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 2014/10/29 16:40:03 UTC
svn commit: r1635180 [2/5] - in /hive/branches/spark:
itests/src/test/resources/ ql/src/java/org/apache/hadoop/hive/ql/optimizer/
ql/src/test/queries/clientpositive/ ql/src/test/results/clientpositive/spark/
Modified: hive/branches/spark/ql/src/test/results/clientpositive/spark/skewjoinopt11.q.out
URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/skewjoinopt11.q.out?rev=1635180&r1=1635179&r2=1635180&view=diff
==============================================================================
--- hive/branches/spark/ql/src/test/results/clientpositive/spark/skewjoinopt11.q.out (original)
+++ hive/branches/spark/ql/src/test/results/clientpositive/spark/skewjoinopt11.q.out Wed Oct 29 15:40:02 2014
@@ -66,9 +66,11 @@ STAGE PLANS:
Stage: Stage-1
Spark
Edges:
+ Reducer 11 <- Map 10 (GROUP PARTITION-LEVEL SORT, 1), Map 13 (GROUP PARTITION-LEVEL SORT, 1)
Reducer 2 <- Map 1 (GROUP PARTITION-LEVEL SORT, 1), Map 4 (GROUP PARTITION-LEVEL SORT, 1)
Reducer 6 <- Map 5 (GROUP PARTITION-LEVEL SORT, 1), Map 7 (GROUP PARTITION-LEVEL SORT, 1)
- Union 3 <- Reducer 2 (NONE, 0), Reducer 6 (NONE, 0)
+ Reducer 9 <- Map 12 (GROUP PARTITION-LEVEL SORT, 1), Map 8 (GROUP PARTITION-LEVEL SORT, 1)
+ Union 3 <- Reducer 11 (NONE, 0), Reducer 2 (NONE, 0), Reducer 6 (NONE, 0), Reducer 9 (NONE, 0)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -77,7 +79,49 @@ STAGE PLANS:
alias: a
Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE
Filter Operator
- predicate: key is not null (type: boolean)
+ predicate: (key is not null and (not (key = '2'))) (type: boolean)
+ Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+ Reduce Output Operator
+ key expressions: key (type: string)
+ sort order: +
+ Map-reduce partition columns: key (type: string)
+ Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+ value expressions: val (type: string)
+ Map 10
+ Map Operator Tree:
+ TableScan
+ alias: b
+ Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE
+ Filter Operator
+ predicate: (key is not null and (not (key = '2'))) (type: boolean)
+ Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+ Reduce Output Operator
+ key expressions: key (type: string)
+ sort order: +
+ Map-reduce partition columns: key (type: string)
+ Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+ value expressions: val (type: string)
+ Map 12
+ Map Operator Tree:
+ TableScan
+ alias: b
+ Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE
+ Filter Operator
+ predicate: (key is not null and (key = '2')) (type: boolean)
+ Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+ Reduce Output Operator
+ key expressions: key (type: string)
+ sort order: +
+ Map-reduce partition columns: key (type: string)
+ Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+ value expressions: val (type: string)
+ Map 13
+ Map Operator Tree:
+ TableScan
+ alias: a
+ Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE
+ Filter Operator
+ predicate: (key is not null and (not (key = '2'))) (type: boolean)
Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
Reduce Output Operator
key expressions: key (type: string)
@@ -91,7 +135,7 @@ STAGE PLANS:
alias: b
Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE
Filter Operator
- predicate: key is not null (type: boolean)
+ predicate: (key is not null and (not (key = '2'))) (type: boolean)
Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
Reduce Output Operator
key expressions: key (type: string)
@@ -105,7 +149,7 @@ STAGE PLANS:
alias: a
Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE
Filter Operator
- predicate: key is not null (type: boolean)
+ predicate: (key is not null and (key = '2')) (type: boolean)
Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
Reduce Output Operator
key expressions: key (type: string)
@@ -119,7 +163,7 @@ STAGE PLANS:
alias: b
Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE
Filter Operator
- predicate: key is not null (type: boolean)
+ predicate: (key is not null and (key = '2')) (type: boolean)
Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
Reduce Output Operator
key expressions: key (type: string)
@@ -127,6 +171,43 @@ STAGE PLANS:
Map-reduce partition columns: key (type: string)
Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
value expressions: val (type: string)
+ Map 8
+ Map Operator Tree:
+ TableScan
+ alias: a
+ Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE
+ Filter Operator
+ predicate: (key is not null and (key = '2')) (type: boolean)
+ Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+ Reduce Output Operator
+ key expressions: key (type: string)
+ sort order: +
+ Map-reduce partition columns: key (type: string)
+ Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+ value expressions: val (type: string)
+ Reducer 11
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0 {KEY.reducesinkkey0} {VALUE._col0}
+ 1 {VALUE._col0}
+ outputColumnNames: _col0, _col1, _col6
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: string), _col6 (type: string)
+ outputColumnNames: _col0, _col1, _col2
+ Select Operator
+ SELECT * : (no compute)
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string)
+ outputColumnNames: _col0, _col1, _col2
+ File Output Operator
+ compressed: false
+ 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
Reducer 2
Reduce Operator Tree:
Join Operator
@@ -140,14 +221,16 @@ STAGE PLANS:
expressions: _col0 (type: string), _col1 (type: string), _col6 (type: string)
outputColumnNames: _col0, _col1, _col2
Select Operator
- expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string)
