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 [23/43] - 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/mapjoin_memcheck.q.out
URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/mapjoin_memcheck.q.out?rev=1641614&r1=1641613&r2=1641614&view=diff
==============================================================================
--- hive/branches/spark/ql/src/test/results/clientpositive/spark/mapjoin_memcheck.q.out (original)
+++ hive/branches/spark/ql/src/test/results/clientpositive/spark/mapjoin_memcheck.q.out Tue Nov 25 13:03:18 2014
@@ -29,14 +29,13 @@ select src1.key as k1, src1.value as v1,
from src0 src1 inner join src0 src2 on src1.key = src2.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
@@ -47,13 +46,21 @@ STAGE PLANS:
Filter Operator
predicate: key is not null (type: boolean)
Statistics: Num rows: 5 Data size: 35 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: 5 Data size: 35 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: string)
+ 1 key (type: string)
+ Local Work:
+ Map Reduce Local Work
+
+ Stage: Stage-1
+ Spark
+#### A masked pattern was here ####
+ Vertices:
+ Map 2
Map Operator Tree:
TableScan
alias: src1
@@ -61,33 +68,32 @@ STAGE PLANS:
Filter Operator
predicate: key is not null (type: boolean)
Statistics: Num rows: 5 Data size: 35 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: 5 Data size: 35 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: 5 Data size: 38 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string)
- outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 5 Data size: 38 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 5 Data size: 38 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: string)
+ 1 key (type: string)
+ outputColumnNames: _col0, _col1, _col5, _col6
+ input vertices:
+ 1 Map 1
+ Statistics: Num rows: 5 Data size: 38 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 5 Data size: 38 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 5 Data size: 38 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/mapjoin_subquery.q.out
URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/mapjoin_subquery.q.out?rev=1641614&r1=1641613&r2=1641614&view=diff
==============================================================================
--- hive/branches/spark/ql/src/test/results/clientpositive/spark/mapjoin_subquery.q.out (original)
+++ hive/branches/spark/ql/src/test/results/clientpositive/spark/mapjoin_subquery.q.out Tue Nov 25 13:03:18 2014
@@ -19,15 +19,13 @@ FROM
JOIN srcpart z ON (subq.key1 = z.key and z.ds='2008-04-08' and z.hr=11)
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 4 (PARTITION-LEVEL SORT, 1)
- Reducer 3 <- Map 5 (PARTITION-LEVEL SORT, 1), Reducer 2 (PARTITION-LEVEL SORT, 1)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -38,78 +36,88 @@ STAGE PLANS:
Filter Operator
predicate: key is not null (type: boolean)
Statistics: Num rows: 13 Data size: 99 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: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE
- Map 4
+ Spark HashTable Sink Operator
+ condition expressions:
+ 0
+ 1
+ keys:
+ 0 key (type: string)
+ 1 key (type: string)
+ Local Work:
+ Map Reduce Local Work
+ Map 3
Map Operator Tree:
TableScan
- alias: y
+ alias: z
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
- 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 5
+ Spark HashTable Sink Operator
+ condition expressions:
+ 0 {_col0}
+ 1 {value}
+ 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 2
Map Operator Tree:
TableScan
- alias: z
+ alias: y
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
- 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
- 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
- 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
- Reduce Output Operator
- key expressions: _col0 (type: string)
- sort order: +
- Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
- Reducer 3
- Reduce Operator Tree:
- Join Operator
- condition map:
- Inner Join 0 to 1
- condition expressions:
- 0 {KEY.reducesinkkey0}
