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 [2/43] - 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/annotate_stats_join.q.out
URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/annotate_stats_join.q.out?rev=1641614&r1=1641613&r2=1641614&view=diff
==============================================================================
--- hive/branches/spark/ql/src/test/results/clientpositive/spark/annotate_stats_join.q.out (original)
+++ hive/branches/spark/ql/src/test/results/clientpositive/spark/annotate_stats_join.q.out Tue Nov 25 13:03:18 2014
@@ -155,14 +155,13 @@ POSTHOOK: query: -- number of rows
explain select * from emp e join dept d on (e.deptid = d.deptid)
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
@@ -173,13 +172,21 @@ STAGE PLANS:
Filter Operator
predicate: deptid is not null (type: boolean)
Statistics: Num rows: 6 Data size: 570 Basic stats: COMPLETE Column stats: COMPLETE
- Reduce Output Operator
- key expressions: deptid (type: int)
- sort order: +
- Map-reduce partition columns: deptid (type: int)
- Statistics: Num rows: 6 Data size: 570 Basic stats: COMPLETE Column stats: COMPLETE
- value expressions: deptname (type: string)
- Map 3
+ Spark HashTable Sink Operator
+ condition expressions:
+ 0 {lastname} {deptid} {locid}
+ 1 {deptname}
+ keys:
+ 0 deptid (type: int)
+ 1 deptid (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: e
@@ -187,33 +194,32 @@ STAGE PLANS:
Filter Operator
predicate: deptid is not null (type: boolean)
Statistics: Num rows: 48 Data size: 4752 Basic stats: COMPLETE Column stats: COMPLETE
- Reduce Output Operator
- key expressions: deptid (type: int)
- sort order: +
- Map-reduce partition columns: deptid (type: int)
- Statistics: Num rows: 48 Data size: 4752 Basic stats: COMPLETE Column stats: COMPLETE
- value expressions: lastname (type: string), locid (type: int)
- Reducer 2
- Reduce Operator Tree:
- Join Operator
- condition map:
- Inner Join 0 to 1
- condition expressions:
- 0 {VALUE._col0} {KEY.reducesinkkey0} {VALUE._col1}
- 1 {KEY.reducesinkkey0} {VALUE._col0}
- outputColumnNames: _col0, _col1, _col2, _col6, _col7
- Statistics: Num rows: 41 Data size: 7954 Basic stats: COMPLETE Column stats: COMPLETE
- Select Operator
- expressions: _col0 (type: string), _col1 (type: int), _col2 (type: int), _col6 (type: int), _col7 (type: string)
- outputColumnNames: _col0, _col1, _col2, _col3, _col4
- Statistics: Num rows: 41 Data size: 7954 Basic stats: COMPLETE Column stats: COMPLETE
- File Output Operator
- compressed: false
- Statistics: Num rows: 41 Data size: 7954 Basic stats: COMPLETE Column stats: COMPLETE
- 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 {lastname} {deptid} {locid}
+ 1 {deptid} {deptname}
+ keys:
+ 0 deptid (type: int)
+ 1 deptid (type: int)
+ outputColumnNames: _col0, _col1, _col2, _col6, _col7
+ input vertices:
+ 1 Map 1
+ Statistics: Num rows: 41 Data size: 7954 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: int), _col2 (type: int), _col6 (type: int), _col7 (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4
+ Statistics: Num rows: 41 Data size: 7954 Basic stats: COMPLETE Column stats: COMPLETE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 41 Data size: 7954 Basic stats: COMPLETE Column stats: COMPLETE
+ 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
@@ -230,14 +236,13 @@ POSTHOOK: query: -- 2 relations, 2 attri
explain select * from emp,dept where emp.deptid = dept.deptid and emp.lastname = dept.deptname
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
@@ -248,12 +253,21 @@ STAGE PLANS:
Filter Operator
predicate: (deptid is not null and deptname is not null) (type: boolean)
Statistics: Num rows: 6 Data size: 570 Basic stats: COMPLETE Column stats: COMPLETE
- Reduce Output Operator
- key expressions: deptid (type: int), deptname (type: string)
- sort order: ++
- Map-reduce partition columns: deptid (type: int), deptname (type: string)
- Statistics: Num rows: 6 Data size: 570 Basic stats: COMPLETE Column stats: COMPLETE
- Map 3
+ Spark HashTable Sink Operator
+ condition expressions:
+ 0 {lastname} {deptid} {locid}
+ 1
+ keys:
+ 0 deptid (type: int), lastname (type: string)
+ 1 deptid (type: int), deptname (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: emp
@@ -261,36 +275,35 @@ STAGE PLANS:
Filter Operator
predicate: (deptid is not null and lastname is not null) (type: boolean)
Statistics: Num rows: 48 Data size: 4752 Basic stats: COMPLETE Column stats: COMPLETE
- Reduce Output Operator
- key expressions: deptid (type: int), lastname (type: string)
- sort order: ++
- Map-reduce partition columns: deptid (type: int), lastname (type: string)
- Statistics: Num rows: 48 Data size: 4752 Basic stats: COMPLETE Column stats: COMPLETE
- value expressions: locid (type: int)
- Reducer 2
- Reduce Operator Tree:
- Join Operator
- condition map:
- Inner Join 0 to 1
- condition expressions:
- 0 {KEY.reducesinkkey1} {KEY.reducesinkkey0} {VALUE._col0}
- 1 {KEY.reducesinkkey0} {KEY.reducesinkkey1}
- outputColumnNames: _col0, _col1, _col2, _col6, _col7
- Statistics: Num rows: 6 Data size: 1164 Basic stats: COMPLETE Column stats: COMPLETE
- Filter Operator
- predicate: ((_col1 = _col6) and (_col0 = _col7)) (type: boolean)
- Statistics: Num rows: 1 Data size: 194 Basic stats: COMPLETE Column stats: COMPLETE