- outputColumnNames: _col0, _col1, _col2
- File Output Operator
- compressed: false
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ SELECT * : (no compute)
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string)
+ outputColumnNames: _col0, _col1, _col2
+ File Output Operator
+ compressed: false
+ 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
Reducer 6
Reduce Operator Tree:
Join Operator
@@ -161,14 +244,39 @@ STAGE PLANS:
expressions: _col0 (type: string), _col1 (type: string), _col6 (type: string)
outputColumnNames: _col0, _col1, _col2
Select Operator
- expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string)
- outputColumnNames: _col0, _col1, _col2
- File Output Operator
- compressed: false
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ SELECT * : (no compute)
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string)
+ outputColumnNames: _col0, _col1, _col2
+ File Output Operator
+ compressed: false
+ 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
+ Reducer 9
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0 {KEY.reducesinkkey0} {VALUE._col0}
+ 1 {VALUE._col0}
+ outputColumnNames: _col0, _col1, _col6
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: string), _col6 (type: string)
+ outputColumnNames: _col0, _col1, _col2
+ Select Operator
+ SELECT * : (no compute)
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string)
+ outputColumnNames: _col0, _col1, _col2
+ File Output Operator
+ compressed: false
+ 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
Union 3
Vertex: Union 3
Modified: hive/branches/spark/ql/src/test/results/clientpositive/spark/skewjoinopt12.q.out
URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/skewjoinopt12.q.out?rev=1635180&r1=1635179&r2=1635180&view=diff
==============================================================================
--- hive/branches/spark/ql/src/test/results/clientpositive/spark/skewjoinopt12.q.out (original)
+++ hive/branches/spark/ql/src/test/results/clientpositive/spark/skewjoinopt12.q.out Wed Oct 29 15:40:02 2014
@@ -56,29 +56,57 @@ STAGE PLANS:
Stage: Stage-1
Spark
Edges:
- Reducer 2 <- Map 1 (GROUP PARTITION-LEVEL SORT, 1), Map 3 (GROUP PARTITION-LEVEL SORT, 1)
+ Reducer 2 <- Map 1 (GROUP PARTITION-LEVEL SORT, 1), Map 4 (GROUP PARTITION-LEVEL SORT, 1)
+ Reducer 6 <- Map 5 (GROUP PARTITION-LEVEL SORT, 1), Map 7 (GROUP PARTITION-LEVEL SORT, 1)
+ Union 3 <- Reducer 2 (NONE, 0), Reducer 6 (NONE, 0)
#### A masked pattern was here ####
Vertices:
Map 1
Map Operator Tree:
TableScan
+ alias: a
+ Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE
+ Filter Operator
+ predicate: ((key is not null and val is not null) and (not ((((key = '2') and (val = '12')) or ((key = '8') and (val = '18'))) or ((key = '3') and (val = '13'))))) (type: boolean)
+ Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+ Reduce Output Operator
+ key expressions: key (type: string), val (type: string)
+ sort order: ++
+ Map-reduce partition columns: key (type: string), val (type: string)
+ Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+ Map 4
+ Map Operator Tree:
+ TableScan
+ alias: b
+ Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE
+ Filter Operator
+ predicate: ((key is not null and val is not null) and (not ((((key = '2') and (val = '12')) or ((key = '8') and (val = '18'))) or ((key = '3') and (val = '13'))))) (type: boolean)
+ Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+ Reduce Output Operator
+ key expressions: key (type: string), val (type: string)
+ sort order: ++
+ Map-reduce partition columns: key (type: string), val (type: string)
+ Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+ Map 5
+ Map Operator Tree:
+ TableScan
alias: b
Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE
Filter Operator
- predicate: (key is not null and val is not null) (type: boolean)
+ predicate: ((key is not null and val is not null) and ((((key = '2') and (val = '12')) or ((key = '8') and (val = '18'))) or ((key = '3') and (val = '13')))) (type: boolean)
Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
Reduce Output Operator
key expressions: key (type: string), val (type: string)
sort order: ++
Map-reduce partition columns: key (type: string), val (type: string)
Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
- Map 3
+ Map 7
Map Operator Tree:
TableScan
alias: a
Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE
Filter Operator
- predicate: (key is not null and val is not null) (type: boolean)
+ predicate: ((key is not null and val is not null) and ((((key = '2') and (val = '12')) or ((key = '8') and (val = '18'))) or ((key = '3') and (val = '13')))) (type: boolean)
Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
Reduce Output Operator
key expressions: key (type: string), val (type: string)
@@ -94,18 +122,39 @@ STAGE PLANS:
0 {KEY.reducesinkkey0} {KEY.reducesinkkey1}
1 {KEY.reducesinkkey0} {KEY.reducesinkkey1}
outputColumnNames: _col0, _col1, _col5, _col6
- Statistics: Num rows: 0 Data size: 0 Basic stats: NONE 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: 0 Data size: 0 Basic stats: NONE Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ Select Operator
+ SELECT * : (no compute)
+ File Output Operator
+ compressed: false
+ 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
+ Reducer 6
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0 {KEY.reducesinkkey0} {KEY.reducesinkkey1}
+ 1 {KEY.reducesinkkey0} {KEY.reducesinkkey1}
+ outputColumnNames: _col0, _col1, _col5, _col6
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Select Operator
+ SELECT * : (no compute)
+ File Output Operator
+ compressed: false