- 1 {VALUE._col0}
- outputColumnNames: _col0, _col5
- Statistics: Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col0 (type: string), _col5 (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 302 Data size: 3213 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}
+ 1
+ keys:
+ 0 key (type: string)
+ 1 key (type: string)
+ outputColumnNames: _col0
+ input vertices:
+ 0 Map 1
+ 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
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0 {_col0}
+ 1 {value}
+ keys:
+ 0 _col0 (type: string)
+ 1 key (type: string)
+ outputColumnNames: _col0, _col5
+ input vertices:
+ 1 Map 3
+ Statistics: Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: string), _col5 (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 302 Data size: 3213 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
@@ -261,15 +269,13 @@ FROM
JOIN srcpart z ON (subq.key1 = z.key and z.ds='2008-04-08' and z.hr=11)
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 4 (PARTITION-LEVEL SORT, 1)
- Reducer 3 <- Map 5 (PARTITION-LEVEL SORT, 1), Reducer 2 (PARTITION-LEVEL SORT, 1)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -280,78 +286,88 @@ STAGE PLANS:
Filter Operator
predicate: key is not null (type: boolean)
Statistics: Num rows: 13 Data size: 99 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: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE
- Map 4
+ Spark HashTable Sink Operator
+ condition expressions:
+ 0
+ 1
+ keys:
+ 0 key (type: string)
+ 1 key (type: string)
+ Local Work:
+ Map Reduce Local Work
+ Map 3
Map Operator Tree:
TableScan
- alias: y
+ alias: z
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
- 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 5
+ Spark HashTable Sink Operator
+ condition expressions:
+ 0 {_col0}
+ 1 {value}
+ 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 2
Map Operator Tree:
TableScan
- alias: z
+ alias: y
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
- 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
- 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
- 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
- Reduce Output Operator
- key expressions: _col0 (type: string)
- sort order: +
- Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
- Reducer 3
- Reduce Operator Tree:
- Join Operator
- condition map:
- Inner Join 0 to 1
- condition expressions:
- 0 {KEY.reducesinkkey0}
- 1 {VALUE._col0}
- outputColumnNames: _col0, _col5
- Statistics: Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col0 (type: string), _col5 (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 302 Data size: 3213 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}
+ 1
+ keys:
+ 0 key (type: string)
+ 1 key (type: string)
+ outputColumnNames: _col0
+ input vertices:
+ 0 Map 1
+ 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
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0 {_col0}
+ 1 {value}
+ keys:
+ 0 _col0 (type: string)
+ 1 key (type: string)
+ outputColumnNames: _col0, _col5
+ input vertices:
+ 1 Map 3
+ Statistics: Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: string), _col5 (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 302 Data size: 3213 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/mapjoin_subquery2.q.out
URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/mapjoin_subquery2.q.out?rev=1641614&r1=1641613&r2=1641614&view=diff
==============================================================================
--- hive/branches/spark/ql/src/test/results/clientpositive/spark/mapjoin_subquery2.q.out (original)
+++ hive/branches/spark/ql/src/test/results/clientpositive/spark/mapjoin_subquery2.q.out Tue Nov 25 13:03:18 2014
@@ -83,15 +83,13 @@ FROM
JOIN z ON (subq.key1 = z.id)
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 4 (PARTITION-LEVEL SORT, 1)
- Reducer 3 <- Map 5 (PARTITION-LEVEL SORT, 1), Reducer 2 (PARTITION-LEVEL SORT, 1)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -102,81 +100,88 @@ STAGE PLANS:
Filter Operator
