http://git-wip-us.apache.org/repos/asf/hive/blob/6e9b63e4/ql/src/test/results/clientpositive/spark/auto_sortmerge_join_2.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/spark/auto_sortmerge_join_2.q.out b/ql/src/test/results/clientpositive/spark/auto_sortmerge_join_2.q.out index 8cfa113..117ff4a 100644 --- a/ql/src/test/results/clientpositive/spark/auto_sortmerge_join_2.q.out +++ b/ql/src/test/results/clientpositive/spark/auto_sortmerge_join_2.q.out @@ -1,8 +1,8 @@ -PREHOOK: query: CREATE TABLE bucket_small (key string, value string) partitioned by (ds string) CLUSTERED BY (key) SORTED BY (key) INTO 4 BUCKETS STORED AS TEXTFILE +PREHOOK: query: CREATE TABLE bucket_small (key string, value string) partitioned by (ds string) CLUSTERED BY (key) SORTED BY (key) INTO 2 BUCKETS STORED AS TEXTFILE PREHOOK: type: CREATETABLE PREHOOK: Output: database:default PREHOOK: Output: default@bucket_small -POSTHOOK: query: CREATE TABLE bucket_small (key string, value string) partitioned by (ds string) CLUSTERED BY (key) SORTED BY (key) INTO 4 BUCKETS STORED AS TEXTFILE +POSTHOOK: query: CREATE TABLE bucket_small (key string, value string) partitioned by (ds string) CLUSTERED BY (key) SORTED BY (key) INTO 2 BUCKETS STORED AS TEXTFILE POSTHOOK: type: CREATETABLE POSTHOOK: Output: database:default POSTHOOK: Output: default@bucket_small @@ -23,27 +23,11 @@ POSTHOOK: query: load data local inpath '../../data/files/auto_sortmerge_join/sm POSTHOOK: type: LOAD #### A masked pattern was here #### POSTHOOK: Output: default@bucket_small@ds=2008-04-08 -PREHOOK: query: load data local inpath '../../data/files/auto_sortmerge_join/small/000002_0' INTO TABLE bucket_small partition(ds='2008-04-08') -PREHOOK: type: LOAD -#### A masked pattern was here #### -PREHOOK: Output: default@bucket_small@ds=2008-04-08 -POSTHOOK: query: load data local inpath '../../data/files/auto_sortmerge_join/small/000002_0' INTO TABLE bucket_small partition(ds='2008-04-08') -POSTHOOK: type: LOAD -#### A masked pattern was here #### -POSTHOOK: Output: default@bucket_small@ds=2008-04-08 -PREHOOK: query: load data local inpath '../../data/files/auto_sortmerge_join/small/000003_0' INTO TABLE bucket_small partition(ds='2008-04-08') -PREHOOK: type: LOAD -#### A masked pattern was here #### -PREHOOK: Output: default@bucket_small@ds=2008-04-08 -POSTHOOK: query: load data local inpath '../../data/files/auto_sortmerge_join/small/000003_0' INTO TABLE bucket_small partition(ds='2008-04-08') -POSTHOOK: type: LOAD -#### A masked pattern was here #### -POSTHOOK: Output: default@bucket_small@ds=2008-04-08 -PREHOOK: query: CREATE TABLE bucket_big (key string, value string) partitioned by (ds string) CLUSTERED BY (key) SORTED BY (key) INTO 2 BUCKETS STORED AS TEXTFILE +PREHOOK: query: CREATE TABLE bucket_big (key string, value string) partitioned by (ds string) CLUSTERED BY (key) SORTED BY (key) INTO 4 BUCKETS STORED AS TEXTFILE PREHOOK: type: CREATETABLE PREHOOK: Output: database:default PREHOOK: Output: default@bucket_big -POSTHOOK: query: CREATE TABLE bucket_big (key string, value string) partitioned by (ds string) CLUSTERED BY (key) SORTED BY (key) INTO 2 BUCKETS STORED AS TEXTFILE +POSTHOOK: query: CREATE TABLE bucket_big (key string, value string) partitioned by (ds string) CLUSTERED BY (key) SORTED BY (key) INTO 4 BUCKETS STORED AS TEXTFILE POSTHOOK: type: CREATETABLE POSTHOOK: Output: database:default POSTHOOK: Output: default@bucket_big @@ -64,6 +48,22 @@ POSTHOOK: query: load data local inpath '../../data/files/auto_sortmerge_join/bi POSTHOOK: type: LOAD #### A masked pattern was here #### POSTHOOK: Output: default@bucket_big@ds=2008-04-08 +PREHOOK: query: load data local inpath '../../data/files/auto_sortmerge_join/big/000002_0' INTO TABLE bucket_big partition(ds='2008-04-08') +PREHOOK: type: LOAD +#### A masked pattern was here #### +PREHOOK: Output: default@bucket_big@ds=2008-04-08 +POSTHOOK: query: load data local inpath '../../data/files/auto_sortmerge_join/big/000002_0' INTO TABLE bucket_big partition(ds='2008-04-08') +POSTHOOK: type: LOAD +#### A masked pattern was here #### +POSTHOOK: Output: default@bucket_big@ds=2008-04-08 +PREHOOK: query: load data local inpath '../../data/files/auto_sortmerge_join/big/000003_0' INTO TABLE bucket_big partition(ds='2008-04-08') +PREHOOK: type: LOAD +#### A masked pattern was here #### +PREHOOK: Output: default@bucket_big@ds=2008-04-08 +POSTHOOK: query: load data local inpath '../../data/files/auto_sortmerge_join/big/000003_0' INTO TABLE bucket_big partition(ds='2008-04-08') +POSTHOOK: type: LOAD +#### A masked pattern was here #### +POSTHOOK: Output: default@bucket_big@ds=2008-04-08 PREHOOK: query: load data local inpath '../../data/files/auto_sortmerge_join/big/000000_0' INTO TABLE bucket_big partition(ds='2008-04-09') PREHOOK: type: LOAD #### A masked pattern was here #### @@ -81,6 +81,22 @@ POSTHOOK: query: load data local inpath '../../data/files/auto_sortmerge_join/bi POSTHOOK: type: LOAD #### A masked pattern was here #### POSTHOOK: Output: default@bucket_big@ds=2008-04-09 +PREHOOK: query: load data local inpath '../../data/files/auto_sortmerge_join/big/000002_0' INTO TABLE bucket_big partition(ds='2008-04-09') +PREHOOK: type: LOAD +#### A masked pattern was here #### +PREHOOK: Output: default@bucket_big@ds=2008-04-09 +POSTHOOK: query: load data local inpath '../../data/files/auto_sortmerge_join/big/000002_0' INTO TABLE bucket_big partition(ds='2008-04-09') +POSTHOOK: type: LOAD +#### A masked pattern was here #### +POSTHOOK: Output: default@bucket_big@ds=2008-04-09 +PREHOOK: query: load data local inpath '../../data/files/auto_sortmerge_join/big/000003_0' INTO TABLE bucket_big partition(ds='2008-04-09') +PREHOOK: type: LOAD +#### A masked pattern was here #### +PREHOOK: Output: default@bucket_big@ds=2008-04-09 +POSTHOOK: query: load data local inpath '../../data/files/auto_sortmerge_join/big/000003_0' INTO TABLE bucket_big partition(ds='2008-04-09') +POSTHOOK: type: LOAD +#### A masked pattern was here #### +POSTHOOK: Output: default@bucket_big@ds=2008-04-09 PREHOOK: query: explain extended select count(*) FROM bucket_big a JOIN bucket_small b ON a.key = b.key PREHOOK: type: QUERY POSTHOOK: query: explain extended select count(*) FROM bucket_big a JOIN bucket_small b ON a.key = b.key @@ -100,16 +116,16 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 112 Data size: 55000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 240 Data size: 116240 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 112 Data size: 55000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 240 Data size: 116240 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 112 Data size: 55000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 240 Data size: 116240 Basic stats: COMPLETE Column stats: NONE Sorted Merge Bucket Map Join Operator condition map: Inner Join 0 to 1 @@ -117,7 +133,7 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) Position of Big Table: 0 - Statistics: Num rows: 123 Data size: 60500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 264 Data size: 127864 Basic stats: COMPLETE Column stats: NONE BucketMapJoin: true Group By Operator aggregations: count() @@ -142,7 +158,7 @@ STAGE PLANS: partition values: ds 2008-04-08 properties: - bucket_count 2 + bucket_count 4 bucket_field_name key column.name.delimiter , columns key,value @@ -150,7 +166,7 @@ STAGE PLANS: columns.types string:string #### A masked pattern was here #### name default.bucket_big - numFiles 2 + numFiles 4 numRows 0 partition_columns ds partition_columns.types string @@ -158,7 +174,7 @@ STAGE PLANS: serialization.ddl struct bucket_big { string key, string value} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 2750 + totalSize 5812 #### A masked pattern was here #### serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe @@ -166,7 +182,7 @@ 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 @@ -191,7 +207,7 @@ STAGE PLANS: partition values: ds 2008-04-09 properties: - bucket_count 2 + bucket_count 4 bucket_field_name key column.name.delimiter , columns key,value @@ -199,7 +215,7 @@ STAGE PLANS: columns.types string:string #### A masked pattern was here #### name default.bucket_big - numFiles 2 + numFiles 4 numRows 0 partition_columns ds partition_columns.types string @@ -207,7 +223,7 @@ STAGE PLANS: serialization.ddl struct bucket_big { string key, string value} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 2750 + totalSize 5812 #### A masked pattern was here #### serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe @@ -215,7 +231,7 @@ 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 @@ -308,16 +324,16 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 112 Data size: 55000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 240 Data size: 116240 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 112 Data size: 55000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 240 Data size: 116240 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 112 Data size: 55000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 240 Data size: 116240 Basic stats: COMPLETE Column stats: NONE Sorted Merge Bucket Map Join Operator condition map: Inner Join 0 to 1 @@ -325,7 +341,7 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) Position of Big Table: 0 - Statistics: Num rows: 123 Data size: 60500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 264 Data size: 127864 Basic stats: COMPLETE Column stats: NONE BucketMapJoin: true Group By Operator aggregations: count() @@ -350,7 +366,7 @@ STAGE PLANS: partition values: ds 2008-04-08 properties: - bucket_count 2 + bucket_count 4 bucket_field_name key column.name.delimiter , columns key,value @@ -358,7 +374,7 @@ STAGE PLANS: columns.types string:string #### A masked pattern was here #### name default.bucket_big - numFiles 2 + numFiles 4 numRows 0 partition_columns ds partition_columns.types string @@ -366,7 +382,7 @@ STAGE PLANS: serialization.ddl struct bucket_big { string key, string value} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 2750 + totalSize 5812 #### A masked pattern was here #### serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe @@ -374,7 +390,7 @@ 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 @@ -399,7 +415,7 @@ STAGE PLANS: partition values: ds 2008-04-09 properties: - bucket_count 2 + bucket_count 4 bucket_field_name key column.name.delimiter , columns key,value @@ -407,7 +423,7 @@ STAGE PLANS: columns.types string:string #### A masked pattern was here #### name default.bucket_big - numFiles 2 + numFiles 4 numRows 0 partition_columns ds partition_columns.types string @@ -415,7 +431,7 @@ STAGE PLANS: serialization.ddl struct bucket_big { string key, string value} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 2750 + totalSize 5812 #### A masked pattern was here #### serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe @@ -423,7 +439,7 @@ 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
http://git-wip-us.apache.org/repos/asf/hive/blob/6e9b63e4/ql/src/test/results/clientpositive/spark/auto_sortmerge_join_4.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/spark/auto_sortmerge_join_4.q.out b/ql/src/test/results/clientpositive/spark/auto_sortmerge_join_4.q.out index fce5e0c..aff5a0d 100644 --- a/ql/src/test/results/clientpositive/spark/auto_sortmerge_join_4.q.out +++ b/ql/src/test/results/clientpositive/spark/auto_sortmerge_join_4.q.out @@ -72,11 +72,11 @@ POSTHOOK: query: load data local inpath '../../data/files/auto_sortmerge_join/sm POSTHOOK: type: LOAD #### A masked pattern was here #### POSTHOOK: Output: default@bucket_small@ds=2008-04-09 -PREHOOK: query: CREATE TABLE bucket_big (key string, value string) partitioned by (ds string) CLUSTERED BY (key) SORTED BY (key) INTO 2 BUCKETS STORED AS TEXTFILE +PREHOOK: query: CREATE TABLE bucket_big (key string, value string) partitioned by (ds string) CLUSTERED BY (key) SORTED BY (key) INTO 4 BUCKETS STORED AS TEXTFILE PREHOOK: type: CREATETABLE PREHOOK: Output: database:default PREHOOK: Output: default@bucket_big -POSTHOOK: query: CREATE TABLE bucket_big (key string, value string) partitioned by (ds string) CLUSTERED BY (key) SORTED BY (key) INTO 2 BUCKETS STORED AS TEXTFILE +POSTHOOK: query: CREATE TABLE bucket_big (key string, value string) partitioned by (ds string) CLUSTERED BY (key) SORTED BY (key) INTO 4 BUCKETS STORED AS TEXTFILE POSTHOOK: type: CREATETABLE POSTHOOK: Output: database:default POSTHOOK: Output: default@bucket_big @@ -97,6 +97,22 @@ POSTHOOK: query: load data local inpath '../../data/files/auto_sortmerge_join/bi POSTHOOK: type: LOAD #### A masked pattern was here #### POSTHOOK: Output: default@bucket_big@ds=2008-04-08 +PREHOOK: query: load data local inpath '../../data/files/auto_sortmerge_join/big/000002_0' INTO TABLE bucket_big partition(ds='2008-04-08') +PREHOOK: type: LOAD +#### A masked pattern was here #### +PREHOOK: Output: default@bucket_big@ds=2008-04-08 +POSTHOOK: query: load data local inpath '../../data/files/auto_sortmerge_join/big/000002_0' INTO TABLE bucket_big partition(ds='2008-04-08') +POSTHOOK: type: LOAD +#### A masked pattern was here #### +POSTHOOK: Output: default@bucket_big@ds=2008-04-08 +PREHOOK: query: load data local inpath '../../data/files/auto_sortmerge_join/big/000003_0' INTO TABLE bucket_big partition(ds='2008-04-08') +PREHOOK: type: LOAD +#### A masked pattern was here #### +PREHOOK: Output: default@bucket_big@ds=2008-04-08 +POSTHOOK: query: load data local inpath '../../data/files/auto_sortmerge_join/big/000003_0' INTO TABLE bucket_big partition(ds='2008-04-08') +POSTHOOK: type: LOAD +#### A masked pattern was here #### +POSTHOOK: Output: default@bucket_big@ds=2008-04-08 PREHOOK: query: explain extended select count(*) FROM bucket_small a JOIN bucket_big b ON a.key = b.key PREHOOK: type: QUERY POSTHOOK: query: explain extended select count(*) FROM bucket_small a JOIN bucket_big b ON a.key = b.key @@ -116,16 +132,16 @@ STAGE PLANS: Map Operator Tree: TableScan alias: b - Statistics: Num rows: 56 Data size: 27500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 120 Data size: 58120 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: 27500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 120 Data size: 58120 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 56 Data size: 27500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 120 Data size: 58120 Basic stats: COMPLETE Column stats: NONE Sorted Merge Bucket Map Join Operator condition map: Inner Join 0 to 1 @@ -133,7 +149,7 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) Position of Big Table: 1 - Statistics: Num rows: 61 Data size: 30250 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 132 Data size: 63932 Basic stats: COMPLETE Column stats: NONE BucketMapJoin: true Group By Operator aggregations: count() @@ -158,7 +174,7 @@ STAGE PLANS: partition values: ds 2008-04-08 properties: - bucket_count 2 + bucket_count 4 bucket_field_name key column.name.delimiter , columns key,value @@ -166,7 +182,7 @@ STAGE PLANS: columns.types string:string #### A masked pattern was here #### name default.bucket_big - numFiles 2 + numFiles 4 numRows 0 partition_columns ds partition_columns.types string @@ -174,7 +190,7 @@ STAGE PLANS: serialization.ddl struct bucket_big { string key, string value} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 2750 + totalSize 5812 #### A masked pattern was here #### serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe @@ -182,7 +198,7 @@ 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 @@ -254,7 +270,7 @@ POSTHOOK: Input: default@bucket_small POSTHOOK: Input: default@bucket_small@ds=2008-04-08 POSTHOOK: Input: default@bucket_small@ds=2008-04-09 #### A masked pattern was here #### -38 +78 PREHOOK: query: explain extended select count(*) FROM bucket_big a JOIN bucket_small b ON a.key = b.key PREHOOK: type: QUERY POSTHOOK: query: explain extended select count(*) FROM bucket_big a JOIN bucket_small b ON a.key = b.key @@ -274,16 +290,16 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 56 Data size: 27500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 120 Data size: 58120 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: 27500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 120 Data size: 58120 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 56 Data size: 27500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 120 Data size: 58120 Basic stats: COMPLETE Column stats: NONE Sorted Merge Bucket Map Join Operator condition map: Inner Join 0 to 1 @@ -291,7 +307,7 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) Position of Big Table: 0 - Statistics: Num rows: 61 Data size: 30250 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 132 Data size: 63932 Basic stats: COMPLETE Column stats: NONE BucketMapJoin: true Group By Operator aggregations: count() @@ -316,7 +332,7 @@ STAGE PLANS: partition values: ds 2008-04-08 properties: - bucket_count 2 + bucket_count 4 bucket_field_name key column.name.delimiter , columns key,value @@ -324,7 +340,7 @@ STAGE PLANS: columns.types string:string #### A masked pattern was here #### name default.bucket_big - numFiles 2 + numFiles 4 numRows 0 partition_columns ds partition_columns.types string @@ -332,7 +348,7 @@ STAGE PLANS: serialization.ddl struct bucket_big { string key, string value} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 2750 + totalSize 5812 #### A masked pattern was here #### serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe @@ -340,7 +356,7 @@ 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 @@ -412,7 +428,7 @@ POSTHOOK: Input: default@bucket_small POSTHOOK: Input: default@bucket_small@ds=2008-04-08 POSTHOOK: Input: default@bucket_small@ds=2008-04-09 #### A masked pattern was here #### -38 +78 PREHOOK: query: explain extended select count(*) FROM bucket_big a JOIN bucket_small b ON a.key = b.key PREHOOK: type: QUERY POSTHOOK: query: explain extended select count(*) FROM bucket_big a JOIN bucket_small b ON a.key = b.key @@ -432,16 +448,16 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 56 Data size: 27500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 120 Data size: 58120 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: 27500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 120 Data size: 58120 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 56 Data size: 27500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 120 Data size: 58120 Basic stats: COMPLETE Column stats: NONE Sorted Merge Bucket Map Join Operator condition map: Inner Join 0 to 1 @@ -449,7 +465,7 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) Position of Big Table: 0 - Statistics: Num rows: 61 Data size: 30250 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 132 Data size: 63932 Basic stats: COMPLETE Column stats: NONE BucketMapJoin: true Group By Operator aggregations: count() @@ -474,7 +490,7 @@ STAGE PLANS: partition values: ds 2008-04-08 properties: - bucket_count 2 + bucket_count 4 bucket_field_name key column.name.delimiter , columns key,value @@ -482,7 +498,7 @@ STAGE PLANS: columns.types string:string #### A masked pattern was here #### name default.bucket_big - numFiles 2 + numFiles 4 numRows 0 partition_columns ds partition_columns.types string @@ -490,7 +506,7 @@ STAGE PLANS: serialization.ddl struct bucket_big { string key, string value} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 2750 + totalSize 5812 #### A masked pattern was here #### serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe @@ -498,7 +514,7 @@ 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 @@ -570,4 +586,4 @@ POSTHOOK: Input: default@bucket_small POSTHOOK: Input: default@bucket_small@ds=2008-04-08 POSTHOOK: Input: default@bucket_small@ds=2008-04-09 #### A masked pattern was here #### -38 +78 http://git-wip-us.apache.org/repos/asf/hive/blob/6e9b63e4/ql/src/test/results/clientpositive/spark/auto_sortmerge_join_5.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/spark/auto_sortmerge_join_5.q.out b/ql/src/test/results/clientpositive/spark/auto_sortmerge_join_5.q.out index 8250eca..6255dd2 100644 --- a/ql/src/test/results/clientpositive/spark/auto_sortmerge_join_5.q.out +++ b/ql/src/test/results/clientpositive/spark/auto_sortmerge_join_5.q.out @@ -1,8 +1,8 @@ -PREHOOK: query: CREATE TABLE bucket_small (key string, value string) CLUSTERED BY (key) SORTED BY (key) INTO 4 BUCKETS STORED AS TEXTFILE +PREHOOK: query: CREATE TABLE bucket_small (key string, value string) CLUSTERED BY (key) SORTED BY (key) INTO 2 BUCKETS STORED AS TEXTFILE PREHOOK: type: CREATETABLE PREHOOK: Output: database:default PREHOOK: Output: default@bucket_small -POSTHOOK: query: CREATE TABLE bucket_small (key string, value string) CLUSTERED BY (key) SORTED BY (key) INTO 4 BUCKETS STORED AS TEXTFILE +POSTHOOK: query: CREATE TABLE bucket_small (key string, value string) CLUSTERED BY (key) SORTED BY (key) INTO 2 BUCKETS STORED AS TEXTFILE POSTHOOK: type: CREATETABLE POSTHOOK: Output: database:default POSTHOOK: Output: default@bucket_small @@ -22,27 +22,11 @@ POSTHOOK: query: load data local inpath '../../data/files/auto_sortmerge_join/sm POSTHOOK: type: LOAD #### A masked pattern was here #### POSTHOOK: Output: default@bucket_small -PREHOOK: query: load data local inpath '../../data/files/auto_sortmerge_join/small/000002_0' INTO TABLE bucket_small -PREHOOK: type: LOAD -#### A masked pattern was here #### -PREHOOK: Output: default@bucket_small -POSTHOOK: query: load data local inpath '../../data/files/auto_sortmerge_join/small/000002_0' INTO TABLE bucket_small -POSTHOOK: type: LOAD -#### A masked pattern was here #### -POSTHOOK: Output: default@bucket_small -PREHOOK: query: load data local inpath '../../data/files/auto_sortmerge_join/small/000003_0' INTO TABLE bucket_small -PREHOOK: type: LOAD -#### A masked pattern was here #### -PREHOOK: Output: default@bucket_small -POSTHOOK: query: load data local inpath '../../data/files/auto_sortmerge_join/small/000003_0' INTO TABLE bucket_small -POSTHOOK: type: LOAD -#### A masked pattern was here #### -POSTHOOK: Output: default@bucket_small -PREHOOK: query: CREATE TABLE bucket_big (key string, value string) CLUSTERED BY (key) SORTED BY (key) INTO 2 BUCKETS STORED AS TEXTFILE +PREHOOK: query: CREATE TABLE bucket_big (key string, value string) CLUSTERED BY (key) SORTED BY (key) INTO 4 BUCKETS STORED AS TEXTFILE PREHOOK: type: CREATETABLE PREHOOK: Output: database:default PREHOOK: Output: default@bucket_big -POSTHOOK: query: CREATE TABLE bucket_big (key string, value string) CLUSTERED BY (key) SORTED BY (key) INTO 2 BUCKETS STORED AS TEXTFILE +POSTHOOK: query: CREATE TABLE bucket_big (key string, value string) CLUSTERED BY (key) SORTED BY (key) INTO 4 BUCKETS STORED AS TEXTFILE POSTHOOK: type: CREATETABLE POSTHOOK: Output: database:default POSTHOOK: Output: default@bucket_big @@ -62,6 +46,22 @@ POSTHOOK: query: load data local inpath '../../data/files/auto_sortmerge_join/bi POSTHOOK: type: LOAD #### A masked pattern was here #### POSTHOOK: Output: default@bucket_big +PREHOOK: query: load data local inpath '../../data/files/auto_sortmerge_join/big/000002_0' INTO TABLE bucket_big +PREHOOK: type: LOAD +#### A masked pattern was here #### +PREHOOK: Output: default@bucket_big +POSTHOOK: query: load data local inpath '../../data/files/auto_sortmerge_join/big/000002_0' INTO TABLE bucket_big +POSTHOOK: type: LOAD +#### A masked pattern was here #### +POSTHOOK: Output: default@bucket_big +PREHOOK: query: load data local inpath '../../data/files/auto_sortmerge_join/big/000003_0' INTO TABLE bucket_big +PREHOOK: type: LOAD +#### A masked pattern was here #### +PREHOOK: Output: default@bucket_big +POSTHOOK: query: load data local inpath '../../data/files/auto_sortmerge_join/big/000003_0' INTO TABLE bucket_big +POSTHOOK: type: LOAD +#### A masked pattern was here #### +POSTHOOK: Output: default@bucket_big PREHOOK: query: explain extended select count(*) FROM bucket_small a JOIN bucket_big b ON a.key = b.key PREHOOK: type: QUERY POSTHOOK: query: explain extended select count(*) FROM bucket_small a JOIN bucket_big b ON a.key = b.key @@ -81,16 +81,16 @@ STAGE PLANS: Map Operator Tree: TableScan alias: b - Statistics: Num rows: 1 Data size: 27500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 58120 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 27500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 58120 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 27500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 58120 Basic stats: COMPLETE Column stats: NONE Sorted Merge Bucket Map Join Operator condition map: Inner Join 0 to 1 @@ -98,7 +98,7 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) Position of Big Table: 1 - Statistics: Num rows: 1 Data size: 2486 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1254 Basic stats: COMPLETE Column stats: NONE BucketMapJoin: true Group By Operator aggregations: count() @@ -122,7 +122,7 @@ 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 @@ -130,13 +130,13 @@ STAGE PLANS: columns.types string:string #### A masked pattern was here #### name default.bucket_big - numFiles 2 + numFiles 4 numRows 0 rawDataSize 0 serialization.ddl struct bucket_big { string key, string value} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 2750 + totalSize 5812 #### A masked pattern was here #### serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe @@ -144,7 +144,7 @@ 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 @@ -152,13 +152,13 @@ STAGE PLANS: columns.types string:string #### A masked pattern was here #### name default.bucket_big - numFiles 2 + numFiles 4 numRows 0 rawDataSize 0 serialization.ddl struct bucket_big { string key, string value} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 2750 + totalSize 5812 #### A masked pattern was here #### serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.bucket_big @@ -232,16 +232,16 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 1 Data size: 27500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 58120 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 27500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 58120 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 27500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 58120 Basic stats: COMPLETE Column stats: NONE Sorted Merge Bucket Map Join Operator condition map: Inner Join 0 to 1 @@ -249,7 +249,7 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) Position of Big Table: 0 - Statistics: Num rows: 1 Data size: 30250 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 63932 Basic stats: COMPLETE Column stats: NONE BucketMapJoin: true Group By Operator aggregations: count() @@ -273,7 +273,7 @@ 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 @@ -281,13 +281,13 @@ STAGE PLANS: columns.types string:string #### A masked pattern was here #### name default.bucket_big - numFiles 2 + numFiles 4 numRows 0 rawDataSize 0 serialization.ddl struct bucket_big { string key, string value} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 2750 + totalSize 5812 #### A masked pattern was here #### serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe @@ -295,7 +295,7 @@ 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 @@ -303,13 +303,13 @@ STAGE PLANS: columns.types string:string #### A masked pattern was here #### name default.bucket_big - numFiles 2 + numFiles 4 numRows 0 rawDataSize 0 serialization.ddl struct bucket_big { string key, string value} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 2750 + totalSize 5812 #### A masked pattern was here #### serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.bucket_big @@ -382,16 +382,16 @@ STAGE PLANS: Map Operator Tree: TableScan alias: b - Statistics: Num rows: 1 Data size: 2260 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1140 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 2260 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1140 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 2260 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 1140 Basic stats: COMPLETE Column stats: NONE Spark HashTable Sink Operator keys: 0 _col0 (type: string) @@ -414,7 +414,7 @@ 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 @@ -422,13 +422,13 @@ STAGE PLANS: columns.types string:string #### A masked pattern was here #### name default.bucket_small - numFiles 4 + numFiles 2 numRows 0 rawDataSize 0 serialization.ddl struct bucket_small { string key, string value} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 226 + totalSize 114 #### A masked pattern was here #### serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe @@ -436,7 +436,7 @@ 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 @@ -444,13 +444,13 @@ STAGE PLANS: columns.types string:string #### A masked pattern was here #### name default.bucket_small - numFiles 4 + numFiles 2 numRows 0 rawDataSize 0 serialization.ddl struct bucket_small { string key, string value} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 226 + totalSize 114 #### A masked pattern was here #### serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.bucket_small @@ -468,16 +468,16 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 1 Data size: 27500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 58120 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 27500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 58120 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 27500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 58120 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 @@ -487,7 +487,7 @@ STAGE PLANS: input vertices: 1 Map 3 Position of Big Table: 0 - Statistics: Num rows: 1 Data size: 30250 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 63932 Basic stats: COMPLETE Column stats: NONE BucketMapJoin: true Group By Operator aggregations: count() @@ -518,7 +518,7 @@ 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 @@ -526,13 +526,13 @@ STAGE PLANS: columns.types string:string #### A masked pattern was here #### name default.bucket_big - numFiles 2 + numFiles 4 numRows 0 rawDataSize 0 serialization.ddl struct bucket_big { string key, string value} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 2750 + totalSize 5812 #### A masked pattern was here #### serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe @@ -540,7 +540,7 @@ 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 @@ -548,13 +548,13 @@ STAGE PLANS: columns.types string:string #### A masked pattern was here #### name default.bucket_big - numFiles 2 + numFiles 4 numRows 0 rawDataSize 0 serialization.ddl struct bucket_big { string key, string value} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 2750 + totalSize 5812 #### A masked pattern was here #### serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.bucket_big http://git-wip-us.apache.org/repos/asf/hive/blob/6e9b63e4/ql/src/test/results/clientpositive/spark/auto_sortmerge_join_7.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/spark/auto_sortmerge_join_7.q.out b/ql/src/test/results/clientpositive/spark/auto_sortmerge_join_7.q.out index eb813c1..ac5cd47 100644 --- a/ql/src/test/results/clientpositive/spark/auto_sortmerge_join_7.q.out +++ b/ql/src/test/results/clientpositive/spark/auto_sortmerge_join_7.q.out @@ -72,11 +72,11 @@ POSTHOOK: query: load data local inpath '../../data/files/auto_sortmerge_join/sm POSTHOOK: type: LOAD #### A masked pattern was here #### POSTHOOK: Output: default@bucket_small@ds=2008-04-09 -PREHOOK: query: CREATE TABLE bucket_big (key string, value string) partitioned by (ds string) CLUSTERED BY (key) SORTED BY (key) INTO 2 BUCKETS STORED AS TEXTFILE +PREHOOK: query: CREATE TABLE bucket_big (key string, value string) partitioned by (ds string) CLUSTERED BY (key) SORTED BY (key) INTO 4 BUCKETS STORED AS TEXTFILE PREHOOK: type: CREATETABLE PREHOOK: Output: database:default PREHOOK: Output: default@bucket_big -POSTHOOK: query: CREATE TABLE bucket_big (key string, value string) partitioned by (ds string) CLUSTERED BY (key) SORTED BY (key) INTO 2 BUCKETS STORED AS TEXTFILE +POSTHOOK: query: CREATE TABLE bucket_big (key string, value string) partitioned by (ds string) CLUSTERED BY (key) SORTED BY (key) INTO 4 BUCKETS STORED AS TEXTFILE POSTHOOK: type: CREATETABLE POSTHOOK: Output: database:default POSTHOOK: Output: default@bucket_big @@ -97,6 +97,22 @@ POSTHOOK: query: load data local inpath '../../data/files/auto_sortmerge_join/bi POSTHOOK: type: LOAD #### A masked pattern was here #### POSTHOOK: Output: default@bucket_big@ds=2008-04-08 +PREHOOK: query: load data local inpath '../../data/files/auto_sortmerge_join/big/000002_0' INTO TABLE bucket_big partition(ds='2008-04-08') +PREHOOK: type: LOAD +#### A masked pattern was here #### +PREHOOK: Output: default@bucket_big@ds=2008-04-08 +POSTHOOK: query: load data local inpath '../../data/files/auto_sortmerge_join/big/000002_0' INTO TABLE bucket_big partition(ds='2008-04-08') +POSTHOOK: type: LOAD +#### A masked pattern was here #### +POSTHOOK: Output: default@bucket_big@ds=2008-04-08 +PREHOOK: query: load data local inpath '../../data/files/auto_sortmerge_join/big/000003_0' INTO TABLE bucket_big partition(ds='2008-04-08') +PREHOOK: type: LOAD +#### A masked pattern was here #### +PREHOOK: Output: default@bucket_big@ds=2008-04-08 +POSTHOOK: query: load data local inpath '../../data/files/auto_sortmerge_join/big/000003_0' INTO TABLE bucket_big partition(ds='2008-04-08') +POSTHOOK: type: LOAD +#### A masked pattern was here #### +POSTHOOK: Output: default@bucket_big@ds=2008-04-08 PREHOOK: query: load data local inpath '../../data/files/auto_sortmerge_join/big/000000_0' INTO TABLE bucket_big partition(ds='2008-04-09') PREHOOK: type: LOAD #### A masked pattern was here #### @@ -114,6 +130,22 @@ POSTHOOK: query: load data local inpath '../../data/files/auto_sortmerge_join/bi POSTHOOK: type: LOAD #### A masked pattern was here #### POSTHOOK: Output: default@bucket_big@ds=2008-04-09 +PREHOOK: query: load data local inpath '../../data/files/auto_sortmerge_join/big/000002_0' INTO TABLE bucket_big partition(ds='2008-04-09') +PREHOOK: type: LOAD +#### A masked pattern was here #### +PREHOOK: Output: default@bucket_big@ds=2008-04-09 +POSTHOOK: query: load data local inpath '../../data/files/auto_sortmerge_join/big/000002_0' INTO TABLE bucket_big partition(ds='2008-04-09') +POSTHOOK: type: LOAD +#### A masked pattern was here #### +POSTHOOK: Output: default@bucket_big@ds=2008-04-09 +PREHOOK: query: load data local inpath '../../data/files/auto_sortmerge_join/big/000003_0' INTO TABLE bucket_big partition(ds='2008-04-09') +PREHOOK: type: LOAD +#### A masked pattern was here #### +PREHOOK: Output: default@bucket_big@ds=2008-04-09 +POSTHOOK: query: load data local inpath '../../data/files/auto_sortmerge_join/big/000003_0' INTO TABLE bucket_big partition(ds='2008-04-09') +POSTHOOK: type: LOAD +#### A masked pattern was here #### +POSTHOOK: Output: default@bucket_big@ds=2008-04-09 PREHOOK: query: explain extended select count(*) FROM bucket_small a JOIN bucket_big b ON a.key = b.key PREHOOK: type: QUERY POSTHOOK: query: explain extended select count(*) FROM bucket_small a JOIN bucket_big b ON a.key = b.key @@ -133,16 +165,16 @@ STAGE PLANS: Map Operator Tree: TableScan alias: b - Statistics: Num rows: 112 Data size: 55000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 240 Data size: 116240 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 112 Data size: 55000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 240 Data size: 116240 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 112 Data size: 55000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 240 Data size: 116240 Basic stats: COMPLETE Column stats: NONE Sorted Merge Bucket Map Join Operator condition map: Inner Join 0 to 1 @@ -150,7 +182,7 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) Position of Big Table: 1 - Statistics: Num rows: 123 Data size: 60500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 264 Data size: 127864 Basic stats: COMPLETE Column stats: NONE BucketMapJoin: true Group By Operator aggregations: count() @@ -175,7 +207,7 @@ STAGE PLANS: partition values: ds 2008-04-08 properties: - bucket_count 2 + bucket_count 4 bucket_field_name key column.name.delimiter , columns key,value @@ -183,7 +215,7 @@ STAGE PLANS: columns.types string:string #### A masked pattern was here #### name default.bucket_big - numFiles 2 + numFiles 4 numRows 0 partition_columns ds partition_columns.types string @@ -191,7 +223,7 @@ STAGE PLANS: serialization.ddl struct bucket_big { string key, string value} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 2750 + totalSize 5812 #### A masked pattern was here #### serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe @@ -199,7 +231,7 @@ 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 @@ -224,7 +256,7 @@ STAGE PLANS: partition values: ds 2008-04-09 properties: - bucket_count 2 + bucket_count 4 bucket_field_name key column.name.delimiter , columns key,value @@ -232,7 +264,7 @@ STAGE PLANS: columns.types string:string #### A masked pattern was here #### name default.bucket_big - numFiles 2 + numFiles 4 numRows 0 partition_columns ds partition_columns.types string @@ -240,7 +272,7 @@ STAGE PLANS: serialization.ddl struct bucket_big { string key, string value} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 2750 + totalSize 5812 #### A masked pattern was here #### serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe @@ -248,7 +280,7 @@ 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 @@ -323,7 +355,7 @@ POSTHOOK: Input: default@bucket_small POSTHOOK: Input: default@bucket_small@ds=2008-04-08 POSTHOOK: Input: default@bucket_small@ds=2008-04-09 #### A masked pattern was here #### -76 +156 PREHOOK: query: explain extended select count(*) FROM bucket_big a JOIN bucket_small b ON a.key = b.key PREHOOK: type: QUERY POSTHOOK: query: explain extended select count(*) FROM bucket_big a JOIN bucket_small b ON a.key = b.key @@ -343,16 +375,16 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 112 Data size: 55000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 240 Data size: 116240 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 112 Data size: 55000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 240 Data size: 116240 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 112 Data size: 55000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 240 Data size: 116240 Basic stats: COMPLETE Column stats: NONE Sorted Merge Bucket Map Join Operator condition map: Inner Join 0 to 1 @@ -360,7 +392,7 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) Position of Big Table: 0 - Statistics: Num rows: 123 Data size: 60500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 264 Data size: 127864 Basic stats: COMPLETE Column stats: NONE BucketMapJoin: true Group By Operator aggregations: count() @@ -385,7 +417,7 @@ STAGE PLANS: partition values: ds 2008-04-08 properties: - bucket_count 2 + bucket_count 4 bucket_field_name key column.name.delimiter , columns key,value @@ -393,7 +425,7 @@ STAGE PLANS: columns.types string:string #### A masked pattern was here #### name default.bucket_big - numFiles 2 + numFiles 4 numRows 0 partition_columns ds partition_columns.types string @@ -401,7 +433,7 @@ STAGE PLANS: serialization.ddl struct bucket_big { string key, string value} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 2750 + totalSize 5812 #### A masked pattern was here #### serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe @@ -409,7 +441,7 @@ 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 @@ -434,7 +466,7 @@ STAGE PLANS: partition values: ds 2008-04-09 properties: - bucket_count 2 + bucket_count 4 bucket_field_name key column.name.delimiter , columns key,value @@ -442,7 +474,7 @@ STAGE PLANS: columns.types string:string #### A masked pattern was here #### name default.bucket_big - numFiles 2 + numFiles 4 numRows 0 partition_columns ds partition_columns.types string @@ -450,7 +482,7 @@ STAGE PLANS: serialization.ddl struct bucket_big { string key, string value} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 2750 + totalSize 5812 #### A masked pattern was here #### serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe @@ -458,7 +490,7 @@ 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 @@ -533,7 +565,7 @@ POSTHOOK: Input: default@bucket_small POSTHOOK: Input: default@bucket_small@ds=2008-04-08 POSTHOOK: Input: default@bucket_small@ds=2008-04-09 #### A masked pattern was here #### -76 +156 PREHOOK: query: explain extended select count(*) FROM bucket_big a JOIN bucket_small b ON a.key = b.key PREHOOK: type: QUERY POSTHOOK: query: explain extended select count(*) FROM bucket_big a JOIN bucket_small b ON a.key = b.key @@ -553,16 +585,16 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 112 Data size: 55000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 240 Data size: 116240 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 112 Data size: 55000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 240 Data size: 116240 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 112 Data size: 55000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 240 Data size: 116240 Basic stats: COMPLETE Column stats: NONE Sorted Merge Bucket Map Join Operator condition map: Inner Join 0 to 1 @@ -570,7 +602,7 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) Position of Big Table: 0 - Statistics: Num rows: 123 Data size: 60500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 264 Data size: 127864 Basic stats: COMPLETE Column stats: NONE BucketMapJoin: true Group By Operator aggregations: count() @@ -595,7 +627,7 @@ STAGE PLANS: partition values: ds 2008-04-08 properties: - bucket_count 2 + bucket_count 4 bucket_field_name key column.name.delimiter , columns key,value @@ -603,7 +635,7 @@ STAGE PLANS: columns.types string:string #### A masked pattern was here #### name default.bucket_big - numFiles 2 + numFiles 4 numRows 0 partition_columns ds partition_columns.types string @@ -611,7 +643,7 @@ STAGE PLANS: serialization.ddl struct bucket_big { string key, string value} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 2750 + totalSize 5812 #### A masked pattern was here #### serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe @@ -619,7 +651,7 @@ 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 @@ -644,7 +676,7 @@ STAGE PLANS: partition values: ds 2008-04-09 properties: - bucket_count 2 + bucket_count 4 bucket_field_name key column.name.delimiter , columns key,value @@ -652,7 +684,7 @@ STAGE PLANS: columns.types string:string #### A masked pattern was here #### name default.bucket_big - numFiles 2 + numFiles 4 numRows 0 partition_columns ds partition_columns.types string @@ -660,7 +692,7 @@ STAGE PLANS: serialization.ddl struct bucket_big { string key, string value} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 2750 + totalSize 5812 #### A masked pattern was here #### serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe @@ -668,7 +700,7 @@ 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 @@ -743,4 +775,4 @@ POSTHOOK: Input: default@bucket_small POSTHOOK: Input: default@bucket_small@ds=2008-04-08 POSTHOOK: Input: default@bucket_small@ds=2008-04-09 #### A masked pattern was here #### -76 +156