http://git-wip-us.apache.org/repos/asf/hive/blob/10423f51/ql/src/test/results/clientpositive/llap/tez_vector_dynpart_hashjoin_1.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/llap/tez_vector_dynpart_hashjoin_1.q.out b/ql/src/test/results/clientpositive/llap/tez_vector_dynpart_hashjoin_1.q.out index 17d5992..d02e096 100644 --- a/ql/src/test/results/clientpositive/llap/tez_vector_dynpart_hashjoin_1.q.out +++ b/ql/src/test/results/clientpositive/llap/tez_vector_dynpart_hashjoin_1.q.out @@ -55,7 +55,7 @@ STAGE PLANS: alias: a Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (cint BETWEEN 1000000 AND 3000000 and cbigint is not null) (type: boolean) + predicate: (cint is not null and cbigint is not null and cint BETWEEN 1000000 AND 3000000) (type: boolean) Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctinyint (type: tinyint), csmallint (type: smallint), cint (type: int), cbigint (type: bigint), cfloat (type: float), cdouble (type: double), cstring1 (type: string), cstring2 (type: string), ctimestamp1 (type: timestamp), ctimestamp2 (type: timestamp), cboolean1 (type: boolean), cboolean2 (type: boolean) @@ -186,7 +186,7 @@ STAGE PLANS: alias: a Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (cint BETWEEN 1000000 AND 3000000 and cbigint is not null) (type: boolean) + predicate: (cint is not null and cbigint is not null and cint BETWEEN 1000000 AND 3000000) (type: boolean) Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cint (type: int) @@ -315,7 +315,7 @@ STAGE PLANS: alias: a Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (cint BETWEEN 1000000 AND 3000000 and cbigint is not null) (type: boolean) + predicate: (cint is not null and cbigint is not null and cint BETWEEN 1000000 AND 3000000) (type: boolean) Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cint (type: int) @@ -468,7 +468,7 @@ STAGE PLANS: alias: a Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (cint BETWEEN 1000000 AND 3000000 and cbigint is not null) (type: boolean) + predicate: (cint is not null and cbigint is not null and cint BETWEEN 1000000 AND 3000000) (type: boolean) Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctinyint (type: tinyint), csmallint (type: smallint), cint (type: int), cbigint (type: bigint), cfloat (type: float), cdouble (type: double), cstring1 (type: string), cstring2 (type: string), ctimestamp1 (type: timestamp), ctimestamp2 (type: timestamp), cboolean1 (type: boolean), cboolean2 (type: boolean) @@ -602,7 +602,7 @@ STAGE PLANS: alias: a Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (cint BETWEEN 1000000 AND 3000000 and cbigint is not null) (type: boolean) + predicate: (cint is not null and cbigint is not null and cint BETWEEN 1000000 AND 3000000) (type: boolean) Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cint (type: int) @@ -734,7 +734,7 @@ STAGE PLANS: alias: a Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (cint BETWEEN 1000000 AND 3000000 and cbigint is not null) (type: boolean) + predicate: (cint is not null and cbigint is not null and cint BETWEEN 1000000 AND 3000000) (type: boolean) Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cint (type: int)
http://git-wip-us.apache.org/repos/asf/hive/blob/10423f51/ql/src/test/results/clientpositive/llap/vectorized_dynamic_partition_pruning.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/llap/vectorized_dynamic_partition_pruning.q.out b/ql/src/test/results/clientpositive/llap/vectorized_dynamic_partition_pruning.q.out index 9475487..b0f3071 100644 --- a/ql/src/test/results/clientpositive/llap/vectorized_dynamic_partition_pruning.q.out +++ b/ql/src/test/results/clientpositive/llap/vectorized_dynamic_partition_pruning.q.out @@ -1388,12 +1388,12 @@ STAGE PLANS: outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: UDFToDouble(UDFToInteger((_col0 / UDFToDouble(2)))) (type: double) + key expressions: UDFToDouble(UDFToInteger((_col0 / 2.0))) (type: double) sort order: + - Map-reduce partition columns: UDFToDouble(UDFToInteger((_col0 / UDFToDouble(2)))) (type: double) + Map-reduce partition columns: UDFToDouble(UDFToInteger((_col0 / 2.0))) (type: double) Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: UDFToDouble(UDFToInteger((_col0 / UDFToDouble(2)))) (type: double) + expressions: UDFToDouble(UDFToInteger((_col0 / 2.0))) (type: double) outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE Group By Operator @@ -1417,7 +1417,7 @@ STAGE PLANS: Inner Join 0 to 1 keys: 0 UDFToDouble(_col0) (type: double) - 1 UDFToDouble(UDFToInteger((_col0 / UDFToDouble(2)))) (type: double) + 1 UDFToDouble(UDFToInteger((_col0 / 2.0))) (type: double) Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() @@ -1497,9 +1497,9 @@ STAGE PLANS: outputColumnNames: _col0 Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: (UDFToDouble(_col0) * UDFToDouble(2)) (type: double) + key expressions: (UDFToDouble(_col0) * 2.0) (type: double) sort order: + - Map-reduce partition columns: (UDFToDouble(_col0) * UDFToDouble(2)) (type: double) + Map-reduce partition columns: (UDFToDouble(_col0) * 2.0) (type: double) Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Execution mode: llap LLAP IO: no inputs @@ -1545,7 +1545,7 @@ STAGE PLANS: condition map: Inner Join 0 to 1 keys: - 0 (UDFToDouble(_col0) * UDFToDouble(2)) (type: double) + 0 (UDFToDouble(_col0) * 2.0) (type: double) 1 _col0 (type: double) Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE Group By Operator @@ -1646,9 +1646,9 @@ STAGE PLANS: outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: UDFToDouble(UDFToInteger((_col0 / UDFToDouble(2)))) (type: double) + key expressions: UDFToDouble(UDFToInteger((_col0 / 2.0))) (type: double) sort order: + - Map-reduce partition columns: UDFToDouble(UDFToInteger((_col0 / UDFToDouble(2)))) (type: double) + Map-reduce partition columns: UDFToDouble(UDFToInteger((_col0 / 2.0))) (type: double) Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized, llap LLAP IO: all inputs @@ -1660,7 +1660,7 @@ STAGE PLANS: Inner Join 0 to 1 keys: 0 UDFToDouble(_col0) (type: double) - 1 UDFToDouble(UDFToInteger((_col0 / UDFToDouble(2)))) (type: double) + 1 UDFToDouble(UDFToInteger((_col0 / 2.0))) (type: double) Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() @@ -1740,9 +1740,9 @@ STAGE PLANS: outputColumnNames: _col0 Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: (UDFToDouble(_col0) * UDFToDouble(2)) (type: double) + key expressions: (UDFToDouble(_col0) * 2.0) (type: double) sort order: + - Map-reduce partition columns: (UDFToDouble(_col0) * UDFToDouble(2)) (type: double) + Map-reduce partition columns: (UDFToDouble(_col0) * 2.0) (type: double) Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Execution mode: llap LLAP IO: no inputs @@ -1773,7 +1773,7 @@ STAGE PLANS: condition map: Inner Join 0 to 1 keys: - 0 (UDFToDouble(_col0) * UDFToDouble(2)) (type: double) + 0 (UDFToDouble(_col0) * 2.0) (type: double) 1 _col0 (type: double) Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE Group By Operator @@ -1867,9 +1867,9 @@ STAGE PLANS: outputColumnNames: _col0 Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: UDFToString((UDFToDouble(_col0) * UDFToDouble(2))) (type: string) + key expressions: UDFToString((UDFToDouble(_col0) * 2.0)) (type: string) sort order: + - Map-reduce partition columns: UDFToString((UDFToDouble(_col0) * UDFToDouble(2))) (type: string) + Map-reduce partition columns: UDFToString((UDFToDouble(_col0) * 2.0)) (type: string) Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Execution mode: llap LLAP IO: no inputs @@ -1915,7 +1915,7 @@ STAGE PLANS: condition map: Inner Join 0 to 1 keys: - 0 UDFToString((UDFToDouble(_col0) * UDFToDouble(2))) (type: string) + 0 UDFToString((UDFToDouble(_col0) * 2.0)) (type: string) 1 UDFToString(_col0) (type: string) Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE Group By Operator @@ -1981,6 +1981,7 @@ POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 #### A masked pattern was here #### 1000 +Warning: Shuffle Join MERGEJOIN[22][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product PREHOOK: query: -- parent is reduce tasks EXPLAIN select count(*) from srcpart join (select ds as ds, ds as `date` from srcpart group by ds) s on (srcpart.ds = s.ds) where s.`date` = '2008-04-08' PREHOOK: type: QUERY @@ -2005,17 +2006,13 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcpart - filterExpr: ds is not null (type: boolean) - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + filterExpr: (ds = '2008-04-08') (type: boolean) + Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: ds (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 10624 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: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + sort order: + Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Execution mode: llap LLAP IO: no inputs Map 4 @@ -2024,16 +2021,18 @@ STAGE PLANS: alias: srcpart filterExpr: (ds = '2008-04-08') (type: boolean) Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: '2008-04-08' (type: string) - mode: hash - outputColumnNames: _col0 + Select Operator Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: '2008-04-08' (type: string) - sort order: + - Map-reduce partition columns: '2008-04-08' (type: string) + Group By Operator + keys: '2008-04-08' (type: string) + mode: hash + outputColumnNames: _col0 Statistics: Num rows: 1000 Data size: 10624 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: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Execution mode: llap LLAP IO: no inputs Reducer 2 @@ -2043,9 +2042,9 @@ STAGE PLANS: condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 '2008-04-08' (type: string) - Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE + 0 + 1 + Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() mode: hash @@ -2074,32 +2073,15 @@ STAGE PLANS: Execution mode: vectorized, llap Reduce Operator Tree: Group By Operator - keys: '2008-04-08' (type: string) + keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: '2008-04-08' (type: string) - sort order: + - Map-reduce partition columns: '2008-04-08' (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: '2008-04-08' (type: string) - outputColumnNames: _col0 + sort order: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Dynamic Partitioning Event Operator - Target column: ds (string) - Target Input: srcpart - Partition key expr: ds - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Target Vertex: Map 1 Stage: Stage-0 Fetch Operator @@ -2107,21 +2089,18 @@ STAGE PLANS: Processor Tree: ListSink +Warning: Shuffle Join MERGEJOIN[22][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product PREHOOK: query: select count(*) from srcpart join (select ds as ds, ds as `date` from srcpart group by ds) s on (srcpart.ds = s.ds) where s.`date` = '2008-04-08' PREHOOK: type: QUERY PREHOOK: Input: default@srcpart PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 -PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 -PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 #### A masked pattern was here #### POSTHOOK: query: select count(*) from srcpart join (select ds as ds, ds as `date` from srcpart group by ds) s on (srcpart.ds = s.ds) where s.`date` = '2008-04-08' POSTHOOK: type: QUERY POSTHOOK: Input: default@srcpart POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 -POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 -POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 #### A masked pattern was here #### 1000 PREHOOK: query: select count(*) from srcpart where ds = '2008-04-08' @@ -2137,7 +2116,7 @@ POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 #### A masked pattern was here #### 1000 -Warning: Shuffle Join MERGEJOIN[17][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product +Warning: Shuffle Join MERGEJOIN[16][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product PREHOOK: query: -- non-equi join EXPLAIN select count(*) from srcpart, srcpart_date_hour where (srcpart_date_hour.`date` = '2008-04-08' and srcpart_date_hour.hour = 11) and (srcpart.ds = srcpart_date_hour.ds or srcpart.hr = srcpart_date_hour.hr) PREHOOK: type: QUERY @@ -2238,7 +2217,7 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Shuffle Join MERGEJOIN[17][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product +Warning: Shuffle Join MERGEJOIN[16][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product PREHOOK: query: select count(*) from srcpart, srcpart_date_hour where (srcpart_date_hour.`date` = '2008-04-08' and srcpart_date_hour.hour = 11) and (srcpart.ds = srcpart_date_hour.ds or srcpart.hr = srcpart_date_hour.hr) PREHOOK: type: QUERY PREHOOK: Input: default@srcpart @@ -4372,7 +4351,7 @@ STAGE PLANS: Inner Join 0 to 1 keys: 0 UDFToDouble(_col0) (type: double) - 1 UDFToDouble(UDFToInteger((_col0 / UDFToDouble(2)))) (type: double) + 1 UDFToDouble(UDFToInteger((_col0 / 2.0))) (type: double) input vertices: 1 Map 3 Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE @@ -4401,12 +4380,12 @@ STAGE PLANS: outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: UDFToDouble(UDFToInteger((_col0 / UDFToDouble(2)))) (type: double) + key expressions: UDFToDouble(UDFToInteger((_col0 / 2.0))) (type: double) sort order: + - Map-reduce partition columns: UDFToDouble(UDFToInteger((_col0 / UDFToDouble(2)))) (type: double) + Map-reduce partition columns: UDFToDouble(UDFToInteger((_col0 / 2.0))) (type: double) Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: UDFToDouble(UDFToInteger((_col0 / UDFToDouble(2)))) (type: double) + expressions: UDFToDouble(UDFToInteger((_col0 / 2.0))) (type: double) outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE Group By Operator @@ -4494,7 +4473,7 @@ STAGE PLANS: condition map: Inner Join 0 to 1 keys: - 0 (UDFToDouble(_col0) * UDFToDouble(2)) (type: double) + 0 (UDFToDouble(_col0) * 2.0) (type: double) 1 _col0 (type: double) input vertices: 1 Map 3 @@ -4599,6 +4578,7 @@ POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 #### A masked pattern was here #### 1000 +Warning: Map Join MAPJOIN[22][bigTable=?] in task 'Reducer 3' is a cross product PREHOOK: query: -- parent is reduce tasks EXPLAIN select count(*) from srcpart join (select ds as ds, ds as `date` from srcpart group by ds) s on (srcpart.ds = s.ds) where s.`date` = '2008-04-08' PREHOOK: type: QUERY @@ -4614,60 +4594,72 @@ STAGE PLANS: Tez #### A masked pattern was here #### Edges: - Map 1 <- Reducer 4 (BROADCAST_EDGE) - Reducer 2 <- Map 1 (SIMPLE_EDGE) - Reducer 4 <- Map 3 (SIMPLE_EDGE) + Reducer 3 <- Map 1 (BROADCAST_EDGE), Map 2 (SIMPLE_EDGE) + Reducer 4 <- Reducer 3 (SIMPLE_EDGE) #### A masked pattern was here #### Vertices: Map 1 Map Operator Tree: TableScan alias: srcpart - filterExpr: ds is not null (type: boolean) - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + filterExpr: (ds = '2008-04-08') (type: boolean) + Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: ds (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 '2008-04-08' (type: string) - input vertices: - 1 Reducer 4 - Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: bigint) + Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + sort order: + Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Execution mode: llap LLAP IO: no inputs - Map 3 + Map 2 Map Operator Tree: TableScan alias: srcpart filterExpr: (ds = '2008-04-08') (type: boolean) Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: '2008-04-08' (type: string) - mode: hash - outputColumnNames: _col0 + Select Operator Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: '2008-04-08' (type: string) - sort order: + - Map-reduce partition columns: '2008-04-08' (type: string) + Group By Operator + keys: '2008-04-08' (type: string) + mode: hash + outputColumnNames: _col0 Statistics: Num rows: 1000 Data size: 10624 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: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Execution mode: llap LLAP IO: no inputs - Reducer 2 + Reducer 3 + Execution mode: vectorized, llap + Reduce Operator Tree: + Group By Operator + keys: KEY._col0 (type: string) + mode: mergepartial + outputColumnNames: _col0 + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Select Operator + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 + 1 + input vertices: + 0 Map 1 + Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: bigint) + Reducer 4 Execution mode: vectorized, llap Reduce Operator Tree: Group By Operator @@ -4682,36 +4674,6 @@ 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 - Reducer 4 - Execution mode: vectorized, llap - Reduce Operator Tree: - Group By Operator - keys: '2008-04-08' (type: string) - mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Select Operator - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: '2008-04-08' (type: string) - sort order: + - Map-reduce partition columns: '2008-04-08' (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: '2008-04-08' (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Dynamic Partitioning Event Operator - Target column: ds (string) - Target Input: srcpart - Partition key expr: ds - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Target Vertex: Map 1 Stage: Stage-0 Fetch Operator @@ -4719,21 +4681,18 @@ STAGE PLANS: Processor Tree: ListSink +Warning: Map Join MAPJOIN[22][bigTable=?] in task 'Reducer 3' is a cross product PREHOOK: query: select count(*) from srcpart join (select ds as ds, ds as `date` from srcpart group by ds) s on (srcpart.ds = s.ds) where s.`date` = '2008-04-08' PREHOOK: type: QUERY PREHOOK: Input: default@srcpart PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 -PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 -PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 #### A masked pattern was here #### POSTHOOK: query: select count(*) from srcpart join (select ds as ds, ds as `date` from srcpart group by ds) s on (srcpart.ds = s.ds) where s.`date` = '2008-04-08' POSTHOOK: type: QUERY POSTHOOK: Input: default@srcpart POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 -POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 -POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 #### A masked pattern was here #### 1000 PREHOOK: query: select count(*) from srcpart where ds = '2008-04-08' http://git-wip-us.apache.org/repos/asf/hive/blob/10423f51/ql/src/test/results/clientpositive/masking_2.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/masking_2.q.out b/ql/src/test/results/clientpositive/masking_2.q.out index f998cbd..ff045a9 100644 --- a/ql/src/test/results/clientpositive/masking_2.q.out +++ b/ql/src/test/results/clientpositive/masking_2.q.out @@ -192,7 +192,7 @@ STAGE PLANS: alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((UDFToInteger(key) % 2) = 0) and (UDFToInteger(key) < 10) and UDFToInteger(key) is not null) (type: boolean) + predicate: (((UDFToInteger(key) % 2) = 0) and (UDFToInteger(key) < 10)) (type: boolean) Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: UDFToInteger(key) (type: int), reverse(value) (type: string) http://git-wip-us.apache.org/repos/asf/hive/blob/10423f51/ql/src/test/results/clientpositive/mergejoin.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/mergejoin.q.out b/ql/src/test/results/clientpositive/mergejoin.q.out index a85fd8b..8dd86de 100644 --- a/ql/src/test/results/clientpositive/mergejoin.q.out +++ b/ql/src/test/results/clientpositive/mergejoin.q.out @@ -2692,6 +2692,7 @@ POSTHOOK: Input: default@tab_part@ds=2008-04-08 #### A masked pattern was here #### NULL NULL NULL 98 val_98 2008-04-08 NULL NULL NULL 98 val_98 2008-04-08 +Warning: Shuffle Join JOIN[14][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Stage-2:MAPRED' is a cross product PREHOOK: query: select * from (select * from tab where tab.key = 0)a full outer join @@ -2699,6 +2700,7 @@ full outer join PREHOOK: type: QUERY PREHOOK: Input: default@tab PREHOOK: Input: default@tab_part +PREHOOK: Input: default@tab_part@ds=2008-04-08 #### A masked pattern was here #### POSTHOOK: query: select * from (select * from tab where tab.key = 0)a @@ -2707,7 +2709,9 @@ full outer join POSTHOOK: type: QUERY POSTHOOK: Input: default@tab POSTHOOK: Input: default@tab_part +POSTHOOK: Input: default@tab_part@ds=2008-04-08 #### A masked pattern was here #### +Warning: Shuffle Join JOIN[14][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Stage-2:MAPRED' is a cross product PREHOOK: query: select * from (select * from tab where tab.key = 0)a full outer join @@ -2730,7 +2734,7 @@ NULL NULL NULL 98 val_98 2008-04-08 98 val_98 2008-04-08 NULL NULL NULL 98 val_98 2008-04-08 98 val_98 2008-04-08 NULL NULL NULL 98 val_98 2008-04-08 98 val_98 2008-04-08 NULL NULL NULL 98 val_98 2008-04-08 98 val_98 2008-04-08 -Warning: Shuffle Join JOIN[11][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product +Warning: Shuffle Join JOIN[10][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product PREHOOK: query: select * from (select * from tab where tab.key = 0)a join http://git-wip-us.apache.org/repos/asf/hive/blob/10423f51/ql/src/test/results/clientpositive/nonblock_op_deduplicate.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/nonblock_op_deduplicate.q.out b/ql/src/test/results/clientpositive/nonblock_op_deduplicate.q.out index ea25416..71ba502 100644 --- a/ql/src/test/results/clientpositive/nonblock_op_deduplicate.q.out +++ b/ql/src/test/results/clientpositive/nonblock_op_deduplicate.q.out @@ -37,7 +37,7 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Shuffle Join JOIN[11][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product +Warning: Shuffle Join JOIN[10][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product PREHOOK: query: -- This test query is introduced for HIVE-4968. -- First, we do not convert the join to MapJoin. EXPLAIN @@ -140,7 +140,7 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Shuffle Join JOIN[11][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product +Warning: Shuffle Join JOIN[10][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product PREHOOK: query: SELECT tmp4.key as key, tmp4.value as value, tmp4.count as count FROM (SELECT tmp2.key as key, tmp2.value as value, tmp3.count as count FROM (SELECT * @@ -188,7 +188,7 @@ POSTHOOK: Input: default@src1 406 val_406 25 66 val_66 25 98 val_98 25 -Warning: Map Join MAPJOIN[16][bigTable=?] in task 'Stage-3:MAPRED' is a cross product +Warning: Map Join MAPJOIN[15][bigTable=?] in task 'Stage-3:MAPRED' is a cross product PREHOOK: query: -- Then, we convert the join to MapJoin. EXPLAIN SELECT tmp4.key as key, tmp4.value as value, tmp4.count as count @@ -296,7 +296,7 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Map Join MAPJOIN[16][bigTable=?] in task 'Stage-3:MAPRED' is a cross product +Warning: Map Join MAPJOIN[15][bigTable=?] in task 'Stage-3:MAPRED' is a cross product PREHOOK: query: SELECT tmp4.key as key, tmp4.value as value, tmp4.count as count FROM (SELECT tmp2.key as key, tmp2.value as value, tmp3.count as count FROM (SELECT * http://git-wip-us.apache.org/repos/asf/hive/blob/10423f51/ql/src/test/results/clientpositive/orc_llap.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/orc_llap.q.out b/ql/src/test/results/clientpositive/orc_llap.q.out index bae69bb..658c41d 100644 --- a/ql/src/test/results/clientpositive/orc_llap.q.out +++ b/ql/src/test/results/clientpositive/orc_llap.q.out @@ -81,7 +81,7 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@alltypesorc POSTHOOK: Output: default@cross_numbers POSTHOOK: Lineage: cross_numbers.i EXPRESSION [(alltypesorc)alltypesorc.FieldSchema(name:csmallint, type:smallint, comment:null), ] -Warning: Shuffle Join JOIN[7][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product +Warning: Shuffle Join JOIN[6][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product PREHOOK: query: insert into table orc_llap select ctinyint + i, csmallint + i, cint + i, cbigint + i, cfloat + i, cdouble + i, cstring1, cstring2, ctimestamp1, ctimestamp2, cboolean1, cboolean2 from alltypesorc cross join cross_numbers @@ -121,7 +121,7 @@ POSTHOOK: Output: default@orc_llap_small POSTHOOK: Lineage: orc_llap_small.cint SIMPLE [(alltypesorc)alltypesorc.FieldSchema(name:cint, type:int, comment:null), ] POSTHOOK: Lineage: orc_llap_small.csmallint SIMPLE [(alltypesorc)alltypesorc.FieldSchema(name:csmallint, type:smallint, comment:null), ] POSTHOOK: Lineage: orc_llap_small.ctinyint SIMPLE [(alltypesorc)alltypesorc.FieldSchema(name:ctinyint, type:tinyint, comment:null), ] -Warning: Map Join MAPJOIN[17][bigTable=?] in task 'Stage-2:MAPRED' is a cross product +Warning: Map Join MAPJOIN[16][bigTable=?] in task 'Stage-2:MAPRED' is a cross product PREHOOK: query: -- Cross join with no projection - do it on small table explain select count(1) from orc_llap_small y join orc_llap_small x @@ -202,7 +202,7 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Map Join MAPJOIN[17][bigTable=?] in task 'Stage-2:MAPRED' is a cross product +Warning: Map Join MAPJOIN[16][bigTable=?] in task 'Stage-2:MAPRED' is a cross product PREHOOK: query: select count(1) from orc_llap_small y join orc_llap_small x PREHOOK: type: QUERY PREHOOK: Input: default@orc_llap_small @@ -657,7 +657,7 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@llap_temp_table #### A masked pattern was here #### -735462183586256 -Warning: Map Join MAPJOIN[11][bigTable=?] in task 'Stage-4:MAPRED' is a cross product +Warning: Map Join MAPJOIN[10][bigTable=?] in task 'Stage-4:MAPRED' is a cross product PREHOOK: query: -- multi-stripe test insert into table orc_llap select ctinyint + i, csmallint + i, cint + i, cbigint + i, cfloat + i, cdouble + i, cstring1, cstring2, ctimestamp1, ctimestamp2, cboolean1, cboolean2 http://git-wip-us.apache.org/repos/asf/hive/blob/10423f51/ql/src/test/results/clientpositive/partition_multilevels.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/partition_multilevels.q.out b/ql/src/test/results/clientpositive/partition_multilevels.q.out index 948d3a0..96aa76f 100644 --- a/ql/src/test/results/clientpositive/partition_multilevels.q.out +++ b/ql/src/test/results/clientpositive/partition_multilevels.q.out @@ -991,29 +991,29 @@ STAGE PLANS: Statistics: Num rows: 108 Data size: 1146 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: level2 (type: string), level3 (type: string) - outputColumnNames: _col1, _col2 + outputColumnNames: level2, level3 Statistics: Num rows: 108 Data size: 1146 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() - keys: '2222' (type: string), _col1 (type: string), _col2 (type: string) + keys: level2 (type: string), level3 (type: string) mode: hash - outputColumnNames: _col0, _col1, _col2, _col3 + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 108 Data size: 1146 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: '2222' (type: string), _col1 (type: string), _col2 (type: string) - sort order: +++ - Map-reduce partition columns: '2222' (type: string), _col1 (type: string), _col2 (type: string) + key expressions: _col0 (type: string), _col1 (type: string) + sort order: ++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string) Statistics: Num rows: 108 Data size: 1146 Basic stats: COMPLETE Column stats: NONE - value expressions: _col3 (type: bigint) + value expressions: _col2 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) - keys: '2222' (type: string), KEY._col1 (type: string), KEY._col2 (type: string) + keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1, _col2, _col3 + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 54 Data size: 573 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: '2222' (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: bigint) + expressions: '2222' (type: string), _col0 (type: string), _col1 (type: string), _col2 (type: bigint) outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 54 Data size: 573 Basic stats: COMPLETE Column stats: NONE File Output Operator @@ -1583,29 +1583,29 @@ STAGE PLANS: Statistics: Num rows: 108 Data size: 1146 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: level2 (type: string), level3 (type: string) - outputColumnNames: _col1, _col2 + outputColumnNames: level2, level3 Statistics: Num rows: 108 Data size: 1146 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() - keys: '2222' (type: string), _col1 (type: string), _col2 (type: string) + keys: level2 (type: string), level3 (type: string) mode: hash - outputColumnNames: _col0, _col1, _col2, _col3 + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 108 Data size: 1146 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: '2222' (type: string), _col1 (type: string), _col2 (type: string) - sort order: +++ - Map-reduce partition columns: '2222' (type: string), _col1 (type: string), _col2 (type: string) + key expressions: _col0 (type: string), _col1 (type: string) + sort order: ++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string) Statistics: Num rows: 108 Data size: 1146 Basic stats: COMPLETE Column stats: NONE - value expressions: _col3 (type: bigint) + value expressions: _col2 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) - keys: '2222' (type: string), KEY._col1 (type: string), KEY._col2 (type: string) + keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1, _col2, _col3 + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 54 Data size: 573 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: '2222' (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: bigint) + expressions: '2222' (type: string), _col0 (type: string), _col1 (type: string), _col2 (type: bigint) outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 54 Data size: 573 Basic stats: COMPLETE Column stats: NONE File Output Operator http://git-wip-us.apache.org/repos/asf/hive/blob/10423f51/ql/src/test/results/clientpositive/pcr.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/pcr.q.out b/ql/src/test/results/clientpositive/pcr.q.out index 7222617..9daddfb 100644 --- a/ql/src/test/results/clientpositive/pcr.q.out +++ b/ql/src/test/results/clientpositive/pcr.q.out @@ -1505,7 +1505,7 @@ STAGE PLANS: Needs Tagging: false Reduce Operator Tree: Select Operator - expressions: 14 (type: int), KEY.reducesinkkey1 (type: string) + expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE File Output Operator @@ -2327,23 +2327,27 @@ STAGE PLANS: 1 _col0 (type: int) outputColumnNames: _col0, _col1, _col3, _col4 Statistics: Num rows: 22 Data size: 176 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - GlobalTableId: 0 + Select Operator + expressions: _col0 (type: int), _col1 (type: string), '2000-04-08' (type: string), _col3 (type: int), _col4 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4 + Statistics: Num rows: 22 Data size: 176 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + GlobalTableId: 0 #### A masked pattern was here #### - NumFilesPerFileSink: 1 - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - columns _col0,_col1,_col3,_col4 - columns.types int,string,int,string - escape.delim \ - serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false + NumFilesPerFileSink: 1 + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + properties: + columns _col0,_col1,_col2,_col3,_col4 + columns.types int,string,string,int,string + escape.delim \ + serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false Stage: Stage-2 Map Reduce @@ -2356,7 +2360,7 @@ STAGE PLANS: sort order: + Statistics: Num rows: 22 Data size: 176 Basic stats: COMPLETE Column stats: NONE tag: -1 - value expressions: _col1 (type: string), _col3 (type: int), _col4 (type: string) + value expressions: _col1 (type: string), _col2 (type: string), _col3 (type: int), _col4 (type: string) auto parallelism: false Path -> Alias: #### A masked pattern was here #### @@ -2367,8 +2371,8 @@ STAGE PLANS: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: - columns _col0,_col1,_col3,_col4 - columns.types int,string,int,string + columns _col0,_col1,_col2,_col3,_col4 + columns.types int,string,string,int,string escape.delim \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe @@ -2376,8 +2380,8 @@ STAGE PLANS: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: - columns _col0,_col1,_col3,_col4 - columns.types int,string,int,string + columns _col0,_col1,_col2,_col3,_col4 + columns.types int,string,string,int,string escape.delim \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe @@ -2386,7 +2390,7 @@ STAGE PLANS: Needs Tagging: false Reduce Operator Tree: Select Operator - expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: string), '2000-04-08' (type: string), VALUE._col2 (type: int), VALUE._col3 (type: string), '2000-04-08' (type: string) + expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: string), VALUE._col1 (type: string), VALUE._col2 (type: int), VALUE._col3 (type: string), VALUE._col1 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 Statistics: Num rows: 22 Data size: 176 Basic stats: COMPLETE Column stats: NONE File Output Operator @@ -2627,23 +2631,27 @@ STAGE PLANS: 1 _col0 (type: int) outputColumnNames: _col0, _col1, _col3, _col4 Statistics: Num rows: 22 Data size: 176 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - GlobalTableId: 0 + Select Operator + expressions: _col0 (type: int), _col1 (type: string), '2000-04-08' (type: string), _col3 (type: int), _col4 (type: string), '2000-04-09' (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + Statistics: Num rows: 22 Data size: 176 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + GlobalTableId: 0 #### A masked pattern was here #### - NumFilesPerFileSink: 1 - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - columns _col0,_col1,_col3,_col4 - columns.types int,string,int,string - escape.delim \ - serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false + NumFilesPerFileSink: 1 + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + properties: + columns _col0,_col1,_col2,_col3,_col4,_col5 + columns.types int,string,string,int,string,string + escape.delim \ + serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false Stage: Stage-2 Map Reduce @@ -2656,7 +2664,7 @@ STAGE PLANS: sort order: + Statistics: Num rows: 22 Data size: 176 Basic stats: COMPLETE Column stats: NONE tag: -1 - value expressions: _col1 (type: string), _col3 (type: int), _col4 (type: string) + value expressions: _col1 (type: string), _col2 (type: string), _col3 (type: int), _col4 (type: string), _col5 (type: string) auto parallelism: false Path -> Alias: #### A masked pattern was here #### @@ -2667,8 +2675,8 @@ STAGE PLANS: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: - columns _col0,_col1,_col3,_col4 - columns.types int,string,int,string + columns _col0,_col1,_col2,_col3,_col4,_col5 + columns.types int,string,string,int,string,string escape.delim \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe @@ -2676,8 +2684,8 @@ STAGE PLANS: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: - columns _col0,_col1,_col3,_col4 - columns.types int,string,int,string + columns _col0,_col1,_col2,_col3,_col4,_col5 + columns.types int,string,string,int,string,string escape.delim \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe @@ -2686,7 +2694,7 @@ STAGE PLANS: Needs Tagging: false Reduce Operator Tree: Select Operator - expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: string), '2000-04-08' (type: string), VALUE._col2 (type: int), VALUE._col3 (type: string), '2000-04-09' (type: string) + expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: string), VALUE._col1 (type: string), VALUE._col2 (type: int), VALUE._col3 (type: string), VALUE._col4 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 Statistics: Num rows: 22 Data size: 176 Basic stats: COMPLETE Column stats: NONE File Output Operator @@ -4845,7 +4853,7 @@ STAGE PLANS: Needs Tagging: false Reduce Operator Tree: Select Operator - expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string), '2008-04-08' (type: string), KEY.reducesinkkey2 (type: string) + expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE File Output Operator @@ -5024,7 +5032,7 @@ STAGE PLANS: Needs Tagging: false Reduce Operator Tree: Select Operator - expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string), KEY.reducesinkkey1 (type: string), '11' (type: string) + expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE File Output Operator http://git-wip-us.apache.org/repos/asf/hive/blob/10423f51/ql/src/test/results/clientpositive/perf/query18.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/perf/query18.q.out b/ql/src/test/results/clientpositive/perf/query18.q.out index a1c9da5..5bd0f1f 100644 --- a/ql/src/test/results/clientpositive/perf/query18.q.out +++ b/ql/src/test/results/clientpositive/perf/query18.q.out @@ -49,11 +49,11 @@ Stage-0 <-Map 15 [SIMPLE_EDGE] SHUFFLE [RS_28] PartitionCols:_col0 - Select Operator [SEL_20] (rows=5047 width=16) + Select Operator [SEL_20] (rows=388 width=208) Output:["_col0","_col3"] - Filter Operator [FIL_77] (rows=5047 width=16) + Filter Operator [FIL_77] (rows=388 width=208) predicate:((cd_gender = 'M') and (cd_education_status = 'College') and cd_demo_sk is not null) - TableScan [TS_18] (rows=20191 width=16) + TableScan [TS_18] (rows=1553 width=208) default@customer_demographics,cd1,Tbl:COMPLETE,Col:NONE,Output:["cd_demo_sk","cd_gender","cd_education_status","cd_dep_count"] <-Reducer 11 [SIMPLE_EDGE] SHUFFLE [RS_27] http://git-wip-us.apache.org/repos/asf/hive/blob/10423f51/ql/src/test/results/clientpositive/perf/query26.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/perf/query26.q.out b/ql/src/test/results/clientpositive/perf/query26.q.out index 98a85f7..6564631 100644 --- a/ql/src/test/results/clientpositive/perf/query26.q.out +++ b/ql/src/test/results/clientpositive/perf/query26.q.out @@ -38,11 +38,11 @@ Stage-0 <-Map 11 [SIMPLE_EDGE] SHUFFLE [RS_25] PartitionCols:_col0 - Select Operator [SEL_14] (rows=3106 width=13) + Select Operator [SEL_14] (rows=132 width=304) Output:["_col0"] - Filter Operator [FIL_54] (rows=3106 width=13) + Filter Operator [FIL_54] (rows=132 width=304) predicate:((cd_gender = 'F') and (cd_marital_status = 'W') and (cd_education_status = 'Primary') and cd_demo_sk is not null) - TableScan [TS_12] (rows=24850 width=13) + TableScan [TS_12] (rows=1062 width=304) default@customer_demographics,customer_demographics,Tbl:COMPLETE,Col:NONE,Output:["cd_demo_sk","cd_gender","cd_marital_status","cd_education_status"] <-Reducer 4 [SIMPLE_EDGE] SHUFFLE [RS_24] http://git-wip-us.apache.org/repos/asf/hive/blob/10423f51/ql/src/test/results/clientpositive/perf/query27.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/perf/query27.q.out b/ql/src/test/results/clientpositive/perf/query27.q.out index 36302ca..d3e568d 100644 --- a/ql/src/test/results/clientpositive/perf/query27.q.out +++ b/ql/src/test/results/clientpositive/perf/query27.q.out @@ -38,11 +38,11 @@ Stage-0 <-Map 11 [SIMPLE_EDGE] SHUFFLE [RS_25] PartitionCols:_col0 - Select Operator [SEL_14] (rows=3106 width=13) + Select Operator [SEL_14] (rows=132 width=304) Output:["_col0"] - Filter Operator [FIL_54] (rows=3106 width=13) + Filter Operator [FIL_54] (rows=132 width=304) predicate:((cd_gender = 'F') and (cd_marital_status = 'D') and (cd_education_status = 'Unknown') and cd_demo_sk is not null) - TableScan [TS_12] (rows=24850 width=13) + TableScan [TS_12] (rows=1062 width=304) default@customer_demographics,customer_demographics,Tbl:COMPLETE,Col:NONE,Output:["cd_demo_sk","cd_gender","cd_marital_status","cd_education_status"] <-Reducer 4 [SIMPLE_EDGE] SHUFFLE [RS_24] http://git-wip-us.apache.org/repos/asf/hive/blob/10423f51/ql/src/test/results/clientpositive/perf/query28.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/perf/query28.q.out b/ql/src/test/results/clientpositive/perf/query28.q.out index 0157928..9e956f5 100644 --- a/ql/src/test/results/clientpositive/perf/query28.q.out +++ b/ql/src/test/results/clientpositive/perf/query28.q.out @@ -1,4 +1,4 @@ -Warning: Shuffle Join MERGEJOIN[63][tables = [$hdt$_0, $hdt$_1, $hdt$_2, $hdt$_3, $hdt$_4, $hdt$_5]] in Stage 'Reducer 3' is a cross product +Warning: Shuffle Join MERGEJOIN[58][tables = [$hdt$_0, $hdt$_1, $hdt$_2, $hdt$_3, $hdt$_4, $hdt$_5]] in Stage 'Reducer 3' is a cross product PREHOOK: query: explain select * from (select avg(ss_list_price) B1_LP ,count(ss_list_price) B1_CNT @@ -117,15 +117,15 @@ Stage-0 limit:100 Stage-1 Reducer 3 - File Output Operator [FS_56] - Limit [LIM_55] (rows=5 width=149) + File Output Operator [FS_51] + Limit [LIM_50] (rows=5 width=149) Number of rows:100 - Select Operator [SEL_54] (rows=5 width=149) + Select Operator [SEL_49] (rows=5 width=149) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14","_col15","_col16","_col17"] - Merge Join Operator [MERGEJOIN_63] (rows=5 width=149) + Merge Join Operator [MERGEJOIN_58] (rows=5 width=149) Conds:(Inner),(Inner),(Inner),(Inner),(Inner),Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14","_col15","_col16","_col17"] <-Reducer 11 [SIMPLE_EDGE] - SHUFFLE [RS_51] + SHUFFLE [RS_46] Group By Operator [GBY_33] (rows=1 width=136) Output:["_col0","_col1","_col2"],aggregations:["avg(VALUE._col0)","count(VALUE._col1)","count(DISTINCT KEY._col0:0._col0)"] <-Map 10 [SIMPLE_EDGE] @@ -134,12 +134,12 @@ Stage-0 Output:["_col0","_col1","_col2","_col3"],aggregations:["avg(ss_list_price)","count(ss_list_price)","count(DISTINCT ss_list_price)"],keys:ss_list_price Select Operator [SEL_30] (rows=431996724 width=88) Output:["ss_list_price"] - Filter Operator [FIL_61] (rows=431996724 width=88) + Filter Operator [FIL_56] (rows=431996724 width=88) predicate:(ss_quantity BETWEEN 11 AND 15 and (ss_list_price BETWEEN 66 AND 76 or ss_coupon_amt BETWEEN 920 AND 1920 or ss_wholesale_cost BETWEEN 4 AND 24)) TableScan [TS_28] (rows=575995635 width=88) default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_quantity","ss_wholesale_cost","ss_list_price","ss_coupon_amt"] <-Reducer 13 [SIMPLE_EDGE] - SHUFFLE [RS_52] + SHUFFLE [RS_47] Group By Operator [GBY_40] (rows=1 width=136) Output:["_col0","_col1","_col2"],aggregations:["avg(VALUE._col0)","count(VALUE._col1)","count(DISTINCT KEY._col0:0._col0)"] <-Map 12 [SIMPLE_EDGE] @@ -148,12 +148,12 @@ Stage-0 Output:["_col0","_col1","_col2","_col3"],aggregations:["avg(ss_list_price)","count(ss_list_price)","count(DISTINCT ss_list_price)"],keys:ss_list_price Select Operator [SEL_37] (rows=431996724 width=88) Output:["ss_list_price"] - Filter Operator [FIL_62] (rows=431996724 width=88) + Filter Operator [FIL_57] (rows=431996724 width=88) predicate:(ss_quantity BETWEEN 6 AND 10 and (ss_list_price BETWEEN 91 AND 101 or ss_coupon_amt BETWEEN 1430 AND 2430 or ss_wholesale_cost BETWEEN 32 AND 52)) TableScan [TS_35] (rows=575995635 width=88) default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_quantity","ss_wholesale_cost","ss_list_price","ss_coupon_amt"] <-Reducer 2 [SIMPLE_EDGE] - SHUFFLE [RS_47] + SHUFFLE [RS_42] Group By Operator [GBY_5] (rows=1 width=136) Output:["_col0","_col1","_col2"],aggregations:["avg(VALUE._col0)","count(VALUE._col1)","count(DISTINCT KEY._col0:0._col0)"] <-Map 1 [SIMPLE_EDGE] @@ -162,12 +162,12 @@ Stage-0 Output:["_col0","_col1","_col2","_col3"],aggregations:["avg(ss_list_price)","count(ss_list_price)","count(DISTINCT ss_list_price)"],keys:ss_list_price Select Operator [SEL_2] (rows=431996724 width=88) Output:["ss_list_price"] - Filter Operator [FIL_57] (rows=431996724 width=88) + Filter Operator [FIL_52] (rows=431996724 width=88) predicate:(ss_quantity BETWEEN 0 AND 5 and (ss_list_price BETWEEN 11 AND 21 or ss_coupon_amt BETWEEN 460 AND 1460 or ss_wholesale_cost BETWEEN 14 AND 34)) TableScan [TS_0] (rows=575995635 width=88) default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_quantity","ss_wholesale_cost","ss_list_price","ss_coupon_amt"] <-Reducer 5 [SIMPLE_EDGE] - SHUFFLE [RS_48] + SHUFFLE [RS_43] Group By Operator [GBY_12] (rows=1 width=136) Output:["_col0","_col1","_col2"],aggregations:["avg(VALUE._col0)","count(VALUE._col1)","count(DISTINCT KEY._col0:0._col0)"] <-Map 4 [SIMPLE_EDGE] @@ -176,12 +176,12 @@ Stage-0 Output:["_col0","_col1","_col2","_col3"],aggregations:["avg(ss_list_price)","count(ss_list_price)","count(DISTINCT ss_list_price)"],keys:ss_list_price Select Operator [SEL_9] (rows=431996724 width=88) Output:["ss_list_price"] - Filter Operator [FIL_58] (rows=431996724 width=88) + Filter Operator [FIL_53] (rows=431996724 width=88) predicate:(ss_quantity BETWEEN 26 AND 30 and (ss_list_price BETWEEN 28 AND 38 or ss_coupon_amt BETWEEN 2513 AND 3513 or ss_wholesale_cost BETWEEN 42 AND 62)) TableScan [TS_7] (rows=575995635 width=88) default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_quantity","ss_wholesale_cost","ss_list_price","ss_coupon_amt"] <-Reducer 7 [SIMPLE_EDGE] - SHUFFLE [RS_49] + SHUFFLE [RS_44] Group By Operator [GBY_19] (rows=1 width=136) Output:["_col0","_col1","_col2"],aggregations:["avg(VALUE._col0)","count(VALUE._col1)","count(DISTINCT KEY._col0:0._col0)"] <-Map 6 [SIMPLE_EDGE] @@ -190,12 +190,12 @@ Stage-0 Output:["_col0","_col1","_col2","_col3"],aggregations:["avg(ss_list_price)","count(ss_list_price)","count(DISTINCT ss_list_price)"],keys:ss_list_price Select Operator [SEL_16] (rows=431996724 width=88) Output:["ss_list_price"] - Filter Operator [FIL_59] (rows=431996724 width=88) + Filter Operator [FIL_54] (rows=431996724 width=88) predicate:(ss_quantity BETWEEN 21 AND 25 and (ss_list_price BETWEEN 135 AND 145 or ss_coupon_amt BETWEEN 14180 AND 15180 or ss_wholesale_cost BETWEEN 38 AND 58)) TableScan [TS_14] (rows=575995635 width=88) default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_quantity","ss_wholesale_cost","ss_list_price","ss_coupon_amt"] <-Reducer 9 [SIMPLE_EDGE] - SHUFFLE [RS_50] + SHUFFLE [RS_45] Group By Operator [GBY_26] (rows=1 width=136) Output:["_col0","_col1","_col2"],aggregations:["avg(VALUE._col0)","count(VALUE._col1)","count(DISTINCT KEY._col0:0._col0)"] <-Map 8 [SIMPLE_EDGE] @@ -204,7 +204,7 @@ Stage-0 Output:["_col0","_col1","_col2","_col3"],aggregations:["avg(ss_list_price)","count(ss_list_price)","count(DISTINCT ss_list_price)"],keys:ss_list_price Select Operator [SEL_23] (rows=431996724 width=88) Output:["ss_list_price"] - Filter Operator [FIL_60] (rows=431996724 width=88) + Filter Operator [FIL_55] (rows=431996724 width=88) predicate:(ss_quantity BETWEEN 16 AND 20 and (ss_list_price BETWEEN 142 AND 152 or ss_coupon_amt BETWEEN 3054 AND 4054 or ss_wholesale_cost BETWEEN 80 AND 100)) TableScan [TS_21] (rows=575995635 width=88) default@store_sales,store_sales,Tbl:COMPLETE,Col:NONE,Output:["ss_quantity","ss_wholesale_cost","ss_list_price","ss_coupon_amt"]
