http://git-wip-us.apache.org/repos/asf/hive/blob/0a961aa8/ql/src/test/results/clientpositive/llap/smb_mapjoin_6.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/llap/smb_mapjoin_6.q.out b/ql/src/test/results/clientpositive/llap/smb_mapjoin_6.q.out index 3e5acd0..1f7e93d 100644 --- a/ql/src/test/results/clientpositive/llap/smb_mapjoin_6.q.out +++ b/ql/src/test/results/clientpositive/llap/smb_mapjoin_6.q.out @@ -73,14 +73,13 @@ STAGE PLANS: Tez #### A masked pattern was here #### Edges: - Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 4 (SIMPLE_EDGE) - Reducer 3 <- Reducer 2 (CUSTOM_SIMPLE_EDGE) + Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE) #### A masked pattern was here #### Vertices: Map 1 Map Operator Tree: TableScan - alias: a + alias: b Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) @@ -89,18 +88,9 @@ STAGE PLANS: expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: string) - Execution mode: vectorized, llap - LLAP IO: no inputs - Map 4 Map Operator Tree: TableScan - alias: b + alias: a Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) @@ -109,47 +99,37 @@ STAGE PLANS: expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: string) - Execution mode: vectorized, llap - LLAP IO: no inputs - Reducer 2 + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 825 Data size: 156750 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 825 Data size: 156750 Basic stats: COMPLETE Column stats: COMPLETE + 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.smb_join_results_n0 + Select Operator + expressions: _col0 (type: int), _col1 (type: string), _col2 (type: int), _col3 (type: string) + outputColumnNames: k1, v1, k2, v2 + Statistics: Num rows: 825 Data size: 156750 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: compute_stats(k1, 'hll'), compute_stats(v1, 'hll'), compute_stats(k2, 'hll'), compute_stats(v2, 'hll') + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 1 Data size: 1728 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 1728 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col2 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col3 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>) Execution mode: llap - Reduce Operator Tree: - Merge Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 825 Data size: 156750 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 825 Data size: 156750 Basic stats: COMPLETE Column stats: COMPLETE - 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.smb_join_results_n0 - Select Operator - expressions: _col0 (type: int), _col1 (type: string), _col2 (type: int), _col3 (type: string) - outputColumnNames: k1, v1, k2, v2 - Statistics: Num rows: 825 Data size: 156750 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: compute_stats(k1, 'hll'), compute_stats(v1, 'hll'), compute_stats(k2, 'hll'), compute_stats(v2, 'hll') - mode: hash - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 1728 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 1728 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col2 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col3 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>) - Reducer 3 + Reducer 2 Execution mode: llap Reduce Operator Tree: Group By Operator @@ -1289,14 +1269,13 @@ STAGE PLANS: Tez #### A masked pattern was here #### Edges: - Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 4 (SIMPLE_EDGE) - Reducer 3 <- Reducer 2 (CUSTOM_SIMPLE_EDGE) + Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE) #### A masked pattern was here #### Vertices: Map 1 Map Operator Tree: TableScan - alias: a + alias: b Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) @@ -1305,18 +1284,9 @@ STAGE PLANS: expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: string) - Execution mode: vectorized, llap - LLAP IO: no inputs - Map 4 Map Operator Tree: TableScan - alias: b + alias: a Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: key is not null (type: boolean) @@ -1325,47 +1295,37 @@ STAGE PLANS: expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: string) - Execution mode: vectorized, llap - LLAP IO: no inputs - Reducer 2 + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 825 Data size: 156750 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 825 Data size: 156750 Basic stats: COMPLETE Column stats: COMPLETE + 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.smb_join_results_n0 + Select Operator + expressions: _col0 (type: int), _col1 (type: string), _col2 (type: int), _col3 (type: string) + outputColumnNames: k1, v1, k2, v2 + Statistics: Num rows: 825 Data size: 156750 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: compute_stats(k1, 'hll'), compute_stats(v1, 'hll'), compute_stats(k2, 'hll'), compute_stats(v2, 'hll') + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 1 Data size: 1728 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 1728 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col2 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col3 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>) Execution mode: llap - Reduce Operator Tree: - Merge Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 825 Data size: 156750 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 825 Data size: 156750 Basic stats: COMPLETE Column stats: COMPLETE - 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.smb_join_results_n0 - Select Operator - expressions: _col0 (type: int), _col1 (type: string), _col2 (type: int), _col3 (type: string) - outputColumnNames: k1, v1, k2, v2 - Statistics: Num rows: 825 Data size: 156750 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: compute_stats(k1, 'hll'), compute_stats(v1, 'hll'), compute_stats(k2, 'hll'), compute_stats(v2, 'hll') - mode: hash - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 1728 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 1728 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col2 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col3 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>) - Reducer 3 + Reducer 2 Execution mode: llap Reduce Operator Tree: Group By Operator @@ -2521,14 +2481,13 @@ STAGE PLANS: Tez #### A masked pattern was here #### Edges: - Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 4 (SIMPLE_EDGE) - Reducer 3 <- Reducer 2 (CUSTOM_SIMPLE_EDGE) + Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE) #### A masked pattern was here #### Vertices: Map 1 Map Operator Tree: TableScan - alias: a + alias: b Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key > 1000) (type: boolean) @@ -2537,18 +2496,9 @@ STAGE PLANS: expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 95 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 95 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: string) - Execution mode: vectorized, llap - LLAP IO: no inputs - Map 4 Map Operator Tree: TableScan - alias: b + alias: a Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key > 1000) (type: boolean) @@ -2557,47 +2507,37 @@ STAGE PLANS: expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 95 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 95 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: string) - Execution mode: vectorized, llap - LLAP IO: no inputs - Reducer 2 + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 1 Data size: 190 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 190 Basic stats: COMPLETE Column stats: COMPLETE + 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.smb_join_results_n0 + Select Operator + expressions: _col0 (type: int), _col1 (type: string), _col2 (type: int), _col3 (type: string) + outputColumnNames: k1, v1, k2, v2 + Statistics: Num rows: 1 Data size: 190 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: compute_stats(k1, 'hll'), compute_stats(v1, 'hll'), compute_stats(k2, 'hll'), compute_stats(v2, 'hll') + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 1 Data size: 1728 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 1728 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col2 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col3 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>) Execution mode: llap - Reduce Operator Tree: - Merge Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 190 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 190 Basic stats: COMPLETE Column stats: COMPLETE - 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.smb_join_results_n0 - Select Operator - expressions: _col0 (type: int), _col1 (type: string), _col2 (type: int), _col3 (type: string) - outputColumnNames: k1, v1, k2, v2 - Statistics: Num rows: 1 Data size: 190 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: compute_stats(k1, 'hll'), compute_stats(v1, 'hll'), compute_stats(k2, 'hll'), compute_stats(v2, 'hll') - mode: hash - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 1728 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 1728 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col2 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col3 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>) - Reducer 3 + Reducer 2 Execution mode: llap Reduce Operator Tree: Group By Operator @@ -2669,14 +2609,13 @@ STAGE PLANS: Tez #### A masked pattern was here #### Edges: - Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 4 (SIMPLE_EDGE) - Reducer 3 <- Reducer 2 (CUSTOM_SIMPLE_EDGE) + Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE) #### A masked pattern was here #### Vertices: Map 1 Map Operator Tree: TableScan - alias: a + alias: b Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key > 1000) (type: boolean) @@ -2685,18 +2624,9 @@ STAGE PLANS: expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 95 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 95 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: string) - Execution mode: vectorized, llap - LLAP IO: no inputs - Map 4 Map Operator Tree: TableScan - alias: b + alias: a Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key > 1000) (type: boolean) @@ -2705,47 +2635,37 @@ STAGE PLANS: expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 95 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 95 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: string) - Execution mode: vectorized, llap - LLAP IO: no inputs - Reducer 2 + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 1 Data size: 190 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 190 Basic stats: COMPLETE Column stats: COMPLETE + 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.smb_join_results_n0 + Select Operator + expressions: _col0 (type: int), _col1 (type: string), _col2 (type: int), _col3 (type: string) + outputColumnNames: k1, v1, k2, v2 + Statistics: Num rows: 1 Data size: 190 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: compute_stats(k1, 'hll'), compute_stats(v1, 'hll'), compute_stats(k2, 'hll'), compute_stats(v2, 'hll') + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 1 Data size: 1728 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 1728 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col2 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col3 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>) Execution mode: llap - Reduce Operator Tree: - Merge Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 190 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 190 Basic stats: COMPLETE Column stats: COMPLETE - 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.smb_join_results_n0 - Select Operator - expressions: _col0 (type: int), _col1 (type: string), _col2 (type: int), _col3 (type: string) - outputColumnNames: k1, v1, k2, v2 - Statistics: Num rows: 1 Data size: 190 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: compute_stats(k1, 'hll'), compute_stats(v1, 'hll'), compute_stats(k2, 'hll'), compute_stats(v2, 'hll') - mode: hash - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 1728 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 1728 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col2 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col3 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>) - Reducer 3 + Reducer 2 Execution mode: llap Reduce Operator Tree: Group By Operator @@ -2812,14 +2732,11 @@ STAGE PLANS: Stage: Stage-1 Tez #### A masked pattern was here #### - Edges: - Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 3 (SIMPLE_EDGE), Map 4 (SIMPLE_EDGE) -#### A masked pattern was here #### Vertices: Map 1 Map Operator Tree: TableScan - alias: a + alias: b Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key > 1000) (type: boolean) @@ -2828,18 +2745,9 @@ STAGE PLANS: expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 95 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 95 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: string) - Execution mode: vectorized, llap - LLAP IO: no inputs - Map 3 Map Operator Tree: TableScan - alias: b + alias: c Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key > 1000) (type: boolean) @@ -2848,18 +2756,9 @@ STAGE PLANS: expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 95 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 95 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: string) - Execution mode: vectorized, llap - LLAP IO: no inputs - Map 4 Map Operator Tree: TableScan - alias: c + alias: a Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key > 1000) (type: boolean) @@ -2868,34 +2767,24 @@ STAGE PLANS: expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 95 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 95 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: string) - Execution mode: vectorized, llap - LLAP IO: no inputs - Reducer 2 + Merge Join Operator + condition map: + Inner Join 0 to 1 + Inner Join 1 to 2 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + 2 _col0 (type: int) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + Statistics: Num rows: 1 Data size: 285 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 285 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Execution mode: llap - Reduce Operator Tree: - Merge Join Operator - condition map: - Inner Join 0 to 1 - Inner Join 1 to 2 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - 2 _col0 (type: int) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 1 Data size: 285 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 285 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator
http://git-wip-us.apache.org/repos/asf/hive/blob/0a961aa8/ql/src/test/results/clientpositive/llap/subquery_in_having.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/llap/subquery_in_having.q.out b/ql/src/test/results/clientpositive/llap/subquery_in_having.q.out index b4ce6f8..0bd5ca0 100644 --- a/ql/src/test/results/clientpositive/llap/subquery_in_having.q.out +++ b/ql/src/test/results/clientpositive/llap/subquery_in_having.q.out @@ -265,9 +265,7 @@ STAGE PLANS: Tez #### A masked pattern was here #### Edges: - Reducer 2 <- Map 1 (SIMPLE_EDGE) - Reducer 3 <- Reducer 2 (ONE_TO_ONE_EDGE), Reducer 4 (ONE_TO_ONE_EDGE) - Reducer 4 <- Map 1 (SIMPLE_EDGE) + Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 3 (SIMPLE_EDGE) #### A masked pattern was here #### Vertices: Map 1 @@ -290,6 +288,16 @@ STAGE PLANS: Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint), _col2 (type: bigint) + Execution mode: vectorized, llap + LLAP IO: no inputs + Map 3 + Map Operator Tree: + TableScan + alias: part_subq + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: p_mfgr is not null (type: boolean) + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: max(p_size), min(p_size) keys: p_mfgr (type: string) @@ -305,63 +313,47 @@ STAGE PLANS: Execution mode: vectorized, llap LLAP IO: no inputs Reducer 2 - Execution mode: vectorized, llap Reduce Operator Tree: Group By Operator - aggregations: sum(VALUE._col0), count(VALUE._col1) + aggregations: max(VALUE._col0), min(VALUE._col1) keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string), (_col1 / _col2) (type: double) - outputColumnNames: _col0, _col1 + Filter Operator + predicate: ((_col1 - _col2) < 20) (type: boolean) Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) + Select Operator + expressions: _col0 (type: string) + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: double) - Reducer 3 Execution mode: llap Reduce Operator Tree: - Merge Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 206 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 206 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Reducer 4 - Execution mode: vectorized, llap - Reduce Operator Tree: Group By Operator - aggregations: max(VALUE._col0), min(VALUE._col1) + aggregations: sum(VALUE._col0), count(VALUE._col1) keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: ((_col1 - _col2) < 20) (type: boolean) + Select Operator + expressions: _col0 (type: string), (_col1 / _col2) (type: double) + outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 188 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: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 206 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 206 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -400,9 +392,7 @@ STAGE PLANS: Tez #### A masked pattern was here #### Edges: - Reducer 2 <- Map 1 (SIMPLE_EDGE) - Reducer 3 <- Reducer 2 (ONE_TO_ONE_EDGE), Reducer 4 (ONE_TO_ONE_EDGE) - Reducer 4 <- Map 1 (SIMPLE_EDGE) + Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 3 (SIMPLE_EDGE) #### A masked pattern was here #### Vertices: Map 1 @@ -425,6 +415,16 @@ STAGE PLANS: Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint), _col2 (type: bigint) + Execution mode: vectorized, llap + LLAP IO: no inputs + Map 3 + Map Operator Tree: + TableScan + alias: part_subq + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: p_mfgr is not null (type: boolean) + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: max(p_size), min(p_size) keys: p_mfgr (type: string) @@ -440,63 +440,47 @@ STAGE PLANS: Execution mode: vectorized, llap LLAP IO: no inputs Reducer 2 - Execution mode: vectorized, llap Reduce Operator Tree: Group By Operator - aggregations: sum(VALUE._col0), count(VALUE._col1) + aggregations: max(VALUE._col0), min(VALUE._col1) keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string), (_col1 / _col2) (type: double) - outputColumnNames: _col0, _col1 + Filter Operator + predicate: ((_col1 - _col2) < 20) (type: boolean) Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) + Select Operator + expressions: _col0 (type: string) + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: double) - Reducer 3 Execution mode: llap Reduce Operator Tree: - Merge Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 206 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 206 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - Reducer 4 - Execution mode: vectorized, llap - Reduce Operator Tree: Group By Operator - aggregations: max(VALUE._col0), min(VALUE._col1) + aggregations: sum(VALUE._col0), count(VALUE._col1) keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: ((_col1 - _col2) < 20) (type: boolean) + Select Operator + expressions: _col0 (type: string), (_col1 / _col2) (type: double) + outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 188 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: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 206 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 206 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator http://git-wip-us.apache.org/repos/asf/hive/blob/0a961aa8/ql/src/test/results/clientpositive/llap/subquery_notin.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/llap/subquery_notin.q.out b/ql/src/test/results/clientpositive/llap/subquery_notin.q.out index 21a0f84..8a5ccf5 100644 --- a/ql/src/test/results/clientpositive/llap/subquery_notin.q.out +++ b/ql/src/test/results/clientpositive/llap/subquery_notin.q.out @@ -5786,18 +5786,20 @@ STAGE PLANS: Processor Tree: ListSink -PREHOOK: query: SELECT c1 FROM t1_n0 WHERE c1 NOT IN (SELECT c1 FROM t2_n0 where t1_n0.c1=t2_n0.c1) +PREHOOK: query: SELECT c1 FROM t1_n0 WHERE c1 NOT IN (SELECT c1 FROM t2_n0 where t1_n0.c2=t2_n0.c1) PREHOOK: type: QUERY PREHOOK: Input: default@t1_n0 PREHOOK: Input: default@t2_n0 #### A masked pattern was here #### -POSTHOOK: query: SELECT c1 FROM t1_n0 WHERE c1 NOT IN (SELECT c1 FROM t2_n0 where t1_n0.c1=t2_n0.c1) +POSTHOOK: query: SELECT c1 FROM t1_n0 WHERE c1 NOT IN (SELECT c1 FROM t2_n0 where t1_n0.c2=t2_n0.c1) POSTHOOK: type: QUERY POSTHOOK: Input: default@t1_n0 POSTHOOK: Input: default@t2_n0 #### A masked pattern was here #### NULL 1 +2 +100 PREHOOK: query: DROP TABLE t1_n0 PREHOOK: type: DROPTABLE PREHOOK: Input: default@t1_n0 @@ -6078,11 +6080,9 @@ STAGE PLANS: Tez #### A masked pattern was here #### Edges: - Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 4 (ONE_TO_ONE_EDGE), Reducer 6 (ONE_TO_ONE_EDGE) + Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 4 (ONE_TO_ONE_EDGE), Reducer 7 (SIMPLE_EDGE) Reducer 4 <- Map 3 (SIMPLE_EDGE) - Reducer 5 <- Map 3 (SIMPLE_EDGE) - Reducer 6 <- Reducer 5 (SIMPLE_EDGE), Reducer 8 (ONE_TO_ONE_EDGE) - Reducer 8 <- Map 7 (SIMPLE_EDGE) + Reducer 7 <- Map 3 (SIMPLE_EDGE), Map 6 (SIMPLE_EDGE) #### A masked pattern was here #### Vertices: Map 1 @@ -6137,7 +6137,7 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized, llap LLAP IO: no inputs - Map 7 + Map 6 Map Operator Tree: TableScan alias: fixob @@ -6199,8 +6199,7 @@ STAGE PLANS: Map-reduce partition columns: _col0 (type: int) Statistics: Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint), _col2 (type: bigint) - Reducer 5 - Execution mode: vectorized, llap + Reducer 7 Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: int), KEY._col1 (type: int) @@ -6211,42 +6210,27 @@ STAGE PLANS: expressions: _col0 (type: int), true (type: boolean) outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: boolean) - Reducer 6 Execution mode: llap Reduce Operator Tree: - Merge Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col1, _col2 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col2 (type: int) - sort order: + - Map-reduce partition columns: _col2 (type: int) - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: boolean) - Reducer 8 - Execution mode: vectorized, llap - Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: int) mode: mergepartial outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1, _col2 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col2 (type: int) + sort order: + + Map-reduce partition columns: _col2 (type: int) + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: boolean) Stage: Stage-0 Fetch Operator @@ -6312,11 +6296,9 @@ STAGE PLANS: Tez #### A masked pattern was here #### Edges: - Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 3 (ONE_TO_ONE_EDGE), Reducer 5 (ONE_TO_ONE_EDGE) + Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 3 (ONE_TO_ONE_EDGE), Reducer 4 (SIMPLE_EDGE) Reducer 3 <- Map 1 (SIMPLE_EDGE) - Reducer 4 <- Map 1 (SIMPLE_EDGE) - Reducer 5 <- Reducer 4 (SIMPLE_EDGE), Reducer 7 (ONE_TO_ONE_EDGE) - Reducer 7 <- Map 6 (SIMPLE_EDGE) + Reducer 4 <- Map 1 (SIMPLE_EDGE), Map 5 (SIMPLE_EDGE) #### A masked pattern was here #### Vertices: Map 1 @@ -6364,7 +6346,7 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized, llap LLAP IO: no inputs - Map 6 + Map 5 Map Operator Tree: TableScan alias: t_n0 @@ -6427,7 +6409,13 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint), _col2 (type: bigint) Reducer 4 - Execution mode: vectorized, llap + Reduce Operator Tree: + Group By Operator + keys: KEY._col0 (type: int) + mode: mergepartial + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: llap Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: int), KEY._col1 (type: int) @@ -6438,42 +6426,20 @@ STAGE PLANS: expressions: _col0 (type: int), true (type: boolean) outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1, _col2 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: boolean) - Reducer 5 - Execution mode: llap - Reduce Operator Tree: - Merge Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col1, _col2 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col2 (type: int) - sort order: + - Map-reduce partition columns: _col2 (type: int) - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: boolean) - Reducer 7 - Execution mode: vectorized, llap - Reduce Operator Tree: - Group By Operator - keys: KEY._col0 (type: int) - mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col2 (type: int) + sort order: + + Map-reduce partition columns: _col2 (type: int) + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: boolean) Stage: Stage-0 Fetch Operator http://git-wip-us.apache.org/repos/asf/hive/blob/0a961aa8/ql/src/test/results/clientpositive/llap/vectorized_bucketmapjoin1.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/llap/vectorized_bucketmapjoin1.q.out b/ql/src/test/results/clientpositive/llap/vectorized_bucketmapjoin1.q.out index 61c5051..386c8be 100644 --- a/ql/src/test/results/clientpositive/llap/vectorized_bucketmapjoin1.q.out +++ b/ql/src/test/results/clientpositive/llap/vectorized_bucketmapjoin1.q.out @@ -112,102 +112,42 @@ STAGE PLANS: Stage: Stage-1 Tez #### A masked pattern was here #### - Edges: - Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 3 (SIMPLE_EDGE) -#### A masked pattern was here #### Vertices: Map 1 Map Operator Tree: TableScan - alias: a + alias: b Statistics: Num rows: 2 Data size: 208 Basic stats: COMPLETE Column stats: COMPLETE - TableScan Vectorization: - native: true Filter Operator - Filter Vectorization: - className: VectorFilterOperator - native: true - predicateExpression: SelectColumnIsNotNull(col 0:int) predicate: key is not null (type: boolean) Statistics: Num rows: 2 Data size: 208 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: key (type: int) - sort order: + - Map-reduce partition columns: key (type: int) - Reduce Sink Vectorization: - className: VectorReduceSinkLongOperator - native: true - nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - Statistics: Num rows: 2 Data size: 208 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: value (type: string) - Execution mode: vectorized, llap - LLAP IO: all inputs - Map Vectorization: - enabled: true - enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true - inputFormatFeatureSupport: [] - featureSupportInUse: [] - inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat - allNative: true - usesVectorUDFAdaptor: false - vectorized: true - Map 3 Map Operator Tree: TableScan - alias: b + alias: a Statistics: Num rows: 2 Data size: 208 Basic stats: COMPLETE Column stats: COMPLETE - TableScan Vectorization: - native: true Filter Operator - Filter Vectorization: - className: VectorFilterOperator - native: true - predicateExpression: SelectColumnIsNotNull(col 0:int) predicate: key is not null (type: boolean) Statistics: Num rows: 2 Data size: 208 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: key (type: int) - sort order: + - Map-reduce partition columns: key (type: int) - Reduce Sink Vectorization: - className: VectorReduceSinkLongOperator - native: true - nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - Statistics: Num rows: 2 Data size: 208 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: value (type: string) - Execution mode: vectorized, llap - LLAP IO: all inputs - Map Vectorization: - enabled: true - enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true - inputFormatFeatureSupport: [] - featureSupportInUse: [] - inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat - allNative: true - usesVectorUDFAdaptor: false - vectorized: true - Reducer 2 + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 key (type: int) + 1 key (type: int) + outputColumnNames: _col0, _col1, _col5, _col6 + Statistics: Num rows: 4 Data size: 832 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: int), _col1 (type: string), _col5 (type: int), _col6 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 4 Data size: 832 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 4 Data size: 832 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Execution mode: llap - Reduce Operator Tree: - Merge Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 key (type: int) - 1 key (type: int) - outputColumnNames: _col0, _col1, _col5, _col6 - Statistics: Num rows: 4 Data size: 832 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col0 (type: int), _col1 (type: string), _col5 (type: int), _col6 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 4 Data size: 832 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 4 Data size: 832 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -247,102 +187,42 @@ STAGE PLANS: Stage: Stage-1 Tez #### A masked pattern was here #### - Edges: - Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 3 (SIMPLE_EDGE) -#### A masked pattern was here #### Vertices: Map 1 Map Operator Tree: TableScan - alias: a + alias: b Statistics: Num rows: 2 Data size: 208 Basic stats: COMPLETE Column stats: COMPLETE - TableScan Vectorization: - native: true Filter Operator - Filter Vectorization: - className: VectorFilterOperator - native: true - predicateExpression: SelectColumnIsNotNull(col 0:int) predicate: key is not null (type: boolean) Statistics: Num rows: 2 Data size: 208 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: key (type: int) - sort order: + - Map-reduce partition columns: key (type: int) - Reduce Sink Vectorization: - className: VectorReduceSinkLongOperator - native: true - nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - Statistics: Num rows: 2 Data size: 208 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: value (type: string) - Execution mode: vectorized, llap - LLAP IO: all inputs - Map Vectorization: - enabled: true - enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true - inputFormatFeatureSupport: [] - featureSupportInUse: [] - inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat - allNative: true - usesVectorUDFAdaptor: false - vectorized: true - Map 3 Map Operator Tree: TableScan - alias: b + alias: a Statistics: Num rows: 2 Data size: 208 Basic stats: COMPLETE Column stats: COMPLETE - TableScan Vectorization: - native: true Filter Operator - Filter Vectorization: - className: VectorFilterOperator - native: true - predicateExpression: SelectColumnIsNotNull(col 0:int) predicate: key is not null (type: boolean) Statistics: Num rows: 2 Data size: 208 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: key (type: int) - sort order: + - Map-reduce partition columns: key (type: int) - Reduce Sink Vectorization: - className: VectorReduceSinkLongOperator - native: true - nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - Statistics: Num rows: 2 Data size: 208 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: value (type: string) - Execution mode: vectorized, llap - LLAP IO: no inputs - Map Vectorization: - enabled: true - enabledConditionsMet: hive.vectorized.use.row.serde.deserialize IS true - inputFormatFeatureSupport: [] - featureSupportInUse: [] - inputFileFormats: org.apache.hadoop.hive.ql.io.RCFileInputFormat - allNative: true - usesVectorUDFAdaptor: false - vectorized: true - Reducer 2 + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 key (type: int) + 1 key (type: int) + outputColumnNames: _col0, _col1, _col5, _col6 + Statistics: Num rows: 4 Data size: 832 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: int), _col1 (type: string), _col5 (type: int), _col6 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 4 Data size: 832 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 4 Data size: 832 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Execution mode: llap - Reduce Operator Tree: - Merge Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 key (type: int) - 1 key (type: int) - outputColumnNames: _col0, _col1, _col5, _col6 - Statistics: Num rows: 4 Data size: 832 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col0 (type: int), _col1 (type: string), _col5 (type: int), _col6 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 4 Data size: 832 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 4 Data size: 832 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -382,103 +262,42 @@ STAGE PLANS: Stage: Stage-1 Tez #### A masked pattern was here #### - Edges: - Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 3 (SIMPLE_EDGE) -#### A masked pattern was here #### Vertices: Map 1 Map Operator Tree: TableScan - alias: a + alias: b Statistics: Num rows: 2 Data size: 208 Basic stats: COMPLETE Column stats: COMPLETE - TableScan Vectorization: - native: true Filter Operator - Filter Vectorization: - className: VectorFilterOperator - native: true - predicateExpression: SelectColumnIsNotNull(col 0:int) predicate: key is not null (type: boolean) Statistics: Num rows: 2 Data size: 208 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: key (type: int) - sort order: + - Map-reduce partition columns: key (type: int) - Reduce Sink Vectorization: - className: VectorReduceSinkLongOperator - native: true - nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - Statistics: Num rows: 2 Data size: 208 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: value (type: string) - Execution mode: vectorized, llap - LLAP IO: all inputs - Map Vectorization: - enabled: true - enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true - inputFormatFeatureSupport: [] - featureSupportInUse: [] - inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat - allNative: true - usesVectorUDFAdaptor: false - vectorized: true - Map 3 Map Operator Tree: TableScan - alias: b + alias: a Statistics: Num rows: 2 Data size: 208 Basic stats: COMPLETE Column stats: COMPLETE - TableScan Vectorization: - native: true Filter Operator - Filter Vectorization: - className: VectorFilterOperator - native: true - predicateExpression: SelectColumnIsNotNull(col 0:int) predicate: key is not null (type: boolean) Statistics: Num rows: 2 Data size: 208 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: key (type: int) - sort order: + - Map-reduce partition columns: key (type: int) - Reduce Sink Vectorization: - className: VectorReduceSinkLongOperator - native: true - nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - Statistics: Num rows: 2 Data size: 208 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: value (type: string) - Execution mode: vectorized, llap - LLAP IO: no inputs - Map Vectorization: - enabled: true - enabledConditionsMet: hive.vectorized.use.vector.serde.deserialize IS true - inputFormatFeatureSupport: [DECIMAL_64] - vectorizationSupportRemovedReasons: [DECIMAL_64 disabled because LLAP is enabled] - featureSupportInUse: [] - inputFileFormats: org.apache.hadoop.mapred.TextInputFormat - allNative: true - usesVectorUDFAdaptor: false - vectorized: true - Reducer 2 + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 key (type: int) + 1 key (type: int) + outputColumnNames: _col0, _col1, _col5, _col6 + Statistics: Num rows: 4 Data size: 832 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: int), _col1 (type: string), _col5 (type: int), _col6 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 4 Data size: 832 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 4 Data size: 832 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Execution mode: llap - Reduce Operator Tree: - Merge Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 key (type: int) - 1 key (type: int) - outputColumnNames: _col0, _col1, _col5, _col6 - Statistics: Num rows: 4 Data size: 832 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col0 (type: int), _col1 (type: string), _col5 (type: int), _col6 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 4 Data size: 832 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - Statistics: Num rows: 4 Data size: 832 Basic stats: COMPLETE Column stats: COMPLETE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator