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 [3/43] - 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/src...
Modified: hive/branches/spark/ql/src/test/results/clientpositive/spark/auto_join14.q.out
URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/auto_join14.q.out?rev=1641614&r1=1641613&r2=1641614&view=diff
==============================================================================
--- hive/branches/spark/ql/src/test/results/clientpositive/spark/auto_join14.q.out (original)
+++ hive/branches/spark/ql/src/test/results/clientpositive/spark/auto_join14.q.out Tue Nov 25 13:03:18 2014
@@ -19,16 +19,37 @@ FROM src JOIN srcpart ON src.key = srcpa
INSERT OVERWRITE TABLE dest1 SELECT src.key, srcpart.value
POSTHOOK: type: QUERY
STAGE DEPENDENCIES:
- Stage-1 is a root stage
+ Stage-4 is a root stage
+ Stage-1 depends on stages: Stage-4
Stage-2 depends on stages: Stage-1
Stage-0 depends on stages: Stage-2
Stage-3 depends on stages: Stage-0
STAGE PLANS:
+ Stage: Stage-4
+ Spark
+#### A masked pattern was here ####
+ Vertices:
+ Map 2
+ Map Operator Tree:
+ TableScan
+ alias: src
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: (key > 100) (type: boolean)
+ Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
+ Spark HashTable Sink Operator
+ condition expressions:
+ 0
+ 1 {value}
+ keys:
+ 0 key (type: string)
+ 1 key (type: string)
+ Local Work:
+ Map Reduce Local Work
+
Stage: Stage-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
@@ -39,47 +60,33 @@ STAGE PLANS:
Filter Operator
predicate: ((key > 100) and key is not null) (type: boolean)
Statistics: Num rows: 167 Data size: 1774 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: 167 Data size: 1774 Basic stats: COMPLETE Column stats: NONE
- value expressions: value (type: string)
- Map 3
- Map Operator Tree:
- TableScan
- alias: src
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- predicate: (key > 100) (type: boolean)
- Statistics: Num rows: 166 Data size: 1763 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: 166 Data size: 1763 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 {VALUE._col0}
- outputColumnNames: _col0, _col6
- Statistics: Num rows: 183 Data size: 1951 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: UDFToInteger(_col0) (type: int), _col6 (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 183 Data size: 1951 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 183 Data size: 1951 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
- name: default.dest1
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0 {key}
+ 1 {value}
+ keys:
+ 0 key (type: string)
+ 1 key (type: string)
+ outputColumnNames: _col0, _col6
+ input vertices:
+ 0 Map 2
+ Statistics: Num rows: 183 Data size: 1951 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: UDFToInteger(_col0) (type: int), _col6 (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 183 Data size: 1951 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 183 Data size: 1951 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
+ name: default.dest1
+ Local Work:
+ Map Reduce Local Work
Stage: Stage-2
Dependency Collection
Modified: hive/branches/spark/ql/src/test/results/clientpositive/spark/auto_join15.q.out
URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/auto_join15.q.out?rev=1641614&r1=1641613&r2=1641614&view=diff
==============================================================================
--- hive/branches/spark/ql/src/test/results/clientpositive/spark/auto_join15.q.out (original)
+++ hive/branches/spark/ql/src/test/results/clientpositive/spark/auto_join15.q.out Tue Nov 25 13:03:18 2014
@@ -15,16 +15,13 @@ SORT BY k1, v1, k2, v2
) a
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)
- Reducer 3 <- Reducer 2 (SORT, 1)
- Reducer 4 <- Reducer 3 (GROUP, 1)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -35,13 +32,24 @@ STAGE PLANS:
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)
- Map 5
+ 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
+ Edges:
+ Reducer 3 <- Map 2 (SORT, 1)
+ Reducer 4 <- Reducer 3 (GROUP, 1)
+#### A masked pattern was here ####
+ Vertices:
+ Map 2
Map Operator Tree:
TableScan
alias: src1
@@ -49,30 +57,29 @@ STAGE PLANS:
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} {VALUE._col0}
- 1 {KEY.reducesinkkey0} {VALUE._col0}
- outputColumnNames: _col0, _col1, _col5, _col6
- Statistics: Num rows: 275 Data size: 2921 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: 275 Data size: 2921 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: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0 {key} {value}
