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 2015/11/30 01:11:10 UTC
[13/91] [abbrv] [partial] hive git commit: HIVE-12017: Do not disable
CBO by default when number of joins in a query is equal or less than 1 (Jesus
Camacho Rodriguez, reviewed by Ashutosh Chauhan)
http://git-wip-us.apache.org/repos/asf/hive/blob/7dab21ac/ql/src/test/results/clientpositive/smb_mapjoin_25.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/smb_mapjoin_25.q.out b/ql/src/test/results/clientpositive/smb_mapjoin_25.q.out
index c0a8959..441338e 100644
--- a/ql/src/test/results/clientpositive/smb_mapjoin_25.q.out
+++ b/ql/src/test/results/clientpositive/smb_mapjoin_25.q.out
@@ -46,6 +46,9 @@ POSTHOOK: query: load data local inpath '../../data/files/smbbucket_3.rc' overwr
POSTHOOK: type: LOAD
#### A masked pattern was here ####
POSTHOOK: Output: default@smb_bucket_3
+Warning: Shuffle Join JOIN[27][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-2:MAPRED' is a cross product
+Warning: Shuffle Join JOIN[9][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product
+Warning: Shuffle Join JOIN[22][tables = [$hdt$_1, $hdt$_2]] in Stage 'Stage-4:MAPRED' is a cross product
PREHOOK: query: explain
select * from (select a.key from smb_bucket_1 a join smb_bucket_2 b on (a.key = b.key) where a.key = 5) t1 left outer join (select c.key from smb_bucket_2 c join smb_bucket_3 d on (c.key = d.key) where c.key=5) t2 on (t1.key=t2.key) where t2.key=5
PREHOOK: type: QUERY
@@ -68,123 +71,107 @@ STAGE PLANS:
Filter Operator
predicate: (key = 5) (type: boolean)
Statistics: Num rows: 26 Data size: 104 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: 5 (type: int)
- sort order: +
- Map-reduce partition columns: 5 (type: int)
+ Select Operator
Statistics: Num rows: 26 Data size: 104 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 26 Data size: 104 Basic stats: COMPLETE Column stats: NONE
TableScan
alias: b
Statistics: Num rows: 51 Data size: 206 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: (key = 5) (type: boolean)
+ predicate: (5 = key) (type: boolean)
Statistics: Num rows: 25 Data size: 100 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: 5 (type: int)
- sort order: +
- Map-reduce partition columns: 5 (type: int)
+ Select Operator
Statistics: Num rows: 25 Data size: 100 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 25 Data size: 100 Basic stats: COMPLETE Column stats: NONE
Reduce Operator Tree:
Join Operator
condition map:
Inner Join 0 to 1
keys:
- 0 key (type: int)
- 1 key (type: int)
+ 0
+ 1
Statistics: Num rows: 28 Data size: 114 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: 5 (type: int)
- outputColumnNames: _col0
- Statistics: Num rows: 28 Data size: 114 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+ File Output Operator
+ compressed: false
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
Stage: Stage-2
Map Reduce
Map Operator Tree:
TableScan
Reduce Output Operator
- key expressions: _col0 (type: int)
- sort order: +
- Map-reduce partition columns: _col0 (type: int)
+ sort order:
Statistics: Num rows: 28 Data size: 114 Basic stats: COMPLETE Column stats: NONE
TableScan
Reduce Output Operator
- key expressions: _col0 (type: int)
- sort order: +
- Map-reduce partition columns: _col0 (type: int)
+ sort order:
Statistics: Num rows: 29 Data size: 118 Basic stats: COMPLETE Column stats: NONE
Reduce Operator Tree:
Join Operator
condition map:
- Left Outer Join0 to 1
+ Inner Join 0 to 1
keys:
- 0 _col0 (type: int)
- 1 _col0 (type: int)
- outputColumnNames: _col0, _col1
+ 0
+ 1
Statistics: Num rows: 31 Data size: 129 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- predicate: (_col1 = 5) (type: boolean)
- Statistics: Num rows: 15 Data size: 62 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col0 (type: int), 5 (type: int)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 15 Data size: 62 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 15 Data size: 62 Basic stats: COMPLETE Column stats: NONE
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ Select Operator
+ expressions: 5 (type: int), 5 (type: int)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 31 Data size: 129 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 31 Data size: 129 Basic stats: COMPLETE Column stats: NONE
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
Stage: Stage-4
Map Reduce
Map Operator Tree:
TableScan
- alias: c
+ alias: b
Statistics: Num rows: 51 Data size: 206 Basic stats: COMPLETE Column stats: NONE
Filter Operator
predicate: (key = 5) (type: boolean)
Statistics: Num rows: 25 Data size: 100 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: 5 (type: int)
- sort order: +
- Map-reduce partition columns: 5 (type: int)
+ Select Operator
Statistics: Num rows: 25 Data size: 100 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 25 Data size: 100 Basic stats: COMPLETE Column stats: NONE
TableScan
alias: d
Statistics: Num rows: 55 Data size: 222 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: (key = 5) (type: boolean)
+ predicate: (5 = key) (type: boolean)
Statistics: Num rows: 27 Data size: 108 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: 5 (type: int)
- sort order: +
- Map-reduce partition columns: 5 (type: int)
+ Select Operator
Statistics: Num rows: 27 Data size: 108 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 27 Data size: 108 Basic stats: COMPLETE Column stats: NONE
Reduce Operator Tree:
Join Operator
condition map:
Inner Join 0 to 1
keys:
- 0 key (type: int)
- 1 key (type: int)
+ 0
+ 1
Statistics: Num rows: 29 Data size: 118 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: 5 (type: int)
