Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 0 Data size: 0 Basic stats: NONE 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
@@ -503,71 +495,63 @@ FROM T1 JOIN T2
ON T1.key = T2.key AND T1.val = 3 and T2.val = 3
PREHOOK: 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: t2
- Statistics: Num rows: 0 Data size: 20 Basic stats: PARTIAL Column stats: NONE
+ alias: t1
+ Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE
Filter Operator
predicate: ((val = 3) and key is not null) (type: boolean)
Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
- Spark HashTable Sink Operator
- condition expressions:
- 0 {key}
- 1
- 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: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+ Map 3
Map Operator Tree:
TableScan
- alias: t1
- Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE
+ alias: t2
+ Statistics: Num rows: 0 Data size: 20 Basic stats: PARTIAL Column stats: NONE
Filter Operator
predicate: ((val = 3) and key is not null) (type: boolean)
Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
- Map Join Operator
- condition map:
- Inner Join 0 to 1
- condition expressions:
- 0 {key}
- 1 {key}
- keys:
- 0 key (type: string)
- 1 key (type: string)
- outputColumnNames: _col0, _col5
- input vertices:
- 1 Map 2
+ Reduce Output Operator
+ key expressions: key (type: string)
+ sort order: +
+ Map-reduce partition columns: key (type: string)
Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
- Select Operator
- expressions: _col0 (type: string), '3' (type: string), _col5 (type: string), '3' (type: string)
- outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 0 Data size: 0 Basic stats: NONE 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
+ Reducer 2
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0 {KEY.reducesinkkey0}
+ 1 {KEY.reducesinkkey0}
+ outputColumnNames: _col0, _col5
+ Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: string), '3' (type: string), _col5 (type: string), '3' (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 0 Data size: 0 Basic stats: NONE 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
@@ -601,79 +585,71 @@ JOIN
ON subq1.val = subq2.val
PREHOOK: 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: t2
- Statistics: Num rows: 0 Data size: 20 Basic stats: PARTIAL Column stats: NONE
+ alias: t1
+ Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE
Filter Operator
- predicate: ((key = 6) and val is not null) (type: boolean)
+ predicate: ((key = 5) and val is not null) (type: boolean)
Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
Select Operator
expressions: val (type: string)
outputColumnNames: _col0
Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
- Spark HashTable Sink Operator
- condition expressions:
- 0 {_col0}
- 1
- keys:
- 0 _col0 (type: string)
- 1 _col0 (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: _col0 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+ Map 3
Map Operator Tree:
TableScan
- alias: t1
- Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE
+ alias: t2
+ Statistics: Num rows: 0 Data size: 20 Basic stats: PARTIAL Column stats: NONE
Filter Operator
- predicate: ((key = 5) and val is not null) (type: boolean)
+ predicate: ((key = 6) and val is not null) (type: boolean)
Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
Select Operator
expressions: val (type: string)
outputColumnNames: _col0
Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
- Map Join Operator
- condition map:
- Inner Join 0 to 1
- condition expressions:
- 0 {_col0}
- 1
- keys:
- 0 _col0 (type: string)
- 1 _col0 (type: string)
- outputColumnNames: _col0
- input vertices:
- 1 Map 2
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
- Select Operator
- expressions: _col0 (type: string)
- outputColumnNames: _col0
- Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 0 Data size: 0 Basic stats: NONE 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
+ Reducer 2
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0 {KEY.reducesinkkey0}
+ 1
+ outputColumnNames: _col0
+ Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 0 Data size: 0 Basic stats: NONE 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
@@ -721,20 +697,22 @@ JOIN T3
ON T3.key = T4.key
PREHOOK: 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 4 (PARTITION-LEVEL SORT, 3)
+ Reducer 3 <- Map 5 (PARTITION-LEVEL SORT, 3), Reducer 2 (PARTITION-LEVEL SORT, 3)
#### A masked pattern was here ####
Vertices:
- Map 2
+ Map 1
Map Operator Tree:
TableScan
- alias: t2
- Statistics: Num rows: 0 Data size: 20 Basic stats: PARTIAL Column stats: NONE
+ alias: t1
+ Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE
Filter Operator
predicate: key is not null (type: boolean)
Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
@@ -742,88 +720,78 @@ STAGE PLANS:
expressions: key (type: string)
outputColumnNames: _col0
Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
- Spark HashTable Sink Operator
- condition expressions:
- 0 {_col0}
- 1
- keys:
- 0 _col0 (type: string)
- 1 _col0 (type: string)
- Local Work:
- Map Reduce Local Work
- Map 3
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+ Map 4
Map Operator Tree:
TableScan
- alias: t3
- Statistics: Num rows: 0 Data size: 35 Basic stats: PARTIAL Column stats: NONE
+ alias: t2
+ Statistics: Num rows: 0 Data size: 20 Basic stats: PARTIAL Column stats: NONE
Filter Operator
predicate: key is not null (type: boolean)
Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
- Spark HashTable Sink Operator
- condition expressions:
- 0 {_col0}
- 1 {val}
- keys:
- 0 _col0 (type: string)
- 1 key (type: string)
- Local Work:
- Map Reduce Local Work
-
- Stage: Stage-1
- Spark
-#### A masked pattern was here ####
- Vertices:
- Map 1
+ Select Operator
+ expressions: key (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+ Map 5
Map Operator Tree:
TableScan
- alias: t1
- Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE
+ alias: t3
+ Statistics: Num rows: 0 Data size: 35 Basic stats: PARTIAL Column stats: NONE
Filter Operator
predicate: key is not null (type: boolean)
Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
- Select Operator
- expressions: key (type: string)
- outputColumnNames: _col0
+ Reduce Output Operator
+ key expressions: key (type: string)
+ sort order: +
+ Map-reduce partition columns: key (type: string)
Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
- Map Join Operator
- condition map:
- Inner Join 0 to 1
- condition expressions:
- 0 {_col0}
- 1
- keys:
- 0 _col0 (type: string)
- 1 _col0 (type: string)
- outputColumnNames: _col0
- input vertices:
- 1 Map 2
- Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
- Map Join Operator
- condition map:
- Inner Join 0 to 1
- condition expressions:
- 0 {_col0}
- 1 {key} {val}
- keys:
- 0 _col0 (type: string)
- 1 key (type: string)
- outputColumnNames: _col0, _col1, _col2
- input vertices:
- 1 Map 3
- Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
- Select Operator
- expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string)
- outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 0 Data size: 0 Basic stats: NONE 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
+ value expressions: val (type: string)
+ Reducer 2
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0 {KEY.reducesinkkey0}
+ 1
+ outputColumnNames: _col0
+ Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+ Reducer 3
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0 {KEY.reducesinkkey0}
+ 1 {KEY.reducesinkkey0} {VALUE._col0}
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string)
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 0 Data size: 0 Basic stats: NONE 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/cross_join.q.out
URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/cross_join.q.out?rev=1642997&r1=1642996&r2=1642997&view=diff
==============================================================================
--- hive/branches/spark/ql/src/test/results/clientpositive/spark/cross_join.q.out (original)
+++ hive/branches/spark/ql/src/test/results/clientpositive/spark/cross_join.q.out Tue Dec 2 19:57:10 2014
@@ -5,32 +5,14 @@ POSTHOOK: query: -- current
explain select src.key from src join src src2
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: src2
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE
- Spark HashTable Sink Operator
- condition expressions:
- 0 {key}
- 1
- keys:
- 0
- 1
- 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
@@ -38,32 +20,39 @@ STAGE PLANS:
TableScan
alias: src
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- Map Join Operator
- condition map:
- Inner Join 0 to 1
- condition expressions:
- 0 {key}
- 1
- keys:
- 0
- 1
- outputColumnNames: _col0
- input vertices:
- 1 Map 2
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ value expressions: key (type: string)
+ Map 3
+ Map Operator Tree:
+ TableScan
+ alias: src2
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE
+ Reducer 2
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0 {VALUE._col0}
+ 1
+ outputColumnNames: _col0
+ Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col0 (type: string)
- outputColumnNames: _col0
- Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 550 Data size: 5843 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
@@ -78,32 +67,14 @@ POSTHOOK: query: -- ansi cross join
explain select src.key from src cross join src src2
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: src2
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE
- Spark HashTable Sink Operator
- condition expressions:
- 0 {key}
- 1
- keys:
- 0
- 1
- 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
@@ -111,32 +82,39 @@ STAGE PLANS:
TableScan
alias: src
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- Map Join Operator
- condition map:
- Inner Join 0 to 1
- condition expressions:
- 0 {key}
- 1
- keys:
- 0
- 1
- outputColumnNames: _col0
- input vertices:
- 1 Map 2
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ value expressions: key (type: string)
+ Map 3
+ Map Operator Tree:
+ TableScan
+ alias: src2
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE
+ Reducer 2
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0 {VALUE._col0}
+ 1
+ outputColumnNames: _col0
+ Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col0 (type: string)
- outputColumnNames: _col0
- Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 550 Data size: 5843 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
@@ -151,71 +129,63 @@ POSTHOOK: query: -- appending condition
explain select src.key from src cross join src src2 on src.key=src2.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)
#### A masked pattern was here ####
Vertices:
- Map 2
+ Map 1
Map Operator Tree:
TableScan
- alias: src2
+ alias: src
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
Filter Operator
predicate: key is not null (type: boolean)
Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
- Spark HashTable Sink Operator
- condition expressions:
- 0 {key}
- 1
- 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: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Map 3
Map Operator Tree:
TableScan
- alias: src
+ alias: src2
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
Filter Operator
predicate: key is not null (type: boolean)
Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
- Map Join Operator
- condition map:
- Inner Join 0 to 1
- condition expressions:
- 0 {key}
- 1
- keys:
- 0 key (type: string)
- 1 key (type: string)
- outputColumnNames: _col0
- input vertices:
- 1 Map 2
- Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col0 (type: string)
- outputColumnNames: _col0
- Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 275 Data size: 2921 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: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Reducer 2
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0 {KEY.reducesinkkey0}
+ 1
+ outputColumnNames: _col0
+ Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 275 Data size: 2921 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/filter_join_breaktask.q.out
URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/filter_join_breaktask.q.out?rev=1642997&r1=1642996&r2=1642997&view=diff
==============================================================================
