You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@hive.apache.org by jd...@apache.org on 2017/12/12 20:51:31 UTC
[08/12] hive git commit: HIVE-18208: SMB Join : Fix the unit tests to
run SMB Joins. (Deepak Jaiswal, reviewed by Jason Dere)
http://git-wip-us.apache.org/repos/asf/hive/blob/38405c14/ql/src/test/results/clientpositive/llap/auto_sortmerge_join_15.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/auto_sortmerge_join_15.q.out b/ql/src/test/results/clientpositive/llap/auto_sortmerge_join_15.q.out
index 91b1d8e..d76bf84 100644
--- a/ql/src/test/results/clientpositive/llap/auto_sortmerge_join_15.q.out
+++ b/ql/src/test/results/clientpositive/llap/auto_sortmerge_join_15.q.out
@@ -49,27 +49,32 @@ STAGE PLANS:
Tez
#### A masked pattern was here ####
Edges:
- Map 1 <- Map 3 (BROADCAST_EDGE)
Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE)
#### A masked pattern was here ####
Vertices:
Map 1
Map Operator Tree:
TableScan
+ alias: b
+ Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: key (type: int)
+ outputColumnNames: _col0
+ Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE
+ Map Operator Tree:
+ TableScan
alias: a
Statistics: Num rows: 20 Data size: 80 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: key (type: int)
outputColumnNames: _col0
Statistics: Num rows: 20 Data size: 80 Basic stats: COMPLETE Column stats: COMPLETE
- Map Join Operator
+ Merge Join Operator
condition map:
Left Outer Join 0 to 1
keys:
0 _col0 (type: int)
1 _col0 (type: int)
- input vertices:
- 1 Map 3
Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count()
@@ -81,23 +86,6 @@ STAGE PLANS:
Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: bigint)
Execution mode: llap
- LLAP IO: no inputs
- Map 3
- Map Operator Tree:
- TableScan
- alias: b
- Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE
- Select Operator
- expressions: key (type: int)
- outputColumnNames: _col0
- Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE
- Reduce Output Operator
- key expressions: _col0 (type: int)
- sort order: +
- Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE
- Execution mode: llap
- LLAP IO: no inputs
Reducer 2
Execution mode: llap
Reduce Operator Tree:
@@ -135,11 +123,10 @@ STAGE PLANS:
Tez
#### A masked pattern was here ####
Edges:
- Map 2 <- Map 1 (BROADCAST_EDGE)
Reducer 3 <- Map 2 (CUSTOM_SIMPLE_EDGE)
#### A masked pattern was here ####
Vertices:
- Map 1
+ Map 2
Map Operator Tree:
TableScan
alias: a
@@ -148,14 +135,6 @@ STAGE PLANS:
expressions: key (type: int)
outputColumnNames: _col0
Statistics: Num rows: 20 Data size: 80 Basic stats: COMPLETE Column stats: COMPLETE
- Reduce Output Operator
- key expressions: _col0 (type: int)
- sort order: +
- Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 20 Data size: 80 Basic stats: COMPLETE Column stats: COMPLETE
- Execution mode: llap
- LLAP IO: no inputs
- Map 2
Map Operator Tree:
TableScan
alias: b
@@ -164,14 +143,12 @@ STAGE PLANS:
expressions: key (type: int)
outputColumnNames: _col0
Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE
- Map Join Operator
+ Merge Join Operator
condition map:
Right Outer Join 0 to 1
keys:
0 _col0 (type: int)
1 _col0 (type: int)
- input vertices:
- 0 Map 1
Statistics: Num rows: 15 Data size: 120 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count()
@@ -183,7 +160,6 @@ STAGE PLANS:
Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: bigint)
Execution mode: llap
- LLAP IO: no inputs
Reducer 3
Execution mode: llap
Reduce Operator Tree:
http://git-wip-us.apache.org/repos/asf/hive/blob/38405c14/ql/src/test/results/clientpositive/llap/auto_sortmerge_join_2.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/auto_sortmerge_join_2.q.out b/ql/src/test/results/clientpositive/llap/auto_sortmerge_join_2.q.out
index 90d362e..ee70e6e 100644
--- a/ql/src/test/results/clientpositive/llap/auto_sortmerge_join_2.q.out
+++ b/ql/src/test/results/clientpositive/llap/auto_sortmerge_join_2.q.out
@@ -94,77 +94,50 @@ STAGE PLANS:
Tez
#### A masked pattern was here ####
Edges:
- Map 1 <- Map 3 (BROADCAST_EDGE)
Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE)
#### A masked pattern was here ####
Vertices:
Map 1
