Modified: hive/branches/spark/ql/src/test/results/clientpositive/spark/join11.q.out URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/join11.q.out?rev=1642997&r1=1642996&r2=1642997&view=diff ============================================================================== --- hive/branches/spark/ql/src/test/results/clientpositive/spark/join11.q.out (original) +++ hive/branches/spark/ql/src/test/results/clientpositive/spark/join11.q.out Tue Dec 2 19:57:10 2014 @@ -19,16 +19,17 @@ JOIN ON src1.c1 = src2.c3 AND src1.c1 < 100 POSTHOOK: type: QUERY STAGE DEPENDENCIES: - Stage-2 is a root stage - Stage-1 depends on stages: Stage-2 + Stage-1 is a root stage Stage-0 depends on stages: Stage-1 STAGE PLANS: - Stage: Stage-2 + Stage: Stage-1 Spark + Edges: + Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 1), Map 3 (PARTITION-LEVEL SORT, 1) #### A masked pattern was here #### Vertices: - Map 2 + Map 1 Map Operator Tree: TableScan alias: src @@ -37,24 +38,15 @@ STAGE PLANS: predicate: (key < 100) (type: boolean) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + expressions: key (type: string) + outputColumnNames: _col0 Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - Spark HashTable Sink Operator - condition expressions: - 0 {_col0} - 1 {_col1} - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - Local Work: - Map Reduce Local Work - - Stage: Stage-1 - Spark -#### A masked pattern was here #### - Vertices: - Map 1 + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Map 3 Map Operator Tree: TableScan alias: src @@ -63,35 +55,36 @@ STAGE PLANS: predicate: (key < 100) (type: boolean) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string) - outputColumnNames: _col0 + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - condition expressions: - 0 {_col0} - 1 {_col1} - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col3 - input vertices: - 1 Map 2 - Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string), _col3 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Local Work: - Map Reduce Local Work + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: string) + Reducer 2 + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + condition expressions: + 0 {KEY.reducesinkkey0} + 1 {VALUE._col0} + outputColumnNames: _col0, _col3 + Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: string), _col3 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator
Modified: hive/branches/spark/ql/src/test/results/clientpositive/spark/join12.q.out URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/join12.q.out?rev=1642997&r1=1642996&r2=1642997&view=diff ============================================================================== --- hive/branches/spark/ql/src/test/results/clientpositive/spark/join12.q.out (original) +++ hive/branches/spark/ql/src/test/results/clientpositive/spark/join12.q.out Tue Dec 2 19:57:10 2014 @@ -25,108 +25,91 @@ JOIN ON src1.c1 = src3.c5 AND src3.c5 < 80 POSTHOOK: type: QUERY STAGE DEPENDENCIES: - Stage-2 is a root stage - Stage-1 depends on stages: Stage-2 + Stage-1 is a root stage Stage-0 depends on stages: Stage-1 STAGE PLANS: - Stage: Stage-2 + Stage: Stage-1 Spark + Edges: + Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 1), Map 3 (PARTITION-LEVEL SORT, 1), Map 4 (PARTITION-LEVEL SORT, 1) #### A masked pattern was here #### Vertices: - Map 2 + Map 1 Map Operator Tree: TableScan alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((key < 100) and (key < 80)) and key is not null) (type: boolean) - Statistics: Num rows: 28 Data size: 297 Basic stats: COMPLETE Column stats: NONE + predicate: ((key < 80) and (key < 100)) (type: boolean) + Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 28 Data size: 297 Basic stats: COMPLETE Column stats: NONE - Spark HashTable Sink Operator - condition expressions: - 0 {_col0} - 1 {_col1} - 2 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - 2 _col0 (type: string) - Local Work: - Map Reduce Local Work + expressions: key (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 55 Data size: 584 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: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE Map 3 Map Operator Tree: TableScan alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((key < 100) and (key < 80)) (type: boolean) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + predicate: (((key < 100) and (key < 80)) and key is not null) (type: boolean) + Statistics: Num rows: 28 Data size: 297 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE - Spark HashTable Sink Operator - condition expressions: - 0 {_col0} - 1 {_col1} - 2 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - 2 _col0 (type: string) - Local Work: - Map Reduce Local Work - - Stage: Stage-1 - Spark -#### A masked pattern was here #### - Vertices: - Map 1 + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 28 Data size: 297 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: 28 Data size: 297 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: string) + Map 4 Map Operator Tree: TableScan alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((key < 80) and (key < 100)) (type: boolean) + predicate: ((key < 100) and (key < 80)) (type: boolean) Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: _col0 Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - Inner Join 0 to 2 - condition expressions: - 0 {_col0} - 1 {_col1} - 2 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - 2 _col0 (type: string) - outputColumnNames: _col0, _col3 - input vertices: - 1 Map 2 - 2 Map 3 - Statistics: Num rows: 121 Data size: 1284 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string), _col3 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 121 Data size: 1284 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 121 Data size: 1284 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Local Work: - Map Reduce Local Work + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Reducer 2 + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + Inner Join 0 to 2 + condition expressions: + 0 {KEY.reducesinkkey0} + 1 {VALUE._col0} + 2 + outputColumnNames: _col0, _col3 + Statistics: Num rows: 121 Data size: 1284 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: string), _col3 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 121 Data size: 1284 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 121 Data size: 1284 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator Modified: hive/branches/spark/ql/src/test/results/clientpositive/spark/join13.q.out URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/join13.q.out?rev=1642997&r1=1642996&r2=1642997&view=diff ============================================================================== --- hive/branches/spark/ql/src/test/results/clientpositive/spark/join13.q.out (original) +++ hive/branches/spark/ql/src/test/results/clientpositive/spark/join13.q.out Tue Dec 2 19:57:10 2014 @@ -25,16 +25,18 @@ JOIN ON src1.c1 + src2.c3 = src3.c5 AND src3.c5 < 200 POSTHOOK: type: QUERY STAGE DEPENDENCIES: - Stage-2 is a root stage - Stage-1 depends on stages: Stage-2 + Stage-1 is a root stage Stage-0 depends on stages: Stage-1 STAGE PLANS: - Stage: Stage-2 + Stage: Stage-1 Spark + Edges: + Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 1), Map 4 (PARTITION-LEVEL SORT, 1) + Reducer 3 <- Map 5 (PARTITION-LEVEL SORT, 1), Reducer 2 (PARTITION-LEVEL SORT, 1) #### A masked pattern was here #### Vertices: - Map 2 + Map 1 Map Operator Tree: TableScan alias: src @@ -43,98 +45,89 @@ STAGE PLANS: predicate: (key < 100) (type: boolean) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + expressions: key (type: string) + outputColumnNames: _col0 Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - Spark HashTable Sink Operator - condition expressions: - 0 {_col0} - 1 {_col1} - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - Local Work: - Map Reduce Local Work - Map 3 + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Map 4 Map Operator Tree: TableScan alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((key < 200) and UDFToDouble(key) is not null) (type: boolean) - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + predicate: (key < 100) (type: boolean) + Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE - Spark HashTable Sink Operator - condition expressions: - 0 {_col0} {_col3} - 1 - keys: - 0 (_col0 + _col2) (type: double) - 1 UDFToDouble(_col0) (type: double) - Local Work: - Map Reduce Local Work - - Stage: Stage-1 - Spark -#### A masked pattern was here #### - Vertices: - Map 1 + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: string) + Map 5 Map Operator Tree: TableScan alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (key < 100) (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + predicate: ((key < 200) and UDFToDouble(key) is not null) (type: boolean) + Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - condition expressions: - 0 {_col0} - 1 {_col0} {_col1} - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col2, _col3 - input vertices: - 1 Map 2 - Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (_col0 + _col2) is not null (type: boolean) - Statistics: Num rows: 91 Data size: 969 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - condition expressions: - 0 {_col0} {_col3} - 1 - keys: - 0 (_col0 + _col2) (type: double) - 1 UDFToDouble(_col0) (type: double) - outputColumnNames: _col0, _col3 - input vertices: - 1 Map 3 - Statistics: Num rows: 100 Data size: 1065 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string), _col3 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 100 Data size: 1065 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 100 Data size: 1065 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Local Work: - Map Reduce Local Work + Statistics: Num rows: 83 Data size: 881 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: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Reducer 2 + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + condition expressions: + 0 {KEY.reducesinkkey0} + 1 {KEY.reducesinkkey0} {VALUE._col0} + outputColumnNames: _col0, _col2, _col3 + Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (_col0 + _col2) is not null (type: boolean) + Statistics: Num rows: 91 Data size: 969 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: (_col0 + _col2) (type: double) + sort order: + + Map-reduce partition columns: (_col0 + _col2) (type: double) + Statistics: Num rows: 91 Data size: 969 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: string), _col3 (type: string) + Reducer 3 + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + condition expressions: + 0 {VALUE._col0} {VALUE._col3} + 1 + outputColumnNames: _col0, _col3 + Statistics: Num rows: 100 Data size: 1065 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: string), _col3 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 100 Data size: 1065 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 100 Data size: 1065 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator Modified: hive/branches/spark/ql/src/test/results/clientpositive/spark/join14.q.out URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/join14.q.out?rev=1642997&r1=1642996&r2=1642997&view=diff ============================================================================== --- hive/branches/spark/ql/src/test/results/clientpositive/spark/join14.q.out (original) +++ hive/branches/spark/ql/src/test/results/clientpositive/spark/join14.q.out Tue Dec 2 19:57:10 2014 @@ -21,14 +21,15 @@ FROM src JOIN srcpart ON src.key = srcpa INSERT OVERWRITE TABLE dest1 SELECT src.key, srcpart.value POSTHOOK: type: QUERY STAGE DEPENDENCIES: - Stage-3 is a root stage - Stage-1 depends on stages: Stage-3 + Stage-1 is a root stage Stage-0 depends on stages: Stage-1 Stage-2 depends on stages: Stage-0 STAGE PLANS: - Stage: Stage-3 + Stage: Stage-1 Spark + Edges: + Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 1), Map 3 (PARTITION-LEVEL SORT, 1) #### A masked pattern was here #### Vertices: Map 1 @@ -39,21 +40,12 @@ STAGE PLANS: Filter Operator predicate: (key > 100) (type: boolean) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - Spark HashTable Sink Operator - condition expressions: - 0 - 1 {value} - keys: - 0 key (type: string) - 1 key (type: string) - Local Work: - Map Reduce Local Work - - Stage: Stage-1 - Spark -#### A masked pattern was here #### - Vertices: - Map 2 + Reduce Output Operator + key expressions: key (type: string) + sort order: + + Map-reduce partition columns: key (type: string) + Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Map 3 Map Operator Tree: TableScan alias: srcpart @@ -61,33 +53,34 @@ STAGE PLANS: Filter Operator predicate: ((key > 100) and key is not null) (type: boolean) Statistics: Num rows: 167 Data size: 1774 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - condition expressions: - 0 {key} - 1 {value} - keys: - 0 key (type: string) - 1 key (type: string) - outputColumnNames: _col0, _col6 - input vertices: - 0 Map 1 - Statistics: Num rows: 183 Data size: 1951 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: UDFToInteger(_col0) (type: int), _col6 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 183 Data size: 1951 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 183 Data size: 1951 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.dest1 - Local Work: - Map Reduce Local Work + Reduce Output Operator + key expressions: key (type: string) + sort order: + + Map-reduce partition columns: key (type: string) + Statistics: Num rows: 167 Data size: 1774 Basic stats: COMPLETE Column stats: NONE + value expressions: value (type: string) + Reducer 2 + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + condition expressions: + 0 {KEY.reducesinkkey0} + 1 {VALUE._col0} + outputColumnNames: _col0, _col6 + Statistics: Num rows: 183 Data size: 1951 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: UDFToInteger(_col0) (type: int), _col6 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 183 Data size: 1951 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 183 Data size: 1951 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.dest1 Stage: Stage-0 Move Operator Modified: hive/branches/spark/ql/src/test/results/clientpositive/spark/join15.q.out URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/join15.q.out?rev=1642997&r1=1642996&r2=1642997&view=diff ============================================================================== --- hive/branches/spark/ql/src/test/results/clientpositive/spark/join15.q.out (original) +++ hive/branches/spark/ql/src/test/results/clientpositive/spark/join15.q.out Tue Dec 2 19:57:10 2014 @@ -5,72 +5,65 @@ POSTHOOK: query: EXPLAIN SELECT * FROM src src1 JOIN src src2 ON (src1.key = src2.key) SORT BY src1.key, src1.value, src2.key, src2.value POSTHOOK: type: QUERY STAGE DEPENDENCIES: - Stage-2 is a root stage - Stage-1 depends on stages: Stage-2 + Stage-1 is a root stage Stage-0 depends on stages: Stage-1 STAGE PLANS: - Stage: Stage-2 + Stage: Stage-1 Spark + Edges: + Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 1), Map 4 (PARTITION-LEVEL SORT, 1) + Reducer 3 <- Reducer 2 (SORT, 1) #### A masked