- outputColumnNames: _col0
- Statistics: Num rows: 29 Data size: 118 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+ File Output Operator
+ compressed: false
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
Stage: Stage-0
Fetch Operator
@@ -192,6 +179,11 @@ STAGE PLANS:
Processor Tree:
ListSink
+Warning: Map Join MAPJOIN[56][bigTable=?] in task 'Stage-7:MAPRED' is a cross product
+Warning: Map Join MAPJOIN[48][bigTable=?] in task 'Stage-6:MAPRED' is a cross product
+Warning: Shuffle Join JOIN[27][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-2:MAPRED' is a cross product
+Warning: Map Join MAPJOIN[57][bigTable=?] in task 'Stage-9:MAPRED' is a cross product
+Warning: Map Join MAPJOIN[58][bigTable=?] in task 'Stage-10:MAPRED' is a cross product
PREHOOK: query: -- explain
-- select * from smb_bucket_1 a left outer join smb_bucket_2 b on a.key = b.key left outer join src c on a.key=c.value
@@ -209,11 +201,41 @@ explain
select * from (select a.key from smb_bucket_1 a join smb_bucket_2 b on (a.key = b.key) where a.key = 5) t1 left outer join (select c.key from smb_bucket_2 c join smb_bucket_3 d on (c.key = d.key) where c.key=5) t2 on (t1.key=t2.key) where t2.key=5
POSTHOOK: type: QUERY
STAGE DEPENDENCIES:
- Stage-1 is a root stage
- Stage-0 depends on stages: Stage-1
+ Stage-13 is a root stage
+ Stage-9 depends on stages: Stage-13
+ Stage-8 depends on stages: Stage-9, Stage-10 , consists of Stage-11, Stage-12, Stage-2
+ Stage-11 has a backup stage: Stage-2
+ Stage-6 depends on stages: Stage-11
+ Stage-12 has a backup stage: Stage-2
+ Stage-7 depends on stages: Stage-12
+ Stage-2
+ Stage-14 is a root stage
+ Stage-10 depends on stages: Stage-14
+ Stage-0 depends on stages: Stage-6, Stage-7, Stage-2
STAGE PLANS:
- Stage: Stage-1
+ Stage: Stage-13
+ Map Reduce Local Work
+ Alias -> Map Local Tables:
+ $hdt$_0:$hdt$_1:b
+ Fetch Operator
+ limit: -1
+ Alias -> Map Local Operator Tree:
+ $hdt$_0:$hdt$_1:b
+ TableScan
+ alias: b
+ Statistics: Num rows: 51 Data size: 206 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: (5 = key) (type: boolean)
+ Statistics: Num rows: 25 Data size: 100 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ Statistics: Num rows: 25 Data size: 100 Basic stats: COMPLETE Column stats: NONE
+ HashTable Sink Operator
+ keys:
+ 0
+ 1
+
+ Stage: Stage-9
Map Reduce
Map Operator Tree:
TableScan
@@ -222,57 +244,183 @@ STAGE PLANS:
Filter Operator
predicate: (key = 5) (type: boolean)
Statistics: Num rows: 26 Data size: 104 Basic stats: COMPLETE Column stats: NONE
- Sorted Merge Bucket Map Join Operator
- condition map:
- Inner Join 0 to 1
- keys:
- 0 5 (type: int)
- 1 5 (type: int)
- Select Operator
- expressions: 5 (type: int)
- outputColumnNames: _col0
- Reduce Output Operator
- key expressions: _col0 (type: int)
- sort order: +
- Map-reduce partition columns: _col0 (type: int)
+ Select Operator
+ Statistics: Num rows: 26 Data size: 104 Basic stats: COMPLETE Column stats: NONE
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0
+ 1
+ Statistics: Num rows: 28 Data size: 114 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+ Local Work:
+ Map Reduce Local Work
+
+ Stage: Stage-8
+ Conditional Operator
+
+ Stage: Stage-11
+ Map Reduce Local Work
+ Alias -> Map Local Tables:
+ $INTNAME1
+ Fetch Operator
+ limit: -1
+ Alias -> Map Local Operator Tree:
+ $INTNAME1
TableScan
- alias: c
- Statistics: Num rows: 51 Data size: 206 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- predicate: (key = 5) (type: boolean)
- Statistics: Num rows: 25 Data size: 100 Basic stats: COMPLETE Column stats: NONE
- Sorted Merge Bucket Map Join Operator
- condition map:
- Inner Join 0 to 1
- keys:
- 0 5 (type: int)
- 1 5 (type: int)
- Select Operator
- expressions: 5 (type: int)
- outputColumnNames: _col0
- Reduce Output Operator
- key expressions: _col0 (type: int)
- sort order: +
- Map-reduce partition columns: _col0 (type: int)
+ HashTable Sink Operator
+ keys:
+ 0
+ 1
+
+ Stage: Stage-6
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0
+ 1
+ Statistics: Num rows: 31 Data size: 129 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: 5 (type: int), 5 (type: int)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 31 Data size: 129 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 31 Data size: 129 Basic stats: COMPLETE Column stats: NONE
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ Local Work:
+ Map Reduce Local Work
+
+ Stage: Stage-12
+ Map Reduce Local Work
+ Alias -> Map Local Tables:
+ $INTNAME
+ Fetch Operator
+ limit: -1
+ Alias -> Map Local Operator Tree:
+ $INTNAME
+ TableScan
+ HashTable Sink Operator
+ keys:
+ 0
+ 1
+
+ Stage: Stage-7
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0
+ 1
+ Statistics: Num rows: 31 Data size: 129 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: 5 (type: int), 5 (type: int)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 31 Data size: 129 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 31 Data size: 129 Basic stats: COMPLETE Column stats: NONE
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ Local Work:
+ Map Reduce Local Work
+
+ Stage: Stage-2
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 28 Data size: 114 Basic stats: COMPLETE Column stats: NONE
+ TableScan
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 29 Data size: 118 Basic stats: COMPLETE Column stats: NONE
Reduce Operator Tree:
Join Operator
condition map:
- Left Outer Join0 to 1
+ Inner Join 0 to 1
keys:
- 0 _col0 (type: int)
- 1 _col0 (type: int)
- outputColumnNames: _col0, _col1
- Filter Operator
- predicate: (_col1 = 5) (type: boolean)
- Select Operator
- expressions: _col0 (type: int), 5 (type: int)
- outputColumnNames: _col0, _col1
- 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
+ 0
+ 1
+ Statistics: Num rows: 31 Data size: 129 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: 5 (type: int), 5 (type: int)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 31 Data size: 129 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 31 Data size: 129 Basic stats: COMPLETE Column stats: NONE
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ Stage: Stage-14
+ Map Reduce Local Work
+ Alias -> Map Local Tables:
+ $hdt$_1:$hdt$_1:$hdt$_1:b
+ Fetch Operator
+ limit: -1
+ Alias -> Map Local Operator Tree:
+ $hdt$_1:$hdt$_1:$hdt$_1:b
+ TableScan
+ alias: b
+ Statistics: Num rows: 51 Data size: 206 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: (key = 5) (type: boolean)
+ Statistics: Num rows: 25 Data size: 100 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ Statistics: Num rows: 25 Data size: 100 Basic stats: COMPLETE Column stats: NONE
+ HashTable Sink Operator
+ keys:
+ 0
+ 1
+
+ Stage: Stage-10
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ alias: d
+ Statistics: Num rows: 55 Data size: 222 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: (5 = key) (type: boolean)
+ Statistics: Num rows: 27 Data size: 108 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ Statistics: Num rows: 27 Data size: 108 Basic stats: COMPLETE Column stats: NONE
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0
+ 1
+ Statistics: Num rows: 29 Data size: 118 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+ Local Work:
+ Map Reduce Local Work
Stage: Stage-0
Fetch Operator
@@ -280,6 +428,11 @@ STAGE PLANS:
Processor Tree:
ListSink
+Warning: Map Join MAPJOIN[56][bigTable=?] in task 'Stage-7:MAPRED' is a cross product
+Warning: Map Join MAPJOIN[48][bigTable=?] in task 'Stage-6:MAPRED' is a cross product
+Warning: Shuffle Join JOIN[27][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-2:MAPRED' is a cross product
+Warning: Map Join MAPJOIN[57][bigTable=?] in task 'Stage-9:MAPRED' is a cross product
+Warning: Map Join MAPJOIN[58][bigTable=?] in task 'Stage-10:MAPRED' is a cross product
PREHOOK: query: select * from (select a.key from smb_bucket_1 a join smb_bucket_2 b on (a.key = b.key) where a.key = 5) t1 left outer join (select c.key from smb_bucket_2 c join smb_bucket_3 d on (c.key = d.key) where c.key=5) t2 on (t1.key=t2.key) where t2.key=5
PREHOOK: type: QUERY
PREHOOK: Input: default@smb_bucket_1
http://git-wip-us.apache.org/repos/asf/hive/blob/7dab21ac/ql/src/test/results/clientpositive/spark/auto_join1.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/auto_join1.q.out b/ql/src/test/results/clientpositive/spark/auto_join1.q.out
index d26a33e..31eebde 100644
--- a/ql/src/test/results/clientpositive/spark/auto_join1.q.out
+++ b/ql/src/test/results/clientpositive/spark/auto_join1.q.out
@@ -38,8 +38,8 @@ 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
Spark HashTable Sink Operator
keys:
@@ -61,8 +61,8 @@ 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
Map Join Operator
condition map:
@@ -70,12 +70,12 @@ STAGE PLANS:
keys:
0 _col0 (type: string)
1 _col0 (type: string)
- outputColumnNames: _col1, _col2
+ outputColumnNames: _col0, _col2
input vertices:
1 Map 2
Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
Select Operator
- expressions: UDFToInteger(_col2) (type: int), _col1 (type: string)
+ expressions: UDFToInteger(_col0) (type: int), _col2 (type: string)
outputColumnNames: _col0, _col1
Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
File Output Operator
http://git-wip-us.apache.org/repos/asf/hive/blob/7dab21ac/ql/src/test/results/clientpositive/spark/auto_join10.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/auto_join10.q.out b/ql/src/test/results/clientpositive/spark/auto_join10.q.out
index b43e55c..7e814d0 100644
--- a/ql/src/test/results/clientpositive/spark/auto_join10.q.out
+++ b/ql/src/test/results/clientpositive/spark/auto_join10.q.out
@@ -33,8 +33,8 @@ 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
Spark HashTable Sink Operator
keys:
@@ -58,8 +58,8 @@ 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
Map Join Operator
condition map:
@@ -67,12 +67,12 @@ STAGE PLANS:
keys:
0 _col0 (type: string)
1 _col0 (type: string)
- outputColumnNames: _col0, _col1
+ outputColumnNames: _col1, _col2
input vertices:
1 Map 3
Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
Select Operator
- expressions: hash(_col0,_col1) (type: int)
+ expressions: hash(_col1,_col2) (type: int)
outputColumnNames: _col0
Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
Group By Operator
http://git-wip-us.apache.org/repos/asf/hive/blob/7dab21ac/ql/src/test/results/clientpositive/spark/auto_join11.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/auto_join11.q.out b/ql/src/test/results/clientpositive/spark/auto_join11.q.out
index f8fc309..90e272c 100644
--- a/ql/src/test/results/clientpositive/spark/auto_join11.q.out
+++ b/ql/src/test/results/clientpositive/spark/auto_join11.q.out
@@ -33,8 +33,8 @@ STAGE PLANS:
predicate: (UDFToDouble(key) < 100.0) (type: boolean)
Statistics: Num rows: 166 Data size: 1763 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: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
Spark HashTable Sink Operator
keys:
@@ -58,8 +58,8 @@ STAGE PLANS:
predicate: (UDFToDouble(key) < 100.0) (type: boolean)
Statistics: Num rows: 166 Data size: 1763 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: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
Map Join Operator
condition map:
@@ -67,12 +67,12 @@ STAGE PLANS:
keys:
0 _col0 (type: string)
1 _col0 (type: string)
- outputColumnNames: _col1, _col2
+ outputColumnNames: _col0, _col2
input vertices:
1 Map 3
Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE
Select Operator
- expressions: hash(_col2,_col1) (type: int)
+ expressions: hash(_col0,_col2) (type: int)
outputColumnNames: _col0
Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE
Group By Operator
http://git-wip-us.apache.org/repos/asf/hive/blob/7dab21ac/ql/src/test/results/clientpositive/spark/auto_join14.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/auto_join14.q.out b/ql/src/test/results/clientpositive/spark/auto_join14.q.out
index 710a316..209eeeb 100644
--- a/ql/src/test/results/clientpositive/spark/auto_join14.q.out
+++ b/ql/src/test/results/clientpositive/spark/auto_join14.q.out
@@ -29,7 +29,7 @@ STAGE PLANS:
Spark
#### A masked pattern was here ####
Vertices:
- Map 2
+ Map 1
Map Operator Tree:
TableScan
alias: src
@@ -52,7 +52,7 @@ STAGE PLANS:
Spark
#### A masked pattern was here ####
Vertices:
- Map 1
+ Map 2
Map Operator Tree:
TableScan
alias: srcpart
@@ -70,12 +70,12 @@ STAGE PLANS:
keys:
0 _col0 (type: string)
1 _col0 (type: string)
- outputColumnNames: _col1, _col3
+ outputColumnNames: _col0, _col2
input vertices:
- 1 Map 2
+ 0 Map 1
Statistics: Num rows: 366 Data size: 3890 Basic stats: COMPLETE Column stats: NONE
Select Operator
- expressions: UDFToInteger(_col3) (type: int), _col1 (type: string)
+ expressions: UDFToInteger(_col0) (type: int), _col2 (type: string)
outputColumnNames: _col0, _col1
Statistics: Num rows: 366 Data size: 3890 Basic stats: COMPLETE Column stats: NONE
File Output Operator
http://git-wip-us.apache.org/repos/asf/hive/blob/7dab21ac/ql/src/test/results/clientpositive/spark/auto_join24.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/auto_join24.q.out b/ql/src/test/results/clientpositive/spark/auto_join24.q.out
index c714e19..9bc9b93 100644
--- a/ql/src/test/results/clientpositive/spark/auto_join24.q.out
+++ b/ql/src/test/results/clientpositive/spark/auto_join24.q.out
@@ -37,15 +37,19 @@ STAGE PLANS:
Map 3
Map Operator Tree:
TableScan
- alias: b
+ alias: a
Statistics: Num rows: 309 Data size: 1482 Basic stats: COMPLETE Column stats: NONE
Filter Operator
predicate: key is not null (type: boolean)
Statistics: Num rows: 155 Data size: 743 Basic stats: COMPLETE Column stats: NONE
- Spark HashTable Sink Operator
- keys:
- 0 key (type: string)
- 1 key (type: string)
+ Select Operator
+ expressions: key (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 155 Data size: 743 Basic stats: COMPLETE Column stats: NONE
+ Spark HashTable Sink Operator
+ keys:
+ 0 _col0 (type: string)
+ 1 _col0 (type: string)
Local Work:
Map Reduce Local Work
@@ -63,25 +67,29 @@ STAGE PLANS:
Filter Operator
predicate: key is not null (type: boolean)
Statistics: Num rows: 155 Data size: 743 Basic stats: COMPLETE Column stats: NONE
- Map Join Operator
- condition map:
- Inner Join 0 to 1
- keys:
- 0 key (type: string)
- 1 key (type: string)
- outputColumnNames: _col1
- input vertices:
- 1 Map 3
- Statistics: Num rows: 170 Data size: 817 Basic stats: COMPLETE Column stats: NONE
- Group By Operator
- aggregations: sum(_col1)
- mode: hash
- outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- sort order:
+ Select Operator
+ expressions: key (type: string), cnt (type: int)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 155 Data size: 743 Basic stats: COMPLETE Column stats: NONE
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col0 (type: string)
+ 1 _col0 (type: string)
+ outputColumnNames: _col1
+ input vertices:
+ 1 Map 3
+ Statistics: Num rows: 170 Data size: 817 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: sum(_col1)
+ mode: hash
+ outputColumnNames: _col0
Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col0 (type: bigint)
+ 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
http://git-wip-us.apache.org/repos/asf/hive/blob/7dab21ac/ql/src/test/results/clientpositive/spark/auto_join26.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/auto_join26.q.out b/ql/src/test/results/clientpositive/spark/auto_join26.q.out
index 3c437a1..71f4338 100644
--- a/ql/src/test/results/clientpositive/spark/auto_join26.q.out
+++ b/ql/src/test/results/clientpositive/spark/auto_join26.q.out
@@ -29,7 +29,7 @@ STAGE PLANS:
Spark
#### A masked pattern was here ####
Vertices:
- Map 3
+ Map 1
Map Operator Tree:
TableScan
alias: x
@@ -51,10 +51,10 @@ STAGE PLANS:
Stage: Stage-1
Spark
Edges:
- Reducer 2 <- Map 1 (GROUP, 2)
+ Reducer 3 <- Map 2 (GROUP, 2)
#### A masked pattern was here ####
Vertices:
- Map 1
+ Map 2
Map Operator Tree:
TableScan
alias: y
@@ -72,29 +72,25 @@ STAGE PLANS:
keys:
0 _col0 (type: string)
1 _col0 (type: string)
- outputColumnNames: _col1
+ outputColumnNames: _col0
input vertices:
- 1 Map 3
+ 0 Map 1
Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col1 (type: string)
- outputColumnNames: _col0
+ Group By Operator
+ aggregations: count(1)
+ keys: _col0 (type: string)
+ mode: hash
+ outputColumnNames: _col0, _col1
Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
- Group By Operator
- aggregations: count(1)
- keys: _col0 (type: string)
- mode: hash
- outputColumnNames: _col0, _col1
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: string)
- sort order: +
- Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col1 (type: bigint)
+ value expressions: _col1 (type: bigint)
Local Work:
Map Reduce Local Work
- Reducer 2
+ Reducer 3
Reduce Operator Tree:
Group By Operator
aggregations: count(VALUE._col0)
http://git-wip-us.apache.org/repos/asf/hive/blob/7dab21ac/ql/src/test/results/clientpositive/spark/auto_join32.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/auto_join32.q.out b/ql/src/test/results/clientpositive/spark/auto_join32.q.out
index 679dd79..2dd6cc1 100644
--- a/ql/src/test/results/clientpositive/spark/auto_join32.q.out
+++ b/ql/src/test/results/clientpositive/spark/auto_join32.q.out
@@ -44,10 +44,14 @@ STAGE PLANS:
Filter Operator
predicate: name is not null (type: boolean)
Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
- Spark HashTable Sink Operator
- keys:
- 0 name (type: string)
- 1 name (type: string)
+ Select Operator
+ expressions: name (type: string), registration (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
+ Spark HashTable Sink Operator
+ keys:
+ 0 _col0 (type: string)
+ 1 _col0 (type: string)
Local Work:
Map Reduce Local Work
@@ -65,44 +69,52 @@ STAGE PLANS:
Filter Operator
predicate: name is not null (type: boolean)
Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
- Map Join Operator
- condition map:
- Inner Join 0 to 1
- keys:
- 0 name (type: string)
- 1 name (type: string)
- outputColumnNames: _col0, _col8
- input vertices:
- 1 Map 3
+ Select Operator
+ expressions: name (type: string)
+ outputColumnNames: _col0
Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
- Group By Operator
- aggregations: count(DISTINCT _col8)
- keys: _col0 (type: string), _col8 (type: string)
- mode: hash
- outputColumnNames: _col0, _col1, _col2
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col0 (type: string)
+ 1 _col0 (type: string)
+ outputColumnNames: _col0, _col2
+ input vertices:
+ 1 Map 3
Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: string), _col1 (type: string)
- sort order: ++
- Map-reduce partition columns: _col0 (type: string)
+ Group By Operator
+ keys: _col0 (type: string), _col2 (type: string)
+ mode: hash
+ outputColumnNames: _col0, _col1
Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: string), _col1 (type: string)
+ sort order: ++
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
Local Work:
Map Reduce Local Work
Reducer 2
Reduce Operator Tree:
Group By Operator
- aggregations: count(DISTINCT KEY._col1:0._col0)
- keys: KEY._col0 (type: string)
+ keys: KEY._col0 (type: string), KEY._col1 (type: string)
mode: mergepartial
outputColumnNames: _col0, _col1
Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
- File Output Operator
- compressed: false
+ Group By Operator
+ aggregations: count(_col1)
+ keys: _col0 (type: string)
+ mode: complete
+ outputColumnNames: _col0, _col1
Statistics: Num rows: 1 Data size: 0 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
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 0 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
Stage: Stage-0
Fetch Operator
@@ -173,40 +185,48 @@ STAGE PLANS:
Filter Operator
predicate: name is not null (type: boolean)
Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
- Sorted Merge Bucket Map Join Operator
- condition map:
- Inner Join 0 to 1
- keys:
- 0 name (type: string)
- 1 name (type: string)
- outputColumnNames: _col0, _col8
+ Select Operator
+ expressions: name (type: string)
+ outputColumnNames: _col0
Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
- Group By Operator
- aggregations: count(DISTINCT _col8)
- keys: _col0 (type: string), _col8 (type: string)
- mode: hash
- outputColumnNames: _col0, _col1, _col2
+ Sorted Merge Bucket Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col0 (type: string)
+ 1 _col0 (type: string)
+ outputColumnNames: _col0, _col2
Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: string), _col1 (type: string)
- sort order: ++
- Map-reduce partition columns: _col0 (type: string)
+ Group By Operator
+ keys: _col0 (type: string), _col2 (type: string)
+ mode: hash
+ outputColumnNames: _col0, _col1
Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: string), _col1 (type: string)
+ sort order: ++
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
Reducer 2
Reduce Operator Tree:
Group By Operator
- aggregations: count(DISTINCT KEY._col1:0._col0)
- keys: KEY._col0 (type: string)
+ keys: KEY._col0 (type: string), KEY._col1 (type: string)
mode: mergepartial
outputColumnNames: _col0, _col1
Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
- File Output Operator
- compressed: false
+ Group By Operator
+ aggregations: count(_col1)
+ keys: _col0 (type: string)
+ mode: complete
+ outputColumnNames: _col0, _col1
Statistics: Num rows: 1 Data size: 0 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
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 0 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
Stage: Stage-0
Fetch Operator
@@ -291,40 +311,48 @@ STAGE PLANS:
Filter Operator
predicate: name is not null (type: boolean)
Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
- Sorted Merge Bucket Map Join Operator
- condition map:
- Inner Join 0 to 1
- keys:
- 0 name (type: string)
- 1 name (type: string)
- outputColumnNames: _col0, _col8
+ Select Operator
+ expressions: name (type: string)
+ outputColumnNames: _col0
Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
- Group By Operator
- aggregations: count(DISTINCT _col8)
- keys: _col0 (type: string), _col8 (type: string)
- mode: hash
- outputColumnNames: _col0, _col1, _col2
+ Sorted Merge Bucket Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col0 (type: string)
+ 1 _col0 (type: string)
+ outputColumnNames: _col0, _col2
Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: string), _col1 (type: string)
- sort order: ++
- Map-reduce partition columns: _col0 (type: string)
+ Group By Operator
+ keys: _col0 (type: string), _col2 (type: string)
+ mode: hash
+ outputColumnNames: _col0, _col1
Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: string), _col1 (type: string)
+ sort order: ++
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
Reducer 2
Reduce Operator Tree:
Group By Operator
- aggregations: count(DISTINCT KEY._col1:0._col0)
- keys: KEY._col0 (type: string)
+ keys: KEY._col0 (type: string), KEY._col1 (type: string)
mode: mergepartial
outputColumnNames: _col0, _col1
Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
- File Output Operator
- compressed: false
+ Group By Operator
+ aggregations: count(_col1)
+ keys: _col0 (type: string)
+ mode: complete
+ outputColumnNames: _col0, _col1
Statistics: Num rows: 1 Data size: 0 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
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 0 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
Stage: Stage-0
Fetch Operator
@@ -422,21 +450,20 @@ STAGE PLANS:
Stage: Stage-1
Spark
Edges:
- Reducer 2 <- Map 1 (GROUP, 2)
- Reducer 3 <- Reducer 2 (GROUP, 2)
+ Reducer 2 <- Map 1 (GROUP PARTITION-LEVEL SORT, 2)
#### A masked pattern was here ####
Vertices:
Map 1
Map Operator Tree:
TableScan
- alias: v
+ alias: s
Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
Filter Operator
predicate: ((p = 'bar') and name is not null) (type: boolean)
Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
Select Operator
- expressions: name (type: string), registration (type: string)
- outputColumnNames: _col0, _col1
+ expressions: name (type: string)
+ outputColumnNames: _col0
Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
Sorted Merge Bucket Map Join Operator
condition map:
@@ -444,17 +471,17 @@ STAGE PLANS:
keys:
0 _col0 (type: string)
1 _col0 (type: string)
- outputColumnNames: _col1, _col3
+ outputColumnNames: _col0, _col3
Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
Group By Operator
- keys: _col1 (type: string), _col3 (type: string)
+ keys: _col0 (type: string), _col3 (type: string)
mode: hash
outputColumnNames: _col0, _col1
Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: string), _col1 (type: string)
sort order: ++
- Map-reduce partition columns: _col0 (type: string), _col1 (type: string)
+ Map-reduce partition columns: _col0 (type: string)
Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
Reducer 2
Reduce Operator Tree:
@@ -464,32 +491,18 @@ STAGE PLANS:
outputColumnNames: _col0, _col1
Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
Group By Operator
- aggregations: count(_col0)
- keys: _col1 (type: string)
- mode: hash
+ aggregations: count(_col1)
+ keys: _col0 (type: string)
+ mode: complete
outputColumnNames: _col0, _col1
Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: string)
- sort order: +
- Map-reduce partition columns: _col0 (type: string)
+ File Output Operator
+ compressed: false
Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
- value expressions: _col1 (type: bigint)
- Reducer 3
- Reduce Operator Tree:
- Group By Operator
- aggregations: count(VALUE._col0)
- keys: KEY._col0 (type: string)
- mode: mergepartial
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 1 Data size: 0 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
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
Stage: Stage-0
Fetch Operator
http://git-wip-us.apache.org/repos/asf/hive/blob/7dab21ac/ql/src/test/results/clientpositive/spark/auto_join_filters.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/auto_join_filters.q.out b/ql/src/test/results/clientpositive/spark/auto_join_filters.q.out
index b6b89c1..601b27d 100644
--- a/ql/src/test/results/clientpositive/spark/auto_join_filters.q.out
+++ b/ql/src/test/results/clientpositive/spark/auto_join_filters.q.out
@@ -14,7 +14,7 @@ POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/in3.txt' INTO TABLE my
POSTHOOK: type: LOAD
#### A masked pattern was here ####
POSTHOOK: Output: default@myinput1
-Warning: Map Join MAPJOIN[19][bigTable=?] in task 'Stage-1:MAPRED' is a cross product
+Warning: Map Join MAPJOIN[20][bigTable=?] in task 'Stage-1:MAPRED' is a cross product
PREHOOK: query: SELECT sum(hash(a.key,a.value,b.key,b.value)) FROM myinput1 a JOIN myinput1 b on a.key > 40 AND a.value > 50 AND a.key = a.value AND b.key > 40 AND b.value > 50 AND b.key = b.value
PREHOOK: type: QUERY
PREHOOK: Input: default@myinput1
@@ -24,7 +24,7 @@ POSTHOOK: type: QUERY
POSTHOOK: Input: default@myinput1
#### A masked pattern was here ####
3078400
-Warning: Map Join MAPJOIN[15][bigTable=a] in task 'Stage-1:MAPRED' is a cross product
+Warning: Map Join MAPJOIN[16][bigTable=?] in task 'Stage-1:MAPRED' is a cross product
PREHOOK: query: SELECT sum(hash(a.key,a.value,b.key,b.value)) FROM myinput1 a LEFT OUTER JOIN myinput1 b on a.key > 40 AND a.value > 50 AND a.key = a.value AND b.key > 40 AND b.value > 50 AND b.key = b.value
PREHOOK: type: QUERY
PREHOOK: Input: default@myinput1
@@ -34,7 +34,7 @@ POSTHOOK: type: QUERY
POSTHOOK: Input: default@myinput1
#### A masked pattern was here ####
4937935
-Warning: Map Join MAPJOIN[15][bigTable=b] in task 'Stage-1:MAPRED' is a cross product
+Warning: Map Join MAPJOIN[16][bigTable=?] in task 'Stage-1:MAPRED' is a cross product
PREHOOK: query: SELECT sum(hash(a.key,a.value,b.key,b.value)) FROM myinput1 a RIGHT OUTER JOIN myinput1 b on a.key > 40 AND a.value > 50 AND a.key = a.value AND b.key > 40 AND b.value > 50 AND b.key = b.value
PREHOOK: type: QUERY
PREHOOK: Input: default@myinput1
@@ -300,7 +300,7 @@ POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/in2.txt' into table sm
POSTHOOK: type: LOAD
#### A masked pattern was here ####
POSTHOOK: Output: default@smb_input2
-Warning: Map Join MAPJOIN[19][bigTable=?] in task 'Stage-1:MAPRED' is a cross product
+Warning: Map Join MAPJOIN[20][bigTable=?] in task 'Stage-1:MAPRED' is a cross product
PREHOOK: query: SELECT sum(hash(a.key,a.value,b.key,b.value)) FROM myinput1 a JOIN myinput1 b on a.key > 40 AND a.value > 50 AND a.key = a.value AND b.key > 40 AND b.value > 50 AND b.key = b.value
PREHOOK: type: QUERY
PREHOOK: Input: default@myinput1
@@ -310,7 +310,7 @@ POSTHOOK: type: QUERY
POSTHOOK: Input: default@myinput1
#### A masked pattern was here ####
3078400
-Warning: Map Join MAPJOIN[19][bigTable=?] in task 'Stage-1:MAPRED' is a cross product
+Warning: Map Join MAPJOIN[20][bigTable=?] in task 'Stage-1:MAPRED' is a cross product
PREHOOK: query: SELECT sum(hash(a.key,a.value,b.key,b.value)) FROM myinput1 a LEFT OUTER JOIN myinput1 b on a.key > 40 AND a.value > 50 AND a.key = a.value AND b.key > 40 AND b.value > 50 AND b.key = b.value
PREHOOK: type: QUERY
PREHOOK: Input: default@myinput1
@@ -320,7 +320,7 @@ POSTHOOK: type: QUERY
POSTHOOK: Input: default@myinput1
#### A masked pattern was here ####
3078400
-Warning: Map Join MAPJOIN[19][bigTable=?] in task 'Stage-1:MAPRED' is a cross product
+Warning: Map Join MAPJOIN[20][bigTable=?] in task 'Stage-1:MAPRED' is a cross product
PREHOOK: query: SELECT sum(hash(a.key,a.value,b.key,b.value)) FROM myinput1 a RIGHT OUTER JOIN myinput1 b on a.key > 40 AND a.value > 50 AND a.key = a.value AND b.key > 40 AND b.value > 50 AND b.key = b.value
PREHOOK: type: QUERY
PREHOOK: Input: default@myinput1
http://git-wip-us.apache.org/repos/asf/hive/blob/7dab21ac/ql/src/test/results/clientpositive/spark/auto_join_nulls.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/auto_join_nulls.q.out b/ql/src/test/results/clientpositive/spark/auto_join_nulls.q.out
index 4b809ce..0024b24 100644
--- a/ql/src/test/results/clientpositive/spark/auto_join_nulls.q.out
+++ b/ql/src/test/results/clientpositive/spark/auto_join_nulls.q.out
@@ -34,7 +34,7 @@ POSTHOOK: type: QUERY
POSTHOOK: Input: default@myinput1
#### A masked pattern was here ####
13630578
-Warning: Map Join MAPJOIN[15][bigTable=?] in task 'Stage-1:MAPRED' is a cross product
+Warning: Map Join MAPJOIN[14][bigTable=?] in task 'Stage-1:MAPRED' is a cross product
PREHOOK: query: SELECT sum(hash(a.key,a.value,b.key,b.value)) FROM myinput1 a RIGHT OUTER JOIN myinput1 b
PREHOOK: type: QUERY
PREHOOK: Input: default@myinput1
http://git-wip-us.apache.org/repos/asf/hive/blob/7dab21ac/ql/src/test/results/clientpositive/spark/auto_join_reordering_values.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/auto_join_reordering_values.q.out b/ql/src/test/results/clientpositive/spark/auto_join_reordering_values.q.out
index 9df55b9..6466c39 100644
--- a/ql/src/test/results/clientpositive/spark/auto_join_reordering_values.q.out
+++ b/ql/src/test/results/clientpositive/spark/auto_join_reordering_values.q.out
@@ -191,14 +191,18 @@ STAGE PLANS:
isSamplingPred: false
predicate: (((date is not null and dealid is not null) and cityid is not null) and userid is not null) (type: boolean)
Statistics: Num rows: 1 Data size: 36 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: date (type: string)
- sort order: +
- Map-reduce partition columns: date (type: string)
+ Select Operator
+ expressions: dealid (type: int), date (type: string), cityid (type: int), userid (type: int)
+ outputColumnNames: _col0, _col1, _col2, _col3
Statistics: Num rows: 1 Data size: 36 Basic stats: COMPLETE Column stats: NONE
- tag: 0
- value expressions: dealid (type: int), cityid (type: int), userid (type: int)
- auto parallelism: false
+ Reduce Output Operator
+ key expressions: _col1 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col1 (type: string)
+ Statistics: Num rows: 1 Data size: 36 Basic stats: COMPLETE Column stats: NONE
+ tag: 0
+ value expressions: _col0 (type: int), _col2 (type: int), _col3 (type: int)
+ auto parallelism: false
Path -> Alias:
#### A masked pattern was here ####
Path -> Partition:
@@ -251,20 +255,24 @@ STAGE PLANS:
Map 6
Map Operator Tree:
TableScan
- alias: dim_pay_date
+ alias: orderpayment
Statistics: Num rows: 1 Data size: 36 Basic stats: COMPLETE Column stats: NONE
GatherStats: false
Filter Operator
isSamplingPred: false
predicate: date is not null (type: boolean)
Statistics: Num rows: 1 Data size: 36 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: date (type: string)
- sort order: +
- Map-reduce partition columns: date (type: string)
+ Select Operator
+ expressions: date (type: string)
+ outputColumnNames: _col0
Statistics: Num rows: 1 Data size: 36 Basic stats: COMPLETE Column stats: NONE
- tag: 1
- auto parallelism: false
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 1 Data size: 36 Basic stats: COMPLETE Column stats: NONE
+ tag: 1
+ auto parallelism: false
Path -> Alias:
#### A masked pattern was here ####
Path -> Partition:
@@ -313,24 +321,28 @@ STAGE PLANS:
name: default.orderpayment_small
name: default.orderpayment_small
Truncated Path -> Alias:
- /orderpayment_small [dim_pay_date]
+ /orderpayment_small [orderpayment]
Map 7
Map Operator Tree:
TableScan
- alias: deal
+ alias: orderpayment
Statistics: Num rows: 1 Data size: 36 Basic stats: COMPLETE Column stats: NONE
GatherStats: false
Filter Operator
isSamplingPred: false
predicate: dealid is not null (type: boolean)
Statistics: Num rows: 1 Data size: 36 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: dealid (type: int)
- sort order: +
- Map-reduce partition columns: dealid (type: int)
+ Select Operator
+ expressions: dealid (type: int)
+ outputColumnNames: _col0
Statistics: Num rows: 1 Data size: 36 Basic stats: COMPLETE Column stats: NONE
- tag: 1
- auto parallelism: false
+ Reduce Output Operator
+ key expressions: _col0 (type: int)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: int)
+ Statistics: Num rows: 1 Data size: 36 Basic stats: COMPLETE Column stats: NONE
+ tag: 1
+ auto parallelism: false
Path -> Alias:
#### A masked pattern was here ####
Path -> Partition:
@@ -379,24 +391,28 @@ STAGE PLANS:
name: default.orderpayment_small
name: default.orderpayment_small
Truncated Path -> Alias:
- /orderpayment_small [deal]
+ /orderpayment_small [orderpayment]
Map 8
Map Operator Tree:
TableScan
- alias: order_city
+ alias: orderpayment
Statistics: Num rows: 1 Data size: 36 Basic stats: COMPLETE Column stats: NONE
GatherStats: false
Filter Operator
isSamplingPred: false
predicate: cityid is not null (type: boolean)
Statistics: Num rows: 1 Data size: 36 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: cityid (type: int)
- sort order: +
- Map-reduce partition columns: cityid (type: int)
+ Select Operator
+ expressions: cityid (type: int)
+ outputColumnNames: _col0
Statistics: Num rows: 1 Data size: 36 Basic stats: COMPLETE Column stats: NONE
- tag: 1
- auto parallelism: false
+ Reduce Output Operator
+ key expressions: _col0 (type: int)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: int)
+ Statistics: Num rows: 1 Data size: 36 Basic stats: COMPLETE Column stats: NONE
+ tag: 1
+ auto parallelism: false
Path -> Alias:
#### A masked pattern was here ####
Path -> Partition:
@@ -445,7 +461,7 @@ STAGE PLANS:
name: default.orderpayment_small
name: default.orderpayment_small
Truncated Path -> Alias:
- /orderpayment_small [order_city]
+ /orderpayment_small [orderpayment]
Map 9
Map Operator Tree:
TableScan
@@ -456,13 +472,17 @@ STAGE PLANS:
isSamplingPred: false
predicate: userid is not null (type: boolean)
Statistics: Num rows: 50 Data size: 144 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: userid (type: int)
- sort order: +
- Map-reduce partition columns: userid (type: int)
+ Select Operator
+ expressions: userid (type: int)
+ outputColumnNames: _col0
Statistics: Num rows: 50 Data size: 144 Basic stats: COMPLETE Column stats: NONE
- tag: 1
- auto parallelism: false
+ Reduce Output Operator
+ key expressions: _col0 (type: int)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: int)
+ Statistics: Num rows: 50 Data size: 144 Basic stats: COMPLETE Column stats: NONE
+ tag: 1
+ auto parallelism: false
Path -> Alias:
#### A masked pattern was here ####
Path -> Partition:
@@ -519,9 +539,9 @@ STAGE PLANS:
condition map:
Inner Join 0 to 1
keys:
- 0 date (type: string)
- 1 date (type: string)
- outputColumnNames: _col0, _col3, _col4, _col9
+ 0 _col1 (type: string)
+ 1 _col0 (type: string)
+ outputColumnNames: _col0, _col2, _col3, _col4
Statistics: Num rows: 1 Data size: 39 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: int)
@@ -529,7 +549,7 @@ STAGE PLANS:
Map-reduce partition columns: _col0 (type: int)
Statistics: Num rows: 1 Data size: 39 Basic stats: COMPLETE Column stats: NONE
tag: 0
- value expressions: _col3 (type: int), _col4 (type: int), _col9 (type: string)
+ value expressions: _col2 (type: int), _col3 (type: int), _col4 (type: string)
auto parallelism: false
Reducer 3
Needs Tagging: true
@@ -539,16 +559,16 @@ STAGE PLANS:
Inner Join 0 to 1
keys:
0 _col0 (type: int)
- 1 dealid (type: int)
- outputColumnNames: _col3, _col4, _col9, _col16
+ 1 _col0 (type: int)
+ outputColumnNames: _col2, _col3, _col4, _col5
Statistics: Num rows: 1 Data size: 42 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
- key expressions: _col3 (type: int)
+ key expressions: _col2 (type: int)
sort order: +
- Map-reduce partition columns: _col3 (type: int)
+ Map-reduce partition columns: _col2 (type: int)
Statistics: Num rows: 1 Data size: 42 Basic stats: COMPLETE Column stats: NONE
tag: 0
- value expressions: _col4 (type: int), _col9 (type: string), _col16 (type: int)
+ value expressions: _col3 (type: int), _col4 (type: string), _col5 (type: int)
auto parallelism: false
Reducer 4
Needs Tagging: true
@@ -557,17 +577,17 @@ STAGE PLANS:
condition map:
Inner Join 0 to 1
keys:
- 0 _col3 (type: int)
- 1 cityid (type: int)
- outputColumnNames: _col4, _col9, _col16
+ 0 _col2 (type: int)
+ 1 _col0 (type: int)
+ outputColumnNames: _col3, _col4, _col5
Statistics: Num rows: 1 Data size: 46 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
- key expressions: _col4 (type: int)
+ key expressions: _col3 (type: int)
sort order: +
- Map-reduce partition columns: _col4 (type: int)
+ Map-reduce partition columns: _col3 (type: int)
Statistics: Num rows: 1 Data size: 46 Basic stats: COMPLETE Column stats: NONE
tag: 0
- value expressions: _col9 (type: string), _col16 (type: int)
+ value expressions: _col4 (type: string), _col5 (type: int)
auto parallelism: false
Reducer 5
Needs Tagging: true
@@ -576,12 +596,12 @@ STAGE PLANS:
condition map:
Inner Join 0 to 1
keys:
- 0 _col4 (type: int)
- 1 userid (type: int)
- outputColumnNames: _col9, _col16
+ 0 _col3 (type: int)
+ 1 _col0 (type: int)
+ outputColumnNames: _col4, _col5
Statistics: Num rows: 55 Data size: 158 Basic stats: COMPLETE Column stats: NONE
Select Operator
- expressions: _col9 (type: string), _col16 (type: int)
+ expressions: _col4 (type: string), _col5 (type: int)
outputColumnNames: _col0, _col1
Statistics: Num rows: 55 Data size: 158 Basic stats: COMPLETE Column stats: NONE
Limit