Map Operator Tree:
TableScan
- alias: a
- Statistics: Num rows: 54 Data size: 15252 Basic stats: COMPLETE Column stats: NONE
+ alias: b
+ Statistics: Num rows: 2 Data size: 594 Basic stats: COMPLETE Column stats: NONE
GatherStats: false
Filter Operator
isSamplingPred: false
predicate: key is not null (type: boolean)
- Statistics: Num rows: 52 Data size: 14687 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 594 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: key (type: string)
outputColumnNames: _col0
- Statistics: Num rows: 52 Data size: 14687 Basic stats: COMPLETE Column stats: NONE
- Map Join Operator
- condition map:
- Inner Join 0 to 1
- Estimated key counts: Map 3 => 2
- keys:
- 0 _col0 (type: string)
- 1 _col0 (type: string)
- input vertices:
- 1 Map 3
- Position of Big Table: 0
- Statistics: Num rows: 57 Data size: 16155 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
- null sort order:
- 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
- Execution mode: llap
- LLAP IO: no inputs
+ Statistics: Num rows: 2 Data size: 594 Basic stats: COMPLETE Column stats: NONE
Path -> Alias:
#### A masked pattern was here ####
Path -> Partition:
#### A masked pattern was here ####
Partition
- base file name: ds=2008-04-08
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
partition values:
ds 2008-04-08
properties:
- bucket_count 2
+ bucket_count 4
bucket_field_name key
column.name.delimiter ,
columns key,value
columns.comments
columns.types string:string
#### A masked pattern was here ####
- name default.bucket_big
- numFiles 2
+ name default.bucket_small
+ numFiles 4
numRows 0
partition_columns ds
partition_columns.types string
rawDataSize 0
- serialization.ddl struct bucket_big { string key, string value}
+ serialization.ddl struct bucket_small { string key, string value}
serialization.format 1
serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 2750
+ totalSize 226
#### A masked pattern was here ####
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
@@ -172,30 +145,68 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
SORTBUCKETCOLSPREFIX TRUE
- bucket_count 2
+ bucket_count 4
bucket_field_name key
column.name.delimiter ,
columns key,value
columns.comments
columns.types string:string
#### A masked pattern was here ####
- name default.bucket_big
+ name default.bucket_small
partition_columns ds
partition_columns.types string
- serialization.ddl struct bucket_big { string key, string value}
+ serialization.ddl struct bucket_small { string 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.bucket_big
- name: default.bucket_big
+ name: default.bucket_small
+ name: default.bucket_small
+ Truncated Path -> Alias:
+ /bucket_small/ds=2008-04-08 [b]
+ Map Operator Tree:
+ TableScan
+ alias: a
+ Statistics: Num rows: 54 Data size: 15252 Basic stats: COMPLETE Column stats: NONE
+ GatherStats: false
+ Filter Operator
+ isSamplingPred: false
+ predicate: key is not null (type: boolean)
+ Statistics: Num rows: 52 Data size: 14687 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: key (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 52 Data size: 14687 Basic stats: COMPLETE Column stats: NONE
+ Merge Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col0 (type: string)
+ 1 _col0 (type: string)
+ Position of Big Table: 0
+ Statistics: Num rows: 57 Data size: 16155 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
+ null sort order:
+ 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
+ Execution mode: llap
+ Path -> Alias:
+#### A masked pattern was here ####
+ Path -> Partition:
#### A masked pattern was here ####
Partition
- base file name: ds=2008-04-09
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
partition values:
- ds 2008-04-09
+ ds 2008-04-08
properties:
bucket_count 2
bucket_field_name key
@@ -238,61 +249,30 @@ STAGE PLANS:
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.bucket_big
name: default.bucket_big
- Truncated Path -> Alias:
- /bucket_big/ds=2008-04-08 [a]
- /bucket_big/ds=2008-04-09 [a]
- Map 3
- Map Operator Tree:
- TableScan
- alias: b
- Statistics: Num rows: 2 Data size: 594 Basic stats: COMPLETE Column stats: NONE
- GatherStats: false
- Filter Operator
- isSamplingPred: false
- predicate: key is not null (type: boolean)
- Statistics: Num rows: 2 Data size: 594 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: key (type: string)
- outputColumnNames: _col0
- Statistics: Num rows: 2 Data size: 594 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: string)
- null sort order: a
- sort order: +
- Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 2 Data size: 594 Basic stats: COMPLETE Column stats: NONE
- tag: 1
- auto parallelism: true
- Execution mode: llap
- LLAP IO: no inputs
- Path -> Alias:
-#### A masked pattern was here ####
- Path -> Partition:
#### A masked pattern was here ####
Partition
- base file name: ds=2008-04-08
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
partition values:
- ds 2008-04-08
+ ds 2008-04-09
properties:
- bucket_count 4
+ bucket_count 2
bucket_field_name key
column.name.delimiter ,
columns key,value
columns.comments
columns.types string:string
#### A masked pattern was here ####
- name default.bucket_small
- numFiles 4
+ name default.bucket_big
+ numFiles 2
numRows 0
partition_columns ds
partition_columns.types string
rawDataSize 0
- serialization.ddl struct bucket_small { string key, string value}
+ serialization.ddl struct bucket_big { string key, string value}
serialization.format 1
serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 226
+ totalSize 2750
#### A masked pattern was here ####
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
@@ -300,25 +280,26 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
SORTBUCKETCOLSPREFIX TRUE
- bucket_count 4
+ bucket_count 2
bucket_field_name key
column.name.delimiter ,
columns key,value
columns.comments
columns.types string:string
#### A masked pattern was here ####
- name default.bucket_small
+ name default.bucket_big
partition_columns ds
partition_columns.types string
- serialization.ddl struct bucket_small { string key, string value}
+ serialization.ddl struct bucket_big { string 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.bucket_small
- name: default.bucket_small
+ name: default.bucket_big
+ name: default.bucket_big
Truncated Path -> Alias:
- /bucket_small/ds=2008-04-08 [b]
+ /bucket_big/ds=2008-04-08 [a]
+ /bucket_big/ds=2008-04-09 [a]
Reducer 2
Execution mode: llap
Needs Tagging: false
@@ -387,77 +368,50 @@ STAGE PLANS:
Tez
#### A masked pattern was here ####
Edges:
- Map 1 <- Map 3 (BROADCAST_EDGE)
Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE)
#### A masked pattern was here ####
Vertices:
Map 1
Map Operator Tree:
TableScan
- alias: a
- Statistics: Num rows: 54 Data size: 15252 Basic stats: COMPLETE Column stats: NONE
+ alias: b
+ Statistics: Num rows: 2 Data size: 594 Basic stats: COMPLETE Column stats: NONE
GatherStats: false
Filter Operator
isSamplingPred: false
predicate: key is not null (type: boolean)
- Statistics: Num rows: 52 Data size: 14687 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 594 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: key (type: string)
outputColumnNames: _col0
- Statistics: Num rows: 52 Data size: 14687 Basic stats: COMPLETE Column stats: NONE
- Map Join Operator
- condition map:
- Inner Join 0 to 1
- Estimated key counts: Map 3 => 2
- keys:
- 0 _col0 (type: string)
- 1 _col0 (type: string)
- input vertices:
- 1 Map 3
- Position of Big Table: 0
- Statistics: Num rows: 57 Data size: 16155 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
- null sort order:
- 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
- Execution mode: llap
- LLAP IO: no inputs
+ Statistics: Num rows: 2 Data size: 594 Basic stats: COMPLETE Column stats: NONE
Path -> Alias:
#### A masked pattern was here ####
Path -> Partition:
#### A masked pattern was here ####
Partition
- base file name: ds=2008-04-08
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
partition values:
ds 2008-04-08
properties:
- bucket_count 2
+ bucket_count 4
bucket_field_name key
column.name.delimiter ,
columns key,value
columns.comments
columns.types string:string
#### A masked pattern was here ####
- name default.bucket_big
- numFiles 2
+ name default.bucket_small
+ numFiles 4
numRows 0
partition_columns ds
