http://git-wip-us.apache.org/repos/asf/hive/blob/08f73adc/ql/src/test/results/clientpositive/spark/auto_join30.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/spark/auto_join30.q.out b/ql/src/test/results/clientpositive/spark/auto_join30.q.out index 4b67445..5cb05ab 100644 --- a/ql/src/test/results/clientpositive/spark/auto_join30.q.out +++ b/ql/src/test/results/clientpositive/spark/auto_join30.q.out @@ -33,15 +33,15 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col1 (type: string) sort order: + - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: string) Reducer 5 Local Work: @@ -50,7 +50,7 @@ STAGE PLANS: Select Operator expressions: VALUE._col0 (type: string), KEY.reducesinkkey0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Spark HashTable Sink Operator keys: 0 _col0 (type: string) @@ -70,15 +70,15 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reducer 2 Local Work: Map Reduce Local Work @@ -86,7 +86,7 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 @@ -96,7 +96,7 @@ STAGE PLANS: outputColumnNames: _col2, _col3 input vertices: 1 Reducer 5 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: sum(hash(_col2,_col3)) mode: hash @@ -472,15 +472,15 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col1 (type: string) sort order: + - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: string) Reducer 5 Local Work: @@ -489,7 +489,7 @@ STAGE PLANS: Select Operator expressions: VALUE._col0 (type: string), KEY.reducesinkkey0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Spark HashTable Sink Operator keys: 0 _col0 (type: string) @@ -502,7 +502,7 @@ STAGE PLANS: Select Operator expressions: VALUE._col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Spark HashTable Sink Operator keys: 0 _col0 (type: string) @@ -523,15 +523,15 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reducer 2 Local Work: Map Reduce Local Work @@ -539,7 +539,7 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 @@ -552,7 +552,7 @@ STAGE PLANS: input vertices: 1 Reducer 5 2 Reducer 7 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: sum(hash(_col2,_col3)) mode: hash
http://git-wip-us.apache.org/repos/asf/hive/blob/08f73adc/ql/src/test/results/clientpositive/spark/auto_join8.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/spark/auto_join8.q.out b/ql/src/test/results/clientpositive/spark/auto_join8.q.out index 21374ff..7c4ed3a 100644 --- a/ql/src/test/results/clientpositive/spark/auto_join8.q.out +++ b/ql/src/test/results/clientpositive/spark/auto_join8.q.out @@ -76,12 +76,12 @@ STAGE PLANS: alias: src1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((UDFToDouble(key) > 10.0) and (UDFToDouble(key) < 20.0)) and key is not null) (type: boolean) - Statistics: Num rows: 28 Data size: 297 Basic stats: COMPLETE Column stats: NONE + predicate: ((UDFToDouble(key) > 10.0) and (UDFToDouble(key) < 20.0)) (type: boolean) + Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 28 Data size: 297 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Left Outer Join0 to 1 @@ -91,17 +91,17 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col2, _col3 input vertices: 1 Map 2 - Statistics: Num rows: 30 Data size: 326 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 60 Data size: 642 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: _col2 is null (type: boolean) - Statistics: Num rows: 15 Data size: 163 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 30 Data size: 321 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: UDFToInteger(_col0) (type: int), _col1 (type: string), null (type: int), _col3 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 15 Data size: 163 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 30 Data size: 321 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 15 Data size: 163 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 30 Data size: 321 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat http://git-wip-us.apache.org/repos/asf/hive/blob/08f73adc/ql/src/test/results/clientpositive/spark/auto_join9.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/spark/auto_join9.q.out b/ql/src/test/results/clientpositive/spark/auto_join9.q.out index 568891b..b2ed51c 100644 --- a/ql/src/test/results/clientpositive/spark/auto_join9.q.out +++ b/ql/src/test/results/clientpositive/spark/auto_join9.q.out @@ -32,11 +32,11 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Spark HashTable Sink Operator keys: 0 _col0 (type: string) @@ -55,11 +55,11 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 @@ -69,14 +69,14 @@ STAGE PLANS: outputColumnNames: _col0, _col4 input vertices: 1 Map 2 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: UDFToInteger(_col0) (type: int), _col4 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat http://git-wip-us.apache.org/repos/asf/hive/blob/08f73adc/ql/src/test/results/clientpositive/spark/auto_join_reordering_values.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/spark/auto_join_reordering_values.q.out b/ql/src/test/results/clientpositive/spark/auto_join_reordering_values.q.out index 6466c39..250c1ef 100644 --- a/ql/src/test/results/clientpositive/spark/auto_join_reordering_values.q.out +++ b/ql/src/test/results/clientpositive/spark/auto_join_reordering_values.q.out @@ -471,16 +471,16 @@ STAGE PLANS: Filter Operator isSamplingPred: false predicate: userid is not null (type: boolean) - Statistics: Num rows: 50 Data size: 144 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 288 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: userid (type: int) outputColumnNames: _col0 - Statistics: Num rows: 50 Data size: 144 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 288 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 50 Data size: 144 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 100 Data size: 288 Basic stats: COMPLETE Column stats: NONE tag: 1 auto parallelism: false Path -> Alias: @@ -599,11 +599,11 @@ STAGE PLANS: 0 _col3 (type: int) 1 _col0 (type: int) outputColumnNames: _col4, _col5 - Statistics: Num rows: 55 Data size: 158 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 110 Data size: 316 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col4 (type: string), _col5 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 55 Data size: 158 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 110 Data size: 316 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 5 Statistics: Num rows: 5 Data size: 10 Basic stats: COMPLETE Column stats: NONE http://git-wip-us.apache.org/repos/asf/hive/blob/08f73adc/ql/src/test/results/clientpositive/spark/auto_join_stats.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/spark/auto_join_stats.q.out b/ql/src/test/results/clientpositive/spark/auto_join_stats.q.out index 71fe68e..e826380 100644 --- a/ql/src/test/results/clientpositive/spark/auto_join_stats.q.out +++ b/ql/src/test/results/clientpositive/spark/auto_join_stats.q.out @@ -48,12 +48,12 @@ STAGE PLANS: alias: smalltable Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: UDFToDouble(key) is not null (type: boolean) - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + predicate: (key is not null and UDFToDouble(key) is not null) (type: boolean) + Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Spark HashTable Sink Operator keys: 0 (UDFToDouble(_col0) + UDFToDouble(_col1)) (type: double) @@ -74,16 +74,16 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Map 3 Map Operator Tree: TableScan @@ -91,16 +91,16 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reducer 2 Local Work: Map Reduce Local Work @@ -112,10 +112,10 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (UDFToDouble(_col0) + UDFToDouble(_col1)) is not null (type: boolean) - Statistics: Num rows: 138 Data size: 1465 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 @@ -125,10 +125,10 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col2 input vertices: 1 Map 4 - Statistics: Num rows: 151 Data size: 1611 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 151 Data size: 1611 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -196,12 +196,12 @@ STAGE PLANS: alias: smalltable Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: UDFToDouble(key) is not null (type: boolean) - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + predicate: (key is not null and UDFToDouble(key) is not null) (type: boolean) + Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Spark HashTable Sink Operator keys: 0 (UDFToDouble(_col0) + UDFToDouble(_col1)) (type: double) @@ -214,7 +214,7 @@ STAGE PLANS: alias: smalltable2 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: UDFToDouble(key) is not null (type: boolean) + predicate: (key is not null and UDFToDouble(key) is not null) (type: boolean) Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) @@ -240,16 +240,16 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Map 3 Map Operator Tree: TableScan @@ -257,16 +257,16 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reducer 2 Local Work: Map Reduce Local Work @@ -278,10 +278,10 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (UDFToDouble(_col0) + UDFToDouble(_col1)) is not null (type: boolean) - Statistics: Num rows: 138 Data size: 1465 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 @@ -291,10 +291,10 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col2 input vertices: 1 Map 4 - Statistics: Num rows: 151 Data size: 1611 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (UDFToDouble(_col0) + UDFToDouble(_col1)) is not null (type: boolean) - Statistics: Num rows: 76 Data size: 810 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 @@ -304,10 +304,10 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col2 input vertices: 1 Map 5 - Statistics: Num rows: 83 Data size: 891 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 665 Data size: 7069 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 83 Data size: 891 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 665 Data size: 7069 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat http://git-wip-us.apache.org/repos/asf/hive/blob/08f73adc/ql/src/test/results/clientpositive/spark/auto_join_stats2.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/spark/auto_join_stats2.q.out b/ql/src/test/results/clientpositive/spark/auto_join_stats2.q.out index 7a6bf9b..4062faf 100644 --- a/ql/src/test/results/clientpositive/spark/auto_join_stats2.q.out +++ b/ql/src/test/results/clientpositive/spark/auto_join_stats2.q.out @@ -41,11 +41,11 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Spark HashTable Sink Operator keys: 0 _col0 (type: string) @@ -58,7 +58,7 @@ STAGE PLANS: alias: smalltable Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: UDFToDouble(key) is not null (type: boolean) + predicate: (key is not null and UDFToDouble(key) is not null) (type: boolean) Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) @@ -82,11 +82,11 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 @@ -96,10 +96,10 @@ STAGE PLANS: outputColumnNames: _col0, _col1 input vertices: 1 Map 2 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (UDFToDouble(_col0) + UDFToDouble(_col1)) is not null (type: boolean) - Statistics: Num rows: 138 Data size: 1465 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 @@ -109,10 +109,10 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col2 input vertices: 1 Map 3 - Statistics: Num rows: 151 Data size: 1611 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 151 Data size: 1611 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -183,11 +183,11 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Spark HashTable Sink Operator keys: 0 _col0 (type: string) @@ -200,12 +200,12 @@ STAGE PLANS: alias: smalltable Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: UDFToDouble(key) is not null (type: boolean) - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + predicate: (key is not null and UDFToDouble(key) is not null) (type: boolean) + Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE Spark HashTable Sink Operator keys: 0 (UDFToDouble(_col0) + UDFToDouble(_col1)) (type: double) @@ -218,7 +218,7 @@ STAGE PLANS: alias: smalltable2 Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: UDFToDouble(key) is not null (type: boolean) + predicate: (key is not null and UDFToDouble(key) is not null) (type: boolean) Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) @@ -242,11 +242,11 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 @@ -256,10 +256,10 @@ STAGE PLANS: outputColumnNames: _col0, _col1 input vertices: 1 Map 2 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (UDFToDouble(_col0) + UDFToDouble(_col1)) is not null (type: boolean) - Statistics: Num rows: 138 Data size: 1465 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 @@ -269,10 +269,10 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col2 input vertices: 1 Map 3 - Statistics: Num rows: 151 Data size: 1611 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (UDFToDouble(_col0) + UDFToDouble(_col1)) is not null (type: boolean) - Statistics: Num rows: 76 Data size: 810 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 @@ -282,10 +282,10 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col2 input vertices: 1 Map 4 - Statistics: Num rows: 83 Data size: 891 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 665 Data size: 7069 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 83 Data size: 891 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 665 Data size: 7069 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat http://git-wip-us.apache.org/repos/asf/hive/blob/08f73adc/ql/src/test/results/clientpositive/spark/auto_join_without_localtask.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/spark/auto_join_without_localtask.q.out b/ql/src/test/results/clientpositive/spark/auto_join_without_localtask.q.out index 932fdcc..659c305 100644 --- a/ql/src/test/results/clientpositive/spark/auto_join_without_localtask.q.out +++ b/ql/src/test/results/clientpositive/spark/auto_join_without_localtask.q.out @@ -23,16 +23,16 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) Map 4 Map Operator Tree: @@ -41,16 +41,16 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reducer 2 Reduce Operator Tree: Join Operator @@ -60,18 +60,18 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE TopN Hash Memory Usage: 0.1 Reducer 3 Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 40 Statistics: Num rows: 40 Data size: 400 Basic stats: COMPLETE Column stats: NONE @@ -163,17 +163,17 @@ STAGE PLANS: alias: a Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (value is not null and key is not null) (type: boolean) - Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE + predicate: (key is not null and value is not null) (type: boolean) + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: string) Map 5 Map Operator Tree: @@ -182,16 +182,16 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: value is not null (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: value (type: string) outputColumnNames: _col0 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Map 6 Map Operator Tree: TableScan @@ -199,16 +199,16 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reducer 2 Reduce Operator Tree: Join Operator @@ -218,12 +218,12 @@ STAGE PLANS: 0 _col1 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) Reducer 3 Reduce Operator Tree: @@ -234,18 +234,18 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ - Statistics: Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE TopN Hash Memory Usage: 0.1 Reducer 4 Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 40 Statistics: Num rows: 40 Data size: 400 Basic stats: COMPLETE Column stats: NONE @@ -337,17 +337,17 @@ STAGE PLANS: alias: a Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((UDFToDouble(key) > 100.0) and value is not null) (type: boolean) - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + predicate: (((UDFToDouble(key) > 100.0) and value is not null) and key is not null) (type: boolean) + Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) Map 5 Map Operator Tree: @@ -373,16 +373,16 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: value is not null (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: value (type: string) outputColumnNames: _col0 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reducer 2 Reduce Operator Tree: Join Operator @@ -408,18 +408,18 @@ STAGE PLANS: 0 _col1 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE TopN Hash Memory Usage: 0.1 Reducer 4 Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 40 Statistics: Num rows: 40 Data size: 400 Basic stats: COMPLETE Column stats: NONE http://git-wip-us.apache.org/repos/asf/hive/blob/08f73adc/ql/src/test/results/clientpositive/spark/auto_smb_mapjoin_14.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/spark/auto_smb_mapjoin_14.q.out b/ql/src/test/results/clientpositive/spark/auto_smb_mapjoin_14.q.out index 1660d70..0c96d4c 100644 --- a/ql/src/test/results/clientpositive/spark/auto_smb_mapjoin_14.q.out +++ b/ql/src/test/results/clientpositive/spark/auto_smb_mapjoin_14.q.out @@ -72,18 +72,18 @@ STAGE PLANS: Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 5 Data size: 35 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 5 Data size: 35 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE Sorted Merge Bucket Map Join Operator condition map: Inner Join 0 to 1 keys: 0 _col0 (type: int) 1 _col0 (type: int) - Statistics: Num rows: 5 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 77 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() mode: hash @@ -170,11 +170,11 @@ STAGE PLANS: Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 5 Data size: 35 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 5 Data size: 35 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE Sorted Merge Bucket Map Join Operator condition map: Inner Join 0 to 1 @@ -182,26 +182,26 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) outputColumnNames: _col0 - Statistics: Num rows: 5 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 77 Basic stats: COMPLETE Column stats: NONE Group By Operator keys: _col0 (type: int) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 5 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 77 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 5 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 77 Basic stats: COMPLETE Column stats: NONE Reducer 2 Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: int) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 15 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 35 Basic stats: COMPLETE Column stats: NONE Select Operator - Statistics: Num rows: 2 Data size: 15 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 35 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() mode: hash @@ -315,11 +315,11 @@ STAGE PLANS: Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 5 Data size: 35 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 5 Data size: 35 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE Sorted Merge Bucket Map Join Operator condition map: Inner Join 0 to 1 @@ -327,18 +327,18 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) outputColumnNames: _col0 - Statistics: Num rows: 5 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 77 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() keys: _col0 (type: int) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 5 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 77 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 5 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 77 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) Reducer 2 Reduce Operator Tree: @@ -347,12 +347,12 @@ STAGE PLANS: keys: KEY._col0 (type: int) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 2 Data size: 15 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 35 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 2 Data size: 15 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 35 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) Reducer 3 Reduce Operator Tree: @@ -363,14 +363,14 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) outputColumnNames: _col0, _col1, _col3 - Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 38 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: int), _col1 (type: bigint), _col3 (type: bigint) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 38 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 38 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -382,12 +382,12 @@ STAGE PLANS: keys: KEY._col0 (type: int) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 2 Data size: 15 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 35 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 2 Data size: 15 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 35 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) Stage: Stage-0 @@ -931,35 +931,41 @@ STAGE PLANS: TableScan alias: a Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: (key + 1) (type: int) - outputColumnNames: _col0 + Filter Operator + predicate: (key + 1) is not null (type: boolean) Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: _col0 is not null (type: boolean) - Statistics: Num rows: 5 Data size: 35 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 5 Data size: 35 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: (key + 1) (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: _col0 is not null (type: boolean) + Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE Map 4 Map Operator Tree: TableScan alias: a Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: (key + 1) (type: int) - outputColumnNames: _col0 + Filter Operator + predicate: (key + 1) is not null (type: boolean) Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: _col0 is not null (type: boolean) - Statistics: Num rows: 5 Data size: 35 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 5 Data size: 35 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: (key + 1) (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: _col0 is not null (type: boolean) + Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE Reducer 2 Reduce Operator Tree: Join Operator @@ -968,7 +974,7 @@ STAGE PLANS: keys: 0 _col0 (type: int) 1 _col0 (type: int) - Statistics: Num rows: 5 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 77 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() mode: hash @@ -1392,7 +1398,7 @@ STAGE PLANS: Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 5 Data size: 35 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE Sorted Merge Bucket Map Join Operator condition map: Inner Join 0 to 1 @@ -1400,18 +1406,18 @@ STAGE PLANS: 0 key (type: int) 1 key (type: int) outputColumnNames: _col0, _col1, _col6 - Statistics: Num rows: 5 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 77 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: int), _col1 (type: string), _col6 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 5 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 77 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: int), _col1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 5 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 77 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 5 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 77 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -1419,7 +1425,7 @@ STAGE PLANS: name: default.dest1 File Output Operator compressed: false - Statistics: Num rows: 5 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 77 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -1592,7 +1598,7 @@ STAGE PLANS: Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 5 Data size: 35 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE Sorted Merge Bucket Map Join Operator condition map: Inner Join 0 to 1 @@ -1600,10 +1606,10 @@ STAGE PLANS: 0 key (type: int) 1 key (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 5 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 77 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 5 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 77 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -1612,18 +1618,18 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int) outputColumnNames: _col0 - Statistics: Num rows: 5 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 77 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() keys: _col0 (type: int) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 5 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 77 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 5 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 77 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) Reducer 2 Reduce Operator Tree: @@ -1632,14 +1638,14 @@ STAGE PLANS: keys: KEY._col0 (type: int) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 2 Data size: 15 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 35 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: int), UDFToInteger(_col1) (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 2 Data size: 15 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 35 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 2 Data size: 15 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 35 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat http://git-wip-us.apache.org/repos/asf/hive/blob/08f73adc/ql/src/test/results/clientpositive/spark/auto_sortmerge_join_1.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/spark/auto_sortmerge_join_1.q.out b/ql/src/test/results/clientpositive/spark/auto_sortmerge_join_1.q.out index 7afdc37..fb9ba66 100644 --- a/ql/src/test/results/clientpositive/spark/auto_sortmerge_join_1.q.out +++ b/ql/src/test/results/clientpositive/spark/auto_sortmerge_join_1.q.out @@ -161,11 +161,11 @@ STAGE PLANS: Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 58 Data size: 5812 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 116 Data size: 11624 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 58 Data size: 5812 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 116 Data size: 11624 Basic stats: COMPLETE Column stats: NONE Sorted Merge Bucket Map Join Operator condition map: Inner Join 0 to 1 @@ -173,7 +173,7 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) Position of Big Table: 1 - Statistics: Num rows: 63 Data size: 6393 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 127 Data size: 12786 Basic stats: COMPLETE Column stats: NONE BucketMapJoin: true Group By Operator aggregations: count() @@ -398,11 +398,11 @@ STAGE PLANS: Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 58 Data size: 5812 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 116 Data size: 11624 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 58 Data size: 5812 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 116 Data size: 11624 Basic stats: COMPLETE Column stats: NONE Sorted Merge Bucket Map Join Operator condition map: Inner Join 0 to 1 @@ -410,7 +410,7 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) Position of Big Table: 0 - Statistics: Num rows: 63 Data size: 6393 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 127 Data size: 12786 Basic stats: COMPLETE Column stats: NONE BucketMapJoin: true Group By Operator aggregations: count() @@ -720,11 +720,11 @@ STAGE PLANS: Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 58 Data size: 5812 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 116 Data size: 11624 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 58 Data size: 5812 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 116 Data size: 11624 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 @@ -734,7 +734,7 @@ STAGE PLANS: input vertices: 1 Map 3 Position of Big Table: 0 - Statistics: Num rows: 63 Data size: 6393 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 127 Data size: 12786 Basic stats: COMPLETE Column stats: NONE BucketMapJoin: true Group By Operator aggregations: count() http://git-wip-us.apache.org/repos/asf/hive/blob/08f73adc/ql/src/test/results/clientpositive/spark/auto_sortmerge_join_12.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/spark/auto_sortmerge_join_12.q.out b/ql/src/test/results/clientpositive/spark/auto_sortmerge_join_12.q.out index fdf332d..89251b7 100644 --- a/ql/src/test/results/clientpositive/spark/auto_sortmerge_join_12.q.out +++ b/ql/src/test/results/clientpositive/spark/auto_sortmerge_join_12.q.out @@ -138,7 +138,7 @@ POSTHOOK: query: load data local inpath '../../data/files/smallsrcsortbucket3out POSTHOOK: type: LOAD #### A masked pattern was here #### POSTHOOK: Output: default@bucket_medium@ds=2008-04-08 -Warning: Map Join MAPJOIN[29][bigTable=?] in task 'Stage-1:MAPRED' is a cross product +Warning: Map Join MAPJOIN[32][bigTable=?] in task 'Stage-1:MAPRED' is a cross product PREHOOK: query: explain extended select count(*) FROM bucket_small a JOIN bucket_medium b ON a.key = b.key JOIN bucket_big c ON c.key = b.key JOIN bucket_medium d ON c.key = b.key PREHOOK: type: QUERY POSTHOOK: query: explain extended select count(*) FROM bucket_small a JOIN bucket_medium b ON a.key = b.key JOIN bucket_big c ON c.key = b.key JOIN bucket_medium d ON c.key = b.key @@ -447,11 +447,11 @@ STAGE PLANS: Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 58 Data size: 5812 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 116 Data size: 11624 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 58 Data size: 5812 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 116 Data size: 11624 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 @@ -464,7 +464,7 @@ STAGE PLANS: 0 Map 1 1 Map 2 Position of Big Table: 2 - Statistics: Num rows: 127 Data size: 12786 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 255 Data size: 25572 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 @@ -474,7 +474,7 @@ STAGE PLANS: input vertices: 1 Map 5 Position of Big Table: 0 - Statistics: Num rows: 139 Data size: 14064 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 280 Data size: 28129 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() mode: hash @@ -627,7 +627,7 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Map Join MAPJOIN[29][bigTable=?] in task 'Stage-1:MAPRED' is a cross product +Warning: Map Join MAPJOIN[32][bigTable=?] in task 'Stage-1:MAPRED' is a cross product PREHOOK: query: select count(*) FROM bucket_small a JOIN bucket_medium b ON a.key = b.key JOIN bucket_big c ON c.key = b.key JOIN bucket_medium d ON c.key = b.key PREHOOK: type: QUERY PREHOOK: Input: default@bucket_big