- Select Operator
- expressions: _col0 (type: string), _col1 (type: int), _col2 (type: int), _col6 (type: int), _col7 (type: string)
- outputColumnNames: _col0, _col1, _col2, _col3, _col4
- Statistics: Num rows: 1 Data size: 194 Basic stats: COMPLETE Column stats: COMPLETE
- File Output Operator
- compressed: false
- Statistics: Num rows: 1 Data size: 194 Basic stats: COMPLETE Column stats: COMPLETE
- 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 {lastname} {deptid} {locid}
+ 1 {deptid} {deptname}
+ keys:
+ 0 deptid (type: int), lastname (type: string)
+ 1 deptid (type: int), deptname (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col6, _col7
+ input vertices:
+ 1 Map 1
+ Statistics: Num rows: 6 Data size: 1164 Basic stats: COMPLETE Column stats: COMPLETE
+ Filter Operator
+ predicate: ((_col1 = _col6) and (_col0 = _col7)) (type: boolean)
+ Statistics: Num rows: 1 Data size: 194 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: int), _col2 (type: int), _col6 (type: int), _col7 (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4
+ Statistics: Num rows: 1 Data size: 194 Basic stats: COMPLETE Column stats: COMPLETE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 194 Basic stats: COMPLETE Column stats: COMPLETE
+ 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
@@ -303,14 +316,13 @@ PREHOOK: type: QUERY
POSTHOOK: query: explain select * from emp e join dept d on (e.deptid = d.deptid and e.lastname = d.deptname)
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
@@ -321,12 +333,21 @@ STAGE PLANS:
Filter Operator
predicate: (deptid is not null and deptname is not null) (type: boolean)
Statistics: Num rows: 6 Data size: 570 Basic stats: COMPLETE Column stats: COMPLETE
- Reduce Output Operator
- key expressions: deptid (type: int), deptname (type: string)
- sort order: ++
- Map-reduce partition columns: deptid (type: int), deptname (type: string)
- Statistics: Num rows: 6 Data size: 570 Basic stats: COMPLETE Column stats: COMPLETE
- Map 3
+ Spark HashTable Sink Operator
+ condition expressions:
+ 0 {lastname} {deptid} {locid}
+ 1
+ keys:
+ 0 deptid (type: int), lastname (type: string)
+ 1 deptid (type: int), deptname (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: e
@@ -334,33 +355,32 @@ STAGE PLANS:
Filter Operator
predicate: (deptid is not null and lastname is not null) (type: boolean)
Statistics: Num rows: 48 Data size: 4752 Basic stats: COMPLETE Column stats: COMPLETE
- Reduce Output Operator
- key expressions: deptid (type: int), lastname (type: string)
- sort order: ++
- Map-reduce partition columns: deptid (type: int), lastname (type: string)
- Statistics: Num rows: 48 Data size: 4752 Basic stats: COMPLETE Column stats: COMPLETE
- value expressions: locid (type: int)
- Reducer 2
- Reduce Operator Tree:
- Join Operator
- condition map:
- Inner Join 0 to 1
- condition expressions:
- 0 {KEY.reducesinkkey1} {KEY.reducesinkkey0} {VALUE._col0}
- 1 {KEY.reducesinkkey0} {KEY.reducesinkkey1}
- outputColumnNames: _col0, _col1, _col2, _col6, _col7
- Statistics: Num rows: 6 Data size: 1164 Basic stats: COMPLETE Column stats: COMPLETE
- Select Operator
- expressions: _col0 (type: string), _col1 (type: int), _col2 (type: int), _col6 (type: int), _col7 (type: string)
- outputColumnNames: _col0, _col1, _col2, _col3, _col4
- Statistics: Num rows: 6 Data size: 1164 Basic stats: COMPLETE Column stats: COMPLETE
- File Output Operator
- compressed: false
- Statistics: Num rows: 6 Data size: 1164 Basic stats: COMPLETE Column stats: COMPLETE
- 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 {lastname} {deptid} {locid}
+ 1 {deptid} {deptname}
+ keys:
+ 0 deptid (type: int), lastname (type: string)
+ 1 deptid (type: int), deptname (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col6, _col7
+ input vertices:
+ 1 Map 1
+ Statistics: Num rows: 6 Data size: 1164 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: int), _col2 (type: int), _col6 (type: int), _col7 (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4
+ Statistics: Num rows: 6 Data size: 1164 Basic stats: COMPLETE Column stats: COMPLETE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 6 Data size: 1164 Basic stats: COMPLETE Column stats: COMPLETE
+ 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
@@ -377,14 +397,13 @@ POSTHOOK: query: -- 2 relations, 3 attri
explain select * from emp,dept where emp.deptid = dept.deptid and emp.lastname = dept.deptname and dept.deptname = emp.lastname
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
@@ -395,12 +414,21 @@ STAGE PLANS:
Filter Operator
predicate: (deptid is not null and deptname is not null) (type: boolean)
Statistics: Num rows: 6 Data size: 570 Basic stats: COMPLETE Column stats: COMPLETE
- Reduce Output Operator
- key expressions: deptid (type: int), deptname (type: string), deptname (type: string)
- sort order: +++
- Map-reduce partition columns: deptid (type: int), deptname (type: string), deptname (type: string)
- Statistics: Num rows: 6 Data size: 570 Basic stats: COMPLETE Column stats: COMPLETE
- Map 3
+ Spark HashTable Sink Operator
+ condition expressions:
+ 0 {lastname} {deptid} {locid}
+ 1
+ keys:
+ 0 deptid (type: int), lastname (type: string), lastname (type: string)