partition_columns.types string
rawDataSize 0
- serialization.ddl struct bucket_big { string key, string value}
+ serialization.ddl struct bucket_small { string key, string value}
serialization.format 1
serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 2750
+ totalSize 226
#### A masked pattern was here ####
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
@@ -465,30 +419,68 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
SORTBUCKETCOLSPREFIX TRUE
- bucket_count 2
+ bucket_count 4
bucket_field_name key
column.name.delimiter ,
columns key,value
columns.comments
columns.types string:string
#### A masked pattern was here ####
- name default.bucket_big
+ name default.bucket_small
partition_columns ds
partition_columns.types string
- serialization.ddl struct bucket_big { string key, string value}
+ serialization.ddl struct bucket_small { string 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.bucket_big
- name: default.bucket_big
+ name: default.bucket_small
+ name: default.bucket_small
+ Truncated Path -> Alias:
+ /bucket_small/ds=2008-04-08 [b]
+ Map Operator Tree:
+ TableScan
+ alias: a
+ Statistics: Num rows: 54 Data size: 15252 Basic stats: COMPLETE Column stats: NONE
+ GatherStats: false
+ Filter Operator
+ isSamplingPred: false
+ predicate: key is not null (type: boolean)
+ Statistics: Num rows: 52 Data size: 14687 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: key (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 52 Data size: 14687 Basic stats: COMPLETE Column stats: NONE
+ Merge Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col0 (type: string)
+ 1 _col0 (type: string)
+ Position of Big Table: 0
+ Statistics: Num rows: 57 Data size: 16155 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
+ null sort order:
+ 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
+ Execution mode: llap
+ Path -> Alias:
+#### A masked pattern was here ####
+ Path -> Partition:
#### A masked pattern was here ####
Partition
- base file name: ds=2008-04-09
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
partition values:
- ds 2008-04-09
+ ds 2008-04-08
properties:
bucket_count 2
bucket_field_name key
@@ -531,61 +523,30 @@ STAGE PLANS:
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.bucket_big
name: default.bucket_big
- Truncated Path -> Alias:
- /bucket_big/ds=2008-04-08 [a]
- /bucket_big/ds=2008-04-09 [a]
- Map 3
- Map Operator Tree:
- TableScan
- alias: b
- Statistics: Num rows: 2 Data size: 594 Basic stats: COMPLETE Column stats: NONE
- GatherStats: false
- Filter Operator
- isSamplingPred: false
- predicate: key is not null (type: boolean)
- Statistics: Num rows: 2 Data size: 594 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: key (type: string)
- outputColumnNames: _col0
- Statistics: Num rows: 2 Data size: 594 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: string)
- null sort order: a
- sort order: +
- Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 2 Data size: 594 Basic stats: COMPLETE Column stats: NONE
- tag: 1
- auto parallelism: true
- Execution mode: llap
- LLAP IO: no inputs
- Path -> Alias:
-#### A masked pattern was here ####
- Path -> Partition:
#### A masked pattern was here ####
Partition
- base file name: ds=2008-04-08
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
partition values:
- ds 2008-04-08
+ ds 2008-04-09
properties:
- bucket_count 4
+ bucket_count 2
bucket_field_name key
column.name.delimiter ,
columns key,value
columns.comments
columns.types string:string
#### A masked pattern was here ####
- name default.bucket_small
- numFiles 4
+ name default.bucket_big
+ numFiles 2
numRows 0
partition_columns ds
partition_columns.types string
rawDataSize 0
- serialization.ddl struct bucket_small { string key, string value}
+ serialization.ddl struct bucket_big { string key, string value}
serialization.format 1
serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 226
+ totalSize 2750
#### A masked pattern was here ####
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
@@ -593,25 +554,26 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
SORTBUCKETCOLSPREFIX TRUE
- bucket_count 4
+ bucket_count 2
