You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@hive.apache.org by om...@apache.org on 2015/11/23 18:23:32 UTC
[09/55] [partial] hive git commit: HIVE-12017: Do not disable CBO by
default when number of joins in a query is equal or less than 1 (Jesus
Camacho Rodriguez, reviewed by Ashutosh Chauhan)
http://git-wip-us.apache.org/repos/asf/hive/blob/855e43df/ql/src/test/results/clientpositive/spark/bucket_map_join_spark3.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/bucket_map_join_spark3.q.out b/ql/src/test/results/clientpositive/spark/bucket_map_join_spark3.q.out
index fed923c..4133fda 100644
--- a/ql/src/test/results/clientpositive/spark/bucket_map_join_spark3.q.out
+++ b/ql/src/test/results/clientpositive/spark/bucket_map_join_spark3.q.out
@@ -173,11 +173,15 @@ STAGE PLANS:
isSamplingPred: false
predicate: key is not null (type: boolean)
Statistics: Num rows: 15 Data size: 1583 Basic stats: COMPLETE Column stats: NONE
- Spark HashTable Sink Operator
- keys:
- 0 key (type: int)
- 1 key (type: int)
- Position of Big Table: 1
+ Select Operator
+ expressions: key (type: int), value (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 15 Data size: 1583 Basic stats: COMPLETE Column stats: NONE
+ Spark HashTable Sink Operator
+ keys:
+ 0 _col0 (type: int)
+ 1 _col0 (type: int)
+ Position of Big Table: 1
Local Work:
Map Reduce Local Work
Bucket Mapjoin Context:
@@ -252,48 +256,52 @@ STAGE PLANS:
isSamplingPred: false
predicate: key is not null (type: boolean)
Statistics: Num rows: 28 Data size: 2958 Basic stats: COMPLETE Column stats: NONE
- Map Join Operator
- condition map:
- Inner Join 0 to 1
- keys:
- 0 key (type: int)
- 1 key (type: int)
- outputColumnNames: _col0, _col1, _col7
- input vertices:
- 0 Map 1
- Position of Big Table: 1
- Statistics: Num rows: 30 Data size: 3253 Basic stats: COMPLETE Column stats: NONE
- BucketMapJoin: true
- Select Operator
- expressions: _col0 (type: int), _col1 (type: string), _col7 (type: string)
- outputColumnNames: _col0, _col1, _col2
+ Select Operator
+ expressions: key (type: int), value (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 28 Data size: 2958 Basic stats: COMPLETE Column stats: NONE
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col0 (type: int)
+ 1 _col0 (type: int)
+ outputColumnNames: _col0, _col1, _col3
+ input vertices:
+ 0 Map 1
+ Position of Big Table: 1
Statistics: Num rows: 30 Data size: 3253 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- GlobalTableId: 1
-#### A masked pattern was here ####
- NumFilesPerFileSink: 1
+ BucketMapJoin: true
+ Select Operator
+ expressions: _col0 (type: int), _col1 (type: string), _col3 (type: string)
+ outputColumnNames: _col0, _col1, _col2
Statistics: Num rows: 30 Data size: 3253 Basic stats: COMPLETE Column stats: NONE
-#### A masked pattern was here ####
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- bucket_count -1
- columns key,value1,value2
- columns.comments
- columns.types string:string:string
-#### A masked pattern was here ####
- name default.bucketmapjoin_tmp_result
- serialization.ddl struct bucketmapjoin_tmp_result { string key, string value1, string value2}
- 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.bucketmapjoin_tmp_result
- TotalFiles: 1
- GatherStats: true
- MultiFileSpray: false
+ File Output Operator
+ compressed: false
+ GlobalTableId: 1
+#### A masked pattern was here ####
+ NumFilesPerFileSink: 1
+ Statistics: Num rows: 30 Data size: 3253 Basic stats: COMPLETE Column stats: NONE
+#### A masked pattern was here ####
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ properties:
+ bucket_count -1
+ columns key,value1,value2
+ columns.comments
+ columns.types string:string:string
+#### A masked pattern was here ####
+ name default.bucketmapjoin_tmp_result
+ serialization.ddl struct bucketmapjoin_tmp_result { string key, string value1, string value2}
+ 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.bucketmapjoin_tmp_result
+ TotalFiles: 1
+ GatherStats: true
+ MultiFileSpray: false
Local Work:
Map Reduce Local Work