+ 1 deptid (type: int), deptname (type: string), deptname (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: emp
@@ -408,36 +436,35 @@ STAGE PLANS:
Filter Operator
predicate: (deptid is not null and lastname is not null) (type: boolean)
Statistics: Num rows: 48 Data size: 4752 Basic stats: COMPLETE Column stats: COMPLETE
- Reduce Output Operator
- key expressions: deptid (type: int), lastname (type: string), lastname (type: string)
- sort order: +++
- Map-reduce partition columns: deptid (type: int), lastname (type: string), lastname (type: string)
- Statistics: Num rows: 48 Data size: 4752 Basic stats: COMPLETE Column stats: COMPLETE
- value expressions: locid (type: int)
- Reducer 2
- Reduce Operator Tree:
- Join Operator
- condition map:
- Inner Join 0 to 1
- condition expressions:
- 0 {KEY.reducesinkkey1} {KEY.reducesinkkey0} {VALUE._col0}
- 1 {KEY.reducesinkkey0} {KEY.reducesinkkey1}
- outputColumnNames: _col0, _col1, _col2, _col6, _col7
- Statistics: Num rows: 11 Data size: 2134 Basic stats: COMPLETE Column stats: COMPLETE
- Filter Operator
- predicate: (((_col1 = _col6) and (_col0 = _col7)) and (_col7 = _col0)) (type: boolean)
- Statistics: Num rows: 1 Data size: 194 Basic stats: COMPLETE Column stats: COMPLETE
- Select Operator
- expressions: _col0 (type: string), _col1 (type: int), _col2 (type: int), _col6 (type: int), _col7 (type: string)
- outputColumnNames: _col0, _col1, _col2, _col3, _col4
- Statistics: Num rows: 1 Data size: 194 Basic stats: COMPLETE Column stats: COMPLETE
- File Output Operator
- compressed: false
- Statistics: Num rows: 1 Data size: 194 Basic stats: COMPLETE Column stats: COMPLETE
- 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 {lastname} {deptid} {locid}
+ 1 {deptid} {deptname}
+ keys:
+ 0 deptid (type: int), lastname (type: string), lastname (type: string)
+ 1 deptid (type: int), deptname (type: string), deptname (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col6, _col7
+ input vertices:
+ 1 Map 1
+ Statistics: Num rows: 11 Data size: 2134 Basic stats: COMPLETE Column stats: COMPLETE
+ Filter Operator
+ predicate: (((_col1 = _col6) and (_col0 = _col7)) and (_col7 = _col0)) (type: boolean)
+ Statistics: Num rows: 1 Data size: 194 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: int), _col2 (type: int), _col6 (type: int), _col7 (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4
+ Statistics: Num rows: 1 Data size: 194 Basic stats: COMPLETE Column stats: COMPLETE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 194 Basic stats: COMPLETE Column stats: COMPLETE
+ 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
@@ -454,14 +481,13 @@ POSTHOOK: query: -- 3 relations, 1 attri
explain select * from emp e join dept d on (e.deptid = d.deptid) join emp e1 on (e.deptid = e1.deptid)
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
@@ -472,13 +498,18 @@ STAGE PLANS:
Filter Operator
predicate: deptid is not null (type: boolean)
Statistics: Num rows: 6 Data size: 570 Basic stats: COMPLETE Column stats: COMPLETE
- Reduce Output Operator
- key expressions: deptid (type: int)
- sort order: +
- Map-reduce partition columns: deptid (type: int)
- Statistics: Num rows: 6 Data size: 570 Basic stats: COMPLETE Column stats: COMPLETE
- value expressions: deptname (type: string)
- Map 3
+ Spark HashTable Sink Operator
+ condition expressions:
+ 0 {lastname} {deptid} {locid}
+ 1 {deptname}
+ 2 {lastname} {deptid} {locid}
+ keys:
+ 0 deptid (type: int)
+ 1 deptid (type: int)
+ 2 deptid (type: int)
+ Local Work:
+ Map Reduce Local Work
+ Map 2
Map Operator Tree:
TableScan
alias: e1
@@ -486,13 +517,23 @@ STAGE PLANS:
Filter Operator
predicate: deptid is not null (type: boolean)
Statistics: Num rows: 48 Data size: 4752 Basic stats: COMPLETE Column stats: COMPLETE
- Reduce Output Operator
- key expressions: deptid (type: int)
- sort order: +
- Map-reduce partition columns: deptid (type: int)
- Statistics: Num rows: 48 Data size: 4752 Basic stats: COMPLETE Column stats: COMPLETE
- value expressions: lastname (type: string), locid (type: int)
- Map 4
+ Spark HashTable Sink Operator
+ condition expressions:
+ 0 {lastname} {deptid} {locid}
+ 1 {deptid} {deptname}
+ 2 {lastname} {locid}
+ keys:
+ 0 deptid (type: int)
+ 1 deptid (type: int)
+ 2 deptid (type: int)
+ Local Work:
+ Map Reduce Local Work
+
+ Stage: Stage-1
+ Spark
+#### A masked pattern was here ####
+ Vertices:
+ Map 3
Map Operator Tree:
TableScan
alias: e
@@ -500,35 +541,36 @@ STAGE PLANS:
Filter Operator
predicate: deptid is not null (type: boolean)
Statistics: Num rows: 48 Data size: 4752 Basic stats: COMPLETE Column stats: COMPLETE
- Reduce Output Operator
- key expressions: deptid (type: int)
- sort order: +
- Map-reduce partition columns: deptid (type: int)
- Statistics: Num rows: 48 Data size: 4752 Basic stats: COMPLETE Column stats: COMPLETE
- value expressions: lastname (type: string), locid (type: int)
- Reducer 2
- Reduce Operator Tree:
- Join Operator
- condition map:
- Inner Join 0 to 1
- Inner Join 0 to 2
- condition expressions:
- 0 {VALUE._col0} {KEY.reducesinkkey0} {VALUE._col1}
- 1 {KEY.reducesinkkey0} {VALUE._col0}
- 2 {VALUE._col0} {KEY.reducesinkkey0} {VALUE._col1}
- outputColumnNames: _col0, _col1, _col2, _col6, _col7, _col11, _col12, _col13
- Statistics: Num rows: 658 Data size: 192794 Basic stats: COMPLETE Column stats: COMPLETE