predicate: id is not null (type: boolean)
Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
- Reduce Output Operator
- key expressions: id (type: int)
- sort order: +
- Map-reduce partition columns: id (type: int)
- Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
- value expressions: name (type: string)
- Map 4
+ Spark HashTable Sink Operator
+ condition expressions:
+ 0 {id} {name}
+ 1 {name}
+ keys:
+ 0 id (type: int)
+ 1 id (type: int)
+ Local Work:
+ Map Reduce Local Work
+ Map 3
Map Operator Tree:
TableScan
- alias: y
+ alias: z
Statistics: Num rows: 0 Data size: 6 Basic stats: PARTIAL Column stats: NONE
Filter Operator
predicate: id is not null (type: boolean)
Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
- Reduce Output Operator
- key expressions: id (type: int)
- sort order: +
- Map-reduce partition columns: id (type: int)
- Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
- value expressions: name (type: string)
- Map 5
+ Spark HashTable Sink Operator
+ condition expressions:
+ 0 {_col0} {_col1} {_col2} {_col3}
+ 1 {name}
+ keys:
+ 0 _col0 (type: int)
+ 1 id (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: z
+ alias: y
Statistics: Num rows: 0 Data size: 6 Basic stats: PARTIAL Column stats: NONE
Filter Operator
predicate: id is not null (type: boolean)
Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
- Reduce Output Operator
- key expressions: id (type: int)
- sort order: +
- Map-reduce partition columns: id (type: int)
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0 {id} {name}
+ 1 {name} {id}
+ keys:
+ 0 id (type: int)
+ 1 id (type: int)
+ outputColumnNames: _col0, _col1, _col5, _col6
+ input vertices:
+ 1 Map 1
Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
- value expressions: name (type: string)
- Reducer 2
- Reduce Operator Tree:
- Join Operator
- condition map:
- Inner Join 0 to 1
- condition expressions:
- 0 {KEY.reducesinkkey0} {VALUE._col0}
- 1 {VALUE._col0} {KEY.reducesinkkey0}
- outputColumnNames: _col0, _col1, _col5, _col6
- Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
- Select Operator
- expressions: _col6 (type: int), _col5 (type: string), _col0 (type: int), _col1 (type: string)
- outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: int)
- sort order: +
- Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
- value expressions: _col1 (type: string), _col2 (type: int), _col3 (type: string)
- Reducer 3
- Reduce Operator Tree:
- Join Operator
- condition map:
- Inner Join 0 to 1
- condition expressions:
- 0 {KEY.reducesinkkey0} {VALUE._col0} {VALUE._col1} {VALUE._col2}
- 1 {KEY.reducesinkkey0} {VALUE._col0}
- outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
- Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
- Select Operator
- expressions: _col0 (type: int), _col1 (type: string), _col2 (type: int), _col3 (type: string), _col4 (type: int), _col5 (type: string)
- outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
- 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
+ Select Operator
+ expressions: _col6 (type: int), _col5 (type: string), _col0 (type: int), _col1 (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3
+ 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} {_col1} {_col2} {_col3}
+ 1 {id} {name}
+ keys:
+ 0 _col0 (type: int)
+ 1 id (type: int)
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
+ input vertices:
+ 1 Map 3
+ Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: int), _col1 (type: string), _col2 (type: int), _col3 (type: string), _col4 (type: int), _col5 (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
+ 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
Stage: Stage-0
Fetch Operator
Modified: hive/branches/spark/ql/src/test/results/clientpositive/spark/mapjoin_test_outer.q.out
URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/mapjoin_test_outer.q.out?rev=1641614&r1=1641613&r2=1641614&view=diff
==============================================================================
--- hive/branches/spark/ql/src/test/results/clientpositive/spark/mapjoin_test_outer.q.out (original)
+++ hive/branches/spark/ql/src/test/results/clientpositive/spark/mapjoin_test_outer.q.out Tue Nov 25 13:03:18 2014
@@ -244,71 +244,87 @@ SELECT /*+ mapjoin(src1, src2) */ * FROM
SORT BY src1.key, src1.value, src2.key, src2.value, src3.key, src3.value
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 4 (PARTITION-LEVEL SORT, 1), Map 5 (PARTITION-LEVEL SORT, 1)
- Reducer 3 <- Reducer 2 (SORT, 1)
#### A masked pattern was here ####
Vertices:
- Map 1
- Map Operator Tree:
- TableScan
- alias: src2
- Statistics: Num rows: 9 Data size: 40 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: 9 Data size: 40 Basic stats: COMPLETE Column stats: NONE
- value expressions: value (type: string)
- Map 4
+ Map 3
Map Operator Tree:
TableScan
alias: src3
Statistics: Num rows: 9 Data size: 40 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: 9 Data size: 40 Basic stats: COMPLETE Column stats: NONE
- value expressions: value (type: string)
- Map 5
+ Spark HashTable Sink Operator
+ condition expressions:
+ 0 {key} {value}
+ 1 {key} {value}
+ 2 {value}
+ keys:
+ 0 key (type: string)
+ 1 key (type: string)
+ 2 key (type: string)
+ Local Work:
+ Map Reduce Local Work
+ Map 4
Map Operator Tree:
TableScan
alias: src1
Statistics: Num rows: 25 Data size: 191 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: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE
- value expressions: value (type: string)
- Reducer 2
- Reduce Operator Tree:
- Join Operator
- condition map:
- Right Outer Join0 to 1
- Inner Join 1 to 2
- condition expressions:
- 0 {KEY.reducesinkkey0} {VALUE._col0}
- 1 {KEY.reducesinkkey0} {VALUE._col0}
- 2 {KEY.reducesinkkey0} {VALUE._col0}
- outputColumnNames: _col0, _col1, _col5, _col6, _col10, _col11
- Statistics: Num rows: 55 Data size: 420 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string), _col10 (type: string), _col11 (type: string)
- outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
- Statistics: Num rows: 55 Data size: 420 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string)
- sort order: ++++++
+ Spark HashTable Sink Operator
+ condition expressions:
+ 0 {value}
+ 1 {key} {value}
+ 2 {key} {value}
+ keys:
+ 0 key (type: string)
+ 1 key (type: string)
+ 2 key (type: string)
+ Local Work:
+ Map Reduce Local Work
+
+ Stage: Stage-1
+ Spark
+ Edges:
+ Reducer 2 <- Map 1 (SORT, 1)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: src2
+ Statistics: Num rows: 9 Data size: 40 Basic stats: COMPLETE Column stats: NONE
+ Map Join Operator
+ condition map:
+ Right Outer Join0 to 1
+ Inner Join 1 to 2
+ condition expressions:
+ 0 {key} {value}
+ 1 {key} {value}
+ 2 {key} {value}
+ keys:
+ 0 key (type: string)
+ 1 key (type: string)
+ 2 key (type: string)
+ outputColumnNames: _col0, _col1, _col5, _col6, _col10, _col11
+ input vertices:
+ 0 Map 4
+ 2 Map 3
Statistics: Num rows: 55 Data size: 420 Basic stats: COMPLETE Column stats: NONE
- Reducer 3
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string), _col10 (type: string), _col11 (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
+ Statistics: Num rows: 55 Data size: 420 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string)
+ sort order: ++++++
+ Statistics: Num rows: 55 Data size: 420 Basic stats: COMPLETE Column stats: NONE
+ Local Work:
+ Map Reduce Local Work
+ Reducer 2
Reduce Operator Tree:
Select Operator
expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey3 (type: string), KEY.reducesinkkey4 (type: string), KEY.reducesinkkey5 (type: string)
@@ -1070,71 +1086,87 @@ SELECT * FROM src1
SORT BY src1.key, src1.value, src2.key, src2.value, src3.key, src3.value
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 4 (PARTITION-LEVEL SORT, 1), Map 5 (PARTITION-LEVEL SORT, 1)
- Reducer 3 <- Reducer 2 (SORT, 1)
#### A masked pattern was here ####
Vertices:
- Map 1
- Map Operator Tree:
- TableScan
- alias: src2
- Statistics: Num rows: 9 Data size: 40 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: 9 Data size: 40 Basic stats: COMPLETE Column stats: NONE
- value expressions: value (type: string)
- Map 4
+ Map 3
Map Operator Tree:
TableScan
alias: src3
Statistics: Num rows: 9 Data size: 40 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: 9 Data size: 40 Basic stats: COMPLETE Column stats: NONE
- value expressions: value (type: string)
- Map 5
+ Spark HashTable Sink Operator
+ condition expressions:
+ 0 {key} {value}
+ 1 {key} {value}
+ 2 {value}
+ keys:
+ 0 key (type: string)
+ 1 key (type: string)
+ 2 key (type: string)
+ Local Work:
+ Map Reduce Local Work
+ Map 4
Map Operator Tree:
TableScan
alias: src1
Statistics: Num rows: 25 Data size: 191 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: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE
- value expressions: value (type: string)
- Reducer 2
- Reduce Operator Tree:
- Join Operator
- condition map:
- Right Outer Join0 to 1
- Inner Join 1 to 2
- condition expressions:
- 0 {KEY.reducesinkkey0} {VALUE._col0}
- 1 {KEY.reducesinkkey0} {VALUE._col0}
- 2 {KEY.reducesinkkey0} {VALUE._col0}
- outputColumnNames: _col0, _col1, _col5, _col6, _col10, _col11
- Statistics: Num rows: 55 Data size: 420 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string), _col10 (type: string), _col11 (type: string)
- outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
- Statistics: Num rows: 55 Data size: 420 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string)
- sort order: ++++++
+ Spark HashTable Sink Operator
+ condition expressions:
+ 0 {value}
+ 1 {key} {value}
+ 2 {key} {value}
+ keys:
+ 0 key (type: string)
+ 1 key (type: string)
+ 2 key (type: string)
+ Local Work:
+ Map Reduce Local Work
+
+ Stage: Stage-1
+ Spark
+ Edges:
+ Reducer 2 <- Map 1 (SORT, 1)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: src2
+ Statistics: Num rows: 9 Data size: 40 Basic stats: COMPLETE Column stats: NONE
+ Map Join Operator
+ condition map:
+ Right Outer Join0 to 1
+ Inner Join 1 to 2
+ condition expressions:
+ 0 {key} {value}
+ 1 {key} {value}
+ 2 {key} {value}
+ keys:
+ 0 key (type: string)
+ 1 key (type: string)
+ 2 key (type: string)
+ outputColumnNames: _col0, _col1, _col5, _col6, _col10, _col11
+ input vertices:
+ 0 Map 4
+ 2 Map 3
Statistics: Num rows: 55 Data size: 420 Basic stats: COMPLETE Column stats: NONE
- Reducer 3
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string), _col10 (type: string), _col11 (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
+ Statistics: Num rows: 55 Data size: 420 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string)
+ sort order: ++++++
+ Statistics: Num rows: 55 Data size: 420 Basic stats: COMPLETE Column stats: NONE
+ Local Work:
+ Map Reduce Local Work
+ Reducer 2
Reduce Operator Tree:
Select Operator
expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey3 (type: string), KEY.reducesinkkey4 (type: string), KEY.reducesinkkey5 (type: string)
Modified: hive/branches/spark/ql/src/test/results/clientpositive/spark/mergejoins.q.out
URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/mergejoins.q.out?rev=1641614&r1=1641613&r2=1641614&view=diff
==============================================================================
--- hive/branches/spark/ql/src/test/results/clientpositive/spark/mergejoins.q.out (original)
+++ hive/branches/spark/ql/src/test/results/clientpositive/spark/mergejoins.q.out Tue Nov 25 13:03:18 2014
@@ -43,15 +43,13 @@ PREHOOK: type: QUERY
POSTHOOK: query: explain select * from a join b on a.val1=b.val1 join c on a.val1=c.val1 join d on a.val1=d.val1 join e on a.val2=e.val2
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 5 (PARTITION-LEVEL SORT, 1), Map 6 (PARTITION-LEVEL SORT, 1), Map 7 (PARTITION-LEVEL SORT, 1)
- Reducer 3 <- Map 4 (PARTITION-LEVEL SORT, 1), Reducer 2 (PARTITION-LEVEL SORT, 1)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -62,13 +60,20 @@ STAGE PLANS:
Filter Operator
predicate: val1 is not null (type: boolean)
Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
- Reduce Output Operator
- key expressions: val1 (type: int)
- sort order: +
