http://git-wip-us.apache.org/repos/asf/hive/blob/a37827ec/ql/src/test/results/clientpositive/llap/mapjoin46.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/llap/mapjoin46.q.out b/ql/src/test/results/clientpositive/llap/mapjoin46.q.out index 52eb609..d0d9c87 100644 --- a/ql/src/test/results/clientpositive/llap/mapjoin46.q.out +++ b/ql/src/test/results/clientpositive/llap/mapjoin46.q.out @@ -128,14 +128,14 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@test1_n4 POSTHOOK: Input: default@test2_n2 #### A masked pattern was here #### -NULL NULL None NULL NULL NULL +100 1 Bob NULL NULL NULL +101 2 Car 102 2 Del +101 2 Car 103 2 Ema 98 NULL None NULL NULL NULL 99 0 Alice NULL NULL NULL 99 2 Mat 102 2 Del 99 2 Mat 103 2 Ema -100 1 Bob NULL NULL NULL -101 2 Car 102 2 Del -101 2 Car 103 2 Ema +NULL NULL None NULL NULL NULL PREHOOK: query: EXPLAIN SELECT * FROM test1_n4 LEFT OUTER JOIN test2_n2 @@ -239,12 +239,12 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@test1_n4 POSTHOOK: Input: default@test2_n2 #### A masked pattern was here #### -NULL NULL None NULL NULL NULL +100 1 Bob NULL NULL NULL +101 2 Car 102 2 Del 98 NULL None NULL NULL NULL 99 0 Alice NULL NULL NULL 99 2 Mat NULL NULL NULL -100 1 Bob NULL NULL NULL -101 2 Car 102 2 Del +NULL NULL None NULL NULL NULL Warning: Map Join MAPJOIN[11][bigTable=?] in task 'Map 1' is a cross product PREHOOK: query: EXPLAIN SELECT * @@ -344,12 +344,12 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@test1_n4 POSTHOOK: Input: default@test2_n2 #### A masked pattern was here #### -NULL NULL None NULL NULL NULL +100 1 Bob 102 2 Del +101 2 Car 102 2 Del 98 NULL None NULL NULL NULL 99 0 Alice NULL NULL NULL 99 2 Mat NULL NULL NULL -100 1 Bob 102 2 Del -101 2 Car 102 2 Del +NULL NULL None NULL NULL NULL PREHOOK: query: EXPLAIN SELECT * FROM test1_n4 RIGHT OUTER JOIN test2_n2 @@ -438,10 +438,10 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@test1_n4 POSTHOOK: Input: default@test2_n2 #### A masked pattern was here #### -99 2 Mat 102 2 Del 101 2 Car 102 2 Del -99 2 Mat 103 2 Ema 101 2 Car 103 2 Ema +99 2 Mat 102 2 Del +99 2 Mat 103 2 Ema NULL NULL NULL 104 3 Fli NULL NULL NULL 105 NULL None Warning: Map Join MAPJOIN[9][bigTable=?] in task 'Map 1' is a cross product @@ -535,18 +535,18 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@test1_n4 POSTHOOK: Input: default@test2_n2 #### A masked pattern was here #### -NULL NULL None NULL NULL NULL -98 NULL None NULL NULL NULL -99 0 Alice NULL NULL NULL -99 2 Mat NULL NULL NULL 100 1 Bob 102 2 Del -100 1 Bob 105 NULL None -100 1 Bob 104 3 Fli 100 1 Bob 103 2 Ema +100 1 Bob 104 3 Fli +100 1 Bob 105 NULL None 101 2 Car 102 2 Del -101 2 Car 105 NULL None -101 2 Car 104 3 Fli 101 2 Car 103 2 Ema +101 2 Car 104 3 Fli +101 2 Car 105 NULL None +98 NULL None NULL NULL NULL +99 0 Alice NULL NULL NULL +99 2 Mat NULL NULL NULL +NULL NULL None NULL NULL NULL Warning: Map Join MAPJOIN[9][bigTable=?] in task 'Map 1' is a cross product PREHOOK: query: EXPLAIN SELECT * @@ -644,19 +644,19 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@test1_n4 POSTHOOK: Input: default@test2_n2 #### A masked pattern was here #### -NULL NULL None 102 2 Del -98 NULL None 102 2 Del -99 0 Alice 102 2 Del -99 2 Mat 102 2 Del -99 2 Mat 103 2 Ema 100 1 Bob 102 2 Del -100 1 Bob 105 NULL None -100 1 Bob 104 3 Fli 100 1 Bob 103 2 Ema +100 1 Bob 104 3 Fli +100 1 Bob 105 NULL None 101 2 Car 102 2 Del -101 2 Car 105 NULL None -101 2 Car 104 3 Fli 101 2 Car 103 2 Ema +101 2 Car 104 3 Fli +101 2 Car 105 NULL None +98 NULL None 102 2 Del +99 0 Alice 102 2 Del +99 2 Mat 102 2 Del +99 2 Mat 103 2 Ema +NULL NULL None 102 2 Del Warning: Map Join MAPJOIN[9][bigTable=?] in task 'Map 1' is a cross product PREHOOK: query: EXPLAIN SELECT * @@ -750,19 +750,19 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@test1_n4 POSTHOOK: Input: default@test2_n2 #### A masked pattern was here #### -NULL NULL None NULL NULL NULL -98 NULL None NULL NULL NULL -99 0 Alice NULL NULL NULL -99 2 Mat 102 2 Del -99 2 Mat 103 2 Ema 100 1 Bob 102 2 Del -100 1 Bob 105 NULL None -100 1 Bob 104 3 Fli 100 1 Bob 103 2 Ema +100 1 Bob 104 3 Fli +100 1 Bob 105 NULL None 101 2 Car 102 2 Del -101 2 Car 105 NULL None -101 2 Car 104 3 Fli 101 2 Car 103 2 Ema +101 2 Car 104 3 Fli +101 2 Car 105 NULL None +98 NULL None NULL NULL NULL +99 0 Alice NULL NULL NULL +99 2 Mat 102 2 Del +99 2 Mat 103 2 Ema +NULL NULL None NULL NULL NULL Warning: Map Join MAPJOIN[9][bigTable=?] in task 'Map 1' is a cross product PREHOOK: query: EXPLAIN SELECT * @@ -856,14 +856,14 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@test1_n4 POSTHOOK: Input: default@test2_n2 #### A masked pattern was here #### -NULL NULL None 102 2 Del +100 1 Bob 102 2 Del +101 2 Car 102 2 Del +101 2 Car 103 2 Ema 98 NULL None 102 2 Del 99 0 Alice 102 2 Del 99 2 Mat 102 2 Del 99 2 Mat 103 2 Ema -100 1 Bob 102 2 Del -101 2 Car 102 2 Del -101 2 Car 103 2 Ema +NULL NULL None 102 2 Del PREHOOK: query: EXPLAIN SELECT * FROM test1_n4 LEFT OUTER JOIN test2_n2 @@ -961,13 +961,13 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@test1_n4 POSTHOOK: Input: default@test2_n2 #### A masked pattern was here #### -NULL NULL None NULL NULL NULL -98 NULL None NULL NULL NULL -99 0 Alice NULL NULL NULL -99 2 Mat 102 2 Del 100 1 Bob NULL NULL NULL 101 2 Car 102 2 Del 101 2 Car 103 2 Ema +98 NULL None NULL NULL NULL +99 0 Alice NULL NULL NULL +99 2 Mat 102 2 Del +NULL NULL None NULL NULL NULL Warning: Map Join MAPJOIN[9][bigTable=?] in task 'Map 2' is a cross product PREHOOK: query: EXPLAIN SELECT * @@ -1065,19 +1065,19 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@test1_n4 POSTHOOK: Input: default@test2_n2 #### A masked pattern was here #### -NULL NULL None 102 2 Del -101 2 Car 102 2 Del 100 1 Bob 102 2 Del -99 2 Mat 102 2 Del -99 0 Alice 102 2 Del -98 NULL None 102 2 Del -101 2 Car 103 2 Ema 100 1 Bob 103 2 Ema -99 2 Mat 103 2 Ema -101 2 Car 104 3 Fli 100 1 Bob 104 3 Fli -101 2 Car 105 NULL None 100 1 Bob 105 NULL None +101 2 Car 102 2 Del +101 2 Car 103 2 Ema +101 2 Car 104 3 Fli +101 2 Car 105 NULL None +98 NULL None 102 2 Del +99 0 Alice 102 2 Del +99 2 Mat 102 2 Del +99 2 Mat 103 2 Ema +NULL NULL None 102 2 Del Warning: Map Join MAPJOIN[9][bigTable=?] in task 'Map 2' is a cross product PREHOOK: query: EXPLAIN SELECT * @@ -1171,16 +1171,16 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@test1_n4 POSTHOOK: Input: default@test2_n2 #### A masked pattern was here #### -101 2 Car 102 2 Del 100 1 Bob 102 2 Del -99 2 Mat 102 2 Del -101 2 Car 103 2 Ema 100 1 Bob 103 2 Ema -99 2 Mat 103 2 Ema -101 2 Car 104 3 Fli 100 1 Bob 104 3 Fli -101 2 Car 105 NULL None 100 1 Bob 105 