diff --git a/ql/src/test/results/clientpositive/tez/explainanalyze_2.q.out b/ql/src/test/results/clientpositive/tez/explainanalyze_2.q.out index 0cbddde..37fc7d3 100644 --- a/ql/src/test/results/clientpositive/tez/explainanalyze_2.q.out +++ b/ql/src/test/results/clientpositive/tez/explainanalyze_2.q.out @@ -380,141 +380,143 @@ POSTHOOK: type: QUERY Plan optimized by CBO. Vertex dependency in root stage -Reducer 10 <- Reducer 9 (SIMPLE_EDGE) -Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 11 (SIMPLE_EDGE) -Reducer 3 <- Map 12 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) -Reducer 4 <- Map 13 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE) -Reducer 5 <- Map 14 (SIMPLE_EDGE), Reducer 4 (SIMPLE_EDGE) -Reducer 6 <- Map 15 (SIMPLE_EDGE), Reducer 5 (SIMPLE_EDGE) -Reducer 7 <- Map 16 (SIMPLE_EDGE), Reducer 6 (SIMPLE_EDGE) -Reducer 8 <- Map 17 (SIMPLE_EDGE), Reducer 7 (SIMPLE_EDGE) -Reducer 9 <- Reducer 8 (SIMPLE_EDGE) +Reducer 10 <- Map 14 (SIMPLE_EDGE), Reducer 9 (SIMPLE_EDGE) +Reducer 11 <- Reducer 10 (SIMPLE_EDGE), Reducer 16 (SIMPLE_EDGE) +Reducer 16 <- Map 15 (SIMPLE_EDGE), Map 17 (SIMPLE_EDGE) +Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 6 (SIMPLE_EDGE) +Reducer 3 <- Reducer 11 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) +Reducer 4 <- Reducer 3 (SIMPLE_EDGE) +Reducer 5 <- Reducer 4 (SIMPLE_EDGE) +Reducer 8 <- Map 12 (SIMPLE_EDGE), Map 7 (SIMPLE_EDGE) +Reducer 9 <- Map 13 (SIMPLE_EDGE), Reducer 8 (SIMPLE_EDGE) Stage-0 Fetch Operator limit:100 Stage-1 - Reducer 10 - File Output Operator [FS_53] - Limit [LIM_52] (rows=100/0 width=18) + Reducer 5 + File Output Operator [FS_55] + Limit [LIM_54] (rows=24/0 width=285) Number of rows:100 - Select Operator [SEL_51] (rows=550/0 width=18) + Select Operator [SEL_53] (rows=24/0 width=285) Output:["_col0","_col1","_col2","_col3","_col4","_col5"] - <-Reducer 9 [SIMPLE_EDGE] - SHUFFLE [RS_50] - Group By Operator [GBY_48] (rows=550/0 width=18) + <-Reducer 4 [SIMPLE_EDGE] + SHUFFLE [RS_52] + Group By Operator [GBY_50] (rows=24/0 width=285) Output:["_col0","_col1","_col2","_col3","_col4","_col5"],aggregations:["count(VALUE._col0)","count(VALUE._col1)","count(VALUE._col2)"],keys:KEY._col0, KEY._col1, KEY._col2 - <-Reducer 8 [SIMPLE_EDGE] - SHUFFLE [RS_47] + <-Reducer 3 [SIMPLE_EDGE] + SHUFFLE [RS_49] PartitionCols:_col0, _col1, _col2 - Group By Operator [GBY_46] (rows=1100/0 width=18) - Output:["_col0","_col1","_col2","_col3","_col4","_col5"],aggregations:["count(_col1)","count(_col9)","count(_col15)"],keys:_col0, _col8, _col14 - Select Operator [SEL_45] (rows=1100/0 width=18) - Output:["_col0","_col8","_col14","_col1","_col9","_col15"] - Merge Join Operator [MERGEJOIN_103] (rows=1100/0 width=18) - Conds:RS_42._col3=RS_43._col1(Inner),Output:["_col0","_col1","_col8","_col9","_col14","_col15"] - <-Map 17 [SIMPLE_EDGE] - SHUFFLE [RS_43] - PartitionCols:_col1 - Select Operator [SEL_23] (rows=1000/0 width=18) - Output:["_col1"] - Filter Operator [FIL_96] (rows=1000/0 width=18) - predicate:((key = 'srcpartkey') and value is not null) - TableScan [TS_21] (rows=2000/2000 width=18) - default@srcpart,srcpart,Tbl:COMPLETE,Col:NONE,Output:["key","value"] - <-Reducer 7 [SIMPLE_EDGE] - SHUFFLE [RS_42] - PartitionCols:_col3 - Merge Join Operator [MERGEJOIN_102] (rows=129/0 width=625) - Conds:RS_39._col1=RS_40._col1(Inner),Output:["_col0","_col1","_col3","_col8","_col9","_col14","_col15"] - <-Map 16 [SIMPLE_EDGE] - SHUFFLE [RS_40] - PartitionCols:_col1 - Select Operator [SEL_20] (rows=2/0 width=180) - Output:["_col1"] - Filter Operator [FIL_95] (rows=2/0 width=175) - predicate:((key = 'src1key') and value is not null) - TableScan [TS_18] (rows=25/25 width=175) - default@src1,src1,Tbl:COMPLETE,Col:COMPLETE,Output:["key","value"] - <-Reducer 6 [SIMPLE_EDGE] - SHUFFLE [RS_39] - PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_101] (rows=129/0 width=625) - Conds:RS_36._col12=RS_37._col0(Inner),Output:["_col0","_col1","_col3","_col8","_col9","_col14","_col15"] - <-Map 15 [SIMPLE_EDGE] - SHUFFLE [RS_37] - PartitionCols:_col0 - Select Operator [SEL_17] (rows=500/0 width=178) - Output:["_col0"] - Filter Operator [FIL_94] (rows=500/0 width=178) - predicate:((value) IN ('2000Q1', '2000Q2', '2000Q3') and key is not null) - TableScan [TS_15] (rows=500/500 width=178) - default@src,d3,Tbl:COMPLETE,Col:COMPLETE,Output:["key","value"] - <-Reducer 5 [SIMPLE_EDGE] - SHUFFLE [RS_36] - PartitionCols:_col12 - Merge Join Operator [MERGEJOIN_100] (rows=53/0 width=712) - Conds:RS_33._col6=RS_34._col0(Inner),Output:["_col0","_col1","_col3","_col8","_col9","_col12","_col14","_col15"] - <-Map 14 [SIMPLE_EDGE] - SHUFFLE [RS_34] - PartitionCols:_col0 - Select Operator [SEL_14] (rows=500/0 width=178) - Output:["_col0"] - Filter Operator [FIL_93] (rows=500/0 width=178) - predicate:((value) IN ('2000Q1', '2000Q2', '2000Q3') and key is not null) - TableScan [TS_12] (rows=500/500 width=178) - default@src,d2,Tbl:COMPLETE,Col:COMPLETE,Output:["key","value"] - <-Reducer 4 [SIMPLE_EDGE] - SHUFFLE [RS_33] - PartitionCols:_col6 - Merge Join Operator [MERGEJOIN_99] (rows=22/0 width=799) - Conds:RS_30._col0=RS_31._col0(Inner),Output:["_col0","_col1","_col3","_col6","_col8","_col9","_col12","_col14","_col15"] - <-Map 13 [SIMPLE_EDGE] - SHUFFLE [RS_31] - PartitionCols:_col0 - Select Operator [SEL_11] (rows=2/0 width=178) - Output:["_col0"] - Filter Operator [FIL_92] (rows=2/0 width=178) - predicate:((value = 'd1value') and key is not null) - TableScan [TS_9] (rows=500/500 width=178) - default@src,d1,Tbl:COMPLETE,Col:COMPLETE,Output:["key","value"] - <-Reducer 3 [SIMPLE_EDGE] - SHUFFLE [RS_30] - PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_98] (rows=22/0 width=799) - Conds:RS_27._col9, _col11=RS_28._col1, _col3(Inner),Output:["_col0","_col1","_col3","_col6","_col8","_col9","_col12","_col14","_col15"] - <-Map 12 [SIMPLE_EDGE] - SHUFFLE [RS_28] - PartitionCols:_col1, _col3 - Select Operator [SEL_8] (rows=170/170 width=356) - Output:["_col0","_col1","_col2","_col3"] - Filter Operator [FIL_91] (rows=170/170 width=356) - predicate:(v2 is not null and v3 is not null and k1 is not null) - TableScan [TS_6] (rows=170/170 width=356) - default@cs,cs,Tbl:COMPLETE,Col:COMPLETE,Output:["k1","v2","k3","v3"] - <-Reducer 2 [SIMPLE_EDGE] - SHUFFLE [RS_27] - PartitionCols:_col9, _col11 - Merge Join Operator [MERGEJOIN_97] (rows=16/0 width=625) - Conds:RS_24._col2, _col4=RS_25._col2, _col4(Inner),Output:["_col0","_col1","_col3","_col6","_col8","_col9","_col11"] - <-Map 1 [SIMPLE_EDGE] - SHUFFLE [RS_24] - PartitionCols:_col2, _col4 - Select Operator [SEL_2] (rows=8/0 width=531) - Output:["_col0","_col1","_col2","_col3","_col4"] - Filter Operator [FIL_89] (rows=8/0 width=534) - predicate:((v3 = 'ssv3') and k2 is not null and k3 is not null and k1 is not null and v1 is not null and v2 is not null) - TableScan [TS_0] (rows=85/85 width=534) - default@ss,ss,Tbl:COMPLETE,Col:COMPLETE,Output:["k1","v1","k2","v2","k3","v3"] - <-Map 11 [SIMPLE_EDGE] - SHUFFLE [RS_25] - PartitionCols:_col2, _col4 - Select Operator [SEL_5] (rows=8/0 width=531) - Output:["_col0","_col2","_col3","_col4","_col5"] - Filter Operator [FIL_90] (rows=8/0 width=534) - predicate:((v1 = 'srv1') and k2 is not null and k3 is not null and v2 is not null and v3 is not null and k1 is not null) - TableScan [TS_3] (rows=85/85 width=534) - default@sr,sr,Tbl:COMPLETE,Col:COMPLETE,Output:["k1","v1","k2","v2","k3","v3"] + Group By Operator [GBY_48] (rows=24/0 