http://git-wip-us.apache.org/repos/asf/hive/blob/08f73adc/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/08f73adc/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 http://git-wip-us.apache.org/repos/asf/hive/blob/08f73adc/ql/src/test/results/clientpositive/spark/bucket_map_join_spark2.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/spark/bucket_map_join_spark2.q.out b/ql/src/test/results/clientpositive/spark/bucket_map_join_spark2.q.out index 4dd1157..58903d7 100644 --- a/ql/src/test/results/clientpositive/spark/bucket_map_join_spark2.q.out +++ b/ql/src/test/results/clientpositive/spark/bucket_map_join_spark2.q.out @@ -172,11 +172,11 @@ STAGE PLANS: Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 15 Data size: 1583 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 29 Data size: 3062 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 15 Data size: 1583 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 29 Data size: 3062 Basic stats: COMPLETE Column stats: NONE Spark HashTable Sink Operator keys: 0 _col0 (type: int) @@ -255,11 +255,11 @@ 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 @@ -270,18 +270,18 @@ 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 @@ -517,11 +517,11 @@ STAGE PLANS: Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 15 Data size: 1583 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 29 Data size: 3062 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 15 Data size: 1583 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 29 Data size: 3062 Basic stats: COMPLETE Column stats: NONE Spark HashTable Sink Operator keys: 0 _col0 (type: int) @@ -600,11 +600,11 @@ 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 @@ -615,18 +615,18 @@ 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 http://git-wip-us.apache.org/repos/asf/hive/blob/08f73adc/ql/src/test/results/clientpositive/spark/bucket_map_join_spark3.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/spark/bucket_map_join_spark3.q.out b/ql/src/test/results/clientpositive/spark/bucket_map_join_spark3.q.out index 4133fda..60ce126 100644 --- a/ql/src/test/results/clientpositive/spark/bucket_map_join_spark3.q.out +++ b/ql/src/test/results/clientpositive/spark/bucket_map_join_spark3.q.out @@ -172,11 +172,11 @@ STAGE PLANS: Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 15 Data size: 1583 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 29 Data size: 3062 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 15 Data size: 1583 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 29 Data size: 3062 Basic stats: COMPLETE Column stats: NONE Spark HashTable Sink Operator keys: 0 _col0 (type: int) @@ -255,11 +255,11 @@ 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 @@ -270,18 +270,18 @@ STAGE PLANS: input vertices: 0 Map 1 Position of Big Table: 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 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 @@ -517,11 +517,11 @@ STAGE PLANS: Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 15 Data size: 1583 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 29 Data size: 3062 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 15 Data size: 1583 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 29 Data size: 3062 Basic stats: COMPLETE Column stats: NONE Spark HashTable Sink Operator keys: 0 _col0 (type: int) @@ -595,11 +595,11 @@ 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 @@ -610,17 +610,17 @@ STAGE PLANS: input vertices: 0 Map 1 Position of Big Table: 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 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 http://git-wip-us.apache.org/repos/asf/hive/blob/08f73adc/ql/src/test/results/clientpositive/spark/bucket_map_join_spark4.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/spark/bucket_map_join_spark4.q.out b/ql/src/test/results/clientpositive/spark/bucket_map_join_spark4.q.out index 64fb785..338384f 100644 --- a/ql/src/test/results/clientpositive/spark/bucket_map_join_spark4.q.out +++ b/ql/src/test/results/clientpositive/spark/bucket_map_join_spark4.q.out @@ -147,25 +147,25 @@ STAGE PLANS: Spark #### A masked pattern was here #### Vertices: - Map 1 + Map 2 Map Operator Tree: TableScan - alias: a + alias: b Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false - predicate: (key is not null and value is not null) (type: boolean) - Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE + predicate: key is not null (type: boolean) + Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE + 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) - Position of Big Table: 1 + Position of Big Table: 0 Local Work: Map Reduce Local Work Bucket Mapjoin Context: @@ -178,7 +178,7 @@ STAGE PLANS: Path -> Partition: #### A masked pattern was here #### Partition - base file name: tbl1 + base file name: tbl2 input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat properties: @@ -190,11 +190,11 @@ STAGE PLANS: columns.comments columns.types int:string #### A masked pattern was here #### - name default.tbl1 + name default.tbl2 numFiles 2 numRows 10 rawDataSize 70 - serialization.ddl struct tbl1 { i32 key, string value} + serialization.ddl struct tbl2 { i32 key, string value} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe totalSize 80 @@ -212,20 +212,20 @@ STAGE PLANS: columns.comments columns.types int:string #### A masked pattern was here #### - name default.tbl1 + name default.tbl2 numFiles 2 numRows 10 rawDataSize 70 - serialization.ddl struct tbl1 { i32 key, string value} + serialization.ddl struct tbl2 { i32 key, string value} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe totalSize 80 #### A masked pattern was here #### serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.tbl1 - name: default.tbl1 + name: default.tbl2 + name: default.tbl2 Truncated Path -> Alias: - /tbl1 [a] + /tbl2 [b] Map 3 Map Operator Tree: TableScan @@ -235,11 +235,11 @@ STAGE PLANS: Filter Operator isSamplingPred: false predicate: value 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: value (type: string) outputColumnNames: _col1 - 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 _col1 (type: string) @@ -305,20 +305,20 @@ STAGE PLANS: Spark #### A masked pattern was here #### Vertices: - Map 2 + Map 1 Map Operator Tree: TableScan - alias: b + alias: a Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false - predicate: key is not null (type: boolean) - Statistics: Num rows: 5 Data size: 35 Basic stats: COMPLETE Column stats: NONE + predicate: (key is not null and value is not null) (type: boolean) + Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 5 Data size: 35 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 @@ -327,9 +327,9 @@ STAGE PLANS: 1 _col0 (type: int) outputColumnNames: _col0, _col1, _col3 input vertices: - 0 Map 1 - Position of Big Table: 1 - Statistics: Num rows: 5 Data size: 38 Basic stats: COMPLETE Column stats: NONE + 1 Map 2 + Position of Big Table: 0 + Statistics: Num rows: 11 Data size: 77 Basic stats: COMPLETE Column stats: NONE BucketMapJoin: true Map Join Operator condition map: @@ -341,17 +341,17 @@ STAGE PLANS: input vertices: 1 Map 3 Position of Big Table: 0 - Statistics: Num rows: 5 Data size: 41 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12 Data size: 84 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: int), _col1 (type: string), _col3 (type: string), _col5 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 5 Data size: 41 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12 Data size: 84 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 5 Data size: 41 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12 Data size: 84 Basic stats: COMPLETE Column stats: NONE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.TextInputFormat @@ -380,7 +380,7 @@ STAGE PLANS: Path -> Partition: #### A masked pattern was here #### Partition - base file name: tbl2 + base file name: tbl1 input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat properties: @@ -392,11 +392,11 @@ STAGE PLANS: columns.comments columns.types int:string #### A masked pattern was here #### - name default.tbl2 + name default.tbl1 numFiles 2 numRows 10 rawDataSize 70 - serialization.ddl struct tbl2 { i32 key, string value} + serialization.ddl struct tbl1 { i32 key, string value} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe totalSize 80 @@ -414,20 +414,20 @@ STAGE PLANS: columns.comments columns.types int:string #### A masked pattern was here #### - name default.tbl2 + name default.tbl1 numFiles 2 numRows 10 rawDataSize 70 - serialization.ddl struct tbl2 { i32 key, string value} + serialization.ddl struct tbl1 { i32 key, string value} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe totalSize 80 #### A masked pattern was here #### serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.tbl2 - name: default.tbl2 + name: default.tbl1 + name: default.tbl1 Truncated Path -> Alias: - /tbl2 [b] + /tbl1 [a] Stage: Stage-0 Fetch Operator @@ -592,25 +592,25 @@ STAGE PLANS: Spark #### A masked pattern was here #### Vertices: - Map 1 + Map 2 Map Operator Tree: TableScan - alias: a + alias: b Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false - predicate: (key is not null and value is not null) (type: boolean) - Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE + predicate: key is not null (type: boolean) + Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE + 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) - Position of Big Table: 1 + Position of Big Table: 0 Local Work: Map Reduce Local Work Path -> Alias: @@ -618,7 +618,7 @@ STAGE PLANS: Path -> Partition: #### A masked pattern was here #### Partition - base file name: tbl1 + base file name: tbl2 input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat properties: @@ -630,11 +630,11 @@ STAGE PLANS: columns.comments columns.types int:string #### A masked pattern was here #### - name default.tbl1 + name default.tbl2 numFiles 2 numRows 10 rawDataSize 70 - serialization.ddl struct tbl1 { i32 key, string value} + serialization.ddl struct tbl2 { i32 key, string value} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe totalSize 80 @@ -652,20 +652,20 @@ STAGE PLANS: columns.comments columns.types int:string #### A masked pattern was here #### - name default.tbl1 + name default.tbl2 numFiles 2 numRows 10 rawDataSize 70 - serialization.ddl struct tbl1 { i32 key, string value} + serialization.ddl struct tbl2 { i32 key, string value} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe totalSize 80 #### A masked pattern was here #### serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.tbl1 - name: default.tbl1 + name: default.tbl2 + name: default.tbl2 Truncated Path -> Alias: - /tbl1 [a] + /tbl2 [b] Map 3 Map Operator Tree: TableScan @@ -675,11 +675,11 @@ STAGE PLANS: Filter Operator isSamplingPred: false predicate: value 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: value (type: string) outputColumnNames: _col1 - 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 _col1 (type: string) @@ -745,20 +745,20 @@ STAGE PLANS: Spark #### A masked pattern was here #### Vertices: - Map 2 + Map 1 Map Operator Tree: TableScan - alias: b + alias: a Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false - predicate: key is not null (type: boolean) - Statistics: Num rows: 5 Data size: 35 Basic stats: COMPLETE Column stats: NONE + predicate: (key is not null and value is not null) (type: boolean) + Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 5 Data size: 35 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 @@ -767,9 +767,9 @@ STAGE PLANS: 1 _col0 (type: int) outputColumnNames: _col0, _col1, _col3 input vertices: - 0 Map 1 - Position of Big Table: 1 - Statistics: Num rows: 5 Data size: 38 Basic stats: COMPLETE Column stats: NONE + 1 Map 2 + Position of Big Table: 0 + Statistics: Num rows: 11 Data size: 77 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 @@ -780,17 +780,17 @@ STAGE PLANS: input vertices: 1 Map 3 Position of Big Table: 0 - Statistics: Num rows: 5 Data size: 41 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12 Data size: 84 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: int), _col1 (type: string), _col3 (type: string), _col5 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 5 Data size: 41 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12 Data size: 84 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 5 Data size: 41 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12 Data size: 84 Basic stats: COMPLETE Column stats: NONE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.TextInputFormat @@ -814,7 +814,7 @@ STAGE PLANS: Path -> Partition: #### A masked pattern was here #### Partition - base file name: tbl2 + base file name: tbl1 input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat properties: @@ -826,11 +826,11 @@ STAGE PLANS: columns.comments columns.types int:string #### A masked pattern was here #### - name default.tbl2 + name default.tbl1 numFiles 2 numRows 10 rawDataSize 70 - serialization.ddl struct tbl2 { i32 key, string value} + serialization.ddl struct tbl1 { i32 key, string value} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe totalSize 80 @@ -848,20 +848,20 @@ STAGE PLANS: columns.comments columns.types int:string #### A masked pattern was here #### - name default.tbl2 + name default.tbl1 numFiles 2 numRows 10 rawDataSize 70 - serialization.ddl struct tbl2 { i32 key, string value} + serialization.ddl struct tbl1 { i32 key, string value} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe totalSize 80 #### A masked pattern was here #### serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.tbl2 - name: default.tbl2 + name: default.tbl1 + name: default.tbl1 Truncated Path -> Alias: - /tbl2 [b] + /tbl1 [a] Stage: Stage-0 Fetch Operator