NULL None +101 2 Car 102 2 Del +101 2 Car 103 2 Ema +101 2 Car 104 3 Fli +101 2 Car 105 NULL None +99 2 Mat 102 2 Del +99 2 Mat 103 2 Ema Warning: Map Join MAPJOIN[9][bigTable=?] in task 'Map 2' is a cross product PREHOOK: query: EXPLAIN SELECT * @@ -1274,16 +1274,16 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@test1_n4 POSTHOOK: Input: default@test2_n2 #### A masked pattern was here #### -NULL NULL None 102 2 Del -101 2 Car 102 2 Del 100 1 Bob 102 2 Del -99 2 Mat 102 2 Del -99 0 Alice 102 2 Del -98 NULL None 102 2 Del +101 2 Car 102 2 Del 101 2 Car 103 2 Ema +98 NULL None 102 2 Del +99 0 Alice 102 2 Del +99 2 Mat 102 2 Del 99 2 Mat 103 2 Ema NULL NULL NULL 104 3 Fli NULL NULL NULL 105 NULL None +NULL NULL None 102 2 Del PREHOOK: query: EXPLAIN SELECT * FROM test1_n4 RIGHT OUTER JOIN test2_n2 @@ -1381,9 +1381,9 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@test1_n4 POSTHOOK: Input: default@test2_n2 #### A masked pattern was here #### -99 2 Mat 102 2 Del 101 2 Car 102 2 Del 101 2 Car 103 2 Ema +99 2 Mat 102 2 Del NULL NULL NULL 104 3 Fli NULL NULL NULL 105 NULL None Warning: Shuffle Join MERGEJOIN[9][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product @@ -1448,7 +1448,7 @@ STAGE PLANS: Reduce Operator Tree: Merge Join Operator condition map: - Outer Join 0 to 1 + Full Outer Join 0 to 1 keys: 0 1 @@ -1488,11 +1488,6 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@test1_n4 POSTHOOK: Input: default@test2_n2 #### A masked pattern was here #### -NULL NULL None 102 2 Del -98 NULL None 102 2 Del -99 0 Alice 102 2 Del -99 2 Mat 102 2 Del -99 2 Mat 103 2 Ema 100 1 Bob 102 2 Del 100 1 Bob 103 2 Ema 100 1 Bob 104 3 Fli @@ -1501,18 +1496,25 @@ NULL NULL None 102 2 Del 101 2 Car 103 2 Ema 101 2 Car 104 3 Fli 101 2 Car 105 NULL None +98 NULL None 102 2 Del +99 0 Alice 102 2 Del +99 2 Mat 102 2 Del +99 2 Mat 103 2 Ema +NULL NULL None 102 2 Del Warning: Shuffle Join MERGEJOIN[9][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product PREHOOK: query: EXPLAIN SELECT * FROM test1_n4 FULL OUTER JOIN test2_n2 ON (test1_n4.value=test2_n2.value - OR test1_n4.key between 100 and 102) + OR test1_n4.key between 100 and 102 + OR test2_n2.key between 100 and 102) PREHOOK: type: QUERY POSTHOOK: query: EXPLAIN SELECT * FROM test1_n4 FULL OUTER JOIN test2_n2 ON (test1_n4.value=test2_n2.value - OR test1_n4.key between 100 and 102) + OR test1_n4.key between 100 and 102 + OR test2_n2.key between 100 and 102) POSTHOOK: type: QUERY STAGE DEPENDENCIES: Stage-1 is a root stage @@ -1561,12 +1563,12 @@ STAGE PLANS: Reduce Operator Tree: Merge Join Operator condition map: - Outer Join 0 to 1 + Full Outer Join 0 to 1 keys: 0 1 outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - residual filter predicates: {((_col1 = _col4) or _col0 BETWEEN 100 AND 102)} + residual filter predicates: {((_col1 = _col4) or _col0 BETWEEN 100 AND 102 or _col3 BETWEEN 100 AND 102)} Statistics: Num rows: 24 Data size: 4580 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false @@ -1586,7 +1588,8 @@ Warning: Shuffle Join MERGEJOIN[9][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reduce PREHOOK: query: SELECT * FROM test1_n4 FULL OUTER JOIN test2_n2 ON (test1_n4.value=test2_n2.value - OR test1_n4.key between 100 and 102) + OR test1_n4.key between 100 and 102 + OR test2_n2.key between 100 and 102) PREHOOK: type: QUERY PREHOOK: Input: default@test1_n4 PREHOOK: Input: default@test2_n2 @@ -1594,16 +1597,12 @@ PREHOOK: Input: default@test2_n2 POSTHOOK: query: SELECT * FROM test1_n4 FULL OUTER JOIN test2_n2 ON (test1_n4.value=test2_n2.value - OR test1_n4.key between 100 and 102) + OR test1_n4.key between 100 and 102 + OR test2_n2.key between 100 and 102) POSTHOOK: type: QUERY POSTHOOK: Input: default@test1_n4 POSTHOOK: Input: default@test2_n2 #### A masked pattern was here #### -NULL NULL None NULL NULL NULL -98 NULL None NULL NULL NULL -99 0 Alice NULL NULL NULL -99 2 Mat 102 2 Del -99 2 Mat 103 2 Ema 100 1 Bob 102 2 Del 100 1 Bob 103 2 Ema 100 1 Bob 104 3 Fli @@ -1612,18 +1611,23 @@ NULL NULL None NULL NULL NULL 101 2 Car 103 2 Ema 101 2 Car 104 3 Fli 101 2 Car 105 NULL None +98 NULL None 102 2 Del +99 0 Alice 102 2 Del +99 2 Mat 102 2 Del +99 2 Mat 103 2 Ema +NULL NULL None 102 2 Del Warning: Shuffle Join MERGEJOIN[9][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product PREHOOK: query: EXPLAIN SELECT * FROM test1_n4 FULL OUTER JOIN test2_n2 ON (test1_n4.value=test2_n2.value - OR test2_n2.key between 100 and 102) + OR test1_n4.key between 100 and 102) PREHOOK: type: QUERY POSTHOOK: query: EXPLAIN SELECT * FROM test1_n4 FULL OUTER JOIN test2_n2 ON (test1_n4.value=test2_n2.value - OR test2_n2.key between 100 and 102) + OR test1_n4.key between 100 and 102) POSTHOOK: type: QUERY STAGE DEPENDENCIES: Stage-1 is a root stage @@ -1672,12 +1676,12 @@ STAGE PLANS: Reduce Operator Tree: Merge Join Operator condition map: - Outer Join 0 to 1 + Full Outer Join 0 to 1 keys: 0 1 outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - residual filter predicates: {((_col1 = _col4) or _col3 BETWEEN 100 AND 102)} + residual filter predicates: {((_col1 = _col4) or _col0 BETWEEN 100 AND 102)} Statistics: Num rows: 24 Data size: 4580 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false @@ -1697,7 +1701,7 @@ Warning: Shuffle Join MERGEJOIN[9][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reduce PREHOOK: query: SELECT * FROM test1_n4 FULL OUTER JOIN test2_n2 ON (test1_n4.value=test2_n2.value - OR test2_n2.key between 100 and 102) + OR test1_n4.key between 100 and 102) PREHOOK: type: QUERY PREHOOK: Input: default@test1_n4 PREHOOK: Input: default@test2_n2 @@ -1705,34 +1709,36 @@ PREHOOK: Input: default@test2_n2 POSTHOOK: query: SELECT * FROM test1_n4 FULL OUTER JOIN test2_n2 ON (test1_n4.value=test2_n2.value - OR test2_n2.key between 100 and 102) + OR test1_n4.key between 100 and 102) POSTHOOK: type: QUERY POSTHOOK: Input: default@test1_n4 POSTHOOK: Input: default@test2_n2 #### A masked pattern was here #### -NULL NULL None 102 2 Del -98 NULL None 102 2 Del -99 0 Alice 102 2 Del -99 2 Mat 102 2 Del -99 2 Mat 103 2 Ema 100 1 Bob 102 2 Del +100 1 Bob 103 2 Ema +100 1 Bob 104 3 Fli +100 1 Bob 105 NULL None 101 2 Car 102 2 Del 101 2 Car 103 2 Ema -NULL NULL NULL 104 3 Fli -NULL NULL NULL 105 NULL None +101 2 Car 104 3 Fli +101 2 Car 105 NULL None +98 NULL None NULL NULL NULL +99 0 Alice NULL NULL NULL +99 2 Mat 102 2 Del +99 2 Mat 103 2 Ema +NULL NULL None NULL NULL NULL +Warning: Shuffle Join MERGEJOIN[9][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product PREHOOK: query: EXPLAIN SELECT * FROM test1_n4 FULL OUTER JOIN test2_n2 ON (test1_n4.value=test2_n2.value - AND (test1_n4.key between 100 and 102 - OR test2_n2.key between 100 and 102)) + OR test1_n4.key between 100 and 102) PREHOOK: type: QUERY POSTHOOK: query: EXPLAIN SELECT * FROM test1_n4 FULL OUTER JOIN test2_n2 ON (test1_n4.value=test2_n2.value - AND (test1_n4.key between 100 and 102 - OR test2_n2.key between 100 and 102)) + OR test1_n4.key between 100 and 102) POSTHOOK: type: QUERY STAGE DEPENDENCIES: Stage-1 is a root stage @@ -1743,7 +1749,7 @@ STAGE PLANS: Tez #### A masked pattern was here #### Edges: - Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 3 (SIMPLE_EDGE) + Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE), Map 3 (CUSTOM_SIMPLE_EDGE) #### A masked pattern was here #### Vertices: Map 1 @@ -1756,11 +1762,9 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator - key expressions: _col1 (type: int) - sort order: + - Map-reduce partition columns: _col1 (type: int) + sort order: Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: int), _col2 (type: string) + value expressions: _col0 (type: int), _col1 (type: int), _col2 (type: string) Execution mode: llap LLAP IO: no inputs Map 3 @@ -1773,11 +1777,9 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 4 Data size: 380 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator - key expressions: _col1 (type: int) - sort order: + - Map-reduce partition columns: _col1 (type: int) + sort order: Statistics: Num rows: 4 Data size: 380 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: int), _col2 (type: string) + value expressions: _col0 (type: int), _col1 (type: int), _col2 (type: string) Execution mode: llap LLAP IO: no inputs Reducer 2 @@ -1785,16 +1787,16 @@ STAGE PLANS: Reduce Operator Tree: Merge Join Operator condition map: - Outer Join 0 to 1 + Full Outer Join 0 to 1 keys: - 0 _col1 (type: int) - 1 _col1 (type: int) + 0 + 1 outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - residual filter predicates: {(_col0 BETWEEN 100 AND 102 or _col3 BETWEEN 100 AND 102)} - Statistics: Num rows: 10 Data size: 191 Basic stats: COMPLETE Column stats: COMPLETE + residual filter predicates: {((_col1 = _col4) or _col0 BETWEEN 100 AND 102)} + Statistics: Num rows: 24 Data size: 4580 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 10 Data size: 191 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 24 Data size: 4580 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1806,11 +1808,11 @@ STAGE PLANS: Processor Tree: ListSink +Warning: Shuffle Join MERGEJOIN[9][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product PREHOOK: query: SELECT * FROM test1_n4 FULL OUTER JOIN test2_n2 ON (test1_n4.value=test2_n2.value - AND (test1_n4.key between 100 and 102 - OR test2_n2.key between 100 and 102)) + OR test1_n4.key between 100 and 102) PREHOOK: type: QUERY PREHOOK: Input: default@test1_n4 PREHOOK: Input: default@test2_n2 @@ -1818,29 +1820,474 @@ PREHOOK: Input: default@test2_n2 POSTHOOK: query: SELECT * FROM test1_n4 FULL OUTER JOIN test2_n2 ON (test1_n4.value=test2_n2.value - AND (test1_n4.key between 100 and 102 - OR test2_n2.key between 100 and 102)) + OR test1_n4.key between 100 and 102) POSTHOOK: type: QUERY POSTHOOK: Input: default@test1_n4 POSTHOOK: Input: default@test2_n2 #### A masked pattern was here #### -NULL NULL NULL 105 NULL None -NULL NULL None NULL NULL NULL +100 1 Bob 102 2 Del +100 1 Bob 103 2 Ema +100 1 Bob 104 3 Fli +100 1 Bob 105 NULL None +101 2 Car 102 2 Del +101 2 Car 103 2 Ema +101 2 Car 104 3 Fli +101 2 Car 105 NULL None 98 NULL None NULL NULL NULL 99 0 Alice NULL NULL NULL -100 1 Bob NULL NULL NULL 99 2 Mat 102 2 Del -101 2 Car 102 2 Del -101 2 Car 103 2 Ema -NULL NULL NULL 104 3 Fli -Warning: Shuffle Join MERGEJOIN[36][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Reducer 2' is a cross product +99 2 Mat 103 2 Ema +NULL NULL None NULL NULL NULL +Warning: Shuffle Join MERGEJOIN[9][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product PREHOOK: query: EXPLAIN SELECT * -FROM ( - SELECT test1_n4.key AS key1, test1_n4.value AS value1, test1_n4.col_1 AS col_1, - test2_n2.key AS key2, test2_n2.value AS value2, test2_n2.col_2 AS col_2 - FROM test1_n4 RIGHT OUTER JOIN test2_n2 - ON (test1_n4.value=test2_n2.value +FROM test1_n4 FULL OUTER JOIN test2_n2 +ON (test1_n4.value=test2_n2.value + OR test2_n2.key between 100 and 102) +PREHOOK: type: QUERY +POSTHOOK: query: EXPLAIN +SELECT * +FROM test1_n4 FULL OUTER JOIN test2_n2 +ON (test1_n4.value=test2_n2.value + OR test2_n2.key between 100 and 102) +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE), Map 3 (CUSTOM_SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: test1_n4 + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: int), value (type: int), col_1 (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + sort order: + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: int), _col1 (type: int), _col2 (type: string) + Execution mode: llap + LLAP IO: no inputs + Map 3 + Map Operator Tree: + TableScan + alias: test2_n2 + Statistics: Num rows: 4 Data size: 380 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: int), value (type: int), col_2 (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 4 Data size: 380 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + sort order: + Statistics: Num rows: 4 Data size: 380 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: int), _col1 (type: int), _col2 (type: string) + Execution mode: llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Full Outer Join 0 to 1 + keys: + 0 + 1 + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + residual filter predicates: {((_col1 = _col4) or _col3 BETWEEN 100 AND 102)} + Statistics: Num rows: 24 Data size: 4580 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 24 Data size: 4580 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 + limit: -1 + Processor Tree: + ListSink + +Warning: Shuffle Join MERGEJOIN[9][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product +PREHOOK: query: SELECT * +FROM test1_n4 FULL OUTER JOIN test2_n2 +ON (test1_n4.value=test2_n2.value + OR test2_n2.key between 100 and 102) +PREHOOK: type: QUERY +PREHOOK: Input: default@test1_n4 +PREHOOK: Input: default@test2_n2 +#### A masked pattern was here #### +POSTHOOK: query: SELECT * +FROM test1_n4 FULL OUTER JOIN test2_n2 +ON (test1_n4.value=test2_n2.value + OR test2_n2.key between 100 and 102) +POSTHOOK: type: QUERY +POSTHOOK: Input: default@test1_n4 +POSTHOOK: Input: default@test2_n2 +#### A masked pattern was here #### +100 1 Bob 102 2 Del +101 2 Car 102 2 Del +101 2 Car 103 2 Ema +98 NULL None 102 2 Del +99 0 Alice 102 2 Del +99 2 Mat 102 2 Del +99 2 Mat 103 2 Ema +NULL NULL NULL 