You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@hive.apache.org by xu...@apache.org on 2014/12/15 18:11:42 UTC
svn commit: r1642997 [39/42] - in /hive/branches/spark:
itests/src/test/resources/
ql/src/java/org/apache/hadoop/hive/ql/optimizer/spark/
ql/src/test/results/clientpositive/spark/
Modified: hive/branches/spark/ql/src/test/results/clientpositive/spark/sort_merge_join_desc_3.q.out
URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/sort_merge_join_desc_3.q.out?rev=1642997&r1=1642996&r2=1642997&view=diff
==============================================================================
--- hive/branches/spark/ql/src/test/results/clientpositive/spark/sort_merge_join_desc_3.q.out (original)
+++ hive/branches/spark/ql/src/test/results/clientpositive/spark/sort_merge_join_desc_3.q.out Tue Dec 2 19:57:10 2014
@@ -63,72 +63,63 @@ select /*+ mapjoin(b) */ count(*) from t
on a.key=b.key and a.value=b.value where a.key < 10
POSTHOOK: type: QUERY
STAGE DEPENDENCIES:
- Stage-2 is a root stage
- Stage-1 depends on stages: Stage-2
+ Stage-1 is a root stage
Stage-0 depends on stages: Stage-1
STAGE PLANS:
- Stage: Stage-2
+ Stage: Stage-1
Spark
+ Edges:
+ Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 3), Map 4 (PARTITION-LEVEL SORT, 3)
+ Reducer 3 <- Reducer 2 (GROUP, 1)
#### A masked pattern was here ####
Vertices:
- Map 3
+ Map 1
Map Operator Tree:
TableScan
- alias: b
+ alias: a
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
Filter Operator
predicate: ((key is not null and value is not null) and (key < 10)) (type: boolean)
Statistics: Num rows: 41 Data size: 435 Basic stats: COMPLETE Column stats: NONE
- Spark HashTable Sink Operator
- condition expressions:
- 0
- 1
- keys:
- 0 key (type: string), value (type: string)
- 1 key (type: string), value (type: string)
- Local Work:
- Map Reduce Local Work
-
- Stage: Stage-1
- Spark
- Edges:
- Reducer 2 <- Map 1 (GROUP, 1)
-#### A masked pattern was here ####
- Vertices:
- Map 1
+ Reduce Output Operator
+ key expressions: key (type: string), value (type: string)
+ sort order: ++
+ Map-reduce partition columns: key (type: string), value (type: string)
+ Statistics: Num rows: 41 Data size: 435 Basic stats: COMPLETE Column stats: NONE
+ Map 4
Map Operator Tree:
TableScan
- alias: a
+ alias: b
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
Filter Operator
predicate: ((key is not null and value is not null) and (key < 10)) (type: boolean)
Statistics: Num rows: 41 Data size: 435 Basic stats: COMPLETE Column stats: NONE
- Map Join Operator
- condition map:
- Inner Join 0 to 1
- condition expressions:
- 0
- 1
- keys:
- 0 key (type: string), value (type: string)
- 1 key (type: string), value (type: string)
- input vertices:
- 1 Map 3
- Statistics: Num rows: 45 Data size: 478 Basic stats: COMPLETE Column stats: NONE
- Group By Operator
- aggregations: count()
- mode: hash
- outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- sort order:
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col0 (type: bigint)
- Local Work:
- Map Reduce Local Work
+ Reduce Output Operator
+ key expressions: key (type: string), value (type: string)
+ sort order: ++
+ Map-reduce partition columns: key (type: string), value (type: string)
+ Statistics: Num rows: 41 Data size: 435 Basic stats: COMPLETE Column stats: NONE
Reducer 2
Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0
+ 1
+ Statistics: Num rows: 45 Data size: 478 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: count()
+ mode: hash
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: bigint)
+ Reducer 3
+ Reduce Operator Tree:
Group By Operator
aggregations: count(VALUE._col0)
mode: mergepartial
Modified: hive/branches/spark/ql/src/test/results/clientpositive/spark/sort_merge_join_desc_4.q.out
URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/sort_merge_join_desc_4.q.out?rev=1642997&r1=1642996&r2=1642997&view=diff
==============================================================================
--- hive/branches/spark/ql/src/test/results/clientpositive/spark/sort_merge_join_desc_4.q.out (original)
+++ hive/branches/spark/ql/src/test/results/clientpositive/spark/sort_merge_join_desc_4.q.out Tue Dec 2 19:57:10 2014
@@ -61,72 +61,63 @@ select /*+ mapjoin(b) */ count(*) from t
on a.key=b.key and a.value=b.value where a.key < 10
POSTHOOK: type: QUERY
STAGE DEPENDENCIES:
- Stage-2 is a root stage
- Stage-1 depends on stages: Stage-2
+ Stage-1 is a root stage
Stage-0 depends on stages: Stage-1
STAGE PLANS:
- Stage: Stage-2
+ Stage: Stage-1
Spark
+ Edges:
+ Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 3), Map 4 (PARTITION-LEVEL SORT, 3)
+ Reducer 3 <- Reducer 2 (GROUP, 1)
#### A masked pattern was here ####
Vertices:
- Map 3
+ Map 1
Map Operator Tree:
TableScan
- alias: b
+ alias: a
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
Filter Operator
predicate: ((key is not null and value is not null) and (key < 10)) (type: boolean)
Statistics: Num rows: 41 Data size: 435 Basic stats: COMPLETE Column stats: NONE
- Spark HashTable Sink Operator
- condition expressions:
- 0
- 1
- keys:
- 0 key (type: string), value (type: string)
- 1 key (type: string), value (type: string)
- Local Work:
- Map Reduce Local Work
-
- Stage: Stage-1
- Spark
- Edges:
- Reducer 2 <- Map 1 (GROUP, 1)
-#### A masked pattern was here ####
- Vertices:
- Map 1
+ Reduce Output Operator
+ key expressions: key (type: string), value (type: string)
+ sort order: ++
+ Map-reduce partition columns: key (type: string), value (type: string)