+ 1 {key} {value}
+ keys:
+ 0 key (type: string)
+ 1 key (type: string)
+ outputColumnNames: _col0, _col1, _col5, _col6
+ input vertices:
+ 1 Map 1
+ Statistics: Num rows: 275 Data size: 2921 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: 275 Data size: 2921 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: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
+ Local Work:
+ Map Reduce Local Work
Reducer 3
Reduce Operator Tree:
Select Operator
Modified: hive/branches/spark/ql/src/test/results/clientpositive/spark/auto_join16.q.out
URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/auto_join16.q.out?rev=1641614&r1=1641613&r2=1641614&view=diff
==============================================================================
--- hive/branches/spark/ql/src/test/results/clientpositive/spark/auto_join16.q.out (original)
+++ hive/branches/spark/ql/src/test/results/clientpositive/spark/auto_join16.q.out Tue Nov 25 13:03:18 2014
@@ -15,15 +15,13 @@ ON (subq.key = tab.key and subq.key > 20
where tab.value < 200
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 <- Reducer 2 (GROUP, 1)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -38,12 +36,23 @@ STAGE PLANS:
expressions: key (type: string), value (type: string)
outputColumnNames: _col0, _col1
Statistics: Num rows: 9 Data size: 95 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)
- Statistics: Num rows: 9 Data size: 95 Basic stats: COMPLETE Column stats: NONE
- Map 4
+ Spark HashTable Sink Operator
+ condition expressions:
+ 0
+ 1 {value}
+ keys:
+ 0 _col0 (type: string), _col1 (type: string)
+ 1 key (type: string), value (type: string)
+ Local Work:
+ Map Reduce Local Work
+
+ Stage: Stage-1
+ Spark
+ Edges:
+ Reducer 3 <- Map 2 (GROUP, 1)
+#### A masked pattern was here ####
+ Vertices:
+ Map 2
Map Operator Tree:
TableScan
alias: tab
@@ -51,34 +60,34 @@ STAGE PLANS:
Filter Operator
predicate: ((((key > 20) and value is not null) and key is not null) and (value < 200)) (type: boolean)
Statistics: Num rows: 14 Data size: 148 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: key (type: string), value (type: string)
- sort order: ++
- Map-reduce partition columns: key (type: string), value (type: string)
- Statistics: Num rows: 14 Data size: 148 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 {KEY.reducesinkkey1}
- outputColumnNames: _col0, _col3
- Statistics: Num rows: 15 Data size: 162 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col0 (type: string), _col3 (type: string)
- outputColumnNames: _col0, _col3
- Statistics: Num rows: 15 Data size: 162 Basic stats: COMPLETE Column stats: NONE
- Group By Operator
- aggregations: sum(hash(_col0,_col3))
- mode: hash
- outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- sort order:
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col0 (type: bigint)
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0 {_col0}
+ 1 {value}
+ keys:
+ 0 _col0 (type: string), _col1 (type: string)
+ 1 key (type: string), value (type: string)
+ outputColumnNames: _col0, _col3
+ input vertices:
+ 0 Map 1
+ Statistics: Num rows: 15 Data size: 162 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: string), _col3 (type: string)
+ outputColumnNames: _col0, _col3
+ Statistics: Num rows: 15 Data size: 162 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: sum(hash(_col0,_col3))
+ mode: hash
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: bigint)
+ Local Work:
+ Map Reduce Local Work
Reducer 3
Reduce Operator Tree:
Group By Operator
Modified: hive/branches/spark/ql/src/test/results/clientpositive/spark/auto_join17.q.out
URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/auto_join17.q.out?rev=1641614&r1=1641613&r2=1641614&view=diff
==============================================================================
--- hive/branches/spark/ql/src/test/results/clientpositive/spark/auto_join17.q.out (original)
+++ hive/branches/spark/ql/src/test/results/clientpositive/spark/auto_join17.q.out Tue Nov 25 13:03:18 2014
@@ -15,16 +15,15 @@ FROM src src1 JOIN src src2 ON (src1.key
INSERT OVERWRITE TABLE dest1 SELECT src1.*, src2.*
POSTHOOK: type: QUERY
STAGE DEPENDENCIES:
- Stage-1 is a root stage
+ Stage-4 is a root stage
+ Stage-1 depends on stages: Stage-4
Stage-2 depends on stages: Stage-1
Stage-0 depends on stages: Stage-2
Stage-3 depends on stages: Stage-0
STAGE PLANS:
- Stage: Stage-1
+ Stage: Stage-4
Spark
- Edges:
- Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 1), Map 3 (PARTITION-LEVEL SORT, 1)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -35,13 +34,21 @@ STAGE PLANS:
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)
- 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
@@ -49,34 +56,33 @@ STAGE PLANS:
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} {VALUE._col0}
- 1 {KEY.reducesinkkey0} {VALUE._col0}
- outputColumnNames: _col0, _col1, _col5, _col6
- Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: UDFToInteger(_col0) (type: int), _col1 (type: string), UDFToInteger(_col5) (type: int), _col6 (type: string)
- outputColumnNames: _col0, _col1, _col2, _col3
- 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
- name: default.dest1
+ 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: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: UDFToInteger(_col0) (type: int), _col1 (type: string), UDFToInteger(_col5) (type: int), _col6 (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3
+ 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
+ name: default.dest1
+ Local Work:
+ Map Reduce Local Work
Stage: Stage-2
Dependency Collection
Modified: hive/branches/spark/ql/src/test/results/clientpositive/spark/auto_join19.q.out
URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/auto_join19.q.out?rev=1641614&r1=1641613&r2=1641614&view=diff
==============================================================================
--- hive/branches/spark/ql/src/test/results/clientpositive/spark/auto_join19.q.out (original)
+++ hive/branches/spark/ql/src/test/results/clientpositive/spark/auto_join19.q.out Tue Nov 25 13:03:18 2014
@@ -17,16 +17,15 @@ INSERT OVERWRITE TABLE dest1 SELECT src1
where (src1.ds = '2008-04-08' or src1.ds = '2008-04-09' )and (src1.hr = '12' or src1.hr = '11')
POSTHOOK: type: QUERY
STAGE DEPENDENCIES:
- Stage-1 is a root stage
+ Stage-4 is a root stage
+ Stage-1 depends on stages: Stage-4
Stage-2 depends on stages: Stage-1
Stage-0 depends on stages: Stage-2
Stage-3 depends on stages: Stage-0
STAGE PLANS:
- Stage: Stage-1
+ Stage: Stage-4
Spark
- Edges:
- Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 1), Map 3 (PARTITION-LEVEL SORT, 1)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -37,13 +36,21 @@ STAGE PLANS:
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)
- Map 3
+ Spark HashTable Sink Operator
+ condition expressions:
+ 0 {key}
+ 1 {value}
+ keys:
+ 0 key (type: string)
+ 1 key (type: string)
+ Local Work:
+ Map Reduce Local Work
+
+ Stage: Stage-1
+ Spark
+#### A masked pattern was here ####
+ Vertices:
+ Map 2
Map Operator Tree:
TableScan
alias: src1
@@ -51,33 +58,33 @@ STAGE PLANS:
Filter Operator
predicate: key is not null (type: boolean)
Statistics: Num rows: 1000 Data size: 10624 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: 1000 Data size: 10624 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 {VALUE._col0}
- outputColumnNames: _col0, _col8
- Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: UDFToInteger(_col0) (type: int), _col8 (type: string)
- outputColumnNames: _col0, _col1
- 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
- name: default.dest1
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0 {key}
+ 1 {value}
+ keys:
+ 0 key (type: string)
+ 1 key (type: string)
+ outputColumnNames: _col0, _col8
+ input vertices:
+ 1 Map 1
+ Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: UDFToInteger(_col0) (type: int), _col8 (type: string)
+ outputColumnNames: _col0, _col1
+ 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
+ name: default.dest1
+ Local Work:
+ Map Reduce Local Work
Stage: Stage-2
Dependency Collection
Modified: hive/branches/spark/ql/src/test/results/clientpositive/spark/auto_join2.q.out
URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/auto_join2.q.out?rev=1641614&r1=1641613&r2=1641614&view=diff
==============================================================================
--- hive/branches/spark/ql/src/test/results/clientpositive/spark/auto_join2.q.out (original)
+++ hive/branches/spark/ql/src/test/results/clientpositive/spark/auto_join2.q.out Tue Nov 25 13:03:18 2014
@@ -15,17 +15,16 @@ FROM src src1 JOIN src src2 ON (src1.key
INSERT OVERWRITE TABLE dest_j2 SELECT src1.key, src3.value
POSTHOOK: type: QUERY
STAGE DEPENDENCIES:
- Stage-1 is a root stage
+ Stage-5 is a root stage
+ Stage-4 depends on stages: Stage-5
+ Stage-1 depends on stages: Stage-4
Stage-2 depends on stages: Stage-1
Stage-0 depends on stages: Stage-2
Stage-3 depends on stages: Stage-0
STAGE PLANS:
- Stage: Stage-1
+ Stage: Stage-5
Spark
- Edges:
- Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 1), Map 5 (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
@@ -36,79 +35,93 @@ STAGE PLANS:
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 4