104 3 Fli +NULL NULL NULL 105 NULL None +NULL NULL None 102 2 Del +Warning: Shuffle Join MERGEJOIN[9][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product +PREHOOK: query: EXPLAIN +SELECT * +FROM test1_n4 FULL OUTER JOIN test2_n2 +ON (test1_n4.value=test2_n2.value + OR test2_n2.key between 100 and 102) +PREHOOK: type: QUERY +POSTHOOK: query: EXPLAIN +SELECT * +FROM test1_n4 FULL OUTER JOIN test2_n2 +ON (test1_n4.value=test2_n2.value + OR test2_n2.key between 100 and 102) +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE), Map 3 (CUSTOM_SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: test1_n4 + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: int), value (type: int), col_1 (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + sort order: + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: int), _col1 (type: int), _col2 (type: string) + Execution mode: llap + LLAP IO: no inputs + Map 3 + Map Operator Tree: + TableScan + alias: test2_n2 + Statistics: Num rows: 4 Data size: 380 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: int), value (type: int), col_2 (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 4 Data size: 380 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + sort order: + Statistics: Num rows: 4 Data size: 380 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: int), _col1 (type: int), _col2 (type: string) + Execution mode: llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Full Outer Join 0 to 1 + keys: + 0 + 1 + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + residual filter predicates: {((_col1 = _col4) or _col3 BETWEEN 100 AND 102)} + Statistics: Num rows: 24 Data size: 4580 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 24 Data size: 4580 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 + limit: -1 + Processor Tree: + ListSink + +Warning: Shuffle Join MERGEJOIN[9][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product +PREHOOK: query: SELECT * +FROM test1_n4 FULL OUTER JOIN test2_n2 +ON (test1_n4.value=test2_n2.value + OR test2_n2.key between 100 and 102) +PREHOOK: type: QUERY +PREHOOK: Input: default@test1_n4 +PREHOOK: Input: default@test2_n2 +#### A masked pattern was here #### +POSTHOOK: query: SELECT * +FROM test1_n4 FULL OUTER JOIN test2_n2 +ON (test1_n4.value=test2_n2.value + OR test2_n2.key between 100 and 102) +POSTHOOK: type: QUERY +POSTHOOK: Input: default@test1_n4 +POSTHOOK: Input: default@test2_n2 +#### A masked pattern was here #### +100 1 Bob 102 2 Del +101 2 Car 102 2 Del +101 2 Car 103 2 Ema +98 NULL None 102 2 Del +99 0 Alice 102 2 Del +99 2 Mat 102 2 Del +99 2 Mat 103 2 Ema +NULL NULL NULL 104 3 Fli +NULL NULL NULL 105 NULL None +NULL NULL None 102 2 Del +PREHOOK: query: EXPLAIN +SELECT * +FROM test1_n4 FULL OUTER JOIN test2_n2 +ON (test1_n4.value=test2_n2.value + AND (test1_n4.key between 100 and 102 + OR test2_n2.key between 100 and 102)) +PREHOOK: type: QUERY +POSTHOOK: query: EXPLAIN +SELECT * +FROM test1_n4 FULL OUTER JOIN test2_n2 +ON (test1_n4.value=test2_n2.value + AND (test1_n4.key between 100 and 102 + OR test2_n2.key between 100 and 102)) +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +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: test1_n4 + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: int), value (type: int), col_1 (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col1 (type: int) + sort order: + + Map-reduce partition columns: _col1 (type: int) + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: int), _col2 (type: string) + Execution mode: llap + LLAP IO: no inputs + Map 3 + Map Operator Tree: + TableScan + alias: test2_n2 + Statistics: Num rows: 4 Data size: 380 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: int), value (type: int), col_2 (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 4 Data size: 380 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col1 (type: int) + sort order: + + Map-reduce partition columns: _col1 (type: int) + Statistics: Num rows: 4 Data size: 380 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: int), _col2 (type: string) + Execution mode: llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Full Outer Join 0 to 1 + keys: + 0 _col1 (type: int) + 1 _col1 (type: int) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + residual filter predicates: {(_col0 BETWEEN 100 AND 102 or _col3 BETWEEN 100 AND 102)} + Statistics: Num rows: 10 Data size: 191 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 10 Data size: 191 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 + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: SELECT * +FROM test1_n4 FULL OUTER JOIN test2_n2 +ON (test1_n4.value=test2_n2.value + AND (test1_n4.key between 100 and 102 + OR test2_n2.key between 100 and 102)) +PREHOOK: type: QUERY +PREHOOK: Input: default@test1_n4 +PREHOOK: Input: default@test2_n2 +#### A masked pattern was here #### +POSTHOOK: query: SELECT * +FROM test1_n4 FULL OUTER JOIN test2_n2 +ON (test1_n4.value=test2_n2.value + AND (test1_n4.key between 100 and 102 + OR test2_n2.key between 100 and 102)) +POSTHOOK: type: QUERY +POSTHOOK: Input: default@test1_n4 +POSTHOOK: Input: default@test2_n2 +#### A masked pattern was here #### +100 1 Bob NULL NULL NULL +101 2 Car 102 2 Del +101 2 Car 103 2 Ema +98 NULL None NULL NULL NULL +99 0 Alice NULL NULL NULL +99 2 Mat 102 2 Del +NULL NULL NULL 104 3 Fli +NULL NULL NULL 105 NULL None +NULL NULL None NULL NULL NULL +PREHOOK: query: EXPLAIN +SELECT * +FROM test1_n4 FULL OUTER JOIN test2_n2 +ON (test1_n4.value=test2_n2.value + AND (test1_n4.key between 100 and 102 + OR test2_n2.key between 100 and 102)) +PREHOOK: type: QUERY +POSTHOOK: query: EXPLAIN +SELECT * +FROM test1_n4 FULL OUTER JOIN test2_n2 +ON (test1_n4.value=test2_n2.value + AND (test1_n4.key between 100 and 102 + OR test2_n2.key between 100 and 102)) +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +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: test1_n4 + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: int), value (type: int), col_1 (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col1 (type: int) + sort order: + + Map-reduce partition columns: _col1 (type: int) + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: int), _col2 (type: string) + Execution mode: llap + LLAP IO: no inputs + Map 3 + Map Operator Tree: + TableScan + alias: test2_n2 + Statistics: Num rows: 4 Data size: 380 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: int), value (type: int), col_2 (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 4 Data size: 380 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col1 (type: int) + sort