+ Statistics: Num rows: 41 Data size: 435 Basic stats: COMPLETE Column stats: NONE
+ Map 4
Map Operator Tree:
TableScan
- alias: a
+ alias: b
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
Filter Operator
predicate: ((key is not null and value is not null) and (key < 10)) (type: boolean)
Statistics: Num rows: 41 Data size: 435 Basic stats: COMPLETE Column stats: NONE
- Map Join Operator
- condition map:
- Inner Join 0 to 1
- condition expressions:
- 0
- 1
- keys:
- 0 key (type: string), value (type: string)
- 1 key (type: string), value (type: string)
- input vertices:
- 1 Map 3
- Statistics: Num rows: 45 Data size: 478 Basic stats: COMPLETE Column stats: NONE
- Group By Operator
- aggregations: count()
- mode: hash
- outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- sort order:
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col0 (type: bigint)
- Local Work:
- Map Reduce Local Work
+ Reduce Output Operator
+ key expressions: key (type: string), value (type: string)
+ sort order: ++
+ Map-reduce partition columns: key (type: string), value (type: string)
+ Statistics: Num rows: 41 Data size: 435 Basic stats: COMPLETE Column stats: NONE
Reducer 2
Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0
+ 1
+ Statistics: Num rows: 45 Data size: 478 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: count()
+ mode: hash
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: bigint)
+ Reducer 3
+ Reduce Operator Tree:
Group By Operator
aggregations: count(VALUE._col0)
mode: mergepartial
Modified: hive/branches/spark/ql/src/test/results/clientpositive/spark/sort_merge_join_desc_5.q.out
URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/sort_merge_join_desc_5.q.out?rev=1642997&r1=1642996&r2=1642997&view=diff
==============================================================================
--- hive/branches/spark/ql/src/test/results/clientpositive/spark/sort_merge_join_desc_5.q.out (original)
+++ hive/branches/spark/ql/src/test/results/clientpositive/spark/sort_merge_join_desc_5.q.out Tue Dec 2 19:57:10 2014
@@ -112,35 +112,34 @@ TOK_QUERY
STAGE DEPENDENCIES:
- Stage-2 is a root stage
- Stage-1 depends on stages: Stage-2
+ Stage-1 is a root stage
Stage-0 depends on stages: Stage-1
STAGE PLANS:
- Stage: Stage-2
+ Stage: Stage-1
Spark
+ Edges:
+ Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 3), Map 4 (PARTITION-LEVEL SORT, 3)
+ Reducer 3 <- Reducer 2 (GROUP, 1)
#### A masked pattern was here ####
Vertices:
- Map 3
+ Map 1
Map Operator Tree:
TableScan
- alias: b
+ alias: a
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: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
- Spark HashTable Sink Operator
- condition expressions:
- 0
- 1
- keys:
- 0 key (type: int)
- 1 key (type: int)
- Position of Big Table: 0
- Local Work:
- Map Reduce Local Work
+ Reduce Output Operator
+ key expressions: key (type: int)
+ sort order: +
+ Map-reduce partition columns: key (type: int)
+ Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ tag: 0
+ auto parallelism: false
Path -> Alias:
#### A masked pattern was here ####
Path -> Partition:
@@ -159,13 +158,13 @@ STAGE PLANS:
columns.comments
columns.types int:string
#### A masked pattern was here ####
- name default.srcbucket_mapjoin_part_2
+ name default.srcbucket_mapjoin_part_1
numFiles 1
numRows 500
partition_columns part
partition_columns.types string
rawDataSize 5312
- serialization.ddl struct srcbucket_mapjoin_part_2 { i32 key, string value}
+ serialization.ddl struct srcbucket_mapjoin_part_1 { i32 key, string value}
serialization.format 1
serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
totalSize 5812
@@ -182,61 +181,35 @@ STAGE PLANS:
columns.comments
columns.types int:string
#### A masked pattern was here ####
- name default.srcbucket_mapjoin_part_2
+ name default.srcbucket_mapjoin_part_1
partition_columns part
partition_columns.types string
- serialization.ddl struct srcbucket_mapjoin_part_2 { i32 key, string value}
+ serialization.ddl struct srcbucket_mapjoin_part_1 { i32 key, string value}
serialization.format 1
serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
#### A masked pattern was here ####
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.srcbucket_mapjoin_part_2
- name: default.srcbucket_mapjoin_part_2
+ name: default.srcbucket_mapjoin_part_1
+ name: default.srcbucket_mapjoin_part_1
Truncated Path -> Alias:
- /srcbucket_mapjoin_part_2/part=1 [b]
-
- Stage: Stage-1
- Spark
- Edges:
- Reducer 2 <- Map 1 (GROUP, 1)
-#### A masked pattern was here ####
- Vertices:
- Map 1
+ /srcbucket_mapjoin_part_1/part=1 [a]
+ Map 4
Map Operator Tree:
TableScan
- alias: a
+ alias: b
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: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
- Map Join Operator
- condition map:
- Inner Join 0 to 1
- condition expressions:
- 0
- 1
- keys:
- 0 key (type: int)
- 1 key (type: int)
- input vertices:
- 1 Map 3
- Position of Big Table: 0
- Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
- Group By Operator
- aggregations: count()
- mode: hash
- outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- sort order:
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
- tag: -1
- value expressions: _col0 (type: bigint)
- auto parallelism: false
- Local Work:
- Map Reduce Local Work
+ Reduce Output Operator
+ key expressions: key (type: int)
+ sort order: +
+ Map-reduce partition columns: key (type: int)
+ Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ tag: 1
+ auto parallelism: false
Path -> Alias:
#### A masked pattern was here ####
Path -> Partition:
@@ -255,13 +228,13 @@ STAGE PLANS:
columns.comments
columns.types int:string
#### A masked pattern was here ####
- name default.srcbucket_mapjoin_part_1
+ name default.srcbucket_mapjoin_part_2
numFiles 1
numRows 500
partition_columns part
partition_columns.types string
rawDataSize 5312
- serialization.ddl struct srcbucket_mapjoin_part_1 { i32 key, string value}
+ serialization.ddl struct srcbucket_mapjoin_part_2 { i32 key, string value}
serialization.format 1
serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
totalSize 5812
@@ -278,19 +251,40 @@ STAGE PLANS:
columns.comments
columns.types int:string
#### A masked pattern was here ####
- name default.srcbucket_mapjoin_part_1
+ name default.srcbucket_mapjoin_part_2
partition_columns part
partition_columns.types string
- serialization.ddl struct srcbucket_mapjoin_part_1 { i32 key, string value}
+ serialization.ddl struct srcbucket_mapjoin_part_2 { i32 key, string value}
serialization.format 1
serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
#### A masked pattern was here ####
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.srcbucket_mapjoin_part_1
- name: default.srcbucket_mapjoin_part_1
+ name: default.srcbucket_mapjoin_part_2
+ name: default.srcbucket_mapjoin_part_2
Truncated Path -> Alias:
- /srcbucket_mapjoin_part_1/part=1 [a]
+ /srcbucket_mapjoin_part_2/part=1 [b]
Reducer 2
+ Needs Tagging: true
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0
+ 1
+ Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: count()
+ mode: hash
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ tag: -1
+ value expressions: _col0 (type: bigint)
+ auto parallelism: false
+ Reducer 3
Needs Tagging: false
Reduce Operator Tree:
Group By Operator
Modified: hive/branches/spark/ql/src/test/results/clientpositive/spark/sort_merge_join_desc_6.q.out
URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/sort_merge_join_desc_6.q.out?rev=1642997&r1=1642996&r2=1642997&view=diff
==============================================================================
--- hive/branches/spark/ql/src/test/results/clientpositive/spark/sort_merge_join_desc_6.q.out (original)
+++ hive/branches/spark/ql/src/test/results/clientpositive/spark/sort_merge_join_desc_6.q.out Tue Dec 2 19:57:10 2014
@@ -112,35 +112,34 @@ TOK_QUERY
STAGE DEPENDENCIES:
- Stage-2 is a root stage
- Stage-1 depends on stages: Stage-2
+ Stage-1 is a root stage
Stage-0 depends on stages: Stage-1
STAGE PLANS:
- Stage: Stage-2
+ Stage: Stage-1
Spark
+ Edges:
+ Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 3), Map 4 (PARTITION-LEVEL SORT, 3)
+ Reducer 3 <- Reducer 2 (GROUP, 1)
#### A masked pattern was here ####
Vertices:
- Map 3
+ Map 1
Map Operator Tree:
TableScan
- alias: b
+ alias: a
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: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
- Spark HashTable Sink Operator
- condition expressions:
- 0
- 1
- keys:
- 0 key (type: int)
- 1 key (type: int)
- Position of Big Table: 0
- Local Work:
- Map Reduce Local Work
+ Reduce Output Operator
+ key expressions: key (type: int)
+ sort order: +
+ Map-reduce partition columns: key (type: int)
+ Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ tag: 0
+ auto parallelism: false
Path -> Alias:
#### A masked pattern was here ####
Path -> Partition:
@@ -159,13 +158,13 @@ STAGE PLANS:
columns.comments
columns.types int:string
#### A masked pattern was here ####
- name default.srcbucket_mapjoin_part_2
+ name default.srcbucket_mapjoin_part_1
numFiles 2
numRows 500
partition_columns part
partition_columns.types string
rawDataSize 5312
- serialization.ddl struct srcbucket_mapjoin_part_2 { i32 key, string value}
+ serialization.ddl struct srcbucket_mapjoin_part_1 { i32 key, string value}
serialization.format 1
serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
totalSize 5812
@@ -175,67 +174,42 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
+ SORTBUCKETCOLSPREFIX TRUE
bucket_count 2
bucket_field_name key
columns key,value
columns.comments
columns.types int:string
#### A masked pattern was here ####
- name default.srcbucket_mapjoin_part_2
+ name default.srcbucket_mapjoin_part_1
partition_columns part
partition_columns.types string
- serialization.ddl struct srcbucket_mapjoin_part_2 { i32 key, string value}
+ serialization.ddl struct srcbucket_mapjoin_part_1 { i32 key, string value}
serialization.format 1
serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
#### A masked pattern was here ####
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.srcbucket_mapjoin_part_2
- name: default.srcbucket_mapjoin_part_2
+ name: default.srcbucket_mapjoin_part_1
+ name: default.srcbucket_mapjoin_part_1
Truncated Path -> Alias:
- /srcbucket_mapjoin_part_2/part=1 [b]
-
- Stage: Stage-1
- Spark
- Edges:
- Reducer 2 <- Map 1 (GROUP, 1)
-#### A masked pattern was here ####
- Vertices:
- Map 1
+ /srcbucket_mapjoin_part_1/part=1 [a]
+ Map 4
Map Operator Tree:
TableScan
- alias: a
+ alias: b
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: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
- Map Join Operator
- condition map:
- Inner Join 0 to 1
- condition expressions:
- 0
- 1
- keys:
- 0 key (type: int)
- 1 key (type: int)
- input vertices:
- 1 Map 3
- Position of Big Table: 0
- Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
- Group By Operator
- aggregations: count()
- mode: hash
- outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- sort order:
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
- tag: -1
- value expressions: _col0 (type: bigint)
- auto parallelism: false
- Local Work:
- Map Reduce Local Work
+ Reduce Output Operator
+ key expressions: key (type: int)
+ sort order: +
+ Map-reduce partition columns: key (type: int)
+ Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ tag: 1
+ auto parallelism: false
Path -> Alias:
#### A masked pattern was here ####
Path -> Partition:
@@ -254,13 +228,13 @@ STAGE PLANS:
columns.comments
columns.types int:string
#### A masked pattern was here ####
- name default.srcbucket_mapjoin_part_1
+ name default.srcbucket_mapjoin_part_2
numFiles 2
numRows 500
partition_columns part
partition_columns.types string
rawDataSize 5312
- serialization.ddl struct srcbucket_mapjoin_part_1 { i32 key, string value}
+ serialization.ddl struct srcbucket_mapjoin_part_2 { i32 key, string value}
serialization.format 1
serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
totalSize 5812
@@ -270,26 +244,46 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- SORTBUCKETCOLSPREFIX TRUE
bucket_count 2
bucket_field_name key
columns key,value
columns.comments
columns.types int:string
#### A masked pattern was here ####
- name default.srcbucket_mapjoin_part_1
+ name default.srcbucket_mapjoin_part_2
partition_columns part
partition_columns.types string
- serialization.ddl struct srcbucket_mapjoin_part_1 { i32 key, string value}
+ serialization.ddl struct srcbucket_mapjoin_part_2 { i32 key, string value}
serialization.format 1
serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
#### A masked pattern was here ####
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.srcbucket_mapjoin_part_1
- name: default.srcbucket_mapjoin_part_1
+ name: default.srcbucket_mapjoin_part_2
+ name: default.srcbucket_mapjoin_part_2
Truncated Path -> Alias:
- /srcbucket_mapjoin_part_1/part=1 [a]
+ /srcbucket_mapjoin_part_2/part=1 [b]
Reducer 2
+ Needs Tagging: true
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0
+ 1
+ Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: count()
+ mode: hash
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ tag: -1
+ value expressions: _col0 (type: bigint)
+ auto parallelism: false
+ Reducer 3
Needs Tagging: false
Reduce Operator Tree:
Group By Operator
Modified: hive/branches/spark/ql/src/test/results/clientpositive/spark/sort_merge_join_desc_7.q.out
URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/sort_merge_join_desc_7.q.out?rev=1642997&r1=1642996&r2=1642997&view=diff
==============================================================================
--- hive/branches/spark/ql/src/test/results/clientpositive/spark/sort_merge_join_desc_7.q.out (original)
+++ hive/branches/spark/ql/src/test/results/clientpositive/spark/sort_merge_join_desc_7.q.out Tue Dec 2 19:57:10 2014
@@ -148,35 +148,34 @@ TOK_QUERY
STAGE DEPENDENCIES:
- Stage-2 is a root stage
- Stage-1 depends on stages: Stage-2
+ Stage-1 is a root stage
Stage-0 depends on stages: Stage-1
STAGE PLANS:
- Stage: Stage-2
+ Stage: Stage-1
Spark
+ Edges:
+ Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 3), Map 4 (PARTITION-LEVEL SORT, 3)
+ Reducer 3 <- Reducer 2 (GROUP, 1)
#### A masked pattern was here ####
Vertices:
- Map 3
+ Map 1
Map Operator Tree:
TableScan
- alias: b
+ alias: a
Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
GatherStats: false
Filter Operator
isSamplingPred: false
predicate: key is not null (type: boolean)
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- Spark HashTable Sink Operator
- condition expressions:
- 0
- 1
- keys:
- 0 key (type: int)
- 1 key (type: int)
- Position of Big Table: 0
- Local Work:
- Map Reduce Local Work
+ Reduce Output Operator
+ key expressions: key (type: int)
+ sort order: +
+ Map-reduce partition columns: key (type: int)
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ tag: 0
+ auto parallelism: false
Path -> Alias:
#### A masked pattern was here ####
Path -> Partition:
@@ -195,13 +194,13 @@ STAGE PLANS:
columns.comments
columns.types int:string
#### A masked pattern was here ####
- name default.srcbucket_mapjoin_part_2
+ name default.srcbucket_mapjoin_part_1
numFiles 2
numRows 500
partition_columns part
partition_columns.types string
rawDataSize 5312
- serialization.ddl struct srcbucket_mapjoin_part_2 { i32 key, string value}
+ serialization.ddl struct srcbucket_mapjoin_part_1 { i32 key, string value}
serialization.format 1
serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
totalSize 5812
@@ -217,16 +216,16 @@ STAGE PLANS:
columns.comments
columns.types int:string
#### A masked pattern was here ####
- name default.srcbucket_mapjoin_part_2
+ name default.srcbucket_mapjoin_part_1
partition_columns part
partition_columns.types string
- serialization.ddl struct srcbucket_mapjoin_part_2 { i32 key, string value}
+ serialization.ddl struct srcbucket_mapjoin_part_1 { i32 key, string value}
serialization.format 1
serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
#### A masked pattern was here ####
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.srcbucket_mapjoin_part_2
- name: default.srcbucket_mapjoin_part_2
+ name: default.srcbucket_mapjoin_part_1
+ name: default.srcbucket_mapjoin_part_1
#### A masked pattern was here ####
Partition
base file name: part=2
@@ -242,13 +241,13 @@ STAGE PLANS:
columns.comments
columns.types int:string
#### A masked pattern was here ####
- name default.srcbucket_mapjoin_part_2
+ name default.srcbucket_mapjoin_part_1
numFiles 2
numRows 500
partition_columns part
partition_columns.types string