+ 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-4
+ Spark
+#### A masked pattern was here ####
+ Vertices:
+ Map 3
Map Operator Tree:
TableScan
- alias: src3
+ alias: src1
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: UDFToDouble(key) is not null (type: boolean)
+ 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: UDFToDouble(key) (type: double)
- sort order: +
- Map-reduce partition columns: UDFToDouble(key) (type: double)
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
- value expressions: value (type: string)
- Map 5
+ 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 1
+ Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: (_col0 + _col5) is not null (type: boolean)
+ Statistics: Num rows: 138 Data size: 1465 Basic stats: COMPLETE Column stats: NONE
+ Spark HashTable Sink Operator
+ condition expressions:
+ 0 {_col0}
+ 1 {value}
+ keys:
+ 0 (_col0 + _col5) (type: double)
+ 1 UDFToDouble(key) (type: double)
+ Local Work:
+ Map Reduce Local Work
+
+ Stage: Stage-1
+ Spark
+#### A masked pattern was here ####
+ Vertices:
+ Map 2
Map Operator Tree:
TableScan
- alias: src1
+ alias: src3
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: key is not null (type: boolean)
+ predicate: UDFToDouble(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
- 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: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- predicate: (_col0 + _col5) is not null (type: boolean)
- Statistics: Num rows: 138 Data size: 1465 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: (_col0 + _col5) (type: double)
- sort order: +
- Map-reduce partition columns: (_col0 + _col5) (type: double)
- Statistics: Num rows: 138 Data size: 1465 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col0 (type: string)
- Reducer 3
- Reduce Operator Tree:
- Join Operator
- condition map:
- Inner Join 0 to 1
- condition expressions:
- 0 {VALUE._col0}
- 1 {VALUE._col1}
- outputColumnNames: _col0, _col11
- Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: UDFToInteger(_col0) (type: int), _col11 (type: string)
- outputColumnNames: _col0, _col1
- 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
- name: default.dest_j2
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0 {_col0}
+ 1 {value}
+ keys:
+ 0 (_col0 + _col5) (type: double)
+ 1 UDFToDouble(key) (type: double)
+ outputColumnNames: _col0, _col11
+ input vertices:
+ 0 Map 3
+ Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: UDFToInteger(_col0) (type: int), _col11 (type: string)
+ outputColumnNames: _col0, _col1
+ 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
+ name: default.dest_j2
+ Local Work:
+ Map Reduce Local Work
Stage: Stage-2
Dependency Collection
Modified: hive/branches/spark/ql/src/test/results/clientpositive/spark/auto_join20.q.out
URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/auto_join20.q.out?rev=1641614&r1=1641613&r2=1641614&view=diff
==============================================================================
--- hive/branches/spark/ql/src/test/results/clientpositive/spark/auto_join20.q.out (original)
+++ hive/branches/spark/ql/src/test/results/clientpositive/spark/auto_join20.q.out Tue Nov 25 13:03:18 2014
@@ -15,30 +15,16 @@ SORT BY k1,v1,k2,v2,k3,v3
)a
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)
- Reducer 3 <- Reducer 2 (SORT, 1)
- Reducer 4 <- Reducer 3 (GROUP, 1)
#### A masked pattern was here ####
Vertices:
- Map 1
- Map Operator Tree:
- TableScan
- alias: src3
- 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 5
+ Map 4
Map Operator Tree:
TableScan
alias: src2
@@ -46,13 +32,22 @@ STAGE PLANS:
Filter Operator
predicate: (key < 10) (type: boolean)
Statistics: Num rows: 166 Data size: 1763 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: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
- value expressions: value (type: string)
- Map 6
+ Spark HashTable Sink Operator
+ condition expressions:
+ 0 {key} {value}
+ 1 {value}
+ 2 {key} {value}
+ filter predicates:
+ 0
+ 1
+ 2 {(key < 20)}
+ keys:
+ 0 key (type: string)
+ 1 key (type: string)
+ 2 key (type: string)
+ Local Work:
+ Map Reduce Local Work
+ Map 5
Map Operator Tree:
TableScan
alias: src1
@@ -60,37 +55,66 @@ STAGE PLANS:
Filter Operator
predicate: (key < 10) (type: boolean)
Statistics: Num rows: 166 Data size: 1763 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: 166 Data size: 1763 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
- Right Outer Join0 to 2
- condition expressions:
- 0 {KEY.reducesinkkey0} {VALUE._col0}
- 1 {KEY.reducesinkkey0} {VALUE._col0}
- 2 {KEY.reducesinkkey0} {VALUE._col0}