- Map-reduce partition columns: val1 (type: int)
- Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
- value expressions: val2 (type: int)
- Map 4
+ Spark HashTable Sink Operator
+ condition expressions:
+ 0 {val1} {val2}
+ 1 {val1} {val2}
+ 2 {val1} {val2}
+ 3 {val2}
+ keys:
+ 0 val1 (type: int)
+ 1 val1 (type: int)
+ 2 val1 (type: int)
+ 3 val1 (type: int)
+ Local Work:
+ Map Reduce Local Work
+ Map 2
Map Operator Tree:
TableScan
alias: e
@@ -76,13 +81,16 @@ STAGE PLANS:
Filter Operator
predicate: val2 is not null (type: boolean)
Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
- Reduce Output Operator
- key expressions: val2 (type: int)
- sort order: +
- Map-reduce partition columns: val2 (type: int)
- Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
- value expressions: val1 (type: int)
- Map 5
+ Spark HashTable Sink Operator
+ condition expressions:
+ 0 {_col0} {_col1} {_col5} {_col6} {_col10} {_col11} {_col15} {_col16}
+ 1 {val1}
+ keys:
+ 0 _col1 (type: int)
+ 1 val2 (type: int)
+ Local Work:
+ Map Reduce Local Work
+ Map 3
Map Operator Tree:
TableScan
alias: b
@@ -90,13 +98,20 @@ STAGE PLANS:
Filter Operator
predicate: val1 is not null (type: boolean)
Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
- Reduce Output Operator
- key expressions: val1 (type: int)
- sort order: +
- Map-reduce partition columns: val1 (type: int)
- Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
- value expressions: val2 (type: int)
- Map 6
+ Spark HashTable Sink Operator
+ condition expressions:
+ 0 {val1} {val2}
+ 1 {val2}
+ 2 {val1} {val2}
+ 3 {val1} {val2}
+ keys:
+ 0 val1 (type: int)
+ 1 val1 (type: int)
+ 2 val1 (type: int)
+ 3 val1 (type: int)
+ Local Work:
+ Map Reduce Local Work
+ Map 4
Map Operator Tree:
TableScan
alias: c
@@ -104,13 +119,25 @@ STAGE PLANS:
Filter Operator
predicate: val1 is not null (type: boolean)
Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
- Reduce Output Operator
- key expressions: val1 (type: int)
- sort order: +
- Map-reduce partition columns: val1 (type: int)
- Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
- value expressions: val2 (type: int)
- Map 7
+ Spark HashTable Sink Operator
+ condition expressions:
+ 0 {val1} {val2}
+ 1 {val1} {val2}
+ 2 {val2}
+ 3 {val1} {val2}
+ keys:
+ 0 val1 (type: int)
+ 1 val1 (type: int)
+ 2 val1 (type: int)
+ 3 val1 (type: int)
+ Local Work:
+ Map Reduce Local Work
+
+ Stage: Stage-1
+ Spark
+#### A masked pattern was here ####
+ Vertices:
+ Map 5
Map Operator Tree:
TableScan
alias: a
@@ -118,53 +145,53 @@ STAGE PLANS:
Filter Operator
predicate: (val1 is not null and val2 is not null) (type: boolean)
Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
- Reduce Output Operator
- key expressions: val1 (type: int)
- sort order: +
- Map-reduce partition columns: val1 (type: int)
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ Inner Join 0 to 2
+ Inner Join 0 to 3
+ condition expressions:
+ 0 {val1} {val2}
+ 1 {val1} {val2}
+ 2 {val1} {val2}
+ 3 {val1} {val2}
+ keys:
+ 0 val1 (type: int)
+ 1 val1 (type: int)
+ 2 val1 (type: int)
+ 3 val1 (type: int)
+ outputColumnNames: _col0, _col1, _col5, _col6, _col10, _col11, _col15, _col16
+ input vertices:
+ 1 Map 3
+ 2 Map 4
+ 3 Map 1
Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
- value expressions: val2 (type: int)
- Reducer 2
- Reduce Operator Tree:
- Join Operator
- condition map:
- Inner Join 0 to 1
- Inner Join 0 to 2
- Inner Join 0 to 3
- condition expressions:
- 0 {KEY.reducesinkkey0} {VALUE._col0}
- 1 {KEY.reducesinkkey0} {VALUE._col0}
- 2 {KEY.reducesinkkey0} {VALUE._col0}
- 3 {KEY.reducesinkkey0} {VALUE._col0}
- outputColumnNames: _col0, _col1, _col5, _col6, _col10, _col11, _col15, _col16
- Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
- Reduce Output Operator
- key expressions: _col1 (type: int)
- sort order: +
- Map-reduce partition columns: _col1 (type: int)
- Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
- value expressions: _col0 (type: int), _col5 (type: int), _col6 (type: int), _col10 (type: int), _col11 (type: int), _col15 (type: int), _col16 (type: int)
