diff --git a/ql/src/test/queries/clientpositive/unionDistinct_1.q b/ql/src/test/queries/clientpositive/unionDistinct_1.q index 984ce2e..a86b37a 100644 --- a/ql/src/test/queries/clientpositive/unionDistinct_1.q +++ b/ql/src/test/queries/clientpositive/unionDistinct_1.q @@ -995,6 +995,11 @@ insert overwrite table src10_2 select * insert overwrite table src10_3 select * insert overwrite table src10_4 select *; +analyze table src10_1 compute statistics; +analyze table src10_2 compute statistics; +analyze table src10_3 compute statistics; +analyze table src10_4 compute statistics; + set hive.auto.convert.join=true; -- When we convert the Join of sub1 and sub0 into a MapJoin, -- we can use a single MR job to evaluate this entire query. diff --git a/ql/src/test/queries/clientpositive/union_view.q b/ql/src/test/queries/clientpositive/union_view.q index b727199..733ed3e 100644 --- a/ql/src/test/queries/clientpositive/union_view.q +++ b/ql/src/test/queries/clientpositive/union_view.q @@ -1,4 +1,6 @@ set hive.stats.dbclass=fs; +set hive.explain.user=false; + CREATE TABLE src_union_1 (key int, value string) PARTITIONED BY (ds string); CREATE INDEX src_union_1_key_idx ON TABLE src_union_1(key) AS 'COMPACT' WITH DEFERRED REBUILD; diff --git a/ql/src/test/results/clientpositive/acid_vectorization_partition.q.out b/ql/src/test/results/clientpositive/acid_vectorization_partition.q.out index ee97cc9..f608b10 100644 --- a/ql/src/test/results/clientpositive/acid_vectorization_partition.q.out +++ b/ql/src/test/results/clientpositive/acid_vectorization_partition.q.out @@ -26,13 +26,13 @@ POSTHOOK: Input: default@alltypesorc POSTHOOK: Output: default@acid_vectorized_part@ds=tomorrow POSTHOOK: Lineage: acid_vectorized_part PARTITION(ds=tomorrow).a SIMPLE [(alltypesorc)alltypesorc.FieldSchema(name:cint, type:int, comment:null), ] POSTHOOK: Lineage: acid_vectorized_part PARTITION(ds=tomorrow).b SIMPLE [(alltypesorc)alltypesorc.FieldSchema(name:cstring1, type:string, comment:null), ] -PREHOOK: query: select * from acid_vectorized_part order by a, b +PREHOOK: query: select * from acid_vectorized_part order by a, b, ds PREHOOK: type: QUERY PREHOOK: Input: default@acid_vectorized_part PREHOOK: Input: default@acid_vectorized_part@ds=today PREHOOK: Input: default@acid_vectorized_part@ds=tomorrow #### A masked pattern was here #### -POSTHOOK: query: select * from acid_vectorized_part order by a, b +POSTHOOK: query: select * from acid_vectorized_part order by a, b, ds POSTHOOK: type: QUERY POSTHOOK: Input: default@acid_vectorized_part POSTHOOK: Input: default@acid_vectorized_part@ds=today @@ -40,21 +40,21 @@ POSTHOOK: Input: default@acid_vectorized_part@ds=tomorrow #### A masked pattern was here #### -1073279343 oj1YrV5Wa today -1073279343 oj1YrV5Wa tomorrow --1073051226 A34p7oRr2WvUJNf tomorrow -1073051226 A34p7oRr2WvUJNf today --1072910839 0iqrc5 tomorrow +-1073051226 A34p7oRr2WvUJNf tomorrow -1072910839 0iqrc5 today +-1072910839 0iqrc5 tomorrow -1072081801 dPkN74F7 today -1072081801 dPkN74F7 tomorrow -1072076362 2uLyD28144vklju213J1mr today -1072076362 2uLyD28144vklju213J1mr tomorrow --1071480828 aw724t8c5558x2xneC624 tomorrow -1071480828 aw724t8c5558x2xneC624 today +-1071480828 aw724t8c5558x2xneC624 tomorrow -1071363017 Anj0oF today -1071363017 Anj0oF tomorrow --1070883071 0ruyd6Y50JpdGRf6HqD tomorrow -1070883071 0ruyd6Y50JpdGRf6HqD today +-1070883071 0ruyd6Y50JpdGRf6HqD tomorrow -1070551679 iUR3Q today -1070551679 iUR3Q tomorrow --1069736047 k17Am8uPHWk02cEf1jet tomorrow -1069736047 k17Am8uPHWk02cEf1jet today +-1069736047 k17Am8uPHWk02cEf1jet tomorrow diff --git a/ql/src/test/results/clientpositive/llap/count.q.out b/ql/src/test/results/clientpositive/llap/count.q.out index d59b063..e8d5a8a 100644 --- a/ql/src/test/results/clientpositive/llap/count.q.out +++ b/ql/src/test/results/clientpositive/llap/count.q.out @@ -53,11 +53,11 @@ STAGE PLANS: Statistics: Num rows: 4 Data size: 78 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: a (type: int), b (type: int), c (type: int), d (type: int) - outputColumnNames: _col0, _col1, _col2, _col3 + outputColumnNames: a, b, c, d Statistics: Num rows: 4 Data size: 78 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(DISTINCT _col1), count(DISTINCT _col2), sum(_col3) - keys: _col0 (type: int), _col1 (type: int), _col2 (type: int) + aggregations: count(DISTINCT b), count(DISTINCT c), sum(d) + keys: a (type: int), b (type: int), c (type: int) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 Statistics: Num rows: 4 Data size: 78 Basic stats: COMPLETE Column stats: NONE @@ -192,14 +192,14 @@ STAGE PLANS: Statistics: Num rows: 4 Data size: 78 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: a (type: int), b (type: int), c (type: int), d (type: int) - outputColumnNames: _col0, _col1, _col2, _col3 + outputColumnNames: a, b, c, d Statistics: Num rows: 4 Data size: 78 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: int), _col1 (type: int), _col2 (type: int) + key expressions: a (type: int), b (type: int), c (type: int) sort order: +++ - Map-reduce partition columns: _col0 (type: int) + Map-reduce partition columns: a (type: int) Statistics: Num rows: 4 Data size: 78 Basic stats: COMPLETE Column stats: NONE - value expressions: _col3 (type: int) + value expressions: d (type: int) Execution mode: llap Reducer 2 Execution mode: uber diff --git a/ql/src/test/results/clientpositive/llap/dynamic_partition_pruning.q.out b/ql/src/test/results/clientpositive/llap/dynamic_partition_pruning.q.out index 5a67250..cdb11b6 100644 --- a/ql/src/test/results/clientpositive/llap/dynamic_partition_pruning.q.out +++ b/ql/src/test/results/clientpositive/llap/dynamic_partition_pruning.q.out @@ -59,10 +59,10 @@ STAGE PLANS: Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ds (type: string) - outputColumnNames: _col0 + outputColumnNames: ds Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: _col0 (type: string) + keys: ds (type: string) mode: hash outputColumnNames: _col0 Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE @@ -1831,7 +1831,7 @@ 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[23][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product +Warning: Shuffle Join MERGEJOIN[21][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 @@ -1871,10 +1871,10 @@ STAGE PLANS: Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: '2008-04-08' (type: string) - outputColumnNames: _col0 + outputColumnNames: ds Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: _col0 (type: string) + keys: ds (type: string) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE @@ -1938,7 +1938,7 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Shuffle Join MERGEJOIN[23][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product +Warning: Shuffle Join MERGEJOIN[21][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 @@ -2835,10 +2835,10 @@ STAGE PLANS: Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ds (type: string) - outputColumnNames: _col0 + outputColumnNames: ds Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: max(_col0) + aggregations: max(ds) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 84 Basic stats: COMPLETE Column stats: NONE @@ -2854,10 +2854,10 @@ STAGE PLANS: Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ds (type: string) - outputColumnNames: _col0 + outputColumnNames: ds Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: min(_col0) + aggregations: min(ds) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 84 Basic stats: COMPLETE Column stats: NONE @@ -3039,10 +3039,10 @@ STAGE PLANS: Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ds (type: string) - outputColumnNames: _col0 + outputColumnNames: ds Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: max(_col0) + aggregations: max(ds) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 84 Basic stats: COMPLETE Column stats: NONE @@ -3058,10 +3058,10 @@ STAGE PLANS: Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ds (type: string) - outputColumnNames: _col0 + outputColumnNames: ds Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: min(_col0) + aggregations: min(ds) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 84 Basic stats: COMPLETE Column stats: NONE @@ -3230,20 +3230,16 @@ STAGE PLANS: alias: srcpart filterExpr: ds is not null (type: boolean) Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: ds (type: string) + Group By Operator + keys: ds (type: string) + mode: hash outputColumnNames: _col0 Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 + 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 - 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 Execution mode: llap Map 10 Map Operator Tree: @@ -3252,10 +3248,10 @@ STAGE PLANS: Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ds (type: string) - outputColumnNames: _col0 + outputColumnNames: ds Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: min(_col0) + aggregations: min(ds) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 84 Basic stats: COMPLETE Column stats: NONE @@ -3270,20 +3266,16 @@ STAGE PLANS: alias: srcpart filterExpr: ds is not null (type: boolean) Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: ds (type: string) + Group By Operator + keys: ds (type: string) + mode: hash outputColumnNames: _col0 Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 + 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 - 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 Execution mode: llap Map 7 Map Operator Tree: @@ -3292,10 +3284,10 @@ STAGE PLANS: Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ds (type: string) - outputColumnNames: _col0 + outputColumnNames: ds Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: max(_col0) + aggregations: max(ds) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 84 Basic stats: COMPLETE Column stats: NONE @@ -4270,7 +4262,7 @@ 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[23][bigTable=?] in task 'Map 1' is a cross product +Warning: Map Join MAPJOIN[21][bigTable=?] in task 'Map 1' 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 @@ -4326,10 +4318,10 @@ STAGE PLANS: Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: '2008-04-08' (type: string) - outputColumnNames: _col0 + outputColumnNames: ds Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: _col0 (type: string) + keys: ds (type: string) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE @@ -4374,7 +4366,7 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Map Join MAPJOIN[23][bigTable=?] in task 'Map 1' is a cross product +Warning: Map Join MAPJOIN[21][bigTable=?] in task 'Map 1' 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 @@ -4984,10 +4976,10 @@ STAGE PLANS: Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ds (type: string) - outputColumnNames: _col0 + outputColumnNames: ds Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: max(_col0) + aggregations: max(ds) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 84 Basic stats: COMPLETE Column stats: NONE @@ -5003,10 +4995,10 @@ STAGE PLANS: Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ds (type: string) - outputColumnNames: _col0 + outputColumnNames: ds Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: min(_col0) + aggregations: min(ds) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 84 Basic stats: COMPLETE Column stats: NONE diff --git a/ql/src/test/results/clientpositive/llap/dynpart_sort_opt_vectorization.q.out b/ql/src/test/results/clientpositive/llap/dynpart_sort_opt_vectorization.q.out index 4f291dd..07a87c8 100644 --- a/ql/src/test/results/clientpositive/llap/dynpart_sort_opt_vectorization.q.out +++ b/ql/src/test/results/clientpositive/llap/dynpart_sort_opt_vectorization.q.out @@ -1591,37 +1591,37 @@ STAGE PLANS: Filter Operator predicate: (t is null or (t = 27)) (type: boolean) Statistics: Num rows: 1048 Data size: 310873 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: si (type: smallint), i (type: int), b (type: bigint), f (type: float), t (type: tinyint) + Group By Operator + keys: t (type: tinyint), si (type: smallint), i (type: int), b (type: bigint), f (type: float) + mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4 Statistics: Num rows: 1048 Data size: 310873 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float), _col4 (type: tinyint) - mode: hash - outputColumnNames: _col0, _col1, _col2, _col3, _col4 + Reduce Output Operator + key expressions: _col0 (type: tinyint), _col1 (type: smallint), _col2 (type: int), _col3 (type: bigint), _col4 (type: float) + sort order: +++++ + Map-reduce partition columns: _col0 (type: tinyint), _col1 (type: smallint), _col2 (type: int), _col3 (type: bigint), _col4 (type: float) Statistics: Num rows: 1048 Data size: 310873 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float), _col4 (type: tinyint) - sort order: +++++ - Map-reduce partition columns: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float), _col4 (type: tinyint) - Statistics: Num rows: 1048 Data size: 310873 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized, llap Reducer 2 Execution mode: vectorized, uber Reduce Operator Tree: Group By Operator - keys: KEY._col0 (type: smallint), KEY._col1 (type: int), KEY._col2 (type: bigint), KEY._col3 (type: float), KEY._col4 (type: tinyint) + keys: KEY._col0 (type: tinyint), KEY._col1 (type: smallint), KEY._col2 (type: int), KEY._col3 (type: bigint), KEY._col4 (type: float) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4 Statistics: Num rows: 524 Data size: 155436 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col1 (type: smallint), _col2 (type: int), _col3 (type: bigint), _col4 (type: float), _col0 (type: tinyint) + outputColumnNames: _col0, _col1, _col2, _col3, _col4 Statistics: Num rows: 524 Data size: 155436 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.over1k_part2_orc + File Output Operator + compressed: false + Statistics: Num rows: 524 Data size: 155436 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.over1k_part2_orc Stage: Stage-2 Dependency Collection @@ -1659,7 +1659,6 @@ STAGE PLANS: Tez Edges: Reducer 2 <- Map 1 (SIMPLE_EDGE) - Reducer 3 <- Reducer 2 (SIMPLE_EDGE) #### A masked pattern was here #### Vertices: Map 1 @@ -1670,50 +1669,37 @@ STAGE PLANS: Filter Operator predicate: (t is null or (t = 27)) (type: boolean) Statistics: Num rows: 1048 Data size: 310873 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: si (type: smallint), i (type: int), b (type: bigint), f (type: float), t (type: tinyint) + Group By Operator + keys: t (type: tinyint), si (type: smallint), i (type: int), b (type: bigint), f (type: float) + mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4 Statistics: Num rows: 1048 Data size: 310873 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float), _col4 (type: tinyint) - mode: hash - outputColumnNames: _col0, _col1, _col2, _col3, _col4 + Reduce Output Operator + key expressions: _col0 (type: tinyint), _col1 (type: smallint), _col2 (type: int), _col3 (type: bigint), _col4 (type: float) + sort order: +++++ + Map-reduce partition columns: _col0 (type: tinyint) Statistics: Num rows: 1048 Data size: 310873 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float), _col4 (type: tinyint) - sort order: +++++ - Map-reduce partition columns: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float), _col4 (type: tinyint) - Statistics: Num rows: 1048 Data size: 310873 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized, llap Reducer 2 - Execution mode: vectorized, llap + Execution mode: vectorized, uber Reduce Operator Tree: Group By Operator - keys: KEY._col0 (type: smallint), KEY._col1 (type: int), KEY._col2 (type: bigint), KEY._col3 (type: float), KEY._col4 (type: tinyint) + keys: KEY._col0 (type: tinyint), KEY._col1 (type: smallint), KEY._col2 (type: int), KEY._col3 (type: bigint), KEY._col4 (type: float) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4 Statistics: Num rows: 524 Data size: 155436 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col4 (type: tinyint) - sort order: + - Map-reduce partition columns: _col4 (type: tinyint) - Statistics: Num rows: 524 Data size: 155436 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float), _col4 (type: tinyint) - Reducer 3 - Execution mode: vectorized, uber - Reduce Operator Tree: - Select Operator - expressions: VALUE._col0 (type: smallint), VALUE._col1 (type: int), VALUE._col2 (type: bigint), VALUE._col3 (type: float), VALUE._col4 (type: tinyint) - outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 524 Data size: 155436 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col1 (type: smallint), _col2 (type: int), _col3 (type: bigint), _col4 (type: float), _col0 (type: tinyint) + outputColumnNames: _col0, _col1, _col2, _col3, _col4 Statistics: Num rows: 524 Data size: 155436 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.over1k_part2_orc + File Output Operator + compressed: false + Statistics: Num rows: 524 Data size: 155436 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.over1k_part2_orc Stage: Stage-2 Dependency Collection diff --git a/ql/src/test/results/clientpositive/llap/dynpart_sort_optimization.q.out b/ql/src/test/results/clientpositive/llap/dynpart_sort_optimization.q.out index 356aafc..2534254 100644 --- a/ql/src/test/results/clientpositive/llap/dynpart_sort_optimization.q.out +++ b/ql/src/test/results/clientpositive/llap/dynpart_sort_optimization.q.out @@ -1522,37 +1522,37 @@ STAGE PLANS: Filter Operator predicate: (t is null or (t = 27)) (type: boolean) Statistics: Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: si (type: smallint), i (type: int), b (type: bigint), f (type: float), t (type: tinyint) + Group By Operator + keys: t (type: tinyint), si (type: smallint), i (type: int), b (type: bigint), f (type: float) + mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4 Statistics: Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float), _col4 (type: tinyint) - mode: hash - outputColumnNames: _col0, _col1, _col2, _col3, _col4 + Reduce Output Operator + key expressions: _col0 (type: tinyint), _col1 (type: smallint), _col2 (type: int), _col3 (type: bigint), _col4 (type: float) + sort order: +++++ + Map-reduce partition columns: _col0 (type: tinyint), _col1 (type: smallint), _col2 (type: int), _col3 (type: bigint), _col4 (type: float) Statistics: Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float), _col4 (type: tinyint) - sort order: +++++ - Map-reduce partition columns: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float), _col4 (type: tinyint) - Statistics: Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE Execution mode: llap Reducer 2 Execution mode: uber Reduce