http://git-wip-us.apache.org/repos/asf/hive/blob/ae1eb15d/ql/src/test/results/clientpositive/spark/subquery_notin.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/spark/subquery_notin.q.out b/ql/src/test/results/clientpositive/spark/subquery_notin.q.out index 39080da..e28bfcf 100644 --- a/ql/src/test/results/clientpositive/spark/subquery_notin.q.out +++ b/ql/src/test/results/clientpositive/spark/subquery_notin.q.out @@ -1,4 +1,4 @@ -Warning: Shuffle Join JOIN[18][tables = [$hdt$_0, $hdt$_1]] in Work 'Reducer 2' is a cross product +Warning: Shuffle Join JOIN[21][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Work 'Reducer 3' is a cross product PREHOOK: query: explain select * from src @@ -27,10 +27,10 @@ STAGE PLANS: Stage: Stage-1 Spark Edges: - Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 1), Reducer 5 (PARTITION-LEVEL SORT, 1) - Reducer 3 <- Reducer 2 (PARTITION-LEVEL SORT, 2), Reducer 7 (PARTITION-LEVEL SORT, 2) - Reducer 5 <- Map 4 (GROUP, 1) - Reducer 7 <- Map 6 (GROUP, 2) + Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 2), Reducer 5 (PARTITION-LEVEL SORT, 2) + Reducer 3 <- Reducer 2 (PARTITION-LEVEL SORT, 1), Reducer 7 (PARTITION-LEVEL SORT, 1) + Reducer 5 <- Map 4 (GROUP, 2) + Reducer 7 <- Map 6 (GROUP, 1) #### A masked pattern was here #### Vertices: Map 1 @@ -43,9 +43,11 @@ STAGE PLANS: outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - sort order: + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string), _col1 (type: string) + value expressions: _col1 (type: string) Execution mode: vectorized Map 4 Map Operator Tree: @@ -57,14 +59,15 @@ STAGE PLANS: predicate: (key > '2') (type: boolean) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(), count(key) + keys: key (type: string) mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: _col0 + Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: bigint), _col1 (type: bigint) + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized Map 6 Map Operator Tree: @@ -76,72 +79,61 @@ STAGE PLANS: predicate: (key > '2') (type: boolean) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: key (type: string) + aggregations: count(), count(key) mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + sort order: + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: bigint), _col1 (type: bigint) Execution mode: vectorized Reducer 2 Reduce Operator Tree: Join Operator condition map: - Inner Join 0 to 1 + Left Outer Join 0 to 1 keys: - 0 - 1 - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 500 Data size: 13812 Basic stats: COMPLETE Column stats: NONE + 0 _col0 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0, _col1, _col3 + Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 13812 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string), _col2 (type: bigint), _col3 (type: bigint) + sort order: + Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: string), _col1 (type: string), _col3 (type: boolean) Reducer 3 Reduce Operator Tree: Join Operator condition map: - Left Outer Join 0 to 1 + Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col5 + 0 + 1 + outputColumnNames: _col0, _col1, _col3, _col4, _col5 Statistics: Num rows: 550 Data size: 15193 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: ((_col2 = 0L) or (_col5 is null and _col0 is not null and (_col3 >= _col2))) (type: boolean) - Statistics: Num rows: 366 Data size: 10110 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string), _col1 (type: string) - outputColumnNames: _col0, _col1 + Select Operator + expressions: _col0 (type: string), _col1 (type: string), _col4 (type: bigint), _col5 (type: bigint), _col3 (type: boolean) + outputColumnNames: _col0, _col1, _col2, _col3, _col5 + Statistics: Num rows: 550 Data size: 15193 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: ((_col2 = 0L) or (_col5 is null and _col0 is not null and (_col3 >= _col2))) (type: boolean) Statistics: Num rows: 366 Data size: 10110 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 366 Data size: 10110 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 366 Data size: 10110 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Reducer 5 Execution mode: vectorized Reduce Operator Tree: Group By Operator - aggregations: count(VALUE._col0), count(VALUE._col1) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: bigint), _col1 (type: bigint) - Reducer 7 - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0 @@ -156,6 +148,18 @@ STAGE PLANS: Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: boolean) + Reducer 7 + Execution mode: vectorized + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0), count(VALUE._col1) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: bigint), _col1 (type: bigint) Stage: Stage-0 Fetch Operator @@ -163,7 +167,7 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Shuffle Join JOIN[18][tables = [$hdt$_0, $hdt$_1]] in Work 'Reducer 2' is a cross product +Warning: Shuffle Join JOIN[21][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Work 'Reducer 3' is a cross product PREHOOK: query: select * from src where src.key not in ( select key from src s1 where s1.key > '2') @@ -578,7 +582,7 @@ Manufacturer#4 almond azure aquamarine papaya violet 12 Manufacturer#5 almond antique blue firebrick mint 31 Manufacturer#5 almond aquamarine dodger light gainsboro 46 Manufacturer#5 almond azure blanched chiffon midnight 23 -Warning: Shuffle Join JOIN[33][tables = [$hdt$_0, $hdt$_1]] in Work 'Reducer 2' is a cross product +Warning: Shuffle Join JOIN[36][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Work 'Reducer 3' is a cross product PREHOOK: query: explain select p_name, p_size from @@ -609,8 +613,8 @@ STAGE PLANS: Stage: Stage-1 Spark Edges: - Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 1), Reducer 6 (PARTITION-LEVEL SORT, 1) - Reducer 3 <- Reducer 2 (PARTITION-LEVEL SORT, 2), Reducer 9 (PARTITION-LEVEL SORT, 2) + Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 2), Reducer 6 (PARTITION-LEVEL SORT, 2) + Reducer 3 <- Reducer 2 (PARTITION-LEVEL SORT, 1), Reducer 9 (PARTITION-LEVEL SORT, 1) Reducer 5 <- Map 4 (PARTITION-LEVEL SORT, 2) Reducer 6 <- Reducer 5 (GROUP, 1) Reducer 8 <- Map 4 (PARTITION-LEVEL SORT, 2) @@ -627,7 +631,9 @@ STAGE PLANS: outputColumnNames: _col0, _col1 Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - sort order: + key expressions: UDFToDouble(_col1) (type: double) + sort order: + + Map-reduce partition columns: UDFToDouble(_col1) (type: double) Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: string), _col1 (type: int) Execution mode: vectorized @@ -647,42 +653,44 @@ STAGE PLANS: Reduce Operator Tree: Join Operator condition map: - Inner Join 0 to 1 + Left Outer Join 0 to 1 keys: - 0 - 1 - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 26 Data size: 3589 Basic stats: COMPLETE Column stats: NONE + 0 UDFToDouble(_col1) (type: double) + 1 _col0 (type: double) + outputColumnNames: _col0, _col1, _col3 + Statistics: Num rows: 28 Data size: 3461 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: UDFToDouble(_col1) (type: double) - sort order: + - Map-reduce partition columns: UDFToDouble(_col1) (type: double) - Statistics: Num rows: 26 Data size: 3589 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string), _col1 (type: int), _col2 (type: bigint), _col3 (type: bigint) + sort order: + Statistics: Num rows: 28 Data size: 3461 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: string), _col1 (type: int), _col3 (type: boolean) Reducer 3 Reduce Operator Tree: Join Operator condition map: - Left Outer Join 0 to 1 + Inner Join 0 to 1 keys: - 0 UDFToDouble(_col1) (type: double) - 1 _col0 (type: double) - outputColumnNames: _col0, _col1, _col2, _col3, _col5 - Statistics: Num rows: 28 Data size: 3947 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: ((_col2 = 0L) or (_col5 is null and _col1 is not null and (_col3 >= _col2))) (type: boolean) - Statistics: Num rows: 18 Data size: 2537 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string), _col1 (type: int) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 18 Data size: 2537 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 18 Data size: 2537 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + 0 + 1 + outputColumnNames: _col0, _col1, _col3, _col4, _col5 + Statistics: Num rows: 28 Data size: 3937 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: string), _col1 (type: int), _col4 (type: bigint), _col5 (type: bigint), _col3 (type: boolean) + outputColumnNames: _col0, _col1, _col2, _col3, _col5 + Statistics: Num rows: 28 Data size: 3937 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: ((_col2 = 0L) or (_col5 is null and _col1 is not null and (_col3 >= _col2))) (type: boolean) + Statistics: Num rows: 18 Data size: 2530 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: string), _col1 (type: int) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 18 Data size: 2530 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 18 Data size: 2530 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Reducer 5 Execution mode: vectorized Reduce Operator Tree: @@ -736,18 +744,15 @@ STAGE PLANS: outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: (UDFToDouble(_col0) / _col1) (type: double) - outputColumnNames: _col0 + expressions: (UDFToDouble(_col0) / _col1) (type: double), true (type: boolean) + outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(), count(_col0) - mode: complete - outputColumnNames: _col0, _col1 + Reduce Output Operator + key expressions: _col0 (type: double) + sort order: + + Map-reduce partition columns: _col0 (type: double) Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: bigint), _col1 (type: bigint) + value expressions: _col1 (type: boolean) Reducer 8 Execution mode: vectorized Reduce Operator Tree: @@ -801,15 +806,18 @@ STAGE PLANS: outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: (UDFToDouble(_col0) / _col1) (type: double), true (type: boolean) - outputColumnNames: _col0, _col1 + expressions: (UDFToDouble(_col0) / _col1) (type: double) + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: double) - sort order: + - Map-reduce partition columns: _col0 (type: double) + Group By Operator + aggregations: count(), count(_col0) + mode: complete + outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: boolean) + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: bigint), _col1 (type: bigint) Stage: Stage-0 Fetch Operator @@ -817,7 +825,7 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Shuffle Join JOIN[33][tables = [$hdt$_0, $hdt$_1]] in Work 'Reducer 2' is a cross product +Warning: Shuffle Join JOIN[36][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Work 'Reducer 3' is a cross product PREHOOK: query: select p_name, p_size from part where part.p_size not in @@ -1225,27 +1233,27 @@ from part b where b.p_size not in POSTHOOK: type: QUERY POSTHOOK: Input: default@part #### A masked pattern was here #### +Manufacturer#1 almond antique chartreuse lavender yellow 34 +Manufacturer#1 almond antique salmon chartreuse burlywood 6 Manufacturer#1 almond aquamarine burnished black steel 28 Manufacturer#1 almond aquamarine pink moccasin thistle 42 Manufacturer#2 almond antique violet chocolate turquoise 14 -Manufacturer#2 almond aquamarine sandy cyan gainsboro 18 Manufacturer#2 almond antique violet turquoise frosted 40 -Manufacturer#3 almond antique metallic orange dim 19 -Manufacturer#4 almond aquamarine floral ivory bisque 27 -Manufacturer#4 almond antique violet mint lemon 39 -Manufacturer#5 almond antique medium spring khaki 6 -Manufacturer#5 almond azure blanched chiffon midnight 23 -Manufacturer#5 almond antique blue firebrick mint 31 -Manufacturer#5 almond aquamarine dodger light gainsboro 46 -Manufacturer#1 almond antique salmon chartreuse burlywood 6 -Manufacturer#1 almond antique chartreuse lavender yellow 34 Manufacturer#2 almond aquamarine rose maroon antique 25 -Manufacturer#3 almond antique forest lavender goldenrod 14 +Manufacturer#2 almond aquamarine sandy cyan gainsboro 18 Manufacturer#3 almond antique chartreuse khaki white 17 +Manufacturer#3 almond antique forest lavender goldenrod 14 +Manufacturer#3 almond antique metallic orange dim 19 Manufacturer#3 almond antique olive coral navajo 45 Manufacturer#4 almond antique gainsboro frosted violet 10 +Manufacturer#4 almond antique violet mint lemon 39 +Manufacturer#4 almond aquamarine floral ivory bisque 27 Manufacturer#4 almond azure aquamarine papaya violet 12 -Warning: Shuffle Join JOIN[19][tables = [$hdt$_0, $hdt$_1]] in Work 'Reducer 2' is a cross product +Manufacturer#5 almond antique blue firebrick mint 31 +Manufacturer#5 almond antique medium spring khaki 6 +Manufacturer#5 almond aquamarine dodger light gainsboro 