+ 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
+ Union 3
+ Vertex: Union 3
Stage: Stage-0
Fetch Operator
Modified: hive/branches/spark/ql/src/test/results/clientpositive/spark/skewjoinopt14.q.out
URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/skewjoinopt14.q.out?rev=1635180&r1=1635179&r2=1635180&view=diff
==============================================================================
--- hive/branches/spark/ql/src/test/results/clientpositive/spark/skewjoinopt14.q.out (original)
+++ hive/branches/spark/ql/src/test/results/clientpositive/spark/skewjoinopt14.q.out Wed Oct 29 15:40:02 2014
@@ -87,16 +87,46 @@ STAGE PLANS:
Spark
Edges:
Reducer 2 <- Map 1 (GROUP PARTITION-LEVEL SORT, 1), Map 5 (GROUP PARTITION-LEVEL SORT, 1)
- Reducer 3 <- Map 4 (GROUP PARTITION-LEVEL SORT, 1), Reducer 2 (GROUP PARTITION-LEVEL SORT, 1)
+ Reducer 4 <- Map 8 (GROUP PARTITION-LEVEL SORT, 1), Union 3 (GROUP PARTITION-LEVEL SORT, 1)
+ Reducer 7 <- Map 6 (GROUP PARTITION-LEVEL SORT, 1), Map 9 (GROUP PARTITION-LEVEL SORT, 1)
+ Union 3 <- Reducer 2 (NONE, 0), Reducer 7 (NONE, 0)
#### A masked pattern was here ####
Vertices:
Map 1
Map Operator Tree:
TableScan
+ alias: a
+ Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE
+ Filter Operator
+ predicate: ((key is not null and val is not null) and (not (key = '2'))) (type: boolean)
+ Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+ Reduce Output Operator
+ key expressions: key (type: string)
+ sort order: +
+ Map-reduce partition columns: key (type: string)
+ Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+ value expressions: val (type: string)
+ Map 5
+ Map Operator Tree:
+ TableScan
+ alias: b
+ Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE
+ Filter Operator
+ predicate: (key is not null and (not (key = '2'))) (type: boolean)
+ Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+ Reduce Output Operator
+ key expressions: key (type: string)
+ sort order: +
+ Map-reduce partition columns: key (type: string)
+ Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+ value expressions: val (type: string)
+ Map 6
+ Map Operator Tree:
+ TableScan
alias: b
Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE
Filter Operator
- predicate: key is not null (type: boolean)
+ predicate: (key is not null and (key = '2')) (type: boolean)
Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
Reduce Output Operator
key expressions: key (type: string)
@@ -104,7 +134,7 @@ STAGE PLANS:
Map-reduce partition columns: key (type: string)
Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
value expressions: val (type: string)
- Map 4
+ Map 8
Map Operator Tree:
TableScan
alias: c
@@ -118,13 +148,13 @@ STAGE PLANS:
Map-reduce partition columns: val (type: string)
Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
value expressions: key (type: string)
- Map 5
+ Map 9
Map Operator Tree:
TableScan
alias: a
Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE
Filter Operator
- predicate: (key is not null and val is not null) (type: boolean)
+ predicate: ((key is not null and val is not null) and (key = '2')) (type: boolean)
Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
Reduce Output Operator
key expressions: key (type: string)
@@ -141,14 +171,14 @@ STAGE PLANS:
0 {KEY.reducesinkkey0} {VALUE._col0}
1 {KEY.reducesinkkey0} {VALUE._col0}
outputColumnNames: _col0, _col1, _col5, _col6
- Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
- Reduce Output Operator
- key expressions: _col1 (type: string)
- sort order: +
- Map-reduce partition columns: _col1 (type: string)
- Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
- value expressions: _col0 (type: string), _col5 (type: string), _col6 (type: string)
- Reducer 3
+ Select Operator
+ SELECT * : (no compute)
+ Reduce Output Operator
+ key expressions: _col1 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col1 (type: string)
+ value expressions: _col0 (type: string), _col5 (type: string), _col6 (type: string)
+ Reducer 4
Reduce Operator Tree:
Join Operator
condition map:
@@ -169,6 +199,24 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ Reducer 7
+ 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
+ Select Operator
+ SELECT * : (no compute)
+ Reduce Output Operator
+ key expressions: _col1 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col1 (type: string)
+ value expressions: _col0 (type: string), _col5 (type: string), _col6 (type: string)
+ Union 3
+ Vertex: Union 3
Stage: Stage-0
Fetch Operator
Modified: hive/branches/spark/ql/src/test/results/clientpositive/spark/skewjoinopt15.q.out
URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/skewjoinopt15.q.out?rev=1635180&r1=1635179&r2=1635180&view=diff
==============================================================================
--- hive/branches/spark/ql/src/test/results/clientpositive/spark/skewjoinopt15.q.out (original)
+++ hive/branches/spark/ql/src/test/results/clientpositive/spark/skewjoinopt15.q.out Wed Oct 29 15:40:02 2014
@@ -96,16 +96,32 @@ STAGE PLANS:
Stage: Stage-1
Spark
Edges:
- Reducer 2 <- Map 1 (GROUP PARTITION-LEVEL SORT, 1), Map 3 (GROUP PARTITION-LEVEL SORT, 1)
+ Reducer 2 <- Map 1 (GROUP PARTITION-LEVEL SORT, 1), Map 4 (GROUP PARTITION-LEVEL SORT, 1)
+ Reducer 6 <- Map 5 (GROUP PARTITION-LEVEL SORT, 1), Map 7 (GROUP PARTITION-LEVEL SORT, 1)
+ Union 3 <- Reducer 2 (NONE, 0), Reducer 6 (NONE, 0)
#### A masked pattern was here ####
Vertices:
Map 1
Map Operator Tree:
TableScan
+ alias: a
+ Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE
+ Filter Operator
+ predicate: (key is not null and (not ((key = 2) or (key = 3)))) (type: boolean)
+ Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+ Reduce Output Operator
+ key expressions: key (type: int)
+ sort order: +
+ Map-reduce partition columns: key (type: int)
+ Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+ value expressions: val (type: string)
+ Map 4
+ Map Operator Tree:
+ TableScan
alias: b
Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE
Filter Operator
- predicate: key is not null (type: boolean)
+ predicate: (key is not null and (not ((key = 2) or (key = 3)))) (type: boolean)
Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
Reduce Output Operator
key expressions: key (type: int)
@@ -113,13 +129,27 @@ STAGE PLANS:
Map-reduce partition columns: key (type: int)
Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
value expressions: val (type: string)
- Map 3
+ Map 5
+ Map Operator Tree:
+ TableScan
+ alias: b
+ Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE
+ Filter Operator
+ predicate: (key is not null and ((key = 2) or (key = 3))) (type: boolean)
+ Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+ Reduce Output Operator
+ key expressions: key (type: int)
+ sort order: +
+ Map-reduce partition columns: key (type: int)
+ Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+ value expressions: val (type: string)
+ Map 7
Map Operator Tree:
TableScan
alias: a
Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE
Filter Operator
- predicate: key is not null (type: boolean)
+ predicate: (key is not null and ((key = 2) or (key = 3))) (type: boolean)
Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
Reduce Output Operator
key expressions: key (type: int)
@@ -136,18 +166,39 @@ STAGE PLANS:
0 {KEY.reducesinkkey0} {VALUE._col0}
1 {KEY.reducesinkkey0} {VALUE._col0}
outputColumnNames: _col0, _col1, _col5, _col6
- Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
Select Operator
expressions: _col0 (type: int), _col1 (type: string), _col5 (type: int), _col6 (type: string)
outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ Select Operator
+ SELECT * : (no compute)
+ File Output Operator
+ compressed: false
+ 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
+ Reducer 6
+ 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
+ Select Operator
+ expressions: _col0 (type: int), _col1 (type: string), _col5 (type: int), _col6 (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Select Operator
+ SELECT * : (no compute)
+ File Output Operator
+ compressed: false
+ 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
+ Union 3
+ Vertex: Union 3
Stage: Stage-0
Fetch Operator
@@ -191,31 +242,67 @@ STAGE PLANS:
Stage: Stage-1
Spark
Edges:
- Reducer 2 <- Map 1 (GROUP PARTITION-LEVEL SORT, 1), Map 3 (GROUP PARTITION-LEVEL SORT, 1)
+ Reducer 2 <- Map 1 (GROUP PARTITION-LEVEL SORT, 1), Map 4 (GROUP PARTITION-LEVEL SORT, 1)
+ Reducer 6 <- Map 5 (GROUP PARTITION-LEVEL SORT, 1), Map 7 (GROUP PARTITION-LEVEL SORT, 1)
+ Union 3 <- Reducer 2 (NONE, 0), Reducer 6 (NONE, 0)
#### A masked pattern was here ####
Vertices:
Map 1
Map Operator Tree:
TableScan
+ alias: a
+ Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE
+ Filter Operator
+ predicate: (not ((key = 2) or (key = 3))) (type: boolean)
+ Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+ Reduce Output Operator
+ key expressions: key (type: int)
+ sort order: +
+ Map-reduce partition columns: key (type: int)
+ Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+ value expressions: val (type: string)
+ Map 4
+ Map Operator Tree:
+ TableScan
+ alias: b
+ Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE
+ Filter Operator
+ predicate: (not ((key = 2) or (key = 3))) (type: boolean)
+ Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+ Reduce Output Operator
+ key expressions: key (type: int)
+ sort order: +
+ Map-reduce partition columns: key (type: int)
+ Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+ value expressions: val (type: string)
+ Map 5
+ Map Operator Tree:
+ TableScan
alias: b
Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE
- Reduce Output Operator
- key expressions: key (type: int)
- sort order: +
- Map-reduce partition columns: key (type: int)
- Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE
- value expressions: val (type: string)
- Map 3
+ Filter Operator
+ predicate: ((key = 2) or (key = 3)) (type: boolean)
+ Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+ Reduce Output Operator
+ key expressions: key (type: int)
+ sort order: +
+ Map-reduce partition columns: key (type: int)
+ Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+ value expressions: val (type: string)
+ Map 7
Map Operator Tree:
TableScan
alias: a
Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE
- Reduce Output Operator
- key expressions: key (type: int)
- sort order: +
- Map-reduce partition columns: key (type: int)
- Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE
- value expressions: val (type: string)
+ Filter Operator
+ predicate: ((key = 2) or (key = 3)) (type: boolean)
+ Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+ Reduce Output Operator
+ key expressions: key (type: int)
+ sort order: +
+ Map-reduce partition columns: key (type: int)
+ Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+ value expressions: val (type: string)
Reducer 2
Reduce Operator Tree:
Join Operator
@@ -225,18 +312,39 @@ STAGE PLANS:
0 {KEY.reducesinkkey0} {VALUE._col0}
1 {KEY.reducesinkkey0} {VALUE._col0}
outputColumnNames: _col0, _col1, _col5, _col6
- Statistics: Num rows: 0 Data size: 33 Basic stats: PARTIAL Column stats: NONE
Select Operator
expressions: _col0 (type: int), _col1 (type: string), _col5 (type: int), _col6 (type: string)
outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 0 Data size: 33 Basic stats: PARTIAL Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 0 Data size: 33 Basic stats: PARTIAL Column stats: NONE
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ Select Operator
+ SELECT * : (no compute)
+ File Output Operator
+ compressed: false
+ 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
+ Reducer 6
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Right Outer Join0 to 1
+ condition expressions:
+ 0 {KEY.reducesinkkey0} {VALUE._col0}
+ 1 {KEY.reducesinkkey0} {VALUE._col0}
+ outputColumnNames: _col0, _col1, _col5, _col6
+ Select Operator
+ expressions: _col0 (type: int), _col1 (type: string), _col5 (type: int), _col6 (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Select Operator
+ SELECT * : (no compute)
+ File Output Operator
+ compressed: false
+ 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
+ Union 3
+ Vertex: Union 3
Stage: Stage-0
Fetch Operator
@@ -282,30 +390,58 @@ STAGE PLANS:
Stage: Stage-1
Spark
Edges:
- Reducer 2 <- Map 1 (GROUP PARTITION-LEVEL SORT, 1), Map 4 (GROUP PARTITION-LEVEL SORT, 1)
- Reducer 3 <- Reducer 2 (GROUP, 1)
+ Reducer 2 <- Map 1 (GROUP PARTITION-LEVEL SORT, 1), Map 5 (GROUP PARTITION-LEVEL SORT, 1)
+ Reducer 4 <- Union 3 (GROUP, 1)
+ Reducer 7 <- Map 6 (GROUP PARTITION-LEVEL SORT, 1), Map 8 (GROUP PARTITION-LEVEL SORT, 1)
+ Union 3 <- Reducer 2 (NONE, 0), Reducer 7 (NONE, 0)
#### A masked pattern was here ####
Vertices:
Map 1
Map Operator Tree:
TableScan
+ alias: a
+ Statistics: Num rows: 7 Data size: 30 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: (key is not null and (not ((key = 2) or (key = 3)))) (type: boolean)
+ Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+ Reduce Output Operator
+ key expressions: key (type: int)
+ sort order: +
+ Map-reduce partition columns: key (type: int)
+ Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+ Map 5
+ Map Operator Tree:
+ TableScan
+ alias: b
+ Statistics: Num rows: 7 Data size: 30 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: (key is not null and (not ((key = 2) or (key = 3)))) (type: boolean)
+ Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+ Reduce Output Operator
+ key expressions: key (type: int)
+ sort order: +
+ Map-reduce partition columns: key (type: int)
+ Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+ Map 6
+ Map Operator Tree:
+ TableScan
alias: b
Statistics: Num rows: 7 Data size: 30 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: key is not null (type: boolean)
+ predicate: (key is not null and ((key = 2) or (key = 3))) (type: boolean)
Statistics: Num rows: 4 Data size: 17 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: key (type: int)
sort order: +
Map-reduce partition columns: key (type: int)
Statistics: Num rows: 4 Data size: 17 Basic stats: COMPLETE Column stats: NONE
- Map 4
+ Map 8
Map Operator Tree:
TableScan
alias: a
Statistics: Num rows: 7 Data size: 30 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: key is not null (type: boolean)
+ predicate: (key is not null and ((key = 2) or (key = 3))) (type: boolean)
Statistics: Num rows: 4 Data size: 17 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: key (type: int)
@@ -320,19 +456,17 @@ STAGE PLANS:
condition expressions:
0
1
- Statistics: Num rows: 4 Data size: 18 Basic stats: COMPLETE Column stats: NONE
Select Operator
- Statistics: Num rows: 4 Data size: 18 Basic stats: COMPLETE Column stats: NONE
- Group By Operator
- aggregations: count(1)
- 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
+ Select Operator
+ SELECT * : (no compute)
+ Group By Operator
+ aggregations: count(1)
+ mode: hash
+ outputColumnNames: _col0
+ Reduce Output Operator
+ sort order:
+ value expressions: _col0 (type: bigint)
+ Reducer 4
Reduce Operator Tree:
Group By Operator
aggregations: count(VALUE._col0)
@@ -350,6 +484,26 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ Reducer 7
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0
+ 1
+ Select Operator
+ Select Operator
+ SELECT * : (no compute)
+ Group By Operator
+ aggregations: count(1)
+ mode: hash
+ outputColumnNames: _col0
+ Reduce Output Operator
+ sort order:
+ value expressions: _col0 (type: bigint)
+ Union 3
+ Vertex: Union 3
Stage: Stage-0
Fetch Operator
@@ -382,30 +536,64 @@ STAGE PLANS:
Stage: Stage-1
Spark
Edges:
- Reducer 2 <- Map 1 (GROUP PARTITION-LEVEL SORT, 1), Map 4 (GROUP PARTITION-LEVEL SORT, 1)
- Reducer 3 <- Reducer 2 (GROUP, 1)
+ Reducer 2 <- Map 1 (GROUP PARTITION-LEVEL SORT, 1), Map 5 (GROUP PARTITION-LEVEL SORT, 1)
+ Reducer 4 <- Union 3 (GROUP, 1)
+ Reducer 7 <- Map 6 (GROUP PARTITION-LEVEL SORT, 1), Map 8 (GROUP PARTITION-LEVEL SORT, 1)
+ Union 3 <- Reducer 2 (NONE, 0), Reducer 7 (NONE, 0)
#### A masked pattern was here ####
Vertices:
Map 1
Map Operator Tree:
TableScan
+ alias: a
+ Statistics: Num rows: 7 Data size: 30 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: (not ((key = 2) or (key = 3))) (type: boolean)
+ Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: key (type: int)
+ sort order: +
+ Map-reduce partition columns: key (type: int)
+ Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE
+ Map 5
+ Map Operator Tree:
+ TableScan
alias: b
Statistics: Num rows: 7 Data size: 30 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: key (type: int)
- sort order: +
- Map-reduce partition columns: key (type: int)
- Statistics: Num rows: 7 Data size: 30 Basic stats: COMPLETE Column stats: NONE
- Map 4
+ Filter Operator
+ predicate: (not ((key = 2) or (key = 3))) (type: boolean)
+ Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: key (type: int)