order: + + Map-reduce partition columns: _col1 (type: int) + Statistics: Num rows: 4 Data size: 380 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: int), _col2 (type: string) + Execution mode: llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Full Outer Join 0 to 1 + keys: + 0 _col1 (type: int) + 1 _col1 (type: int) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + residual filter predicates: {(_col0 BETWEEN 100 AND 102 or _col3 BETWEEN 100 AND 102)} + Statistics: Num rows: 10 Data size: 191 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 10 Data size: 191 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 + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: SELECT * +FROM test1_n4 FULL OUTER JOIN test2_n2 +ON (test1_n4.value=test2_n2.value + AND (test1_n4.key between 100 and 102 + OR test2_n2.key between 100 and 102)) +PREHOOK: type: QUERY +PREHOOK: Input: default@test1_n4 +PREHOOK: Input: default@test2_n2 +#### A masked pattern was here #### +POSTHOOK: query: SELECT * +FROM test1_n4 FULL OUTER JOIN test2_n2 +ON (test1_n4.value=test2_n2.value + AND (test1_n4.key between 100 and 102 + OR test2_n2.key between 100 and 102)) +POSTHOOK: type: QUERY +POSTHOOK: Input: default@test1_n4 +POSTHOOK: Input: default@test2_n2 +#### A masked pattern was here #### +100 1 Bob NULL NULL NULL +101 2 Car 102 2 Del +101 2 Car 103 2 Ema +98 NULL None NULL NULL NULL +99 0 Alice NULL NULL NULL +99 2 Mat 102 2 Del +NULL NULL NULL 104 3 Fli +NULL NULL NULL 105 NULL None +NULL NULL None NULL NULL NULL +Warning: Shuffle Join MERGEJOIN[36][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Reducer 2' is a cross product +PREHOOK: query: EXPLAIN +SELECT * +FROM ( + SELECT test1_n4.key AS key1, test1_n4.value AS value1, test1_n4.col_1 AS col_1, + test2_n2.key AS key2, test2_n2.value AS value2, test2_n2.col_2 AS col_2 + FROM test1_n4 RIGHT OUTER JOIN test2_n2 + ON (test1_n4.value=test2_n2.value AND (test1_n4.key between 100 and 102 OR test2_n2.key between 100 and 102)) ) sq1 @@ -1972,7 +2419,7 @@ STAGE PLANS: Reduce Operator Tree: Merge Join Operator condition map: - Outer Join 0 to 1 + Full Outer Join 0 to 1 keys: 0 1 @@ -2038,23 +2485,248 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@test1_n4 POSTHOOK: Input: default@test2_n2 #### A masked pattern was here #### -99 2 Mat 102 2 Del 99 0 Alice NULL NULL NULL -99 2 Mat 102 2 Del 100 1 Bob NULL NULL NULL -101 2 Car 102 2 Del 99 0 Alice NULL NULL NULL 101 2 Car 102 2 Del 100 1 Bob NULL NULL NULL -101 2 Car 103 2 Ema 99 0 Alice NULL NULL NULL +101 2 Car 102 2 Del 99 0 Alice NULL NULL NULL 101 2 Car 103 2 Ema 100 1 Bob NULL NULL NULL -NULL NULL NULL 104 3 Fli NULL NULL None NULL NULL NULL -NULL NULL NULL 104 3 Fli 98 NULL None NULL NULL NULL -NULL NULL NULL 104 3 Fli 99 0 Alice NULL NULL NULL -NULL NULL NULL 104 3 Fli 99 2 Mat 102 2 Del +101 2 Car 103 2 Ema 99 0 Alice NULL NULL NULL +99 2 Mat 102 2 Del 100 1 Bob NULL NULL NULL +99 2 Mat 102 2 Del 99 0 Alice NULL NULL NULL NULL NULL NULL 104 3 Fli 100 1 Bob NULL NULL NULL NULL NULL NULL 104 3 Fli 101 2 Car 102 2 Del NULL NULL NULL 104 3 Fli 101 2 Car 103 2 Ema -NULL NULL NULL 105 NULL None NULL NULL None NULL NULL NULL +NULL NULL NULL 104 3 Fli 98 NULL None NULL NULL NULL +NULL NULL NULL 104 3 Fli 99 0 Alice NULL NULL NULL +NULL NULL NULL 104 3 Fli 99 2 Mat 102 2 Del +NULL NULL NULL 104 3 Fli NULL NULL None NULL NULL NULL +NULL NULL NULL 105 NULL None 100 1 Bob NULL NULL NULL +NULL NULL NULL 105 NULL None 101 2 Car 102 2 Del +NULL NULL NULL 105 NULL None 101 2 Car 103 2 Ema NULL NULL NULL 105 NULL None 98 NULL None NULL NULL NULL NULL NULL NULL 105 NULL None 99 0 Alice NULL NULL NULL NULL NULL NULL 105 NULL None 99 2 Mat 102 2 Del +NULL NULL NULL 105 NULL None NULL NULL None NULL NULL NULL +Warning: Shuffle Join MERGEJOIN[36][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Reducer 2' is a cross product +PREHOOK: query: EXPLAIN +SELECT * +FROM ( + SELECT test1_n4.key AS key1, test1_n4.value AS value1, test1_n4.col_1 AS col_1, + test2_n2.key AS key2, test2_n2.value AS value2, test2_n2.col_2 AS col_2 + FROM test1_n4 RIGHT OUTER JOIN test2_n2 + ON (test1_n4.value=test2_n2.value + AND (test1_n4.key between 100 and 102 + OR test2_n2.key between 100 and 102)) + ) sq1 +FULL OUTER JOIN ( + SELECT test1_n4.key AS key3, test1_n4.value AS value3, test1_n4.col_1 AS col_3, + test2_n2.key AS key4, test2_n2.value AS value4, test2_n2.col_2 AS col_4 + FROM test1_n4 LEFT OUTER JOIN test2_n2 + ON (test1_n4.value=test2_n2.value + AND (test1_n4.key between 100 and 102 + OR test2_n2.key between 100 and 102)) + ) sq2 +ON (sq1.value1 is null or sq2.value4 is null and sq2.value3 != sq1.value2) +PREHOOK: type: QUERY +POSTHOOK: query: EXPLAIN +SELECT * +FROM ( + SELECT test1_n4.key AS key1, test1_n4.value AS value1, test1_n4.col_1 AS col_1, + test2_n2.key AS key2, test2_n2.value AS value2, test2_n2.col_2 AS col_2 + FROM test1_n4 RIGHT OUTER JOIN test2_n2 + ON (test1_n4.value=test2_n2.value + AND (test1_n4.key between 100 and 102 + OR test2_n2.key between 100 and 102)) + ) sq1 +FULL OUTER JOIN ( + SELECT test1_n4.key AS key3, test1_n4.value AS value3, test1_n4.col_1 AS col_3, + test2_n2.key AS key4, test2_n2.value AS value4, test2_n2.col_2 AS col_4 + FROM test1_n4 LEFT OUTER JOIN test2_n2 + ON (test1_n4.value=test2_n2.value + AND (test1_n4.key between 100 and 102 + OR test2_n2.key between 100 and 102)) + ) sq2 +ON (sq1.value1 is null or sq2.value4 is null and sq2.value3 != sq1.value2) +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Map 1 <- Map 4 (BROADCAST_EDGE) + Map 3 <- Map 1 (BROADCAST_EDGE) + Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE), Map 3 (CUSTOM_SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: test1_n4 + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: int), value (type: int), col_1 (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col1 (type: int) + sort order: + + Map-reduce partition columns: _col1 (type: int) + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: int), _col2 (type: string) + Select Operator + expressions: key (type: int), value (type: int), col_1 (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 6 Data size: 572 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Left Outer Join 0 to 1 + keys: + 0 _col1 (type: int) + 1 _col1 (type: int) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + input vertices: + 1 Map 4 + residual filter predicates: {(_col0 BETWEEN 100 AND 102 or _col3 BETWEEN 100 AND 102)} + Statistics: Num rows: 8 Data size: 859 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + sort order: + Statistics: Num rows: 8 Data size: 859 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: int), _col1 (type: int), _col2 (type: string), _col3 (type: int), _col4 (type: int), _col5 (type: string) + Execution mode: llap + LLAP IO: no inputs + Map 3 + Map Operator Tree: + TableScan + alias: test2_n2 + Statistics: Num rows: 4 Data size: 380 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: int), value (type: int), col_2 (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 4 Data size: 380 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Right Outer Join 0 to 1 + keys: + 0 _col1 (type: int) + 1 _col1 (type: int) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + input vertices: + 0 Map 1 + residual filter predicates: {(_col0 BETWEEN 100 AND 102 or _col3 BETWEEN 100 AND 102)} + Statistics: Num rows: 8 Data size: 856 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + sort order: + Statistics: Num rows: 8 Data size: 856 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: int), _col1 (type: int), _col2 (type: string), _col3 (type: int), _col4 (type: int), _col5 (type: string) + Execution mode: llap + LLAP IO: no inputs + Map 4 + Map Operator Tree: + TableScan + alias: test2_n2 + Statistics: Num rows: 4 Data size: 380 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: int), value (type: int), col_2 (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 4 Data size: 380 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col1 (type: int) + sort order: + + Map-reduce partition columns: _col1 (type: int) + Statistics: Num rows: 4 Data size: 380 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: int), _col2 (type: string) + Execution mode: llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Full Outer Join 0 to 1 + keys: + 0 + 1 + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11 + residual filter predicates: {(_col1 is null or (_col10 is null and (_col7 <> _col4)))} + Statistics: Num rows: 64 Data size: 23107 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 64 Data size: 23107 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 + limit: -1 + Processor Tree: + ListSink + +Warning: Shuffle Join MERGEJOIN[36][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Reducer 2' is a cross product +PREHOOK: query: SELECT * +FROM ( + SELECT test1_n4.key AS key1, test1_n4.value AS value1, test1_n4.col_1 AS col_1, + test2_n2.key AS key2, test2_n2.value AS value2, test2_n2.col_2 AS col_2 + FROM test1_n4 RIGHT OUTER JOIN test2_n2 + ON (test1_n4.value=test2_n2.value + AND (test1_n4.key between 100 and 102 + OR test2_n2.key between 100 and 102)) + ) sq1 +FULL OUTER JOIN ( + SELECT test1_n4.key AS key3, test1_n4.value AS value3, test1_n4.col_1 AS col_3, + test2_n2.key AS key4, test2_n2.value AS value4, test2_n2.col_2 AS col_4 + FROM test1_n4 LEFT OUTER JOIN test2_n2 + ON (test1_n4.value=test2_n2.value + AND (test1_n4.key between 100 and 102 + OR test2_n2.key between 100 and 102)) + ) sq2 +ON (sq1.value1 is null or sq2.value4 is null and sq2.value3 != sq1.value2) +PREHOOK: type: QUERY +PREHOOK: Input: default@test1_n4 +PREHOOK: Input: default@test2_n2 +#### A masked pattern was here #### +POSTHOOK: query: SELECT * +FROM ( + SELECT test1_n4.key AS key1, test1_n4.value AS value1, test1_n4.col_1 AS col_1, + test2_n2.key AS key2, test2_n2.value AS value2, test2_n2.col_2 AS col_2 + FROM test1_n4 RIGHT OUTER JOIN test2_n2 + ON (test1_n4.value=test2_n2.value + AND (test1_n4.key between 100 and 102 + OR test2_n2.key between 100 and 102)) + ) sq1 +FULL OUTER JOIN ( + SELECT test1_n4.key AS key3, test1_n4.value AS value3, test1_n4.col_1 AS col_3, + test2_n2.key AS key4, test2_n2.value AS value4, test2_n2.col_2 AS col_4 + FROM test1_n4 LEFT OUTER JOIN test2_n2 + ON (test1_n4.value=test2_n2.value + AND (test1_n4.key between 100 and 102 + OR test2_n2.key between 100 and 102)) + ) sq2 +ON (sq1.value1 is null or sq2.value4 is null and sq2.value3 != sq1.value2) +POSTHOOK: type: QUERY +POSTHOOK: Input: default@test1_n4 +POSTHOOK: Input: default@test2_n2 +#### A masked pattern was here #### +101 2 Car 102 2 Del 100 1 Bob NULL NULL NULL +101 2 Car 102 2 Del 99 0 Alice NULL NULL NULL +101 2 Car 103 2 Ema 100 1 Bob NULL NULL NULL +101 2 Car 103 2 Ema 99 0 Alice NULL NULL NULL +99 2 Mat 102 2 Del 100 1 Bob NULL NULL NULL +99 2 Mat 102 2 Del 99 0 Alice NULL NULL NULL +NULL NULL NULL 104 3 Fli 100 1 Bob NULL NULL NULL +NULL NULL NULL 104 3 Fli 101 2 Car 102 2 Del +NULL NULL NULL 104 3 Fli 101 2 Car 103 2 Ema +NULL NULL NULL 104 3 Fli 98 NULL None NULL NULL NULL +NULL NULL NULL 104 3 Fli 99 0 Alice NULL NULL NULL +NULL NULL NULL 104 3 Fli 99 2 Mat 102 2 Del +NULL NULL NULL 104 3 Fli NULL NULL None NULL NULL NULL NULL NULL NULL 105 NULL None 100 1 Bob NULL NULL NULL NULL NULL NULL 105 NULL None 101 2 Car 102 2 Del NULL NULL NULL 105 NULL None 101 2 Car 103 2 Ema +NULL NULL NULL 105 NULL None 98 NULL None NULL NULL NULL +NULL NULL NULL 105 NULL None 99 0 Alice NULL NULL NULL +NULL NULL NULL 105 NULL None 99 2 Mat 102 2 Del +NULL NULL NULL 105 NULL None NULL NULL None NULL NULL NULL
http://git-wip-us.apache.org/repos/asf/hive/blob/a37827ec/ql/src/test/results/clientpositive/llap/mergejoin.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/llap/mergejoin.q.out b/ql/src/test/results/clientpositive/llap/mergejoin.q.out index 1e4f632..b86d822 100644 --- a/ql/src/test/results/clientpositive/llap/mergejoin.q.out +++ b/ql/src/test/results/clientpositive/llap/mergejoin.q.out @@ -52,10 +52,10 @@ STAGE PLANS: Map-reduce partition columns: _col0 (type: string) Reduce Sink Vectorization: className: VectorReduceSinkStringOperator - keyColumnNums: [0] + keyColumns: 0:string 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 - valueColumnNums: [1] + valueColumns: 1:string Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Execution mode: vectorized, llap @@ -105,10 +105,10 @@ STAGE PLANS: Map-reduce partition columns: _col0 (type: string) Reduce Sink Vectorization: className: VectorReduceSinkStringOperator - keyColumnNums: [0] + keyColumns: 0:string 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 - valueColumnNums: [1] + valueColumns: 1:string Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Select Operator @@ -135,10 +135,9 @@ STAGE PLANS: sort order: Reduce Sink Vectorization: className: VectorReduceSinkEmptyKeyOperator - keyColumnNums: [] 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 - valueColumnNums: [0, 1, 2] + valueColumns: 0:string, 1:string, 2:binary Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: binary) Execution mode: vectorized, llap @@ -176,6 +175,9 @@ STAGE PLANS: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + MergeJoin Vectorization: + enabled: false + enableConditionsNotMet: Vectorizing