width=285) + Output:["_col0","_col1","_col2","_col3","_col4","_col5"],aggregations:["count(_col13)","count(_col21)","count(_col3)"],keys:_col12, _col20, _col2 + Select Operator [SEL_47] (rows=650/0 width=534) + Output:["_col12","_col20","_col2","_col13","_col21","_col3"] + Merge Join Operator [MERGEJOIN_97] (rows=650/0 width=534) + Conds:RS_44._col1, _col3=RS_45._col15, _col17(Inner),Output:["_col2","_col3","_col12","_col13","_col20","_col21"] + <-Reducer 11 [SIMPLE_EDGE] + SHUFFLE [RS_45] + PartitionCols:_col15, _col17 + Select Operator [SEL_40] (rows=190/0 width=447) + Output:["_col14","_col15","_col17","_col6","_col7"] + Merge Join Operator [MERGEJOIN_96] (rows=190/0 width=447) + Conds:RS_37._col6, _col4=RS_38._col4, _col2(Inner),Output:["_col2","_col3","_col14","_col15","_col17"] + <-Reducer 10 [SIMPLE_EDGE] + SHUFFLE [RS_37] + PartitionCols:_col6, _col4 + Merge Join Operator [MERGEJOIN_94] (rows=40/0 width=352) + Conds:RS_34._col3=RS_35._col1(Inner),Output:["_col2","_col3","_col4","_col6"] + <-Map 14 [SIMPLE_EDGE] + SHUFFLE [RS_35] + PartitionCols:_col1 + Select Operator [SEL_17] (rows=2/0 width=180) + Output:["_col1"] + Filter Operator [FIL_88] (rows=2/0 width=175) + predicate:((key = 'src1key') and value is not null) + TableScan [TS_15] (rows=25/25 width=175) + default@src1,src1,Tbl:COMPLETE,Col:COMPLETE,Output:["key","value"] + <-Reducer 9 [SIMPLE_EDGE] + SHUFFLE [RS_34] + PartitionCols:_col3 + Merge Join Operator [MERGEJOIN_93] (rows=40/0 width=352) + Conds:RS_31._col2=RS_32._col0(Inner),Output:["_col2","_col3","_col4","_col6"] + <-Map 13 [SIMPLE_EDGE] + SHUFFLE [RS_32] + PartitionCols:_col0 + Select Operator [SEL_14] (rows=2/0 width=178) + Output:["_col0"] + Filter Operator [FIL_87] (rows=2/0 width=178) + predicate:((value = 'd1value') and key is not null) + TableScan [TS_12] (rows=500/500 width=178) + default@src,d1,Tbl:COMPLETE,Col:COMPLETE,Output:["key","value"] + <-Reducer 8 [SIMPLE_EDGE] + SHUFFLE [RS_31] + PartitionCols:_col2 + Merge Join Operator [MERGEJOIN_92] (rows=40/0 width=352) + Conds:RS_28._col1=RS_29._col3(Inner),Output:["_col2","_col3","_col4","_col6"] + <-Map 12 [SIMPLE_EDGE] + SHUFFLE [RS_29] + PartitionCols:_col3 + Select Operator [SEL_11] (rows=8/0 width=531) + Output:["_col0","_col1","_col2","_col3","_col4"] + Filter Operator [FIL_86] (rows=8/0 width=534) + predicate:((v3 = 'ssv3') and k2 is not null and k3 is not null and k1 is not null and v1 is not null and v2 is not null) + TableScan [TS_9] (rows=85/85 width=534) + default@ss,ss,Tbl:COMPLETE,Col:COMPLETE,Output:["k1","v1","k2","v2","k3","v3"] + <-Map 7 [SIMPLE_EDGE] + SHUFFLE [RS_28] + PartitionCols:_col1 + Select Operator [SEL_8] (rows=10/0 width=185) + Output:["_col1"] + Filter Operator [FIL_85] (rows=10/0 width=178) + predicate:((key = 'srcpartkey') and value is not null) + TableScan [TS_6] (rows=2000/2000 width=178) + default@srcpart,srcpart,Tbl:COMPLETE,Col:COMPLETE,Output:["key","value"] + <-Reducer 16 [SIMPLE_EDGE] + SHUFFLE [RS_38] + PartitionCols:_col4, _col2 + Merge Join Operator [MERGEJOIN_95] (rows=19/0 width=356) + Conds:RS_24._col0=RS_25._col0(Inner),Output:["_col2","_col3","_col4","_col5"] + <-Map 15 [SIMPLE_EDGE] + SHUFFLE [RS_24] + PartitionCols:_col0 + Select Operator [SEL_20] (rows=8/0 width=531) + Output:["_col0","_col2","_col3","_col4","_col5"] + Filter Operator [FIL_89] (rows=8/0 width=534) + predicate:((v1 = 'srv1') and k2 is not null and k3 is not null and v2 is not null and v3 is not null and k1 is not null) + TableScan [TS_18] (rows=85/85 width=534) + default@sr,sr,Tbl:COMPLETE,Col:COMPLETE,Output:["k1","v1","k2","v2","k3","v3"] + <-Map 17 [SIMPLE_EDGE] + SHUFFLE [RS_25] + PartitionCols:_col0 + Select Operator [SEL_23] (rows=500/0 width=178) + Output:["_col0"] + Filter Operator [FIL_90] (rows=500/0 width=178) + predicate:((value) IN ('2000Q1', '2000Q2', '2000Q3') and