- filter predicates:
- 0
- 1
- 2 {(KEY.reducesinkkey0 < 20)}
- 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
- 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}
+ filter predicates:
+ 0
+ 1
+ 2 {(key < 20)}
+ 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)
+ Reducer 3 <- Reducer 2 (GROUP, 1)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: src3
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ Right Outer Join0 to 2
+ condition expressions:
+ 0 {key} {value}
+ 1 {key} {value}
+ 2 {key} {value}
+ filter predicates:
+ 0
+ 1
+ 2 {(key < 20)}
+ keys:
+ 0 key (type: string)
+ 1 key (type: string)
+ 2 key (type: string)
+ outputColumnNames: _col0, _col1, _col5, _col6, _col10, _col11
+ input vertices:
+ 0 Map 5
+ 1 Map 4
Statistics: Num rows: 1100 Data size: 11686 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: 1100 Data size: 11686 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: 1100 Data size: 11686 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)
@@ -105,7 +129,7 @@ STAGE PLANS:
sort order:
Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
value expressions: _col0 (type: bigint)
- Reducer 4
+ Reducer 3
Reduce Operator Tree:
Group By Operator
aggregations: sum(VALUE._col0)
@@ -166,30 +190,16 @@ SORT BY k1,v1,k2,v2,k3,v3
)a
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)
- Reducer 3 <- Reducer 2 (SORT, 1)
- Reducer 4 <- Reducer 3 (GROUP, 1)
#### A masked pattern was here ####
Vertices:
- Map 1
- Map Operator Tree:
- TableScan
- alias: src3
- 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 5
+ Map 4
Map Operator Tree:
TableScan
alias: src2
@@ -197,13 +207,22 @@ STAGE PLANS:
Filter Operator
predicate: ((key < 10) and (key < 15)) (type: boolean)
Statistics: Num rows: 55 Data size: 584 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: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
- value expressions: value (type: string)
- Map 6
+ Spark HashTable Sink Operator
+ condition expressions:
+ 0 {key} {value}
+ 1 {value}
+ 2 {key} {value}
+ filter predicates:
+ 0
+ 1
+ 2 {(key < 20)}
+ keys:
+ 0 key (type: string)
+ 1 key (type: string)
+ 2 key (type: string)
+ Local Work:
+ Map Reduce Local Work
+ Map 5
Map Operator Tree:
TableScan
alias: src1
@@ -211,37 +230,66 @@ STAGE PLANS:
Filter Operator
predicate: ((key < 15) and (key < 10)) (type: boolean)
Statistics: Num rows: 55 Data size: 584 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: 55 Data size: 584 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
- Right Outer Join0 to 2
- condition expressions:
- 0 {KEY.reducesinkkey0} {VALUE._col0}
- 1 {KEY.reducesinkkey0} {VALUE._col0}
- 2 {KEY.reducesinkkey0} {VALUE._col0}
- filter predicates:
- 0
- 1
- 2 {(KEY.reducesinkkey0 < 20)}
- 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
- 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}
+ filter predicates:
+ 0
+ 1
+ 2 {(key < 20)}
+ 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)
+ Reducer 3 <- Reducer 2 (GROUP, 1)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: src3
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ Right Outer Join0 to 2
+ condition expressions:
+ 0 {key} {value}
+ 1 {key} {value}
+ 2 {key} {value}
+ filter predicates:
+ 0
+ 1
+ 2 {(key < 20)}
+ keys:
+ 0 key (type: string)
+ 1 key (type: string)
+ 2 key (type: string)
+ outputColumnNames: _col0, _col1, _col5, _col6, _col10, _col11
+ input vertices:
+ 0 Map 5
+ 1 Map 4
Statistics: Num rows: 1100 Data size: 11686 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: 1100 Data size: 11686 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: 1100 Data size: 11686 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)
@@ -256,7 +304,7 @@ STAGE PLANS:
sort order:
Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
value expressions: _col0 (type: bigint)
- Reducer 4
+ Reducer 3
Reduce Operator Tree:
Group By Operator
aggregations: sum(VALUE._col0)
Modified: hive/branches/spark/ql/src/test/results/clientpositive/spark/auto_join21.q.out
URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/auto_join21.q.out?rev=1641614&r1=1641613&r2=1641614&view=diff
==============================================================================
--- hive/branches/spark/ql/src/test/results/clientpositive/spark/auto_join21.q.out (original)
+++ hive/branches/spark/ql/src/test/results/clientpositive/spark/auto_join21.q.out Tue Nov 25 13:03:18 2014
@@ -5,15 +5,13 @@ POSTHOOK: query: explain
SELECT * FROM src src1 LEFT OUTER JOIN src src2 ON (src1.key = src2.key AND src1.key < 10 AND src2.key > 10) RIGHT OUTER JOIN src src3 ON (src2.key = src3.key AND src3.key < 10) 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
@@ -24,58 +22,84 @@ STAGE PLANS:
Filter Operator
predicate: (key > 10) (type: boolean)
Statistics: Num rows: 166 Data size: 1763 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: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
- value expressions: value (type: string)
+ Spark HashTable Sink Operator
+ condition expressions:
+ 0 {key} {value}
+ 1 {value}
+ 2 {key} {value}
+ filter predicates:
+ 0 {(key < 10)}
+ 1
+ 2 {(key < 10)}
+ 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: src3
+ alias: src1
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 5
+ Spark HashTable Sink Operator
+ condition expressions:
+ 0 {value}
+ 1 {key} {value}
+ 2 {key} {value}
+ filter predicates:
+ 0 {(key < 10)}
+ 1
+ 2 {(key < 10)}
+ 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 3 <- Map 2 (SORT, 1)
+#### A masked pattern was here ####
+ Vertices:
+ Map 2
Map Operator Tree:
TableScan
- alias: src1
+ alias: src3
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:
- Left Outer Join0 to 1
- Right Outer Join1 to 2
- condition expressions:
- 0 {KEY.reducesinkkey0} {VALUE._col0}
- 1 {KEY.reducesinkkey0} {VALUE._col0}
- 2 {KEY.reducesinkkey0} {VALUE._col0}
- filter predicates:
- 0 {(KEY.reducesinkkey0 < 10)}
- 1
- 2 {(KEY.reducesinkkey0 < 10)}
- 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
- 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: ++++++
+ Map Join Operator
+ condition map:
+ Left Outer Join0 to 1
+ Right Outer Join1 to 2
+ condition expressions:
+ 0 {key} {value}
+ 1 {key} {value}
+ 2 {key} {value}
+ filter predicates:
+ 0 {(key < 10)}
+ 1
+ 2 {(key < 10)}
+ 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
+ 1 Map 1
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
+ 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: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE
+ Local Work:
+ Map Reduce Local Work
Reducer 3
Reduce Operator Tree:
Select Operator
Modified: hive/branches/spark/ql/src/test/results/clientpositive/spark/auto_join22.q.out
URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/auto_join22.q.out?rev=1641614&r1=1641613&r2=1641614&view=diff
==============================================================================
--- hive/branches/spark/ql/src/test/results/clientpositive/spark/auto_join22.q.out (original)
+++ hive/branches/spark/ql/src/test/results/clientpositive/spark/auto_join22.q.out Tue Nov 25 13:03:18 2014
@@ -5,16 +5,13 @@ POSTHOOK: query: explain
SELECT sum(hash(src5.src1_value)) FROM (SELECT src3.*, src4.value as src4_value, src4.key as src4_key FROM src src4 JOIN (SELECT src2.*, src1.key as src1_key, src1.value as src1_value FROM src src1 JOIN src src2 ON src1.key = src2.key) src3 ON src3.src1_key = src4.key) src5
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)
- Reducer 3 <- Map 6 (PARTITION-LEVEL SORT, 1), Reducer 2 (PARTITION-LEVEL SORT, 1)
- Reducer 4 <- Reducer 3 (GROUP, 1)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -25,83 +22,94 @@ STAGE PLANS:
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 {key} {value}
+ 1
+ keys:
+ 0 key (type: string)
+ 1 key (type: string)
+ Local Work:
+ Map Reduce Local Work
+ Map 4
Map Operator Tree:
TableScan
- alias: src1
+ alias: src4
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)
- Map 6
+ Spark HashTable Sink Operator
+ condition expressions:
+ 0
+ 1 {_col3}
+ keys:
+ 0 key (type: string)
+ 1 _col2 (type: string)
+ Local Work:
+ Map Reduce Local Work
+
+ Stage: Stage-1
+ Spark
+ Edges:
+ Reducer 3 <- Map 2 (GROUP, 1)
+#### A masked pattern was here ####
+ Vertices:
+ Map 2
Map Operator Tree:
TableScan
- alias: src4
+ alias: src1
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
- Reducer 2
- Reduce Operator Tree:
- Join Operator
- condition map:
- Inner Join 0 to 1
- condition expressions:
- 0 {KEY.reducesinkkey0} {VALUE._col0}
- 1
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col0 (type: string), _col1 (type: string)
- outputColumnNames: _col2, _col3
- Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col2 (type: string)
- sort order: +
- Map-reduce partition columns: _col2 (type: string)
- Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col3 (type: string)
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0 {key} {value}
+ 1
+ keys:
+ 0 key (type: string)
+ 1 key (type: string)
+ outputColumnNames: _col0, _col1
+ input vertices:
+ 1 Map 1
+ Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: string)
+ outputColumnNames: _col2, _col3
+ 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
+ 1 {_col3}
+ keys:
+ 0 key (type: string)
+ 1 _col2 (type: string)
+ outputColumnNames: _col8
+ input vertices:
+ 0 Map 4
+ Statistics: Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col8 (type: string)
+ outputColumnNames: _col3
+ Statistics: Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: sum(hash(_col3))
+ mode: hash
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: bigint)
+ Local Work:
+ Map Reduce Local Work
Reducer 3
Reduce Operator Tree:
- Join Operator
- condition map:
- Inner Join 0 to 1
- condition expressions:
- 0
- 1 {VALUE._col2}
- outputColumnNames: _col8
- Statistics: Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col8 (type: string)
- outputColumnNames: _col3
- Statistics: Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE
- Group By Operator
- aggregations: sum(hash(_col3))
- mode: hash
- outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- sort order:
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col0 (type: bigint)
- Reducer 4
- Reduce Operator Tree:
Group By Operator
aggregations: sum(VALUE._col0)
mode: mergepartial
Modified: hive/branches/spark/ql/src/test/results/clientpositive/spark/auto_join23.q.out
URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/auto_join23.q.out?rev=1641614&r1=1641613&r2=1641614&view=diff
==============================================================================
--- hive/branches/spark/ql/src/test/results/clientpositive/spark/auto_join23.q.out (original)
+++ hive/branches/spark/ql/src/test/results/clientpositive/spark/auto_join23.q.out Tue Nov 25 13:03:18 2014
@@ -5,15 +5,13 @@ POSTHOOK: query: explain
SELECT * FROM src src1 JOIN src src2 WHERE src1.key < 10 and src2.key < 10 SORT BY src1.key, src1.value, src2.key, src2.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)
- Reducer 3 <- Reducer 2 (SORT, 1)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -24,11 +22,23 @@ STAGE PLANS:
Filter Operator
predicate: (key < 10) (type: boolean)
Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- sort order:
- Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
- value expressions: key (type: string), value (type: string)
- Map 4
+ Spark HashTable Sink Operator
+ condition expressions:
+ 0 {key} {value}
+ 1 {key} {value}
+ keys:
+ 0
+ 1
+ Local Work:
+ Map Reduce Local Work
+
+ Stage: Stage-1
+ Spark
+ Edges:
+ Reducer 3 <- Map 2 (SORT, 1)
+#### A masked pattern was here ####
+ Vertices:
+ Map 2
Map Operator Tree:
TableScan
alias: src1
@@ -36,28 +46,29 @@ STAGE PLANS:
Filter Operator
predicate: (key < 10) (type: boolean)
Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- sort order:
- Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
- value expressions: key (type: string), value (type: string)
- Reducer 2
- Reduce Operator Tree:
- Join Operator
- condition map:
- Inner Join 0 to 1
- condition expressions:
- 0 {VALUE._col0} {VALUE._col1}
- 1 {VALUE._col0} {VALUE._col1}
- outputColumnNames: _col0, _col1, _col5, _col6
- Statistics: Num rows: 182 Data size: 1939 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: 182 Data size: 1939 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: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0 {key} {value}
+ 1 {key} {value}
+ keys:
+ 0
+ 1
+ outputColumnNames: _col0, _col1, _col5, _col6
+ input vertices:
+ 1 Map 1
+ Statistics: Num rows: 182 Data size: 1939 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: 182 Data size: 1939 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: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE
+ Local Work:
+ Map Reduce Local Work
Reducer 3
Reduce Operator Tree:
Select Operator
Modified: hive/branches/spark/ql/src/test/results/clientpositive/spark/auto_join24.q.out
URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/auto_join24.q.out?rev=1641614&r1=1641613&r2=1641614&view=diff
==============================================================================
--- hive/branches/spark/ql/src/test/results/clientpositive/spark/auto_join24.q.out (original)
+++ hive/branches/spark/ql/src/test/results/clientpositive/spark/auto_join24.q.out Tue Nov 25 13:03:18 2014
@@ -25,15 +25,13 @@ POSTHOOK: query: explain
SELECT sum(a.cnt) FROM tst1 a JOIN tst1 b ON a.key = b.key
POSTHOOK: type: QUERY
STAGE DEPENDENCIES:
- Stage-1 is a root stage
+ Stage-3 is a root stage
+ Stage-1 depends on stages: Stage-3
Stage-0 depends on stages: Stage-1
STAGE PLANS:
- Stage: Stage-1
+ Stage: Stage-3
Spark
- Edges:
- Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 1), Map 4 (PARTITION-LEVEL SORT, 1)
- Reducer 3 <- Reducer 2 (GROUP, 1)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -44,12 +42,23 @@ STAGE PLANS:
Filter Operator
predicate: key is not null (type: boolean)
Statistics: Num rows: 155 Data size: 743 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: 155 Data size: 743 Basic stats: COMPLETE Column stats: NONE
- Map 4
+ Spark HashTable Sink Operator
+ condition expressions:
+ 0 {cnt}
+ 1
+ keys:
+ 0 key (type: string)
+ 1 key (type: string)
+ Local Work:
+ Map Reduce Local Work
+
+ Stage: Stage-1
+ Spark
+ Edges:
+ Reducer 3 <- Map 2 (GROUP, 1)
+#### A masked pattern was here ####
+ Vertices:
+ Map 2
Map Operator Tree:
TableScan
alias: a
@@ -57,35 +66,34 @@ STAGE PLANS:
Filter Operator
predicate: key is not null (type: boolean)
Statistics: Num rows: 155 Data size: 743 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: 155 Data size: 743 Basic stats: COMPLETE Column stats: NONE
- value expressions: cnt (type: int)
- Reducer 2
- Reduce Operator Tree:
- Join Operator
- condition map:
- Inner Join 0 to 1
- condition expressions:
- 0 {VALUE._col0}
- 1
- outputColumnNames: _col1
- Statistics: Num rows: 170 Data size: 817 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col1 (type: int)
- outputColumnNames: _col1
- Statistics: Num rows: 170 Data size: 817 Basic stats: COMPLETE Column stats: NONE
- Group By Operator
- aggregations: sum(_col1)
- mode: hash
- outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- sort order:
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col0 (type: bigint)
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0 {cnt}
+ 1
+ keys:
+ 0 key (type: string)
+ 1 key (type: string)
+ outputColumnNames: _col1
+ input vertices:
+ 1 Map 1
+ Statistics: Num rows: 170 Data size: 817 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col1 (type: int)
+ outputColumnNames: _col1
+ Statistics: Num rows: 170 Data size: 817 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: sum(_col1)
+ mode: hash
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: bigint)
+ Local Work:
+ Map Reduce Local Work
Reducer 3
Reduce Operator Tree:
Group By Operator
Modified: hive/branches/spark/ql/src/test/results/clientpositive/spark/auto_join26.q.out
URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/auto_join26.q.out?rev=1641614&r1=1641613&r2=1641614&view=diff
==============================================================================
--- hive/branches/spark/ql/src/test/results/clientpositive/spark/auto_join26.q.out (original)
+++ hive/branches/spark/ql/src/test/results/clientpositive/spark/auto_join26.q.out Tue Nov 25 13:03:18 2014
@@ -19,17 +19,39 @@ INSERT OVERWRITE TABLE dest_j1
SELECT x.key, count(1) FROM src1 x JOIN src y ON (x.key = y.key) group by x.key
POSTHOOK: type: QUERY
STAGE DEPENDENCIES:
- Stage-1 is a root stage
+ Stage-4 is a root stage
+ Stage-1 depends on stages: Stage-4
Stage-2 depends on stages: Stage-1
Stage-0 depends on stages: Stage-2
Stage-3 depends on stages: Stage-0
STAGE PLANS:
+ Stage: Stage-4
+ Spark
+#### A masked pattern was here ####
+ Vertices:
+ Map 3
+ Map Operator Tree:
+ TableScan
+ alias: x
+ Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: key is not null (type: boolean)
+ Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE
+ Spark HashTable Sink Operator
+ condition expressions:
+ 0
+ 1
+ keys:
+ 0 key (type: string)
+ 1 key (type: string)
+ Local Work:
+ Map Reduce Local Work
+
Stage: Stage-1
Spark
Edges:
- Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 1), Map 4 (PARTITION-LEVEL SORT, 1)
- Reducer 3 <- Reducer 2 (GROUP, 1)
+ Reducer 2 <- Map 1 (GROUP, 1)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -40,51 +62,38 @@ STAGE PLANS:
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 4
- Map Operator Tree:
- TableScan
- alias: x
- Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE
- 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
- 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
- Group By Operator
- aggregations: count(1)
- keys: _col0 (type: string)
- mode: hash
- outputColumnNames: _col0, _col1
- 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)
+ 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 3
Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col1 (type: bigint)
- Reducer 3
+ Select Operator
+ expressions: _col0 (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: count(1)
+ keys: _col0 (type: string)
+ mode: hash
+ outputColumnNames: _col0, _col1
+ 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
+ value expressions: _col1 (type: bigint)
+ Local Work:
+ Map Reduce Local Work
+ Reducer 2
Reduce Operator Tree:
Group By Operator
aggregations: count(VALUE._col0)