http://git-wip-us.apache.org/repos/asf/hive/blob/3464df45/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 117ff4a..8cfa113 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 2 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 4 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 2 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 4 BUCKETS STORED AS TEXTFILE POSTHOOK: type: CREATETABLE POSTHOOK: Output: database:default POSTHOOK: Output: default@bucket_small @@ -23,11 +23,27 @@ 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: 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: 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: 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 4 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 2 BUCKETS STORED AS TEXTFILE POSTHOOK: type: CREATETABLE POSTHOOK: Output: database:default POSTHOOK: Output: default@bucket_big @@ -48,22 +64,6 @@ 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 #### @@ -81,22 +81,6 @@ 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 @@ -116,16 +100,16 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 240 Data size: 116240 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 112 Data size: 55000 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 240 Data size: 116240 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 112 Data size: 55000 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 240 Data size: 116240 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 112 Data size: 55000 Basic stats: COMPLETE Column stats: NONE Sorted Merge Bucket Map Join Operator condition map: Inner Join 0 to 1 @@ -133,7 +117,7 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) Position of Big Table: 0 - Statistics: Num rows: 264 Data size: 127864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 123 Data size: 60500 Basic stats: COMPLETE Column stats: NONE BucketMapJoin: true Group By Operator aggregations: count() @@ -158,7 +142,7 @@ STAGE PLANS: partition values: ds 2008-04-08 properties: - bucket_count 4 + bucket_count 2 bucket_field_name key column.name.delimiter , columns key,value @@ -166,7 +150,7 @@ STAGE PLANS: columns.types string:string #### A masked pattern was here #### name default.bucket_big - numFiles 4 + numFiles 2 numRows 0 partition_columns ds partition_columns.types string @@ -174,7 +158,7 @@ STAGE PLANS: serialization.ddl struct bucket_big { string key, string value} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 5812 + totalSize 2750 #### A masked pattern was here #### serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe @@ -182,7 +166,7 @@ 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 @@ -207,7 +191,7 @@ STAGE PLANS: partition values: ds 2008-04-09 properties: - bucket_count 4 + bucket_count 2 bucket_field_name key column.name.delimiter , columns key,value @@ -215,7 +199,7 @@ STAGE PLANS: columns.types string:string #### A masked pattern was here #### name default.bucket_big - numFiles 4 + numFiles 2 numRows 0 partition_columns ds partition_columns.types string @@ -223,7 +207,7 @@ STAGE PLANS: serialization.ddl struct bucket_big { string key, string value} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 5812 + totalSize 2750 #### A masked pattern was here #### serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe @@ -231,7 +215,7 @@ 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 @@ -324,16 +308,16 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 240 Data size: 116240 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 112 Data size: 55000 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 240 Data size: 116240 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 112 Data size: 55000 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 240 Data size: 116240 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 112 Data size: 55000 Basic stats: COMPLETE Column stats: NONE Sorted Merge Bucket Map Join Operator condition map: Inner Join 0 to 1 @@ -341,7 +325,7 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) Position of Big Table: 0 - Statistics: Num rows: 264 Data size: 127864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 123 Data size: 60500 Basic stats: COMPLETE Column stats: NONE BucketMapJoin: true Group By Operator aggregations: count() @@ -366,7 +350,7 @@ STAGE PLANS: partition values: ds 2008-04-08 properties: - bucket_count 4 + bucket_count 2 bucket_field_name key column.name.delimiter , columns key,value @@ -374,7 +358,7 @@ STAGE PLANS: columns.types string:string #### A masked pattern was here #### name default.bucket_big - numFiles 4 + numFiles 2 numRows 0 partition_columns ds partition_columns.types string @@ -382,7 +366,7 @@ STAGE PLANS: serialization.ddl struct bucket_big { string key, string value} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 5812 + totalSize 2750 #### A masked pattern was here #### serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe @@ -390,7 +374,7 @@ 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 @@ -415,7 +399,7 @@ STAGE PLANS: partition values: ds 2008-04-09 properties: - bucket_count 4 + bucket_count 2 bucket_field_name key column.name.delimiter , columns key,value @@ -423,7 +407,7 @@ STAGE PLANS: columns.types string:string #### A masked pattern was here #### name default.bucket_big - numFiles 4 + numFiles 2 numRows 0 partition_columns ds partition_columns.types string @@ -431,7 +415,7 @@ STAGE PLANS: serialization.ddl struct bucket_big { string key, string value} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 5812 + totalSize 2750 #### A masked pattern was here #### serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe @@ -439,7 +423,7 @@ 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
http://git-wip-us.apache.org/repos/asf/hive/blob/3464df45/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 aff5a0d..fce5e0c 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 4 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 2 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 4 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 2 BUCKETS STORED AS TEXTFILE POSTHOOK: type: CREATETABLE POSTHOOK: Output: database:default POSTHOOK: Output: default@bucket_big @@ -97,22 +97,6 @@ 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 @@ -132,16 +116,16 @@ STAGE PLANS: Map Operator Tree: TableScan alias: b - Statistics: Num rows: 120 Data size: 58120 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 56 Data size: 27500 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 120 Data size: 58120 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 56 Data size: 27500 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 120 Data size: 58120 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 56 Data size: 27500 Basic stats: COMPLETE Column stats: NONE Sorted Merge Bucket Map Join Operator condition map: Inner Join 0 to 1 @@ -149,7 +133,7 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) Position of Big Table: 1 - Statistics: Num rows: 132 Data size: 63932 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 61 Data size: 30250 Basic stats: COMPLETE Column stats: NONE BucketMapJoin: true Group By Operator aggregations: count() @@ -174,7 +158,7 @@ STAGE PLANS: partition values: ds 2008-04-08 properties: - bucket_count 4 + bucket_count 2 bucket_field_name key column.name.delimiter , columns key,value @@ -182,7 +166,7 @@ STAGE PLANS: columns.types string:string #### A masked pattern was here #### name default.bucket_big - numFiles 4 + numFiles 2 numRows 0 partition_columns ds partition_columns.types string @@ -190,7 +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 5812 + totalSize 2750 #### A masked pattern was here #### serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe @@ -198,7 +182,7 @@ 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 @@ -270,7 +254,7 @@ 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 #### -78 +38 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 @@ -290,16 +274,16 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 120 Data size: 58120 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 56 Data size: 27500 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 120 Data size: 58120 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 56 Data size: 27500 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 120 Data size: 58120 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 56 Data size: 27500 Basic stats: COMPLETE Column stats: NONE Sorted Merge Bucket Map Join Operator condition map: Inner Join 0 to 1 @@ -307,7 +291,7 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) Position of Big Table: 0 - Statistics: Num rows: 132 Data size: 63932 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 61 Data size: 30250 Basic stats: COMPLETE Column stats: NONE BucketMapJoin: true Group By Operator aggregations: count() @@ -332,7 +316,7 @@ STAGE PLANS: partition values: ds 2008-04-08 properties: - bucket_count 4 + bucket_count 2 bucket_field_name key column.name.delimiter , columns key,value @@ -340,7 +324,7 @@ STAGE PLANS: columns.types string:string #### A masked pattern was here #### name default.bucket_big - numFiles 4 + numFiles 2 numRows 0 partition_columns ds partition_columns.types string @@ -348,7 +332,7 @@ STAGE PLANS: serialization.ddl struct bucket_big { string key, string value} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 5812 + totalSize 2750 #### A masked pattern was here #### serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe @@ -356,7 +340,7 @@ 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 @@ -428,7 +412,7 @@ 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 #### -78 +38 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 @@ -448,16 +432,16 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 120 Data size: 58120 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 56 Data size: 27500 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 120 Data size: 58120 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 56 Data size: 27500 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 120 Data size: 58120 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 56 Data size: 27500 Basic stats: COMPLETE Column stats: NONE Sorted Merge Bucket Map Join Operator condition map: Inner Join 0 to 1 @@ -465,7 +449,7 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) Position of Big Table: 0 - Statistics: Num rows: 132 Data size: 63932 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 61 Data size: 30250 Basic stats: COMPLETE Column stats: NONE BucketMapJoin: true Group By Operator aggregations: count() @@ -490,7 +474,7 @@ STAGE PLANS: partition values: ds 2008-04-08 properties: - bucket_count 4 + bucket_count 2 bucket_field_name key column.name.delimiter , columns key,value @@ -498,7 +482,7 @@ STAGE PLANS: columns.types string:string #### A masked pattern was here #### name default.bucket_big - numFiles 4 + numFiles 2 numRows 0 partition_columns ds partition_columns.types string @@ -506,7 +490,7 @@ STAGE PLANS: serialization.ddl struct bucket_big { string key, string value} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 5812 + totalSize 2750 #### A masked pattern was here #### serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe @@ -514,7 +498,7 @@ 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 @@ -586,4 +570,4 @@ 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 #### -78 +38 http://git-wip-us.apache.org/repos/asf/hive/blob/3464df45/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 6255dd2..8250eca 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 2 BUCKETS STORED AS TEXTFILE +PREHOOK: query: CREATE TABLE bucket_small (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_small -POSTHOOK: query: CREATE TABLE bucket_small (key string, value string) CLUSTERED BY (key) SORTED BY (key) INTO 2 BUCKETS STORED AS TEXTFILE +POSTHOOK: query: CREATE TABLE bucket_small (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_small @@ -22,11 +22,27 @@ 