key is not null) + TableScan [TS_21] (rows=500/500 width=178) + default@src,d2,Tbl:COMPLETE,Col:COMPLETE,Output:["key","value"] + <-Reducer 2 [SIMPLE_EDGE] + SHUFFLE [RS_44] + PartitionCols:_col1, _col3 + Merge Join Operator [MERGEJOIN_91] (rows=414/0 width=269) + Conds:RS_41._col0=RS_42._col0(Inner),Output:["_col1","_col2","_col3"] + <-Map 1 [SIMPLE_EDGE] + SHUFFLE [RS_41] + PartitionCols:_col0 + Select Operator [SEL_2] (rows=170/170 width=356) + Output:["_col0","_col1","_col2","_col3"] + Filter Operator [FIL_83] (rows=170/170 width=356) + predicate:(v2 is not null and v3 is not null and k1 is not null) + TableScan [TS_0] (rows=170/170 width=356) + default@cs,cs,Tbl:COMPLETE,Col:COMPLETE,Output:["k1","v2","k3","v3"] + <-Map 6 [SIMPLE_EDGE] + SHUFFLE [RS_42] + PartitionCols:_col0 + Select Operator [SEL_5] (rows=500/0 width=178) + Output:["_col0"] + Filter Operator [FIL_84] (rows=500/0 width=178) + predicate:((value) IN ('2000Q1', '2000Q2', '2000Q3') and key is not null) + TableScan [TS_3] (rows=500/500 width=178) + default@src,d3,Tbl:COMPLETE,Col:COMPLETE,Output:["key","value"] PREHOOK: query: SELECT x.key, z.value, y.value FROM src1 x JOIN src y ON (x.key = y.key) @@ -3424,15 +3426,11 @@ STAGE PLANS: expressions: value (type: string) outputColumnNames: _col1 Statistics: Num rows: 25/25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col1 (type: string) - outputColumnNames: _col1 + Reduce Output Operator + key expressions: _col1 (type: string) + sort order: + + Map-reduce partition columns: _col1 (type: string) Statistics: Num rows: 525/525 Data size: 5503 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: string) - sort order: + - Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 525/525 Data size: 5503 Basic stats: COMPLETE Column stats: NONE Map 11 Map Operator Tree: TableScan @@ -3445,15 +3443,11 @@ STAGE PLANS: expressions: value (type: string) outputColumnNames: _col1 Statistics: Num rows: 500/500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col1 (type: string) - outputColumnNames: _col1 + Reduce Output Operator + key expressions: _col1 (type: string) + sort order: + + Map-reduce partition columns: _col1 (type: string) Statistics: Num rows: 1025/1025 Data size: 10815 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: string) - sort order: + - Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 1025/1025 Data size: 10815 Basic stats: COMPLETE Column stats: NONE Map 12 Map Operator Tree: TableScan @@ -3466,15 +3460,11 @@ STAGE PLANS: expressions: value (type: string) outputColumnNames: _col1 Statistics: Num rows: 500/500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col1 (type: string) - outputColumnNames: _col1 + Reduce Output Operator + key expressions: _col1 (type: string) + sort order: + + Map-reduce partition columns: _col1 (type: string) Statistics: Num rows: 1025/1025 Data size: 10815 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: string) - sort order: + - Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 1025/1025 Data size: 10815 Basic stats: COMPLETE Column stats: NONE Map 13 Map Operator Tree: TableScan @@ -3515,49 +3505,45 @@ STAGE PLANS: expressions: value (type: string) outputColumnNames: _col1 Statistics: Num rows: 25/25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col1 (type: string) - outputColumnNames: _col1 - Statistics: Num rows: 1525/1525 Data size: 16127 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col1 (type: string) - 1 _col1 (type: string) - outputColumnNames: _col0, _col6 - input vertices: - 0 Map 20 + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col1 (type: string) + 1 _col1 (type: string) + outputColumnNames: _col0, _col6 + input vertices: + 0 Map 20 + Statistics: Num rows: 1677/820 Data size: 17739 Basic stats: COMPLETE Column stats: NONE + HybridGraceHashJoin: true + Select Operator + expressions: _col0 (type: string), _col6 (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 1677/820 Data size: 17739 Basic stats: COMPLETE Column stats: NONE - HybridGraceHashJoin: true - Select Operator - expressions: _col0 (type: string), _col6 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1677/820 Data size: 17739 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 3409/6411 Data size: 36062 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.a - File Output Operator - compressed: false - Statistics: Num rows: 3409/6411 Data size: 36062 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.b - File Output Operator - compressed: false - Statistics: Num rows: 3409/6411 Data size: 36062 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.c + File Output Operator + compressed: false + Statistics: Num rows: 3409/6411 Data size: 36062 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.a + File Output Operator + compressed: false + Statistics: Num rows: 3409/6411 Data size: 36062 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.b + File Output Operator + compressed: false + Statistics: Num rows: 3409/6411 Data size: 36062 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.c Map 17 Map Operator Tree: TableScan @@ -3570,49 +3556,45 @@ STAGE PLANS: expressions: value (type: string) outputColumnNames: _col1 Statistics: Num rows: 500/500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col1 (type: string) - outputColumnNames: _col1 - Statistics: Num rows: 1525/1525 Data size: 16127 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col1 (type: string) - 1 _col1 (type: string) - outputColumnNames: _col0, _col6 - input vertices: - 0 Map 20 + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col1 (type: string) + 1 _col1 (type: string) + outputColumnNames: _col0, _col6 + input vertices: + 0 Map 20 + Statistics: Num rows: 1677/820 Data size: 17739 Basic stats: COMPLETE Column stats: NONE + HybridGraceHashJoin: true + Select Operator + expressions: _col0 (type: string), _col6 (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 1677/820 Data size: 17739 Basic stats: COMPLETE Column stats: NONE - HybridGraceHashJoin: true - Select Operator - expressions: _col0 (type: string), _col6 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1677/820 Data size: 17739 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 3409/6411 Data size: 36062 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.a - File Output Operator - compressed: false - Statistics: Num rows: 3409/6411 Data size: 36062 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.b - File Output Operator - compressed: false - Statistics: Num rows: 3409/6411 Data size: 36062 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.c + File Output Operator + compressed: false + Statistics: Num rows: 3409/6411 Data size: 36062 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.a + File Output Operator + compressed: false + Statistics: Num rows: 3409/6411 Data size: 36062 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.b + File Output Operator + compressed: false + Statistics: Num rows: 3409/6411 Data size: 36062 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.c Map 18 Map Operator Tree: TableScan @@ -3625,49 +3607,45 @@ STAGE PLANS: expressions: value (type: string) outputColumnNames: _col1 Statistics: Num rows: 500/500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col1 (type: string) - outputColumnNames: _col1 - Statistics: Num rows: 1525/1525 Data size: 16127 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col1 (type: string) - 1 _col1 (type: string) - outputColumnNames: _col0, _col6 - input vertices: - 0 Map 