http://git-wip-us.apache.org/repos/asf/hive/blob/d8ee05ae/ql/src/test/results/clientpositive/spark/auto_sortmerge_join_6.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/spark/auto_sortmerge_join_6.q.out b/ql/src/test/results/clientpositive/spark/auto_sortmerge_join_6.q.out index 7616f6d..0609bc8 100644 --- a/ql/src/test/results/clientpositive/spark/auto_sortmerge_join_6.q.out +++ b/ql/src/test/results/clientpositive/spark/auto_sortmerge_join_6.q.out @@ -107,11 +107,11 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (key is not null and value is not null) (type: boolean) - 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 Select Operator expressions: key (type: int), 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 Sorted Merge Bucket Map Join Operator condition map: Inner Join 0 to 1 @@ -119,12 +119,12 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) outputColumnNames: _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: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (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 Map 4 Map Operator Tree: TableScan @@ -132,16 +132,16 @@ 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 @@ -150,7 +150,7 @@ STAGE PLANS: keys: 0 _col1 (type: string) 1 _col0 (type: string) - 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 Group By Operator aggregations: count() mode: hash @@ -223,11 +223,11 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (key is not null and value is not null) (type: boolean) - 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 Select Operator expressions: key (type: int), 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 Sorted Merge Bucket Map Join Operator condition map: Inner Join 0 to 1 @@ -235,12 +235,12 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) outputColumnNames: _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: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (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 Map 4 Map Operator Tree: TableScan @@ -248,16 +248,16 @@ 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 @@ -266,7 +266,7 @@ STAGE PLANS: keys: 0 _col1 (type: string) 1 _col0 (type: string) - 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 Group By Operator aggregations: count() mode: hash @@ -339,11 +339,11 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (key is not null and value is not null) (type: boolean) - 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 Select Operator expressions: key (type: int), 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 Sorted Merge Bucket Map Join Operator condition map: Inner Join 0 to 1 @@ -351,12 +351,12 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) outputColumnNames: _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: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (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 Map 4 Map Operator Tree: TableScan @@ -364,16 +364,16 @@ 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 @@ -382,7 +382,7 @@ STAGE PLANS: keys: 0 _col1 (type: string) 1 _col0 (type: string) - 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 Group By Operator aggregations: count() mode: hash @@ -451,11 +451,11 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (key is not null and UDFToDouble(key) is not null) (type: boolean) - 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 Select Operator expressions: key (type: int) outputColumnNames: _col0 - 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 Sorted Merge Bucket Map Join Operator condition map: Inner Join 0 to 1 @@ -463,29 +463,29 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) outputColumnNames: _col0 - Statistics: Num rows: 137 Data size: 1460 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: UDFToDouble(_col0) (type: double) sort order: + Map-reduce partition columns: UDFToDouble(_col0) (type: double) - Statistics: Num rows: 137 Data size: 1460 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE Map 4 Map Operator Tree: TableScan alias: c Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: UDFToDouble(key) is not null (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + predicate: (key is not null and UDFToDouble(key) is not null) (type: boolean) + 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: UDFToDouble(_col0) (type: double) sort order: + Map-reduce partition columns: UDFToDouble(_col0) (type: double) - 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 @@ -494,7 +494,7 @@ STAGE PLANS: keys: 0 UDFToDouble(_col0) (type: double) 1 UDFToDouble(_col0) (type: double) - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() mode: hash @@ -562,11 +562,11 @@ 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: int) 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 Sorted Merge Bucket Map Join Operator condition map: Inner Join 0 to 1 @@ -575,7 +575,7 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) 2 _col0 (type: int) - 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: count() mode: hash @@ -644,11 +644,11 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (key is not null and value is not null) (type: boolean) - 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 Select Operator expressions: key (type: int), 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 Sorted Merge Bucket Map Join Operator condition map: Inner Join 0 to 1 @@ -656,12 +656,12 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) outputColumnNames: _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: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (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 Map 4 Map Operator Tree: TableScan @@ -669,16 +669,16 @@ 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 @@ -687,7 +687,7 @@ STAGE PLANS: keys: 0 _col1 (type: string) 1 _col0 (type: string) - 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 Group By Operator aggregations: count() mode: hash @@ -756,11 +756,11 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (key is not null and value is not null) (type: boolean) - 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 Select Operator expressions: key (type: int), 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 Sorted Merge Bucket Map Join Operator condition map: Inner Join 0 to 1 @@ -768,12 +768,12 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) outputColumnNames: _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: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (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 Map 4 Map Operator Tree: TableScan @@ -781,16 +781,16 @@ 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 @@ -799,7 +799,7 @@ STAGE PLANS: keys: 0 _col1 (type: string) 1 _col0 (type: string) - 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 Group By Operator aggregations: count() mode: hash @@ -868,11 +868,11 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (key is not null and UDFToDouble(key) is not null) (type: boolean) - 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 Select Operator expressions: key (type: int) outputColumnNames: _col0 - 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 Sorted Merge Bucket Map Join Operator condition map: Inner Join 0 to 1 @@ -880,29 +880,29 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) outputColumnNames: _col0 - Statistics: Num rows: 137 Data size: 1460 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: UDFToDouble(_col0) (type: double) sort order: + Map-reduce partition columns: UDFToDouble(_col0) (type: double) - Statistics: Num rows: 137 Data size: 1460 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE Map 4 Map Operator Tree: TableScan alias: c Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: UDFToDouble(key) is not null (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + predicate: (key is not null and UDFToDouble(key) is not null) (type: boolean) + 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: UDFToDouble(_col0) (type: double) sort order: + Map-reduce partition columns: UDFToDouble(_col0) (type: double) - 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 @@ -911,7 +911,7 @@ STAGE PLANS: keys: 0 UDFToDouble(_col0) (type: double) 1 UDFToDouble(_col0) (type: double) - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() mode: hash @@ -979,11 +979,11 @@ 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: int) 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 Sorted Merge Bucket Map Join Operator condition map: Inner Join 0 to 1 @@ -992,7 +992,7 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) 2 _col0 (type: int) - 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: count() mode: hash @@ -1061,11 +1061,11 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (key is not null and value is not null) (type: boolean) - 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 Select Operator expressions: key (type: int), 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 Sorted Merge Bucket Map Join Operator condition map: Inner Join 0 to 1 @@ -1073,12 +1073,12 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) outputColumnNames: _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: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (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 Map 4 Map Operator Tree: TableScan @@ -1086,16 +1086,16 @@ 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 @@ -1104,7 +1104,7 @@ STAGE PLANS: keys: 0 _col1 (type: string) 1 _col0 (type: string) - 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 Group By Operator aggregations: count() mode: hash
http://git-wip-us.apache.org/repos/asf/hive/blob/d8ee05ae/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 5669d31..39d085d 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 @@ -174,11 +174,11 @@ STAGE PLANS: Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 27 Data size: 2750 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 54 Data size: 5500 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 27 Data size: 2750 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 54 Data size: 5500 Basic stats: COMPLETE Column stats: NONE Sorted Merge Bucket Map Join Operator condition map: Inner Join 0 to 1 @@ -186,7 +186,7 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) Position of Big Table: 1 - Statistics: Num rows: 29 Data size: 3025 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 59 Data size: 6050 Basic stats: COMPLETE Column stats: NONE BucketMapJoin: true Group By Operator aggregations: count() @@ -413,11 +413,11 @@ STAGE PLANS: Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 27 Data size: 2750 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 54 Data size: 5500 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 27 Data size: 2750 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 54 Data size: 5500 Basic stats: COMPLETE Column stats: NONE Sorted Merge Bucket Map Join Operator condition map: Inner Join 0 to 1 @@ -425,7 +425,7 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) Position of Big Table: 0 - Statistics: Num rows: 29 Data size: 3025 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 59 Data size: 6050 Basic stats: COMPLETE Column stats: NONE BucketMapJoin: true Group By Operator aggregations: count() @@ -651,11 +651,11 @@ STAGE PLANS: Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 2 Data size: 226 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 452 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 226 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 452 Basic stats: COMPLETE Column stats: NONE Spark HashTable Sink Operator keys: 0 _col0 (type: string) @@ -786,11 +786,11 @@ STAGE PLANS: Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 27 Data size: 2750 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 54 Data size: 5500 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 27 Data size: 2750 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 54 Data size: 5500 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 @@ -800,7 +800,7 @@ STAGE PLANS: input vertices: 1 Map 3 Position of Big Table: 0 - Statistics: Num rows: 29 Data size: 3025 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 59 Data size: 6050 Basic stats: COMPLETE Column stats: NONE BucketMapJoin: true Group By Operator aggregations: count() http://git-wip-us.apache.org/repos/asf/hive/blob/d8ee05ae/ql/src/test/results/clientpositive/spark/auto_sortmerge_join_8.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/spark/auto_sortmerge_join_8.q.out b/ql/src/test/results/clientpositive/spark/auto_sortmerge_join_8.q.out index d053e3f..15efeb7 100644 --- a/ql/src/test/results/clientpositive/spark/auto_sortmerge_join_8.q.out +++ b/ql/src/test/results/clientpositive/spark/auto_sortmerge_join_8.q.out @@ -174,11 +174,11 @@ 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 @@ -186,7 +186,7 @@ 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() @@ -413,11 +413,11 @@ 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 @@ -425,7 +425,7 @@ 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() @@ -653,11 +653,11 @@ STAGE PLANS: Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 114 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 228 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 114 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 228 Basic stats: COMPLETE Column stats: NONE Spark HashTable Sink Operator keys: 0 _col0 (type: string) @@ -788,11 +788,11 @@ 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 @@ -802,7 +802,7 @@ 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/d8ee05ae/ql/src/test/results/clientpositive/spark/auto_sortmerge_join_9.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/spark/auto_sortmerge_join_9.q.out b/ql/src/test/results/clientpositive/spark/auto_sortmerge_join_9.q.out index 686d7ca..be42791 100644 --- a/ql/src/test/results/clientpositive/spark/auto_sortmerge_join_9.q.out +++ b/ql/src/test/results/clientpositive/spark/auto_sortmerge_join_9.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 @@ -163,11 +163,11 @@ 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 @@ -175,18 +175,18 @@ 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: @@ -195,10 +195,10 @@ 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 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 @@ -275,11 +275,11 @@ 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 @@ -287,26 +287,26 @@ 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 @@ -419,11 +419,11 @@ 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 @@ -431,18 +431,18 @@ 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 4 Local Work: @@ -453,7 +453,7 @@ 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 Spark HashTable Sink Operator keys: 0 _col0 (type: int) @@ -472,11 +472,11 @@ 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 @@ -484,18 +484,18 @@ 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 Local Work: @@ -506,7 +506,7 @@ 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 Map Join Operator condition map: Inner Join 0 to 1 @@ -516,14 +516,14 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col3 input vertices: 1 Reducer 4 - 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 @@ -1068,17 +1068,20 @@ 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 - Spark HashTable Sink Operator - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) + 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 + Spark HashTable Sink Operator + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) Local Work: Map Reduce Local Work @@ -1093,31 +1096,34 @@ 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 - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - input vertices: - 1 Map 3 - Statistics: Num rows: 5 Data size: 38 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: + 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 + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + input vertices: + 1 Map 3 + Statistics: Num rows: 11 Data size: 77 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: bigint) + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: bigint) Local Work: Map Reduce Local Work Reducer 2 @@ -1603,11 +1609,11 @@ 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 Spark HashTable Sink Operator keys: 0 _col0 (type: int) @@ -1628,11 +1634,11 @@ 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 Map Join Operator condition map: Inner Join 0 to 1 @@ -1641,7 +1647,7 @@ STAGE PLANS: 1 _col0 (type: int) input vertices: 1 Map 3 - 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 @@ -1722,11 +1728,11 @@ 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 Spark HashTable Sink Operator keys: 0 _col0 (type: int) @@ -1747,11 +1753,11 @@ 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 Map Join Operator condition map: Inner Join 0 to 1 @@ -1761,18 +1767,18 @@ STAGE PLANS: outputColumnNames: _col0 input vertices: 1 Map 3 - 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) Local Work: Map Reduce Local Work @@ -1783,10 +1789,10 @@ 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 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 @@ -1861,11 +1867,11 @@ 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 Spark HashTable Sink Operator keys: 0 _col0 (type: int) @@ -1887,11 +1893,11 @@ 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 Map Join Operator condition map: Inner Join 0 to 1 @@ -1901,17 +1907,17 @@ STAGE PLANS: outputColumnNames: _col0 input vertices: 1 Map 4 - 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 Local Work: Map Reduce Local Work Reducer 2 @@ -1920,9 +1926,9 @@ STAGE PLANS: 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 @@ -2035,11 +2041,11 @@ 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 Spark HashTable Sink Operator keys: 0 _col0 (type: int) @@ -2060,11 +2066,11 @@ 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 Map Join Operator condition map: Inner Join 0 to 1 @@ -2074,18 +2080,18 @@ STAGE PLANS: outputColumnNames: _col0 input vertices: 1 Map 6 - 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) Local Work: Map Reduce Local Work @@ -2098,7 +2104,7 @@ 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 Spark HashTable Sink Operator keys: 0 _col0 (type: int) @@ -2115,11 +2121,11 @@ 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 Spark HashTable Sink Operator keys: 0 _col0 (type: int) @@ -2140,11 +2146,11 @@ 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 Map Join Operator condition map: Inner Join 0 to 1 @@ -2154,18 +2160,18 @@ STAGE PLANS: outputColumnNames: _col0 input vertices: 1 Map 3 - 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) Local Work: Map Reduce Local Work @@ -2178,7 +2184,7 @@ 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 Map Join Operator condition map: Inner Join 0 to 1 @@ -2188,14 +2194,14 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col3 input vertices: 1 Reducer 5 - 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 http://git-wip-us.apache.org/repos/asf/hive/blob/d8ee05ae/ql/src/test/results/clientpositive/spark/bucket_map_join_spark1.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/spark/bucket_map_join_spark1.q.out b/ql/src/test/results/clientpositive/spark/bucket_map_join_spark1.q.out index fb8f8d6..e162f4a 100644 --- a/ql/src/test/results/clientpositive/spark/bucket_map_join_spark1.q.out +++ b/ql/src/test/results/clientpositive/spark/bucket_map_join_spark1.q.out @@ -188,11 +188,11 @@ STAGE PLANS: Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 28 Data size: 2958 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 5812 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 28 Data size: 2958 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 5812 Basic stats: COMPLETE Column stats: NONE Spark HashTable Sink Operator keys: 0 _col0 (type: int) @@ -271,11 +271,11 @@ STAGE PLANS: Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 28 Data size: 2958 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 5812 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 28 Data size: 2958 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 5812 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 @@ -286,18 +286,18 @@ STAGE PLANS: input vertices: 1 Map 2 Position of Big Table: 0 - Statistics: Num rows: 30 Data size: 3253 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 60 Data size: 6393 Basic stats: COMPLETE Column stats: NONE BucketMapJoin: true Select Operator expressions: _col0 (type: int), _col1 (type: string), _col3 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 30 Data size: 3253 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 60 Data size: 6393 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 1 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 30 Data size: 3253 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 60 Data size: 6393 Basic stats: COMPLETE Column stats: NONE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.TextInputFormat @@ -533,11 +533,11 @@ STAGE PLANS: Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 28 Data size: 2958 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 5812 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 28 Data size: 2958 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 5812 Basic stats: COMPLETE Column stats: NONE Spark HashTable Sink Operator keys: 0 _col0 (type: int) @@ -611,11 +611,11 @@ STAGE PLANS: Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 28 Data size: 2958 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 5812 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 28 Data size: 2958 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 55 Data size: 5812 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 @@ -626,17 +626,17 @@ STAGE PLANS: input vertices: 1 Map 2 Position of Big Table: 0 - Statistics: Num rows: 30 Data size: 3253 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 60 Data size: 6393 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: int), _col1 (type: string), _col3 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 30 Data size: 3253 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 60 Data size: 6393 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 1 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 30 Data size: 3253 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 60 Data size: 6393 Basic stats: COMPLETE Column stats: NONE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.TextInputFormat