- Select Operator
- expressions: _col0 (type: string), _col1 (type: int), _col2 (type: int), _col6 (type: int), _col7 (type: string), _col11 (type: string), _col12 (type: int), _col13 (type: int)
- outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7
- Statistics: Num rows: 658 Data size: 192794 Basic stats: COMPLETE Column stats: COMPLETE
- File Output Operator
- compressed: false
- Statistics: Num rows: 658 Data size: 192794 Basic stats: COMPLETE Column stats: COMPLETE
- 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
+ Inner Join 0 to 2
+ condition expressions:
+ 0 {lastname} {deptid} {locid}
+ 1 {deptid} {deptname}
+ 2 {lastname} {deptid} {locid}
+ keys:
+ 0 deptid (type: int)
+ 1 deptid (type: int)
+ 2 deptid (type: int)
+ outputColumnNames: _col0, _col1, _col2, _col6, _col7, _col11, _col12, _col13
+ input vertices:
+ 1 Map 1
+ 2 Map 2
+ Statistics: Num rows: 658 Data size: 192794 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: int), _col2 (type: int), _col6 (type: int), _col7 (type: string), _col11 (type: string), _col12 (type: int), _col13 (type: int)
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7
+ Statistics: Num rows: 658 Data size: 192794 Basic stats: COMPLETE Column stats: COMPLETE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 658 Data size: 192794 Basic stats: COMPLETE Column stats: COMPLETE
+ 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
@@ -543,14 +585,13 @@ POSTHOOK: query: -- Expected output rows
explain select * from emp e join dept d on (e.deptid = d.deptid) join loc l on (e.deptid = l.locid)
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
@@ -561,63 +602,79 @@ STAGE PLANS:
Filter Operator
predicate: deptid is not null (type: boolean)
Statistics: Num rows: 6 Data size: 570 Basic stats: COMPLETE Column stats: COMPLETE
- Reduce Output Operator
- key expressions: deptid (type: int)
- sort order: +
- Map-reduce partition columns: deptid (type: int)
- Statistics: Num rows: 6 Data size: 570 Basic stats: COMPLETE Column stats: COMPLETE
- value expressions: deptname (type: string)
+ Spark HashTable Sink Operator
+ condition expressions:
+ 0 {lastname} {deptid} {locid}
+ 1 {deptname}
+ 2 {state} {locid} {zip} {year}
+ keys:
+ 0 deptid (type: int)
+ 1 deptid (type: int)
+ 2 locid (type: int)
+ Local Work:
+ Map Reduce Local Work
Map 3
Map Operator Tree:
TableScan
- alias: e
- Statistics: Num rows: 48 Data size: 552 Basic stats: COMPLETE Column stats: COMPLETE
- Filter Operator
- predicate: deptid is not null (type: boolean)
- Statistics: Num rows: 48 Data size: 4752 Basic stats: COMPLETE Column stats: COMPLETE
- Reduce Output Operator
- key expressions: deptid (type: int)
- sort order: +
- Map-reduce partition columns: deptid (type: int)
- Statistics: Num rows: 48 Data size: 4752 Basic stats: COMPLETE Column stats: COMPLETE
- value expressions: lastname (type: string), locid (type: int)
- Map 4
- Map Operator Tree:
- TableScan
alias: l
Statistics: Num rows: 8 Data size: 109 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: locid is not null (type: boolean)
Statistics: Num rows: 8 Data size: 804 Basic stats: COMPLETE Column stats: COMPLETE
- Reduce Output Operator
- key expressions: locid (type: int)
- sort order: +
- Map-reduce partition columns: locid (type: int)
- Statistics: Num rows: 8 Data size: 804 Basic stats: COMPLETE Column stats: COMPLETE
- value expressions: state (type: string), zip (type: bigint), year (type: int)
- Reducer 2
- Reduce Operator Tree:
- Join Operator
- condition map:
- Inner Join 0 to 1
- Inner Join 0 to 2
- condition expressions:
- 0 {VALUE._col0} {KEY.reducesinkkey0} {VALUE._col1}
- 1 {KEY.reducesinkkey0} {VALUE._col0}
- 2 {VALUE._col0} {KEY.reducesinkkey0} {VALUE._col1} {VALUE._col2}
- outputColumnNames: _col0, _col1, _col2, _col6, _col7, _col11, _col12, _col13, _col14
- Statistics: Num rows: 47 Data size: 13912 Basic stats: COMPLETE Column stats: COMPLETE
- Select Operator
- expressions: _col0 (type: string), _col1 (type: int), _col2 (type: int), _col6 (type: int), _col7 (type: string), _col11 (type: string), _col12 (type: int), _col13 (type: bigint), _col14 (type: int)
- outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8
- Statistics: Num rows: 47 Data size: 13912 Basic stats: COMPLETE Column stats: COMPLETE
- File Output Operator
- compressed: false
- Statistics: Num rows: 47 Data size: 13912 Basic stats: COMPLETE Column stats: COMPLETE
- 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
+ Spark HashTable Sink Operator
+ condition expressions:
+ 0 {lastname} {deptid} {locid}
+ 1 {deptid} {deptname}
+ 2 {state} {zip} {year}
+ keys:
+ 0 deptid (type: int)
+ 1 deptid (type: int)
+ 2 locid (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: e
+ Statistics: Num rows: 48 Data size: 552 Basic stats: COMPLETE Column stats: COMPLETE
+ Filter Operator
+ predicate: deptid is not null (type: boolean)
+ Statistics: Num rows: 48 Data size: 4752 Basic stats: COMPLETE Column stats: COMPLETE
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ Inner Join 0 to 2
+ condition expressions:
+ 0 {lastname} {deptid} {locid}
+ 1 {deptid} {deptname}
+ 2 {state} {locid} {zip} {year}
+ keys:
+ 0 deptid (type: int)
+ 1 deptid (type: int)
+ 2 locid (type: int)
+ outputColumnNames: _col0, _col1, _col2, _col6, _col7, _col11, _col12, _col13, _col14
+ input vertices:
+ 1 Map 1
+ 2 Map 3
+ Statistics: Num rows: 47 Data size: 13912 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: int), _col2 (type: int), _col6 (type: int), _col7 (type: string), _col11 (type: string), _col12 (type: int), _col13 (type: bigint), _col14 (type: int)
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8
+ Statistics: Num rows: 47 Data size: 13912 Basic stats: COMPLETE Column stats: COMPLETE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 47 Data size: 13912 Basic stats: COMPLETE Column stats: COMPLETE
+ 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
@@ -634,14 +691,13 @@ POSTHOOK: query: -- 3 relations and 2 at
explain select * from emp e join dept d on (e.deptid = d.deptid and e.lastname = d.deptname) join loc l on (e.deptid = l.locid and e.lastname = l.state)
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
@@ -652,62 +708,79 @@ STAGE PLANS:
Filter Operator
predicate: (deptid is not null and deptname is not null) (type: boolean)
Statistics: Num rows: 6 Data size: 570 Basic stats: COMPLETE Column stats: COMPLETE
- Reduce Output Operator
- key expressions: deptid (type: int), deptname (type: string)
- sort order: ++
- Map-reduce partition columns: deptid (type: int), deptname (type: string)
- Statistics: Num rows: 6 Data size: 570 Basic stats: COMPLETE Column stats: COMPLETE
+ Spark HashTable Sink Operator
+ condition expressions:
+ 0 {lastname} {deptid} {locid}
+ 1
+ 2 {state} {locid} {zip} {year}
+ keys:
+ 0 deptid (type: int), lastname (type: string)
+ 1 deptid (type: int), deptname (type: string)
+ 2 locid (type: int), state (type: string)
+ Local Work:
+ Map Reduce Local Work
Map 3
Map Operator Tree:
TableScan
- alias: e
- Statistics: Num rows: 48 Data size: 552 Basic stats: COMPLETE Column stats: COMPLETE
- Filter Operator
- predicate: (deptid is not null and lastname is not null) (type: boolean)
- Statistics: Num rows: 48 Data size: 4752 Basic stats: COMPLETE Column stats: COMPLETE
- Reduce Output Operator
- key expressions: deptid (type: int), lastname (type: string)
- sort order: ++
- Map-reduce partition columns: deptid (type: int), lastname (type: string)
- Statistics: Num rows: 48 Data size: 4752 Basic stats: COMPLETE Column stats: COMPLETE
- value expressions: locid (type: int)
- Map 4
- Map Operator Tree:
- TableScan
alias: l
Statistics: Num rows: 8 Data size: 109 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: (locid is not null and state is not null) (type: boolean)
Statistics: Num rows: 8 Data size: 804 Basic stats: COMPLETE Column stats: COMPLETE
- Reduce Output Operator
- key expressions: locid (type: int), state (type: string)
- sort order: ++
- Map-reduce partition columns: locid (type: int), state (type: string)
- Statistics: Num rows: 8 Data size: 804 Basic stats: COMPLETE Column stats: COMPLETE
- value expressions: zip (type: bigint), year (type: int)
- Reducer 2
- Reduce Operator Tree:
- Join Operator
- condition map:
- Inner Join 0 to 1
- Inner Join 0 to 2
- condition expressions:
- 0 {KEY.reducesinkkey1} {KEY.reducesinkkey0} {VALUE._col0}
- 1 {KEY.reducesinkkey0} {KEY.reducesinkkey1}
- 2 {KEY.reducesinkkey1} {KEY.reducesinkkey0} {VALUE._col0} {VALUE._col1}
- outputColumnNames: _col0, _col1, _col2, _col6, _col7, _col11, _col12, _col13, _col14
- Statistics: Num rows: 1 Data size: 296 Basic stats: COMPLETE Column stats: COMPLETE
- Select Operator
- expressions: _col0 (type: string), _col1 (type: int), _col2 (type: int), _col6 (type: int), _col7 (type: string), _col11 (type: string), _col12 (type: int), _col13 (type: bigint), _col14 (type: int)
- outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8
- Statistics: Num rows: 1 Data size: 296 Basic stats: COMPLETE Column stats: COMPLETE
- File Output Operator
- compressed: false
- Statistics: Num rows: 1 Data size: 296 Basic stats: COMPLETE Column stats: COMPLETE
- 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
+ Spark HashTable Sink Operator
+ condition expressions:
+ 0 {lastname} {deptid} {locid}
+ 1 {deptid} {deptname}
+ 2 {zip} {year}
+ keys:
+ 0 deptid (type: int), lastname (type: string)
+ 1 deptid (type: int), deptname (type: string)
+ 2 locid (type: int), state (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: e
+ Statistics: Num rows: 48 Data size: 552 Basic stats: COMPLETE Column stats: COMPLETE
+ Filter Operator
+ predicate: (deptid is not null and lastname is not null) (type: boolean)
+ Statistics: Num rows: 48 Data size: 4752 Basic stats: COMPLETE Column stats: COMPLETE
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ Inner Join 0 to 2
+ condition expressions:
+ 0 {lastname} {deptid} {locid}
+ 1 {deptid} {deptname}
+ 2 {state} {locid} {zip} {year}
+ keys:
+ 0 deptid (type: int), lastname (type: string)
+ 1 deptid (type: int), deptname (type: string)
+ 2 locid (type: int), state (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col6, _col7, _col11, _col12, _col13, _col14
+ input vertices:
+ 1 Map 1
+ 2 Map 3
+ Statistics: Num rows: 1 Data size: 296 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: int), _col2 (type: int), _col6 (type: int), _col7 (type: string), _col11 (type: string), _col12 (type: int), _col13 (type: bigint), _col14 (type: int)