46 +Manufacturer#5 almond azure blanched chiffon midnight 23 +Warning: Shuffle Join JOIN[22][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Work 'Reducer 4' is a cross product PREHOOK: query: select li.l_partkey, count(*) from lineitem li where li.l_linenumber = 1 and @@ -1262,23 +1270,23 @@ group by li.l_partkey POSTHOOK: type: QUERY POSTHOOK: Input: default@lineitem #### A masked pattern was here #### -22630 1 -175839 1 +106170 1 +119477 1 119767 1 +123076 1 139636 1 +175839 1 +182052 1 21636 1 -119477 1 -88362 1 -106170 1 +22630 1 +450 1 59694 1 +61931 1 7068 1 -123076 1 85951 1 -61931 1 -450 1 -182052 1 88035 1 -Warning: Shuffle Join JOIN[18][tables = [$hdt$_0, $hdt$_1]] in Work 'Reducer 2' is a cross product +88362 1 +Warning: Shuffle Join JOIN[21][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Work 'Reducer 3' is a cross product PREHOOK: query: select * from src where not src.key in ( select key from src s1 where s1.key > '2') @@ -1440,7 +1448,7 @@ POSTHOOK: Input: default@t1_v POSTHOOK: Output: database:default POSTHOOK: Output: default@T2_v POSTHOOK: Lineage: T2_v.key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] -Warning: Shuffle Join JOIN[21][tables = [$hdt$_0, $hdt$_1]] in Work 'Reducer 2' is a cross product +Warning: Shuffle Join JOIN[24][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Work 'Reducer 3' is a cross product PREHOOK: query: explain select * from T1_v where T1_v.key not in (select T2_v.key from T2_v) @@ -1465,10 +1473,10 @@ STAGE PLANS: Stage: Stage-1 Spark Edges: - Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 1), Reducer 5 (PARTITION-LEVEL SORT, 1) - Reducer 3 <- Reducer 2 (PARTITION-LEVEL SORT, 2), Reducer 7 (PARTITION-LEVEL SORT, 2) - Reducer 5 <- Map 4 (GROUP, 1) - Reducer 7 <- Map 6 (GROUP, 2) + Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 2), Reducer 5 (PARTITION-LEVEL SORT, 2) + Reducer 3 <- Reducer 2 (PARTITION-LEVEL SORT, 1), Reducer 7 (PARTITION-LEVEL SORT, 1) + Reducer 5 <- Map 4 (GROUP, 2) + Reducer 7 <- Map 6 (GROUP, 1) #### A masked pattern was here #### Vertices: Map 1 @@ -1487,117 +1495,108 @@ STAGE PLANS: outputColumnNames: _col0 Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - sort order: + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string) Execution mode: vectorized Map 4 Map Operator Tree: TableScan alias: src - filterExpr: (key < '11') (type: boolean) + filterExpr: ((key < '11') and CASE WHEN ((key > '104')) THEN (null) ELSE ((key < '11')) END) (type: boolean) properties: insideView TRUE Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (key < '11') (type: boolean) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + predicate: ((key < '11') and CASE WHEN ((key > '104')) THEN (null) ELSE ((key < '11')) END) (type: boolean) + Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: CASE WHEN ((key > '104')) THEN (null) ELSE (key) END (type: string) outputColumnNames: _col0 - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(), count(_col0) + keys: _col0 (type: string) mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: _col0 + Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: bigint), _col1 (type: bigint) + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized Map 6 Map Operator Tree: TableScan alias: src - filterExpr: ((key < '11') and CASE WHEN ((key > '104')) THEN (null) ELSE ((key < '11')) END) (type: boolean) + filterExpr: (key < '11') (type: boolean) properties: insideView TRUE Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((key < '11') and CASE WHEN ((key > '104')) THEN (null) ELSE ((key < '11')) END) (type: boolean) - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + predicate: (key < '11') (type: boolean) + Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: CASE WHEN ((key > '104')) THEN (null) ELSE (key) END (type: string) outputColumnNames: _col0 - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: _col0 (type: string) + aggregations: count(), count(_col0) mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE + sort order: + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: bigint), _col1 (type: bigint) Execution mode: vectorized Reducer 2 Reduce Operator Tree: Join Operator condition map: - Inner Join 0 to 1 + Left Outer Join 0 to 1 keys: - 0 - 1 - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 166 Data size: 4585 Basic stats: COMPLETE Column stats: NONE + 0 _col0 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0, _col2 + Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 166 Data size: 4585 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint), _col2 (type: bigint) + sort order: + Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: string), _col2 (type: boolean) Reducer 3 Reduce Operator Tree: Join Operator condition map: - Left Outer Join 0 to 1 + Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col4 - Statistics: Num rows: 182 Data size: 5043 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: ((_col1 = 0L) or (_col4 is null and _col0 is not null and (_col2 >= _col1))) (type: boolean) - Statistics: Num rows: 121 Data size: 3352 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 121 Data size: 3352 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 121 Data size: 3352 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + 0 + 1 + outputColumnNames: _col0, _col2, _col3, _col4 + Statistics: Num rows: 182 Data size: 5033 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: string), _col3 (type: bigint), _col4 (type: bigint), _col2 (type: boolean) + outputColumnNames: _col0, _col1, _col2, _col4 + Statistics: Num rows: 182 Data size: 5033 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: ((_col1 = 0L) or (_col4 is null and _col0 is not null and (_col2 >= _col1))) (type: boolean) + Statistics: Num rows: 121 Data size: 3346 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 121 Data size: 3346 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 121 Data size: 3346 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Reducer 5 Execution mode: vectorized Reduce Operator Tree: Group By Operator - aggregations: count(VALUE._col0), count(VALUE._col1) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: bigint), _col1 (type: bigint) - Reducer 7 - Execution mode: vectorized - Reduce Operator Tree: - Group By Operator keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0 @@ -1612,6 +1611,18 @@ STAGE PLANS: Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 41 Data size: 435 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: boolean) + Reducer 7 + Execution mode: vectorized + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0), count(VALUE._col1) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: bigint), _col1 (type: bigint) Stage: Stage-0 Fetch Operator @@ -1619,7 +1630,7 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Shuffle Join JOIN[21][tables = [$hdt$_0, $hdt$_1]] in Work 'Reducer 2' is a cross product +Warning: Shuffle Join JOIN[24][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Work 'Reducer 3' is a cross product PREHOOK: query: select * from T1_v where T1_v.key not in (select T2_v.key from T2_v) PREHOOK: type: QUERY @@ -1814,30 +1825,30 @@ POSTHOOK: query: select * from part where p_brand <> 'Brand#14' AND p_size NOT I POSTHOOK: type: QUERY POSTHOOK: Input: default@part #### A masked pattern was here #### -191709 almond antique violet turquoise frosted Manufacturer#2 Brand#22 ECONOMY POLISHED STEEL 40 MED BOX 1800.7 haggle -85768 almond antique chartreuse lavender yellow Manufacturer#1 Brand#12 LARGE BRUSHED STEEL 34 SM BAG 1753.76 refull -65667 almond aquamarine pink moccasin thistle Manufacturer#1 Brand#12 LARGE BURNISHED STEEL 42 JUMBO CASE 1632.66 e across the expr 105685 almond antique violet chocolate turquoise Manufacturer#2 Brand#22 MEDIUM ANODIZED COPPER 14 MED CAN 1690.68 ly pending requ +110592 almond antique salmon chartreuse burlywood Manufacturer#1 Brand#15 PROMO BURNISHED NICKEL 6 JUMBO PKG 1602.59 to the furiously 112398 almond antique metallic orange dim Manufacturer#3 Brand#32 MEDIUM BURNISHED BRASS 19 JUMBO JAR 1410.39 ole car +132666 almond aquamarine rose maroon antique Manufacturer#2 Brand#24 SMALL POLISHED NICKEL 25 MED BOX 1698.66 even +144293 almond antique olive coral navajo Manufacturer#3 Brand#34 STANDARD POLISHED STEEL 45 JUMBO CAN 1337.29 ag furiously about 146985 almond aquamarine midnight light salmon Manufacturer#2 Brand#23 MEDIUM BURNISHED COPPER 2 SM CASE 2031.98 s cajole caref -110592 almond antique salmon chartreuse burlywood Manufacturer#1 Brand#15 PROMO BURNISHED NICKEL 6 JUMBO PKG 1602.59 to the furiously +15103 almond aquamarine dodger light gainsboro Manufacturer#5 Brand#53 ECONOMY BURNISHED STEEL 46 LG PACK 1018.1 packages hinder carefu +155733 almond antique sky peru orange Manufacturer#5 Brand#53 SMALL PLATED BRASS 2 WRAP DRUM 1788.73 furiously. bra +17273 almond antique forest lavender goldenrod Manufacturer#3 Brand#35 PROMO ANODIZED TIN 14 JUMBO CASE 1190.27 along the +17927 almond aquamarine yellow dodger mint Manufacturer#4 Brand#41 ECONOMY BRUSHED COPPER 7 SM PKG 1844.92 ites. eve +191709 almond antique violet turquoise frosted Manufacturer#2 Brand#22 ECONOMY POLISHED STEEL 40 MED BOX 1800.7 haggle +192697 almond antique blue firebrick mint Manufacturer#5 Brand#52 MEDIUM BURNISHED TIN 31 LG DRUM 1789.69 ickly ir +195606 almond aquamarine sandy cyan gainsboro Manufacturer#2 Brand#25 STANDARD PLATED TIN 18 SM PKG 1701.6 ic de +33357 almond azure aquamarine papaya violet Manufacturer#4 Brand#41 STANDARD ANODIZED TIN 12 WRAP CASE 1290.35 reful +42669 almond antique medium spring khaki Manufacturer#5 Brand#51 STANDARD BURNISHED TIN 6 MED CAN 1611.66 sits haggl +45261 almond aquamarine floral ivory bisque Manufacturer#4 Brand#42 SMALL PLATED STEEL 27 WRAP CASE 1206.26 careful 48427 almond antique violet mint lemon Manufacturer#4 Brand#42 PROMO POLISHED STEEL 39 SM CASE 1375.42 hely ironic i 49671 almond antique gainsboro frosted violet Manufacturer#4 Brand#41 SMALL BRUSHED BRASS 10 SM BOX 1620.67 ccounts run quick -45261 almond aquamarine floral ivory bisque Manufacturer#4 Brand#42 SMALL PLATED STEEL 27 WRAP CASE 1206.26 careful -42669 almond antique medium spring khaki Manufacturer#5 Brand#51 STANDARD BURNISHED TIN 6 MED CAN 1611.66 sits haggl -195606 almond aquamarine sandy cyan gainsboro Manufacturer#2 Brand#25 STANDARD PLATED TIN 18 SM PKG 1701.6 ic de -144293 almond antique olive coral navajo Manufacturer#3 Brand#34 STANDARD POLISHED STEEL 45 JUMBO CAN 1337.29 ag furiously about -17927 almond aquamarine yellow dodger mint Manufacturer#4 Brand#41 ECONOMY BRUSHED COPPER 7 SM PKG 1844.92 ites. eve -15103 almond aquamarine dodger light gainsboro Manufacturer#5 Brand#53 ECONOMY BURNISHED STEEL 46 LG PACK 1018.1 packages hinder carefu +65667 almond aquamarine pink moccasin thistle Manufacturer#1 Brand#12 LARGE BURNISHED STEEL 42 JUMBO CASE 1632.66 e across the expr 78486 almond azure blanched chiffon midnight Manufacturer#5 Brand#52 LARGE BRUSHED BRASS 23 MED BAG 1464.48 hely blith -90681 almond antique chartreuse khaki white Manufacturer#3 Brand#31 MEDIUM BURNISHED TIN 17 SM CASE 1671.68 are slyly after the sl -192697 almond antique blue firebrick mint Manufacturer#5 Brand#52 MEDIUM BURNISHED TIN 31 LG DRUM 1789.69 ickly ir -17273 almond antique forest lavender goldenrod Manufacturer#3 Brand#35 PROMO ANODIZED TIN 14 JUMBO CASE 1190.27 along the -155733 almond antique sky peru orange Manufacturer#5 Brand#53 SMALL PLATED BRASS 2 WRAP DRUM 1788.73 furiously. bra -132666 almond aquamarine rose maroon antique Manufacturer#2 Brand#24 SMALL POLISHED NICKEL 25 MED BOX 1698.66 even +85768 almond antique chartreuse lavender yellow Manufacturer#1 Brand#12 LARGE BRUSHED STEEL 34 SM BAG 1753.76 refull 86428 almond aquamarine burnished black steel Manufacturer#1 Brand#12 STANDARD ANODIZED STEEL 28 WRAP BAG 1414.42 arefully -33357 almond azure aquamarine papaya violet Manufacturer#4 Brand#41 STANDARD ANODIZED TIN 12 WRAP CASE 1290.35 reful -Warning: Shuffle Join JOIN[26][tables = [$hdt$_0, $hdt$_1]] in Work 'Reducer 2' is a cross product +90681 almond antique chartreuse khaki white Manufacturer#3 Brand#31 MEDIUM BURNISHED TIN 17 SM CASE 1671.68 are slyly after the sl +Warning: Shuffle Join JOIN[29][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Work 'Reducer 3' is a cross product PREHOOK: query: explain select * from part where (p_size-1) NOT IN (select min(p_size) from part group by p_type) order by p_partkey PREHOOK: type: QUERY PREHOOK: Input: default@part @@ -1854,12 +1865,12 @@ STAGE PLANS: Stage: Stage-1 Spark Edges: - Reducer 10 <- Reducer 9 (GROUP, 2) - Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 1), Reducer 7 (PARTITION-LEVEL SORT, 1) - Reducer 3 <- Reducer 10 (PARTITION-LEVEL SORT, 2), Reducer 2 (PARTITION-LEVEL SORT, 2) + Reducer 10 <- Reducer 9 (GROUP, 1) + Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 2), Reducer 7 (PARTITION-LEVEL SORT, 2) + Reducer 3 <- Reducer 10 (PARTITION-LEVEL SORT, 1), Reducer 2 (PARTITION-LEVEL SORT, 1) Reducer 4 <- Reducer 3 (SORT, 1) Reducer 6 <- Map 5 (GROUP, 2) - Reducer 7 <- Reducer 6 (GROUP, 1) + Reducer 7 <- Reducer 6 (GROUP, 2) Reducer 9 <- Map 5 (GROUP, 2) #### A masked pattern was here #### Vertices: @@ -1873,7 +1884,9 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - sort order: + key expressions: (_col5 - 1) (type: int) + sort order: + + Map-reduce partition columns: (_col5 - 1) (type: int) Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) Execution mode: vectorized @@ -1903,68 +1916,64 @@ STAGE PLANS: Execution mode: vectorized Reduce Operator Tree: Group By Operator - keys: KEY._col0 (type: int) + aggregations: count(VALUE._col0), count(VALUE._col1) mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 6 Data size: 726 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: int), true (type: boolean) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 6 Data size: 726 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 6 Data size: 726 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: boolean) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: bigint), _col1 (type: bigint) Reducer 2 Reduce Operator Tree: Join Operator condition map: - Inner Join 0 to 1 + Left Outer Join 0 to 1 keys: - 0 - 1 - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10 - Statistics: Num rows: 26 Data size: 3589 Basic stats: COMPLETE Column stats: NONE + 0 (_col5 - 1) (type: int) + 1 _col0 (type: int) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col10 + Statistics: Num rows: 28 Data size: 3461 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: (_col5 - 1) (type: int) - sort order: + - Map-reduce partition columns: (_col5 - 1) (type: int) - Statistics: Num rows: 26 Data size: 3589 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string), _col9 (type: bigint), _col10 (type: bigint) + sort order: + Statistics: Num rows: 28 Data size: 3461 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string), _col10 (type: boolean) Reducer 3 Reduce Operator Tree: Join Operator condition map: - Left Outer Join 0 to 1 + Inner Join 0 to 1 keys: - 0 (_col5 - 1) (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col12 - Statistics: Num rows: 28 Data size: 3947 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: ((_col12 is null and _col5 is not null and (_col10 >= _col9)) or (_col9 = 0L)) (type: boolean) - Statistics: Num rows: 18 Data size: 2537 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 18 Data size: 2537 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Statistics: Num rows: 18 Data size: 2537 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) + 0 + 1 + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col10, _col11, _col12 + Statistics: Num rows: 28 Data size: 3937 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string), _col11 (type: bigint), _col12 (type: bigint), _col10 (type: boolean) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col12 + Statistics: Num rows: 28 Data size: 3937 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: ((_col12 is null and _col5 is not null and (_col10 >= _col9)) or (_col9 = 0L)) (type: boolean) + Statistics: Num rows: 18 Data size: 2530 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 + Statistics: Num rows: 18 Data size: 2530 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Statistics: Num rows: 18 Data size: 2530 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) Reducer 4 Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: string), VALUE._col1 (type: string), VALUE._col2 (type: string), VALUE._col3 (type: string), VALUE._col4 (type: int), VALUE._col5 (type: string), VALUE._col6 (type: double), VALUE._col7 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 18 Data size: 2537 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 18 Data size: 2530 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 18 Data size: 2537 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 18 Data size: 2530 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1983,26 +1992,33 @@ STAGE PLANS: outputColumnNames: _col1 Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(), count(_col1) + keys: _col1 (type: int) mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: _col0 + Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: bigint), _col1 (type: bigint) + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE Reducer 7 Execution mode: vectorized Reduce Operator Tree: Group By Operator - aggregations: count(VALUE._col0), count(VALUE._col1) + keys: KEY._col0 (type: int) mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: bigint), _col1 (type: bigint) + outputColumnNames: _col0 + Statistics: Num rows: 6 Data size: 726 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: int), true (type: boolean) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 6 Data size: 726 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 6 Data size: 726 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: boolean) Reducer 9 Execution mode: vectorized Reduce Operator Tree: @@ -2017,15 +2033,14 @@ STAGE PLANS: outputColumnNames: _col1 Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: _col1 (type: int) + aggregations: count(), count(_col1) mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE + sort order: + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: bigint), _col1 (type: bigint) Stage: Stage-0 Fetch Operator @@ -2033,7 +2048,7 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Shuffle Join JOIN[26][tables = [$hdt$_0, $hdt$_1]] in Work 'Reducer 2' is a cross product +Warning: Shuffle Join JOIN[29][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Work 'Reducer 3' is a cross product PREHOOK: query: select * from part where (p_size-1) NOT IN (select min(p_size) from part group by p_type) order by p_partkey PREHOOK: type: QUERY PREHOOK: Input: default@part @@ -2042,7 +2057,12 @@ POSTHOOK: query: select * from part where (p_size-1) NOT IN (select min(p_size) POSTHOOK: type: QUERY POSTHOOK: Input: default@part #### A masked pattern was here #### +105685 almond antique violet chocolate turquoise Manufacturer#2 Brand#22 MEDIUM ANODIZED COPPER 14 MED CAN 1690.68 ly pending requ +110592 almond antique salmon chartreuse burlywood Manufacturer#1 Brand#15 PROMO BURNISHED NICKEL 6 JUMBO PKG 1602.59 to the furiously +132666 almond aquamarine rose maroon antique Manufacturer#2 Brand#24 SMALL POLISHED NICKEL 25 MED BOX 1698.66 even +144293 almond antique olive coral navajo Manufacturer#3 Brand#34 STANDARD POLISHED STEEL 45 JUMBO CAN 1337.29 ag furiously about 17273 almond antique forest lavender goldenrod Manufacturer#3 Brand#35 PROMO ANODIZED TIN 14 JUMBO CASE 1190.27 along the +192697 almond antique blue firebrick mint Manufacturer#5 Brand#52 MEDIUM BURNISHED TIN 31 LG DRUM 1789.69 ickly ir 33357 almond azure aquamarine papaya violet Manufacturer#4 Brand#41 STANDARD ANODIZED TIN 12 WRAP CASE 1290.35 reful 40982 almond antique misty red olive Manufacturer#3 Brand#32 ECONOMY PLATED COPPER 1 LG PKG 1922.98 c foxes can s 42669 almond antique medium spring khaki Manufacturer#5 Brand#51 STANDARD BURNISHED TIN 6 MED CAN 1611.66 sits haggl @@ -2053,12 +2073,7 @@ POSTHOOK: Input: default@part 78486 almond azure blanched chiffon midnight Manufacturer#5 Brand#52 LARGE BRUSHED BRASS 23 MED BAG 1464.48 hely blith 85768 almond antique chartreuse lavender yellow Manufacturer#1 Brand#12 LARGE BRUSHED STEEL 34 SM BAG 1753.76 refull 90681 almond antique chartreuse khaki white Manufacturer#3 Brand#31 MEDIUM BURNISHED TIN 17 SM CASE 1671.68 are slyly after the sl -105685 almond antique violet chocolate turquoise Manufacturer#2 Brand#22 MEDIUM ANODIZED COPPER 14 MED CAN 1690.68 ly pending requ -110592 almond antique salmon chartreuse burlywood Manufacturer#1 Brand#15 PROMO BURNISHED NICKEL 6 JUMBO PKG 1602.59 to the furiously -132666 almond aquamarine rose maroon antique Manufacturer#2 Brand#24 SMALL POLISHED NICKEL 25 MED BOX 1698.66 even -144293 almond antique olive coral navajo Manufacturer#3 Brand#34 STANDARD POLISHED STEEL 45 JUMBO CAN 1337.29 ag furiously about -192697 almond antique blue firebrick mint Manufacturer#5 Brand#52 MEDIUM BURNISHED TIN 31 LG DRUM 1789.69 ickly ir -Warning: Shuffle Join JOIN[26][tables = [$hdt$_0, $hdt$_1]] in Work 'Reducer 2' is a cross product +Warning: Shuffle Join JOIN[29][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Work 'Reducer 3' is a cross product PREHOOK: query: explain select * from part where (p_partkey*p_size) NOT IN (select min(p_partkey) from part group by p_type) PREHOOK: type: QUERY PREHOOK: Input: default@part @@ -2075,12 +2090,12 @@ STAGE PLANS: Stage: Stage-1 Spark Edges: - Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 1), Reducer 6 (PARTITION-LEVEL SORT, 1) - Reducer 3 <- Reducer 2 (PARTITION-LEVEL SORT, 2), Reducer 9 (PARTITION-LEVEL SORT, 2) + Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 2), Reducer 6 (PARTITION-LEVEL SORT, 2) + Reducer 3 <- Reducer 2 (PARTITION-LEVEL SORT, 1), Reducer 9 (PARTITION-LEVEL SORT, 1) Reducer 5 <- Map 4 (GROUP, 2) - Reducer 6 <- Reducer 5 (GROUP, 1) + Reducer 6 <- Reducer 5 (GROUP, 2) Reducer 8 <- Map 4 (GROUP, 2) - Reducer 9 <- Reducer 8 (GROUP, 2) + Reducer 9 <- Reducer 8 (GROUP, 1) #### A masked pattern was here #### Vertices: Map 1 @@ -2093,7 +2108,9 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - sort order: + key expressions: (_col0 * _col5) (type: int) + sort order: + + Map-reduce partition columns: (_col0 * _col5) (type: int) Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) Execution mode: vectorized @@ -2123,42 +2140,44 @@ STAGE PLANS: Reduce Operator Tree: Join Operator condition map: - Inner Join 0 to 1 + Left Outer Join 0 to 1 keys: - 0 - 1 - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10 - Statistics: Num rows: 26 Data size: 3589 Basic stats: COMPLETE Column stats: NONE + 0 (_col0 * _col5) (type: int) + 1 _col0 (type: int) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col10 + Statistics: Num rows: 28 Data size: 3461 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: (_col0 * _col5) (type: int) - sort order: + - Map-reduce partition columns: (_col0 * _col5) (type: int) - Statistics: Num rows: 26 Data size: 3589 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string), _col9 (type: bigint), _col10 (type: bigint) + sort order: + Statistics: Num rows: 28 Data size: 3461 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string), _col10 (type: boolean) Reducer 3 Reduce Operator Tree: Join Operator condition map: - Left Outer Join 0 to 1 + Inner Join 0 to 1 keys: - 0 (_col0 * _col5) (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col12 - Statistics: Num rows: 28 Data size: 3947 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: ((_col12 is null and _col0 is not null and _col5 is not null and (_col10 >= _col9)) or (_col9 = 0L)) (type: boolean) - Statistics: Num rows: 18 Data size: 2537 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 18 Data size: 2537 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 18 Data size: 2537 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + 0 + 1 + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col10, _col11, _col12 + Statistics: Num rows: 28 Data size: 3937 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string), _col11 (type: bigint), _col12 (type: bigint), _col10 (type: boolean) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col12 + Statistics: Num rows: 28 Data size: 3937 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: ((_col12 is null and _col0 is not null and _col5 is not null and (_col10 >= _col9)) or (_col9 = 0L)) (type: boolean) + Statistics: Num rows: 18 Data size: 2530 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 + Statistics: Num rows: 18 Data size: 2530 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 18 Data size: 2530 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Reducer 5 Execution mode: vectorized Reduce Operator Tree: @@ -2173,26 +2192,33 @@ STAGE PLANS: outputColumnNames: _col1 Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(), count(_col1) + keys: _col1 (type: int) mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: _col0 + Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: bigint), _col1 (type: bigint) + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE Reducer 6 Execution mode: vectorized Reduce Operator Tree: Group By Operator - aggregations: count(VALUE._col0), count(VALUE._col1) + keys: KEY._col0 (type: int) mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: bigint), _col1 (type: bigint) + outputColumnNames: _col0 + Statistics: Num rows: 6 Data size: 726 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: int), true (type: boolean) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 6 Data size: 726 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 6 Data size: 726 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: boolean) Reducer 8 Execution mode: vectorized Reduce Operator Tree: @@ -2207,33 +2233,26 @@ STAGE PLANS: outputColumnNames: _col1 Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: _col1 (type: int) + aggregations: count(), count(_col1) mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE + sort order: + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: bigint), _col1 (type: bigint) Reducer 9 Execution mode: vectorized Reduce Operator Tree: Group By Operator - keys: KEY._col0 (type: int) + aggregations: count(VALUE._col0), count(VALUE._col1) mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 6 Data size: 726 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: int), true (type: boolean) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 6 Data size: 726 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 6 Data size: 726 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: boolean) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: bigint), _col1 (type: bigint) Stage: Stage-0 Fetch Operator @@ -2241,7 +2260,7 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Shuffle Join JOIN[26][tables = [$hdt$_0, $hdt$_1]] in Work 'Reducer 2' is a cross product +Warning: Shuffle Join JOIN[29][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Work 'Reducer 3' is a cross product PREHOOK: query: select * from part where (p_partkey*p_size) NOT IN (select min(p_partkey) from part group by p_type) PREHOOK: type: QUERY PREHOOK: Input: default@part @@ -2250,31 +2269,31 @@ POSTHOOK: query: select * from part where (p_partkey*p_size) NOT IN (select min( POSTHOOK: type: QUERY POSTHOOK: Input: default@part #### A masked pattern was here #### -17927 almond aquamarine yellow dodger mint Manufacturer#4 Brand#41 ECONOMY BRUSHED COPPER 7 SM PKG 1844.92 ites. eve +105685 almond antique violet chocolate turquoise Manufacturer#2 Brand#22 MEDIUM ANODIZED COPPER 14 MED CAN 1690.68 ly pending requ +110592 almond antique salmon chartreuse burlywood Manufacturer#1 Brand#15 PROMO BURNISHED NICKEL 6 JUMBO PKG 1602.59 to the furiously +112398 almond antique metallic orange dim Manufacturer#3 Brand#32 MEDIUM BURNISHED BRASS 19 JUMBO JAR 1410.39 ole car 121152 almond antique burnished rose metallic Manufacturer#1 Brand#14 PROMO PLATED TIN 2 JUMBO BOX 1173.15 e pinto beans h 121152 almond antique burnished rose metallic Manufacturer#1 Brand#14 PROMO PLATED TIN 2 JUMBO BOX 1173.15 e pinto beans h -42669 almond antique medium spring khaki Manufacturer#5 Brand#51 STANDARD BURNISHED TIN 6 MED CAN 1611.66 sits haggl +132666 almond aquamarine rose maroon antique Manufacturer#2 Brand#24 SMALL POLISHED NICKEL 25 MED BOX 1698.66 even +144293 almond antique olive coral navajo Manufacturer#3 Brand#34 STANDARD POLISHED STEEL 45 JUMBO CAN 1337.29 ag furiously about 146985 almond aquamarine midnight light salmon Manufacturer#2 Brand#23 MEDIUM BURNISHED COPPER 2 SM CASE 2031.98 s cajole caref 15103 almond aquamarine dodger light gainsboro Manufacturer#5 Brand#53 ECONOMY BURNISHED STEEL 46 LG PACK 1018.1 packages hinder carefu -78486 almond azure blanched chiffon midnight Manufacturer#5 Brand#52 LARGE BRUSHED BRASS 23 MED BAG 1464.48 hely blith -112398 almond antique metallic orange dim Manufacturer#3 Brand#32 MEDIUM BURNISHED BRASS 19 JUMBO JAR 1410.39 ole car -132666 almond aquamarine rose maroon antique Manufacturer#2 Brand#24 SMALL POLISHED NICKEL 25 MED BOX 1698.66 even -191709 almond antique violet turquoise frosted Manufacturer#2 Brand#22 ECONOMY POLISHED STEEL 40 MED BOX 1800.7 haggle -17273 almond antique forest lavender goldenrod Manufacturer#3 Brand#35 PROMO ANODIZED TIN 14 JUMBO CASE 1190.27 along the 155733 almond antique sky peru orange Manufacturer#5 Brand#53 SMALL PLATED BRASS 2 WRAP DRUM 1788.73 furiously. bra +17273 almond antique forest lavender goldenrod Manufacturer#3 Brand#35 PROMO ANODIZED TIN 14 JUMBO CASE 1190.27 along the +17927 almond aquamarine yellow dodger mint Manufacturer#4 Brand#41 ECONOMY BRUSHED COPPER 7 SM PKG 1844.92 ites. eve +191709 almond antique violet turquoise frosted Manufacturer#2 Brand#22 ECONOMY POLISHED STEEL 40 MED BOX 1800.7 haggle +192697 almond antique blue firebrick mint Manufacturer#5 Brand#52 MEDIUM BURNISHED TIN 31 LG DRUM 1789.69 ickly ir +195606 almond aquamarine sandy cyan gainsboro Manufacturer#2 Brand#25 STANDARD PLATED TIN 18 SM PKG 1701.6 ic de 33357 almond azure aquamarine papaya violet Manufacturer#4 Brand#41 STANDARD ANODIZED TIN 12 WRAP CASE 1290.35 reful -49671 almond antique gainsboro frosted violet Manufacturer#4 Brand#41 SMALL BRUSHED BRASS 10 SM BOX 1620.67 ccounts run quick -110592 almond antique salmon chartreuse burlywood Manufacturer#1 Brand#15 PROMO BURNISHED NICKEL 6 JUMBO PKG 1602.59 to the furiously +42669 almond antique medium spring khaki Manufacturer#5 Brand#51 STANDARD BURNISHED TIN 6 MED CAN 1611.66 sits haggl 45261 almond aquamarine floral ivory bisque Manufacturer#4 Brand#42 SMALL PLATED STEEL 27 WRAP CASE 1206.26 careful -105685 almond antique violet chocolate turquoise Manufacturer#2 Brand#22 MEDIUM ANODIZED COPPER 14 MED CAN 1690.68 ly pending requ -90681 almond antique chartreuse khaki white Manufacturer#3 Brand#31 MEDIUM BURNISHED TIN 17 SM CASE 1671.68 are slyly after the sl 48427 almond antique violet mint lemon Manufacturer#4 Brand#42 PROMO POLISHED STEEL 39 SM CASE 1375.42 hely ironic i -86428 almond aquamarine burnished black steel Manufacturer#1 Brand#12 STANDARD ANODIZED STEEL 28 WRAP BAG 1414.42 arefully +49671 almond antique gainsboro frosted violet Manufacturer#4 Brand#41 SMALL BRUSHED BRASS 10 SM BOX 1620.67 ccounts run quick 65667 almond aquamarine pink moccasin thistle Manufacturer#1 Brand#12 LARGE BURNISHED STEEL 42 JUMBO CASE 1632.66 e across the expr +78486 almond azure blanched chiffon midnight Manufacturer#5 Brand#52 LARGE BRUSHED BRASS 23 MED BAG 1464.48 hely blith 85768 almond antique chartreuse lavender yellow Manufacturer#1 Brand#12 LARGE BRUSHED STEEL 34 SM BAG 1753.76 refull -195606 almond aquamarine sandy cyan gainsboro Manufacturer#2 Brand#25 STANDARD PLATED TIN 18 SM PKG 1701.6 ic de -192697 almond antique blue firebrick mint Manufacturer#5 Brand#52 MEDIUM BURNISHED TIN 31 LG DRUM 1789.69 ickly ir -144293 almond antique olive coral navajo Manufacturer#3 Brand#34 STANDARD POLISHED STEEL 45 JUMBO CAN 1337.29 ag furiously about +86428 almond aquamarine burnished black steel Manufacturer#1 Brand#12 STANDARD ANODIZED STEEL 28 WRAP BAG 1414.42 arefully +90681 almond antique chartreuse khaki white Manufacturer#3 Brand#31 MEDIUM BURNISHED TIN 17 SM CASE 1671.68 are slyly after the sl PREHOOK: query: explain select count(*) as c from part as e where p_size + 100 NOT IN (select p_partkey from part where p_name = e.p_name) PREHOOK: type: QUERY PREHOOK: Input: default@part @@ -2512,7 +2531,7 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@part #### A masked pattern was here #### 26 -Warning: Shuffle Join JOIN[26][tables = [$hdt$_0, $hdt$_1]] in Work 'Reducer 2' is a cross product +Warning: Shuffle Join JOIN[29][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Work 'Reducer 3' is a cross product PREHOOK: query: explain select * from part where floor(p_retailprice) NOT IN (select floor(min(p_retailprice)) from part group by p_type) PREHOOK: type: QUERY PREHOOK: Input: default@part @@ -2529,12 +2548,12 @@ STAGE PLANS: Stage: Stage-1 Spark Edges: - Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 1), Reducer 6 (PARTITION-LEVEL SORT, 1) - Reducer 3 <- Reducer 2 (PARTITION-LEVEL SORT, 2), Reducer 9 (PARTITION-LEVEL SORT, 2) + Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 2), Reducer 6 (PARTITION-LEVEL SORT, 2) + Reducer 3 <- Reducer 2 (PARTITION-LEVEL SORT, 1), Reducer 9 (PARTITION-LEVEL SORT, 1) Reducer 5 <- Map 4 (GROUP, 2) - Reducer 6 <- Reducer 5 (GROUP, 1) + Reducer 6 <- Reducer 5 (GROUP, 2) Reducer 8 <- Map 4 (GROUP, 2) - Reducer 9 <- Reducer 8 (GROUP, 2) + Reducer 9 <- Reducer 8 (GROUP, 1) #### A masked pattern was here #### Vertices: Map 1 @@ -2547,7 +2566,9 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - sort order: + key expressions: floor(_col7) (type: bigint) + sort order: + + Map-reduce partition columns: floor(_col7) (type: bigint) Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) Execution mode: vectorized @@ -2577,42 +2598,44 @@ STAGE PLANS: Reduce Operator Tree: Join Operator condition map: - Inner Join 0 to 1 + Left Outer Join 0 to 1 keys: - 0 - 1 - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10 - Statistics: Num rows: 26 Data size: 3589 Basic stats: COMPLETE Column stats: NONE + 0 floor(_col7) (type: bigint) + 1 _col0 (type: bigint) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col10 + Statistics: Num rows: 28 Data size: 3461 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: floor(_col7) (type: bigint) - sort order: + - Map-reduce partition columns: floor(_col7) (type: bigint) - Statistics: Num rows: 26 Data size: 3589 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string), _col9 (type: bigint), _col10 (type: bigint) + sort order: + Statistics: Num rows: 28 Data size: 3461 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string), _col10 (type: boolean) Reducer 3 Reduce Operator Tree: Join Operator condition map: - Left Outer Join 0 to 1 + Inner Join 0 to 1 keys: - 0 floor(_col7) (type: bigint) - 1 _col0 (type: bigint) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col12 - Statistics: Num rows: 28 Data size: 3947 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: ((_col12 is null and _col7 is not null and (_col10 >= _col9)) or (_col9 = 0L)) (type: boolean) - Statistics: Num rows: 18 Data size: 2537 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 18 Data size: 2537 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 18 Data size: 2537 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + 0 + 1 + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col10, _col11, _col12 + Statistics: Num rows: 28 Data size: 3937 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string), _col11 (type: bigint), _col12 (type: bigint), _col10 (type: boolean) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col12 + Statistics: Num rows: 28 Data size: 3937 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: ((_col12 is null and _col7 is not null and (_col10 >= _col9)) or (_col9 = 0L)) (type: boolean) + Statistics: Num rows: 18 Data size: 2530 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 + Statistics: Num rows: 18 Data size: 2530 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 18 Data size: 2530 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Reducer 5 Execution mode: vectorized Reduce Operator Tree: @@ -2627,26 +2650,33 @@ STAGE PLANS: outputColumnNames: _col0 Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(), count(_col0) + keys: _col0 (type: bigint) mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: _col0 + Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: bigint), _col1 (type: bigint) + key expressions: _col0 (type: bigint) + sort order: + + Map-reduce partition columns: _col0 (type: bigint) + Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE Reducer 6 Execution mode: vectorized Reduce Operator Tree: Group By Operator - aggregations: count(VALUE._col0), count(VALUE._col1) + keys: KEY._col0 (type: bigint) mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: bigint), _col1 (type: bigint) + outputColumnNames: _col0 + Statistics: Num rows: 6 Data size: 726 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: bigint), true (type: boolean) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 6 Data size: 726 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: bigint) + sort order: + + Map-reduce partition columns: _col0 (type: bigint) + Statistics: Num rows: 6 Data size: 726 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: boolean) Reducer 8 Execution mode: vectorized Reduce Operator Tree: @@ -2661,33 +2691,26 @@ STAGE PLANS: outputColumnNames: _col0 Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: _col0 (type: bigint) + aggregations: count(), count(_col0) mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: bigint) - sort order: + - Map-reduce partition columns: _col0 (type: bigint) - Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE + sort order: +
<TRUNCATED>