Operator Tree: Group By Operator - keys: KEY._col0 (type: smallint), KEY._col1 (type: int), KEY._col2 (type: bigint), KEY._col3 (type: float), KEY._col4 (type: tinyint) + keys: KEY._col0 (type: tinyint), KEY._col1 (type: smallint), KEY._col2 (type: int), KEY._col3 (type: bigint), KEY._col4 (type: float) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4 Statistics: Num rows: 2221 Data size: 53305 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col1 (type: smallint), _col2 (type: int), _col3 (type: bigint), _col4 (type: float), _col0 (type: tinyint) + outputColumnNames: _col0, _col1, _col2, _col3, _col4 Statistics: Num rows: 2221 Data size: 53305 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.over1k_part2 + File Output Operator + compressed: false + Statistics: Num rows: 2221 Data size: 53305 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.over1k_part2 Stage: Stage-2 Dependency Collection @@ -1590,7 +1590,6 @@ STAGE PLANS: Tez Edges: Reducer 2 <- Map 1 (SIMPLE_EDGE) - Reducer 3 <- Reducer 2 (SIMPLE_EDGE) #### A masked pattern was here #### Vertices: Map 1 @@ -1601,50 +1600,37 @@ STAGE PLANS: Filter Operator predicate: (t is null or (t = 27)) (type: boolean) Statistics: Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: si (type: smallint), i (type: int), b (type: bigint), f (type: float), t (type: tinyint) + Group By Operator + keys: t (type: tinyint), si (type: smallint), i (type: int), b (type: bigint), f (type: float) + mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4 Statistics: Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float), _col4 (type: tinyint) - mode: hash - outputColumnNames: _col0, _col1, _col2, _col3, _col4 + Reduce Output Operator + key expressions: _col0 (type: tinyint), _col1 (type: smallint), _col2 (type: int), _col3 (type: bigint), _col4 (type: float) + sort order: +++++ + Map-reduce partition columns: _col0 (type: tinyint) Statistics: Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float), _col4 (type: tinyint) - sort order: +++++ - Map-reduce partition columns: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float), _col4 (type: tinyint) - Statistics: Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE Execution mode: llap Reducer 2 - Execution mode: llap + Execution mode: uber Reduce Operator Tree: Group By Operator - keys: KEY._col0 (type: smallint), KEY._col1 (type: int), KEY._col2 (type: bigint), KEY._col3 (type: float), KEY._col4 (type: tinyint) + keys: KEY._col0 (type: tinyint), KEY._col1 (type: smallint), KEY._col2 (type: int), KEY._col3 (type: bigint), KEY._col4 (type: float) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4 Statistics: Num rows: 2221 Data size: 53305 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col4 (type: tinyint) - sort order: + - Map-reduce partition columns: _col4 (type: tinyint) - Statistics: Num rows: 2221 Data size: 53305 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float), _col4 (type: tinyint) - Reducer 3 - Execution mode: uber - Reduce Operator Tree: - Select Operator - expressions: VALUE._col0 (type: smallint), VALUE._col1 (type: int), VALUE._col2 (type: bigint), VALUE._col3 (type: float), VALUE._col4 (type: tinyint) - outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 2221 Data size: 53305 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col1 (type: smallint), _col2 (type: int), _col3 (type: bigint), _col4 (type: float), _col0 (type: tinyint) + outputColumnNames: _col0, _col1, _col2, _col3, _col4 Statistics: Num rows: 2221 Data size: 53305 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.over1k_part2 + File Output Operator + compressed: false + Statistics: Num rows: 2221 Data size: 53305 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.over1k_part2 Stage: Stage-2 Dependency Collection diff --git a/ql/src/test/results/clientpositive/llap/explainuser_1.q.out b/ql/src/test/results/clientpositive/llap/explainuser_1.q.out index 36f1099..7d9d99e 100644 --- a/ql/src/test/results/clientpositive/llap/explainuser_1.q.out +++ b/ql/src/test/results/clientpositive/llap/explainuser_1.q.out @@ -398,28 +398,28 @@ Stage-0 compressed:false Statistics:Num rows: 10 Data size: 885 Basic stats: COMPLETE Column stats: COMPLETE table:{"input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat","serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe"} - Select Operator [SEL_6] + Select Operator [SEL_5] outputColumnNames:["_col0","_col1","_col2"] Statistics:Num rows: 10 Data size: 885 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator [GBY_5] + Group By Operator [GBY_4] | aggregations:["sum(VALUE._col0)"] - | keys:KEY._col0 (type: float), KEY._col1 (type: int), KEY._col2 (type: string) + | keys:KEY._col0 (type: string), KEY._col1 (type: int), KEY._col2 (type: float) | outputColumnNames:["_col0","_col1","_col2","_col3"] | Statistics:Num rows: 10 Data size: 917 Basic stats: COMPLETE Column stats: COMPLETE |<-Map 1 [SIMPLE_EDGE] - Reduce Output Operator [RS_4] - key expressions:_col0 (type: float), _col1 (type: int), _col2 (type: string) - Map-reduce partition columns:_col0 (type: float), _col1 (type: int), _col2 (type: string) + Reduce Output Operator [RS_3] + key expressions:_col0 (type: string), _col1 (type: int), _col2 (type: float) + Map-reduce partition columns:_col0 (type: string), _col1 (type: int), _col2 (type: float) sort order:+++ Statistics:Num rows: 10 Data size: 917 Basic stats: COMPLETE Column stats: COMPLETE value expressions:_col3 (type: bigint) - Group By Operator [GBY_3] - aggregations:["sum(_col1)"] - keys:_col0 (type: float), _col1 (type: int), _col2 (type: string) + Group By Operator [GBY_2] + aggregations:["sum(c_int)"] + keys:key (type: string), c_int (type: int), c_float (type: float) outputColumnNames:["_col0","_col1","_col2","_col3"] Statistics:Num rows: 10 Data size: 917 Basic stats: COMPLETE Column stats: COMPLETE Select Operator [SEL_1] - outputColumnNames:["_col0","_col1","_col2"] + outputColumnNames:["key","c_int","c_float"] Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE TableScan [TS_0] alias:cbo_t1 @@ -464,28 +464,28 @@ Stage-0 keys:_col0 (type: bigint), _col1 (type: float) outputColumnNames:["_col0","_col1","_col2"] Statistics:Num rows: 5 Data size: 100 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator [SEL_6] + Select Operator [SEL_5] outputColumnNames:["_col0","_col1"] Statistics:Num rows: 10 Data size: 917 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator [GBY_5] + Group By Operator [GBY_4] | aggregations:["sum(VALUE._col0)"] - | keys:KEY._col0 (type: float), KEY._col1 (type: int), KEY._col2 (type: string) + | keys:KEY._col0 (type: string), KEY._col1 (type: int), KEY._col2 (type: float) | outputColumnNames:["_col0","_col1","_col2","_col3"] | Statistics:Num rows: 10 Data size: 917 Basic stats: COMPLETE Column stats: COMPLETE |<-Map 1 [SIMPLE_EDGE] - Reduce Output Operator [RS_4] - key expressions:_col0 (type: float), _col1 (type: int), _col2 (type: string) - Map-reduce partition columns:_col0 (type: float), _col1 (type: int), _col2 (type: string) + Reduce Output Operator [RS_3] + key expressions:_col0 (type: string), _col1 (type: int), _col2 (type: float) + Map-reduce partition columns:_col0 (type: string), _col1 (type: int), _col2 (type: float) sort order:+++ Statistics:Num rows: 10 Data size: 917 Basic stats: COMPLETE Column stats: COMPLETE value expressions:_col3 (type: bigint) - Group By Operator [GBY_3] - aggregations:["sum(_col1)"] - keys:_col0 (type: float), _col1 (type: int), _col2 (type: string) + Group By Operator [GBY_2] + aggregations:["sum(c_int)"] + keys:key (type: string), c_int (type: int), c_float (type: float) outputColumnNames:["_col0","_col1","_col2","_col3"] Statistics:Num rows: 10 Data size: 917 Basic stats: COMPLETE Column stats: COMPLETE Select Operator [SEL_1] - outputColumnNames:["_col0","_col1","_col2"] + outputColumnNames:["key","c_int","c_float"] Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE TableScan [TS_0] alias:cbo_t1 @@ -525,152 +525,149 @@ Stage-0 sort order:-+ Statistics:Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE value expressions:_col0 (type: int), _col2 (type: bigint) - Group By Operator [GBY_41] - | aggregations:["count(VALUE._col0)"] - | keys:KEY._col0 (type: int), KEY._col1 (type: bigint) - | outputColumnNames:["_col0","_col1","_col2"] - | Statistics:Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE - |<-Reducer 5 [SIMPLE_EDGE] - Reduce Output Operator [RS_40] - key expressions:_col0 (type: int), _col1 (type: bigint) - Map-reduce partition columns:_col0 (type: int), _col1 (type: bigint) - sort order:++ - Statistics:Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE - value expressions:_col2 (type: bigint) - Group By Operator [GBY_39] - aggregations:["count()"] - keys:_col0 (type: int), _col1 (type: bigint) - outputColumnNames:["_col0","_col1","_col2"] + Select Operator [SEL_41] + outputColumnNames:["_col0","_col1","_col2"] + Statistics:Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator [GBY_40] + | aggregations:["count(VALUE._col0)"] + | keys:KEY._col0 (type: bigint), KEY._col1 (type: int) + | outputColumnNames:["_col0","_col1","_col2"] + | Statistics:Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE + |<-Reducer 5 [SIMPLE_EDGE] + Reduce Output Operator [RS_39] + key expressions:_col0 (type: bigint), _col1 (type: int) + Map-reduce partition columns:_col0 (type: bigint), _col1 (type: int) + sort order:++ Statistics:Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator [SEL_37] - outputColumnNames:["_col0","_col1"] - Statistics:Num rows: 2 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator [FIL_36] - predicate:((_col1 > 0) or (_col6 >= 0)) (type: boolean) + value expressions:_col2 (type: bigint) + Group By Operator [GBY_38] + aggregations:["count()"] + keys:_col2 (type: bigint), _col6 (type: int) + outputColumnNames:["_col0","_col1","_col2"] + Statistics:Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator [SEL_37] + outputColumnNames:["_col2","_col6"] Statistics:Num rows: 2 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE - Merge Join Operator [MERGEJOIN_55] - | condition map:[{"":"Inner Join 0 to 1"}] - | keys:{"0":"_col0 (type: string)","1":"_col0 (type: string)"} - | outputColumnNames:["_col1","_col2","_col6"] - | Statistics:Num rows: 3 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE - |<-Map 11 [SIMPLE_EDGE] - | Reduce Output Operator [RS_34] - | key expressions:_col0 (type: string) - | Map-reduce partition columns:_col0 (type: string) - | sort order:+ - | Statistics:Num rows: 18 Data size: 1424 Basic stats: COMPLETE Column stats: COMPLETE - | value expressions:_col1 (type: int) - | Select Operator [SEL_30] - | outputColumnNames:["_col0","_col1"] - | Statistics:Num rows: 18 Data size: 1424 Basic stats: COMPLETE Column stats: COMPLETE - | Filter Operator [FIL_53] - | predicate:key is not null (type: boolean) - | Statistics:Num rows: 18 Data size: 1424 Basic stats: COMPLETE Column stats: COMPLETE - | TableScan [TS_29] - | alias:cbo_t3 - | Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE - |<-Reducer 4 [SIMPLE_EDGE] - Reduce Output Operator [RS_32] - key expressions:_col0 (type: string) - Map-reduce partition columns:_col0 (type: string) - sort order:+ - Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE - value expressions:_col1 (type: int), _col2 (type: bigint) - Select Operator [SEL_28] - outputColumnNames:["_col0","_col1","_col2"] + Filter Operator [FIL_36] + predicate:((_col1 > 0) or (_col6 >= 0)) (type: boolean) + Statistics:Num rows: 2 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE + Merge Join Operator [MERGEJOIN_55] + | condition map:[{"":"Inner Join 0 to 1"}] + | keys:{"0":"_col0 (type: string)","1":"_col0 (type: string)"} + | outputColumnNames:["_col1","_col2","_col6"] + | Statistics:Num rows: 3 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 11 [SIMPLE_EDGE] + | Reduce Output Operator [RS_34] + | key expressions:_col0 (type: string) + | Map-reduce partition columns:_col0 (type: string) + | sort order:+ + | Statistics:Num rows: 18 Data size: 1424 Basic stats: COMPLETE Column stats: COMPLETE + | value expressions:_col1 (type: int) + | Select Operator [SEL_30] + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 18 Data size: 1424 Basic stats: COMPLETE Column stats: COMPLETE + | Filter Operator [FIL_53] + | predicate:key is not null (type: boolean) + | Statistics:Num rows: 18 Data size: 1424 Basic stats: COMPLETE Column stats: COMPLETE + | TableScan [TS_29] + | alias:cbo_t3 + | Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE + |<-Reducer 4 [SIMPLE_EDGE] + Reduce Output Operator [RS_32] + key expressions:_col0 (type: string) + Map-reduce partition columns:_col0 (type: string) + sort order:+ Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator [FIL_27] - predicate:((_col1 + _col4) >= 0) (type: boolean) + value expressions:_col1 (type: int), _col2 (type: bigint) + Select Operator [SEL_28] + outputColumnNames:["_col0","_col1","_col2"] Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE - Merge Join Operator [MERGEJOIN_54] - | condition map:[{"":"Inner Join 0 to 1"}] - | keys:{"0":"_col0 (type: string)","1":"_col0 (type: string)"} - | outputColumnNames:["_col0","_col1","_col2","_col4"] - | Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE - |<-Reducer 10 [SIMPLE_EDGE] - | Reduce Output Operator [RS_25] - | key expressions:_col0 (type: string) - | Map-reduce partition columns:_col0 (type: string) - | sort order:+ - | Statistics:Num rows: 1 Data size: 89 Basic stats: COMPLETE Column stats: COMPLETE - | value expressions:_col1 (type: int) - | Select Operator [SEL_20] - | | outputColumnNames:["_col0","_col1"] - | | Statistics:Num rows: 1 Data size: 89 Basic stats: COMPLETE Column stats: COMPLETE - | |<-Reducer 9 [SIMPLE_EDGE] - | Reduce Output Operator [RS_19] - | key expressions:_col3 (type: double), _col2 (type: bigint) - | sort order:-+ - | Statistics:Num rows: 1 Data size: 105 Basic stats: COMPLETE Column stats: COMPLETE - | value expressions:_col0 (type: string), _col1 (type: int) - | Select Operator [SEL_18] - | outputColumnNames:["_col0","_col1","_col2","_col3"] - | Statistics:Num rows: 1 Data size: 105 Basic stats: COMPLETE Column stats: COMPLETE - | Group By Operator [GBY_17] - | | aggregations:["sum(VALUE._col0)"] - | | keys:KEY._col0 (type: float), KEY._col1 (type: int), KEY._col2 (type: string) - | | outputColumnNames:["_col0","_col1","_col2","_col3"] - | | Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE - | |<-Map 8 [SIMPLE_EDGE] - | Reduce Output Operator [RS_16] - | key expressions:_col0 (type: float), _col1 (type: int), _col2 (type: string) - | Map-reduce partition columns:_col0 (type: float), _col1 (type: int), _col2 (type: string) - | sort order:+++ - | Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE - | value expressions:_col3 (type: bigint) - | Group By Operator [GBY_15] - | aggregations:["sum(_col1)"] - | keys:_col0 (type: float), _col1 (type: int), _col2 (type: string) - | outputColumnNames:["_col0","_col1","_col2","_col3"] - | Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE - | Select Operator [SEL_13] - | outputColumnNames:["_col0","_col1","_col2"] - | Statistics:Num rows: 3 Data size: 279 Basic stats: COMPLETE Column stats: COMPLETE - | Filter Operator [FIL_52] - | predicate:((((c_int + 1) >= 0) and ((c_int > 0) or (c_float >= 0.0))) and key is not null) (type: boolean) - | Statistics:Num rows: 3 Data size: 279 Basic stats: COMPLETE Column stats: COMPLETE - | TableScan [TS_11] - | alias:cbo_t2 - | Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE - |<-Reducer 3 [SIMPLE_EDGE] - Reduce Output Operator [RS_23] - key expressions:_col0 (type: string) - Map-reduce partition columns:_col0 (type: string) - sort order:+ - Statistics:Num rows: 1 Data size: 97 Basic stats: COMPLETE Column stats: COMPLETE - value expressions:_col1 (type: int), _col2 (type: bigint) - Select Operator [SEL_9] - | outputColumnNames:["_col0","_col1","_col2"] - | Statistics:Num rows: 1 Data size: 97 Basic stats: COMPLETE Column stats: COMPLETE - |<-Reducer 2 [SIMPLE_EDGE] - Reduce Output Operator [RS_8] - key expressions:_col0 (type: string) - sort order:+ - Statistics:Num rows: 1 Data size: 97 Basic stats: COMPLETE Column stats: COMPLETE - value expressions:_col1 (type: int), _col2 (type: bigint) - Select Operator [SEL_7] - outputColumnNames:["_col0","_col1","_col2"] + Filter Operator [FIL_27] + predicate:((_col1 + _col4) >= 0) (type: boolean) + Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE + Merge Join Operator [MERGEJOIN_54] + | condition map:[{"":"Inner Join 0 to 1"}] + | keys:{"0":"_col0 (type: string)","1":"_col0 (type: string)"} + | outputColumnNames:["_col0","_col1","_col2","_col4"] + | Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE + |<-Reducer 10 [SIMPLE_EDGE] + | Reduce Output Operator [RS_25] + | key expressions:_col0 (type: string) + | Map-reduce partition columns:_col0 (type: string) + | sort order:+ + | Statistics:Num rows: 1 Data size: 89 Basic stats: COMPLETE Column stats: COMPLETE + | value expressions:_col1 (type: int) + | Select Operator [SEL_20] + | | outputColumnNames:["_col0","_col1"] + | | Statistics:Num rows: 1 Data size: 89 Basic stats: COMPLETE Column stats: COMPLETE + | |<-Reducer 9 [SIMPLE_EDGE] + | Reduce Output Operator [RS_19] + | key expressions:_col3 (type: double), _col2 (type: bigint) + | sort order:-+ + | Statistics:Num rows: 1 Data size: 105 Basic stats: COMPLETE Column stats: COMPLETE + | value expressions:_col0 (type: string), _col1 (type: int) + | Select Operator [SEL_17] + | outputColumnNames:["_col0","_col1","_col2","_col3"] + | Statistics:Num rows: 1 Data size: 105 Basic stats: COMPLETE Column stats: COMPLETE + | Group By Operator [GBY_16] + | | aggregations:["sum(VALUE._col0)"] + | | keys:KEY._col0 (type: string), KEY._col1 (type: int), KEY._col2 (type: float) + | | outputColumnNames:["_col0","_col1","_col2","_col3"] + | | Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE + | |<-Map 8 [SIMPLE_EDGE] + | Reduce Output Operator [RS_15] + | key expressions:_col0 (type: string), _col1 (type: int), _col2 (type: float) + | Map-reduce partition columns:_col0 (type: string), _col1 (type: int), _col2 (type: float) + | sort order:+++ + | Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE + | value expressions:_col3 (type: bigint) + | Group By Operator [GBY_14] + | aggregations:["sum(c_int)"] + | keys:key (type: string), c_int (type: int), c_float (type: float) + | outputColumnNames:["_col0","_col1","_col2","_col3"] + | Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE + | Filter Operator [FIL_52] + | predicate:((((c_int + 1) >= 0) and ((c_int > 0) or (c_float >= 0.0))) and key is not null) (type: boolean) + | Statistics:Num rows: 3 Data size: 279 Basic stats: COMPLETE Column stats: COMPLETE + | TableScan [TS_11] + | alias:cbo_t2 + | Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE + |<-Reducer 3 [SIMPLE_EDGE] + Reduce Output Operator [RS_23] + key expressions:_col0 (type: string) + Map-reduce partition columns:_col0 (type: string) + sort order:+ + Statistics:Num rows: 1 Data size: 97 Basic stats: COMPLETE Column stats: COMPLETE + value expressions:_col1 (type: int), _col2 (type: bigint) + Select Operator [SEL_9] + | outputColumnNames:["_col0","_col1","_col2"] + | Statistics:Num rows: 1 Data size: 97 Basic stats: COMPLETE Column stats: COMPLETE + |<-Reducer 2 [SIMPLE_EDGE] + Reduce Output Operator [RS_8] + key expressions:_col0 (type: string) + sort order:+ Statistics:Num rows: 1 Data size: 97 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator [GBY_6] - | aggregations:["sum(VALUE._col0)"] - | keys:KEY._col0 (type: float), KEY._col1 (type: int), KEY._col2 (type: string) - | outputColumnNames:["_col0","_col1","_col2","_col3"] - | Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE - |<-Map 1 [SIMPLE_EDGE] - Reduce Output Operator [RS_5] - key expressions:_col0 (type: float), _col1 (type: int), _col2 (type: string) - Map-reduce partition columns:_col0 (type: float), _col1 (type: int), _col2 (type: string) - sort order:+++ - Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE - value expressions:_col3 (type: bigint) - Group By Operator [GBY_4] - aggregations:["sum(_col1)"] - keys:_col0 (type: float), _col1 (type: int), _col2 (type: string) - outputColumnNames:["_col0","_col1","_col2","_col3"] + value expressions:_col1 (type: int), _col2 (type: bigint) + Select Operator [SEL_6] + outputColumnNames:["_col0","_col1","_col2"] + Statistics:Num rows: 1 Data size: 97 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator [GBY_5] + | aggregations:["sum(VALUE._col0)"] + | keys:KEY._col0 (type: string), KEY._col1 (type: int), KEY._col2 (type: float) + | outputColumnNames:["_col0","_col1","_col2","_col3"] + | Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 1 [SIMPLE_EDGE] + Reduce Output Operator [RS_4] + key expressions:_col0 (type: string), _col1 (type: int), _col2 (type: float) + Map-reduce partition columns:_col0 (type: string), _col1 (type: int), _col2 (type: float) + sort order:+++ Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator [SEL_2] - outputColumnNames:["_col0","_col1","_col2"] - Statistics:Num rows: 3 Data size: 279 Basic stats: COMPLETE Column stats: COMPLETE + value expressions:_col3 (type: bigint) + Group By Operator [GBY_3] + aggregations:["sum(c_int)"] + keys:key (type: string), c_int (type: int), c_float (type: float) + outputColumnNames:["_col0","_col1","_col2","_col3"] + Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator [FIL_51] predicate:((((c_int + 1) >= 0) and ((c_int > 0) or (c_float >= 0.0))) and key is not null) (type: boolean) Statistics:Num rows: 3 Data size: 279 Basic stats: COMPLETE Column stats: COMPLETE @@ -711,143 +708,146 @@ Stage-0 sort order:+- Statistics:Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE value expressions:_col1 (type: bigint), _col2 (type: bigint) - Group By Operator [GBY_40] - | aggregations:["count(VALUE._col0)"] - | keys:KEY._col0 (type: int), KEY._col1 (type: bigint) - | outputColumnNames:["_col0","_col1","_col2"] - | Statistics:Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE - |<-Reducer 5 [SIMPLE_EDGE] - Reduce Output Operator [RS_39] - key expressions:_col0 (type: int), _col1 (type: bigint) - Map-reduce partition columns:_col0 (type: int), _col1 (type: bigint) - sort order:++ - Statistics:Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE - value expressions:_col2 (type: bigint) - Group By Operator [GBY_38] - aggregations:["count()"] - keys:_col0 (type: int), _col1 (type: bigint) - outputColumnNames:["_col0","_col1","_col2"] + Select Operator [SEL_40] + outputColumnNames:["_col0","_col1","_col2"] + Statistics:Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator [GBY_39] + | aggregations:["count(VALUE._col0)"] + | keys:KEY._col0 (type: bigint), KEY._col1 (type: int) + | outputColumnNames:["_col0","_col1","_col2"] + | Statistics:Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE + |<-Reducer 5 [SIMPLE_EDGE] + Reduce Output Operator [RS_38] + key expressions:_col0 (type: bigint), _col1 (type: int) + Map-reduce partition columns:_col0 (type: bigint), _col1 (type: int) + sort order:++ Statistics:Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator [SEL_34] - outputColumnNames:["_col0","_col1"] - Statistics:Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator [FIL_48] - predicate:((((_col6 > 0) and ((_col6 >= 1) or (_col2 >= 1))) and ((UDFToLong(_col6) + _col2) >= 0)) and ((_col1 > 0) or (_col6 >= 0))) (type: boolean) + value expressions:_col2 (type: bigint) + Group By Operator [GBY_37] + aggregations:["count()"] + keys:_col2 (type: bigint), _col6 (type: int) + outputColumnNames:["_col0","_col1","_col2"] + Statistics:Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator [SEL_34] + outputColumnNames:["_col2","_col6"] Statistics:Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE - Merge Join Operator [MERGEJOIN_53] - | condition map:[{"":"Left Outer Join0 to 1"}] - | keys:{"0":"_col0 (type: string)","1":"_col0 (type: string)"} - | outputColumnNames:["_col1","_col2","_col6"] - | Statistics:Num rows: 4 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE - |<-Map 10 [SIMPLE_EDGE] - | Reduce Output Operator [RS_31] - | key expressions:_col0 (type: string) - | Map-reduce partition columns:_col0 (type: string) - | sort order:+ - | Statistics:Num rows: 20 Data size: 1602 Basic stats: COMPLETE Column stats: COMPLETE - | value expressions:_col1 (type: int) - | Select Operator [SEL_29] - | outputColumnNames:["_col0","_col1"] - | Statistics:Num rows: 20 Data size: 1602 Basic stats: COMPLETE Column stats: COMPLETE - | TableScan [TS_28] - | alias:cbo_t3 - | Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE - |<-Reducer 4 [SIMPLE_EDGE] - Reduce Output Operator [RS_30] - key expressions:_col0 (type: string) - Map-reduce partition columns:_col0 (type: string) - sort order:+ - Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE - value expressions:_col1 (type: int), _col2 (type: bigint) - Select Operator [SEL_27] - outputColumnNames:["_col0","_col1","_col2"] + Filter Operator [FIL_48] + predicate:((((_col6 > 0) and ((_col6 >= 1) or (_col2 >= 1))) and ((UDFToLong(_col6) + _col2) >= 0)) and ((_col1 > 0) or (_col6 >= 0))) (type: boolean) + Statistics:Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE + Merge Join Operator [MERGEJOIN_53] + | condition map:[{"":"Left Outer Join0 to 1"}] + | keys:{"0":"_col0 (type: string)","1":"_col0 (type: string)"} + | outputColumnNames:["_col1","_col2","_col6"] + | Statistics:Num rows: 4 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 10 [SIMPLE_EDGE] + | Reduce Output Operator [RS_31] + | key expressions:_col0 (type: string) + | Map-reduce partition columns:_col0 (type: string) + | sort order:+ + | Statistics:Num rows: 20 Data size: 1602 Basic stats: COMPLETE Column stats: COMPLETE + | value expressions:_col1 (type: int) + | Select Operator [SEL_29] + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 20 Data size: 1602 Basic stats: COMPLETE Column stats: COMPLETE + | TableScan [TS_28] + | alias:cbo_t3 + | Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE + |<-Reducer 4 [SIMPLE_EDGE] + Reduce Output Operator [RS_30] + key expressions:_col0 (type: string) + Map-reduce partition columns:_col0 (type: string) + sort order:+ Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator [FIL_26] - predicate:((_col1 + _col4) >= 0) (type: boolean) + value expressions:_col1 (type: int), _col2 (type: bigint) + Select Operator [SEL_27] + outputColumnNames:["_col0","_col1","_col2"] Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE - Merge Join Operator [MERGEJOIN_52] - | condition map:[{"":"Left Outer Join0 to 1"}] - | keys:{"0":"_col0 (type: string)","1":"_col0 (type: string)"} - | outputColumnNames:["_col0","_col1","_col2","_col4"] - | Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE - |<-Reducer 3 [SIMPLE_EDGE] - | Reduce Output Operator [RS_23] - | key expressions:_col0 (type: string) - | Map-reduce partition columns:_col0 (type: string) - | sort order:+ - | Statistics:Num rows: 1 Data size: 97 Basic stats: COMPLETE Column stats: COMPLETE - | value expressions:_col1 (type: int), _col2 (type: bigint) - | Select Operator [SEL_11] - | | outputColumnNames:["_col0","_col1","_col2"] - | | Statistics:Num rows: 1 Data size: 97 Basic stats: COMPLETE Column stats: COMPLETE - | |<-Reducer 2 [SIMPLE_EDGE] - | Reduce Output Operator [RS_10] - | key expressions:_col3 (type: bigint), _col1 (type: int) - | sort order:+- - | Statistics:Num rows: 1 Data size: 105 Basic stats: COMPLETE Column stats: COMPLETE - | value expressions:_col0 (type: string), _col2 (type: bigint) - | Select Operator [SEL_9] - | outputColumnNames:["_col0","_col1","_col2","_col3"] - | Statistics:Num rows: 1 Data size: 105 Basic stats: COMPLETE Column stats: COMPLETE - | Group By Operator [GBY_8] - | | aggregations:["sum(VALUE._col0)"] - | | keys:KEY._col0 (type: float), KEY._col1 (type: int), KEY._col2 (type: string) - | | outputColumnNames:["_col0","_col1","_col2","_col3"] - | | Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE - | |<-Map 1 [SIMPLE_EDGE] - | Reduce Output Operator [RS_7] - | key expressions:_col0 (type: float), _col1 (type: int), _col2 (type: string) - | Map-reduce partition columns:_col0 (type: float), _col1 (type: int), _col2 (type: string) - | sort order:+++ - | Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE - | value expressions:_col3 (type: bigint) - | Group By Operator [GBY_6] - | aggregations:["sum(_col1)"] - | keys:_col0 (type: float), _col1 (type: int), _col2 (type: string) - | outputColumnNames:["_col0","_col1","_col2","_col3"] - | Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE - | Select Operator [SEL_2] - | outputColumnNames:["_col0","_col1","_col2"] - | Statistics:Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE - | Filter Operator [FIL_49] - | predicate:((((((c_int + 1) >= 0) and ((c_int > 0) or (c_float >= 0.0))) and (c_float > 0.0)) and ((c_int >= 1) or (c_float >= 1.0))) and ((UDFToFloat(c_int) + c_float) >= 0.0)) (type: boolean) - | Statistics:Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE - | TableScan [TS_0] - | alias:cbo_t1 - | Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE - |<-Reducer 9 [SIMPLE_EDGE] - Reduce Output Operator [RS_24] - key expressions:_col0 (type: string) - Map-reduce partition columns:_col0 (type: string) - sort order:+ - Statistics:Num rows: 1 Data size: 89 Basic stats: COMPLETE Column stats: COMPLETE - value expressions:_col1 (type: int) - Select Operator [SEL_22] - outputColumnNames:["_col0","_col1"] + Filter Operator [FIL_26] + predicate:((_col1 + _col4) >= 0) (type: boolean) + Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE + Merge Join Operator [MERGEJOIN_52] + | condition map:[{"":"Left Outer Join0 to 1"}] + | keys:{"0":"_col0 (type: string)","1":"_col0 (type: string)"} + | outputColumnNames:["_col0","_col1","_col2","_col4"] + | Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE + |<-Reducer 3 [SIMPLE_EDGE] + | Reduce Output Operator [RS_23] + | key expressions:_col0 (type: string) + | Map-reduce partition columns:_col0 (type: string) + | sort order:+ + | Statistics:Num rows: 1 Data size: 97 Basic stats: COMPLETE Column stats: COMPLETE + | value expressions:_col1 (type: int), _col2 (type: bigint) + | Select Operator [SEL_11] + | | outputColumnNames:["_col0","_col1","_col2"] + | | Statistics:Num rows: 1 Data size: 97 Basic stats: COMPLETE Column stats: COMPLETE + | |<-Reducer 2 [SIMPLE_EDGE] + | Reduce Output Operator [RS_10] + | key expressions:_col3 (type: bigint), _col1 (type: int) + | sort order:+- + | Statistics:Num rows: 1 Data size: 105 Basic stats: COMPLETE Column stats: COMPLETE + | value expressions:_col0 (type: string), _col2 (type: bigint) + | Select Operator [SEL_8] + | outputColumnNames:["_col0","_col1","_col2","_col3"] + | Statistics:Num rows: 1 Data size: 105 Basic stats: COMPLETE Column stats: COMPLETE + | Group By Operator [GBY_7] + | | aggregations:["sum(VALUE._col0)"] + | | keys:KEY._col0 (type: string), KEY._col1 (type: int), KEY._col2 (type: float) + | | outputColumnNames:["_col0","_col1","_col2","_col3"] + | | Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE + | |<-Map 1 [SIMPLE_EDGE] + | Reduce Output Operator [RS_6] + | key expressions:_col0 (type: string), _col1 (type: int), _col2 (type: float) + | Map-reduce partition columns:_col0 (type: string), _col1 (type: int), _col2 (type: float) + | sort order:+++ + | Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE + | value expressions:_col3 (type: bigint) + | Group By Operator [GBY_5] + | aggregations:["sum(_col2)"] + | keys:_col0 (type: string), _col2 (type: int), _col3 (type: float) + | outputColumnNames:["_col0","_col1","_col2","_col3"] + | Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE + | Select Operator [SEL_2] + | outputColumnNames:["_col0","_col2","_col3"] + | Statistics:Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE + | Filter Operator [FIL_49] + | predicate:((((((c_int + 1) >= 0) and ((c_int > 0) or (c_float >= 0.0))) and (c_float > 0.0)) and ((c_int >= 1) or (c_float >= 1.0))) and ((UDFToFloat(c_int) + c_float) >= 0.0)) (type: boolean) + | Statistics:Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE + | TableScan [TS_0] + | alias:cbo_t1 + | Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE + |<-Reducer 9 [SIMPLE_EDGE] + Reduce Output Operator [RS_24] + key expressions:_col0 (type: string) + Map-reduce partition columns:_col0 (type: string) + sort order:+ Statistics:Num rows: 1 Data size: 89 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator [GBY_21] - | keys:KEY._col0 (type: float), KEY._col1 (type: int), KEY._col2 (type: string) - | outputColumnNames:["_col0","_col1","_col2"] - | Statistics:Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE - |<-Map 8 [SIMPLE_EDGE] - Reduce Output Operator [RS_20] - key expressions:_col0 (type: float), _col1 (type: int), _col2 (type: string) - Map-reduce partition columns:_col0 (type: float), _col1 (type: int), _col2 (type: string) - sort order:+++ - Statistics:Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator [GBY_19] - keys:_col0 (type: float), _col1 (type: int), _col2 (type: string) - outputColumnNames:["_col0","_col1","_col2"] + value expressions:_col1 (type: int) + Select Operator [SEL_21] + outputColumnNames:["_col0","_col1"] + Statistics:Num rows: 1 Data size: 89 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator [GBY_20] + | keys:KEY._col0 (type: string), KEY._col1 (type: int), KEY._col2 (type: float) + | outputColumnNames:["_col0","_col1","_col2"] + | Statistics:Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 8 [SIMPLE_EDGE] + Reduce Output Operator [RS_19] + key expressions:_col0 (type: string), _col1 (type: int), _col2 (type: float) + Map-reduce partition columns:_col0 (type: string), _col1 (type: int), _col2 (type: float) + sort order:+++ Statistics:Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator [SEL_15] + Group By Operator [GBY_18] + keys:_col0 (type: string), _col2 (type: int), _col3 (type: float) outputColumnNames:["_col0","_col1","_col2"] Statistics:Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator [FIL_50] - predicate:((((((c_int + 1) >= 0) and ((c_int > 0) or (c_float >= 0.0))) and (c_float > 0.0)) and ((c_int >= 1) or (c_float >= 1.0))) and ((UDFToFloat(c_int) + c_float) >= 0.0)) (type: boolean) + Select Operator [SEL_15] + outputColumnNames:["_col0","_col2","_col3"] Statistics:Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE - TableScan [TS_13] - alias:cbo_t2 - Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator [FIL_50] + predicate:((((((c_int + 1) >= 0) and ((c_int > 0) or (c_float >= 0.0))) and (c_float > 0.0)) and ((c_int >= 1) or (c_float >= 1.0))) and ((UDFToFloat(c_int) + c_float) >= 0.0)) (type: boolean) + Statistics:Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE + TableScan [TS_13] + alias:cbo_t2 + Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE PREHOOK: query: explain select cbo_t3.c_int, c, count(*) from (select key as a, c_int+1 as b, sum(c_int) as c from cbo_t1 where (cbo_t1.c_int + 1 >= 0) and (cbo_t1.c_int > 0 or cbo_t1.c_float >= 0) group by c_float, cbo_t1.c_int, key having cbo_t1.c_float > 0 and (c_int >=1 or c_float >= 1) and (c_int + c_float) >= 0 order by b+c, a desc) cbo_t1 right outer join (select key as p, c_int+1 as q, sum(c_int) as r from cbo_t2 where (cbo_t2.c_int + 1 >= 0) and (cbo_t2.c_int > 0 or cbo_t2.c_float >= 0) group by c_float, cbo_t2.c_int, key having cbo_t2.c_float > 0 and (c_int >=1 or c_float >= 1) and (c_int + c_float) >= 0) cbo_t2 on cbo_t1.a=p right outer join cbo_t3 on cbo_t1.a=key where (b + cbo_t2.q >= 2) and (b > 0 or c_int >= 0) group by cbo_t3.c_int, c PREHOOK: type: QUERY @@ -867,129 +867,132 @@ Stage-0 limit:-1 Stage-1 Reducer 5 - File Output Operator [FS_36] + File Output Operator [FS_35] compressed:false Statistics:Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE table:{"input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat","serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe"} - Group By Operator [GBY_34] - | aggregations:["count(VALUE._col0)"] - | keys:KEY._col0 (type: int), KEY._col1 (type: bigint) - | outputColumnNames:["_col0","_col1","_col2"] - | Statistics:Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE - |<-Reducer 4 [SIMPLE_EDGE] - Reduce Output Operator [RS_33] - key expressions:_col0 (type: int), _col1 (type: bigint) - Map-reduce partition columns:_col0 (type: int), _col1 (type: bigint) - sort order:++ - Statistics:Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE - value expressions:_col2 (type: bigint) - Group By Operator [GBY_32] - aggregations:["count()"] - keys:_col0 (type: int), _col1 (type: bigint) - outputColumnNames:["_col0","_col1","_col2"] + Select Operator [SEL_34] + outputColumnNames:["_col0","_col1","_col2"] + Statistics:Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator [GBY_33] + | aggregations:["count(VALUE._col0)"] + | keys:KEY._col0 (type: bigint), KEY._col1 (type: int) + | outputColumnNames:["_col0","_col1","_col2"] + | Statistics:Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE + |<-Reducer 4 [SIMPLE_EDGE] + Reduce Output Operator [RS_32] + key expressions:_col0 (type: bigint), _col1 (type: int) + Map-reduce partition columns:_col0 (type: bigint), _col1 (type: int) + sort order:++ Statistics:Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator [SEL_30] - outputColumnNames:["_col0","_col1"] + value expressions:_col2 (type: bigint) + Group By Operator [GBY_31] + aggregations:["count()"] + keys:_col2 (type: bigint), _col6 (type: int) + outputColumnNames:["_col0","_col1","_col2"] Statistics:Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator [FIL_29] - predicate:(((_col1 + _col4) >= 2) and ((_col1 > 0) or (_col6 >= 0))) (type: boolean) + Select Operator [SEL_30] + outputColumnNames:["_col2","_col6"] Statistics:Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE - Merge Join Operator [MERGEJOIN_41] - | condition map:[{"":"Right Outer Join0 to 1"},{"":"Right Outer Join0 to 2"}] - | keys:{"0":"_col0 (type: string)","1":"_col0 (type: string)","2":"_col0 (type: string)"} - | outputColumnNames:["_col1","_col2","_col4","_col6"] - | Statistics:Num rows: 4 Data size: 80 Basic stats: COMPLETE Column stats: COMPLETE - |<-Map 8 [SIMPLE_EDGE] - | Reduce Output Operator [RS_27] - | key expressions:_col0 (type: string) - | Map-reduce partition columns:_col0 (type: string) - | sort order:+ - | Statistics:Num rows: 20 Data size: 1602 Basic stats: COMPLETE Column stats: COMPLETE - | value expressions:_col1 (type: int) - | Select Operator [SEL_24] - | outputColumnNames:["_col0","_col1"] - | Statistics:Num rows: 20 Data size: 1602 Basic stats: COMPLETE Column stats: COMPLETE - | TableScan [TS_23] - | alias:cbo_t3 - | Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE - |<-Reducer 3 [SIMPLE_EDGE] - | Reduce Output Operator [RS_25] - | key expressions:_col0 (type: string) - | Map-reduce partition columns:_col0 (type: string) - | sort order:+ - | Statistics:Num rows: 1 Data size: 97 Basic stats: COMPLETE Column stats: COMPLETE - | value expressions:_col1 (type: int), _col2 (type: bigint) - | Select Operator [SEL_11] - | | outputColumnNames:["_col0","_col1","_col2"] - | | Statistics:Num rows: 1 Data size: 97 Basic stats: COMPLETE Column stats: COMPLETE - | |<-Reducer 2 [SIMPLE_EDGE] - | Reduce Output Operator [RS_10] - | key expressions:_col3 (type: bigint), _col0 (type: string) - | sort order:+- - | Statistics:Num rows: 1 Data size: 105 Basic stats: COMPLETE Column stats: COMPLETE - | value expressions:_col1 (type: int), _col2 (type: bigint) - | Select Operator [SEL_9] - | outputColumnNames:["_col0","_col1","_col2","_col3"] - | Statistics:Num rows: 1 Data size: 105 Basic stats: COMPLETE Column stats: COMPLETE - | Group By Operator [GBY_8] - | | aggregations:["sum(VALUE._col0)"] - | | keys:KEY._col0 (type: float), KEY._col1 (type: int), KEY._col2 (type: string) - | | outputColumnNames:["_col0","_col1","_col2","_col3"] - | | Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE - | |<-Map 1 [SIMPLE_EDGE] - | Reduce Output Operator [RS_7] - | key expressions:_col0 (type: float), _col1 (type: int), _col2 (type: string) - | Map-reduce partition columns:_col0 (type: float), _col1 (type: int), _col2 (type: string) - | sort order:+++ - | Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE - | value expressions:_col3 (type: bigint) - | Group By Operator [GBY_6] - | aggregations:["sum(_col1)"] - | keys:_col0 (type: float), _col1 (type: int), _col2 (type: string) - | outputColumnNames:["_col0","_col1","_col2","_col3"] - | Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE - | Select Operator [SEL_2] - | outputColumnNames:["_col0","_col1","_col2"] - | Statistics:Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE - | Filter Operator [FIL_39] - | predicate:((((((c_int + 1) >= 0) and ((c_int > 0) or (c_float >= 0.0))) and (c_float > 0.0)) and ((c_int >= 1) or (c_float >= 1.0))) and ((UDFToFloat(c_int) + c_float) >= 0.0)) (type: boolean) - | Statistics:Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE - | TableScan [TS_0] - | alias:cbo_t1 - | Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE - |<-Reducer 7 [SIMPLE_EDGE] - Reduce Output Operator [RS_26] - key expressions:_col0 (type: string) - Map-reduce partition columns:_col0 (type: string) - sort order:+ - Statistics:Num rows: 1 Data size: 89 Basic stats: COMPLETE Column stats: COMPLETE - value expressions:_col1 (type: int) - Select Operator [SEL_22] - outputColumnNames:["_col0","_col1"] + Filter Operator [FIL_29] + predicate:(((_col1 + _col4) >= 2) and ((_col1 > 0) or (_col6 >= 0))) (type: boolean) + Statistics:Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE + Merge Join Operator [MERGEJOIN_40] + | condition map:[{"":"Right Outer Join0 to 1"},{"":"Right Outer Join0 to 2"}] + | keys:{"0":"_col0 (type: string)","1":"_col0 (type: string)","2":"_col0 (type: string)"} + | outputColumnNames:["_col1","_col2","_col4","_col6"] + | Statistics:Num rows: 4 Data size: 80 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 8 [SIMPLE_EDGE] + | Reduce Output Operator [RS_27] + | key expressions:_col0 (type: string) + | Map-reduce partition columns:_col0 (type: string) + | sort order:+ + | Statistics:Num rows: 20 Data size: 1602 Basic stats: COMPLETE Column stats: COMPLETE + | value expressions:_col1 (type: int) + | Select Operator [SEL_24] + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 20 Data size: 1602 Basic stats: COMPLETE Column stats: COMPLETE + | TableScan [TS_23] + | alias:cbo_t3 + | Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE + |<-Reducer 3 [SIMPLE_EDGE] + | Reduce Output Operator [RS_25] + | key expressions:_col0 (type: string) + | Map-reduce partition columns:_col0 (type: string) + | sort order:+ + | Statistics:Num rows: 1 Data size: 97 Basic stats: COMPLETE Column stats: COMPLETE + | value expressions:_col1 (type: int), _col2 (type: bigint) + | Select Operator [SEL_11] + | | outputColumnNames:["_col0","_col1","_col2"] + | | Statistics:Num rows: 1 Data size: 97 Basic stats: COMPLETE Column stats: COMPLETE + | |<-Reducer 2 [SIMPLE_EDGE] + | Reduce Output Operator [RS_10] + | key expressions:_col3 (type: bigint), _col0 (type: string) + | sort order:+- + | Statistics:Num rows: 1 Data size: 105 Basic stats: COMPLETE Column stats: COMPLETE + | value expressions:_col1 (type: int), _col2 (type: bigint) + | Select Operator [SEL_8] + | outputColumnNames:["_col0","_col1","_col2","_col3"] + | Statistics:Num rows: 1 Data size: 105 Basic stats: COMPLETE Column stats: COMPLETE + | Group By Operator [GBY_7] + | | aggregations:["sum(VALUE._col0)"] + | | keys:KEY._col0 (type: string), KEY._col1 (type: int), KEY._col2 (type: float) + | | outputColumnNames:["_col0","_col1","_col2","_col3"] + | | Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE + | |<-Map 1 [SIMPLE_EDGE] + | Reduce Output Operator [RS_6] + | key expressions:_col0 (type: string), _col1 (type: int), _col2 (type: float) + | Map-reduce partition columns:_col0 (type: string), _col1 (type: int), _col2 (type: float) + | sort order:+++ + | Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE + | value expressions:_col3 (type: bigint) + | Group By Operator [GBY_5] + | aggregations:["sum(_col2)"] + | keys:_col0 (type: string), _col2 (type: int), _col3 (type: float) + | outputColumnNames:["_col0","_col1","_col2","_col3"] + | Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE + | Select Operator [SEL_2] + | outputColumnNames:["_col0","_col2","_col3"] + | Statistics:Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE + | Filter Operator [FIL_38] + | predicate:((((((c_int + 1) >= 0) and ((c_int > 0) or (c_float >= 0.0))) and (c_float > 0.0)) and ((c_int >= 1) or (c_float >= 1.0))) and ((UDFToFloat(c_int) + c_float) >= 0.0)) (type: boolean) + | Statistics:Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE + | TableScan [TS_0] + | alias:cbo_t1 + | Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE + |<-Reducer 7 [SIMPLE_EDGE] + Reduce Output Operator [RS_26] + key expressions:_col0 (type: string) + Map-reduce partition columns:_col0 (type: string) + sort order:+ Statistics:Num rows: 1 Data size: 89 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator [GBY_21] - | keys:KEY._col0 (type: float), KEY._col1 (type: int), KEY._col2 (type: string) - | outputColumnNames:["_col0","_col1","_col2"] - | Statistics:Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE - |<-Map 6 [SIMPLE_EDGE] - Reduce Output Operator [RS_20] - key expressions:_col0 (type: float), _col1 (type: int), _col2 (type: string) - Map-reduce partition columns:_col0 (type: float), _col1 (type: int), _col2 (type: string) - sort order:+++ - Statistics:Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator [GBY_19] - keys:_col0 (type: float), _col1 (type: int), _col2 (type: string) - outputColumnNames:["_col0","_col1","_col2"] + value expressions:_col1 (type: int) + Select Operator [SEL_21] + outputColumnNames:["_col0","_col1"] + Statistics:Num rows: 1 Data size: 89 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator [GBY_20] + | keys:KEY._col0 (type: string), KEY._col1 (type: int), KEY._col2 (type: float) + | outputColumnNames:["_col0","_col1","_col2"] + | Statistics:Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 6 [SIMPLE_EDGE] + Reduce Output Operator [RS_19] + key expressions:_col0 (type: string), _col1 (type: int), _col2 (type: float) + Map-reduce partition columns:_col0 (type: string), _col1 (type: int), _col2 (type: float) + sort order:+++ Statistics:Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator [SEL_15] + Group By Operator [GBY_18] + keys:_col0 (type: string), _col2 (type: int), _col3 (type: float) outputColumnNames:["_col0","_col1","_col2"] Statistics:Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator [FIL_40] - predicate:((((((c_int + 1) >= 0) and ((c_int > 0) or (c_float >= 0.0))) and (c_float > 0.0)) and ((c_int >= 1) or (c_float >= 1.0))) and ((UDFToFloat(c_int) + c_float) >= 0.0)) (type: boolean) + Select Operator [SEL_15] + outputColumnNames:["_col0","_col2","_col3"] Statistics:Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE - TableScan [TS_13] - alias:cbo_t2 - Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator [FIL_39] + predicate:((((((c_int + 1) >= 0) and ((c_int > 0) or (c_float >= 0.0))) and (c_float > 0.0)) and ((c_int >= 1) or (c_float >= 1.0))) and ((UDFToFloat(c_int) + c_float) >= 0.0)) (type: boolean) + Statistics:Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE + TableScan [TS_13] + alias:cbo_t2 + Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE PREHOOK: query: explain select cbo_t3.c_int, c, count(*) from (select key as a, c_int+1 as b, sum(c_int) as c from cbo_t1 where (cbo_t1.c_int + 1 >= 0) and (cbo_t1.c_int > 0 or cbo_t1.c_float >= 0) group by c_float, cbo_t1.c_int, key having cbo_t1.c_float > 0 and (c_int >=1 or c_float >= 1) and (c_int + c_float) >= 0 order by c+a desc) cbo_t1 full outer join (select key as p, c_int+1 as q, sum(c_int) as r from cbo_t2 where (cbo_t2.c_int + 1 >= 0) and (cbo_t2.c_int > 0 or cbo_t2.c_float >= 0) group by c_float, cbo_t2.c_int, key having cbo_t2.c_float > 0 and (c_int >=1 or c_float >= 1) and (c_int + c_float) >= 0 order by p+q desc, r asc) cbo_t2 on cbo_t1.a=p full outer join cbo_t3 on cbo_t1.a=key where (b + cbo_t2.q >= 0) and (b > 0 or c_int >= 0) group by cbo_t3.c_int, c having cbo_t3.c_int > 0 and (c_int >=1 or c >= 1) and (c_int + c) >= 0 order by cbo_t3.c_int PREHOOK: type: QUERY @@ -1011,150 +1014,153 @@ Stage-0 limit:-1 Stage-1 Reducer 6 - File Output Operator [FS_43] + File Output Operator [FS_42] compressed:false Statistics:Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE table:{"input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat","serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe"} - Select Operator [SEL_42] + Select Operator [SEL_41] | outputColumnNames:["_col0","_col1","_col2"] | Statistics:Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE |<-Reducer 5 [SIMPLE_EDGE] - Reduce Output Operator [RS_41] + Reduce Output Operator [RS_40] key expressions:_col0 (type: int) sort order:+ Statistics:Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE value expressions:_col1 (type: bigint), _col2 (type: bigint) - Group By Operator [GBY_39] - | aggregations:["count(VALUE._col0)"] - | keys:KEY._col0 (type: int), KEY._col1 (type: bigint) - | outputColumnNames:["_col0","_col1","_col2"] - | Statistics:Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE - |<-Reducer 4 [SIMPLE_EDGE] - Reduce Output Operator [RS_38] - key expressions:_col0 (type: int), _col1 (type: bigint) - Map-reduce partition columns:_col0 (type: int), _col1 (type: bigint) - sort order:++ - Statistics:Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE - value expressions:_col2 (type: bigint) - Group By Operator [GBY_37] - aggregations:["count()"] - keys:_col0 (type: int), _col1 (type: bigint) - outputColumnNames:["_col0","_col1","_col2"] + Select Operator [SEL_39] + outputColumnNames:["_col0","_col1","_col2"] + Statistics:Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator [GBY_38] + | aggregations:["count(VALUE._col0)"] + | keys:KEY._col0 (type: bigint), KEY._col1 (type: int) + | outputColumnNames:["_col0","_col1","_col2"] + | Statistics:Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE + |<-Reducer 4 [SIMPLE_EDGE] + Reduce Output Operator [RS_37] + key expressions:_col0 (type: bigint), _col1 (type: int) + Map-reduce partition columns:_col0 (type: bigint), _col1 (type: int) + sort order:++ Statistics:Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator [SEL_33] - outputColumnNames:["_col0","_col1"] + value expressions:_col2 (type: bigint) + Group By Operator [GBY_36] + aggregations:["count()"] + keys:_col2 (type: bigint), _col6 (type: int) + outputColumnNames:["_col0","_col1","_col2"] Statistics:Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator [FIL_45] - predicate:(((((_col6 > 0) and ((_col6 >= 1) or (_col2 >= 1))) and ((UDFToLong(_col6) + _col2) >= 0)) and ((_col1 + _col4) >= 0)) and ((_col1 > 0) or (_col6 >= 0))) (type: boolean) + Select Operator [SEL_33] + outputColumnNames:["_col2","_col6"] Statistics:Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE - Merge Join Operator [MERGEJOIN_48] - | condition map:[{"":"Outer Join 0 to 1"},{"":"Outer Join 0 to 2"}] - | keys:{"0":"_col0 (type: string)","1":"_col0 (type: string)","2":"_col0 (type: string)"} - | outputColumnNames:["_col1","_col2","_col4","_col6"] - | Statistics:Num rows: 4 Data size: 80 Basic stats: COMPLETE Column stats: COMPLETE - |<-Map 10 [SIMPLE_EDGE] - | Reduce Output Operator [RS_30] - | key expressions:_col0 (type: string) - | Map-reduce partition columns:_col0 (type: string) - | sort order:+ - | Statistics:Num rows: 20 Data size: 1602 Basic stats: COMPLETE Column stats: COMPLETE - | value expressions:_col1 (type: int) - | Select Operator [SEL_27] - | outputColumnNames:["_col0","_col1"] - | Statistics:Num rows: 20 Data size: 1602 Basic stats: COMPLETE Column stats: COMPLETE - | TableScan [TS_26] - | alias:cbo_t3 - | Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE - |<-Reducer 3 [SIMPLE_EDGE] - | Reduce Output Operator [RS_28] - | key expressions:_col0 (type: string) - | Map-reduce partition columns:_col0 (type: string) - | sort order:+ - | Statistics:Num rows: 1 Data size: 97 Basic stats: COMPLETE Column stats: COMPLETE - | value expressions:_col1 (type: int), _col2 (type: bigint) - | Select Operator [SEL_11] - | | outputColumnNames:["_col0","_col1","_col2"] - | | Statistics:Num rows: 1 Data size: 97 Basic stats: COMPLETE Column stats: COMPLETE - | |<-Reducer 2 [SIMPLE_EDGE] - | Reduce Output Operator [RS_10] - | key expressions:_col3 (type: double) - | sort order:- - | Statistics:Num rows: 1 Data size: 105 Basic stats: COMPLETE Column stats: COMPLETE - | value expressions:_col0 (type: string), _col1 (type: int), _col2 (type: bigint) - | Select Operator [SEL_9] - | outputColumnNames:["_col0","_col1","_col2","_col3"] - | Statistics:Num rows: 1 Data size: 105 Basic stats: COMPLETE Column stats: COMPLETE - | Group By Operator [GBY_8] - | | aggregations:["sum(VALUE._col0)"] - | | keys:KEY._col0 (type: float), KEY._col1 (type: int), KEY._col2 (type: string) - | | outputColumnNames:["_col0","_col1","_col2","_col3"] - | | Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE - | |<-Map 1 [SIMPLE_EDGE] - | Reduce Output Operator [RS_7] - | key expressions:_col0 (type: float), _col1 (type: int), _col2 (type: string) - | Map-reduce partition columns:_col0 (type: float), _col1 (type: int), _col2 (type: string) - | sort order:+++ - | Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE - | value expressions:_col3 (type: bigint) - | Group By Operator [GBY_6] - | aggregations:["sum(_col1)"] - | keys:_col0 (type: float), _col1 (type: int), _col2 (type: string) - | outputColumnNames:["_col0","_col1","_col2","_col3"] - | Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE - | Select Operator [SEL_2] - | outputColumnNames:["_col0","_col1","_col2"] - | Statistics:Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE - | Filter Operator [FIL_46] - | predicate:((((((c_int + 1) >= 0) and ((c_int > 0) or (c_float >= 0.0))) and (c_float > 0.0)) and ((c_int >= 1) or (c_float >= 1.0))) and ((UDFToFloat(c_int) + c_float) >= 0.0)) (type: boolean) - | Statistics:Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE - | TableScan [TS_0] - | alias:cbo_t1 - | Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE - |<-Reducer 9 [SIMPLE_EDGE] - Reduce Output Operator [RS_29] - key expressions:_col0 (type: string) - Map-reduce partition columns:_col0 (type: string) - sort order:+ - Statistics:Num rows: 1 Data size: 89 Basic stats: COMPLETE Column stats: COMPLETE - value expressions:_col1 (type: int) - Select Operator [SEL_24] - | outputColumnNames:["_col0","_col1"] - | Statistics:Num rows: 1 Data size: 89 Basic stats: COMPLETE Column stats: COMPLETE - |<-Reducer 8 [SIMPLE_EDGE] - Reduce Output Operator [RS_23] - key expressions:_col3 (type: double), _col2 (type: bigint) - sort order:-+ - Statistics:Num rows: 1 Data size: 105 Basic stats: COMPLETE Column stats: COMPLETE - value expressions:_col0 (type: string), _col1 (type: int) - Select Operator [SEL_22] - outputColumnNames:["_col0","_col1","_col2","_col3"] + Filter Operator [FIL_44] + predicate:(((((_col6 > 0) and ((_col6 >= 1) or (_col2 >= 1))) and ((UDFToLong(_col6) + _col2) >= 0)) and ((_col1 + _col4) >= 0)) and ((_col1 > 0) or (_col6 >= 0))) (type: boolean) + Statistics:Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE + Merge Join Operator [MERGEJOIN_47] + | condition map:[{"":"Outer Join 0 to 1"},{"":"Outer Join 0 to 2"}] + | keys:{"0":"_col0 (type: string)","1":"_col0 (type: string)","2":"_col0 (type: string)"} + | outputColumnNames:["_col1","_col2","_col4","_col6"] + | Statistics:Num rows: 4 Data size: 80 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 10 [SIMPLE_EDGE] + | Reduce Output Operator [RS_30] + | key expressions:_col0 (type: string) + | Map-reduce partition columns:_col0 (type: string) + | sort order:+ + | Statistics:Num rows: 20 Data size: 1602 Basic stats: COMPLETE Column stats: COMPLETE + | value expressions:_col1 (type: int) + | Select Operator [SEL_27] + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 20 Data size: 1602 Basic stats: COMPLETE Column stats: COMPLETE + | TableScan [TS_26] + | alias:cbo_t3 + | Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE + |<-Reducer 3 [SIMPLE_EDGE] + | Reduce Output Operator [RS_28] + | key expressions:_col0 (type: string) + | Map-reduce partition columns:_col0 (type: string) + | sort order:+ + | Statistics:Num rows: 1 Data size: 97 Basic stats: COMPLETE Column stats: COMPLETE + | value expressions:_col1 (type: int), _col2 (type: bigint) + | Select Operator [SEL_11] + | | outputColumnNames:["_col0","_col1","_col2"] + | | Statistics:Num rows: 1 Data size: 97 Basic stats: COMPLETE Column stats: COMPLETE + | |<-Reducer 2 [SIMPLE_EDGE] + | Reduce Output Operator [RS_10] + | key expressions:_col3 (type: double) + | sort order:- + | Statistics:Num rows: 1 Data size: 105 Basic stats: COMPLETE Column stats: COMPLETE + | value expressions:_col0 (type: string), _col1 (type: int), _col2 (type: bigint) + | Select Operator [SEL_8] + | outputColumnNames:["_col0","_col1","_col2","_col3"] + | Statistics:Num rows: 1 Data size: 105 Basic stats: COMPLETE Column stats: COMPLETE + | Group By Operator [GBY_7] + | | aggregations:["sum(VALUE._col0)"] + | | keys:KEY._col0 (type: string), KEY._col1 (type: int), KEY._col2 (type: float) + | | outputColumnNames:["_col0","_col1","_col2","_col3"] + | | Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE + | |<-Map 1 [SIMPLE_EDGE] + | Reduce Output Operator [RS_6] + | key expressions:_col0 (type: string), _col1 (type: int), _col2 (type: float) + | Map-reduce partition columns:_col0 (type: string), _col1 (type: int), _col2 (type: float) + | sort order:+++ + | Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE + | value expressions:_col3 (type: bigint) + | Group By Operator [GBY_5] + | aggregations:["sum(_col2)"] + | keys:_col0 (type: string), _col2 (type: int), _col3 (type: float) + | outputColumnNames:["_col0","_col1","_col2","_col3"] + | Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE + | Select Operator [SEL_2] + | outputColumnNames:["_col0","_col2","_col3"] + | Statistics:Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE + | Filter Operator [FIL_45] + | predicate:((((((c_int + 1) >= 0) and ((c_int > 0) or (c_float >= 0.0))) and (c_float > 0.0)) and ((c_int >= 1) or (c_float >= 1.0))) and ((UDFToFloat(c_int) + c_float) >= 0.0)) (type: boolean) + | Statistics:Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE + | TableScan [TS_0] + | alias:cbo_t1 + | Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE + |<-Reducer 9 [SIMPLE_EDGE] + Reduce Output Operator [RS_29] + key expressions:_col0 (type: string) + Map-reduce partition columns:_col0 (type: string) + sort order:+ + Statistics:Num rows: 1 Data size: 89 Basic stats: COMPLETE Column stats: COMPLETE + value expressions:_col1 (type: int) + Select Operator [SEL_24] + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 1 Data size: 89 Basic stats: COMPLETE Column stats: COMPLETE + |<-Reducer 8 [SIMPLE_EDGE] + Reduce Output Operator [RS_23] + key expressions:_col3 (type: double), _col2 (type: bigint) + sort order:-+ Statistics:Num rows: 1 Data size: 105 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator [GBY_21] - | aggregations:["sum(VALUE._col0)"] - | keys:KEY._col0 (type: float), KEY._col1 (type: int), KEY._col2 (type: string) - | outputColumnNames:["_col0","_col1","_col2","_col3"] - | Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE - |<-Map 7 [SIMPLE_EDGE] - Reduce Output Operator [RS_20] - key expressions:_col0 (type: float), _col1 (type: int), _col2 (type: string) - Map-reduce partition columns:_col0 (type: float), _col1 (type: int), _col2 (type: string) - sort order:+++ - Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE - value expressions:_col3 (type: bigint) - Group By Operator [GBY_19] - aggregations:["sum(_col1)"] - keys:_col0 (type: float), _col1 (type: int), _col2 (type: string) - outputColumnNames:["_col0","_col1","_col2","_col3"] + value expressions:_col0 (type: string), _col1 (type: int) + Select Operator [SEL_21] + outputColumnNames:["_col0","_col1","_col2","_col3"] + Statistics:Num rows: 1 Data size: 105 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator [GBY_20] + | aggregations:["sum(VALUE._col0)"] + | keys:KEY._col0 (type: string), KEY._col1 (type: int), KEY._col2 (type: float) + | outputColumnNames:["_col0","_col1","_col2","_col3"] + | Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 7 [SIMPLE_EDGE] + Reduce Output Operator [RS_19] + key expressions:_col0 (type: string), _col1 (type: int), _col2 (type: float) + Map-reduce partition columns:_col0 (type: string), _col1 (type: int), _col2 (type: float) + sort order:+++ Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator [SEL_15] - outputColumnNames:["_col0","_col1","_col2"] - Statistics:Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator [FIL_47] - predicate:((((((c_int + 1) >= 0) and ((c_int > 0) or (c_float >= 0.0))) and (c_float > 0.0)) and ((c_int >= 1) or (c_float >= 1.0))) and ((UDFToFloat(c_int) + c_float) >= 0.0)) (type: boolean) + value expressions:_col3 (type: bigint) + Group By Operator [GBY_18] + aggregations:["sum(_col2)"] + keys:_col0 (type: string), _col2 (type: int), _col3 (type: float) + outputColumnNames:["_col0","_col1","_col2","_col3"] + Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator [SEL_15] + outputColumnNames:["_col0","_col2","_col3"] Statistics:Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE - TableScan [TS_13] - alias:cbo_t2 - Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator [FIL_46] + predicate:((((((c_int + 1) >= 0) and ((c_int > 0) or (c_float >= 0.0))) and (c_float > 0.0)) and ((c_int >= 1) or (c_float >= 1.0))) and ((UDFToFloat(c_int) + c_float) >= 0.0)) (type: boolean) + Statistics:Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE + TableScan [TS_13] + alias:cbo_t2 + Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE PREHOOK: query: explain select cbo_t3.c_int, c, count(*) from (select key as a, c_int+1 as b, sum(c_int) as c from cbo_t1 where (cbo_t1.c_int + 1 >= 0) and (cbo_t1.c_int > 0 or cbo_t1.c_float >= 0) group by c_float, cbo_t1.c_int, key having cbo_t1.c_float > 0 and (c_int >=1 or c_float >= 1) and (c_int + c_float) >= 0) cbo_t1 join (select key as p, c_int+1 as q, sum(c_int) as r from cbo_t2 where (cbo_t2.c_int + 1 >= 0) and (cbo_t2.c_int > 0 or cbo_t2.c_float >= 0) group by c_float, cbo_t2.c_int, key having cbo_t2.c_float > 0 and (c_int >=1 or c_float >= 1) and (c_int + c_float) >= 0) cbo_t2 on cbo_t1.a=p join cbo_t3 on cbo_t1.a=key where (b + cbo_t2.q >= 0) and (b > 0 or c_int >= 0) group by cbo_t3.c_int, c PREHOOK: type: QUERY @@ -1174,141 +1180,144 @@ Stage-0 limit:-1 Stage-1 Reducer 5 - File Output Operator [FS_41] + File Output Operator [FS_40] compressed:false Statistics:Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE table:{"input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat","serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe"} - Group By Operator [GBY_39] - | aggregations:["count(VALUE._col0)"] - | keys:KEY._col0 (type: int), KEY._col1 (type: bigint) - | outputColumnNames:["_col0","_col1","_col2"] - | Statistics:Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE - |<-Reducer 4 [SIMPLE_EDGE] - Reduce Output Operator [RS_38] - key expressions:_col0 (type: int), _col1 (type: bigint) - Map-reduce partition columns:_col0 (type: int), _col1 (type: bigint) - sort order:++ - Statistics:Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE - value expressions:_col2 (type: bigint) - Group By Operator [GBY_37] - aggregations:["count()"] - keys:_col0 (type: int), _col1 (type: bigint) - outputColumnNames:["_col0","_col1","_col2"] + Select Operator [SEL_39] + outputColumnNames:["_col0","_col1","_col2"] + Statistics:Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator [GBY_38] + | aggregations:["count(VALUE._col0)"] + | keys:KEY._col0 (type: bigint), KEY._col1 (type: int) + | outputColumnNames:["_col0","_col1","_col2"] + | Statistics:Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE + |<-Reducer 4 [SIMPLE_EDGE] + Reduce Output Operator [RS_37] + key expressions:_col0 (type: bigint), _col1 (type: int) + Map-reduce partition columns:_col0 (type: bigint), _col1 (type: int) + sort order:++ Statistics:Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator [SEL_35] - outputColumnNames:["_col0","_col1"] - Statistics:Num rows: 2 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator [FIL_34] - predicate:((_col1 > 0) or (_col6 >= 0)) (type: boolean) + value expressions:_col2 (type: bigint) + Group By Operator [GBY_36] + aggregations:["count()"] + keys:_col2 (type: bigint), _col6 (type: int) + outputColumnNames:["_col0","_col1","_col2"] + Statistics:Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator [SEL_35] + outputColumnNames:["_col2","_col6"] Statistics:Num rows: 2 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE - Merge Join Operator [MERGEJOIN_51] - | condition map:[{"":"Inner Join 0 to 1"}] - | keys:{"0":"_col0 (type: string)","1":"_col0 (type: string)"} - | outputColumnNames:["_col1","_col2","_col6"] - | Statistics:Num rows: 3 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE - |<-Map 8 [SIMPLE_EDGE] - | Reduce Output Operator [RS_32] - | key expressions:_col0 (type: string) - | Map-reduce partition columns:_col0 (type: string) - | sort order:+ - | Statistics:Num rows: 18 Data size: 1424 Basic stats: COMPLETE Column stats: COMPLETE - | value expressions:_col1 (type: int) - | Select Operator [SEL_28] - | outputColumnNames:["_col0","_col1"] - | Statistics:Num rows: 18 Data size: 1424 Basic stats: COMPLETE Column stats: COMPLETE - | Filter Operator [FIL_49] - | predicate:key is not null (type: boolean) - | Statistics:Num rows: 18 Data size: 1424 Basic stats: COMPLETE Column stats: COMPLETE - | TableScan [TS_27] - | alias:cbo_t3 - | Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE - |<-Reducer 3 [SIMPLE_EDGE] - Reduce Output Operator [RS_30] - key expressions:_col0 (type: string) - Map-reduce partition columns:_col0 (type: string) - sort order:+ - Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE - value expressions:_col1 (type: int), _col2 (type: bigint) - Select Operator [SEL_26] - outputColumnNames:["_col0","_col1","_col2"] + Filter Operator [FIL_34] + predicate:((_col1 > 0) or (_col6 >= 0)) (type: boolean) + Statistics:Num rows: 2 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE + Merge Join Operator [MERGEJOIN_50] + | condition map:[{"":"Inner Join 0 to 1"}] + | keys:{"0":"_col0 (type: string)","1":"_col0 (type: string)"} + | outputColumnNames:["_col1","_col2","_col6"] + | Statistics:Num rows: 3 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 8 [SIMPLE_EDGE] + | Reduce Output Operator [RS_32] + | key expressions:_col0 (type: string) + | Map-reduce partition columns:_col0 (type: string) + | sort order:+ + | Statistics:Num rows: 18 Data size: 1424 Basic stats: COMPLETE Column stats: COMPLETE + | value expressions:_col1 (type: int) + | Select Operator [SEL_28] + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 18 Data size: 1424 Basic stats: COMPLETE Column stats: COMPLETE + | Filter Operator [FIL_48] + | predicate:key is not null (type: boolean) + | Statistics:Num rows: 18 Data size: 1424 Basic stats: COMPLETE Column stats: COMPLETE + | TableScan [TS_27] + | alias:cbo_t3 + | Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE + |<-Reducer 3 [SIMPLE_EDGE] + Reduce Output Operator [RS_30] + key expressions:_col0 (type: string) + Map-reduce partition columns:_col0 (type: string) + sort order:+ Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator [FIL_25] - predicate:((_col1 + _col4) >= 0) (type: boolean) + value expressions:_col1 (type: int), _col2 (type: bigint) + Select Operator [SEL_26] + outputColumnNames:["_col0","_col1","_col2"] Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE - Merge Join Operator [MERGEJOIN_50] - | condition map:[{"":"Inner Join 0 to 1"}] - | keys:{"0":"_col0 (type: string)","1":"_col0 (type: string)"} - | outputColumnNames:["_col0","_col1","_col2","_col4"] - | Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE - |<-Reducer 2 [SIMPLE_EDGE] - | Reduce Output Operator [RS_21] - | key expressions:_col0 (type: string) - | Map-reduce partition columns:_col0 (type: string) - | sort order:+ - | Statistics:Num rows: 1 Data size: 97 Basic stats: COMPLETE Column stats: COMPLETE - | value expressions:_col1 (type: int), _col2 (type: bigint) - | Select Operator [SEL_9] - | outputColumnNames:["_col0","_col1","_col2"] - | Statistics:Num rows: 1 Data size: 97 Basic stats: COMPLETE Column stats: COMPLETE - | Group By Operator [GBY_8] - | | aggregations:["sum(VALUE._col0)"] - | | keys:KEY._col0 (type: float), KEY._col1 (type: int), KEY._col2 (type: string) - | | outputColumnNames:["_col0","_col1","_col2","_col3"] - | | Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE - | |<-Map 1 [SIMPLE_EDGE] - | Reduce Output Operator [RS_7] - | key expressions:_col0 (type: float), _col1 (type: int), _col2 (type: string) - | Map-reduce partition columns:_col0 (type: float), _col1 (type: int), _col2 (type: string) - | sort order:+++ - | Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE - | value expressions:_col3 (type: bigint) - | Group By Operator [GBY_6] - | aggregations:["sum(_col1)"] - | keys:_col0 (type: float), _col1 (type: int), _col2 (type: string) - | outputColumnNames:["_col0","_col1","_col2","_col3"] - | Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE - | Select Operator [SEL_2] - | outputColumnNames:["_col0","_col1","_col2"] - | Statistics:Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE - | Filter Operator [FIL_47] - | predicate:(((((((c_int + 1) >= 0) and ((c_int > 0) or (c_float >= 0.0))) and (c_float > 0.0)) and ((c_int >= 1) or (c_float >= 1.0))) and ((UDFToFloat(c_int) + c_float) >= 0.0)) and key is not null) (type: boolean) - | Statistics:Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE - | TableScan [TS_0] - | alias:cbo_t1 - | Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE - |<-Reducer 7 [SIMPLE_EDGE] - Reduce Output Operator [RS_23] - key expressions:_col0 (type: string) - Map-reduce partition columns:_col0 (type: string) - sort order:+ - Statistics:Num rows: 1 Data size: 89 Basic stats: COMPLETE Column stats: COMPLETE - value expressions:_col1 (type: int) - Select Operator [SEL_19] - outputColumnNames:["_col0","_col1"] + Filter Operator [FIL_25] + predicate:((_col1 + _col4) >= 0) (type: boolean) + Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE + Merge Join Operator [MERGEJOIN_49] + | condition map:[{"":"Inner Join 0 to 1"}] + | keys:{"0":"_col0 (type: string)","1":"_col0 (type: string)"} + | outputColumnNames:["_col0","_col1","_col2","_col4"] + | Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE + |<-Reducer 2 [SIMPLE_EDGE] + | Reduce Output Operator [RS_21] + | key expressions:_col0 (type: string) + | Map-reduce partition columns:_col0 (type: string) + | sort order:+ + | Statistics:Num rows: 1 Data size: 97 Basic stats: COMPLETE Column stats: COMPLETE + | value expressions:_col1 (type: int), _col2 (type: bigint) + | Select Operator [SEL_8] + | outputColumnNames:["_col0","_col1","_col2"] + | Statistics:Num rows: 1 Data size: 97 Basic stats: COMPLETE Column stats: COMPLETE + | Group By Operator [GBY_7] + | | aggregations:["sum(VALUE._col0)"] + | | keys:KEY._col0 (type: string), KEY._col1 (type: int), KEY._col2 (type: float) + | | outputColumnNames:["_col0","_col1","_col2","_col3"] + | | Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE + | |<-Map 1 [SIMPLE_EDGE] + | Reduce Output Operator [RS_6] + | key expressions:_col0 (type: string), _col1 (type: int), _col2 (type: float) + | Map-reduce partition columns:_col0 (type: string), _col1 (type: int), _col2 (type: float) + | sort order:+++ + | Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE + | value expressions:_col3 (type: bigint) + | Group By Operator [GBY_5] + | aggregations:["sum(_col2)"] + | keys:_col0 (type: string), _col2 (type: int), _col3 (type: float) + | outputColumnNames:["_col0","_col1","_col2","_col3"] + | Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE + | Select Operator [SEL_2] + | outputColumnNames:["_col0","_col2","_col3"] + | Statistics:Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE + | Filter Operator [FIL_46] + | predicate:(((((((c_int + 1) >= 0) and ((c_int > 0) or (c_float >= 0.0))) and (c_float > 0.0)) and ((c_int >= 1) or (c_float >= 1.0))) and ((UDFToFloat(c_int) + c_float) >= 0.0)) and key is not null) (type: boolean) + | Statistics:Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE + | TableScan [TS_0] + | alias:cbo_t1 + | Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE + |<-Reducer 7 [SIMPLE_EDGE] + Reduce Output Operator [RS_23] + key expressions:_col0 (type: string) + Map-reduce partition columns:_col0 (type: string) + sort order:+ Statistics:Num rows: 1 Data size: 89 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator [GBY_18] - | keys:KEY._col0 (type: float), KEY._col1 (type: int), KEY._col2 (type: string) - | outputColumnNames:["_col0","_col1","_col2"] - | Statistics:Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE - |<-Map 6 [SIMPLE_EDGE] - Reduce Output Operator [RS_17] - key expressions:_col0 (type: float), _col1 (type: int), _col2 (type: string) - Map-reduce partition columns:_col0 (type: float), _col1 (type: int), _col2 (type: string) - sort order:+++ - Statistics:Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator [GBY_16] - keys:_col0 (type: float), _col1 (type: int), _col2 (type: string) - outputColumnNames:["_col0","_col1","_col2"] + value expressions:_col1 (type: int) + Select Operator [SEL_18] + outputColumnNames:["_col0","_col1"] + Statistics:Num rows: 1 Data size: 89 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator [GBY_17] + | keys:KEY._col0 (type: string), KEY._col1 (type: int), KEY._col2 (type: float) + | outputColumnNames:["_col0","_col1","_col2"] + | Statistics:Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 6 [SIMPLE_EDGE] + Reduce Output Operator [RS_16] + key expressions:_col0 (type: string), _col1 (type: int), _col2 (type: float) + Map-reduce partition columns:_col0 (type: string), _col1 (type: int), _col2 (type: float) + sort order:+++ Statistics:Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator [SEL_12] + Group By Operator [GBY_15] + keys:_col0 (type: string), _col2 (type: int), _col3 (type: float) outputColumnNames:["_col0","_col1","_col2"] Statistics:Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator [FIL_48] - predicate:(((((((c_int + 1) >= 0) and ((c_int > 0) or (c_float >= 0.0))) and (c_float > 0.0)) and ((c_int >= 1) or (c_float >= 1.0))) and ((UDFToFloat(c_int) + c_float) >= 0.0)) and key is not null) (type: boolean) + Select Operator [SEL_12] + outputColumnNames:["_col0","_col2","_col3"] Statistics:Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE - TableScan [TS_10] - alias:cbo_t2 - Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator [FIL_47] + predicate:(((((((c_int + 1) >= 0) and ((c_int > 0) or (c_float >= 0.0))) and (c_float > 0.0)) and ((c_int >= 1) or (c_float >= 1.0))) and ((UDFToFloat(c_int) + c_float) >= 0.0)) and key is not null) (type: boolean) + Statistics:Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE + TableScan [TS_10] + alias:cbo_t2 + Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE PREHOOK: query: explain select unionsrc.key FROM (select 'tst1' as key, count(1) as value from src) unionsrc PREHOOK: type: QUERY @@ -1324,27 +1333,28 @@ Stage-0 limit:-1 Stage-1 Reducer 2 - File Output Operator [FS_8] + File Output Operator [FS_7] compressed:false Statistics:Num rows: 1 Data size: 88 Basic stats: COMPLETE Column stats: COMPLETE table:{"input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat","serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe"} - Select Operator [SEL_6] + Select Operator [SEL_5] outputColumnNames:["_col0"] Statistics:Num rows: 1 Data size: 88 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator [GBY_5] + Group By Operator [GBY_4] | aggregations:["count(VALUE._col0)"] | outputColumnNames:["_col0"] | Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE |<-Map 1 [SIMPLE_EDGE] - Reduce Output Operator [RS_4] + Reduce Output Operator [RS_3] sort order: Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions:_col0 (type: bigint) - Group By Operator [GBY_3] - aggregations:["count(1)"] + Group By Operator [GBY_2] + aggregations:["count(key)"] outputColumnNames:["_col0"] Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Select Operator [SEL_1] + outputColumnNames:["key"] Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE TableScan [TS_0] alias:src @@ -1375,93 +1385,93 @@ Stage-0 limit:-1 Stage-1 Reducer 4 - File Output Operator [FS_29] + File Output Operator [FS_26] compressed:false Statistics:Num rows: 3 Data size: 261 Basic stats: COMPLETE Column stats: COMPLETE table:{"input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat","serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe"} - Select Operator [SEL_28] + Select Operator [SEL_25] | outputColumnNames:["_col0"] | Statistics:Num rows: 3 Data size: 261 Basic stats: COMPLETE Column stats: COMPLETE |<-Union 3 [SIMPLE_EDGE] |<-Reducer 2 [CONTAINS] - | Reduce Output Operator [RS_27] + | Reduce Output Operator [RS_24] | key expressions:_col0 (type: string) | sort order:+ | Statistics:Num rows: 3 Data size: 261 Basic stats: COMPLETE Column stats: COMPLETE - | Select Operator [SEL_6] + | Select Operator [SEL_5] | outputColumnNames:["_col0"] | Statistics:Num rows: 1 Data size: 87 Basic stats: COMPLETE Column stats: COMPLETE - | Group By Operator [GBY_5] + | Group By Operator [GBY_4] | | aggregations:["count(VALUE._col0)"] | | outputColumnNames:["_col0"] | | Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE | |<-Map 1 [SIMPLE_EDGE] - | Reduce Output Operator [RS_4] + | Reduce Output Operator [RS_3] | sort order: | Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE | value expressions:_col0 (type: bigint) - | Group By Operator [GBY_3] - | aggregations:["count(_col0)"] + | Group By Operator [GBY_2] + | aggregations:["count(key)"] | outputColumnNames:["_col0"] | Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE | Select Operator [SEL_1] - | outputColumnNames:["_col0"] + | outputColumnNames:["key"] | Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE | TableScan [TS_0] | alias:s1 | Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE |<-Reducer 6 [CONTAINS] - | Reduce Output Operator [RS_27] + | Reduce Output Operator [RS_24] | key expressions:_col0 (type: string) | sort order:+ | Statistics:Num rows: 3 Data size: 261 Basic stats: COMPLETE Column stats: COMPLETE - | Select Operator [SEL_14] + | Select Operator [SEL_12] | outputColumnNames:["_col0"] | Statistics:Num rows: 1 Data size: 87 Basic stats: COMPLETE Column stats: COMPLETE - | Group By Operator [GBY_13] + | Group By Operator [GBY_11] | | aggregations:["count(VALUE._col0)"] | | outputColumnNames:["_col0"] | | Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE | |<-Map 5 [SIMPLE_EDGE] - | Reduce Output Operator [RS_12] + | Reduce Output Operator [RS_10] | sort order: | Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE | value expressions:_col0 (type: bigint) - | Group By Operator [GBY_11] - | aggregations:["count(_col0)"] + | Group By Operator [GBY_9] + | aggregations:["count(key)"] | outputColumnNames:["_col0"] | Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - | Select Operator [SEL_9] - | outputColumnNames:["_col0"] + | Select Operator [SEL_8] + | outputColumnNames:["key"] | Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE - | TableScan [TS_8] + | TableScan [TS_7] | alias:s1 | Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE |<-Reducer 8 [CONTAINS] - Reduce Output Operator [RS_27] + Reduce Output Operator [RS_24] key expressions:_col0 (type: string) sort order:+ Statistics:Num rows: 3 Data size: 261 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator [SEL_24] + Select Operator [SEL_21] outputColumnNames:["_col0"] Statistics:Num rows: 1 Data size: 87 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator [GBY_23] + Group By Operator [GBY_20] | aggregations:["count(VALUE._col0)"] | outputColumnNames:["_col0"] | Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE |<-Map 7 [SIMPLE_EDGE] - Reduce Output Operator [RS_22] + Reduce Output Operator [RS_19] sort order: Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions:_col0 (type: bigint) - Group By Operator [GBY_21] - aggregations:["count(_col0)"] + Group By Operator [GBY_18] + aggregations:["count(key)"] outputColumnNames:["_col0"] Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator [SEL_19] - outputColumnNames:["_col0"] + Select Operator [SEL_17] + outputColumnNames:["key"] Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE - TableScan [TS_18] + TableScan [TS_16] alias:s1 Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE @@ -1491,125 +1501,125 @@ Stage-0 limit:-1 Stage-1 Reducer 5 - File Output Operator [FS_34] + File Output Operator [FS_31] compressed:false Statistics:Num rows: 1 Data size: 95 Basic stats: COMPLETE Column stats: COMPLETE table:{"input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat","serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe"} - Select Operator [SEL_33] + Select Operator [SEL_30] | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 1 Data size: 95 Basic stats: COMPLETE Column stats: COMPLETE |<-Reducer 4 [SIMPLE_EDGE] - Reduce Output Operator [RS_32] + Reduce Output Operator [RS_29] key expressions:_col0 (type: string) sort order:+ Statistics:Num rows: 1 Data size: 95 Basic stats: COMPLETE Column stats: COMPLETE value expressions:_col1 (type: bigint) - Group By Operator [GBY_30] + Group By Operator [GBY_27] | aggregations:["count(VALUE._col0)"] | keys:KEY._col0 (type: string) | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 1 Data size: 95 Basic stats: COMPLETE Column stats: COMPLETE |<-Union 3 [SIMPLE_EDGE] |<-Reducer 2 [CONTAINS] - | Reduce Output Operator [RS_29] + | Reduce Output Operator [RS_26] | key expressions:_col0 (type: string) | Map-reduce partition columns:_col0 (type: string) | sort order:+ | Statistics:Num rows: 1 Data size: 95 Basic stats: COMPLETE Column stats: COMPLETE | value expressions:_col1 (type: bigint) - | Group By Operator [GBY_28] + | Group By Operator [GBY_25] | aggregations:["count(1)"] | keys:_col0 (type: string) | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 1 Data size: 95 Basic stats: COMPLETE Column stats: COMPLETE - | Select Operator [SEL_6] + | Select Operator [SEL_5] | outputColumnNames:["_col0"] | Statistics:Num rows: 1 Data size: 87 Basic stats: COMPLETE Column stats: COMPLETE - | Group By Operator [GBY_5] + | Group By Operator [GBY_4] | | aggregations:["count(VALUE._col0)"] | | outputColumnNames:["_col0"] | | Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE | |<-Map 1 [SIMPLE_EDGE] - | Reduce Output Operator [RS_4] + | Reduce Output Operator [RS_3] | sort order: | Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE | value expressions:_col0 (type: bigint) - | Group By Operator [GBY_3] - | aggregations:["count(_col0)"] + | Group By Operator [GBY_2] + | aggregations:["count(key)"] | outputColumnNames:["_col0"] | Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE | Select Operator [SEL_1] - | outputColumnNames:["_col0"] + | outputColumnNames:["key"] | Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE | TableScan [TS_0] | alias:s1 | Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE |<-Reducer 7 [CONTAINS] - | Reduce Output Operator [RS_29] + | Reduce Output Operator [RS_26] | key expressions:_col0 (type: string) | Map-reduce partition columns:_col0 (type: string) | sort order:+ | Statistics:Num rows: 1 Data size: 95 Basic stats: COMPLETE Column stats: COMPLETE | value expressions:_col1 (type: bigint) - | Group By Operator [GBY_28] + | Group By Operator [GBY_25] | aggregations:["count(1)"] | keys:_col0 (type: string) | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 1 Data size: 95 Basic stats: COMPLETE Column stats: COMPLETE - | Select Operator [SEL_14] + | Select Operator [SEL_12] | outputColumnNames:["_col0"] | Statistics:Num rows: 1 Data size: 87 Basic stats: COMPLETE Column stats: COMPLETE - | Group By Operator [GBY_13] + | Group By Operator [GBY_11] | | aggregations:["count(VALUE._col0)"] | | outputColumnNames:["_col0"] | | Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE | |<-Map 6 [SIMPLE_EDGE] - | Reduce Output Operator [RS_12] + | Reduce Output Operator [RS_10] | sort order: | Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE | value expressions:_col0 (type: bigint) - | Group By Operator [GBY_11] - | aggregations:["count(_col0)"] + | Group By Operator [GBY_9] + | aggregations:["count(key)"] | outputColumnNames:["_col0"] | Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - | Select Operator [SEL_9] - | outputColumnNames:["_col0"] + | Select Operator [SEL_8] + | outputColumnNames:["key"] | Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE - | TableScan [TS_8] + | TableScan [TS_7] | alias:s1 | Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE |<-Reducer 9 [CONTAINS] - Reduce Output Operator [RS_29] + Reduce Output Operator [RS_26] key expressions:_col0 (type: string) Map-reduce partition columns:_col0 (type: string) sort order:+ Statistics:Num rows: 1 Data size: 95 Basic stats: COMPLETE Column stats: COMPLETE value expressions:_col1 (type: bigint) - Group By Operator [GBY_28] + Group By Operator [GBY_25] aggregations:["count(1)"] keys:_col0 (type: string) outputColumnNames:["_col0","_col1"] Statistics:Num rows: 1 Data size: 95 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator [SEL_24] + Select Operator [SEL_21] outputColumnNames:["_col0"] Statistics:Num rows: 1 Data size: 87 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator [GBY_23] + Group By Operator [GBY_20] | aggregations:["count(VALUE._col0)"] | outputColumnNames:["_col0"] | Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE |<-Map 8 [SIMPLE_EDGE] - Reduce Output Operator [RS_22] + Reduce Output Operator [RS_19] sort order: Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions:_col0 (type: bigint) - Group By Operator [GBY_21] - aggregations:["count(_col0)"] + Group By Operator [GBY_18] + aggregations:["count(key)"] outputColumnNames:["_col0"] Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator [SEL_19] - outputColumnNames:["_col0"] + Select Operator [SEL_17] + outputColumnNames:["key"] Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE - TableScan [TS_18] + TableScan [TS_16] alias:s1 Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE @@ -2122,28 +2132,28 @@ Stage-0 sort order:+ Statistics:Num rows: 10 Data size: 885 Basic stats: COMPLETE Column stats: COMPLETE value expressions:_col0 (type: string), _col2 (type: bigint) - Select Operator [SEL_6] + Select Operator [SEL_5] outputColumnNames:["_col0","_col1","_col2"] Statistics:Num rows: 10 Data size: 885 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator [GBY_5] + Group By Operator [GBY_4] | aggregations:["sum(VALUE._col0)"] - | keys:KEY._col0 (type: float), KEY._col1 (type: int), KEY._col2 (type: string) + | keys:KEY._col0 (type: string), KEY._col1 (type: int), KEY._col2 (type: float) | outputColumnNames:["_col0","_col1","_col2","_col3"] | Statistics:Num rows: 10 Data size: 917 Basic stats: COMPLETE Column stats: COMPLETE |<-Map 1 [SIMPLE_EDGE] - Reduce Output Operator [RS_4] - key expressions:_col0 (type: float), _col1 (type: int), _col2 (type: string) - Map-reduce partition columns:_col0 (type: float), _col1 (type: int), _col2 (type: string) + Reduce Output Operator [RS_3] + key expressions:_col0 (type: string), _col1 (type: int), _col2 (type: float) + Map-reduce partition columns:_col0 (type: string), _col1 (type: int), _col2 (type: float) sort order:+++ Statistics:Num rows: 10 Data size: 917 Basic stats: COMPLETE Column stats: COMPLETE value expressions:_col3 (type: bigint) - Group By Operator [GBY_3] - aggregations:["sum(_col1)"] - keys:_col0 (type: float), _col1 (type: int), _col2 (type: string) + Group By Operator [GBY_2] + aggregations:["sum(c_int)"] + keys:key (type: string), c_int (type: int), c_float (type: float) outputColumnNames:["_col0","_col1","_col2","_col3"] Statistics:Num rows: 10 Data size: 917 Basic stats: COMPLETE Column stats: COMPLETE Select Operator [SEL_1] - outputColumnNames:["_col0","_col1","_col2"] + outputColumnNames:["key","c_int","c_float"] Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE TableScan [TS_0] alias:cbo_t1 @@ -2201,28 +2211,28 @@ Stage-0 keys:_col0 (type: bigint), _col1 (type: float) outputColumnNames:["_col0","_col1","_col2"] Statistics:Num rows: 5 Data size: 100 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator [SEL_6] + Select Operator [SEL_5] outputColumnNames:["_col0","_col1"] Statistics:Num rows: 10 Data size: 917 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator [GBY_5] + Group By Operator [GBY_4] | aggregations:["sum(VALUE._col0)"] - | keys:KEY._col0 (type: float), KEY._col1 (type: int), KEY._col2 (type: string) + | keys:KEY._col0 (type: string), KEY._col1 (type: int), KEY._col2 (type: float) | outputColumnNames:["_col0","_col1","_col2","_col3"] | Statistics:Num rows: 10 Data size: 917 Basic stats: COMPLETE Column stats: COMPLETE |<-Map 1 [SIMPLE_EDGE] - Reduce Output Operator [RS_4] - key expressions:_col0 (type: float), _col1 (type: int), _col2 (type: string) - Map-reduce partition columns:_col0 (type: float), _col1 (type: int), _col2 (type: string) + Reduce Output Operator [RS_3] + key expressions:_col0 (type: string), _col1 (type: int), _col2 (type: float) + Map-reduce partition columns:_col0 (type: string), _col1 (type: int), _col2 (type: float) sort order:+++ Statistics:Num rows: 10 Data size: 917 Basic stats: COMPLETE Column stats: COMPLETE value expressions:_col3 (type: bigint) - Group By Operator [GBY_3] - aggregations:["sum(_col1)"] - keys:_col0 (type: float), _col1 (type: int), _col2 (type: string) + Group By Operator [GBY_2] + aggregations:["sum(c_int)"] + keys:key (type: string), c_int (type: int), c_float (type: float) outputColumnNames:["_col0","_col1","_col2","_col3"] Statistics:Num rows: 10 Data size: 917 Basic stats: COMPLETE Column stats: COMPLETE Select Operator [SEL_1] - outputColumnNames:["_col0","_col1","_col2"] + outputColumnNames:["key","c_int","c_float"] Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE TableScan [TS_0] alias:cbo_t1 @@ -2385,164 +2395,161 @@ Stage-0 sort order:-+ Statistics:Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE value expressions:_col0 (type: int), _col2 (type: bigint) - Group By Operator [GBY_43] - | aggregations:["count(VALUE._col0)"] - | keys:KEY._col0 (type: int), KEY._col1 (type: bigint) - | outputColumnNames:["_col0","_col1","_col2"] - | Statistics:Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE - |<-Reducer 5 [SIMPLE_EDGE] - Reduce Output Operator [RS_42] - key expressions:_col0 (type: int), _col1 (type: bigint) - Map-reduce partition columns:_col0 (type: int), _col1 (type: bigint) - sort order:++ - Statistics:Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE - value expressions:_col2 (type: bigint) - Group By Operator [GBY_41] - aggregations:["count()"] - keys:_col0 (type: int), _col1 (type: bigint) - outputColumnNames:["_col0","_col1","_col2"] + Select Operator [SEL_43] + outputColumnNames:["_col0","_col1","_col2"] + Statistics:Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator [GBY_42] + | aggregations:["count(VALUE._col0)"] + | keys:KEY._col0 (type: bigint), KEY._col1 (type: int) + | outputColumnNames:["_col0","_col1","_col2"] + | Statistics:Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE + |<-Reducer 5 [SIMPLE_EDGE] + Reduce Output Operator [RS_41] + key expressions:_col0 (type: bigint), _col1 (type: int) + Map-reduce partition columns:_col0 (type: bigint), _col1 (type: int) + sort order:++ Statistics:Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator [SEL_39] - outputColumnNames:["_col0","_col1"] - Statistics:Num rows: 2 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator [FIL_38] - predicate:((_col1 > 0) or (_col6 >= 0)) (type: boolean) + value expressions:_col2 (type: bigint) + Group By Operator [GBY_40] + aggregations:["count()"] + keys:_col2 (type: bigint), _col6 (type: int) + outputColumnNames:["_col0","_col1","_col2"] + Statistics:Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator [SEL_39] + outputColumnNames:["_col2","_col6"] Statistics:Num rows: 2 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE - Merge Join Operator [MERGEJOIN_60] - | condition map:[{"":"Inner Join 0 to 1"}] - | keys:{"0":"_col0 (type: string)","1":"_col0 (type: string)"} - | outputColumnNames:["_col1","_col2","_col6"] - | Statistics:Num