Bucket Mapjoin Context:
@@ -510,11 +518,15 @@ STAGE PLANS:
isSamplingPred: false
predicate: key is not null (type: boolean)
Statistics: Num rows: 15 Data size: 1583 Basic stats: COMPLETE Column stats: NONE
- Spark HashTable Sink Operator
- keys:
- 0 key (type: int)
- 1 key (type: int)
- Position of Big Table: 1
+ Select Operator
+ expressions: key (type: int), value (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 15 Data size: 1583 Basic stats: COMPLETE Column stats: NONE
+ Spark HashTable Sink Operator
+ keys:
+ 0 _col0 (type: int)
+ 1 _col0 (type: int)
+ Position of Big Table: 1
Local Work:
Map Reduce Local Work
Path -> Alias:
@@ -584,52 +596,56 @@ STAGE PLANS:
isSamplingPred: false
predicate: key is not null (type: boolean)
Statistics: Num rows: 28 Data size: 2958 Basic stats: COMPLETE Column stats: NONE
- Map Join Operator
- condition map:
- Inner Join 0 to 1
- keys:
- 0 key (type: int)
- 1 key (type: int)
- outputColumnNames: _col0, _col1, _col7
- input vertices:
- 0 Map 1
- Position of Big Table: 1
- Statistics: Num rows: 30 Data size: 3253 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col0 (type: int), _col1 (type: string), _col7 (type: string)
- outputColumnNames: _col0, _col1, _col2
+ Select Operator
+ expressions: key (type: int), value (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 28 Data size: 2958 Basic stats: COMPLETE Column stats: NONE
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col0 (type: int)
+ 1 _col0 (type: int)
+ outputColumnNames: _col0, _col1, _col3
+ input vertices:
+ 0 Map 1
+ Position of Big Table: 1
Statistics: Num rows: 30 Data size: 3253 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- GlobalTableId: 1
-#### A masked pattern was here ####
- NumFilesPerFileSink: 1
+ Select Operator
+ expressions: _col0 (type: int), _col1 (type: string), _col3 (type: string)
+ outputColumnNames: _col0, _col1, _col2
Statistics: Num rows: 30 Data size: 3253 Basic stats: COMPLETE Column stats: NONE
-#### A masked pattern was here ####
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- COLUMN_STATS_ACCURATE true
- bucket_count -1
- columns key,value1,value2
- columns.comments
- columns.types string:string:string
-#### A masked pattern was here ####
- name default.bucketmapjoin_tmp_result
- numFiles 4
- numRows 564
- rawDataSize 10503
- serialization.ddl struct bucketmapjoin_tmp_result { string key, string value1, string value2}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 11067
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.bucketmapjoin_tmp_result
- TotalFiles: 1
- GatherStats: true
- MultiFileSpray: false
+ File Output Operator
+ compressed: false
+ GlobalTableId: 1
+#### A masked pattern was here ####
+ NumFilesPerFileSink: 1
+ Statistics: Num rows: 30 Data size: 3253 Basic stats: COMPLETE Column stats: NONE
+#### A masked pattern was here ####
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ properties:
+ COLUMN_STATS_ACCURATE true
+ bucket_count -1
+ columns key,value1,value2
+ columns.comments
+ columns.types string:string:string
+#### A masked pattern was here ####
+ name default.bucketmapjoin_tmp_result
+ numFiles 4
+ numRows 564
+ rawDataSize 10503
+ serialization.ddl struct bucketmapjoin_tmp_result { string key, string value1, string value2}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ totalSize 11067
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.bucketmapjoin_tmp_result
+ TotalFiles: 1
+ GatherStats: true
+ MultiFileSpray: false
Local Work:
Map Reduce Local Work
Path -> Alias:
http://git-wip-us.apache.org/repos/asf/hive/blob/855e43df/ql/src/test/results/clientpositive/spark/bucket_map_join_spark4.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/bucket_map_join_spark4.q.out b/ql/src/test/results/clientpositive/spark/bucket_map_join_spark4.q.out
index be46c92..64fb785 100644
--- a/ql/src/test/results/clientpositive/spark/bucket_map_join_spark4.q.out
+++ b/ql/src/test/results/clientpositive/spark/bucket_map_join_spark4.q.out
@@ -157,11 +157,15 @@ STAGE PLANS:
isSamplingPred: false
predicate: (key is not null and value is not null) (type: boolean)
Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE
- Spark HashTable Sink Operator
- keys:
- 0 key (type: int)
- 1 key (type: int)
- Position of Big Table: 1
+ Select Operator
+ expressions: key (type: int), value (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE
+ Spark HashTable Sink Operator
+ keys:
+ 0 _col0 (type: int)
+ 1 _col0 (type: int)
+ Position of Big Table: 1
Local Work:
Map Reduce Local Work
Bucket Mapjoin Context:
@@ -232,11 +236,15 @@ STAGE PLANS:
isSamplingPred: false
predicate: value is not null (type: boolean)
Statistics: Num rows: 5 Data size: 35 Basic stats: COMPLETE Column stats: NONE
- Spark HashTable Sink Operator
- keys:
- 0 _col1 (type: string)
- 1 value (type: string)
- Position of Big Table: 0
+ Select Operator
+ expressions: value (type: string)
+ outputColumnNames: _col1
+ Statistics: Num rows: 5 Data size: 35 Basic stats: COMPLETE Column stats: NONE
+ Spark HashTable Sink Operator
+ keys:
+ 0 _col1 (type: string)
+ 1 _col1 (type: string)
+ Position of Big Table: 0
Local Work:
Map Reduce Local Work
Path -> Alias:
@@ -307,55 +315,59 @@ STAGE PLANS:
isSamplingPred: false
predicate: key is not null (type: boolean)
Statistics: Num rows: 5 Data size: 35 Basic stats: COMPLETE Column stats: NONE
- Map Join Operator
- condition map:
- Inner Join 0 to 1
- keys:
- 0 key (type: int)
- 1 key (type: int)
- outputColumnNames: _col0, _col1, _col6
- input vertices:
- 0 Map 1
- Position of Big Table: 1
- Statistics: Num rows: 5 Data size: 38 Basic stats: COMPLETE Column stats: NONE
- BucketMapJoin: true
+ Select Operator
+ expressions: key (type: int), value (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 5 Data size: 35 Basic stats: COMPLETE Column stats: NONE
Map Join Operator
condition map:
Inner Join 0 to 1
keys:
- 0 _col1 (type: string)
- 1 value (type: string)
- outputColumnNames: _col0, _col1, _col6, _col11
+ 0 _col0 (type: int)
+ 1 _col0 (type: int)
+ outputColumnNames: _col0, _col1, _col3
input vertices:
- 1 Map 3
- Position of Big Table: 0
- Statistics: Num rows: 5 Data size: 41 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col0 (type: int), _col1 (type: string), _col6 (type: string), _col11 (type: string)
- outputColumnNames: _col0, _col1, _col2, _col3
+ 0 Map 1
+ Position of Big Table: 1
+ Statistics: Num rows: 5 Data size: 38 Basic stats: COMPLETE Column stats: NONE
+ BucketMapJoin: true
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col1 (type: string)
+ 1 _col1 (type: string)
+ outputColumnNames: _col0, _col1, _col3, _col5
+ input vertices:
+ 1 Map 3
+ Position of Big Table: 0
Statistics: Num rows: 5 Data size: 41 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- GlobalTableId: 0
-#### A masked pattern was here ####
- NumFilesPerFileSink: 1
+ Select Operator
+ expressions: _col0 (type: int), _col1 (type: string), _col3 (type: string), _col5 (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3
Statistics: Num rows: 5 Data size: 41 Basic stats: COMPLETE Column stats: NONE
-#### A masked pattern was here ####
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- columns _col0,_col1,_col2,_col3
- columns.types int:string:string:string
- escape.delim \
- hive.serialization.extend.additional.nesting.levels true
- serialization.escape.crlf true
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- TotalFiles: 1
- GatherStats: false
- MultiFileSpray: false
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+#### A masked pattern was here ####
+ NumFilesPerFileSink: 1
+ Statistics: Num rows: 5 Data size: 41 Basic stats: COMPLETE Column stats: NONE
+#### A masked pattern was here ####
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ properties:
+ columns _col0,_col1,_col2,_col3
+ columns.types int:string:string:string
+ escape.delim \
+ hive.serialization.extend.additional.nesting.levels true
+ serialization.escape.crlf true
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ TotalFiles: 1
+ GatherStats: false
+ MultiFileSpray: false
Local Work:
Map Reduce Local Work
Bucket Mapjoin Context:
@@ -590,11 +602,15 @@ STAGE PLANS:
isSamplingPred: false
predicate: (key is not null and value is not null) (type: boolean)
Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE
- Spark HashTable Sink Operator
- keys:
- 0 key (type: int)
- 1 key (type: int)
- Position of Big Table: 1
+ Select Operator
+ expressions: key (type: int), value (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE
+ Spark HashTable Sink Operator
+ keys:
+ 0 _col0 (type: int)
+ 1 _col0 (type: int)
+ Position of Big Table: 1
Local Work:
Map Reduce Local Work
Path -> Alias:
@@ -660,11 +676,15 @@ STAGE PLANS:
isSamplingPred: false
predicate: value is not null (type: boolean)
Statistics: Num rows: 5 Data size: 35 Basic stats: COMPLETE Column stats: NONE
- Spark HashTable Sink Operator
- keys:
- 0 _col1 (type: string)
- 1 value (type: string)
- Position of Big Table: 0
+ Select Operator
+ expressions: value (type: string)
+ outputColumnNames: _col1
+ Statistics: Num rows: 5 Data size: 35 Basic stats: COMPLETE Column stats: NONE
+ Spark HashTable Sink Operator
+ keys:
+ 0 _col1 (type: string)
+ 1 _col1 (type: string)
+ Position of Big Table: 0
Local Work:
Map Reduce Local Work
Path -> Alias:
@@ -735,54 +755,58 @@ STAGE PLANS:
isSamplingPred: false
predicate: key is not null (type: boolean)
Statistics: Num rows: 5 Data size: 35 Basic stats: COMPLETE Column stats: NONE
- Map Join Operator
- condition map:
- Inner Join 0 to 1
- keys:
- 0 key (type: int)
- 1 key (type: int)
- outputColumnNames: _col0, _col1, _col6
- input vertices:
- 0 Map 1
- Position of Big Table: 1
- Statistics: Num rows: 5 Data size: 38 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: key (type: int), value (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 5 Data size: 35 Basic stats: COMPLETE Column stats: NONE
Map Join Operator
condition map:
Inner Join 0 to 1
keys:
- 0 _col1 (type: string)
- 1 value (type: string)
- outputColumnNames: _col0, _col1, _col6, _col11
+ 0 _col0 (type: int)
+ 1 _col0 (type: int)
+ outputColumnNames: _col0, _col1, _col3
input vertices:
- 1 Map 3
- Position of Big Table: 0
- Statistics: Num rows: 5 Data size: 41 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col0 (type: int), _col1 (type: string), _col6 (type: string), _col11 (type: string)
- outputColumnNames: _col0, _col1, _col2, _col3
+ 0 Map 1
+ Position of Big Table: 1
+ Statistics: Num rows: 5 Data size: 38 Basic stats: COMPLETE Column stats: NONE
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col1 (type: string)
+ 1 _col1 (type: string)
+ outputColumnNames: _col0, _col1, _col3, _col5
+ input vertices:
+ 1 Map 3
+ Position of Big Table: 0
Statistics: Num rows: 5 Data size: 41 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- GlobalTableId: 0
-#### A masked pattern was here ####
- NumFilesPerFileSink: 1
+ Select Operator
+ expressions: _col0 (type: int), _col1 (type: string), _col3 (type: string), _col5 (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3
Statistics: Num rows: 5 Data size: 41 Basic stats: COMPLETE Column stats: NONE
-#### A masked pattern was here ####
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- columns _col0,_col1,_col2,_col3
- columns.types int:string:string:string
- escape.delim \
- hive.serialization.extend.additional.nesting.levels true
- serialization.escape.crlf true
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- TotalFiles: 1
- GatherStats: false
- MultiFileSpray: false
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+#### A masked pattern was here ####
+ NumFilesPerFileSink: 1
+ Statistics: Num rows: 5 Data size: 41 Basic stats: COMPLETE Column stats: NONE
+#### A masked pattern was here ####
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ properties:
+ columns _col0,_col1,_col2,_col3
+ columns.types int:string:string:string
+ escape.delim \
+ hive.serialization.extend.additional.nesting.levels true
+ serialization.escape.crlf true
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ TotalFiles: 1
+ GatherStats: false
+ MultiFileSpray: false
Local Work:
Map Reduce Local Work
Path -> Alias: