You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@hive.apache.org by se...@apache.org on 2015/07/02 03:49:27 UTC
[22/25] hive git commit: HIVE-11152 : Swapping join inputs in
ASTConverter (Jesus Camacho Rodriguez via John Pullokkaran)
http://git-wip-us.apache.org/repos/asf/hive/blob/6eaa32c8/ql/src/test/results/clientpositive/join_cond_pushdown_3.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/join_cond_pushdown_3.q.out b/ql/src/test/results/clientpositive/join_cond_pushdown_3.q.out
index c098105..9077fc0 100644
--- a/ql/src/test/results/clientpositive/join_cond_pushdown_3.q.out
+++ b/ql/src/test/results/clientpositive/join_cond_pushdown_3.q.out
@@ -287,7 +287,7 @@ STAGE PLANS:
Processor Tree:
ListSink
-Warning: Shuffle Join JOIN[16][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product
+Warning: Shuffle Join JOIN[15][tables = [$hdt$_1, $hdt$_2, $hdt$_0]] in Stage 'Stage-2:MAPRED' is a cross product
PREHOOK: query: explain select *
from part p1 join part p2 join part p3
where p2.p_partkey = 1 and p3.p_name = p2.p_name
@@ -297,12 +297,12 @@ from part p1 join part p2 join part p3
where p2.p_partkey = 1 and p3.p_name = p2.p_name
POSTHOOK: type: QUERY
STAGE DEPENDENCIES:
- Stage-2 is a root stage
- Stage-1 depends on stages: Stage-2
- Stage-0 depends on stages: Stage-1
+ Stage-1 is a root stage
+ Stage-2 depends on stages: Stage-1
+ Stage-0 depends on stages: Stage-2
STAGE PLANS:
- Stage: Stage-2
+ Stage: Stage-1
Map Reduce
Map Operator Tree:
TableScan
@@ -346,21 +346,22 @@ STAGE PLANS:
1 _col1 (type: string)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17
Statistics: Num rows: 14 Data size: 1730 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col0 (type: int), _col1 (type: string), _col10 (type: string), _col11 (type: string), _col12 (type: string), _col13 (type: string), _col14 (type: int), _col15 (type: string), _col16 (type: double), _col17 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string)
- outputColumnNames: _col0, _col1, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col2, _col3, _col4, _col5, _col6, _col7, _col8
- Statistics: Num rows: 14 Data size: 1730 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-1
+ Stage: Stage-2
Map Reduce
Map Operator Tree:
TableScan
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 14 Data size: 1730 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string), _col10 (type: string), _col11 (type: string), _col12 (type: string), _col13 (type: string), _col14 (type: int), _col15 (type: string), _col16 (type: double), _col17 (type: string)
+ TableScan
alias: p1
Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
Select Operator
@@ -371,11 +372,6 @@ STAGE PLANS:
sort order:
Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string)
- TableScan
- Reduce Output Operator
- sort order:
- Statistics: Num rows: 14 Data size: 1730 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string), _col10 (type: string), _col11 (type: string), _col12 (type: string), _col13 (type: string), _col14 (type: int), _col15 (type: string), _col16 (type: double), _col17 (type: string)
Reduce Operator Tree:
Join Operator
condition map:
@@ -383,10 +379,10 @@ STAGE PLANS:
keys:
0
1
- outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col19, _col20, _col21, _col22, _col23, _col24, _col25, _col26
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25, _col26
Statistics: Num rows: 28 Data size: 3461 Basic stats: COMPLETE Column stats: NONE
Select Operator
- expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string), 1 (type: int), _col19 (type: string), _col20 (type: string), _col21 (type: string), _col22 (type: string), _col23 (type: int), _col24 (type: string), _col25 (type: double), _col26 (type: string), _col9 (type: int), _col10 (type: string), _col11 (type: string), _col12 (type: string), _col13 (type: string), _col14 (type: int), _col15 (type: string), _col16 (type: double), _col17 (type: string)
+ expressions: _col18 (type: int), _col19 (type: string), _col20 (type: string), _col21 (type: string), _col22 (type: string), _col23 (type: int), _col24 (type: string), _col25 (type: double), _col26 (type: string), 1 (type: int), _col10 (type: string), _col11 (type: string), _col12 (type: string), _col13 (type: string), _col14 (type: int), _col15 (type: string), _col16 (type: double), _col17 (type: string), _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25, _col26
Statistics: Num rows: 28 Data size: 3461 Basic stats: COMPLETE Column stats: NONE
File Output Operator
http://git-wip-us.apache.org/repos/asf/hive/blob/6eaa32c8/ql/src/test/results/clientpositive/join_cond_pushdown_4.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/join_cond_pushdown_4.q.out b/ql/src/test/results/clientpositive/join_cond_pushdown_4.q.out
index a1dd24e..55e7678 100644
--- a/ql/src/test/results/clientpositive/join_cond_pushdown_4.q.out
+++ b/ql/src/test/results/clientpositive/join_cond_pushdown_4.q.out
@@ -145,13 +145,13 @@ where p2.p_name = p3.p_name and p1.p_partkey = p4.p_partkey
and p1.p_partkey = p2.p_partkey
POSTHOOK: type: QUERY
STAGE DEPENDENCIES:
- Stage-3 is a root stage
- Stage-2 depends on stages: Stage-3
- Stage-1 depends on stages: Stage-2
- Stage-0 depends on stages: Stage-1
+ Stage-1 is a root stage
+ Stage-2 depends on stages: Stage-1
+ Stage-3 depends on stages: Stage-2
+ Stage-0 depends on stages: Stage-3
STAGE PLANS:
- Stage: Stage-3
+ Stage: Stage-1
Map Reduce
Map Operator Tree:
TableScan
@@ -206,6 +206,13 @@ STAGE PLANS:
Map Reduce
Map Operator Tree:
TableScan
+ Reduce Output Operator
+ key expressions: _col10 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col10 (type: string)
+ Statistics: Num rows: 7 Data size: 931 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string), _col9 (type: int), _col11 (type: string), _col12 (type: string), _col13 (type: string), _col14 (type: int), _col15 (type: string), _col16 (type: double), _col17 (type: string)
+ TableScan
alias: p1
Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
Filter Operator
@@ -221,20 +228,13 @@ STAGE PLANS:
Map-reduce partition columns: _col1 (type: string)
Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE
value expressions: _col0 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string)
- TableScan
- Reduce Output Operator
- key expressions: _col10 (type: string)
- sort order: +
- Map-reduce partition columns: _col10 (type: string)
- Statistics: Num rows: 7 Data size: 931 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string), _col9 (type: int), _col11 (type: string), _col12 (type: string), _col13 (type: string), _col14 (type: int), _col15 (type: string), _col16 (type: double), _col17 (type: string)
Reduce Operator Tree:
Join Operator
condition map:
Inner Join 0 to 1
keys:
- 0 _col1 (type: string)
- 1 _col10 (type: string)
+ 0 _col10 (type: string)
+ 1 _col1 (type: string)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25, _col26
Statistics: Num rows: 14 Data size: 1730 Basic stats: COMPLETE Column stats: NONE
File Output Operator
@@ -244,10 +244,17 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
- Stage: Stage-1
+ Stage: Stage-3
Map Reduce
Map Operator Tree:
TableScan
+ Reduce Output Operator
+ key expressions: _col0 (type: int)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: int)
+ Statistics: Num rows: 14 Data size: 1730 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string), _col9 (type: int), _col10 (type: string), _col11 (type: string), _col12 (type: string), _col13 (type: string), _col14 (type: int), _col15 (type: string), _col16 (type: double), _col17 (type: string), _col18 (type: int), _col19 (type: string), _col20 (type: string), _col21 (type: string), _col22 (type: string), _col23 (type: int), _col24 (type: string), _col25 (type: double), _col26 (type: string)
+ TableScan
alias: p1
Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
Filter Operator
@@ -263,33 +270,22 @@ STAGE PLANS:
Map-reduce partition columns: _col0 (type: int)
Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string)
- TableScan
- Reduce Output Operator
- key expressions: _col9 (type: int)
- sort order: +
- Map-reduce partition columns: _col9 (type: int)
- Statistics: Num rows: 14 Data size: 1730 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string), _col10 (type: string), _col11 (type: string), _col12 (type: string), _col13 (type: string), _col14 (type: int), _col15 (type: string), _col16 (type: double), _col17 (type: string), _col18 (type: int), _col19 (type: string), _col20 (type: string), _col21 (type: string), _col22 (type: string), _col23 (type: int), _col24 (type: string), _col25 (type: double), _col26 (type: string)
Reduce Operator Tree:
Join Operator
condition map:
Inner Join 0 to 1
keys:
0 _col0 (type: int)
- 1 _col9 (type: int)
+ 1 _col0 (type: int)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25, _col26, _col27, _col28, _col29, _col30, _col31, _col32, _col33, _col34, _col35
Statistics: Num rows: 15 Data size: 1903 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col18 (type: int), _col19 (type: string), _col20 (type: string), _col21 (type: string), _col22 (type: string), _col23 (type: int), _col24 (type: string), _col25 (type: double), _col26 (type: string), _col27 (type: int), _col28 (type: string), _col29 (type: string), _col30 (type: string), _col31 (type: string), _col32 (type: int), _col33 (type: string), _col34 (type: double), _col35 (type: string), _col9 (type: int), _col10 (type: string), _col11 (type: string), _col12 (type: string), _col13 (type: string), _col14 (type: int), _col15 (type: string), _col16 (type: double), _col17 (type: string), _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string)
- outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25, _col26, _col27, _col28, _col29, _col30, _col31, _col32, _col33, _col34, _col35
+ File Output Operator
+ compressed: false
Statistics: Num rows: 15 Data size: 1903 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 15 Data size: 1903 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
+ 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/6eaa32c8/ql/src/test/results/clientpositive/mapjoin_mapjoin.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/mapjoin_mapjoin.q.out b/ql/src/test/results/clientpositive/mapjoin_mapjoin.q.out
index 3fba77c..9775f30 100644
--- a/ql/src/test/results/clientpositive/mapjoin_mapjoin.q.out
+++ b/ql/src/test/results/clientpositive/mapjoin_mapjoin.q.out
@@ -56,18 +56,18 @@ TOK_QUERY
STAGE DEPENDENCIES:
- Stage-6 is a root stage
- Stage-4 depends on stages: Stage-6
- Stage-0 depends on stages: Stage-4
+ Stage-7 is a root stage
+ Stage-5 depends on stages: Stage-7
+ Stage-0 depends on stages: Stage-5
STAGE PLANS:
- Stage: Stage-6
+ Stage: Stage-7
Map Reduce Local Work
Alias -> Map Local Tables:
$hdt$_0:src
Fetch Operator
limit: -1
- $hdt$_1:$hdt$_2:src1
+ $hdt$_2:src1
Fetch Operator
limit: -1
Alias -> Map Local Operator Tree:
@@ -86,10 +86,10 @@ STAGE PLANS:
Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
HashTable Sink Operator
keys:
- 0 _col0 (type: string)
- 1 _col1 (type: string)
- Position of Big Table: 1
- $hdt$_1:$hdt$_2:src1
+ 0 _col1 (type: string)
+ 1 _col0 (type: string)
+ Position of Big Table: 0
+ $hdt$_2:src1
TableScan
alias: src1
Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE
@@ -108,7 +108,7 @@ STAGE PLANS:
1 _col0 (type: string)
Position of Big Table: 0
- Stage: Stage-4
+ Stage: Stage-5
Map Reduce
Map Operator Tree:
TableScan
@@ -136,36 +136,32 @@ STAGE PLANS:
condition map:
Inner Join 0 to 1
keys:
- 0 _col0 (type: string)
- 1 _col1 (type: string)
- outputColumnNames: _col1
- Position of Big Table: 1
+ 0 _col1 (type: string)
+ 1 _col0 (type: string)
+ outputColumnNames: _col0
+ Position of Big Table: 0
Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col1 (type: string)
- outputColumnNames: _col0
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+#### A masked pattern was here ####
+ NumFilesPerFileSink: 1
Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- GlobalTableId: 0
-#### A masked pattern was here ####
- NumFilesPerFileSink: 1
- Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE
-#### A masked pattern was here ####
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- columns _col0
- columns.types string
- escape.delim \
- hive.serialization.extend.additional.nesting.levels true
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- TotalFiles: 1
- GatherStats: false
- MultiFileSpray: false
+#### A masked pattern was here ####
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ properties:
+ columns _col0
+ columns.types string
+ escape.delim \
+ hive.serialization.extend.additional.nesting.levels true
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ TotalFiles: 1
+ GatherStats: false
+ MultiFileSpray: false
Local Work:
Map Reduce Local Work
Path -> Alias:
@@ -444,10 +440,10 @@ STAGE PLANS:
name: default.srcpart
name: default.srcpart
Truncated Path -> Alias:
- /srcpart/ds=2008-04-08/hr=11 [$hdt$_1:$hdt$_1:srcpart]
- /srcpart/ds=2008-04-08/hr=12 [$hdt$_1:$hdt$_1:srcpart]
- /srcpart/ds=2008-04-09/hr=11 [$hdt$_1:$hdt$_1:srcpart]
- /srcpart/ds=2008-04-09/hr=12 [$hdt$_1:$hdt$_1:srcpart]
+ /srcpart/ds=2008-04-08/hr=11 [$hdt$_1:srcpart]
+ /srcpart/ds=2008-04-08/hr=12 [$hdt$_1:srcpart]
+ /srcpart/ds=2008-04-09/hr=11 [$hdt$_1:srcpart]
+ /srcpart/ds=2008-04-09/hr=12 [$hdt$_1:srcpart]
Stage: Stage-0
Fetch Operator
@@ -462,18 +458,18 @@ POSTHOOK: query: explain
select srcpart.key from srcpart join src on (srcpart.value=src.value) join src1 on (srcpart.key=src1.key) where srcpart.value > 'val_450'
POSTHOOK: type: QUERY
STAGE DEPENDENCIES:
- Stage-6 is a root stage
- Stage-4 depends on stages: Stage-6
- Stage-0 depends on stages: Stage-4
+ Stage-7 is a root stage
+ Stage-5 depends on stages: Stage-7
+ Stage-0 depends on stages: Stage-5
STAGE PLANS:
- Stage: Stage-6
+ Stage: Stage-7
Map Reduce Local Work
Alias -> Map Local Tables:
$hdt$_0:src
Fetch Operator
limit: -1
- $hdt$_1:$hdt$_2:src1
+ $hdt$_2:src1
Fetch Operator
limit: -1
Alias -> Map Local Operator Tree:
@@ -490,9 +486,9 @@ STAGE PLANS:
Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
HashTable Sink Operator
keys:
- 0 _col0 (type: string)
- 1 _col1 (type: string)
- $hdt$_1:$hdt$_2:src1
+ 0 _col1 (type: string)
+ 1 _col0 (type: string)
+ $hdt$_2:src1
TableScan
alias: src1
Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE
@@ -508,7 +504,7 @@ STAGE PLANS:
0 _col0 (type: string)
1 _col0 (type: string)
- Stage: Stage-4
+ Stage: Stage-5
Map Reduce
Map Operator Tree:
TableScan
@@ -533,21 +529,17 @@ STAGE PLANS:
condition map:
Inner Join 0 to 1
keys:
- 0 _col0 (type: string)
- 1 _col1 (type: string)
- outputColumnNames: _col1
+ 0 _col1 (type: string)
+ 1 _col0 (type: string)
+ outputColumnNames: _col0
Statistics: Num rows: 201 Data size: 2146 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col1 (type: string)
- outputColumnNames: _col0
+ File Output Operator
+ compressed: false
Statistics: Num rows: 201 Data size: 2146 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 201 Data size: 2146 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
+ 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
http://git-wip-us.apache.org/repos/asf/hive/blob/6eaa32c8/ql/src/test/results/clientpositive/spark/auto_join13.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/auto_join13.q.out b/ql/src/test/results/clientpositive/spark/auto_join13.q.out
index c81d296..0ffe9e3 100644
--- a/ql/src/test/results/clientpositive/spark/auto_join13.q.out
+++ b/ql/src/test/results/clientpositive/spark/auto_join13.q.out
@@ -30,22 +30,22 @@ STAGE PLANS:
Spark
#### A masked pattern was here ####
Vertices:
- Map 1
+ Map 3
Map Operator Tree:
TableScan
alias: src
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: ((UDFToDouble(key) < 200.0) and UDFToDouble(key) is not null) (type: boolean)
- Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE
+ 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
- Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
Spark HashTable Sink Operator
keys:
- 0 UDFToDouble(_col0) (type: double)
- 1 (UDFToDouble(_col2) + UDFToDouble(_col0)) (type: double)
+ 0 _col0 (type: string)
+ 1 _col0 (type: string)
Local Work:
Map Reduce Local Work
Map 4
@@ -54,26 +54,26 @@ STAGE PLANS:
alias: src
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: (UDFToDouble(key) < 100.0) (type: boolean)
- Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
+ predicate: ((UDFToDouble(key) < 200.0) and UDFToDouble(key) is not null) (type: boolean)
+ Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: key (type: string)
outputColumnNames: _col0
- Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE
Spark HashTable Sink Operator
keys:
- 0 _col0 (type: string)
- 1 _col0 (type: string)
+ 0 (UDFToDouble(_col2) + UDFToDouble(_col0)) (type: double)
+ 1 UDFToDouble(_col0) (type: double)
Local Work:
Map Reduce Local Work
Stage: Stage-1
Spark
Edges:
- Reducer 3 <- Map 2 (GROUP, 1)
+ Reducer 2 <- Map 1 (GROUP, 1)
#### A masked pattern was here ####
Vertices:
- Map 2
+ Map 1
Map Operator Tree:
TableScan
alias: src
@@ -93,7 +93,7 @@ STAGE PLANS:
1 _col0 (type: string)
outputColumnNames: _col0, _col1, _col2
input vertices:
- 1 Map 4
+ 1 Map 3
Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE
Filter Operator
predicate: (UDFToDouble(_col2) + UDFToDouble(_col0)) is not null (type: boolean)
@@ -102,14 +102,14 @@ STAGE PLANS:
condition map:
Inner Join 0 to 1
keys:
- 0 UDFToDouble(_col0) (type: double)
- 1 (UDFToDouble(_col2) + UDFToDouble(_col0)) (type: double)
- outputColumnNames: _col2, _col3
+ 0 (UDFToDouble(_col2) + UDFToDouble(_col0)) (type: double)
+ 1 UDFToDouble(_col0) (type: double)
+ outputColumnNames: _col1, _col2
input vertices:
- 0 Map 1
+ 1 Map 4
Statistics: Num rows: 100 Data size: 1065 Basic stats: COMPLETE Column stats: NONE
Select Operator
- expressions: hash(_col3,_col2) (type: int)
+ expressions: hash(_col2,_col1) (type: int)
outputColumnNames: _col0
Statistics: Num rows: 100 Data size: 1065 Basic stats: COMPLETE Column stats: NONE
Group By Operator
@@ -123,7 +123,7 @@ STAGE PLANS:
value expressions: _col0 (type: bigint)
Local Work:
Map Reduce Local Work
- Reducer 3
+ Reducer 2
Reduce Operator Tree:
Group By Operator
aggregations: sum(VALUE._col0)
http://git-wip-us.apache.org/repos/asf/hive/blob/6eaa32c8/ql/src/test/results/clientpositive/spark/auto_join_without_localtask.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/auto_join_without_localtask.q.out b/ql/src/test/results/clientpositive/spark/auto_join_without_localtask.q.out
index 72f60d0..a234ff5 100644
--- a/ql/src/test/results/clientpositive/spark/auto_join_without_localtask.q.out
+++ b/ql/src/test/results/clientpositive/spark/auto_join_without_localtask.q.out
@@ -324,9 +324,9 @@ STAGE PLANS:
Stage: Stage-1
Spark
Edges:
- Reducer 5 <- Map 4 (PARTITION-LEVEL SORT, 2), Map 6 (PARTITION-LEVEL SORT, 2)
- Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 2), Reducer 5 (PARTITION-LEVEL SORT, 2)
- Reducer 3 <- Reducer 2 (SORT, 1)
+ Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 2), Map 5 (PARTITION-LEVEL SORT, 2)
+ Reducer 3 <- Map 6 (PARTITION-LEVEL SORT, 2), Reducer 2 (PARTITION-LEVEL SORT, 2)
+ Reducer 4 <- Reducer 3 (SORT, 1)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -335,23 +335,6 @@ STAGE PLANS:
alias: a
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: value is not null (type: boolean)
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: value (type: string)
- outputColumnNames: _col0
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: string)
- sort order: +
- Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
- Map 4
- Map Operator Tree:
- TableScan
- alias: a
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
predicate: ((UDFToDouble(key) > 100.0) and value is not null) (type: boolean)
Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE
Select Operator
@@ -364,7 +347,7 @@ STAGE PLANS:
Map-reduce partition columns: _col0 (type: string)
Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: string)
- Map 6
+ Map 5
Map Operator Tree:
TableScan
alias: a
@@ -381,6 +364,23 @@ STAGE PLANS:
sort order: +
Map-reduce partition columns: _col0 (type: string)
Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
+ Map 6
+ Map Operator Tree:
+ TableScan
+ alias: a
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: value is not null (type: boolean)
+ Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: value (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
Reducer 2
Reduce Operator Tree:
Join Operator
@@ -388,18 +388,30 @@ STAGE PLANS:
Inner Join 0 to 1
keys:
0 _col0 (type: string)
- 1 _col1 (type: string)
- outputColumnNames: _col1, _col2
+ 1 _col0 (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col1 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col1 (type: string)
+ Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: string)
+ Reducer 3
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col1 (type: string)
+ 1 _col0 (type: string)
+ outputColumnNames: _col0, _col1
Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col1 (type: string), _col2 (type: string)
- outputColumnNames: _col0, _col1
+ Reduce Output Operator
+ key expressions: _col0 (type: string), _col1 (type: string)
+ sort order: ++
Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: string), _col1 (type: string)
- sort order: ++
- Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
- Reducer 3
+ Reducer 4
Reduce Operator Tree:
Select Operator
expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string)
@@ -415,22 +427,6 @@ 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 5
- Reduce Operator Tree:
- Join Operator
- condition map:
- Inner Join 0 to 1
- keys:
- 0 _col0 (type: string)
- 1 _col0 (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col1 (type: string)
- sort order: +
- Map-reduce partition columns: _col1 (type: string)
- Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col0 (type: string)
Stage: Stage-0
Fetch Operator
http://git-wip-us.apache.org/repos/asf/hive/blob/6eaa32c8/ql/src/test/results/clientpositive/spark/join13.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/join13.q.out b/ql/src/test/results/clientpositive/spark/join13.q.out
index 3eb7720..4a045f7 100644
--- a/ql/src/test/results/clientpositive/spark/join13.q.out
+++ b/ql/src/test/results/clientpositive/spark/join13.q.out
@@ -32,8 +32,8 @@ STAGE PLANS:
Stage: Stage-1
Spark
Edges:
- Reducer 4 <- Map 3 (PARTITION-LEVEL SORT, 2), Map 5 (PARTITION-LEVEL SORT, 2)
- Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 2), Reducer 4 (PARTITION-LEVEL SORT, 2)
+ Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 2), Map 4 (PARTITION-LEVEL SORT, 2)
+ Reducer 3 <- Map 5 (PARTITION-LEVEL SORT, 2), Reducer 2 (PARTITION-LEVEL SORT, 2)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -42,23 +42,6 @@ STAGE PLANS:
alias: src
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: ((UDFToDouble(key) < 200.0) and UDFToDouble(key) is not null) (type: boolean)
- Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: key (type: string)
- outputColumnNames: _col0
- Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: UDFToDouble(_col0) (type: double)
- sort order: +
- Map-reduce partition columns: UDFToDouble(_col0) (type: double)
- Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE
- Map 3
- Map Operator Tree:
- TableScan
- alias: src
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
predicate: (UDFToDouble(key) < 100.0) (type: boolean)
Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
Select Operator
@@ -71,7 +54,7 @@ STAGE PLANS:
Map-reduce partition columns: _col0 (type: string)
Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: string)
- Map 5
+ Map 4
Map Operator Tree:
TableScan
alias: src
@@ -88,33 +71,29 @@ STAGE PLANS:
sort order: +
Map-reduce partition columns: _col0 (type: string)
Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
+ Map 5
+ Map Operator Tree:
+ TableScan
+ alias: src
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: ((UDFToDouble(key) < 200.0) and UDFToDouble(key) is not null) (type: boolean)
+ Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: key (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: UDFToDouble(_col0) (type: double)
+ sort order: +
+ Map-reduce partition columns: UDFToDouble(_col0) (type: double)
+ Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE
Reducer 2
Reduce Operator Tree:
Join Operator
condition map:
Inner Join 0 to 1
keys:
- 0 UDFToDouble(_col0) (type: double)
- 1 (UDFToDouble(_col2) + UDFToDouble(_col0)) (type: double)
- outputColumnNames: _col2, _col3
- Statistics: Num rows: 100 Data size: 1065 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col3 (type: string), _col2 (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 100 Data size: 1065 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 100 Data size: 1065 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
- Reducer 4
- Reduce Operator Tree:
- Join Operator
- condition map:
- Inner Join 0 to 1
- keys:
0 _col0 (type: string)
1 _col0 (type: string)
outputColumnNames: _col0, _col1, _col2
@@ -128,6 +107,27 @@ STAGE PLANS:
Map-reduce partition columns: (UDFToDouble(_col2) + UDFToDouble(_col0)) (type: double)
Statistics: Num rows: 91 Data size: 969 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: string), _col2 (type: string)
+ Reducer 3
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 (UDFToDouble(_col2) + UDFToDouble(_col0)) (type: double)
+ 1 UDFToDouble(_col0) (type: double)
+ outputColumnNames: _col1, _col2
+ Statistics: Num rows: 100 Data size: 1065 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col2 (type: string), _col1 (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 100 Data size: 1065 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 100 Data size: 1065 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-0
Fetch Operator
http://git-wip-us.apache.org/repos/asf/hive/blob/6eaa32c8/ql/src/test/results/clientpositive/spark/join32.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/join32.q.out b/ql/src/test/results/clientpositive/spark/join32.q.out
index d7383fb..4ae9dc6 100644
--- a/ql/src/test/results/clientpositive/spark/join32.q.out
+++ b/ql/src/test/results/clientpositive/spark/join32.q.out
@@ -110,25 +110,25 @@ STAGE PLANS:
Spark
#### A masked pattern was here ####
Vertices:
- Map 1
+ Map 2
Map Operator Tree:
TableScan
- alias: y
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ alias: x
+ Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE
GatherStats: false
Filter Operator
isSamplingPred: false
- predicate: key is not null (type: boolean)
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ predicate: (value is not null and key is not null) (type: boolean)
+ Statistics: Num rows: 7 Data size: 53 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: key (type: string), value (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 7 Data size: 53 Basic stats: COMPLETE Column stats: NONE
Spark HashTable Sink Operator
keys:
0 _col0 (type: string)
- 1 _col3 (type: string)
- Position of Big Table: 1
+ 1 _col1 (type: string)
+ Position of Big Table: 0
Local Work:
Map Reduce Local Work
Path -> Alias:
@@ -136,7 +136,7 @@ STAGE PLANS:
Path -> Partition:
#### A masked pattern was here ####
Partition
- base file name: src
+ base file name: src1
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
@@ -146,14 +146,14 @@ STAGE PLANS:
columns.comments 'default','default'
columns.types string:string
#### A masked pattern was here ####
- name default.src
+ name default.src1
numFiles 1
- numRows 500
- rawDataSize 5312
- serialization.ddl struct src { string key, string value}
+ numRows 25
+ rawDataSize 191
+ serialization.ddl struct src1 { string key, string value}
serialization.format 1
serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 5812
+ totalSize 216
#### A masked pattern was here ####
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
@@ -166,38 +166,38 @@ STAGE PLANS:
columns.comments 'default','default'
columns.types string:string
#### A masked pattern was here ####
- name default.src
+ name default.src1
numFiles 1
- numRows 500
- rawDataSize 5312
- serialization.ddl struct src { string key, string value}
+ numRows 25
+ rawDataSize 191
+ serialization.ddl struct src1 { string key, string value}
serialization.format 1
serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 5812
+ totalSize 216
#### A masked pattern was here ####
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.src
- name: default.src
+ name: default.src1
+ name: default.src1
Truncated Path -> Alias:
- /src [y]
+ /src1 [x]
Map 3
Map Operator Tree:
TableScan
- alias: x
- Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE
+ alias: y
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
GatherStats: false
Filter Operator
isSamplingPred: false
- predicate: (value is not null and key is not null) (type: boolean)
- Statistics: Num rows: 7 Data size: 53 Basic stats: COMPLETE Column stats: NONE
+ 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
- Statistics: Num rows: 7 Data size: 53 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
Spark HashTable Sink Operator
keys:
- 0 _col0 (type: string)
- 1 _col1 (type: string)
+ 0 _col3 (type: string)
+ 1 _col0 (type: string)
Position of Big Table: 0
Local Work:
Map Reduce Local Work
@@ -206,7 +206,7 @@ STAGE PLANS:
Path -> Partition:
#### A masked pattern was here ####
Partition
- base file name: src1
+ base file name: src
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
@@ -216,14 +216,14 @@ STAGE PLANS:
columns.comments 'default','default'
columns.types string:string
#### A masked pattern was here ####
- name default.src1
+ name default.src
numFiles 1
- numRows 25
- rawDataSize 191
- serialization.ddl struct src1 { string key, string value}
+ numRows 500
+ rawDataSize 5312
+ serialization.ddl struct src { string key, string value}
serialization.format 1
serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 216
+ totalSize 5812
#### A masked pattern was here ####
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
@@ -236,26 +236,26 @@ STAGE PLANS:
columns.comments 'default','default'
columns.types string:string
#### A masked pattern was here ####
- name default.src1
+ name default.src
numFiles 1
- numRows 25
- rawDataSize 191
- serialization.ddl struct src1 { string key, string value}
+ numRows 500
+ rawDataSize 5312
+ serialization.ddl struct src { string key, string value}
serialization.format 1
serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 216
+ totalSize 5812
#### A masked pattern was here ####
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.src1
- name: default.src1
+ name: default.src
+ name: default.src
Truncated Path -> Alias:
- /src1 [x]
+ /src [y]
Stage: Stage-1
Spark
#### A masked pattern was here ####
Vertices:
- Map 2
+ Map 1
Map Operator Tree:
TableScan
alias: z
@@ -277,22 +277,22 @@ STAGE PLANS:
1 _col1 (type: string)
outputColumnNames: _col0, _col3
input vertices:
- 1 Map 3
+ 1 Map 2
Position of Big Table: 0
Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
Map Join Operator
condition map:
Inner Join 0 to 1
keys:
- 0 _col0 (type: string)
- 1 _col3 (type: string)
- outputColumnNames: _col1, _col2, _col5
+ 0 _col3 (type: string)
+ 1 _col0 (type: string)
+ outputColumnNames: _col0, _col3, _col6
input vertices:
- 0 Map 1
- Position of Big Table: 1
+ 1 Map 3
+ Position of Big Table: 0
Statistics: Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE
Select Operator
- expressions: _col5 (type: string), _col2 (type: string), _col1 (type: string)
+ expressions: _col3 (type: string), _col0 (type: string), _col6 (type: string)
outputColumnNames: _col0, _col1, _col2
Statistics: Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE
File Output Operator
http://git-wip-us.apache.org/repos/asf/hive/blob/6eaa32c8/ql/src/test/results/clientpositive/spark/join32_lessSize.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/join32_lessSize.q.out b/ql/src/test/results/clientpositive/spark/join32_lessSize.q.out
index b1efc8f..78bb655 100644
--- a/ql/src/test/results/clientpositive/spark/join32_lessSize.q.out
+++ b/ql/src/test/results/clientpositive/spark/join32_lessSize.q.out
@@ -118,25 +118,25 @@ STAGE PLANS:
Spark
#### A masked pattern was here ####
Vertices:
- Map 1
+ Map 2
Map Operator Tree:
TableScan
- alias: y
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ alias: x
+ Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE
GatherStats: false
Filter Operator
isSamplingPred: false
- predicate: key is not null (type: boolean)
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ predicate: (value is not null and key is not null) (type: boolean)
+ Statistics: Num rows: 7 Data size: 53 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: key (type: string), value (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 7 Data size: 53 Basic stats: COMPLETE Column stats: NONE
Spark HashTable Sink Operator
keys:
0 _col0 (type: string)
- 1 _col3 (type: string)
- Position of Big Table: 1
+ 1 _col1 (type: string)
+ Position of Big Table: 0
Local Work:
Map Reduce Local Work
Path -> Alias:
@@ -144,7 +144,7 @@ STAGE PLANS:
Path -> Partition:
#### A masked pattern was here ####
Partition
- base file name: src
+ base file name: src1
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
@@ -154,14 +154,14 @@ STAGE PLANS:
columns.comments 'default','default'
columns.types string:string
#### A masked pattern was here ####
- name default.src
+ name default.src1
numFiles 1
- numRows 500
- rawDataSize 5312
- serialization.ddl struct src { string key, string value}
+ numRows 25
+ rawDataSize 191
+ serialization.ddl struct src1 { string key, string value}
serialization.format 1
serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 5812
+ totalSize 216
#### A masked pattern was here ####
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
@@ -174,38 +174,38 @@ STAGE PLANS:
columns.comments 'default','default'
columns.types string:string
#### A masked pattern was here ####
- name default.src
+ name default.src1
numFiles 1
- numRows 500
- rawDataSize 5312
- serialization.ddl struct src { string key, string value}
+ numRows 25
+ rawDataSize 191
+ serialization.ddl struct src1 { string key, string value}
serialization.format 1
serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 5812
+ totalSize 216
#### A masked pattern was here ####
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.src
- name: default.src
+ name: default.src1
+ name: default.src1
Truncated Path -> Alias:
- /src [y]
+ /src1 [x]
Map 3
Map Operator Tree:
TableScan
- alias: x
- Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE
+ alias: y
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
GatherStats: false
Filter Operator
isSamplingPred: false
- predicate: (value is not null and key is not null) (type: boolean)
- Statistics: Num rows: 7 Data size: 53 Basic stats: COMPLETE Column stats: NONE
+ 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
- Statistics: Num rows: 7 Data size: 53 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
Spark HashTable Sink Operator
keys:
- 0 _col0 (type: string)
- 1 _col1 (type: string)
+ 0 _col3 (type: string)
+ 1 _col0 (type: string)
Position of Big Table: 0
Local Work:
Map Reduce Local Work
@@ -214,7 +214,7 @@ STAGE PLANS:
Path -> Partition:
#### A masked pattern was here ####
Partition
- base file name: src1
+ base file name: src
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
@@ -224,14 +224,14 @@ STAGE PLANS:
columns.comments 'default','default'
columns.types string:string
#### A masked pattern was here ####
- name default.src1
+ name default.src
numFiles 1
- numRows 25
- rawDataSize 191
- serialization.ddl struct src1 { string key, string value}
+ numRows 500
+ rawDataSize 5312
+ serialization.ddl struct src { string key, string value}
serialization.format 1
serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 216
+ totalSize 5812
#### A masked pattern was here ####
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
@@ -244,26 +244,26 @@ STAGE PLANS:
columns.comments 'default','default'
columns.types string:string
#### A masked pattern was here ####
- name default.src1
+ name default.src
numFiles 1
- numRows 25
- rawDataSize 191
- serialization.ddl struct src1 { string key, string value}
+ numRows 500
+ rawDataSize 5312
+ serialization.ddl struct src { string key, string value}
serialization.format 1
serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 216
+ totalSize 5812
#### A masked pattern was here ####
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.src1
- name: default.src1
+ name: default.src
+ name: default.src
Truncated Path -> Alias:
- /src1 [x]
+ /src [y]
Stage: Stage-1
Spark
#### A masked pattern was here ####
Vertices:
- Map 2
+ Map 1
Map Operator Tree:
TableScan
alias: z
@@ -285,22 +285,22 @@ STAGE PLANS:
1 _col1 (type: string)
outputColumnNames: _col0, _col3
input vertices:
- 1 Map 3
+ 1 Map 2
Position of Big Table: 0
Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
Map Join Operator
condition map:
Inner Join 0 to 1
keys:
- 0 _col0 (type: string)
- 1 _col3 (type: string)
- outputColumnNames: _col1, _col2, _col5
+ 0 _col3 (type: string)
+ 1 _col0 (type: string)
+ outputColumnNames: _col0, _col3, _col6
input vertices:
- 0 Map 1
- Position of Big Table: 1
+ 1 Map 3
+ Position of Big Table: 0
Statistics: Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE
Select Operator
- expressions: _col5 (type: string), _col2 (type: string), _col1 (type: string)
+ expressions: _col3 (type: string), _col0 (type: string), _col6 (type: string)
outputColumnNames: _col0, _col1, _col2
Statistics: Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE
File Output Operator
@@ -624,7 +624,7 @@ STAGE PLANS:
Spark
#### A masked pattern was here ####
Vertices:
- Map 3
+ Map 1
Map Operator Tree:
TableScan
alias: x
@@ -699,25 +699,36 @@ STAGE PLANS:
Spark
#### A masked pattern was here ####
Vertices:
- Map 1
+ Map 2
Map Operator Tree:
TableScan
- alias: w
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ alias: x
+ Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE
GatherStats: false
Filter Operator
isSamplingPred: false
predicate: key is not null (type: boolean)
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE
Select Operator
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
+ Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
keys:
0 _col0 (type: string)
- 1 _col1 (type: string)
+ 1 _col0 (type: string)
+ outputColumnNames: _col0, _col1, _col3
+ input vertices:
+ 0 Map 1
Position of Big Table: 1
+ Statistics: Num rows: 14 Data size: 108 Basic stats: COMPLETE Column stats: NONE
+ Spark HashTable Sink Operator
+ keys:
+ 0 _col1 (type: string)
+ 1 _col0 (type: string)
+ Position of Big Table: 1
Local Work:
Map Reduce Local Work
Path -> Alias:
@@ -725,7 +736,7 @@ STAGE PLANS:
Path -> Partition:
#### A masked pattern was here ####
Partition
- base file name: src
+ base file name: src1
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
@@ -735,14 +746,14 @@ STAGE PLANS:
columns.comments 'default','default'
columns.types string:string
#### A masked pattern was here ####
- name default.src
+ name default.src1
numFiles 1
- numRows 500
- rawDataSize 5312
- serialization.ddl struct src { string key, string value}
+ numRows 25
+ rawDataSize 191
+ serialization.ddl struct src1 { string key, string value}
serialization.format 1
serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 5812
+ totalSize 216
#### A masked pattern was here ####
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
@@ -755,50 +766,39 @@ STAGE PLANS:
columns.comments 'default','default'
columns.types string:string
#### A masked pattern was here ####
- name default.src
+ name default.src1
numFiles 1
- numRows 500
- rawDataSize 5312
- serialization.ddl struct src { string key, string value}
+ numRows 25
+ rawDataSize 191
+ serialization.ddl struct src1 { string key, string value}
serialization.format 1
serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 5812
+ totalSize 216
#### A masked pattern was here ####
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.src
- name: default.src
+ name: default.src1
+ name: default.src1
Truncated Path -> Alias:
- /src [w]
+ /src1 [x]
Map 4
Map Operator Tree:
TableScan
- alias: x
- Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE
+ alias: w
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
GatherStats: false
Filter Operator
isSamplingPred: false
predicate: key is not null (type: boolean)
- Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE
+ 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
- Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE
- Map Join Operator
- condition map:
- Inner Join 0 to 1
+ Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Spark HashTable Sink Operator
keys:
0 _col0 (type: string)
1 _col0 (type: string)
- outputColumnNames: _col0, _col1, _col3
- input vertices:
- 0 Map 3
- Position of Big Table: 1
- Statistics: Num rows: 14 Data size: 108 Basic stats: COMPLETE Column stats: NONE
- Spark HashTable Sink Operator
- keys:
- 0 _col0 (type: string)
- 1 _col1 (type: string)
- Position of Big Table: 0
+ Position of Big Table: 0
Local Work:
Map Reduce Local Work
Path -> Alias:
@@ -806,7 +806,7 @@ STAGE PLANS:
Path -> Partition:
#### A masked pattern was here ####
Partition
- base file name: src1
+ base file name: src
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
@@ -816,14 +816,14 @@ STAGE PLANS:
columns.comments 'default','default'
columns.types string:string
#### A masked pattern was here ####
- name default.src1
+ name default.src
numFiles 1
- numRows 25
- rawDataSize 191
- serialization.ddl struct src1 { string key, string value}
+ numRows 500
+ rawDataSize 5312
+ serialization.ddl struct src { string key, string value}
serialization.format 1
serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 216
+ totalSize 5812
#### A masked pattern was here ####
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
@@ -836,26 +836,26 @@ STAGE PLANS:
columns.comments 'default','default'
columns.types string:string
#### A masked pattern was here ####
- name default.src1
+ name default.src
numFiles 1
- numRows 25
- rawDataSize 191
- serialization.ddl struct src1 { string key, string value}
+ numRows 500
+ rawDataSize 5312
+ serialization.ddl struct src { string key, string value}
serialization.format 1
serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 216
+ totalSize 5812
#### A masked pattern was here ####
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.src1
- name: default.src1
+ name: default.src
+ name: default.src
Truncated Path -> Alias:
- /src1 [x]
+ /src [w]
Stage: Stage-1
Spark
#### A masked pattern was here ####
Vertices:
- Map 2
+ Map 3
Map Operator Tree:
TableScan
alias: w
@@ -873,26 +873,26 @@ STAGE PLANS:
condition map:
Inner Join 0 to 1
keys:
- 0 _col0 (type: string)
- 1 _col1 (type: string)
- outputColumnNames: _col1, _col4
+ 0 _col1 (type: string)
+ 1 _col0 (type: string)
+ outputColumnNames: _col0, _col3
input vertices:
- 1 Map 4
- Position of Big Table: 0
+ 0 Map 2
+ Position of Big Table: 1
Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
Map Join Operator
condition map:
Inner Join 0 to 1
keys:
0 _col0 (type: string)
- 1 _col1 (type: string)
- outputColumnNames: _col1, _col3, _col6
+ 1 _col0 (type: string)
+ outputColumnNames: _col0, _col3, _col6
input vertices:
- 0 Map 1
- Position of Big Table: 1
+ 1 Map 4
+ Position of Big Table: 0
Statistics: Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE
Select Operator
- expressions: _col3 (type: string), _col6 (type: string), _col1 (type: string)
+ expressions: _col0 (type: string), _col3 (type: string), _col6 (type: string)
outputColumnNames: _col0, _col1, _col2
Statistics: Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE
File Output Operator
@@ -1029,7 +1029,7 @@ POSTHOOK: Input: default@src1
POSTHOOK: Output: default@dest_j1
POSTHOOK: Lineage: dest_j1.key EXPRESSION [(src1)x.FieldSchema(name:key, type:string, comment:default), ]
POSTHOOK: Lineage: dest_j1.val2 SIMPLE [(src)w.FieldSchema(name:value, type:string, comment:default), ]
-POSTHOOK: Lineage: dest_j1.value SIMPLE [(src1)x.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: dest_j1.value EXPRESSION [(src1)x.FieldSchema(name:value, type:string, comment:default), ]
PREHOOK: query: select * from dest_j1
PREHOOK: type: QUERY
PREHOOK: Input: default@dest_j1