--- hive/branches/spark/ql/src/test/results/clientpositive/spark/filter_join_breaktask.q.out (original)
+++ hive/branches/spark/ql/src/test/results/clientpositive/spark/filter_join_breaktask.q.out Tue Dec 2 19:57:10 2014
@@ -135,35 +135,34 @@ TOK_QUERY
STAGE DEPENDENCIES:
- Stage-3 is a root stage
- Stage-1 depends on stages: Stage-3
+ Stage-1 is a root stage
Stage-0 depends on stages: Stage-1
STAGE PLANS:
- Stage: Stage-3
+ Stage: Stage-1
Spark
+ Edges:
+ Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 3), Map 4 (PARTITION-LEVEL SORT, 3)
+ Reducer 3 <- Map 5 (PARTITION-LEVEL SORT, 3), Reducer 2 (PARTITION-LEVEL SORT, 3)
#### A masked pattern was here ####
Vertices:
- Map 2
+ Map 1
Map Operator Tree:
TableScan
- alias: g
+ alias: f
Statistics: Num rows: 25 Data size: 211 Basic stats: COMPLETE Column stats: NONE
GatherStats: false
Filter Operator
isSamplingPred: false
- predicate: ((value <> '') and value is not null) (type: boolean)
+ predicate: key is not null (type: boolean)
Statistics: Num rows: 13 Data size: 109 Basic stats: COMPLETE Column stats: NONE
- Spark HashTable Sink Operator
- condition expressions:
- 0 {_col0}
- 1
- keys:
- 0 _col7 (type: string)
- 1 value (type: string)
- Position of Big Table: 0
- 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: 13 Data size: 109 Basic stats: COMPLETE Column stats: NONE
+ tag: 0
+ auto parallelism: false
Path -> Alias:
#### A masked pattern was here ####
Path -> Partition:
@@ -213,8 +212,8 @@ STAGE PLANS:
name: default.filter_join_breaktask
name: default.filter_join_breaktask
Truncated Path -> Alias:
- /filter_join_breaktask/ds=2008-04-08 [g]
- Map 3
+ /filter_join_breaktask/ds=2008-04-08 [f]
+ Map 4
Map Operator Tree:
TableScan
alias: m
@@ -224,16 +223,14 @@ STAGE PLANS:
isSamplingPred: false
predicate: ((key is not null and value is not null) and (value <> '')) (type: boolean)
Statistics: Num rows: 7 Data size: 59 Basic stats: COMPLETE Column stats: NONE
- Spark HashTable Sink Operator
- condition expressions:
- 0 {key}
- 1 {value}
- keys:
- 0 key (type: int)
- 1 key (type: int)
- Position of Big Table: 0
- 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: 7 Data size: 59 Basic stats: COMPLETE Column stats: NONE
+ tag: 1
+ value expressions: value (type: string)
+ auto parallelism: false
Path -> Alias:
#### A masked pattern was here ####
Path -> Partition:
@@ -284,76 +281,23 @@ STAGE PLANS:
name: default.filter_join_breaktask
Truncated Path -> Alias:
/filter_join_breaktask/ds=2008-04-08 [m]
-
- Stage: Stage-1
- Spark
-#### A masked pattern was here ####
- Vertices:
- Map 1
+ Map 5
Map Operator Tree:
TableScan
- alias: f
+ alias: g
Statistics: Num rows: 25 Data size: 211 Basic stats: COMPLETE Column stats: NONE
GatherStats: false
Filter Operator
isSamplingPred: false
- predicate: key is not null (type: boolean)
+ predicate: ((value <> '') and value is not null) (type: boolean)
Statistics: Num rows: 13 Data size: 109 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: int)
- 1 key (type: int)
- outputColumnNames: _col0, _col7
- input vertices:
- 1 Map 3
- Position of Big Table: 0
- Statistics: Num rows: 14 Data size: 119 Basic stats: COMPLETE Column stats: NONE
- Map Join Operator
- condition map:
- Inner Join 0 to 1
- condition expressions:
- 0 {_col0}
- 1 {value}
- keys:
- 0 _col7 (type: string)
- 1 value (type: string)
- outputColumnNames: _col0, _col13
- input vertices:
- 1 Map 2
- Position of Big Table: 0
- Statistics: Num rows: 15 Data size: 130 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col0 (type: int), _col13 (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 15 Data size: 130 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- GlobalTableId: 0
-#### A masked pattern was here ####
- NumFilesPerFileSink: 1
- Statistics: Num rows: 15 Data size: 130 Basic stats: COMPLETE Column stats: NONE
-#### A masked pattern was here ####
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- columns _col0,_col1
- columns.types int:string
- escape.delim \
- hive.serialization.extend.nesting.levels true
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- TotalFiles: 1
- GatherStats: false
- MultiFileSpray: false