pattern was here #### Vertices: - Map 3 + Map 1 Map Operator Tree: TableScan - alias: src2 + alias: src1 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 - Spark HashTable Sink Operator - condition expressions: - 0 {key} {value} - 1 {value} - keys: - 0 key (type: string) - 1 key (type: string) - Local Work: - Map Reduce Local Work - - Stage: Stage-1 - Spark - Edges: - Reducer 2 <- Map 1 (SORT, 1) -#### A masked pattern was here #### - Vertices: - Map 1 + Reduce Output Operator + key expressions: key (type: string) + sort order: + + Map-reduce partition columns: key (type: string) + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + value expressions: value (type: string) + Map 4 Map Operator Tree: TableScan - alias: src1 + alias: src2 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 - Map Join Operator - condition map: - Inner Join 0 to 1 - condition expressions: - 0 {key} {value} - 1 {key} {value} - keys: - 0 key (type: string) - 1 key (type: string) - outputColumnNames: _col0, _col1, _col5, _col6 - input vertices: - 1 Map 3 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) - sort order: ++++ - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - Local Work: - Map Reduce Local Work + Reduce Output Operator + key expressions: key (type: string) + sort order: + + Map-reduce partition columns: key (type: string) + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + value expressions: value (type: string) Reducer 2 Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + condition expressions: + 0 {KEY.reducesinkkey0} {VALUE._col0} + 1 {KEY.reducesinkkey0} {VALUE._col0} + outputColumnNames: _col0, _col1, _col5, _col6 + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) + sort order: ++++ + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Reducer 3 + Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey3 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 Modified: hive/branches/spark/ql/src/test/results/clientpositive/spark/join16.q.out URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/join16.q.out?rev=1642997&r1=1642996&r2=1642997&view=diff ============================================================================== --- hive/branches/spark/ql/src/test/results/clientpositive/spark/join16.q.out (original) +++ hive/branches/spark/ql/src/test/results/clientpositive/spark/join16.q.out Tue Dec 2 19:57:10 2014 @@ -3,13 +3,14 @@ PREHOOK: type: QUERY POSTHOOK: query: EXPLAIN SELECT subq.key, tab.value FROM (select a.key, a.value from src a where a.key > 10 ) subq JOIN src tab ON (subq.key = tab.key and subq.key > 20 and subq.value = tab.value) where tab.value < 200 POSTHOOK: type: QUERY STAGE DEPENDENCIES: - Stage-2 is a root stage - Stage-1 depends on stages: Stage-2 + Stage-1 is a root stage Stage-0 depends on stages: Stage-1 STAGE PLANS: - Stage: Stage-2 + Stage: Stage-1 Spark + Edges: + Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 1), Map 3 (PARTITION-LEVEL SORT, 1) #### A masked pattern was here #### Vertices: Map 1 @@ -24,21 +25,12 @@ STAGE PLANS: expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 9 Data size: 95 Basic stats: COMPLETE Column stats: NONE - Spark HashTable Sink Operator - condition expressions: - 0 - 1 {value} - keys: - 0 _col0 (type: string), _col1 (type: string) - 1 key (type: string), value (type: string) - Local Work: - Map Reduce Local Work - - Stage: Stage-1 - Spark -#### A masked pattern was here #### - Vertices: - Map 2 + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string) + sort order: ++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string) + Statistics: Num rows: 9 Data size: 95 Basic stats: COMPLETE Column stats: NONE + Map 3 Map Operator Tree: TableScan alias: tab @@ -46,32 +38,32 @@ STAGE PLANS: Filter Operator predicate: ((((key > 20) and value is not null) and key is not null) and (value < 200)) (type: boolean) Statistics: Num rows: 14 Data size: 148 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - condition expressions: - 0 {_col0} - 1 {value} - keys: - 0 _col0 (type: string), _col1 (type: string) - 1 key (type: string), value (type: string) - outputColumnNames: _col0, _col3 - input vertices: - 0 Map 1 - Statistics: Num rows: 15 Data size: 162 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string), _col3 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 15 Data size: 162 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 15 Data size: 162 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Local Work: - Map Reduce Local Work + Reduce Output Operator + key expressions: key (type: string), value (type: string) + sort order: ++ + Map-reduce partition columns: key (type: string), value (type: string) + Statistics: Num rows: 14 Data size: 148 Basic stats: COMPLETE Column stats: NONE + Reducer 2 + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + condition expressions: + 0 {KEY.reducesinkkey0} + 1 {KEY.reducesinkkey1} + outputColumnNames: _col0, _col3 + Statistics: Num rows: 15 Data size: 162 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: string), _col3 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 15 Data size: 162 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 15 Data size: 162 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator Modified: hive/branches/spark/ql/src/test/results/clientpositive/spark/join17.q.out URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/join17.q.out?rev=1642997&r1=1642996&r2=1642997&view=diff ============================================================================== Files hive/branches/spark/ql/src/test/results/clientpositive/spark/join17.q.out (original) and hive/branches/spark/ql/src/test/results/clientpositive/spark/join17.q.out Tue Dec 2 19:57:10 2014 differ Modified: hive/branches/spark/ql/src/test/results/clientpositive/spark/join19.q.out URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/join19.q.out?rev=1642997&r1=1642996&r2=1642997&view=diff ============================================================================== --- hive/branches/spark/ql/src/test/results/clientpositive/spark/join19.q.out (original) +++ hive/branches/spark/ql/src/test/results/clientpositive/spark/join19.q.out Tue Dec 2 19:57:10 2014 @@ -123,16 +123,36 @@ t6.predicate='http://sofa.semanticweb.or ON (t66.subject=t55.object) POSTHOOK: type: QUERY STAGE DEPENDENCIES: - Stage-2 is a root stage - Stage-1 depends on stages: Stage-2 + Stage-1 is a root stage Stage-0 depends on stages: Stage-1 STAGE PLANS: - Stage: Stage-2 + Stage: Stage-1 Spark + Edges: + Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 1), Map 5 (PARTITION-LEVEL SORT, 1), Map 6 (PARTITION-LEVEL SORT, 1) + Reducer 3 <- Map 7 (PARTITION-LEVEL SORT, 1), Map 8 (PARTITION-LEVEL SORT, 1), Reducer 2 (PARTITION-LEVEL SORT, 1) + Reducer 4 <- Map 9 (PARTITION-LEVEL SORT, 1), Reducer 3 (PARTITION-LEVEL SORT, 1) #### A masked pattern was here #### Vertices: - Map 2 + Map 1 + Map Operator Tree: + TableScan + alias: t1 + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Filter Operator + predicate: (((predicate = 'http://sofa.semanticweb.org/sofa/v1.0/system#__INSTANCEOF_REL') and (object = 'http://ontos/OntosMiner/Common.English/ontology#Citation')) and subject is not null) (type: boolean) + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Select Operator + expressions: subject (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Map 5 Map Operator Tree: TableScan alias: t2 @@ -144,18 +164,13 @@ STAGE PLANS: expressions: subject (type: string), object (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - Spark HashTable Sink Operator - condition expressions: - 0 {_col0} - 1 {_col1} - 2 {_col0} - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - 2 _col1 (type: string) - Local Work: - Map Reduce Local Work - Map 3 + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + value expressions: _col1 (type: string) + Map 6 Map Operator Tree: TableScan alias: t3 @@ -167,18 +182,13 @@ STAGE PLANS: expressions: subject (type: string), object (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - Spark HashTable Sink Operator - condition expressions: - 0 {_col0} - 1 {_col1} - 2 {_col0} - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - 2 _col1 (type: string) - Local Work: - Map Reduce Local Work - Map 4 + Reduce Output Operator + key expressions: _col1 (type: string) + sort order: + + Map-reduce partition columns: _col1 (type: string) + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + value expressions: _col0 (type: string) + Map 7 Map Operator Tree: TableScan alias: t4 @@ -190,18 +200,12 @@ STAGE PLANS: expressions: subject (type: string) outputColumnNames: _col0 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - Spark HashTable Sink Operator - condition expressions: - 0 {_col0} {_col2} {_col3} - 1 - 2 {_col1} - keys: - 0 _col3 (type: string) - 1 _col0 (type: string) - 2 _col0 (type: string) - Local Work: - Map Reduce Local Work - Map 5 + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Map 8 Map Operator Tree: TableScan alias: t5 @@ -213,18 +217,13 @@ STAGE PLANS: expressions: subject (type: string), object (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - Spark HashTable Sink Operator - condition expressions: - 0 {_col0} {_col2} {_col3} - 1 - 2 {_col1} - keys: - 0 _col3 (type: string) - 1 _col0 (type: string) - 2 _col0 (type: string) - Local Work: - Map Reduce Local Work - Map 6 + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + value expressions: _col1 (type: string) + Map 9 Map Operator Tree: TableScan alias: t6 @@ -236,92 +235,69 @@ STAGE PLANS: expressions: subject (type: string), object (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - Spark HashTable Sink Operator - condition expressions: - 0 {_col0} {_col2} {_col3} {_col7} - 1 {_col1} - keys: - 0 _col7 (type: string) - 1 _col0 (type: string) - Local Work: - Map Reduce Local Work - - Stage: Stage-1 - Spark -#### A masked pattern was here #### - Vertices: - Map 1 - Map Operator Tree: - TableScan - alias: t1 - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - Filter Operator - predicate: (((predicate = 'http://sofa.semanticweb.org/sofa/v1.0/system#__INSTANCEOF_REL') and (object = 'http://ontos/OntosMiner/Common.English/ontology#Citation')) and subject is not null) (type: boolean) - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - Select Operator - expressions: subject (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - Inner Join 0 to 2 - condition expressions: - 0 {_col0} - 1 {_col1} - 2 {_col0} - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - 2 _col1 (type: string) - outputColumnNames: _col0, _col2, _col3 - input vertices: - 1 Map 2 - 2 Map 3 - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - Inner Join 1 to 2 - condition expressions: - 0 {_col0} {_col2} {_col3} - 1 - 2 {_col1} - keys: - 0 _col3 (type: string) - 1 _col0 (type: string) - 2 _col0 (type: string) - outputColumnNames: _col0, _col2, _col3, _col7 - input vertices: - 1 Map 4 - 2 Map 5 - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - condition expressions: - 0 {_col0} {_col2} {_col3} {_col7} - 1 {_col1} - keys: - 0 _col7 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col2, _col3, _col7, _col9 - input vertices: - 1 Map 6 - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - Select Operator - expressions: _col0 (type: string), _col2 (type: string), _col3 (type: string), _col7 (type: string), _col9 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Local Work: - Map Reduce Local Work + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + value expressions: _col1 (type: string) + Reducer 2 + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + Inner Join 0 to 2 + condition expressions: + 0 {KEY.reducesinkkey0} + 1 {VALUE._col0} + 2 {VALUE._col0} + outputColumnNames: _col0, _col2, _col3 + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Reduce Output Operator + key expressions: _col3 (type: string) + sort order: + + Map-reduce partition columns: _col3 (type: string) + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + value expressions: _col0 (type: string), _col2 (type: string) + Reducer 3 + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + Inner Join 1 to 2 + condition expressions: + 0 {VALUE._col0} {VALUE._col2} {KEY.reducesinkkey0} + 1 + 2 {VALUE._col0} + outputColumnNames: _col0, _col2, _col3, _col7 + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Reduce Output Operator + key expressions: _col7 (type: string) + sort order: + + Map-reduce partition columns: _col7 (type: string) + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + value expressions: _col0 (type: string), _col2 (type: string), _col3 (type: string) + Reducer 4 + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + condition expressions: + 0 {VALUE._col0} {VALUE._col2} {VALUE._col3} {KEY.reducesinkkey0} + 1 {VALUE._col0} + outputColumnNames: _col0, _col2, _col3, _col7, _col9 + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + Select Operator + expressions: _col0 (type: string), _col2 (type: string), _col3 (type: string), _col7 (type: string), _col9 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4 + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator Modified: hive/branches/spark/ql/src/test/results/clientpositive/spark/join2.q.out URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/join2.q.out?rev=1642997&r1=1642996&r2=1642997&view=diff ============================================================================== --- hive/branches/spark/ql/src/test/results/clientpositive/spark/join2.q.out (original) +++ hive/branches/spark/ql/src/test/results/clientpositive/spark/join2.q.out Tue Dec 2 19:57:10 2014 @@ -19,78 +19,45 @@ FROM src src1 JOIN src src2 ON (src1.key INSERT OVERWRITE TABLE dest_j2 SELECT src1.key, src3.value POSTHOOK: type: QUERY STAGE DEPENDENCIES: - Stage-4 is a root stage - Stage-3 depends on stages: Stage-4 - Stage-1 depends on stages: Stage-3 + Stage-1 is a root stage Stage-0 depends on stages: Stage-1 Stage-2 depends on stages: Stage-0 STAGE PLANS: - Stage: Stage-4 + Stage: Stage-1 Spark + Edges: + Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 1), Map 4 (PARTITION-LEVEL SORT, 1) + Reducer 3 <- Map 5 (PARTITION-LEVEL SORT, 1), Reducer 2 (PARTITION-LEVEL SORT, 1) #### A masked pattern was here #### Vertices: - Map 2 + Map 1 Map Operator Tree: TableScan - alias: src2 + alias: src1 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 - Spark HashTable Sink Operator - condition expressions: - 0 {key} - 1 - keys: - 0 key (type: string) - 1 key (type: string) - Local Work: - Map Reduce Local Work - - Stage: Stage-3 - Spark -#### A masked pattern was here #### - Vertices: - Map 1 + Reduce Output Operator + key expressions: key (type: string) + sort order: + + Map-reduce partition columns: key (type: string) + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Map 4 Map Operator Tree: TableScan - alias: src1 + alias: src2 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 - Map Join Operator - condition map: - Inner Join 0 to 1 - condition expressions: - 0 {key} - 1 {key} - keys: - 0 key (type: string) - 1 key (type: string) - outputColumnNames: _col0, _col5 - input vertices: - 1 Map 2 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (_col0 + _col5) is not null (type: boolean) - Statistics: Num rows: 138 Data size: 1465 Basic stats: COMPLETE Column stats: NONE - Spark HashTable Sink Operator - condition expressions: - 0 {_col0} - 1 {value} - keys: - 0 (_col0 + _col5) (type: double) - 1 UDFToDouble(key) (type: double) - Local Work: - Map Reduce Local Work - - Stage: Stage-1 - Spark -#### A masked pattern was here #### - Vertices: - Map 3 + Reduce Output Operator + key expressions: key (type: string) + sort order: + + Map-reduce partition columns: key (type: string) + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Map 5 Map Operator Tree: TableScan alias: src3 @@ -98,33 +65,53 @@ STAGE PLANS: Filter Operator predicate: UDFToDouble(key) is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - condition expressions: - 0 {_col0} - 1 {value} - keys: - 0 (_col0 + _col5) (type: double) - 1 UDFToDouble(key) (type: double) - outputColumnNames: _col0, _col11 - input vertices: - 0 Map 1 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: UDFToInteger(_col0) (type: int), _col11 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.dest_j2 - Local Work: - Map Reduce Local Work + Reduce Output Operator + key expressions: UDFToDouble(key) (type: double) + sort order: + + Map-reduce partition columns: UDFToDouble(key) (type: double) + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + value expressions: value (type: string) + Reducer 2 + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + condition expressions: + 0 {KEY.reducesinkkey0} + 1 {KEY.reducesinkkey0} + outputColumnNames: _col0, _col5 + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (_col0 + _col5) is not null (type: boolean) + Statistics: Num rows: 138 Data size: 1465 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: (_col0 + _col5) (type: double) + sort order: + + Map-reduce partition columns: (_col0 + _col5) (type: double) + Statistics: Num rows: 138 Data size: 1465 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: string) + Reducer 3 + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + condition expressions: + 0 {VALUE._col0} + 1 {VALUE._col1} + outputColumnNames: _col0, _col11 + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: UDFToInteger(_col0) (type: int), _col11 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.dest_j2 Stage: Stage-0 Move Operator Modified: hive/branches/spark/ql/src/test/results/clientpositive/spark/join20.q.out URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/join20.q.out?rev=1642997&r1=1642996&r2=1642997&view=diff ============================================================================== --- hive/branches/spark/ql/src/test/results/clientpositive/spark/join20.q.out (original) +++ hive/branches/spark/ql/src/test/results/clientpositive/spark/join20.q.out Tue Dec 2 19:57:10 2014 @@ -7,13 +7,15 @@ SELECT * FROM src src1 JOIN src src2 ON SORT BY src1.key, src1.value, src2.key, src2.value, src3.key, src3.value POSTHOOK: type: QUERY STAGE DEPENDENCIES: - Stage-2 is a root stage - Stage-1 depends on stages: Stage-2 + Stage-1 is a root stage Stage-0 depends on stages: Stage-1 STAGE PLANS: - Stage: Stage-2 + Stage: Stage-1 Spark + Edges: + Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 1), Map 4 (PARTITION-LEVEL SORT, 1), Map 5 (PARTITION-LEVEL SORT, 1) + Reducer 3 <- Reducer 2 (SORT, 1) #### A masked pattern was here #### Vertices: Map 1 @@ -24,22 +26,13 @@ STAGE PLANS: Filter Operator predicate: (key < 10) (type: boolean) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - Spark HashTable Sink Operator - condition expressions: - 0 {value} - 1 {key} {value} - 2 {key} {value} - filter predicates: - 0 - 1 - 2 {(key < 20)} - keys: - 0 key (type: string) - 1 key (type: string) - 2 key (type: string) - Local Work: - Map Reduce Local Work - Map 2 + Reduce Output Operator + key expressions: key (type: string) + sort order: + + Map-reduce partition columns: key (type: string) + Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + value expressions: value (type: string) + Map 4 Map Operator Tree: TableScan alias: src2 @@ -47,65 +40,48 @@ STAGE PLANS: Filter Operator predicate: (key < 10) (type: boolean) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - Spark HashTable Sink Operator - condition expressions: - 0 {key} {value} - 1 {value} - 2 {key} {value} - filter predicates: - 0 - 1 - 2 {(key < 20)} - keys: - 0 key (type: string) - 1 key (type: string) - 2 key (type: string) - Local Work: - Map Reduce Local Work - - Stage: Stage-1 - Spark - Edges: - Reducer 4 <- Map 3 (SORT, 1) -#### A masked pattern was here #### - Vertices: - Map 3 + Reduce Output Operator + key expressions: key (type: string) + sort order: + + Map-reduce partition columns: key (type: string) + Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + value expressions: value (type: string) + Map 5 Map Operator Tree: TableScan alias: src3 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - Right Outer Join0 to 2 - condition expressions: - 0 {key} {value} - 1 {key} {value} - 2 {key} {value} - filter predicates: - 0 - 1 - 2 {(key < 20)} - keys: - 0 key (type: string) - 1 key (type: string) - 2 key (type: string) - outputColumnNames: _col0, _col1, _col5, _col6, _col10, _col11 - input vertices: - 0 Map 1 - 1 Map 2 + Reduce Output Operator + key expressions: key (type: string) + sort order: + + Map-reduce partition columns: key (type: string) + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + value expressions: value (type: string) + Reducer 2 + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + Right Outer Join0 to 2 + condition expressions: + 0 {KEY.reducesinkkey0} {VALUE._col0} + 1 {KEY.reducesinkkey0} {VALUE._col0} + 2 {KEY.reducesinkkey0} {VALUE._col0} + filter predicates: + 0 + 1 + 2 {(KEY.reducesinkkey0 < 20)} + outputColumnNames: _col0, _col1, _col5, _col6, _col10, _col11 + Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string), _col10 (type: string), _col11 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string) + sort order: ++++++ Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string), _col10 (type: string), _col11 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string) - sort order: ++++++ - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE - Local Work: - Map Reduce Local Work - Reducer 4 + Reducer 3 Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey3 (type: string), KEY.reducesinkkey4 (type: string), KEY.reducesinkkey5 (type: string) @@ -692,13 +668,15 @@ SELECT * FROM src src1 JOIN src src2 ON SORT BY src1.key, src1.value, src2.key, src2.value, src3.key, src3.value POSTHOOK: type: QUERY STAGE DEPENDENCIES: - Stage-2 is a root stage - Stage-1 depends on stages: Stage-2 + Stage-1 is a root stage Stage-0 depends on stages: Stage-1 STAGE PLANS: - Stage: Stage-2 + Stage: Stage-1 Spark + Edges: + Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 3), Map 4 (PARTITION-LEVEL SORT, 3), Map 5 (PARTITION-LEVEL SORT, 3) + Reducer 3 <- Reducer 2 (SORT, 3) #### A masked pattern was here #### Vertices: Map 1 @@ -709,22 +687,13 @@ STAGE PLANS: Filter Operator predicate: ((key < 15) and (key < 10)) (type: boolean) Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE - Spark HashTable Sink Operator - condition expressions: - 0 {value} - 1 {key} {value} - 2 {key} {value} - filter predicates: - 0 - 1 - 2 {(key < 20)} - keys: - 0 key (type: string) - 1 key (type: string) - 2 key (type: string) - Local Work: - Map Reduce Local Work - Map 2 + Reduce Output Operator + key expressions: key (type: string) + sort order: + + Map-reduce partition columns: key (type: string) + Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + value expressions: value (type: string) + Map 4 Map Operator Tree: TableScan alias: src2 @@ -732,65 +701,48 @@ STAGE PLANS: Filter Operator predicate: ((key < 10) and (key < 15)) (type: boolean) Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE - Spark HashTable Sink Operator - condition expressions: - 0 {key} {value} - 1 {value} - 2 {key} {value} - filter predicates: - 0 - 1 - 2 {(key < 20)} - keys: - 0 key (type: string) - 1 key (type: string) - 2 key (type: string) - Local Work: - Map Reduce Local Work - - Stage: Stage-1 - Spark - Edges: - Reducer 4 <- Map 3 (SORT, 3) -#### A masked pattern was here #### - Vertices: - Map 3 + Reduce Output Operator + key expressions: key (type: string) + sort order: + + Map-reduce partition columns: key (type: string) + Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + value expressions: value (type: string) + Map 5 Map Operator Tree: TableScan alias: src3 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - Right Outer Join0 to 2 - condition expressions: - 0 {key} {value} - 1 {key} {value} - 2 {key} {value} - filter predicates: - 0 - 1 - 2 {(key < 20)} - keys: - 0 key (type: string) - 1 key (type: string) - 2 key (type: string) - outputColumnNames: _col0, _col1, _col5, _col6, _col10, _col11 - input vertices: - 0 Map 1 - 1 Map 2 + Reduce Output Operator + key expressions: key (type: string) + sort order: + + Map-reduce partition columns: key (type: string) + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + value expressions: value (type: string) + Reducer 2 + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + Right Outer Join0 to 2 + condition expressions: + 0 {KEY.reducesinkkey0} {VALUE._col0} + 1 {KEY.reducesinkkey0} {VALUE._col0} + 2 {KEY.reducesinkkey0} {VALUE._col0} + filter predicates: + 0 + 1 + 2 {(KEY.reducesinkkey0 < 20)} + outputColumnNames: _col0, _col1, _col5, _col6, _col10, _col11 + Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string), _col10 (type: string), _col11 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string) + sort order: ++++++ Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string), _col10 (type: string), _col11 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string) - sort order: ++++++ - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE - Local Work: - Map Reduce Local Work - Reducer 4 + Reducer 3 Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey3 (type: string), KEY.reducesinkkey4 (type: string), KEY.reducesinkkey5 (type: string)