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: CREATE TABLE bucket_big (key string, value string) CLUSTERED BY (key) SORTED BY (key) INTO 4 BUCKETS STORED AS TEXTFILE +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: 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 4 BUCKETS STORED AS TEXTFILE +POSTHOOK: query: CREATE TABLE bucket_big (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_big @@ -46,22 +62,6 @@ 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: 58120 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 27500 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: 58120 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 27500 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 58120 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 27500 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: 1254 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 2486 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 4 + bucket_count 2 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 4 + numFiles 2 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 5812 + totalSize 2750 #### 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 4 + bucket_count 2 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 4 + numFiles 2 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 5812 + totalSize 2750 #### 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: 58120 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 27500 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: 58120 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 27500 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 58120 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 27500 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: 63932 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 30250 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 4 + bucket_count 2 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 4 + numFiles 2 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 5812 + totalSize 2750 #### 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 4 + bucket_count 2 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 4 + numFiles 2 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 5812 + totalSize 2750 #### 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: 1140 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 2260 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: 1140 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 2260 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 1140 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 2260 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 2 + bucket_count 4 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 2 + numFiles 4 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 114 + totalSize 226 #### 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 2 + bucket_count 4 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 2 + numFiles 4 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 114 + totalSize 226 #### 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: 58120 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 27500 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: 58120 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 27500 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 58120 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 27500 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: 63932 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 30250 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 4 + bucket_count 2 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 4 + numFiles 2 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 5812 + totalSize 2750 #### 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 4 + bucket_count 2 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 4 + numFiles 2 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 5812 + totalSize 2750 #### 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/3464df45/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 ac5cd47..eb813c1 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 4 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 2 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 4 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 2 BUCKETS STORED AS TEXTFILE POSTHOOK: type: CREATETABLE POSTHOOK: Output: database:default POSTHOOK: Output: default@bucket_big @@ -97,22 +97,6 @@ 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 #### @@ -130,22 +114,6 @@ 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 @@ -165,16 +133,16 @@ STAGE PLANS: Map Operator Tree: TableScan alias: b - Statistics: Num rows: 240 Data size: 116240 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 112 Data size: 55000 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 240 Data size: 116240 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 112 Data size: 55000 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 240 Data size: 116240 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 112 Data size: 55000 Basic stats: COMPLETE Column stats: NONE Sorted Merge Bucket Map Join Operator condition map: Inner Join 0 to 1 @@ -182,7 +150,7 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) Position of Big Table: 1 - Statistics: Num rows: 264 Data size: 127864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 123 Data size: 60500 Basic stats: COMPLETE Column stats: NONE BucketMapJoin: true Group By Operator aggregations: count() @@ -207,7 +175,7 @@ STAGE PLANS: partition values: ds 2008-04-08 properties: - bucket_count 4 + bucket_count 2 bucket_field_name key column.name.delimiter , columns key,value @@ -215,7 +183,7 @@ STAGE PLANS: columns.types string:string #### A masked pattern was here #### name default.bucket_big - numFiles 4 + numFiles 2 numRows 0 partition_columns ds partition_columns.types string @@ -223,7 +191,7 @@ STAGE PLANS: serialization.ddl struct bucket_big { string key, string value} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 5812 + totalSize 2750 #### A masked pattern was here #### serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe @@ -231,7 +199,7 @@ 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 @@ -256,7 +224,7 @@ STAGE PLANS: partition values: ds 2008-04-09 properties: - bucket_count 4 + bucket_count 2 bucket_field_name key column.name.delimiter , columns key,value @@ -264,7 +232,7 @@ STAGE PLANS: columns.types string:string #### A masked pattern was here #### name default.bucket_big - numFiles 4 + numFiles 2 numRows 0 partition_columns ds partition_columns.types string @@ -272,7 +240,7 @@ STAGE PLANS: serialization.ddl struct bucket_big { string key, string value} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 5812 + totalSize 2750 #### A masked pattern was here #### serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe @@ -280,7 +248,7 @@ 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 @@ -355,7 +323,7 @@ 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 #### -156 +76 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 @@ -375,16 +343,16 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 240 Data size: 116240 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 112 Data size: 55000 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 240 Data size: 116240 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 112 Data size: 55000 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 240 Data size: 116240 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 112 Data size: 55000 Basic stats: COMPLETE Column stats: NONE Sorted Merge Bucket Map Join Operator condition map: Inner Join 0 to 1 @@ -392,7 +360,7 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) Position of Big Table: 0 - Statistics: Num rows: 264 Data size: 127864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 123 Data size: 60500 Basic stats: COMPLETE Column stats: NONE BucketMapJoin: true Group By Operator aggregations: count() @@ -417,7 +385,7 @@ STAGE PLANS: partition values: ds 2008-04-08 properties: - bucket_count 4 + bucket_count 2 bucket_field_name key column.name.delimiter , columns key,value @@ -425,7 +393,7 @@ STAGE PLANS: columns.types string:string #### A masked pattern was here #### name default.bucket_big - numFiles 4 + numFiles 2 numRows 0 partition_columns ds partition_columns.types string @@ -433,7 +401,7 @@ STAGE PLANS: serialization.ddl struct bucket_big { string key, string value} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 5812 + totalSize 2750 #### A masked pattern was here #### serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe @@ -441,7 +409,7 @@ 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 @@ -466,7 +434,7 @@ STAGE PLANS: partition values: ds 2008-04-09 properties: - bucket_count 4 + bucket_count 2 bucket_field_name key column.name.delimiter , columns key,value @@ -474,7 +442,7 @@ STAGE PLANS: columns.types string:string #### A masked pattern was here #### name default.bucket_big - numFiles 4 + numFiles 2 numRows 0 partition_columns ds partition_columns.types string @@ -482,7 +450,7 @@ STAGE PLANS: serialization.ddl struct bucket_big { string key, string value} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 5812 + totalSize 2750 #### A masked pattern was here #### serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe @@ -490,7 +458,7 @@ 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 @@ -565,7 +533,7 @@ 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 #### -156 +76 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 @@ -585,16 +553,16 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 240 Data size: 116240 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 112 Data size: 55000 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 240 Data size: 116240 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 112 Data size: 55000 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 240 Data size: 116240 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 112 Data size: 55000 Basic stats: COMPLETE Column stats: NONE Sorted Merge Bucket Map Join Operator condition map: Inner Join 0 to 1 @@ -602,7 +570,7 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) Position of Big Table: 0 - Statistics: Num rows: 264 Data size: 127864 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 123 Data size: 60500 Basic stats: COMPLETE Column stats: NONE BucketMapJoin: true Group By Operator aggregations: count() @@ -627,7 +595,7 @@ STAGE PLANS: partition values: ds 2008-04-08 properties: - bucket_count 4 + bucket_count 2 bucket_field_name key column.name.delimiter , columns key,value @@ -635,7 +603,7 @@ STAGE PLANS: columns.types string:string #### A masked pattern was here #### name default.bucket_big - numFiles 4 + numFiles 2 numRows 0 partition_columns ds partition_columns.types string @@ -643,7 +611,7 @@ STAGE PLANS: serialization.ddl struct bucket_big { string key, string value} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 5812 + totalSize 2750 #### A masked pattern was here #### serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe @@ -651,7 +619,7 @@ 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 @@ -676,7 +644,7 @@ STAGE PLANS: partition values: ds 2008-04-09 properties: - bucket_count 4 + bucket_count 2 bucket_field_name key column.name.delimiter , columns key,value @@ -684,7 +652,7 @@ STAGE PLANS: columns.types string:string #### A masked pattern was here #### name default.bucket_big - numFiles 4 + numFiles 2 numRows 0 partition_columns ds partition_columns.types string @@ -692,7 +660,7 @@ STAGE PLANS: serialization.ddl struct bucket_big { string key, string value} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 5812 + totalSize 2750 #### A masked pattern was here #### serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe @@ -700,7 +668,7 @@ 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 @@ -775,4 +743,4 @@ 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 #### -156 +76