- Local Work:
- Map Reduce Local Work
+ Reduce Output Operator
+ key expressions: value (type: string)
+ sort order: +
+ Map-reduce partition columns: value (type: string)
+ Statistics: Num rows: 13 Data size: 109 Basic stats: COMPLETE Column stats: NONE
+ tag: 1
+ auto parallelism: false
Path -> Alias:
#### A masked pattern was here ####
Path -> Partition:
@@ -403,7 +347,62 @@ STAGE PLANS:
name: default.filter_join_breaktask
name: default.filter_join_breaktask
Truncated Path -> Alias:
- /filter_join_breaktask/ds=2008-04-08 [f]
+ /filter_join_breaktask/ds=2008-04-08 [g]
+ Reducer 2
+ Needs Tagging: true
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0 {KEY.reducesinkkey0}
+ 1 {VALUE._col0}
+ outputColumnNames: _col0, _col7
+ Statistics: Num rows: 14 Data size: 119 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col7 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col7 (type: string)
+ Statistics: Num rows: 14 Data size: 119 Basic stats: COMPLETE Column stats: NONE
+ tag: 0
+ value expressions: _col0 (type: int)
+ auto parallelism: false
+ Reducer 3
+ Needs Tagging: true
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0 {VALUE._col0}
+ 1 {KEY.reducesinkkey0}
+ outputColumnNames: _col0, _col13
+ Statistics: Num rows: 15 Data size: 130 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: int), _col13 (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 15 Data size: 130 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+#### A masked pattern was here ####
+ NumFilesPerFileSink: 1
+ Statistics: Num rows: 15 Data size: 130 Basic stats: COMPLETE Column stats: NONE
+#### A masked pattern was here ####
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ properties:
+ columns _col0,_col1
+ columns.types int:string
+ escape.delim \
+ hive.serialization.extend.nesting.levels true
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ TotalFiles: 1
+ GatherStats: false
+ MultiFileSpray: false
Stage: Stage-0
Fetch Operator
Modified: hive/branches/spark/ql/src/test/results/clientpositive/spark/groupby_position.q.out
URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/groupby_position.q.out?rev=1642997&r1=1642996&r2=1642997&view=diff
==============================================================================
--- hive/branches/spark/ql/src/test/results/clientpositive/spark/groupby_position.q.out (original)
+++ hive/branches/spark/ql/src/test/results/clientpositive/spark/groupby_position.q.out Tue Dec 2 19:57:10 2014
@@ -541,15 +541,17 @@ FROM (
ORDER BY 1 DESC, 2 DESC, 3 ASC, 4 ASC
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 (GROUP PARTITION-LEVEL SORT, 3)
+ Reducer 6 <- Map 5 (GROUP, 3)
+ Reducer 3 <- Reducer 2 (PARTITION-LEVEL SORT, 3), Reducer 6 (PARTITION-LEVEL SORT, 3)
+ Reducer 4 <- Reducer 3 (SORT, 1)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -571,36 +573,7 @@ STAGE PLANS:
sort order: +++
Map-reduce partition columns: _col0 (type: string), _col1 (type: string)
Statistics: Num rows: 28 Data size: 297 Basic stats: COMPLETE Column stats: NONE
- Reducer 2
- Local Work:
- Map Reduce Local Work
- Reduce Operator Tree:
- Group By Operator
- aggregations: count(DISTINCT KEY._col2:0._col0)
- keys: KEY._col0 (type: string), KEY._col1 (type: string)
- mode: mergepartial
- outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 14 Data size: 148 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col0 (type: string), _col1 (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 14 Data size: 148 Basic stats: COMPLETE Column stats: NONE
- Spark HashTable Sink Operator
- condition expressions:
- 0 {_col1}
- 1 {_col0} {_col1}
- keys:
- 0 _col0 (type: string)
- 1 _col0 (type: string)
-
- Stage: Stage-1
- Spark
- Edges:
- Reducer 4 <- Map 3 (GROUP, 3)
- Reducer 5 <- Reducer 4 (SORT, 1)
-#### A masked pattern was here ####
- Vertices:
- Map 3
+ Map 5
Map Operator Tree:
TableScan
alias: src2
@@ -618,37 +591,43 @@ STAGE PLANS:
sort order: ++
Map-reduce partition columns: _col0 (type: string), _col1 (type: string)
Statistics: Num rows: 28 Data size: 297 Basic stats: COMPLETE Column stats: NONE
- Reducer 4
- Local Work:
- Map Reduce Local Work
+ Reducer 2
Reduce Operator Tree:
Group By Operator
+ aggregations: count(DISTINCT KEY._col2:0._col0)
keys: KEY._col0 (type: string), KEY._col1 (type: string)
mode: mergepartial
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 28 Data size: 297 Basic stats: COMPLETE Column stats: NONE
- Map Join Operator
- condition map:
- Inner Join 0 to 1
- condition expressions:
- 0 {_col0} {_col1}
- 1 {_col0} {_col1}
- keys:
- 0 _col0 (type: string)
- 1 _col0 (type: string)
- outputColumnNames: _col0, _col1, _col3, _col4
- input vertices:
- 0 Reducer 2
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 14 Data size: 148 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 14 Data size: 148 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 14 Data size: 148 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col1 (type: string)
+ Reducer 3
+ 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, _col3, _col4
+ Statistics: Num rows: 30 Data size: 326 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: string), _col3 (type: string), _col4 (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3
Statistics: Num rows: 30 Data size: 326 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col0 (type: string), _col1 (type: string), _col3 (type: string), _col4 (type: string)
- outputColumnNames: _col0, _col1, _col2, _col3
+ Reduce Output Operator
+ key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string)
+ sort order: --++
Statistics: Num rows: 30 Data size: 326 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string)
- sort order: --++
- Statistics: Num rows: 30 Data size: 326 Basic stats: COMPLETE Column stats: NONE
- Reducer 5
+ Reducer 4
Reduce Operator Tree:
Select Operator
expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey3 (type: string)
@@ -661,6 +640,19 @@ STAGE PLANS:
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:
+ Group By Operator
+ keys: KEY._col0 (type: string), KEY._col1 (type: string)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 28 Data size: 297 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 28 Data size: 297 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col1 (type: string)
Stage: Stage-0
Fetch Operator
Modified: hive/branches/spark/ql/src/test/results/clientpositive/spark/groupby_sort_1_23.q.out
URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/groupby_sort_1_23.q.out?rev=1642997&r1=1642996&r2=1642997&view=diff
==============================================================================
--- hive/branches/spark/ql/src/test/results/clientpositive/spark/groupby_sort_1_23.q.out (original)
+++ hive/branches/spark/ql/src/test/results/clientpositive/spark/groupby_sort_1_23.q.out Tue Dec 2 19:57:10 2014
@@ -2711,17 +2711,18 @@ TOK_QUERY
STAGE DEPENDENCIES:
- Stage-3 is a root stage
- Stage-1 depends on stages: Stage-3
+ Stage-1 is a root stage
Stage-0 depends on stages: Stage-1
Stage-2 depends on stages: Stage-0
STAGE PLANS:
- Stage: Stage-3
+ 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: t1
@@ -2737,16 +2738,14 @@ STAGE PLANS:
mode: final
outputColumnNames: _col0, _col1
Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE
- Spark HashTable Sink Operator
- condition expressions:
- 0 {_col0} {_col1}
- 1 {_col1}
- keys:
- 0 _col0 (type: string)
- 1 _col0 (type: string)
- Position of Big Table: 0
- Local Work:
- Map Reduce Local Work
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE
+ tag: 0
+ value expressions: _col1 (type: bigint)
+ auto parallelism: false
Path -> Alias:
#### A masked pattern was here ####
Path -> Partition:
@@ -2800,12 +2799,7 @@ STAGE PLANS:
name: default.t1
Truncated Path -> Alias:
/t1 [t1]
-
- Stage: Stage-1
- Spark
-#### A masked pattern was here ####
- Vertices:
- Map 1
+ Map 3
Map Operator Tree:
TableScan
alias: t1
@@ -2821,57 +2815,14 @@ STAGE PLANS:
mode: final
outputColumnNames: _col0, _col1
Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE
- Map Join Operator
- condition map:
- Inner Join 0 to 1
- condition expressions:
- 0 {_col0} {_col1}
- 1 {_col1}
- keys:
- 0 _col0 (type: string)
- 1 _col0 (type: string)
- outputColumnNames: _col0, _col1, _col3
- input vertices:
- 1 Map 2
- Position of Big Table: 0
- Statistics: Num rows: 3 Data size: 13 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: UDFToInteger(_col0) (type: int), UDFToInteger((_col1 + _col3)) (type: int)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 3 Data size: 13 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- GlobalTableId: 1
-#### A masked pattern was here ####
- NumFilesPerFileSink: 1
- Statistics: Num rows: 3 Data size: 13 Basic stats: COMPLETE Column stats: NONE
-#### A masked pattern was here ####
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- COLUMN_STATS_ACCURATE true
- bucket_count -1
- columns key,cnt
- columns.comments
- columns.types int:int
-#### A masked pattern was here ####
- name default.outputtbl1
- numFiles 4
- numRows 10
- rawDataSize 32
- serialization.ddl struct outputtbl1 { i32 key, i32 cnt}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 42
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.outputtbl1
- TotalFiles: 1
- GatherStats: true
- MultiFileSpray: false
- Local Work:
- Map Reduce Local Work
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE
+ tag: 1
+ value expressions: _col1 (type: bigint)
+ auto parallelism: false
Path -> Alias:
#### A masked pattern was here ####
Path -> Partition:
@@ -2925,6 +2876,52 @@ STAGE PLANS:
name: default.t1
Truncated Path -> Alias:
/t1 [t1]
+ Reducer 2
+ Needs Tagging: true
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0 {KEY.reducesinkkey0} {VALUE._col0}
+ 1 {VALUE._col0}
+ outputColumnNames: _col0, _col1, _col3
+ Statistics: Num rows: 3 Data size: 13 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: UDFToInteger(_col0) (type: int), UDFToInteger((_col1 + _col3)) (type: int)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 3 Data size: 13 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ GlobalTableId: 1
+#### A masked pattern was here ####
+ NumFilesPerFileSink: 1
+ Statistics: Num rows: 3 Data size: 13 Basic stats: COMPLETE Column stats: NONE
+#### A masked pattern was here ####
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ properties:
+ COLUMN_STATS_ACCURATE true
+ bucket_count -1
+ columns key,cnt
+ columns.comments
+ columns.types int:int
+#### A masked pattern was here ####
+ name default.outputtbl1
+ numFiles 4
+ numRows 10
+ rawDataSize 32
+ serialization.ddl struct outputtbl1 { i32 key, i32 cnt}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ totalSize 42
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.outputtbl1
+ TotalFiles: 1
+ GatherStats: true
+ MultiFileSpray: false
Stage: Stage-0
Move Operator
@@ -3079,18 +3076,18 @@ TOK_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 3 <- Map 2 (GROUP, 3)
+ Reducer 4 <- Map 3 (GROUP, 3)
+ Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 3), Reducer 4 (PARTITION-LEVEL SORT, 3)
#### A masked pattern was here ####
Vertices:
- Map 2
+ Map 1
Map Operator Tree:
TableScan
alias: t1
@@ -3102,17 +3099,17 @@ STAGE PLANS:
Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: count(1)
- keys: key (type: string), val (type: string)
- mode: hash
- outputColumnNames: _col0, _col1, _col2
+ keys: key (type: string)
+ mode: final
+ outputColumnNames: _col0, _col1
Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
- key expressions: _col0 (type: string), _col1 (type: string)
- sort order: ++
- Map-reduce partition columns: _col0 (type: string), _col1 (type: string)
+ key expressions: _col0 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE
- tag: -1
- value expressions: _col2 (type: bigint)
+ tag: 0
+ value expressions: _col1 (type: bigint)
auto parallelism: false
Path -> Alias:
#### A masked pattern was here ####
@@ -3167,31 +3164,7 @@ STAGE PLANS:
name: default.t1
Truncated Path -> Alias:
/t1 [t1]
- Reducer 3
- Local Work:
- Map Reduce Local Work
- Needs Tagging: false
- Reduce Operator Tree:
- Group By Operator
- aggregations: count(VALUE._col0)
- keys: KEY._col0 (type: string), KEY._col1 (type: string)
- mode: mergepartial
- outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE
- Spark HashTable Sink Operator
- condition expressions:
- 0 {_col0} {_col1}
- 1 {_col1} {_col2}
- keys:
- 0 _col0 (type: string)
- 1 _col0 (type: string)
- Position of Big Table: 0
-
- Stage: Stage-1
- Spark
-#### A masked pattern was here ####
- Vertices:
- Map 1
+ Map 3
Map Operator Tree:
TableScan
alias: t1
@@ -3203,51 +3176,18 @@ STAGE PLANS:
Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: count(1)
- keys: key (type: string)
- mode: final
- outputColumnNames: _col0, _col1
+ keys: key (type: string), val (type: string)
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2
Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE
- Map Join Operator
- condition map:
- Inner Join 0 to 1
- condition expressions:
- 0 {_col0} {_col1}
- 1 {_col0} {_col1} {_col2}
- keys:
- 0 _col0 (type: string)
- 1 _col0 (type: string)
- outputColumnNames: _col0, _col1, _col2, _col3, _col4
- input vertices:
- 1 Reducer 3
- Position of Big Table: 0
- Statistics: Num rows: 3 Data size: 13 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col0 (type: string), _col1 (type: bigint), _col2 (type: string), _col3 (type: string), _col4 (type: bigint)
- outputColumnNames: _col0, _col1, _col2, _col3, _col4
- Statistics: Num rows: 3 Data size: 13 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- GlobalTableId: 0
-#### A masked pattern was here ####
- NumFilesPerFileSink: 1
- Statistics: Num rows: 3 Data size: 13 Basic stats: COMPLETE Column stats: NONE
-#### A masked pattern was here ####
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- columns _col0,_col1,_col2,_col3,_col4
- columns.types string:bigint:string:string:bigint
- escape.delim \
- hive.serialization.extend.nesting.levels true
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- TotalFiles: 1
- GatherStats: false
- MultiFileSpray: false
- Local Work:
- Map Reduce Local Work
+ Reduce Output Operator
+ key expressions: _col0 (type: string), _col1 (type: string)
+ sort order: ++
+ Map-reduce partition columns: _col0 (type: string), _col1 (type: string)
+ Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE
+ tag: -1
+ value expressions: _col2 (type: bigint)
+ auto parallelism: false
Path -> Alias:
#### A masked pattern was here ####
Path -> Partition:
@@ -3301,6 +3241,59 @@ STAGE PLANS:
name: default.t1
Truncated Path -> Alias:
/t1 [t1]
+ Reducer 2
+ Needs Tagging: true
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0 {KEY.reducesinkkey0} {VALUE._col0}
+ 1 {KEY.reducesinkkey0} {VALUE._col0} {VALUE._col1}
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4
+ Statistics: Num rows: 3 Data size: 13 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: bigint), _col2 (type: string), _col3 (type: string), _col4 (type: bigint)
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4
+ Statistics: Num rows: 3 Data size: 13 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+#### A masked pattern was here ####
+ NumFilesPerFileSink: 1
+ Statistics: Num rows: 3 Data size: 13 Basic stats: COMPLETE Column stats: NONE
+#### A masked pattern was here ####
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ properties:
+ columns _col0,_col1,_col2,_col3,_col4
+ columns.types string:bigint:string:string:bigint
+ escape.delim \
+ hive.serialization.extend.nesting.levels true
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ TotalFiles: 1
+ GatherStats: false
+ MultiFileSpray: false
+ Reducer 4
+ Needs Tagging: false
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: count(VALUE._col0)
+ keys: KEY._col0 (type: string), KEY._col1 (type: string)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE
+ tag: 1
+ value expressions: _col1 (type: string), _col2 (type: bigint)
+ auto parallelism: false
Stage: Stage-0
Fetch Operator
@@ -3486,7 +3479,7 @@ STAGE PLANS:
columns.types int:int
#### A masked pattern was here ####
name default.outputtbl1
- numFiles 1
+ numFiles 3
numRows 5
rawDataSize 15
serialization.ddl struct outputtbl1 { i32 key, i32 cnt}
@@ -3516,7 +3509,7 @@ STAGE PLANS:
columns.types int:int
#### A masked pattern was here ####
name default.outputtbl1
- numFiles 1
+ numFiles 3
numRows 5
rawDataSize 15
serialization.ddl struct outputtbl1 { i32 key, i32 cnt}