rawDataSize 5312
- serialization.ddl struct srcbucket_mapjoin_part_2 { i32 key, string value}
+ serialization.ddl struct srcbucket_mapjoin_part_1 { i32 key, string value}
serialization.format 1
serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
totalSize 5812
@@ -264,62 +263,36 @@ STAGE PLANS:
columns.comments
columns.types int:string
#### A masked pattern was here ####
- name default.srcbucket_mapjoin_part_2
+ name default.srcbucket_mapjoin_part_1
partition_columns part
partition_columns.types string
- serialization.ddl struct srcbucket_mapjoin_part_2 { i32 key, string value}
+ serialization.ddl struct srcbucket_mapjoin_part_1 { i32 key, string value}
serialization.format 1
serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
#### A masked pattern was here ####
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.srcbucket_mapjoin_part_2
- name: default.srcbucket_mapjoin_part_2
+ name: default.srcbucket_mapjoin_part_1
+ name: default.srcbucket_mapjoin_part_1
Truncated Path -> Alias:
- /srcbucket_mapjoin_part_2/part=1 [b]
- /srcbucket_mapjoin_part_2/part=2 [b]
-
- Stage: Stage-1
- Spark
- Edges:
- Reducer 2 <- Map 1 (GROUP, 1)
-#### A masked pattern was here ####
- Vertices:
- Map 1
+ /srcbucket_mapjoin_part_1/part=1 [a]
+ /srcbucket_mapjoin_part_1/part=2 [a]
+ Map 4
Map Operator Tree:
TableScan
- alias: a
+ alias: b
Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
GatherStats: false
Filter Operator
isSamplingPred: false
predicate: key is not null (type: boolean)
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- Map Join Operator
- condition map:
- Inner Join 0 to 1
- condition expressions:
- 0
- 1
- keys:
- 0 key (type: int)
- 1 key (type: int)
- input vertices:
- 1 Map 3
- Position of Big Table: 0
- Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
- Group By Operator
- aggregations: count()
- mode: hash
- outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- sort order:
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
- tag: -1
- value expressions: _col0 (type: bigint)
- auto parallelism: false
- Local Work:
- Map Reduce Local Work
+ Reduce Output Operator
+ key expressions: key (type: int)
+ sort order: +
+ Map-reduce partition columns: key (type: int)
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ tag: 1
+ auto parallelism: false
Path -> Alias:
#### A masked pattern was here ####
Path -> Partition:
@@ -338,13 +311,13 @@ STAGE PLANS:
columns.comments
columns.types int:string
#### A masked pattern was here ####
- name default.srcbucket_mapjoin_part_1
+ name default.srcbucket_mapjoin_part_2
numFiles 2
numRows 500
partition_columns part
partition_columns.types string
rawDataSize 5312
- serialization.ddl struct srcbucket_mapjoin_part_1 { i32 key, string value}
+ serialization.ddl struct srcbucket_mapjoin_part_2 { i32 key, string value}
serialization.format 1
serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
totalSize 5812
@@ -360,16 +333,16 @@ STAGE PLANS:
columns.comments
columns.types int:string
#### A masked pattern was here ####
- name default.srcbucket_mapjoin_part_1
+ name default.srcbucket_mapjoin_part_2
partition_columns part
partition_columns.types string
- serialization.ddl struct srcbucket_mapjoin_part_1 { i32 key, string value}
+ serialization.ddl struct srcbucket_mapjoin_part_2 { i32 key, string value}
serialization.format 1
serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
#### A masked pattern was here ####
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.srcbucket_mapjoin_part_1
- name: default.srcbucket_mapjoin_part_1
+ name: default.srcbucket_mapjoin_part_2
+ name: default.srcbucket_mapjoin_part_2
#### A masked pattern was here ####
Partition
base file name: part=2
@@ -385,13 +358,13 @@ STAGE PLANS:
columns.comments
columns.types int:string
#### A masked pattern was here ####
- name default.srcbucket_mapjoin_part_1
+ name default.srcbucket_mapjoin_part_2
numFiles 2
numRows 500
partition_columns part
partition_columns.types string
rawDataSize 5312
- serialization.ddl struct srcbucket_mapjoin_part_1 { i32 key, string value}
+ serialization.ddl struct srcbucket_mapjoin_part_2 { i32 key, string value}
serialization.format 1
serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
totalSize 5812
@@ -407,20 +380,41 @@ STAGE PLANS:
columns.comments
columns.types int:string
#### A masked pattern was here ####
- name default.srcbucket_mapjoin_part_1
+ name default.srcbucket_mapjoin_part_2
partition_columns part
partition_columns.types string
- serialization.ddl struct srcbucket_mapjoin_part_1 { i32 key, string value}
+ serialization.ddl struct srcbucket_mapjoin_part_2 { i32 key, string value}
serialization.format 1
serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
#### A masked pattern was here ####
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.srcbucket_mapjoin_part_1
- name: default.srcbucket_mapjoin_part_1
+ name: default.srcbucket_mapjoin_part_2
+ name: default.srcbucket_mapjoin_part_2
Truncated Path -> Alias:
- /srcbucket_mapjoin_part_1/part=1 [a]
- /srcbucket_mapjoin_part_1/part=2 [a]
+ /srcbucket_mapjoin_part_2/part=1 [b]
+ /srcbucket_mapjoin_part_2/part=2 [b]
Reducer 2
+ Needs Tagging: true
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0
+ 1
+ Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: count()
+ mode: hash
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ tag: -1
+ value expressions: _col0 (type: bigint)
+ auto parallelism: false
+ Reducer 3
Needs Tagging: false
Reduce Operator Tree:
Group By Operator
Modified: hive/branches/spark/ql/src/test/results/clientpositive/spark/sort_merge_join_desc_8.q.out
URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/sort_merge_join_desc_8.q.out?rev=1642997&r1=1642996&r2=1642997&view=diff
==============================================================================
--- hive/branches/spark/ql/src/test/results/clientpositive/spark/sort_merge_join_desc_8.q.out (original)
+++ hive/branches/spark/ql/src/test/results/clientpositive/spark/sort_merge_join_desc_8.q.out Tue Dec 2 19:57:10 2014
@@ -108,72 +108,63 @@ select /*+ mapjoin(b) */ count(*) from t
on a.key=b.key where a.key < 10
POSTHOOK: type: QUERY
STAGE DEPENDENCIES:
- Stage-2 is a root stage
- Stage-1 depends on stages: Stage-2
+ Stage-1 is a root stage
Stage-0 depends on stages: Stage-1
STAGE PLANS:
- Stage: Stage-2
+ Stage: Stage-1
Spark
+ Edges:
+ Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 3), Map 4 (PARTITION-LEVEL SORT, 3)
+ Reducer 3 <- Reducer 2 (GROUP, 1)
#### A masked pattern was here ####
Vertices:
- Map 3
+ Map 1
Map Operator Tree:
TableScan
- alias: b
+ alias: a
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
Filter Operator
predicate: (key < 10) (type: boolean)
Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
- Spark HashTable Sink Operator
- condition expressions:
- 0
- 1
- keys:
- 0 key (type: string)
- 1 key (type: string)
- Local Work:
- Map Reduce Local Work
-
- Stage: Stage-1
- Spark
- Edges:
- Reducer 2 <- Map 1 (GROUP, 1)
-#### A masked pattern was here ####
- Vertices:
- Map 1
+ Reduce Output Operator
+ key expressions: key (type: string)
+ sort order: +
+ Map-reduce partition columns: key (type: string)
+ Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
+ Map 4
Map Operator Tree:
TableScan
- alias: a
+ alias: b
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
Filter Operator
predicate: (key < 10) (type: boolean)
Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
- Map Join Operator
- condition map:
- Inner Join 0 to 1
- condition expressions:
- 0
- 1
- keys:
- 0 key (type: string)
- 1 key (type: string)
- input vertices:
- 1 Map 3
- Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE
- Group By Operator
- aggregations: count()
- mode: hash
- outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- sort order:
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col0 (type: bigint)
- Local Work:
- Map Reduce Local Work
+ Reduce Output Operator
+ key expressions: key (type: string)
+ sort order: +
+ Map-reduce partition columns: key (type: string)
+ Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
Reducer 2
Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0
+ 1
+ Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: count()
+ mode: hash
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: bigint)
+ Reducer 3
+ Reduce Operator Tree:
Group By Operator
aggregations: count(VALUE._col0)
mode: mergepartial
@@ -223,37 +214,15 @@ select /*+ mapjoin(b) */ count(*) from t
on a.key=b.key and a.value2=b.value2 where a.key < 10
POSTHOOK: type: QUERY
STAGE DEPENDENCIES:
- Stage-2 is a root stage
- Stage-1 depends on stages: Stage-2
+ Stage-1 is a root stage
Stage-0 depends on stages: Stage-1
STAGE PLANS:
- Stage: Stage-2
- Spark
-#### A masked pattern was here ####
- Vertices:
- Map 3
- Map Operator Tree:
- TableScan
- alias: b
- Statistics: Num rows: 500 Data size: 6312 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- predicate: ((key is not null and value2 is not null) and (key < 10)) (type: boolean)
- Statistics: Num rows: 41 Data size: 517 Basic stats: COMPLETE Column stats: NONE
- Spark HashTable Sink Operator
- condition expressions:
- 0
- 1
- keys:
- 0 key (type: string), value2 (type: string)
- 1 key (type: string), value2 (type: string)
- Local Work:
- Map Reduce Local Work
-
Stage: Stage-1
Spark
Edges:
- Reducer 2 <- Map 1 (GROUP, 1)
+ Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 3), Map 4 (PARTITION-LEVEL SORT, 3)
+ Reducer 3 <- Reducer 2 (GROUP, 1)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -264,31 +233,44 @@ STAGE PLANS:
Filter Operator
predicate: ((key is not null and value2 is not null) and (key < 10)) (type: boolean)
Statistics: Num rows: 41 Data size: 837 Basic stats: COMPLETE Column stats: NONE
- Map Join Operator
- condition map:
- Inner Join 0 to 1
- condition expressions:
- 0
- 1
- keys:
- 0 key (type: string), value2 (type: string)
- 1 key (type: string), value2 (type: string)
- input vertices:
- 1 Map 3
- Statistics: Num rows: 45 Data size: 920 Basic stats: COMPLETE Column stats: NONE
- Group By Operator
- aggregations: count()
- mode: hash
- outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- sort order:
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col0 (type: bigint)
- Local Work:
- Map Reduce Local Work
+ Reduce Output Operator
+ key expressions: key (type: string), value2 (type: string)
+ sort order: ++
+ Map-reduce partition columns: key (type: string), value2 (type: string)
+ Statistics: Num rows: 41 Data size: 837 Basic stats: COMPLETE Column stats: NONE
+ Map 4
+ Map Operator Tree:
+ TableScan
+ alias: b
+ Statistics: Num rows: 500 Data size: 6312 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: ((key is not null and value2 is not null) and (key < 10)) (type: boolean)
+ Statistics: Num rows: 41 Data size: 517 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: key (type: string), value2 (type: string)
+ sort order: ++
+ Map-reduce partition columns: key (type: string), value2 (type: string)
+ Statistics: Num rows: 41 Data size: 517 Basic stats: COMPLETE Column stats: NONE
Reducer 2
Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0
+ 1
+ Statistics: Num rows: 45 Data size: 920 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: count()
+ mode: hash
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: bigint)
+ Reducer 3
+ Reduce Operator Tree:
Group By Operator
aggregations: count(VALUE._col0)
mode: mergepartial
Modified: hive/branches/spark/ql/src/test/results/clientpositive/spark/subquery_exists.q.out
URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/subquery_exists.q.out?rev=1642997&r1=1642996&r2=1642997&view=diff
==============================================================================
--- hive/branches/spark/ql/src/test/results/clientpositive/spark/subquery_exists.q.out (original)
+++ hive/branches/spark/ql/src/test/results/clientpositive/spark/subquery_exists.q.out Tue Dec 2 19:57:10 2014
@@ -23,16 +23,30 @@ where exists
)
POSTHOOK: type: QUERY
STAGE DEPENDENCIES:
- Stage-2 is a root stage
- Stage-1 depends on stages: Stage-2
+ Stage-1 is a root stage
Stage-0 depends on stages: Stage-1
STAGE PLANS:
- Stage: Stage-2
+ Stage: Stage-1
Spark
+ Edges:
+ Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 1), Map 3 (PARTITION-LEVEL SORT, 1)
#### A masked pattern was here ####
Vertices:
- Map 2
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: b
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: (value is not null and key is not null) (type: boolean)
+ Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: value (type: string), key (type: string)
+ sort order: ++
+ Map-reduce partition columns: value (type: string), key (type: string)
+ Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE
+ Map 3
Map Operator Tree:
TableScan
alias: a
@@ -49,54 +63,32 @@ STAGE PLANS:
mode: hash
outputColumnNames: _col0, _col1
Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE
- Spark HashTable Sink Operator
- condition expressions:
- 0 {key} {value}
- 1
- keys:
- 0 value (type: string), key (type: string)
- 1 _col0 (type: string), _col1 (type: string)
- Local Work:
- Map Reduce Local Work
-
- Stage: Stage-1
- Spark
-#### A masked pattern was here ####
- Vertices:
- Map 1
- Map Operator Tree:
- TableScan
- alias: b
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- predicate: (value is not null and key is not null) (type: boolean)
- Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE
- Map Join Operator
- condition map:
- Left Semi Join 0 to 1
- condition expressions:
- 0 {key} {value}
- 1
- keys:
- 0 value (type: string), key (type: string)
- 1 _col0 (type: string), _col1 (type: string)
- outputColumnNames: _col0, _col1
- input vertices:
- 1 Map 2
- Statistics: Num rows: 137 Data size: 1460 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col0 (type: string), _col1 (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 137 Data size: 1460 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 137 Data size: 1460 Basic stats: COMPLETE Column stats: NONE
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- Local Work:
- Map Reduce Local Work
+ Reduce Output Operator
+ key expressions: _col0 (type: string), _col1 (type: string)
+ sort order: ++
+ Map-reduce partition columns: _col0 (type: string), _col1 (type: string)
+ Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE
+ Reducer 2
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Left Semi Join 0 to 1
+ condition expressions:
+ 0 {KEY.reducesinkkey1} {KEY.reducesinkkey0}
+ 1
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 137 Data size: 1460 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 137 Data size: 1460 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 137 Data size: 1460 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
Modified: hive/branches/spark/ql/src/test/results/clientpositive/spark/subquery_multiinsert.q.out
URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/subquery_multiinsert.q.out?rev=1642997&r1=1642996&r2=1642997&view=diff
==============================================================================
--- hive/branches/spark/ql/src/test/results/clientpositive/spark/subquery_multiinsert.q.out (original)
+++ hive/branches/spark/ql/src/test/results/clientpositive/spark/subquery_multiinsert.q.out Tue Dec 2 19:57:10 2014
@@ -61,21 +61,43 @@ INSERT OVERWRITE TABLE src_5
order by key
POSTHOOK: type: QUERY
STAGE DEPENDENCIES:
- Stage-5 is a root stage
- Stage-2 depends on stages: Stage-5
+ Stage-2 is a root stage
Stage-1 depends on stages: Stage-2
Stage-3 depends on stages: Stage-1
Stage-0 depends on stages: Stage-2
Stage-4 depends on stages: Stage-0
STAGE PLANS:
- Stage: Stage-5
+ Stage: Stage-2
Spark
Edges:
- Reducer 6 <- Map 5 (GROUP, 1)
+ Reducer 2 <- Map 10 (PARTITION-LEVEL SORT, 1), Reducer 9 (PARTITION-LEVEL SORT, 1)
+ Reducer 3 <- Map 7 (PARTITION-LEVEL SORT, 1), Reducer 2 (PARTITION-LEVEL SORT, 1)
+ Reducer 5 <- Map 11 (PARTITION-LEVEL SORT, 1), Map 6 (PARTITION-LEVEL SORT, 1)
+ Reducer 9 <- Map 8 (GROUP, 1)
+ Reducer 4 <- Reducer 3 (SORT, 1)
#### A masked pattern was here ####
Vertices:
- Map 3
+ Map 10
+ Map Operator Tree:
+ TableScan
+ alias: b
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ value expressions: key (type: string), value (type: string)
+ Map 11
+ Map Operator Tree:
+ TableScan
+ alias: b
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: key (type: string), value (type: string)
+ sort order: ++
+ Map-reduce partition columns: key (type: string), value (type: string)
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Map 6
Map Operator Tree:
TableScan
alias: a
@@ -92,16 +114,12 @@ STAGE PLANS:
mode: hash
outputColumnNames: _col0, _col1
Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE
- Spark HashTable Sink Operator
- condition expressions:
- 0 {key} {value}
- 1
- keys:
- 0 key (type: string), value (type: string)
- 1 _col0 (type: string), _col1 (type: string)
- Local Work:
- Map Reduce Local Work
- Map 4
+ Reduce Output Operator
+ key expressions: _col0 (type: string), _col1 (type: string)
+ sort order: ++
+ Map-reduce partition columns: _col0 (type: string), _col1 (type: string)
+ Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE
+ Map 7
Map Operator Tree:
TableScan
alias: s1
@@ -113,16 +131,12 @@ STAGE PLANS:
expressions: key (type: string)
outputColumnNames: _col0
Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
- Spark HashTable Sink Operator
- condition expressions:
- 0 {_col0} {_col1}
- 1
- keys:
- 0 _col0 (type: string)
- 1 _col0 (type: string)
- Local Work:
- Map Reduce Local Work
- Map 5
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
+ Map 8
Map Operator Tree:
TableScan
alias: s1
@@ -141,9 +155,77 @@ STAGE PLANS:
sort order:
Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
value expressions: _col0 (type: bigint)
- Reducer 6
- Local Work:
- Map Reduce Local Work
+ Reducer 2
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Left Semi Join 0 to 1
+ condition expressions:
+ 0 {VALUE._col0} {VALUE._col1}
+ 1
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 550 Data size: 5843 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: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col1 (type: string)
+ Reducer 3
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Left Outer Join0 to 1
+ condition expressions:
+ 0 {KEY.reducesinkkey0} {VALUE._col0}
+ 1 {KEY.reducesinkkey0}
+ outputColumnNames: _col0, _col1, _col5
+ Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: _col5 is null (type: boolean)
+ Statistics: Num rows: 302 Data size: 3208 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 302 Data size: 3208 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ sort order: +
+ Statistics: Num rows: 302 Data size: 3208 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col1 (type: string)
+ Reducer 4
+ Reduce Operator Tree:
+ Select Operator
+ expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 302 Data size: 3208 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 302 Data size: 3208 Basic stats: COMPLETE Column stats: NONE
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.src_5
+ Reducer 5
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Left Semi Join 0 to 1
+ condition expressions:
+ 0 {KEY.reducesinkkey0} {KEY.reducesinkkey1}
+ 1
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.src_4
+ Reducer 9
Reduce Operator Tree:
Group By Operator
aggregations: count(VALUE._col0)
@@ -162,100 +244,9 @@ STAGE PLANS:
mode: hash
outputColumnNames: _col0
Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
- Spark HashTable Sink Operator
- condition expressions:
- 0 {key} {value}
- 1
- keys:
- 0
- 1
-
- Stage: Stage-2
- Spark
- Edges:
- Reducer 2 <- Map 1 (SORT, 1)
-#### A masked pattern was here ####
- Vertices:
- Map 1
- Map Operator Tree:
- TableScan
- alias: b
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- Map Join Operator
- condition map:
- Left Semi Join 0 to 1
- condition expressions:
- 0 {key} {value}
- 1
- keys:
- 0
- 1
- outputColumnNames: _col0, _col1
- input vertices:
- 1 Reducer 6
- Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
- Map Join Operator
- condition map:
- Left Outer Join0 to 1
- condition expressions:
- 0 {_col0} {_col1}
- 1 {_col0}
- keys:
- 0 _col0 (type: string)
- 1 _col0 (type: string)
- outputColumnNames: _col0, _col1, _col5
- input vertices:
- 1 Map 4
- Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- predicate: _col5 is null (type: boolean)
- Statistics: Num rows: 302 Data size: 3208 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col0 (type: string), _col1 (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 302 Data size: 3208 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: string)
- sort order: +
- Statistics: Num rows: 302 Data size: 3208 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col1 (type: string)
- Map Join Operator
- condition map:
- Left Semi Join 0 to 1
- condition expressions:
- 0 {key} {value}
- 1
- keys:
- 0 key (type: string), value (type: string)
- 1 _col0 (type: string), _col1 (type: string)
- outputColumnNames: _col0, _col1
- input vertices:
- 1 Map 3
- Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.src_4
- Local Work:
- Map Reduce Local Work
- Reducer 2
- Reduce Operator Tree:
- Select Operator
- expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 302 Data size: 3208 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 302 Data size: 3208 Basic stats: COMPLETE Column stats: NONE
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.src_5
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
Stage: Stage-1
Move Operator
@@ -319,7 +310,6 @@ POSTHOOK: Lineage: src_4.key EXPRESSION
POSTHOOK: Lineage: src_4.value EXPRESSION [(src)b.FieldSchema(name:value, type:string, comment:default), ]
POSTHOOK: Lineage: src_5.key EXPRESSION [(src)b.FieldSchema(name:key, type:string, comment:default), ]
POSTHOOK: Lineage: src_5.value EXPRESSION [(src)b.FieldSchema(name:value, type:string, comment:default), ]
-RUN: Stage-5:MAPRED
RUN: Stage-2:MAPRED
RUN: Stage-1:MOVE
RUN: Stage-0:MOVE