+ sort order: +
+ Map-reduce partition columns: key (type: int)
+ Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE
+ Map 6
+ Map Operator Tree:
+ TableScan
+ alias: b
+ Statistics: Num rows: 7 Data size: 30 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: ((key = 2) or (key = 3)) (type: boolean)
+ Statistics: Num rows: 6 Data size: 25 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: key (type: int)
+ sort order: +
+ Map-reduce partition columns: key (type: int)
+ Statistics: Num rows: 6 Data size: 25 Basic stats: COMPLETE Column stats: NONE
+ Map 8
Map Operator Tree:
TableScan
alias: a
Statistics: Num rows: 7 Data size: 30 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: key (type: int)
- sort order: +
- Map-reduce partition columns: key (type: int)
- Statistics: Num rows: 7 Data size: 30 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: ((key = 2) or (key = 3)) (type: boolean)
+ Statistics: Num rows: 6 Data size: 25 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: key (type: int)
+ sort order: +
+ Map-reduce partition columns: key (type: int)
+ Statistics: Num rows: 6 Data size: 25 Basic stats: COMPLETE Column stats: NONE
Reducer 2
Reduce Operator Tree:
Join Operator
@@ -414,19 +602,17 @@ STAGE PLANS:
condition expressions:
0
1
- Statistics: Num rows: 7 Data size: 33 Basic stats: COMPLETE Column stats: NONE
Select Operator
- Statistics: Num rows: 7 Data size: 33 Basic stats: COMPLETE Column stats: NONE
- Group By Operator
- aggregations: count(1)
- 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
+ Select Operator
+ SELECT * : (no compute)
+ Group By Operator
+ aggregations: count(1)
+ mode: hash
+ outputColumnNames: _col0
+ Reduce Output Operator
+ sort order:
+ value expressions: _col0 (type: bigint)
+ Reducer 4
Reduce Operator Tree:
Group By Operator
aggregations: count(VALUE._col0)
@@ -444,6 +630,26 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ Reducer 7
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Right Outer Join0 to 1
+ condition expressions:
+ 0
+ 1
+ Select Operator
+ Select Operator
+ SELECT * : (no compute)
+ Group By Operator
+ aggregations: count(1)
+ mode: hash
+ outputColumnNames: _col0
+ Reduce Output Operator
+ sort order:
+ value expressions: _col0 (type: bigint)
+ Union 3
+ Vertex: Union 3
Stage: Stage-0
Fetch Operator
Modified: hive/branches/spark/ql/src/test/results/clientpositive/spark/skewjoinopt16.q.out
URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/skewjoinopt16.q.out?rev=1635180&r1=1635179&r2=1635180&view=diff
==============================================================================
--- hive/branches/spark/ql/src/test/results/clientpositive/spark/skewjoinopt16.q.out (original)
+++ hive/branches/spark/ql/src/test/results/clientpositive/spark/skewjoinopt16.q.out Wed Oct 29 15:40:02 2014
@@ -56,29 +56,57 @@ STAGE PLANS:
Stage: Stage-1
Spark
Edges:
- Reducer 2 <- Map 1 (GROUP PARTITION-LEVEL SORT, 1), Map 3 (GROUP PARTITION-LEVEL SORT, 1)
+ Reducer 2 <- Map 1 (GROUP PARTITION-LEVEL SORT, 1), Map 4 (GROUP PARTITION-LEVEL SORT, 1)
+ Reducer 6 <- Map 5 (GROUP PARTITION-LEVEL SORT, 1), Map 7 (GROUP PARTITION-LEVEL SORT, 1)
+ Union 3 <- Reducer 2 (NONE, 0), Reducer 6 (NONE, 0)
#### A masked pattern was here ####
Vertices:
Map 1
Map Operator Tree:
TableScan
+ alias: a
+ Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE
+ Filter Operator
+ predicate: ((key is not null and val is not null) and (not (((key = '2') and (val = '12')) or (key = '3')))) (type: boolean)
+ Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+ Reduce Output Operator
+ key expressions: key (type: string), val (type: string)
+ sort order: ++
+ Map-reduce partition columns: key (type: string), val (type: string)
+ Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+ Map 4
+ Map Operator Tree:
+ TableScan
+ alias: b
+ Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE
+ Filter Operator
+ predicate: ((key is not null and val is not null) and (not (((key = '2') and (val = '12')) or (key = '3')))) (type: boolean)
+ Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+ Reduce Output Operator
+ key expressions: key (type: string), val (type: string)
+ sort order: ++
+ Map-reduce partition columns: key (type: string), val (type: string)
+ Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+ Map 5
+ Map Operator Tree:
+ TableScan
alias: b
Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE
Filter Operator
- predicate: (key is not null and val is not null) (type: boolean)
+ predicate: ((key is not null and val is not null) and (((key = '2') and (val = '12')) or (key = '3'))) (type: boolean)
Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
Reduce Output Operator
key expressions: key (type: string), val (type: string)
sort order: ++
Map-reduce partition columns: key (type: string), val (type: string)
Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
- Map 3
+ Map 7
Map Operator Tree:
TableScan
alias: a
Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE
Filter Operator
- predicate: (key is not null and val is not null) (type: boolean)
+ predicate: ((key is not null and val is not null) and (((key = '2') and (val = '12')) or (key = '3'))) (type: boolean)
Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
Reduce Output Operator
key expressions: key (type: string), val (type: string)
@@ -94,18 +122,39 @@ STAGE PLANS:
0 {KEY.reducesinkkey0} {KEY.reducesinkkey1}
1 {KEY.reducesinkkey0} {KEY.reducesinkkey1}
outputColumnNames: _col0, _col1, _col5, _col6
- Statistics: Num rows: 0 Data size: 0 Basic stats: NONE 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: 0 Data size: 0 Basic stats: NONE Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ Select Operator
+ SELECT * : (no compute)
+ File Output Operator
+ compressed: false
+ 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
+ Reducer 6
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0 {KEY.reducesinkkey0} {KEY.reducesinkkey1}
+ 1 {KEY.reducesinkkey0} {KEY.reducesinkkey1}
+ outputColumnNames: _col0, _col1, _col5, _col6
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Select Operator
+ SELECT * : (no compute)
+ File Output Operator
+ compressed: false
+ 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
+ Union 3
+ Vertex: Union 3
Stage: Stage-0
Fetch Operator
Modified: hive/branches/spark/ql/src/test/results/clientpositive/spark/skewjoinopt17.q.out
URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/skewjoinopt17.q.out?rev=1635180&r1=1635179&r2=1635180&view=diff
==============================================================================
--- hive/branches/spark/ql/src/test/results/clientpositive/spark/skewjoinopt17.q.out (original)
+++ hive/branches/spark/ql/src/test/results/clientpositive/spark/skewjoinopt17.q.out Wed Oct 29 15:40:02 2014
@@ -60,16 +60,46 @@ STAGE PLANS:
Stage: Stage-1
Spark
Edges:
- Reducer 2 <- Map 1 (GROUP PARTITION-LEVEL SORT, 1), Map 3 (GROUP PARTITION-LEVEL SORT, 1)
+ Reducer 2 <- Map 1 (GROUP PARTITION-LEVEL SORT, 1), Map 4 (GROUP PARTITION-LEVEL SORT, 1)
+ Reducer 6 <- Map 5 (GROUP PARTITION-LEVEL SORT, 1), Map 7 (GROUP PARTITION-LEVEL SORT, 1)
+ Union 3 <- Reducer 2 (NONE, 0), Reducer 6 (NONE, 0)
#### A masked pattern was here ####
Vertices:
Map 1
Map Operator Tree:
TableScan
+ alias: a
+ Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE
+ Filter Operator
+ predicate: (key is not null and (not (key = '2'))) (type: boolean)
+ Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+ Reduce Output Operator
+ key expressions: key (type: string)
+ sort order: +
+ Map-reduce partition columns: key (type: string)
+ Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+ value expressions: val (type: string)
+ Map 4
+ Map Operator Tree:
+ TableScan
+ alias: b
+ Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE
+ Filter Operator
+ predicate: (key is not null and (not (key = '2'))) (type: boolean)
+ Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+ Reduce Output Operator
+ key expressions: key (type: string)
+ sort order: +
+ Map-reduce partition columns: key (type: string)
+ Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+ value expressions: val (type: string)
+ Map 5
+ Map Operator Tree:
+ TableScan
alias: b
Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE
Filter Operator
- predicate: key is not null (type: boolean)
+ predicate: (key is not null and (key = '2')) (type: boolean)
Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
Reduce Output Operator
key expressions: key (type: string)
@@ -77,13 +107,13 @@ STAGE PLANS:
Map-reduce partition columns: key (type: string)
Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
value expressions: val (type: string)
- Map 3
+ Map 7
Map Operator Tree:
TableScan
alias: a
Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE
Filter Operator
- predicate: key is not null (type: boolean)
+ predicate: (key is not null and (key = '2')) (type: boolean)
Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
Reduce Output Operator
key expressions: key (type: string)
@@ -100,18 +130,39 @@ STAGE PLANS:
0 {KEY.reducesinkkey0} {VALUE._col0}
1 {KEY.reducesinkkey0} {VALUE._col0}
outputColumnNames: _col0, _col1, _col5, _col6
- Statistics: Num rows: 0 Data size: 0 Basic stats: NONE 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: 0 Data size: 0 Basic stats: NONE Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ Select Operator
+ SELECT * : (no compute)
+ File Output Operator
+ compressed: false
+ 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
+ Reducer 6
+ 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
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Select Operator
+ SELECT * : (no compute)
+ File Output Operator
+ compressed: false
+ 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
+ Union 3
+ Vertex: Union 3
Stage: Stage-0
Fetch Operator
@@ -211,29 +262,57 @@ STAGE PLANS:
Stage: Stage-1
Spark
Edges:
- Reducer 2 <- Map 1 (GROUP PARTITION-LEVEL SORT, 1), Map 3 (GROUP PARTITION-LEVEL SORT, 1)
+ Reducer 2 <- Map 1 (GROUP PARTITION-LEVEL SORT, 1), Map 4 (GROUP PARTITION-LEVEL SORT, 1)
+ Reducer 6 <- Map 5 (GROUP PARTITION-LEVEL SORT, 1), Map 7 (GROUP PARTITION-LEVEL SORT, 1)
+ Union 3 <- Reducer 2 (NONE, 0), Reducer 6 (NONE, 0)
#### A masked pattern was here ####
Vertices:
Map 1
Map Operator Tree:
TableScan
+ alias: a
+ Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE
+ Filter Operator
+ predicate: ((key is not null and val is not null) and (not (((key = '2') and (val = '12')) or (key = '2')))) (type: boolean)
+ Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+ Reduce Output Operator
+ key expressions: key (type: string), val (type: string)
+ sort order: ++
+ Map-reduce partition columns: key (type: string), val (type: string)
+ Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+ Map 4
+ Map Operator Tree:
+ TableScan
+ alias: b
+ Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE
+ Filter Operator
+ predicate: ((key is not null and val is not null) and (not (((key = '2') and (val = '12')) or (key = '2')))) (type: boolean)
+ Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+ Reduce Output Operator
+ key expressions: key (type: string), val (type: string)
+ sort order: ++
+ Map-reduce partition columns: key (type: string), val (type: string)
+ Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+ Map 5
+ Map Operator Tree:
+ TableScan
alias: b
Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE
Filter Operator
- predicate: (key is not null and val is not null) (type: boolean)
+ predicate: ((key is not null and val is not null) and (((key = '2') and (val = '12')) or (key = '2'))) (type: boolean)
Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
Reduce Output Operator
key expressions: key (type: string), val (type: string)
sort order: ++
Map-reduce partition columns: key (type: string), val (type: string)
Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
- Map 3
+ Map 7
Map Operator Tree:
TableScan
alias: a
Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE
Filter Operator
- predicate: (key is not null and val is not null) (type: boolean)
+ predicate: ((key is not null and val is not null) and (((key = '2') and (val = '12')) or (key = '2'))) (type: boolean)
Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
Reduce Output Operator
key expressions: key (type: string), val (type: string)
@@ -249,18 +328,39 @@ STAGE PLANS:
0 {KEY.reducesinkkey0} {KEY.reducesinkkey1}
1 {KEY.reducesinkkey0} {KEY.reducesinkkey1}
outputColumnNames: _col0, _col1, _col5, _col6
- Statistics: Num rows: 0 Data size: 0 Basic stats: NONE 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: 0 Data size: 0 Basic stats: NONE Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ Select Operator
+ SELECT * : (no compute)
+ File Output Operator
+ compressed: false
+ 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
+ Reducer 6
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0 {KEY.reducesinkkey0} {KEY.reducesinkkey1}
+ 1 {KEY.reducesinkkey0} {KEY.reducesinkkey1}
+ outputColumnNames: _col0, _col1, _col5, _col6
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Select Operator
+ SELECT * : (no compute)
+ File Output Operator
+ compressed: false
+ 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
+ Union 3
+ Vertex: Union 3
Stage: Stage-0
Fetch Operator
Modified: hive/branches/spark/ql/src/test/results/clientpositive/spark/skewjoinopt19.q.out
URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/skewjoinopt19.q.out?rev=1635180&r1=1635179&r2=1635180&view=diff
==============================================================================
--- hive/branches/spark/ql/src/test/results/clientpositive/spark/skewjoinopt19.q.out (original)
+++ hive/branches/spark/ql/src/test/results/clientpositive/spark/skewjoinopt19.q.out Wed Oct 29 15:40:02 2014
@@ -58,16 +58,46 @@ STAGE PLANS:
Stage: Stage-1
Spark
Edges:
- Reducer 2 <- Map 1 (GROUP PARTITION-LEVEL SORT, 1), Map 3 (GROUP PARTITION-LEVEL SORT, 1)
+ Reducer 2 <- Map 1 (GROUP PARTITION-LEVEL SORT, 1), Map 4 (GROUP PARTITION-LEVEL SORT, 1)
+ Reducer 6 <- Map 5 (GROUP PARTITION-LEVEL SORT, 1), Map 7 (GROUP PARTITION-LEVEL SORT, 1)
+ Union 3 <- Reducer 2 (NONE, 0), Reducer 6 (NONE, 0)
#### A masked pattern was here ####
Vertices:
Map 1
Map Operator Tree:
TableScan
+ alias: a
+ Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE
+ Filter Operator
+ predicate: (key is not null and (not (key = '2'))) (type: boolean)
+ Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+ Reduce Output Operator
+ key expressions: key (type: string)
+ sort order: +
+ Map-reduce partition columns: key (type: string)
+ Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+ value expressions: val (type: string)
+ Map 4
+ Map Operator Tree:
+ TableScan
+ alias: b
+ Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE
+ Filter Operator
+ predicate: (key is not null and (not (key = '2'))) (type: boolean)
+ Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+ Reduce Output Operator
+ key expressions: key (type: string)
+ sort order: +
+ Map-reduce partition columns: key (type: string)
+ Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+ value expressions: val (type: string)
+ Map 5
+ Map Operator Tree:
+ TableScan
alias: b
Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE
Filter Operator
- predicate: key is not null (type: boolean)
+ predicate: (key is not null and (key = '2')) (type: boolean)
Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
Reduce Output Operator
key expressions: key (type: string)
@@ -75,13 +105,13 @@ STAGE PLANS:
Map-reduce partition columns: key (type: string)
Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
value expressions: val (type: string)
- Map 3
+ Map 7
Map Operator Tree:
TableScan
alias: a
Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE
Filter Operator
- predicate: key is not null (type: boolean)
+ predicate: (key is not null and (key = '2')) (type: boolean)
Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
Reduce Output Operator
key expressions: key (type: string)
@@ -98,18 +128,39 @@ STAGE PLANS:
0 {KEY.reducesinkkey0} {VALUE._col0}
1 {KEY.reducesinkkey0} {VALUE._col0}
outputColumnNames: _col0, _col1, _col5, _col6
- Statistics: Num rows: 0 Data size: 0 Basic stats: NONE 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: 0 Data size: 0 Basic stats: NONE Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ Select Operator
+ SELECT * : (no compute)
+ File Output Operator
+ compressed: false
+ 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
+ Reducer 6
+ 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
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Select Operator
+ SELECT * : (no compute)
+ File Output Operator
+ compressed: false
+ 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
+ Union 3
+ Vertex: Union 3
Stage: Stage-0
Fetch Operator