MergeJoin Supported IS false Reducer 4 Execution mode: vectorized, llap Reduce Vectorization: @@ -208,10 +210,9 @@ STAGE PLANS: sort order: Reduce Sink Vectorization: className: VectorReduceSinkEmptyKeyOperator - keyColumnNums: [] 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 - valueColumnNums: [0, 1, 2] + valueColumns: 0:string, 1:string, 2:binary Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: binary) @@ -444,6 +445,9 @@ STAGE PLANS: Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Execution mode: llap + MergeJoin Vectorization: + enabled: false + enableConditionsNotMet: Vectorizing MergeJoin Supported IS false Reducer 3 Execution mode: vectorized, llap Reduce Vectorization: @@ -1535,6 +1539,9 @@ STAGE PLANS: Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Execution mode: llap + MergeJoin Vectorization: + enabled: false + enableConditionsNotMet: Vectorizing MergeJoin Supported IS false Reducer 2 Execution mode: vectorized, llap Reduce Vectorization: @@ -1655,6 +1662,9 @@ STAGE PLANS: Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Execution mode: llap + MergeJoin Vectorization: + enabled: false + enableConditionsNotMet: Vectorizing MergeJoin Supported IS false Reducer 3 Execution mode: vectorized, llap Reduce Vectorization: @@ -1764,10 +1774,9 @@ STAGE PLANS: Map-reduce partition columns: _col0 (type: int) Reduce Sink Vectorization: className: VectorReduceSinkLongOperator - keyColumnNums: [0] + keyColumns: 0:int 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 - valueColumnNums: [] Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized, llap LLAP IO: all inputs @@ -1809,10 +1818,9 @@ STAGE PLANS: Map-reduce partition columns: _col0 (type: int) Reduce Sink Vectorization: className: VectorReduceSinkLongOperator - keyColumnNums: [0] + keyColumns: 0:int 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 - valueColumnNums: [] Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized, llap LLAP IO: all inputs @@ -1837,7 +1845,7 @@ STAGE PLANS: Reduce Operator Tree: Merge Join Operator condition map: - Outer Join 0 to 1 + Full Outer Join 0 to 1 keys: 0 _col0 (type: int) 1 _col0 (type: int) @@ -1851,6 +1859,9 @@ STAGE PLANS: sort order: Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) + MergeJoin Vectorization: + enabled: false + enableConditionsNotMet: Vectorizing MergeJoin Supported IS false Reducer 3 Execution mode: vectorized, llap Reduce Vectorization: @@ -1971,10 +1982,10 @@ STAGE PLANS: Map-reduce partition columns: _col1 (type: string) Reduce Sink Vectorization: className: VectorReduceSinkStringOperator - keyColumnNums: [1] + keyColumns: 1:string 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 - valueColumnNums: [0] + valueColumns: 0:int Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int) Execution mode: vectorized, llap @@ -2025,10 +2036,9 @@ STAGE PLANS: Map-reduce partition columns: _col0 (type: string) Reduce Sink Vectorization: className: VectorReduceSinkStringOperator - keyColumnNums: [1] + keyColumns: 1:string 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 - valueColumnNums: [] Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string) @@ -2054,10 +2064,9 @@ STAGE PLANS: sort order: Reduce Sink Vectorization: className: VectorReduceSinkEmptyKeyOperator - keyColumnNums: [] 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 - valueColumnNums: [0, 1, 2] + valueColumns: 0:string, 1:string, 2:binary Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: binary) Execution mode: vectorized, llap @@ -2107,10 +2116,9 @@ STAGE PLANS: Map-reduce partition columns: _col0 (type: int) Reduce Sink Vectorization: className: VectorReduceSinkLongOperator - keyColumnNums: [0] + keyColumns: 0:int 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 - valueColumnNums: [] Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized, llap LLAP IO: all inputs @@ -2159,6 +2167,9 @@ STAGE PLANS: sort order: Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col1 (type: int), _col2 (type: binary) + MergeJoin Vectorization: + enabled: false + enableConditionsNotMet: Vectorizing MergeJoin Supported IS false Reducer 3 Execution mode: llap Reduce Operator Tree: @@ -2178,6 +2189,9 @@ STAGE PLANS: sort order: Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) + MergeJoin Vectorization: + enabled: false + enableConditionsNotMet: Vectorizing MergeJoin Supported IS false Reducer 4 Execution mode: vectorized, llap Reduce Vectorization: @@ -2248,10 +2262,9 @@ STAGE PLANS: sort order: Reduce Sink Vectorization: className: VectorReduceSinkEmptyKeyOperator - keyColumnNums: [] 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 - valueColumnNums: [0, 1, 2] + valueColumns: 0:int, 1:int, 2:binary Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col1 (type: int), _col2 (type: binary) Reducer 7 @@ -2286,10 +2299,9 @@ STAGE PLANS: sort order: Reduce Sink Vectorization: className: VectorReduceSinkEmptyKeyOperator - keyColumnNums: [] 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 - valueColumnNums: [0, 1, 2] + valueColumns: 0:string, 1:string, 2:binary Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: binary) @@ -2369,10 +2381,9 @@ STAGE PLANS: Map-reduce partition columns: _col0 (type: string) Reduce Sink Vectorization: className: VectorReduceSinkStringOperator - keyColumnNums: [1] + keyColumns: 1:string 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 - valueColumnNums: [] Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized, llap LLAP IO: all inputs @@ -2422,10 +2433,9 @@ STAGE PLANS: Map-reduce partition columns: _col0 (type: string) Reduce Sink Vectorization: className: VectorReduceSinkStringOperator - keyColumnNums: [1] + keyColumns: 1:string 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 - valueColumnNums: [] Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized, llap LLAP IO: all inputs @@ -2464,6 +2474,9 @@ STAGE PLANS: sort order: Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) + MergeJoin Vectorization: + enabled: false + enableConditionsNotMet: Vectorizing MergeJoin Supported IS false Reducer 3 Execution mode: vectorized, llap Reduce Vectorization: @@ -2594,6 +2607,9 @@ STAGE PLANS: Map-reduce partition columns: _col0 (type: int) Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap + MergeJoin Vectorization: + enabled: false + enableConditionsNotMet: Vectorizing MergeJoin Supported IS false Map 6 Map Operator Tree: TableScan @@ -2624,10 +2640,9 @@ STAGE PLANS: Map-reduce partition columns: _col0 (type: int) Reduce Sink Vectorization: className: VectorReduceSinkLongOperator - keyColumnNums: [0] + keyColumns: 0:int 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 - valueColumnNums: [] Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized, llap LLAP IO: all inputs @@ -2677,10 +2692,9 @@ STAGE PLANS: Map-reduce partition columns: _col0 (type: int) Reduce Sink Vectorization: className: VectorReduceSinkLongOperator - keyColumnNums: [0] + keyColumns: 0:int 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 - valueColumnNums: [] Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized, llap LLAP IO: all inputs @@ -2719,6 +2733,9 @@ STAGE PLANS: sort order: Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) + MergeJoin Vectorization: + enabled: false + enableConditionsNotMet: Vectorizing MergeJoin Supported IS false Reducer 4 Execution mode: vectorized, llap Reduce Vectorization: @@ -2819,10 +2836,9 @@ STAGE PLANS: Map-reduce partition columns: _col0 (type: string) Reduce Sink Vectorization: className: VectorReduceSinkStringOperator - keyColumnNums: [1] + keyColumns: 1:string 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 - valueColumnNums: [] Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized, llap LLAP IO: all inputs @@ -2872,10 +2888,9 @@ STAGE PLANS: Map-reduce partition columns: _col0 (type: string) Reduce Sink Vectorization: className: VectorReduceSinkStringOperator - keyColumnNums: [1] + keyColumns: 1:string 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 - valueColumnNums: [] Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized, llap LLAP IO: all inputs @@ -2914,6 +2929,9 @@ STAGE PLANS: sort order: Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) + MergeJoin Vectorization: + enabled: false + enableConditionsNotMet: Vectorizing MergeJoin Supported IS false Reducer 3 Execution mode: vectorized, llap Reduce Vectorization: @@ -3032,10 +3050,10 @@ STAGE PLANS: Map-reduce partition columns: _col1 (type: string) Reduce Sink Vectorization: className: VectorReduceSinkStringOperator - keyColumnNums: [1] + keyColumns: 1:string 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 - valueColumnNums: [0] + valueColumns: 0:int Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int) Execution mode: vectorized, llap @@ -3086,10 +3104,9 @@ STAGE PLANS: Map-reduce partition columns: _col0 (type: string) Reduce Sink Vectorization: className: VectorReduceSinkStringOperator - keyColumnNums: [1] + keyColumns: 1:string 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 - valueColumnNums: [] Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string) @@ -3115,10 +3132,9 @@ STAGE PLANS: sort order: Reduce Sink Vectorization: className: VectorReduceSinkEmptyKeyOperator - keyColumnNums: [] 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 - valueColumnNums: [0, 1, 2] + valueColumns: 0:string, 1:string, 2:binary Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: binary) Execution mode: vectorized, llap @@ -3168,10 +3184,9 @@ STAGE PLANS: Map-reduce partition columns: _col0 (type: int) Reduce Sink Vectorization: className: VectorReduceSinkLongOperator - keyColumnNums: [0] + keyColumns: 0:int 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 - valueColumnNums: [] Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized, llap LLAP IO: all inputs @@ -3220,6 +3235,9 @@ STAGE PLANS: sort order: Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col1 (type: int), _col2 (type: binary) + MergeJoin Vectorization: + enabled: false + enableConditionsNotMet: Vectorizing MergeJoin Supported IS false Reducer 3 Execution mode: llap Reduce Operator Tree: @@ -3239,6 +3257,9 @@ STAGE PLANS: sort order: Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) + MergeJoin Vectorization: + enabled: false + enableConditionsNotMet: Vectorizing MergeJoin Supported IS false Reducer 4 Execution mode: vectorized, llap Reduce Vectorization: @@ -3309,10 +3330,9 @@ STAGE PLANS: sort order: Reduce Sink Vectorization: className: VectorReduceSinkEmptyKeyOperator - keyColumnNums: [] 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 - valueColumnNums: [0, 1, 2] + valueColumns: 0:int, 1:int, 2:binary Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col1 (type: int), _col2 (type: binary) Reducer 7 @@ -3347,10 +3367,9 @@ STAGE PLANS: sort order: Reduce Sink Vectorization: className: VectorReduceSinkEmptyKeyOperator - keyColumnNums: [] 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 - valueColumnNums: [0, 1, 2] + valueColumns: 0:string, 1:string, 2:binary Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: binary) @@ -3447,6 +3466,9 @@ STAGE PLANS: Map-reduce partition columns: _col0 (type: int) Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap + MergeJoin Vectorization: + enabled: false + enableConditionsNotMet: Vectorizing MergeJoin Supported IS false Map 6 Map Operator Tree: TableScan @@ -3477,10 +3499,9 @@ STAGE PLANS: Map-reduce partition columns: _col0 (type: int) Reduce Sink Vectorization: className: VectorReduceSinkLongOperator - keyColumnNums: [0] + keyColumns: 0:int 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 - valueColumnNums: [] Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized, llap LLAP IO: all inputs @@ -3530,10 +3551,9 @@ STAGE PLANS: Map-reduce partition columns: _col0 (type: int) Reduce Sink Vectorization: className: VectorReduceSinkLongOperator - keyColumnNums: [0] + keyColumns: 0:int 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 - valueColumnNums: [] Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized, llap LLAP IO: all inputs @@ -3572,6 +3592,9 @@ STAGE PLANS: sort order: Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) + MergeJoin Vectorization: + enabled: false + enableConditionsNotMet: Vectorizing MergeJoin Supported IS false Reducer 4 Execution mode: vectorized, llap Reduce Vectorization: @@ -3683,10 +3706,9 @@ STAGE PLANS: sort order: ++ Reduce Sink Vectorization: className: VectorReduceSinkObjectHashOperator - keyColumnNums: [0, 1] + keyColumns: 0:int, 1:string 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 - valueColumnNums: [] Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized, llap LLAP IO: all inputs @@ -3735,10 +3757,9 @@ STAGE PLANS: sort order: ++ Reduce Sink Vectorization: className: VectorReduceSinkObjectHashOperator - keyColumnNums: [0, 1] + keyColumns: 0:int, 1:string 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 - valueColumnNums: [] Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized, llap LLAP IO: all inputs @@ -3786,6 +3807,9 @@ STAGE PLANS: sort order: Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) + MergeJoin Vectorization: + enabled: false + enableConditionsNotMet: Vectorizing MergeJoin Supported IS false Reducer 5 Execution mode: vectorized, llap Reduce Vectorization: