You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@hive.apache.org by ha...@apache.org on 2015/04/20 08:14:39 UTC
svn commit: r1674738 [5/11] - in /hive/trunk: ./
common/src/java/org/apache/hadoop/hive/conf/ hbase-handler/ metastore/bin/
ql/ ql/src/java/org/apache/hadoop/hive/ql/exec/
ql/src/java/org/apache/hadoop/hive/ql/optimizer/
ql/src/java/org/apache/hadoop/h...
Modified: hive/trunk/ql/src/test/results/clientpositive/spark/join32.q.out
URL: http://svn.apache.org/viewvc/hive/trunk/ql/src/test/results/clientpositive/spark/join32.q.out?rev=1674738&r1=1674737&r2=1674738&view=diff
==============================================================================
--- hive/trunk/ql/src/test/results/clientpositive/spark/join32.q.out (original)
+++ hive/trunk/ql/src/test/results/clientpositive/spark/join32.q.out Mon Apr 20 06:14:38 2015
@@ -113,16 +113,16 @@ STAGE PLANS:
Map 1
Map Operator Tree:
TableScan
- alias: y
+ alias: z
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)
+ predicate: ((11.0 = 11.0) and value 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: value (type: string)
+ outputColumnNames: _col0
Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
Spark HashTable Sink Operator
keys:
@@ -136,9 +136,12 @@ STAGE PLANS:
Path -> Partition:
#### A masked pattern was here ####
Partition
- base file name: src
+ base file name: hr=11
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ partition values:
+ ds 2008-04-08
+ hr 11
properties:
COLUMN_STATS_ACCURATE true
bucket_count -1
@@ -146,11 +149,13 @@ STAGE PLANS:
columns.comments 'default','default'
columns.types string:string
#### A masked pattern was here ####
- name default.src
+ name default.srcpart
numFiles 1
numRows 500
+ partition_columns ds/hr
+ partition_columns.types string:string
rawDataSize 5312
- serialization.ddl struct src { string key, string value}
+ serialization.ddl struct srcpart { string key, string value}
serialization.format 1
serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
totalSize 5812
@@ -160,26 +165,23 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE true
bucket_count -1
columns key,value
columns.comments 'default','default'
columns.types string:string
#### A masked pattern was here ####
- name default.src
- numFiles 1
- numRows 500
- rawDataSize 5312
- serialization.ddl struct src { string key, string value}
+ name default.srcpart
+ partition_columns ds/hr
+ partition_columns.types string:string
+ serialization.ddl struct srcpart { string key, string value}
serialization.format 1
serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 5812
#### A masked pattern was here ####
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.src
- name: default.src
+ name: default.srcpart
+ name: default.srcpart
Truncated Path -> Alias:
- /src [y]
+ /srcpart/ds=2008-04-08/hr=11 [z]
Map 3
Map Operator Tree:
TableScan
@@ -188,7 +190,7 @@ STAGE PLANS:
GatherStats: false
Filter Operator
isSamplingPred: false
- predicate: (value is not null and key is not null) (type: boolean)
+ predicate: (key is not null and value 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)
@@ -197,7 +199,7 @@ STAGE PLANS:
Spark HashTable Sink Operator
keys:
0 _col0 (type: string)
- 1 _col1 (type: string)
+ 1 _col0 (type: string)
Position of Big Table: 0
Local Work:
Map Reduce Local Work
@@ -258,24 +260,24 @@ STAGE PLANS:
Map 2
Map Operator Tree:
TableScan
- alias: z
+ alias: y
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
GatherStats: false
Filter Operator
isSamplingPred: false
- predicate: ((11.0 = 11.0) and value is not null) (type: boolean)
+ predicate: key is not null (type: boolean)
Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
Select Operator
- expressions: value (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
Map Join Operator
condition map:
Inner Join 0 to 1
keys:
0 _col0 (type: string)
- 1 _col1 (type: string)
- outputColumnNames: _col0, _col3
+ 1 _col0 (type: string)
+ outputColumnNames: _col1, _col2, _col3
input vertices:
1 Map 3
Position of Big Table: 0
@@ -286,13 +288,13 @@ STAGE PLANS:
keys:
0 _col0 (type: string)
1 _col3 (type: string)
- outputColumnNames: _col1, _col2, _col5
+ outputColumnNames: _col0, _col4, _col5
input vertices:
0 Map 1
Position of Big Table: 1
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: _col5 (type: string), _col0 (type: string), _col4 (type: string)
outputColumnNames: _col0, _col1, _col2
Statistics: Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE
File Output Operator
@@ -328,12 +330,9 @@ STAGE PLANS:
Path -> Partition:
#### A masked pattern was here ####
Partition
- base file name: hr=11
+ base file name: src
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- partition values:
- ds 2008-04-08
- hr 11
properties:
COLUMN_STATS_ACCURATE true
bucket_count -1
@@ -341,13 +340,11 @@ STAGE PLANS:
columns.comments 'default','default'
columns.types string:string
#### A masked pattern was here ####
- name default.srcpart
+ name default.src
numFiles 1
numRows 500
- partition_columns ds/hr
- partition_columns.types string:string
rawDataSize 5312
- serialization.ddl struct srcpart { string key, string value}
+ serialization.ddl struct src { string key, string value}
serialization.format 1
serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
totalSize 5812
@@ -357,23 +354,26 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
+ COLUMN_STATS_ACCURATE true
bucket_count -1
columns key,value
columns.comments 'default','default'
columns.types string:string
#### A masked pattern was here ####
- name default.srcpart
- partition_columns ds/hr
- partition_columns.types string:string
- serialization.ddl struct srcpart { string key, string value}
+ name default.src
+ numFiles 1
+ 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 5812
#### A masked pattern was here ####
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.srcpart
- name: default.srcpart
+ name: default.src
+ name: default.src
Truncated Path -> Alias:
- /srcpart/ds=2008-04-08/hr=11 [z]
+ /src [y]
Stage: Stage-0
Move Operator
@@ -422,8 +422,8 @@ POSTHOOK: Input: default@srcpart
POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
POSTHOOK: Output: default@dest_j1
POSTHOOK: Lineage: dest_j1.key SIMPLE [(src1)x.FieldSchema(name:key, type:string, comment:default), ]
-POSTHOOK: Lineage: dest_j1.val2 SIMPLE [(src)y.FieldSchema(name:value, type:string, comment:default), ]
-POSTHOOK: Lineage: dest_j1.value EXPRESSION [(srcpart)z.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: dest_j1.val2 EXPRESSION [(src)y.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: dest_j1.value SIMPLE [(srcpart)z.FieldSchema(name:value, type:string, comment:default), ]
PREHOOK: query: select * from dest_j1
PREHOOK: type: QUERY
PREHOOK: Input: default@dest_j1
Modified: hive/trunk/ql/src/test/results/clientpositive/spark/join32_lessSize.q.out
URL: http://svn.apache.org/viewvc/hive/trunk/ql/src/test/results/clientpositive/spark/join32_lessSize.q.out?rev=1674738&r1=1674737&r2=1674738&view=diff
==============================================================================
--- hive/trunk/ql/src/test/results/clientpositive/spark/join32_lessSize.q.out (original)
+++ hive/trunk/ql/src/test/results/clientpositive/spark/join32_lessSize.q.out Mon Apr 20 06:14:38 2015
@@ -121,16 +121,16 @@ STAGE PLANS:
Map 1
Map Operator Tree:
TableScan
- alias: y
+ alias: z
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)
+ predicate: ((11.0 = 11.0) and value 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: value (type: string)
+ outputColumnNames: _col0
Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
Spark HashTable Sink Operator
keys:
@@ -144,9 +144,12 @@ STAGE PLANS:
Path -> Partition:
#### A masked pattern was here ####
Partition
- base file name: src
+ base file name: hr=11
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ partition values:
+ ds 2008-04-08
+ hr 11
properties:
COLUMN_STATS_ACCURATE true
bucket_count -1
@@ -154,11 +157,13 @@ STAGE PLANS:
columns.comments 'default','default'
columns.types string:string
#### A masked pattern was here ####
- name default.src
+ name default.srcpart
numFiles 1
numRows 500
+ partition_columns ds/hr
+ partition_columns.types string:string
rawDataSize 5312
- serialization.ddl struct src { string key, string value}
+ serialization.ddl struct srcpart { string key, string value}
serialization.format 1
serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
totalSize 5812
@@ -168,26 +173,23 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE true
bucket_count -1
columns key,value
columns.comments 'default','default'
columns.types string:string
#### A masked pattern was here ####
- name default.src
- numFiles 1
- numRows 500
- rawDataSize 5312
- serialization.ddl struct src { string key, string value}
+ name default.srcpart
+ partition_columns ds/hr
+ partition_columns.types string:string
+ serialization.ddl struct srcpart { string key, string value}
serialization.format 1
serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 5812
#### A masked pattern was here ####
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.src
- name: default.src
+ name: default.srcpart
+ name: default.srcpart
Truncated Path -> Alias:
- /src [y]
+ /srcpart/ds=2008-04-08/hr=11 [z]
Map 3
Map Operator Tree:
TableScan
@@ -196,7 +198,7 @@ STAGE PLANS:
GatherStats: false
Filter Operator
isSamplingPred: false
- predicate: (value is not null and key is not null) (type: boolean)
+ predicate: (key is not null and value 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)
@@ -205,7 +207,7 @@ STAGE PLANS:
Spark HashTable Sink Operator
keys:
0 _col0 (type: string)
- 1 _col1 (type: string)
+ 1 _col0 (type: string)
Position of Big Table: 0
Local Work:
Map Reduce Local Work
@@ -266,24 +268,24 @@ STAGE PLANS:
Map 2
Map Operator Tree:
TableScan
- alias: z
+ alias: y
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
GatherStats: false
Filter Operator
isSamplingPred: false
- predicate: ((11.0 = 11.0) and value is not null) (type: boolean)
+ predicate: key is not null (type: boolean)
Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
Select Operator
- expressions: value (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
Map Join Operator
condition map:
Inner Join 0 to 1
keys:
0 _col0 (type: string)
- 1 _col1 (type: string)
- outputColumnNames: _col0, _col3
+ 1 _col0 (type: string)
+ outputColumnNames: _col1, _col2, _col3
input vertices:
1 Map 3
Position of Big Table: 0
@@ -294,13 +296,13 @@ STAGE PLANS:
keys:
0 _col0 (type: string)
1 _col3 (type: string)
- outputColumnNames: _col1, _col2, _col5
+ outputColumnNames: _col0, _col4, _col5
input vertices:
0 Map 1
Position of Big Table: 1
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: _col5 (type: string), _col0 (type: string), _col4 (type: string)
outputColumnNames: _col0, _col1, _col2
Statistics: Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE
File Output Operator
@@ -336,12 +338,9 @@ STAGE PLANS:
Path -> Partition:
#### A masked pattern was here ####
Partition
- base file name: hr=11
+ base file name: src
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- partition values:
- ds 2008-04-08
- hr 11
properties:
COLUMN_STATS_ACCURATE true
bucket_count -1
@@ -349,13 +348,11 @@ STAGE PLANS:
columns.comments 'default','default'
columns.types string:string
#### A masked pattern was here ####
- name default.srcpart
+ name default.src
numFiles 1
numRows 500
- partition_columns ds/hr
- partition_columns.types string:string
rawDataSize 5312
- serialization.ddl struct srcpart { string key, string value}
+ serialization.ddl struct src { string key, string value}
serialization.format 1
serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
totalSize 5812
@@ -365,23 +362,26 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
+ COLUMN_STATS_ACCURATE true
bucket_count -1
columns key,value
columns.comments 'default','default'
columns.types string:string
#### A masked pattern was here ####
- name default.srcpart
- partition_columns ds/hr
- partition_columns.types string:string
- serialization.ddl struct srcpart { string key, string value}
+ name default.src
+ numFiles 1
+ 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 5812
#### A masked pattern was here ####
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.srcpart
- name: default.srcpart
+ name: default.src
+ name: default.src
Truncated Path -> Alias:
- /srcpart/ds=2008-04-08/hr=11 [z]
+ /src [y]
Stage: Stage-0
Move Operator
@@ -430,8 +430,8 @@ POSTHOOK: Input: default@srcpart
POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
POSTHOOK: Output: default@dest_j1
POSTHOOK: Lineage: dest_j1.key SIMPLE [(src1)x.FieldSchema(name:key, type:string, comment:default), ]
-POSTHOOK: Lineage: dest_j1.val2 SIMPLE [(src)y.FieldSchema(name:value, type:string, comment:default), ]
-POSTHOOK: Lineage: dest_j1.value EXPRESSION [(srcpart)z.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: dest_j1.val2 EXPRESSION [(src)y.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: dest_j1.value SIMPLE [(srcpart)z.FieldSchema(name:value, type:string, comment:default), ]
PREHOOK: query: select * from dest_j1
PREHOOK: type: QUERY
PREHOOK: Input: default@dest_j1
@@ -613,35 +613,34 @@ TOK_QUERY
STAGE DEPENDENCIES:
- Stage-4 is a root stage
- Stage-3 depends on stages: Stage-4
+ Stage-3 is a root stage
Stage-1 depends on stages: Stage-3
Stage-0 depends on stages: Stage-1
Stage-2 depends on stages: Stage-0
STAGE PLANS:
- Stage: Stage-4
+ Stage: Stage-3
Spark
#### A masked pattern was here ####
Vertices:
- Map 3
+ Map 1
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 and value 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 _col0 (type: string)
+ 1 _col1 (type: string)
Position of Big Table: 1
Local Work:
Map Reduce Local Work
@@ -650,7 +649,7 @@ 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:
@@ -660,14 +659,14 @@ 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
@@ -680,44 +679,39 @@ 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]
-
- Stage: Stage-3
- Spark
-#### A masked pattern was here ####
- Vertices:
- Map 1
+ /src [w]
+ Map 3
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
+ 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 _col1 (type: string)
- Position of Big Table: 1
+ Position of Big Table: 0
Local Work:
Map Reduce Local Work
Path -> Alias:
@@ -725,7 +719,7 @@ 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 +729,14 @@ 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
@@ -755,20 +749,20 @@ 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
@@ -783,22 +777,11 @@ STAGE PLANS:
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
+ Spark HashTable Sink Operator
keys:
- 0 _col0 (type: string)
+ 0 _col1 (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:
@@ -875,57 +858,68 @@ STAGE PLANS:
keys:
0 _col0 (type: string)
1 _col1 (type: string)
- outputColumnNames: _col1, _col4
+ outputColumnNames: _col1
input vertices:
- 1 Map 4
+ 1 Map 3
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 _col1 (type: string)
- outputColumnNames: _col1, _col3, _col6
+ 0 _col1 (type: string)
+ 1 _col0 (type: string)
+ outputColumnNames: _col1, _col4
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)
- outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- GlobalTableId: 1
-#### A masked pattern was here ####
- NumFilesPerFileSink: 1
- Statistics: Num rows: 302 Data size: 3213 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:
- COLUMN_STATS_ACCURATE true
- bucket_count -1
- columns key,value,val2
- columns.comments
- columns.types string:string:string
-#### A masked pattern was here ####
- name default.dest_j1
- numFiles 1
- numRows 85
- rawDataSize 1600
- serialization.ddl struct dest_j1 { string key, string value, string val2}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 1685
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.dest_j1
- TotalFiles: 1
- GatherStats: true
- MultiFileSpray: false
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col0 (type: string)
+ 1 _col1 (type: string)
+ outputColumnNames: _col1, _col3, _col6
+ input vertices:
+ 0 Map 1
+ Position of Big Table: 1
+ Statistics: Num rows: 332 Data size: 3534 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col3 (type: string), _col6 (type: string), _col1 (type: string)
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 332 Data size: 3534 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ GlobalTableId: 1
+#### A masked pattern was here ####
+ NumFilesPerFileSink: 1
+ Statistics: Num rows: 332 Data size: 3534 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:
+ COLUMN_STATS_ACCURATE true
+ bucket_count -1
+ columns key,value,val2
+ columns.comments
+ columns.types string:string:string
+#### A masked pattern was here ####
+ name default.dest_j1
+ numFiles 1
+ numRows 85
+ rawDataSize 1600
+ serialization.ddl struct dest_j1 { string key, string value, string val2}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ totalSize 1685
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.dest_j1
+ TotalFiles: 1
+ GatherStats: true
+ MultiFileSpray: false
Local Work:
Map Reduce Local Work
Path -> Alias:
Modified: hive/trunk/ql/src/test/results/clientpositive/spark/join33.q.out
URL: http://svn.apache.org/viewvc/hive/trunk/ql/src/test/results/clientpositive/spark/join33.q.out?rev=1674738&r1=1674737&r2=1674738&view=diff
==============================================================================
--- hive/trunk/ql/src/test/results/clientpositive/spark/join33.q.out (original)
+++ hive/trunk/ql/src/test/results/clientpositive/spark/join33.q.out Mon Apr 20 06:14:38 2015
@@ -113,16 +113,16 @@ STAGE PLANS:
Map 1
Map Operator Tree:
TableScan
- alias: y
+ alias: z
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)
+ predicate: ((11.0 = 11.0) and value 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: value (type: string)
+ outputColumnNames: _col0
Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
Spark HashTable Sink Operator
keys:
@@ -136,9 +136,12 @@ STAGE PLANS:
Path -> Partition:
#### A masked pattern was here ####
Partition
- base file name: src
+ base file name: hr=11
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ partition values:
+ ds 2008-04-08
+ hr 11
properties:
COLUMN_STATS_ACCURATE true
bucket_count -1
@@ -146,11 +149,13 @@ STAGE PLANS:
columns.comments 'default','default'
columns.types string:string
#### A masked pattern was here ####
- name default.src
+ name default.srcpart
numFiles 1
numRows 500
+ partition_columns ds/hr
+ partition_columns.types string:string
rawDataSize 5312
- serialization.ddl struct src { string key, string value}
+ serialization.ddl struct srcpart { string key, string value}
serialization.format 1
serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
totalSize 5812
@@ -160,26 +165,23 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE true
bucket_count -1
columns key,value
columns.comments 'default','default'
columns.types string:string
#### A masked pattern was here ####
- name default.src
- numFiles 1
- numRows 500
- rawDataSize 5312
- serialization.ddl struct src { string key, string value}
+ name default.srcpart
+ partition_columns ds/hr
+ partition_columns.types string:string
+ serialization.ddl struct srcpart { string key, string value}
serialization.format 1
serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 5812
#### A masked pattern was here ####
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.src
- name: default.src
+ name: default.srcpart
+ name: default.srcpart
Truncated Path -> Alias:
- /src [y]
+ /srcpart/ds=2008-04-08/hr=11 [z]
Map 3
Map Operator Tree:
TableScan
@@ -188,7 +190,7 @@ STAGE PLANS:
GatherStats: false
Filter Operator
isSamplingPred: false
- predicate: (value is not null and key is not null) (type: boolean)
+ predicate: (key is not null and value 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)
@@ -197,7 +199,7 @@ STAGE PLANS:
Spark HashTable Sink Operator
keys:
0 _col0 (type: string)
- 1 _col1 (type: string)
+ 1 _col0 (type: string)
Position of Big Table: 0
Local Work:
Map Reduce Local Work
@@ -258,24 +260,24 @@ STAGE PLANS:
Map 2
Map Operator Tree:
TableScan
- alias: z
+ alias: y
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
GatherStats: false
Filter Operator
isSamplingPred: false
- predicate: ((11.0 = 11.0) and value is not null) (type: boolean)
+ predicate: key is not null (type: boolean)
Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
Select Operator
- expressions: value (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
Map Join Operator
condition map:
Inner Join 0 to 1
keys:
0 _col0 (type: string)
- 1 _col1 (type: string)
- outputColumnNames: _col0, _col3
+ 1 _col0 (type: string)
+ outputColumnNames: _col1, _col2, _col3
input vertices:
1 Map 3
Position of Big Table: 0
@@ -286,13 +288,13 @@ STAGE PLANS:
keys:
0 _col0 (type: string)
1 _col3 (type: string)
- outputColumnNames: _col1, _col2, _col5
+ outputColumnNames: _col0, _col4, _col5
input vertices:
0 Map 1
Position of Big Table: 1
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: _col5 (type: string), _col0 (type: string), _col4 (type: string)
outputColumnNames: _col0, _col1, _col2
Statistics: Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE
File Output Operator
@@ -328,12 +330,9 @@ STAGE PLANS:
Path -> Partition:
#### A masked pattern was here ####
Partition
- base file name: hr=11
+ base file name: src
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- partition values:
- ds 2008-04-08
- hr 11
properties:
COLUMN_STATS_ACCURATE true
bucket_count -1
@@ -341,13 +340,11 @@ STAGE PLANS:
columns.comments 'default','default'
columns.types string:string
#### A masked pattern was here ####
- name default.srcpart
+ name default.src
numFiles 1
numRows 500
- partition_columns ds/hr
- partition_columns.types string:string
rawDataSize 5312
- serialization.ddl struct srcpart { string key, string value}
+ serialization.ddl struct src { string key, string value}
serialization.format 1
serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
totalSize 5812
@@ -357,23 +354,26 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
+ COLUMN_STATS_ACCURATE true
bucket_count -1
columns key,value
columns.comments 'default','default'
columns.types string:string
#### A masked pattern was here ####
- name default.srcpart
- partition_columns ds/hr
- partition_columns.types string:string
- serialization.ddl struct srcpart { string key, string value}
+ name default.src
+ numFiles 1
+ 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 5812
#### A masked pattern was here ####
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.srcpart
- name: default.srcpart
+ name: default.src
+ name: default.src
Truncated Path -> Alias:
- /srcpart/ds=2008-04-08/hr=11 [z]
+ /src [y]
Stage: Stage-0
Move Operator
@@ -422,8 +422,8 @@ POSTHOOK: Input: default@srcpart
POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
POSTHOOK: Output: default@dest_j1
POSTHOOK: Lineage: dest_j1.key SIMPLE [(src1)x.FieldSchema(name:key, type:string, comment:default), ]
-POSTHOOK: Lineage: dest_j1.val2 SIMPLE [(src)y.FieldSchema(name:value, type:string, comment:default), ]
-POSTHOOK: Lineage: dest_j1.value EXPRESSION [(srcpart)z.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: dest_j1.val2 EXPRESSION [(src)y.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: dest_j1.value SIMPLE [(srcpart)z.FieldSchema(name:value, type:string, comment:default), ]
PREHOOK: query: select * from dest_j1
PREHOOK: type: QUERY
PREHOOK: Input: default@dest_j1
Modified: hive/trunk/ql/src/test/results/clientpositive/spark/join_alt_syntax.q.out
URL: http://svn.apache.org/viewvc/hive/trunk/ql/src/test/results/clientpositive/spark/join_alt_syntax.q.out?rev=1674738&r1=1674737&r2=1674738&view=diff
==============================================================================
--- hive/trunk/ql/src/test/results/clientpositive/spark/join_alt_syntax.q.out (original)
+++ hive/trunk/ql/src/test/results/clientpositive/spark/join_alt_syntax.q.out Mon Apr 20 06:14:38 2015
@@ -390,9 +390,9 @@ STAGE PLANS:
Stage: Stage-1
Spark
Edges:
+ Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 2), Map 4 (PARTITION-LEVEL SORT, 2)
Reducer 6 <- Map 5 (PARTITION-LEVEL SORT, 2), Map 7 (PARTITION-LEVEL SORT, 2)
- Reducer 4 <- Map 3 (PARTITION-LEVEL SORT, 2), Reducer 6 (PARTITION-LEVEL SORT, 2)
- Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 2), Reducer 4 (PARTITION-LEVEL SORT, 2)
+ Reducer 3 <- Reducer 2 (PARTITION-LEVEL SORT, 2), Reducer 6 (PARTITION-LEVEL SORT, 2)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -401,69 +401,71 @@ STAGE PLANS:
alias: p1
Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: p_partkey is not null (type: boolean)
- Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE
+ predicate: (p_partkey is not null and p_name is not null) (type: boolean)
+ Statistics: Num rows: 7 Data size: 847 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: p_partkey (type: int), p_name (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 7 Data size: 847 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 7 Data size: 847 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: string)
- Map 3
+ Map 4
Map Operator Tree:
TableScan
alias: p1
Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: p_name is not null (type: boolean)
+ predicate: p_partkey is not null (type: boolean)
Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE
Select Operator
- expressions: p_name (type: string)
- outputColumnNames: _col0
+ expressions: p_partkey (type: int), p_name (type: string)
+ outputColumnNames: _col0, _col1
Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
- key expressions: _col0 (type: string)
+ key expressions: _col0 (type: int)
sort order: +
- Map-reduce partition columns: _col0 (type: string)
+ 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)
Map 5
Map Operator Tree:
TableScan
alias: p1
Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: (p_partkey is not null and p_name is not null) (type: boolean)
+ predicate: (p_name is not null and p_partkey is not null) (type: boolean)
Statistics: Num rows: 7 Data size: 847 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: p_partkey (type: int), p_name (type: string)
outputColumnNames: _col0, _col1
Statistics: Num rows: 7 Data size: 847 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
- key expressions: _col0 (type: int), _col1 (type: string)
- sort order: ++
- Map-reduce partition columns: _col0 (type: int), _col1 (type: string)
+ key expressions: _col1 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col1 (type: string)
Statistics: Num rows: 7 Data size: 847 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: int)
Map 7
Map Operator Tree:
TableScan
alias: p1
Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: (p_partkey is not null and p_name is not null) (type: boolean)
- Statistics: Num rows: 7 Data size: 847 Basic stats: COMPLETE Column stats: NONE
+ predicate: p_name is not null (type: boolean)
+ Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE
Select Operator
- expressions: p_partkey (type: int), p_name (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 7 Data size: 847 Basic stats: COMPLETE Column stats: NONE
+ expressions: p_name (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
- key expressions: _col0 (type: int), _col1 (type: string)
- sort order: ++
- Map-reduce partition columns: _col0 (type: int), _col1 (type: string)
- Statistics: Num rows: 7 Data size: 847 Basic stats: COMPLETE Column stats: NONE
+ key expressions: _col0 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE
Reducer 2
Reduce Operator Tree:
Join Operator
@@ -471,11 +473,27 @@ STAGE PLANS:
Inner Join 0 to 1
keys:
0 _col0 (type: int)
- 1 _col1 (type: int)
- outputColumnNames: _col1, _col2, _col4, _col6
+ 1 _col0 (type: int)
+ outputColumnNames: _col0, _col1, _col3
+ Statistics: Num rows: 14 Data size: 1730 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: int), _col1 (type: string)
+ sort order: ++
+ Map-reduce partition columns: _col0 (type: int), _col1 (type: string)
+ Statistics: Num rows: 14 Data size: 1730 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col3 (type: string)
+ Reducer 3
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col0 (type: int), _col1 (type: string)
+ 1 _col0 (type: int), _col1 (type: string)
+ outputColumnNames: _col1, _col3, _col5, _col6
Statistics: Num rows: 15 Data size: 1903 Basic stats: COMPLETE Column stats: NONE
Select Operator
- expressions: _col4 (type: string), _col6 (type: string), _col2 (type: string), _col1 (type: string)
+ expressions: _col1 (type: string), _col5 (type: string), _col6 (type: string), _col3 (type: string)
outputColumnNames: _col0, _col1, _col2, _col3
Statistics: Num rows: 15 Data size: 1903 Basic stats: COMPLETE Column stats: NONE
File Output Operator
@@ -485,38 +503,22 @@ 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 4
+ Reducer 6
Reduce Operator Tree:
Join Operator
condition map:
Inner Join 0 to 1
keys:
- 0 _col0 (type: string)
- 1 _col3 (type: string)
- outputColumnNames: _col0, _col1, _col2, _col4
+ 0 _col1 (type: string)
+ 1 _col0 (type: string)
+ outputColumnNames: _col0, _col1, _col2
Statistics: Num rows: 14 Data size: 1730 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
- key expressions: _col1 (type: int)
- sort order: +
- Map-reduce partition columns: _col1 (type: int)
+ key expressions: _col0 (type: int), _col1 (type: string)
+ sort order: ++
+ Map-reduce partition columns: _col0 (type: int), _col1 (type: string)
Statistics: Num rows: 14 Data size: 1730 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col0 (type: string), _col2 (type: string), _col4 (type: string)
- Reducer 6
- Reduce Operator Tree:
- Join Operator
- condition map:
- Inner Join 0 to 1
- keys:
- 0 _col0 (type: int), _col1 (type: string)
- 1 _col0 (type: int), _col1 (type: string)
- outputColumnNames: _col0, _col1, _col3
- Statistics: Num rows: 7 Data size: 931 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col3 (type: string)
- sort order: +
- Map-reduce partition columns: _col3 (type: string)
- Statistics: Num rows: 7 Data size: 931 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col0 (type: int), _col1 (type: string)
+ value expressions: _col2 (type: string)
Stage: Stage-0
Fetch Operator
@@ -542,9 +544,9 @@ STAGE PLANS:
Stage: Stage-1
Spark
Edges:
+ Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 2), Map 4 (PARTITION-LEVEL SORT, 2)
Reducer 6 <- Map 5 (PARTITION-LEVEL SORT, 2), Map 7 (PARTITION-LEVEL SORT, 2)
- Reducer 4 <- Map 3 (PARTITION-LEVEL SORT, 2), Reducer 6 (PARTITION-LEVEL SORT, 2)
- Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 2), Reducer 4 (PARTITION-LEVEL SORT, 2)
+ Reducer 3 <- Reducer 2 (PARTITION-LEVEL SORT, 2), Reducer 6 (PARTITION-LEVEL SORT, 2)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -553,35 +555,36 @@ STAGE PLANS:
alias: p1
Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: p_partkey is not null (type: boolean)
- Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE
+ predicate: (p_partkey is not null and p_name is not null) (type: boolean)
+ Statistics: Num rows: 7 Data size: 847 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: p_partkey (type: int), p_name (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 7 Data size: 847 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 7 Data size: 847 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: string)
- Map 3
+ Map 4
Map Operator Tree:
TableScan
alias: p1
Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: p_name is not null (type: boolean)
+ predicate: p_partkey is not null (type: boolean)
Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE
Select Operator
- expressions: p_name (type: string)
- outputColumnNames: _col0
+ expressions: p_partkey (type: int), p_name (type: string)
+ outputColumnNames: _col0, _col1
Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
- key expressions: _col0 (type: string)
+ key expressions: _col0 (type: int)
sort order: +
- Map-reduce partition columns: _col0 (type: string)
+ 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)
Map 5
Map Operator Tree:
TableScan
@@ -595,27 +598,28 @@ STAGE PLANS:
outputColumnNames: _col0, _col1
Statistics: Num rows: 7 Data size: 847 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
- key expressions: _col1 (type: string), _col0 (type: int)
- sort order: ++
- Map-reduce partition columns: _col1 (type: string), _col0 (type: int)
+ key expressions: _col1 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col1 (type: string)
Statistics: Num rows: 7 Data size: 847 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: int)
Map 7
Map Operator Tree:
TableScan
alias: p1
Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: (p_name is not null and p_partkey is not null) (type: boolean)
- Statistics: Num rows: 7 Data size: 847 Basic stats: COMPLETE Column stats: NONE
+ predicate: p_name is not null (type: boolean)
+ Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE
Select Operator
- expressions: p_partkey (type: int), p_name (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 7 Data size: 847 Basic stats: COMPLETE Column stats: NONE
+ expressions: p_name (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
- key expressions: _col1 (type: string), _col0 (type: int)
- sort order: ++
- Map-reduce partition columns: _col1 (type: string), _col0 (type: int)
- Statistics: Num rows: 7 Data size: 847 Basic stats: COMPLETE Column stats: NONE
+ key expressions: _col0 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE
Reducer 2
Reduce Operator Tree:
Join Operator
@@ -623,11 +627,27 @@ STAGE PLANS:
Inner Join 0 to 1
keys:
0 _col0 (type: int)
- 1 _col1 (type: int)
- outputColumnNames: _col1, _col2, _col4, _col6
+ 1 _col0 (type: int)
+ outputColumnNames: _col0, _col1, _col3
+ Statistics: Num rows: 14 Data size: 1730 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col1 (type: string), _col0 (type: int)
+ sort order: ++
+ Map-reduce partition columns: _col1 (type: string), _col0 (type: int)
+ Statistics: Num rows: 14 Data size: 1730 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col3 (type: string)
+ Reducer 3
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col1 (type: string), _col0 (type: int)
+ 1 _col1 (type: string), _col0 (type: int)
+ outputColumnNames: _col1, _col3, _col5, _col6
Statistics: Num rows: 15 Data size: 1903 Basic stats: COMPLETE Column stats: NONE
Select Operator
- expressions: _col4 (type: string), _col6 (type: string), _col2 (type: string), _col1 (type: string)
+ expressions: _col1 (type: string), _col5 (type: string), _col6 (type: string), _col3 (type: string)
outputColumnNames: _col0, _col1, _col2, _col3
Statistics: Num rows: 15 Data size: 1903 Basic stats: COMPLETE Column stats: NONE
File Output Operator
@@ -637,38 +657,22 @@ 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 4
+ Reducer 6
Reduce Operator Tree:
Join Operator
condition map:
Inner Join 0 to 1
keys:
- 0 _col0 (type: string)
- 1 _col3 (type: string)
- outputColumnNames: _col0, _col1, _col2, _col4
+ 0 _col1 (type: string)
+ 1 _col0 (type: string)
+ outputColumnNames: _col0, _col1, _col2
Statistics: Num rows: 14 Data size: 1730 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
- key expressions: _col1 (type: int)
- sort order: +
- Map-reduce partition columns: _col1 (type: int)
+ key expressions: _col1 (type: string), _col0 (type: int)
+ sort order: ++
+ Map-reduce partition columns: _col1 (type: string), _col0 (type: int)
Statistics: Num rows: 14 Data size: 1730 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col0 (type: string), _col2 (type: string), _col4 (type: string)
- Reducer 6
- Reduce Operator Tree:
- Join Operator
- condition map:
- Inner Join 0 to 1
- keys:
- 0 _col1 (type: string), _col0 (type: int)
- 1 _col1 (type: string), _col0 (type: int)
- outputColumnNames: _col0, _col1, _col3
- Statistics: Num rows: 7 Data size: 931 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col3 (type: string)
- sort order: +
- Map-reduce partition columns: _col3 (type: string)
- Statistics: Num rows: 7 Data size: 931 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col0 (type: int), _col1 (type: string)
+ value expressions: _col2 (type: string)
Stage: Stage-0
Fetch Operator