- Reducer 3
- Reduce Operator Tree:
- Join Operator
- condition map:
- Inner Join 0 to 1
- condition expressions:
- 0 {VALUE._col0} {KEY.reducesinkkey0} {VALUE._col4} {VALUE._col5} {VALUE._col9} {VALUE._col10} {VALUE._col14} {VALUE._col15}
- 1 {VALUE._col0} {KEY.reducesinkkey0}
- outputColumnNames: _col0, _col1, _col5, _col6, _col10, _col11, _col15, _col16, _col20, _col21
- Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
- Select Operator
- expressions: _col0 (type: int), _col1 (type: int), _col5 (type: int), _col6 (type: int), _col10 (type: int), _col11 (type: int), _col15 (type: int), _col16 (type: int), _col20 (type: int), _col21 (type: int)
- outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9
- 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
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0 {_col0} {_col1} {_col5} {_col6} {_col10} {_col11} {_col15} {_col16}
+ 1 {val1} {val2}
+ keys:
+ 0 _col1 (type: int)
+ 1 val2 (type: int)
+ outputColumnNames: _col0, _col1, _col5, _col6, _col10, _col11, _col15, _col16, _col20, _col21
+ input vertices:
+ 1 Map 2
+ Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: int), _col1 (type: int), _col5 (type: int), _col6 (type: int), _col10 (type: int), _col11 (type: int), _col15 (type: int), _col16 (type: int), _col20 (type: int), _col21 (type: int)
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9
+ 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
Stage: Stage-0
Fetch Operator
@@ -179,14 +206,13 @@ POSTHOOK: query: --HIVE-3070 filter on o
explain select * from src a join src b on a.key=b.key left outer join src c on b.key=c.key and b.key<10
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), Map 4 (PARTITION-LEVEL SORT, 1)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -194,61 +220,85 @@ STAGE PLANS:
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 3
+ Spark HashTable Sink Operator
+ condition expressions:
+ 0 {key} {value}
+ 1 {value}
+ 2 {key} {value}
+ filter predicates:
+ 0
+ 1 {(key < 10)}
+ 2
+ keys:
+ 0 key (type: string)
+ 1 key (type: string)
+ 2 key (type: string)
+ Local Work:
+ Map Reduce Local Work
+ Map 2
Map Operator Tree:
TableScan
alias: c
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 4
+ Spark HashTable Sink Operator
+ condition expressions:
+ 0 {key} {value}
+ 1 {key} {value}
+ 2 {value}
+ filter predicates:
+ 0
+ 1 {(key < 10)}
+ 2
+ keys:
+ 0 key (type: string)
+ 1 key (type: string)
+ 2 key (type: string)
+ Local Work:
+ Map Reduce Local Work
+
+ Stage: Stage-1
+ Spark
+#### A masked pattern was here ####
+ Vertices:
+ Map 3
Map Operator Tree:
TableScan
alias: a
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)
- Reducer 2
- Reduce Operator Tree:
- Join Operator
- condition map:
- Inner Join 0 to 1
- Left Outer Join1 to 2
- condition expressions:
- 0 {KEY.reducesinkkey0} {VALUE._col0}
- 1 {KEY.reducesinkkey0} {VALUE._col0}
- 2 {KEY.reducesinkkey0} {VALUE._col0}
- filter predicates:
- 0
- 1 {(KEY.reducesinkkey0 < 10)}
- 2
- outputColumnNames: _col0, _col1, _col5, _col6, _col10, _col11
- Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string), _col10 (type: string), _col11 (type: string)
- outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
- Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ Left Outer Join1 to 2
+ condition expressions:
+ 0 {key} {value}
+ 1 {key} {value}
+ 2 {key} {value}
+ filter predicates:
+ 0
+ 1 {(key < 10)}
+ 2
+ keys:
+ 0 key (type: string)
+ 1 key (type: string)
+ 2 key (type: string)
+ outputColumnNames: _col0, _col1, _col5, _col6, _col10, _col11
+ input vertices:
+ 1 Map 1
+ 2 Map 2
Statistics: Num rows: 1100 Data size: 11686 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: string), _col1 (type: string), _col5 (type: string), _col6 (type: string), _col10 (type: string), _col11 (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
+ Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1100 Data size: 11686 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