20 + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col1 (type: string) + 1 _col1 (type: string) + outputColumnNames: _col0, _col6 + input vertices: + 0 Map 20 + Statistics: Num rows: 1677/820 Data size: 17739 Basic stats: COMPLETE Column stats: NONE + HybridGraceHashJoin: true + Select Operator + expressions: _col0 (type: string), _col6 (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 1677/820 Data size: 17739 Basic stats: COMPLETE Column stats: NONE - HybridGraceHashJoin: true - Select Operator - expressions: _col0 (type: string), _col6 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1677/820 Data size: 17739 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 3409/6411 Data size: 36062 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.a - File Output Operator - compressed: false - Statistics: Num rows: 3409/6411 Data size: 36062 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.b - File Output Operator - compressed: false - Statistics: Num rows: 3409/6411 Data size: 36062 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.c + File Output Operator + compressed: false + Statistics: Num rows: 3409/6411 Data size: 36062 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.a + File Output Operator + compressed: false + Statistics: Num rows: 3409/6411 Data size: 36062 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.b + File Output Operator + compressed: false + Statistics: Num rows: 3409/6411 Data size: 36062 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.c Map 19 Map Operator Tree: TableScan @@ -3680,49 +3658,45 @@ STAGE PLANS: expressions: value (type: string) outputColumnNames: _col1 Statistics: Num rows: 500/500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col1 (type: string) - outputColumnNames: _col1 - Statistics: Num rows: 1525/1525 Data size: 16127 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col1 (type: string) - 1 _col1 (type: string) - outputColumnNames: _col0, _col6 - input vertices: - 0 Map 20 + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col1 (type: string) + 1 _col1 (type: string) + outputColumnNames: _col0, _col6 + input vertices: + 0 Map 20 + Statistics: Num rows: 1677/820 Data size: 17739 Basic stats: COMPLETE Column stats: NONE + HybridGraceHashJoin: true + Select Operator + expressions: _col0 (type: string), _col6 (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 1677/820 Data size: 17739 Basic stats: COMPLETE Column stats: NONE - HybridGraceHashJoin: true - Select Operator - expressions: _col0 (type: string), _col6 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1677/820 Data size: 17739 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 3409/6411 Data size: 36062 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.a - File Output Operator - compressed: false - Statistics: Num rows: 3409/6411 Data size: 36062 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.b - File Output Operator - compressed: false - Statistics: Num rows: 3409/6411 Data size: 36062 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.c + File Output Operator + compressed: false + Statistics: Num rows: 3409/6411 Data size: 36062 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.a + File Output Operator + compressed: false + Statistics: Num rows: 3409/6411 Data size: 36062 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.b + File Output Operator + compressed: false + Statistics: Num rows: 3409/6411 Data size: 36062 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.c Map 20 Map Operator Tree: TableScan @@ -3792,15 +3766,11 @@ STAGE PLANS: expressions: value (type: string) outputColumnNames: _col1 Statistics: Num rows: 500/500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col1 (type: string) - outputColumnNames: _col1 + Reduce Output Operator + key expressions: _col1 (type: string) + sort order: + + Map-reduce partition columns: _col1 (type: string) Statistics: Num rows: 525/525 Data size: 5503 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: string) - sort order: + - Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 525/525 Data size: 5503 Basic stats: COMPLETE Column stats: NONE Map 6 Map Operator Tree: TableScan @@ -3852,15 +3822,11 @@ STAGE PLANS: expressions: value (type: string) outputColumnNames: _col1 Statistics: Num rows: 25/25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col1 (type: string) - outputColumnNames: _col1 + Reduce Output Operator + key expressions: _col1 (type: string) + sort order: + + Map-reduce partition columns: _col1 (type: string) Statistics: Num rows: 1025/1025 Data size: 10815 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: string) - sort order: + - Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 1025/1025 Data size: 10815 Basic stats: COMPLETE Column stats: NONE Reducer 10 Reduce Operator Tree: Merge Join Operator @@ -4666,15 +4632,15 @@ Stage-4 Dependency Collection{} Stage-2 Reducer 4 - File Output Operator [FS_20] + File Output Operator [FS_18] table:{"name:":"default.dest1"} - Group By Operator [GBY_18] (rows=1/310 width=96) + Group By Operator [GBY_16] (rows=1/310 width=96) Output:["_col0","_col1"],aggregations:["count(DISTINCT KEY._col1:0._col0)"],keys:KEY._col0 <-Union 3 [SIMPLE_EDGE] <-Map 6 [CONTAINS] - Reduce Output Operator [RS_17] + Reduce Output Operator [RS_15] PartitionCols:_col0 - Group By Operator [GBY_16] (rows=1/619 width=280) + Group By Operator [GBY_14] (rows=1/619 width=280) Output:["_col0","_col1","_col2"],aggregations:["count(DISTINCT substr(_col1, 5))"],keys:_col0, substr(_col1, 5) Select Operator [SEL_9] (rows=501/501 width=272) Output:["_col0","_col1"] @@ -4682,29 +4648,29 @@ Stage-4 Output:["_col0","_col1"] TableScan [TS_6] (rows=500/500 width=10) Output:["key","value"] - Reduce Output Operator [RS_23] + Reduce Output Operator [RS_21] PartitionCols:_col0, _col1 - Group By Operator [GBY_22] (rows=1/619 width=464) + Group By Operator [GBY_20] (rows=1/619 width=464) Output:["_col0","_col1","_col2","_col3"],aggregations:["count(DISTINCT substr(_col1, 5))"],keys:_col0, _col1, substr(_col1, 5) Please refer to the previous Select Operator [SEL_9] <-Map 7 [CONTAINS] - Reduce Output Operator [RS_17] + Reduce Output Operator [RS_15] PartitionCols:_col0 - Group By Operator [GBY_16] (rows=1/619 width=280) + Group By Operator [GBY_14] (rows=1/619 width=280) Output:["_col0","_col1","_col2"],aggregations:["count(DISTINCT substr(_col1, 5))"],keys:_col0, substr(_col1, 5) - Select Operator [SEL_12] (rows=500/500 width=10) + Select Operator [SEL_11] (rows=500/500 width=10) Output:["_col0","_col1"] - TableScan [TS_11] (rows=500/500 width=10) + TableScan [TS_10] (rows=500/500 width=10) Output:["key","value"] - Reduce Output Operator [RS_23] + Reduce Output Operator [RS_21] PartitionCols:_col0, _col1 - Group By Operator [GBY_22] (rows=1/619 width=464) + Group By Operator [GBY_20] (rows=1/619 width=464) Output:["_col0","_col1","_col2","_col3"],aggregations:["count(DISTINCT substr(_col1, 5))"],keys:_col0, _col1, substr(_col1, 5) - Please refer to the previous Select Operator [SEL_12] + Please refer to the previous Select Operator [SEL_11] <-Reducer 2 [CONTAINS] - Reduce Output Operator [RS_17] + Reduce Output Operator [RS_15] PartitionCols:_col0 - Group By Operator [GBY_16] (rows=1/619 width=280) + Group By Operator [GBY_14] (rows=1/619 width=280) Output:["_col0","_col1","_col2"],aggregations:["count(DISTINCT substr(_col1, 5))"],keys:_col0, substr(_col1, 5) Select Operator [SEL_9] (rows=501/501 width=272) Output:["_col0","_col1"] @@ -4719,15 +4685,15 @@ Stage-4 Select Operator [SEL_1] (rows=500/500 width=10) TableScan [TS_0] (rows=500/500 width=10) default@src,s1,Tbl:COMPLETE,Col:COMPLETE - Reduce Output Operator [RS_23] + Reduce Output Operator [RS_21] PartitionCols:_col0, _col1 - Group By Operator [GBY_22] (rows=1/619 width=464) + Group By Operator [GBY_20] (rows=1/619 width=464) Output:["_col0","_col1","_col2","_col3"],aggregations:["count(DISTINCT substr(_col1, 5))"],keys:_col0, _col1, substr(_col1, 5) Please refer to the previous Select Operator [SEL_9] Reducer 5 - File Output Operator [FS_26] + File Output Operator [FS_24] table:{"name:":"default.dest2"} - Group By Operator [GBY_24] (rows=1/310 width=280) + Group By Operator [GBY_22] (rows=1/310 width=280) Output:["_col0","_col1","_col2"],aggregations:["count(DISTINCT KEY._col2:0._col0)"],keys:KEY._col0, KEY._col1 <- Please refer to the previous Union 3 [SIMPLE_EDGE] Stage-5 @@ -4798,15 +4764,15 @@ Stage-4 Dependency Collection{} Stage-2 Reducer 4 - File Output Operator [FS_15] + File Output Operator [FS_14] table:{"name:":"default.dest1"} - Group By Operator [GBY_13] (rows=1/310 width=96) + Group By Operator [GBY_12] (rows=1/310 width=96) Output:["_col0","_col1"],aggregations:["count(DISTINCT KEY._col1:0._col0)"],keys:KEY._col0 <-Union 3 [SIMPLE_EDGE] <-Map 6 [CONTAINS] - Reduce Output Operator [RS_12] + Reduce Output Operator [RS_11] PartitionCols:_col0 - Group By Operator [GBY_11] (rows=1/310 width=280) + Group By Operator [GBY_10] (rows=1/310 width=280) Output:["_col0","_col1","_col2"],aggregations:["count(DISTINCT substr(_col1, 5))"],keys:_col0, substr(_col1, 5) Select Operator [SEL_9] (rows=501/501 width=11) Output:["_col0","_col1"] @@ -4814,15 +4780,17 @@ Stage-4 Output:["_col0","_col1"] TableScan [TS_6] (rows=500/500 width=10) Output:["key","value"] - Reduce Output Operator [RS_18] + Reduce Output Operator [RS_17] PartitionCols:_col0, _col1 - Group By Operator [GBY_17] (rows=1/310 width=464) + Group By Operator [GBY_16] (rows=1/310 width=464) Output:["_col0","_col1","_col2","_col3"],aggregations:["count(DISTINCT substr(_col1, 5))"],keys:_col0, _col1, substr(_col1, 5) - Please refer to the previous Select Operator [SEL_9] + Select Operator [SEL_15] (rows=501/501 width=11) + Output:["_col0","_col1"] + Please refer to the previous Select Operator [SEL_7] <-Reducer 2 [CONTAINS] - Reduce Output Operator [RS_12] + Reduce Output Operator [RS_11] PartitionCols:_col0 - Group By Operator [GBY_11] (rows=1/310 width=280) + Group By Operator [GBY_10] (rows=1/310 width=280) Output:["_col0","_col1","_col2"],aggregations:["count(DISTINCT substr(_col1, 5))"],keys:_col0, substr(_col1, 5) Select Operator [SEL_9] (rows=501/501 width=11) Output:["_col0","_col1"] @@ -4837,15 +4805,17 @@ Stage-4 Select Operator [SEL_1] (rows=500/500 width=10) TableScan [TS_0] (rows=500/500 width=10) default@src,s1,Tbl:COMPLETE,Col:COMPLETE - Reduce Output Operator [RS_18] + Reduce Output Operator [RS_17] PartitionCols:_col0, _col1 - Group By Operator [GBY_17] (rows=1/310 width=464) + Group By Operator [GBY_16] (rows=1/310 width=464) Output:["_col0","_col1","_col2","_col3"],aggregations:["count(DISTINCT substr(_col1, 5))"],keys:_col0, _col1, substr(_col1, 5) - Please refer to the previous Select Operator [SEL_9] + Select Operator [SEL_15] (rows=501/501 width=11) + Output:["_col0","_col1"] + Please refer to the previous Select Operator [SEL_5] Reducer 5 - File Output Operator [FS_21] + File Output Operator [FS_20] table:{"name:":"default.dest2"} - Group By Operator [GBY_19] (rows=1/310 width=280) + Group By Operator [GBY_18] (rows=1/310 width=280) Output:["_col0","_col1","_col2"],aggregations:["count(DISTINCT KEY._col2:0._col0)"],keys:KEY._col0, KEY._col1 <- Please refer to the previous Union 3 [SIMPLE_EDGE] Stage-5