bucket_field_name key
column.name.delimiter ,
columns key,value
columns.comments
columns.types string:string
#### A masked pattern was here ####
- name default.bucket_small
+ name default.bucket_big
partition_columns ds
partition_columns.types string
- serialization.ddl struct bucket_small { string key, string value}
+ serialization.ddl struct bucket_big { string 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.bucket_small
- name: default.bucket_small
+ name: default.bucket_big
+ name: default.bucket_big
Truncated Path -> Alias:
- /bucket_small/ds=2008-04-08 [b]
+ /bucket_big/ds=2008-04-08 [a]
+ /bucket_big/ds=2008-04-09 [a]
Reducer 2
Execution mode: llap
Needs Tagging: false
http://git-wip-us.apache.org/repos/asf/hive/blob/38405c14/ql/src/test/results/clientpositive/llap/auto_sortmerge_join_3.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/auto_sortmerge_join_3.q.out b/ql/src/test/results/clientpositive/llap/auto_sortmerge_join_3.q.out
index 365f63c..26439b9 100644
--- a/ql/src/test/results/clientpositive/llap/auto_sortmerge_join_3.q.out
+++ b/ql/src/test/results/clientpositive/llap/auto_sortmerge_join_3.q.out
@@ -94,11 +94,10 @@ STAGE PLANS:
Tez
#### A masked pattern was here ####
Edges:
- Map 2 <- Map 1 (BROADCAST_EDGE)
Reducer 3 <- Map 2 (CUSTOM_SIMPLE_EDGE)
#### A masked pattern was here ####
Vertices:
- Map 1
+ Map 2
Map Operator Tree:
TableScan
alias: a
@@ -112,22 +111,11 @@ STAGE PLANS:
expressions: key (type: string)
outputColumnNames: _col0
Statistics: Num rows: 2 Data size: 596 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: string)
- null sort order: a
- sort order: +
- Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 2 Data size: 596 Basic stats: COMPLETE Column stats: NONE
- tag: 0
- auto parallelism: true
- Execution mode: llap
- LLAP IO: no inputs
Path -> Alias:
#### A masked pattern was here ####
Path -> Partition:
#### A masked pattern was here ####
Partition
- base file name: ds=2008-04-08
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
partition values:
@@ -176,7 +164,6 @@ STAGE PLANS:
name: default.bucket_small
#### A masked pattern was here ####
Partition
- base file name: ds=2008-04-09
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
partition values:
@@ -226,7 +213,6 @@ STAGE PLANS:
Truncated Path -> Alias:
/bucket_small/ds=2008-04-08 [a]
/bucket_small/ds=2008-04-09 [a]
- Map 2
Map Operator Tree:
TableScan
alias: b
@@ -240,15 +226,12 @@ STAGE PLANS:
expressions: key (type: string)
outputColumnNames: _col0
Statistics: Num rows: 56 Data size: 15737 Basic stats: COMPLETE Column stats: NONE
- Map Join Operator
+ Merge Join Operator
condition map:
Inner Join 0 to 1
- Estimated key counts: Map 1 => 2
keys:
0 _col0 (type: string)
1 _col0 (type: string)
- input vertices:
- 0 Map 1
Position of Big Table: 1
Statistics: Num rows: 61 Data size: 17310 Basic stats: COMPLETE Column stats: NONE
Group By Operator
@@ -264,13 +247,11 @@ STAGE PLANS:
value expressions: _col0 (type: bigint)
auto parallelism: false
Execution mode: llap
- LLAP IO: no inputs
Path -> Alias:
#### A masked pattern was here ####
Path -> Partition:
#### A masked pattern was here ####
Partition
- base file name: ds=2008-04-08
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
partition values:
@@ -387,77 +368,50 @@ STAGE PLANS:
Tez
#### A masked pattern was here ####
Edges:
- Map 1 <- Map 3 (BROADCAST_EDGE)
Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE)
#### A masked pattern was here ####
Vertices:
Map 1
Map Operator Tree:
TableScan
- alias: a
- Statistics: Num rows: 58 Data size: 16300 Basic stats: COMPLETE Column stats: NONE
+ alias: b
+ Statistics: Num rows: 2 Data size: 596 Basic stats: COMPLETE Column stats: NONE
GatherStats: false
Filter Operator
isSamplingPred: false
predicate: key is not null (type: boolean)
- Statistics: Num rows: 56 Data size: 15737 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 596 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: key (type: string)
outputColumnNames: _col0
- Statistics: Num rows: 56 Data size: 15737 Basic stats: COMPLETE Column stats: NONE
- Map Join Operator
- condition map:
- Inner Join 0 to 1
- Estimated key counts: Map 3 => 2
- keys:
- 0 _col0 (type: string)
- 1 _col0 (type: string)
- input vertices:
- 1 Map 3
- Position of Big Table: 0
- Statistics: Num rows: 61 Data size: 17310 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
- null sort order:
- 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
- Execution mode: llap
- LLAP IO: no inputs
+ Statistics: Num rows: 2 Data size: 596 Basic stats: COMPLETE Column stats: NONE
Path -> Alias:
#### A masked pattern was here ####
Path -> Partition:
#### A masked pattern was here ####
Partition
- base file name: ds=2008-04-08
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
partition values:
ds 2008-04-08
properties:
- bucket_count 4
+ bucket_count 2
bucket_field_name key
column.name.delimiter ,
columns key,value
columns.comments
columns.types string:string
#### A masked pattern was here ####
- name default.bucket_big
- numFiles 4
+ name default.bucket_small
+ numFiles 2
numRows 0
partition_columns ds
partition_columns.types string
rawDataSize 0
- serialization.ddl struct bucket_big { string key, string value}
+ serialization.ddl struct bucket_small { string key, string value}
serialization.format 1
serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 5812
+ totalSize 114
#### A masked pattern was here ####
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
@@ -465,59 +419,29 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
SORTBUCKETCOLSPREFIX TRUE
- bucket_count 4
+ bucket_count 2
bucket_field_name key
column.name.delimiter ,
columns key,value
columns.comments
columns.types string:string
#### A masked pattern was here ####
- name default.bucket_big
+ name default.bucket_small
partition_columns ds
partition_columns.types string
- serialization.ddl struct bucket_big { string key, string value}
+ serialization.ddl struct bucket_small { string 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.bucket_big
- name: default.bucket_big
- Truncated Path -> Alias:
- /bucket_big/ds=2008-04-08 [a]
- Map 3
- Map Operator Tree:
- TableScan
- alias: b
- Statistics: Num rows: 2 Data size: 596 Basic stats: COMPLETE Column stats: NONE
- GatherStats: false
- Filter Operator
- isSamplingPred: false
- predicate: key is not null (type: boolean)
- Statistics: Num rows: 2 Data size: 596 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: key (type: string)
- outputColumnNames: _col0
- Statistics: Num rows: 2 Data size: 596 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: string)
- null sort order: a
- sort order: +
- Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 2 Data size: 596 Basic stats: COMPLETE Column stats: NONE
- tag: 1
- auto parallelism: true
- Execution mode: llap
- LLAP IO: no inputs
- Path -> Alias:
-#### A masked pattern was here ####
- Path -> Partition:
+ name: default.bucket_small
+ name: default.bucket_small
#### A masked pattern was here ####
Partition
- base file name: ds=2008-04-08
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
partition values:
- ds 2008-04-08
+ ds 2008-04-09
properties:
bucket_count 2
bucket_field_name key
@@ -560,31 +484,70 @@ STAGE PLANS:
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.bucket_small
name: default.bucket_small
+ Truncated Path -> Alias:
+ /bucket_small/ds=2008-04-08 [b]
+ /bucket_small/ds=2008-04-09 [b]
+ Map Operator Tree:
+ TableScan
+ alias: a
+ Statistics: Num rows: 58 Data size: 16300 Basic stats: COMPLETE Column stats: NONE
+ GatherStats: false
+ Filter Operator
+ isSamplingPred: false
+ predicate: key is not null (type: boolean)
+ Statistics: Num rows: 56 Data size: 15737 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: key (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 56 Data size: 15737 Basic stats: COMPLETE Column stats: NONE
+ Merge Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col0 (type: string)
+ 1 _col0 (type: string)
+ Position of Big Table: 0
+ Statistics: Num rows: 61 Data size: 17310 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
+ null sort order:
+ 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
+ Execution mode: llap
+ Path -> Alias:
+#### A masked pattern was here ####
+ Path -> Partition:
#### A masked pattern was here ####
Partition
- base file name: ds=2008-04-09
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
partition values:
- ds 2008-04-09
+ ds 2008-04-08
properties:
- bucket_count 2
+ bucket_count 4
bucket_field_name key
column.name.delimiter ,
columns key,value
columns.comments
columns.types string:string
#### A masked pattern was here ####
- name default.bucket_small
- numFiles 2
+ name default.bucket_big
+ numFiles 4
numRows 0
partition_columns ds
partition_columns.types string
rawDataSize 0
- serialization.ddl struct bucket_small { string key, string value}
+ serialization.ddl struct bucket_big { string key, string value}
serialization.format 1
serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 114
+ totalSize 5812
#### A masked pattern was here ####
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
@@ -592,26 +555,25 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
SORTBUCKETCOLSPREFIX TRUE
- bucket_count 2
+ bucket_count 4
bucket_field_name key
column.name.delimiter ,
columns key,value
columns.comments
columns.types string:string
#### A masked pattern was here ####
- name default.bucket_small
+ name default.bucket_big
partition_columns ds
partition_columns.types string
- serialization.ddl struct bucket_small { string key, string value}
+ serialization.ddl struct bucket_big { string 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.bucket_small
- name: default.bucket_small
+ name: default.bucket_big
+ name: default.bucket_big
Truncated Path -> Alias:
- /bucket_small/ds=2008-04-08 [b]
- /bucket_small/ds=2008-04-09 [b]
+ /bucket_big/ds=2008-04-08 [a]
Reducer 2
Execution mode: llap
Needs Tagging: false
@@ -680,77 +642,50 @@ STAGE PLANS:
Tez
#### A masked pattern was here ####
Edges:
- Map 1 <- Map 3 (BROADCAST_EDGE)
Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE)
#### A masked pattern was here ####
Vertices:
Map 1
Map Operator Tree:
TableScan
- alias: a
- Statistics: Num rows: 58 Data size: 16300 Basic stats: COMPLETE Column stats: NONE
+ alias: b
+ Statistics: Num rows: 2 Data size: 596 Basic stats: COMPLETE Column stats: NONE
GatherStats: false
Filter Operator
isSamplingPred: false
predicate: key is not null (type: boolean)
- Statistics: Num rows: 56 Data size: 15737 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 596 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: key (type: string)
outputColumnNames: _col0
- Statistics: Num rows: 56 Data size: 15737 Basic stats: COMPLETE Column stats: NONE
- Map Join Operator
- condition map:
- Inner Join 0 to 1
- Estimated key counts: Map 3 => 2
- keys:
- 0 _col0 (type: string)
- 1 _col0 (type: string)
- input vertices:
- 1 Map 3
- Position of Big Table: 0
- Statistics: Num rows: 61 Data size: 17310 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
- null sort order:
- 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
- Execution mode: llap
- LLAP IO: no inputs
+ Statistics: Num rows: 2 Data size: 596 Basic stats: COMPLETE Column stats: NONE
Path -> Alias:
#### A masked pattern was here ####
Path -> Partition:
#### A masked pattern was here ####
Partition
- base file name: ds=2008-04-08
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
partition values:
ds 2008-04-08
properties:
- bucket_count 4
+ bucket_count 2
bucket_field_name key
column.name.delimiter ,
columns key,value
columns.comments
columns.types string:string
#### A masked pattern was here ####
- name default.bucket_big
- numFiles 4
+ name default.bucket_small
+ numFiles 2
numRows 0
partition_columns ds
partition_columns.types string
rawDataSize 0
- serialization.ddl struct bucket_big { string key, string value}
+ serialization.ddl struct bucket_small { string key, string value}
serialization.format 1
serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 5812
+ totalSize 114
#### A masked pattern was here ####
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
@@ -758,59 +693,29 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
SORTBUCKETCOLSPREFIX TRUE
- bucket_count 4
+ bucket_count 2
bucket_field_name key
column.name.delimiter ,
columns key,value
columns.comments
columns.types string:string
#### A masked pattern was here ####
- name default.bucket_big
+ name default.bucket_small
partition_columns ds
partition_columns.types string
- serialization.ddl struct bucket_big { string key, string value}
+ serialization.ddl struct bucket_small { string 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.bucket_big
- name: default.bucket_big
- Truncated Path -> Alias:
- /bucket_big/ds=2008-04-08 [a]
- Map 3
- Map Operator Tree:
- TableScan
- alias: b
- Statistics: Num rows: 2 Data size: 596 Basic stats: COMPLETE Column stats: NONE
- GatherStats: false
- Filter Operator
- isSamplingPred: false
- predicate: key is not null (type: boolean)
- Statistics: Num rows: 2 Data size: 596 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: key (type: string)
- outputColumnNames: _col0
- Statistics: Num rows: 2 Data size: 596 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: string)
- null sort order: a
- sort order: +
- Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 2 Data size: 596 Basic stats: COMPLETE Column stats: NONE
- tag: 1
- auto parallelism: true
- Execution mode: llap
- LLAP IO: no inputs
- Path -> Alias:
-#### A masked pattern was here ####
- Path -> Partition:
+ name: default.bucket_small
+ name: default.bucket_small
#### A masked pattern was here ####
Partition
- base file name: ds=2008-04-08
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
partition values:
- ds 2008-04-08
+ ds 2008-04-09
properties:
bucket_count 2
bucket_field_name key
@@ -853,31 +758,70 @@ STAGE PLANS:
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.bucket_small
name: default.bucket_small
+ Truncated Path -> Alias:
+ /bucket_small/ds=2008-04-08 [b]
+ /bucket_small/ds=2008-04-09 [b]
+ Map Operator Tree:
+ TableScan
+ alias: a
+ Statistics: Num rows: 58 Data size: 16300 Basic stats: COMPLETE Column stats: NONE
+ GatherStats: false
+ Filter Operator
+ isSamplingPred: false
+ predicate: key is not null (type: boolean)
+ Statistics: Num rows: 56 Data size: 15737 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: key (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 56 Data size: 15737 Basic stats: COMPLETE Column stats: NONE
+ Merge Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col0 (type: string)
+ 1 _col0 (type: string)
+ Position of Big Table: 0
+ Statistics: Num rows: 61 Data size: 17310 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
+ null sort order:
+ 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
+ Execution mode: llap
+ Path -> Alias:
+#### A masked pattern was here ####
+ Path -> Partition:
#### A masked pattern was here ####
Partition
- base file name: ds=2008-04-09
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
partition values:
- ds 2008-04-09
+ ds 2008-04-08
properties:
- bucket_count 2
+ bucket_count 4
bucket_field_name key
column.name.delimiter ,
columns key,value
columns.comments
columns.types string:string
#### A masked pattern was here ####
- name default.bucket_small
- numFiles 2
+ name default.bucket_big
+ numFiles 4
numRows 0
partition_columns ds
partition_columns.types string
rawDataSize 0
- serialization.ddl struct bucket_small { string key, string value}
+ serialization.ddl struct bucket_big { string key, string value}
serialization.format 1
serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 114
+ totalSize 5812
#### A masked pattern was here ####
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
@@ -885,26 +829,25 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
SORTBUCKETCOLSPREFIX TRUE
- bucket_count 2
+ bucket_count 4
bucket_field_name key
column.name.delimiter ,
columns key,value
columns.comments
columns.types string:string
#### A masked pattern was here ####
- name default.bucket_small
+ name default.bucket_big
partition_columns ds
partition_columns.types string
- serialization.ddl struct bucket_small { string key, string value}
+ serialization.ddl struct bucket_big { string 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.bucket_small
- name: default.bucket_small
+ name: default.bucket_big
+ name: default.bucket_big
Truncated Path -> Alias:
- /bucket_small/ds=2008-04-08 [b]
- /bucket_small/ds=2008-04-09 [b]
+ /bucket_big/ds=2008-04-08 [a]
Reducer 2
Execution mode: llap
Needs Tagging: false