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8
+ Statistics: Num rows: 1 Data size: 296 Basic stats: COMPLETE Column stats: COMPLETE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 296 Basic stats: COMPLETE Column stats: COMPLETE
+ 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/auto_join0.q.out
URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/auto_join0.q.out?rev=1641614&r1=1641613&r2=1641614&view=diff
==============================================================================
--- hive/branches/spark/ql/src/test/results/clientpositive/spark/auto_join0.q.out (original)
+++ hive/branches/spark/ql/src/test/results/clientpositive/spark/auto_join0.q.out Tue Nov 25 13:03:18 2014
@@ -21,19 +21,16 @@ SELECT src1.key as k1, src1.value as v1,
) 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
+ Map 4
Map Operator Tree:
TableScan
alias: src
@@ -45,11 +42,24 @@ STAGE PLANS:
expressions: key (type: string), value (type: string)
outputColumnNames: _col0, _col1
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: _col0 (type: string), _col1 (type: string)
- Map 5
+ Spark HashTable Sink Operator
+ condition expressions:
+ 0 {_col0} {_col1}
+ 1 {_col0} {_col1}
+ keys:
+ 0
+ 1
+ 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: src
@@ -61,30 +71,31 @@ STAGE PLANS:
expressions: key (type: string), value (type: string)
outputColumnNames: _col0, _col1
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: _col0 (type: string), _col1 (type: string)
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0 {_col0} {_col1}
+ 1 {_col0} {_col1}
+ keys:
+ 0
+ 1
+ outputColumnNames: _col0, _col1, _col2, _col3
+ input vertices:
+ 1 Map 4
+ Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (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 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, _col2, _col3
- Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (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
- Reducer 3
- Reduce Operator Tree:
Select Operator
expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey3 (type: string)
outputColumnNames: _col0, _col1, _col2, _col3
@@ -98,7 +109,7 @@ 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_join1.q.out
URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/auto_join1.q.out?rev=1641614&r1=1641613&r2=1641614&view=diff
==============================================================================
--- hive/branches/spark/ql/src/test/results/clientpositive/spark/auto_join1.q.out (original)
+++ hive/branches/spark/ql/src/test/results/clientpositive/spark/auto_join1.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 dest_j1 SELECT src1.key, src2.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-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}
+ 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
@@ -49,33 +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
- 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: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: UDFToInteger(_col0) (type: int), _col6 (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_j1
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0 {key}
+ 1 {value}
+ keys:
+ 0 key (type: string)
+ 1 key (type: string)
+ outputColumnNames: _col0, _col6
+ input vertices:
+ 1 Map 1
+ Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: UDFToInteger(_col0) (type: int), _col6 (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_j1
+ Local Work:
+ Map Reduce Local Work
Stage: Stage-2
Dependency Collection
Modified: hive/branches/spark/ql/src/test/results/clientpositive/spark/auto_join10.q.out
URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/auto_join10.q.out?rev=1641614&r1=1641613&r2=1641614&view=diff
==============================================================================
--- hive/branches/spark/ql/src/test/results/clientpositive/spark/auto_join10.q.out (original)
+++ hive/branches/spark/ql/src/test/results/clientpositive/spark/auto_join10.q.out Tue Nov 25 13:03:18 2014
@@ -15,18 +15,16 @@ ON (x.key = Y.key)
select sum(hash(Y.key,Y.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 (GROUP, 1)
#### A masked pattern was here ####
Vertices:
- Map 1
+ Map 3
Map Operator Tree:
TableScan
alias: src
@@ -35,15 +33,26 @@ STAGE PLANS:
predicate: key is not null (type: boolean)
Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
Select Operator
- expressions: key (type: string)
- outputColumnNames: _col0
+ expressions: key (type: string), value (type: string)
+ outputColumnNames: _col0, _col1
Statistics: Num rows: 250 Data size: 2656 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: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
- Map 4
+ Spark HashTable Sink Operator
+ condition expressions:
+ 0
+ 1 {_col1}
+ keys:
+ 0 _col0 (type: string)
+ 1 _col0 (type: string)
+ Local Work:
+ Map Reduce Local Work
+
+ Stage: Stage-1
+ Spark
+ Edges:
+ Reducer 2 <- Map 1 (GROUP, 1)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
Map Operator Tree:
TableScan
alias: src
@@ -52,40 +61,39 @@ STAGE PLANS:
predicate: key is not null (type: boolean)
Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
Select Operator
- expressions: key (type: string), value (type: string)
- outputColumnNames: _col0, _col1
+ expressions: key (type: string)
+ outputColumnNames: _col0
Statistics: Num rows: 250 Data size: 2656 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: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col1 (type: string)
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0
+ 1 {_col0} {_col1}
+ keys:
+ 0 _col0 (type: string)
+ 1 _col0 (type: string)
+ outputColumnNames: _col2, _col3
+ input vertices:
+ 1 Map 3
+ Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col2 (type: string), _col3 (type: string)
+ outputColumnNames: _col2, _col3
+ Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: sum(hash(_col2,_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 2
Reduce Operator Tree:
- Join Operator
- condition map:
- Inner Join 0 to 1
- condition expressions:
- 0
- 1 {KEY.reducesinkkey0} {VALUE._col0}
- outputColumnNames: _col2, _col3
- Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col2 (type: string), _col3 (type: string)
- outputColumnNames: _col2, _col3
- Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
- Group By Operator
- aggregations: sum(hash(_col2,_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 3
- Reduce Operator Tree:
Group By Operator
aggregations: sum(VALUE._col0)
mode: mergepartial
Modified: hive/branches/spark/ql/src/test/results/clientpositive/spark/auto_join11.q.out
URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/auto_join11.q.out?rev=1641614&r1=1641613&r2=1641614&view=diff
==============================================================================
--- hive/branches/spark/ql/src/test/results/clientpositive/spark/auto_join11.q.out (original)
+++ hive/branches/spark/ql/src/test/results/clientpositive/spark/auto_join11.q.out Tue Nov 25 13:03:18 2014
@@ -15,15 +15,13 @@ JOIN
ON src1.c1 = src2.c3 AND src1.c1 < 100
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
@@ -38,13 +36,23 @@ STAGE PLANS:
expressions: key (type: string), value (type: string)
outputColumnNames: _col0, _col1
Statistics: Num rows: 166 Data size: 1763 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: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col1 (type: string)
- Map 4
+ Spark HashTable Sink Operator
+ condition expressions:
+ 0 {_col0}
+ 1 {_col1}
+ keys:
+ 0 _col0 (type: string)
+ 1 _col0 (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: src
@@ -56,34 +64,34 @@ STAGE PLANS:
expressions: key (type: string)
outputColumnNames: _col0
Statistics: Num rows: 166 Data size: 1763 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: 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, _col3
- Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col0 (type: string), _col3 (type: string)
- outputColumnNames: _col0, _col3
- Statistics: Num rows: 182 Data size: 1939 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 {_col1}
+ keys:
+ 0 _col0 (type: string)
+ 1 _col0 (type: string)
+ outputColumnNames: _col0, _col3
+ input vertices:
+ 1 Map 1
+ Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: string), _col3 (type: string)
+ outputColumnNames: _col0, _col3
+ Statistics: Num rows: 182 Data size: 1939 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_join12.q.out
URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/auto_join12.q.out?rev=1641614&r1=1641613&r2=1641614&view=diff
==============================================================================
--- hive/branches/spark/ql/src/test/results/clientpositive/spark/auto_join12.q.out (original)
+++ hive/branches/spark/ql/src/test/results/clientpositive/spark/auto_join12.q.out Tue Nov 25 13:03:18 2014
@@ -21,15 +21,13 @@ JOIN
ON src1.c1 = src3.c5 AND src3.c5 < 80
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 (GROUP, 1)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -44,71 +42,91 @@ STAGE PLANS:
expressions: key (type: string), value (type: string)
outputColumnNames: _col0, _col1
Statistics: Num rows: 28 Data size: 297 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: string)
- sort order: +
- Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 28 Data size: 297 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col1 (type: string)
+ Spark HashTable Sink Operator
+ condition expressions:
+ 0 {_col0}
+ 1 {_col1}
+ 2
+ keys:
+ 0 _col0 (type: string)
+ 1 _col0 (type: string)
+ 2 _col0 (type: string)
+ Local Work:
+ Map Reduce Local Work
Map 4
Map Operator Tree:
TableScan
alias: src
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: ((key < 80) and (key < 100)) (type: boolean)
+ predicate: ((key < 100) and (key < 80)) (type: boolean)
Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: key (type: string)
outputColumnNames: _col0
Statistics: Num rows: 55 Data size: 584 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: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
- Map 5
+ Spark HashTable Sink Operator
+ condition expressions:
+ 0 {_col0}
+ 1 {_col1}
+ 2
+ keys:
+ 0 _col0 (type: string)
+ 1 _col0 (type: string)
+ 2 _col0 (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: src
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: ((key < 100) and (key < 80)) (type: boolean)
+ predicate: ((key < 80) and (key < 100)) (type: boolean)
Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: key (type: string)
outputColumnNames: _col0
Statistics: Num rows: 55 Data size: 584 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: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
- Reducer 2
- Reduce Operator Tree:
- Join Operator
- condition map:
- Inner Join 0 to 1
- Inner Join 0 to 2
- condition expressions:
- 0 {KEY.reducesinkkey0}
- 1 {VALUE._col0}
- 2
- outputColumnNames: _col0, _col3
- Statistics: Num rows: 121 Data size: 1284 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col0 (type: string), _col3 (type: string)
- outputColumnNames: _col0, _col3
- Statistics: Num rows: 121 Data size: 1284 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
+ Inner Join 0 to 2
+ condition expressions:
+ 0 {_col0}
+ 1 {_col1}
+ 2
+ keys:
+ 0 _col0 (type: string)
+ 1 _col0 (type: string)
+ 2 _col0 (type: string)
+ outputColumnNames: _col0, _col3
+ input vertices:
+ 1 Map 1
+ 2 Map 4
+ Statistics: Num rows: 121 Data size: 1284 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: string), _col3 (type: string)
+ outputColumnNames: _col0, _col3
+ Statistics: Num rows: 121 Data size: 1284 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_join13.q.out
URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/auto_join13.q.out?rev=1641614&r1=1641613&r2=1641614&view=diff
==============================================================================
--- hive/branches/spark/ql/src/test/results/clientpositive/spark/auto_join13.q.out (original)
+++ hive/branches/spark/ql/src/test/results/clientpositive/spark/auto_join13.q.out Tue Nov 25 13:03:18 2014
@@ -21,16 +21,13 @@ JOIN
ON src1.c1 + src2.c3 = src3.c5 AND src3.c5 < 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 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
@@ -45,90 +42,101 @@ STAGE PLANS:
expressions: key (type: string), value (type: string)
outputColumnNames: _col0, _col1
Statistics: Num rows: 166 Data size: 1763 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: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col1 (type: string)
- Map 5
+ Spark HashTable Sink Operator
+ condition expressions:
+ 0 {_col0}
+ 1 {_col1}
+ keys:
+ 0 _col0 (type: string)
+ 1 _col0 (type: string)
+ Local Work:
+ Map Reduce Local Work
+ Map 4
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
+ predicate: ((key < 200) and UDFToDouble(key) is not null) (type: boolean)
+ Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: key (type: string)
outputColumnNames: _col0
- Statistics: Num rows: 166 Data size: 1763 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: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
- Map 6
+ Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE
+ Spark HashTable Sink Operator
+ condition expressions:
+ 0 {_col0} {_col3}
+ 1
+ keys:
+ 0 (_col0 + _col2) (type: double)
+ 1 UDFToDouble(_col0) (type: double)
+ 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: src
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: ((key < 200) and UDFToDouble(key) is not null) (type: boolean)
- Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE
+ predicate: (key < 100) (type: boolean)
+ Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: key (type: string)
outputColumnNames: _col0
- Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: UDFToDouble(_col0) (type: double)
- sort order: +
- Map-reduce partition columns: UDFToDouble(_col0) (type: double)
- Statistics: Num rows: 83 Data size: 881 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} {VALUE._col0}
- outputColumnNames: _col0, _col2, _col3
- Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- predicate: (_col0 + _col2) is not null (type: boolean)
- Statistics: Num rows: 91 Data size: 969 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: (_col0 + _col2) (type: double)
- sort order: +
- Map-reduce partition columns: (_col0 + _col2) (type: double)
- Statistics: Num rows: 91 Data size: 969 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col0 (type: string), _col3 (type: string)
+ Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0 {_col0}
+ 1 {_col0} {_col1}
+ keys:
+ 0 _col0 (type: string)
+ 1 _col0 (type: string)
+ outputColumnNames: _col0, _col2, _col3
+ input vertices:
+ 1 Map 1
+ Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: (_col0 + _col2) is not null (type: boolean)
+ Statistics: Num rows: 91 Data size: 969 Basic stats: COMPLETE Column stats: NONE
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0 {_col0} {_col3}
+ 1
+ keys:
+ 0 (_col0 + _col2) (type: double)
+ 1 UDFToDouble(_col0) (type: double)
+ outputColumnNames: _col0, _col3
+ input vertices:
+ 1 Map 4
+ Statistics: Num rows: 100 Data size: 1065 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: string), _col3 (type: string)
+ outputColumnNames: _col0, _col3
+ Statistics: Num rows: 100 Data size: 1065 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:
- Join Operator
- condition map:
- Inner Join 0 to 1
- condition expressions:
- 0 {VALUE._col0} {VALUE._col3}
- 1
- outputColumnNames: _col0, _col3
- Statistics: Num rows: 100 Data size: 1065 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col0 (type: string), _col3 (type: string)
- outputColumnNames: _col0, _col3
- Statistics: Num rows: 100 Data size: 1065 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)
- Reducer 4
- Reduce Operator Tree:
Group By Operator
aggregations: sum(VALUE._col0)
mode: mergepartial