rows: 3 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE - |<-Map 11 [SIMPLE_EDGE] - | Reduce Output Operator [RS_36] - | key expressions:_col0 (type: string) - | Map-reduce partition columns:_col0 (type: string) - | sort order:+ - | Statistics:Num rows: 18 Data size: 1424 Basic stats: COMPLETE Column stats: COMPLETE - | value expressions:_col1 (type: int) - | Select Operator [SEL_32] - | outputColumnNames:["_col0","_col1"] - | Statistics:Num rows: 18 Data size: 1424 Basic stats: COMPLETE Column stats: COMPLETE - | Filter Operator [FIL_58] - | predicate:key is not null (type: boolean) - | Statistics:Num rows: 18 Data size: 1424 Basic stats: COMPLETE Column stats: COMPLETE - | TableScan [TS_31] - | alias:cbo_t3 - | Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE - |<-Reducer 4 [SIMPLE_EDGE] - Reduce Output Operator [RS_34] - key expressions:_col0 (type: string) - Map-reduce partition columns:_col0 (type: string) - sort order:+ - Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE - value expressions:_col1 (type: int), _col2 (type: bigint) - Select Operator [SEL_30] - outputColumnNames:["_col0","_col1","_col2"] + Filter Operator [FIL_38] + predicate:((_col1 > 0) or (_col6 >= 0)) (type: boolean) + Statistics:Num rows: 2 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE + Merge Join Operator [MERGEJOIN_60] + | condition map:[{"":"Inner Join 0 to 1"}] + | keys:{"0":"_col0 (type: string)","1":"_col0 (type: string)"} + | outputColumnNames:["_col1","_col2","_col6"] + | Statistics:Num rows: 3 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 11 [SIMPLE_EDGE] + | Reduce Output Operator [RS_36] + | key expressions:_col0 (type: string) + | Map-reduce partition columns:_col0 (type: string) + | sort order:+ + | Statistics:Num rows: 18 Data size: 1424 Basic stats: COMPLETE Column stats: COMPLETE + | value expressions:_col1 (type: int) + | Select Operator [SEL_32] + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 18 Data size: 1424 Basic stats: COMPLETE Column stats: COMPLETE + | Filter Operator [FIL_58] + | predicate:key is not null (type: boolean) + | Statistics:Num rows: 18 Data size: 1424 Basic stats: COMPLETE Column stats: COMPLETE + | TableScan [TS_31] + | alias:cbo_t3 + | Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE + |<-Reducer 4 [SIMPLE_EDGE] + Reduce Output Operator [RS_34] + key expressions:_col0 (type: string) + Map-reduce partition columns:_col0 (type: string) + sort order:+ Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator [FIL_29] - predicate:((_col1 + _col4) >= 0) (type: boolean) + value expressions:_col1 (type: int), _col2 (type: bigint) + Select Operator [SEL_30] + outputColumnNames:["_col0","_col1","_col2"] Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE - Merge Join Operator [MERGEJOIN_59] - | condition map:[{"":"Inner Join 0 to 1"}] - | keys:{"0":"_col0 (type: string)","1":"_col0 (type: string)"} - | outputColumnNames:["_col0","_col1","_col2","_col4"] - | Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE - |<-Reducer 10 [SIMPLE_EDGE] - | Reduce Output Operator [RS_27] - | key expressions:_col0 (type: string) - | Map-reduce partition columns:_col0 (type: string) - | sort order:+ - | Statistics:Num rows: 1 Data size: 105 Basic stats: COMPLETE Column stats: COMPLETE - | value expressions:_col1 (type: int) - | Filter Operator [FIL_56] - | predicate:_col0 is not null (type: boolean) - | Statistics:Num rows: 1 Data size: 105 Basic stats: COMPLETE Column stats: COMPLETE - | Limit [LIM_22] - | Number of rows:5 - | Statistics:Num rows: 1 Data size: 105 Basic stats: COMPLETE Column stats: COMPLETE - | Select Operator [SEL_21] - | | outputColumnNames:["_col0","_col1"] - | | Statistics:Num rows: 1 Data size: 105 Basic stats: COMPLETE Column stats: COMPLETE - | |<-Reducer 9 [SIMPLE_EDGE] - | Reduce Output Operator [RS_20] - | key expressions:_col3 (type: double), _col2 (type: bigint) - | sort order:-+ - | Statistics:Num rows: 1 Data size: 105 Basic stats: COMPLETE Column stats: COMPLETE - | value expressions:_col0 (type: string), _col1 (type: int) - | Select Operator [SEL_19] - | outputColumnNames:["_col0","_col1","_col2","_col3"] - | Statistics:Num rows: 1 Data size: 105 Basic stats: COMPLETE Column stats: COMPLETE - | Group By Operator [GBY_18] - | | aggregations:["sum(VALUE._col0)"] - | | keys:KEY._col0 (type: float), KEY._col1 (type: int), KEY._col2 (type: string) - | | outputColumnNames:["_col0","_col1","_col2","_col3"] - | | Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE - | |<-Map 8 [SIMPLE_EDGE] - | Reduce Output Operator [RS_17] - | key expressions:_col0 (type: float), _col1 (type: int), _col2 (type: string) - | Map-reduce partition columns:_col0 (type: float), _col1 (type: int), _col2 (type: string) - | sort order:+++ - | Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE - | value expressions:_col3 (type: bigint) - | Group By Operator [GBY_16] - | aggregations:["sum(_col1)"] - | keys:_col0 (type: float), _col1 (type: int), _col2 (type: string) - | outputColumnNames:["_col0","_col1","_col2","_col3"] - | Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE - | Select Operator [SEL_14] - | outputColumnNames:["_col0","_col1","_col2"] - | Statistics:Num rows: 4 Data size: 372 Basic stats: COMPLETE Column stats: COMPLETE - | Filter Operator [FIL_57] - | predicate:(((c_int + 1) >= 0) and ((c_int > 0) or (c_float >= 0.0))) (type: boolean) - | Statistics:Num rows: 4 Data size: 372 Basic stats: COMPLETE Column stats: COMPLETE - | TableScan [TS_12] - | alias:cbo_t2 - | Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE - |<-Reducer 3 [SIMPLE_EDGE] - Reduce Output Operator [RS_25] - key expressions:_col0 (type: string) - Map-reduce partition columns:_col0 (type: string) - sort order:+ - Statistics:Num rows: 1 Data size: 97 Basic stats: COMPLETE Column stats: COMPLETE - value expressions:_col1 (type: int), _col2 (type: bigint) - Filter Operator [FIL_54] - predicate:_col0 is not null (type: boolean) + Filter Operator [FIL_29] + predicate:((_col1 + _col4) >= 0) (type: boolean) + Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE + Merge Join Operator [MERGEJOIN_59] + | condition map:[{"":"Inner Join 0 to 1"}] + | keys:{"0":"_col0 (type: string)","1":"_col0 (type: string)"} + | outputColumnNames:["_col0","_col1","_col2","_col4"] + | Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE + |<-Reducer 10 [SIMPLE_EDGE] + | Reduce Output Operator [RS_27] + | key expressions:_col0 (type: string) + | Map-reduce partition columns:_col0 (type: string) + | sort order:+ + | Statistics:Num rows: 1 Data size: 105 Basic stats: COMPLETE Column stats: COMPLETE + | value expressions:_col1 (type: int) + | Filter Operator [FIL_56] + | predicate:_col0 is not null (type: boolean) + | Statistics:Num rows: 1 Data size: 105 Basic stats: COMPLETE Column stats: COMPLETE + | Limit [LIM_22] + | Number of rows:5 + | Statistics:Num rows: 1 Data size: 105 Basic stats: COMPLETE Column stats: COMPLETE + | Select Operator [SEL_21] + | | outputColumnNames:["_col0","_col1"] + | | Statistics:Num rows: 1 Data size: 105 Basic stats: COMPLETE Column stats: COMPLETE + | |<-Reducer 9 [SIMPLE_EDGE] + | Reduce Output Operator [RS_20] + | key expressions:_col3 (type: double), _col2 (type: bigint) + | sort order:-+ + | Statistics:Num rows: 1 Data size: 105 Basic stats: COMPLETE Column stats: COMPLETE + | value expressions:_col0 (type: string), _col1 (type: int) + | Select Operator [SEL_18] + | outputColumnNames:["_col0","_col1","_col2","_col3"] + | Statistics:Num rows: 1 Data size: 105 Basic stats: COMPLETE Column stats: COMPLETE + | Group By Operator [GBY_17] + | | aggregations:["sum(VALUE._col0)"] + | | keys:KEY._col0 (type: string), KEY._col1 (type: int), KEY._col2 (type: float) + | | outputColumnNames:["_col0","_col1","_col2","_col3"] + | | Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE + | |<-Map 8 [SIMPLE_EDGE] + | Reduce Output Operator [RS_16] + | key expressions:_col0 (type: string), _col1 (type: int), _col2 (type: float) + | Map-reduce partition columns:_col0 (type: string), _col1 (type: int), _col2 (type: float) + | sort order:+++ + | Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE + | value expressions:_col3 (type: bigint) + | Group By Operator [GBY_15] + | aggregations:["sum(c_int)"] + | keys:key (type: string), c_int (type: int), c_float (type: float) + | outputColumnNames:["_col0","_col1","_col2","_col3"] + | Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE + | Filter Operator [FIL_57] + | predicate:(((c_int + 1) >= 0) and ((c_int > 0) or (c_float >= 0.0))) (type: boolean) + | Statistics:Num rows: 4 Data size: 372 Basic stats: COMPLETE Column stats: COMPLETE + | TableScan [TS_12] + | alias:cbo_t2 + | Statistics:Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: COMPLETE + |<-Reducer 3 [SIMPLE_EDGE] + Reduce Output Operator [RS_25] + key expressions:_col0 (type: string) + Map-reduce partition columns:_col0 (type: string) + sort order:+ Statistics:Num rows: 1 Data size: 97 Basic stats: COMPLETE Column stats: COMPLETE - Limit [LIM_10] - Number of rows:5 + value expressions:_col1 (type: int), _col2 (type: bigint) + Filter Operator [FIL_54] + predicate:_col0 is not null (type: boolean) Statistics:Num rows: 1 Data size: 97 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator [SEL_9] - | outputColumnNames:["_col0","_col1","_col2"] - | Statistics:Num rows: 1 Data size: 97 Basic stats: COMPLETE Column stats: COMPLETE - |<-Reducer 2 [SIMPLE_EDGE] - Reduce Output Operator [RS_8] - key expressions:_col0 (type: string) - sort order:+ - Statistics:Num rows: 1 Data size: 97 Basic stats: COMPLETE Column stats: COMPLETE - value expressions:_col1 (type: int), _col2 (type: bigint) - Select Operator [SEL_7] - outputColumnNames:["_col0","_col1","_col2"] + Limit [LIM_10] + Number of rows:5 + Statistics:Num rows: 1 Data size: 97 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator [SEL_9] + | outputColumnNames:["_col0","_col1","_col2"] + | Statistics:Num rows: 1 Data size: 97 Basic stats: COMPLETE Column stats: COMPLETE + |<-Reducer 2 [SIMPLE_EDGE] + Reduce Output Operator [RS_8] + key expressions:_col0 (type: string) + sort order:+ Statistics:Num rows: 1 Data size: 97 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator [GBY_6] - | aggregations:["sum(VALUE._col0)"] - | keys:KEY._col0 (type: float), KEY._col1 (type: int), KEY._col2 (type: string) - | outputColumnNames:["_col0","_col1","_col2","_col3"] - | Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE - |<-Map 1 [SIMPLE_EDGE] - Reduce Output Operator [RS_5] - key expressions:_col0 (type: float), _col1 (type: int), _col2 (type: string) - Map-reduce partition columns:_col0 (type: float), _col1 (type: int), _col2 (type: string) - sort order:+++ - Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE - value expressions:_col3 (type: bigint) - Group By Operator [GBY_4] - aggregations:["sum(_col1)"] - keys:_col0 (type: float), _col1 (type: int), _col2 (type: string) - outputColumnNames:["_col0","_col1","_col2","_col3"] + value expressions:_col1 (type: int), _col2 (type: bigint) + Select Operator [SEL_6] + outputColumnNames:["_col0","_col1","_col2"] + Statistics:Num rows: 1 Data size: 97 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator [GBY_5] + | aggregations:["sum(VALUE._col0)"] + | keys:KEY._col0 (type: string), KEY._col1 (type: int), KEY._col2 (type: float) + | outputColumnNames:["_col0","_col1","_col2","_col3"] + | Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE + |<-Map 1 [SIMPLE_EDGE] + Reduce Output Operator [RS_4] + key expressions:_col0 (type: string), _col1 (type: int), _col2 (type: float) + Map-reduce partition columns:_col0 (type: string), _col1 (type: int), _col2 (type: float) + sort order:+++ Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator [SEL_2] - outputColumnNames:["_col0","_col1","_col2"] - Statistics:Num rows: 4 Data size: 372 Basic stats: COMPLETE Column stats: COMPLETE + value expressions:_col3 (type: bigint) + Group By Operator [GBY_3] + aggregations:["sum(c_int)"] + keys:key (type: string), c_int (type: int), c_float (type: float) + outputColumnNames:["_col0","_col1","_col2","_col3"] + Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator [FIL_55] predicate:(((c_int + 1) >= 0) and ((c_int > 0) or (c_float >= 0.0))) (type: boolean) Statistics:Num rows: 4 Data size: 372 Basic stats: COMPLETE Column stats: COMPLETE @@ -2786,34 +2793,34 @@ Stage-0 | Filter Operator [FIL_60] | predicate:(((_col1 + 1) >= 0) and ((_col1 > 0) or (UDFToDouble(_col0) >= 0.0))) (type: boolean) | Statistics:Num rows: 1 Data size: 105 Basic stats: COMPLETE Column stats: COMPLETE - | Select Operator [SEL_9] + | Select Operator [SEL_8] | outputColumnNames:["_col0","_col1","_col2","_col3"] | Statistics:Num rows: 1 Data size: 105 Basic stats: COMPLETE Column stats: COMPLETE | Filter Operator [FIL_61] - | predicate:(((UDFToDouble(_col2) + UDFToDouble(_col3)) >= 0.0) and ((UDFToDouble(_col2) >= 1.0) or (_col3 >= 1))) (type: boolean) + | predicate:(((UDFToDouble(_col0) + UDFToDouble(_col3)) >= 0.0) and ((UDFToDouble(_col0) >= 1.0) or (_col3 >= 1))) (type: boolean) | Statistics:Num rows: 1 Data size: 97 Basic stats: COMPLETE Column stats: COMPLETE | Select Operator [SEL_65] - | outputColumnNames:["_col1","_col2","_col3"] + | outputColumnNames:["_col0","_col1","_col3"] | Statistics:Num rows: 1 Data size: 97 Basic stats: COMPLETE Column stats: COMPLETE - | Group By Operator [GBY_8] + | Group By Operator [GBY_7] | | aggregations:["sum(VALUE._col0)"] - | | keys:KEY._col0 (type: float), KEY._col1 (type: int), KEY._col2 (type: string) + | | keys:KEY._col0 (type: string), KEY._col1 (type: int), KEY._col2 (type: float) | | outputColumnNames:["_col0","_col1","_col2","_col3"] | | Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE | |<-Map 1 [SIMPLE_EDGE] - | Reduce Output Operator [RS_7] - | key expressions:_col0 (type: float), _col1 (type: int), _col2 (type: string) - | Map-reduce partition columns:_col0 (type: float), _col1 (type: int), _col2 (type: string) + | Reduce Output Operator [RS_6] + | key expressions:_col0 (type: string), _col1 (type: int), _col2 (type: float) + | Map-reduce partition columns:_col0 (type: string), _col1 (type: int), _col2 (type: float) | sort order:+++ | Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE | value expressions:_col3 (type: bigint) - | Group By Operator [GBY_6] - | aggregations:["sum(_col1)"] - | keys:_col0 (type: float), _col1 (type: int), _col2 (type: string) + | Group By Operator [GBY_5] + | aggregations:["sum(_col2)"] + | keys:_col0 (type: string), _col2 (type: int), _col3 (type: float) | outputColumnNames:["_col0","_col1","_col2","_col3"] | Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE | Select Operator [SEL_2] - | outputColumnNames:["_col0","_col1","_col2"] + | outputColumnNames:["_col0","_col2","_col3"] | Statistics:Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE | Filter Operator [FIL_62] | predicate:((((((((c_int + 1) >= 0) and ((c_int > 0) or (c_float >= 0.0))) and (c_float > 0.0)) and ((c_int >= 1) or (c_float >= 1.0))) and ((UDFToFloat(c_int) + c_float) >= 0.0)) and (UDFToDouble(key) > 0.0)) and key is not null) (type: boolean) @@ -2839,28 +2846,28 @@ Stage-0 key expressions:_col1 (type: double), _col0 (type: string) sort order:-+ Statistics:Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator [SEL_26] + Select Operator [SEL_25] outputColumnNames:["_col0","_col1"] Statistics:Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator [GBY_25] + Group By Operator [GBY_24] | aggregations:["sum(VALUE._col0)"] - | keys:KEY._col0 (type: float), KEY._col1 (type: int), KEY._col2 (type: string) + | keys:KEY._col0 (type: string), KEY._col1 (type: int), KEY._col2 (type: float) | outputColumnNames:["_col0","_col1","_col2","_col3"] | Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE |<-Map 7 [SIMPLE_EDGE] - Reduce Output Operator [RS_24] - key expressions:_col0 (type: float), _col1 (type: int), _col2 (type: string) - Map-reduce partition columns:_col0 (type: float), _col1 (type: int), _col2 (type: string) + Reduce Output Operator [RS_23] + key expressions:_col0 (type: string), _col1 (type: int), _col2 (type: float) + Map-reduce partition columns:_col0 (type: string), _col1 (type: int), _col2 (type: float) sort order:+++ Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE value expressions:_col3 (type: bigint) - Group By Operator [GBY_23] - aggregations:["sum(_col1)"] - keys:_col0 (type: float), _col1 (type: int), _col2 (type: string) + Group By Operator [GBY_22] + aggregations:["sum(_col2)"] + keys:_col0 (type: string), _col2 (type: int), _col3 (type: float) outputColumnNames:["_col0","_col1","_col2","_col3"] Statistics:Num rows: 1 Data size: 101 Basic stats: COMPLETE Column stats: COMPLETE Select Operator [SEL_19] - outputColumnNames:["_col0","_col1","_col2"] + outputColumnNames:["_col0","_col2","_col3"] Statistics:Num rows: 1 Data size: 93 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator [FIL_63] predicate:((((((((c_int + 1) >= 0) and ((c_int > 0) or (c_float >= 0.0))) and (c_float > 0.0)) and ((c_int >= 1) or (c_float >= 1.0))) and ((UDFToFloat(c_int) + c_float) >= 0.0)) and (UDFToDouble(key) > 0.0)) and key is not null) (type: boolean) @@ -2928,27 +2935,27 @@ Stage-0 limit:-1 Stage-1 Reducer 3 - File Output Operator [FS_16] + File Output Operator [FS_15] compressed:false Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table:{"input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat","serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe"} - Group By Operator [GBY_14] + Group By Operator [GBY_13] | aggregations:["count(VALUE._col0)"] | outputColumnNames:["_col0"] | Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE |<-Reducer 2 [SIMPLE_EDGE] - Reduce Output Operator [RS_13] + Reduce Output Operator [RS_12] sort order: Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions:_col0 (type: bigint) - Group By Operator [GBY_12] + Group By Operator [GBY_11] aggregations:["count(_col0)"] outputColumnNames:["_col0"] Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Select Operator [SEL_10] outputColumnNames:["_col0"] Statistics:Num rows: 200 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE - Merge Join Operator [MERGEJOIN_20] + Merge Join Operator [MERGEJOIN_19] | condition map:[{"":"Inner Join 0 to 1"}] | keys:{} | Statistics:Num rows: 200 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE @@ -2998,23 +3005,23 @@ Stage-0 limit:-1 Stage-1 Reducer 2 - File Output Operator [FS_16] + File Output Operator [FS_15] compressed:false Statistics:Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE table:{"input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat","serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe"} - Select Operator [SEL_15] + Select Operator [SEL_14] outputColumnNames:["_col0","_col1"] Statistics:Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator [FIL_18] + Filter Operator [FIL_17] predicate:_col3 is null (type: boolean) Statistics:Num rows: 1 Data size: 269 Basic stats: COMPLETE Column stats: COMPLETE - Merge Join Operator [MERGEJOIN_20] + Merge Join Operator [MERGEJOIN_19] | condition map:[{"":"Left Outer Join0 to 1"}] | keys:{"0":"_col1 (type: string)","1":"_col1 (type: string)"} | outputColumnNames:["_col0","_col1","_col3"] | Statistics:Num rows: 193 Data size: 51917 Basic stats: COMPLETE Column stats: COMPLETE |<-Map 1 [SIMPLE_EDGE] - | Reduce Output Operator [RS_11] + | Reduce Output Operator [RS_10] | key expressions:_col1 (type: string) | Map-reduce partition columns:_col1 (type: string) | sort order:+ @@ -3027,37 +3034,34 @@ Stage-0 | alias:b | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE |<-Reducer 4 [SIMPLE_EDGE] - Reduce Output Operator [RS_12] + Reduce Output Operator [RS_11] key expressions:_col1 (type: string) Map-reduce partition columns:_col1 (type: string) sort order:+ Statistics:Num rows: 83 Data size: 14774 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator [SEL_10] + Select Operator [SEL_9] outputColumnNames:["_col1"] Statistics:Num rows: 83 Data size: 14774 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator [GBY_9] + Group By Operator [GBY_8] | keys:KEY._col0 (type: string), KEY._col1 (type: string) | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 83 Data size: 14774 Basic stats: COMPLETE Column stats: COMPLETE |<-Map 3 [SIMPLE_EDGE] - Reduce Output Operator [RS_8] + Reduce Output Operator [RS_7] key expressions:_col0 (type: string), _col1 (type: string) Map-reduce partition columns:_col0 (type: string), _col1 (type: string) sort order:++ Statistics:Num rows: 83 Data size: 14774 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator [GBY_7] - keys:_col0 (type: string), _col1 (type: string) + Group By Operator [GBY_6] + keys:key (type: string), value (type: string) outputColumnNames:["_col0","_col1"] Statistics:Num rows: 83 Data size: 14774 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator [SEL_5] - outputColumnNames:["_col0","_col1"] + Filter Operator [FIL_18] + predicate:(value > 'val_2') (type: boolean) Statistics:Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator [FIL_19] - predicate:(value > 'val_2') (type: boolean) - Statistics:Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE - TableScan [TS_3] - alias:b - Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE + TableScan [TS_3] + alias:b + Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE PREHOOK: query: explain select * from src_cbo b @@ -3088,58 +3092,58 @@ Stage-0 limit:-1 Stage-1 Reducer 3 - File Output Operator [FS_16] + File Output Operator [FS_15] compressed:false Statistics:Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE table:{"input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat","serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe"} - Select Operator [SEL_15] + Select Operator [SEL_14] outputColumnNames:["_col0","_col1"] Statistics:Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator [FIL_18] + Filter Operator [FIL_17] predicate:_col3 is null (type: boolean) Statistics:Num rows: 1 Data size: 265 Basic stats: COMPLETE Column stats: COMPLETE - Merge Join Operator [MERGEJOIN_20] + Merge Join Operator [MERGEJOIN_19] | condition map:[{"":"Left Outer Join0 to 1"}] | keys:{"0":"_col1 (type: string), _col0 (type: string)","1":"_col0 (type: string), _col1 (type: string)"} | outputColumnNames:["_col0","_col1","_col3"] | Statistics:Num rows: 1 Data size: 265 Basic stats: COMPLETE Column stats: COMPLETE |<-Map 4 [SIMPLE_EDGE] - | Reduce Output Operator [RS_12] + | Reduce Output Operator [RS_11] | key expressions:_col0 (type: string), _col1 (type: string) | Map-reduce partition columns:_col0 (type: string), _col1 (type: string) | sort order:++ | Statistics:Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE - | Select Operator [SEL_10] + | Select Operator [SEL_9] | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE - | Filter Operator [FIL_19] + | Filter Operator [FIL_18] | predicate:(value > 'val_12') (type: boolean) | Statistics:Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE - | TableScan [TS_8] + | TableScan [TS_7] | alias:b | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE |<-Reducer 2 [SIMPLE_EDGE] - Reduce Output Operator [RS_11] + Reduce Output Operator [RS_10] key expressions:_col1 (type: string), _col0 (type: string) Map-reduce partition columns:_col1 (type: string), _col0 (type: string) sort order:++ Statistics:Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator [GBY_6] + Group By Operator [GBY_5] | keys:KEY._col0 (type: string), KEY._col1 (type: string) | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE |<-Map 1 [SIMPLE_EDGE] - Reduce Output Operator [RS_5] + Reduce Output Operator [RS_4] key expressions:_col0 (type: string), _col1 (type: string) Map-reduce partition columns:_col0 (type: string), _col1 (type: string) sort order:++ Statistics:Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator [GBY_4] - keys:_col0 (type: string), _col1 (type: string) + Group By Operator [GBY_3] + keys:key (type: string), value (type: string) outputColumnNames:["_col0","_col1"] Statistics:Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator [SEL_2] - outputColumnNames:["_col0","_col1"] + outputColumnNames:["key","value"] Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE TableScan [TS_0] alias:b @@ -3382,32 +3386,32 @@ Stage-0 limit:-1 Stage-1 Reducer 3 - File Output Operator [FS_28] + File Output Operator [FS_27] compressed:false Statistics:Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE table:{"input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat","serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe"} - Select Operator [SEL_27] + Select Operator [SEL_26] outputColumnNames:["_col0","_col1"] Statistics:Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE - Merge Join Operator [MERGEJOIN_38] + Merge Join Operator [MERGEJOIN_37] | condition map:[{"":"Inner Join 0 to 1"}] | keys:{"0":"_col1 (type: int)","1":"_col0 (type: int)"} | outputColumnNames:["_col1","_col2"] | Statistics:Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE |<-Reducer 2 [SIMPLE_EDGE] - | Reduce Output Operator [RS_23] + | Reduce Output Operator [RS_22] | key expressions:_col1 (type: int) | Map-reduce partition columns:_col1 (type: int) | sort order:+ | Statistics:Num rows: 12 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE | value expressions:_col2 (type: int) - | Merge Join Operator [MERGEJOIN_37] + | Merge Join Operator [MERGEJOIN_36] | | condition map:[{"":"Left Semi Join 0 to 1"}] | | keys:{"0":"_col0 (type: int)","1":"_col0 (type: int)"} | | outputColumnNames:["_col1","_col2"] | | Statistics:Num rows: 12 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE | |<-Map 1 [SIMPLE_EDGE] - | | Reduce Output Operator [RS_18] + | | Reduce Output Operator [RS_17] | | key expressions:_col0 (type: int) | | Map-reduce partition columns:_col0 (type: int) | | sort order:+ @@ -3416,60 +3420,57 @@ Stage-0 | | Select Operator [SEL_2] | | outputColumnNames:["_col0","_col1","_col2"] | | Statistics:Num rows: 16 Data size: 256 Basic stats: COMPLETE Column stats: COMPLETE - | | Filter Operator [FIL_34] + | | Filter Operator [FIL_33] | | predicate:(((l_linenumber = 1) and l_orderkey is not null) and l_partkey is not null) (type: boolean) | | Statistics:Num rows: 16 Data size: 256 Basic stats: COMPLETE Column stats: COMPLETE | | TableScan [TS_0] | | alias:lineitem | | Statistics:Num rows: 100 Data size: 11999 Basic stats: COMPLETE Column stats: COMPLETE | |<-Map 4 [SIMPLE_EDGE] - | Reduce Output Operator [RS_20] + | Reduce Output Operator [RS_19] | key expressions:_col0 (type: int) | Map-reduce partition columns:_col0 (type: int) | sort order:+ | Statistics:Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE - | Group By Operator [GBY_16] + | Group By Operator [GBY_15] | keys:_col0 (type: int) | outputColumnNames:["_col0"] | Statistics:Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE | Select Operator [SEL_5] | outputColumnNames:["_col0"] | Statistics:Num rows: 14 Data size: 56 Basic stats: COMPLETE Column stats: COMPLETE - | Filter Operator [FIL_35] + | Filter Operator [FIL_34] | predicate:(((l_shipmode = 'AIR') and (l_linenumber = 1)) and l_orderkey is not null) (type: boolean) | Statistics:Num rows: 14 Data size: 1344 Basic stats: COMPLETE Column stats: COMPLETE | TableScan [TS_3] | alias:lineitem | Statistics:Num rows: 100 Data size: 11999 Basic stats: COMPLETE Column stats: COMPLETE |<-Reducer 6 [SIMPLE_EDGE] - Reduce Output Operator [RS_25] + Reduce Output Operator [RS_24] key expressions:_col0 (type: int) Map-reduce partition columns:_col0 (type: int) sort order:+ Statistics:Num rows: 50 Data size: 200 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator [GBY_13] + Group By Operator [GBY_12] | keys:KEY._col0 (type: int) | outputColumnNames:["_col0"] | Statistics:Num rows: 50 Data size: 200 Basic stats: COMPLETE Column stats: COMPLETE |<-Map 5 [SIMPLE_EDGE] - Reduce Output Operator [RS_12] + Reduce Output Operator [RS_11] key expressions:_col0 (type: int) Map-reduce partition columns:_col0 (type: int) sort order:+ Statistics:Num rows: 50 Data size: 200 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator [GBY_11] - keys:_col0 (type: int) + Group By Operator [GBY_10] + keys:l_partkey (type: int) outputColumnNames:["_col0"] Statistics:Num rows: 50 Data size: 200 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator [SEL_9] - outputColumnNames:["_col0"] + Filter Operator [FIL_35] + predicate:l_partkey is not null (type: boolean) Statistics:Num rows: 100 Data size: 400 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator [FIL_36] - predicate:l_partkey is not null (type: boolean) - Statistics:Num rows: 100 Data size: 400 Basic stats: COMPLETE Column stats: COMPLETE - TableScan [TS_8] - alias:lineitem - Statistics:Num rows: 100 Data size: 11999 Basic stats: COMPLETE Column stats: COMPLETE + TableScan [TS_8] + alias:lineitem + Statistics:Num rows: 100 Data size: 11999 Basic stats: COMPLETE Column stats: COMPLETE PREHOOK: query: explain select key, value, count(*) from src_cbo b @@ -3496,23 +3497,23 @@ Stage-0 limit:-1 Stage-1 Reducer 4 - File Output Operator [FS_38] + File Output Operator [FS_37] compressed:false Statistics:Num rows: 34 Data size: 6324 Basic stats: COMPLETE Column stats: COMPLETE table:{"input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat","serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe"} - Merge Join Operator [MERGEJOIN_51] + Merge Join Operator [MERGEJOIN_50] | condition map:[{"":"Left Semi Join 0 to 1"}] | keys:{"0":"_col2 (type: bigint)","1":"_col0 (type: bigint)"} | outputColumnNames:["_col0","_col1","_col2"] | Statistics:Num rows: 34 Data size: 6324 Basic stats: COMPLETE Column stats: COMPLETE |<-Reducer 3 [SIMPLE_EDGE] - | Reduce Output Operator [RS_33] + | Reduce Output Operator [RS_32] | key expressions:_col2 (type: bigint) | Map-reduce partition columns:_col2 (type: bigint) | sort order:+ | Statistics:Num rows: 83 Data size: 15438 Basic stats: COMPLETE Column stats: COMPLETE | value expressions:_col0 (type: string), _col1 (type: string) - | Filter Operator [FIL_44] + | Filter Operator [FIL_43] | predicate:_col2 is not null (type: boolean) | Statistics:Num rows: 83 Data size: 15438 Basic stats: COMPLETE Column stats: COMPLETE | Group By Operator [GBY_20] @@ -3532,7 +3533,7 @@ Stage-0 | keys:_col0 (type: string), _col1 (type: string) | outputColumnNames:["_col0","_col1","_col2"] | Statistics:Num rows: 83 Data size: 15438 Basic stats: COMPLETE Column stats: COMPLETE - | Merge Join Operator [MERGEJOIN_50] + | Merge Join Operator [MERGEJOIN_49] | | condition map:[{"":"Left Semi Join 0 to 1"}] | | keys:{"0":"_col0 (type: string)","1":"_col0 (type: string)"} | | outputColumnNames:["_col0","_col1"] @@ -3547,7 +3548,7 @@ Stage-0 | | Select Operator [SEL_2] | | outputColumnNames:["_col0","_col1"] | | Statistics:Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE - | | Filter Operator [FIL_45] + | | Filter Operator [FIL_44] | | predicate:(key > '8') (type: boolean) | | Statistics:Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE | | TableScan [TS_0] @@ -3566,57 +3567,54 @@ Stage-0 | Select Operator [SEL_9] | outputColumnNames:["_col0"] | Statistics:Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE - | Filter Operator [FIL_46] + | Filter Operator [FIL_45] | predicate:(key > '8') (type: boolean) | Statistics:Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE | TableScan [TS_7] | alias:b | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE |<-Reducer 7 [SIMPLE_EDGE] - Reduce Output Operator [RS_35] + Reduce Output Operator [RS_34] key expressions:_col0 (type: bigint) Map-reduce partition columns:_col0 (type: bigint) sort order:+ Statistics:Num rows: 34 Data size: 272 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator [GBY_31] + Group By Operator [GBY_30] keys:_col0 (type: bigint) outputColumnNames:["_col0"] Statistics:Num rows: 34 Data size: 272 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator [SEL_29] + Select Operator [SEL_28] outputColumnNames:["_col0"] Statistics:Num rows: 69 Data size: 552 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator [FIL_47] + Filter Operator [FIL_46] predicate:_col1 is not null (type: boolean) Statistics:Num rows: 69 Data size: 552 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator [SEL_49] + Select Operator [SEL_48] outputColumnNames:["_col1"] Statistics:Num rows: 69 Data size: 552 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator [GBY_28] + Group By Operator [GBY_27] | aggregations:["count(VALUE._col0)"] | keys:KEY._col0 (type: string) | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 69 Data size: 6555 Basic stats: COMPLETE Column stats: COMPLETE |<-Map 6 [SIMPLE_EDGE] - Reduce Output Operator [RS_27] + Reduce Output Operator [RS_26] key expressions:_col0 (type: string) Map-reduce partition columns:_col0 (type: string) sort order:+ Statistics:Num rows: 69 Data size: 6555 Basic stats: COMPLETE Column stats: COMPLETE value expressions:_col1 (type: bigint) - Group By Operator [GBY_26] + Group By Operator [GBY_25] aggregations:["count()"] - keys:_col0 (type: string) + keys:key (type: string) outputColumnNames:["_col0","_col1"] Statistics:Num rows: 69 Data size: 6555 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator [SEL_24] - outputColumnNames:["_col0"] + Filter Operator [FIL_47] + predicate:(key > '9') (type: boolean) Statistics:Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator [FIL_48] - predicate:(key > '9') (type: boolean) - Statistics:Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE - TableScan [TS_22] - alias:b - Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE + TableScan [TS_22] + alias:b + Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE PREHOOK: query: explain select p_mfgr, p_name, avg(p_size) from part @@ -3642,78 +3640,78 @@ Stage-0 limit:-1 Stage-1 Reducer 3 - File Output Operator [FS_22] + File Output Operator [FS_21] compressed:false Statistics:Num rows: 3 Data size: 681 Basic stats: COMPLETE Column stats: COMPLETE table:{"input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat","serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe"} - Merge Join Operator [MERGEJOIN_27] + Merge Join Operator [MERGEJOIN_26] | condition map:[{"":"Left Semi Join 0 to 1"}] | keys:{"0":"_col1 (type: string)","1":"_col0 (type: string)"} | outputColumnNames:["_col0","_col1","_col2"] | Statistics:Num rows: 3 Data size: 681 Basic stats: COMPLETE Column stats: COMPLETE |<-Reducer 2 [SIMPLE_EDGE] - | Reduce Output Operator [RS_17] + | Reduce Output Operator [RS_16] | key expressions:_col1 (type: string) | Map-reduce partition columns:_col1 (type: string) | sort order:+ | Statistics:Num rows: 13 Data size: 2951 Basic stats: COMPLETE Column stats: COMPLETE | value expressions:_col0 (type: string), _col2 (type: double) - | Group By Operator [GBY_6] - | | aggregations:["avg(VALUE._col0)"] - | | keys:KEY._col0 (type: string), KEY._col1 (type: string) - | | outputColumnNames:["_col0","_col1","_col2"] - | | Statistics:Num rows: 13 Data size: 2951 Basic stats: COMPLETE Column stats: COMPLETE - | |<-Map 1 [SIMPLE_EDGE] - | Reduce Output Operator [RS_5] - | key expressions:_col0 (type: string), _col1 (type: string) - | Map-reduce partition columns:_col0 (type: string), _col1 (type: string) - | sort order:++ - | Statistics:Num rows: 13 Data size: 2847 Basic stats: COMPLETE Column stats: COMPLETE - | value expressions:_col2 (type: struct) - | Group By Operator [GBY_4] - | aggregations:["avg(_col2)"] - | keys:_col0 (type: string), _col1 (type: string) - | outputColumnNames:["_col0","_col1","_col2"] + | Select Operator [SEL_6] + | outputColumnNames:["_col0","_col1","_col2"] + | Statistics:Num rows: 13 Data size: 2951 Basic stats: COMPLETE Column stats: COMPLETE + | Group By Operator [GBY_5] + | | aggregations:["avg(VALUE._col0)"] + | | keys:KEY._col0 (type: string), KEY._col1 (type: string) + | | outputColumnNames:["_col0","_col1","_col2"] + | | Statistics:Num rows: 13 Data size: 2951 Basic stats: COMPLETE Column stats: COMPLETE + | |<-Map 1 [SIMPLE_EDGE] + | Reduce Output Operator [RS_4] + | key expressions:_col0 (type: string), _col1 (type: string) + | Map-reduce partition columns:_col0 (type: string), _col1 (type: string) + | sort order:++ | Statistics:Num rows: 13 Data size: 2847 Basic stats: COMPLETE Column stats: COMPLETE - | Select Operator [SEL_2] + | value expressions:_col2 (type: struct) + | Group By Operator [GBY_3] + | aggregations:["avg(p_size)"] + | keys:p_name (type: string), p_mfgr (type: string) | outputColumnNames:["_col0","_col1","_col2"] - | Statistics:Num rows: 26 Data size: 5798 Basic stats: COMPLETE Column stats: COMPLETE - | Filter Operator [FIL_25] + | Statistics:Num rows: 13 Data size: 2847 Basic stats: COMPLETE Column stats: COMPLETE + | Filter Operator [FIL_24] | predicate:p_name is not null (type: boolean) | Statistics:Num rows: 26 Data size: 5798 Basic stats: COMPLETE Column stats: COMPLETE | TableScan [TS_0] | alias:part | Statistics:Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: COMPLETE |<-Reducer 5 [SIMPLE_EDGE] - Reduce Output Operator [RS_19] + Reduce Output Operator [RS_18] key expressions:_col0 (type: string) Map-reduce partition columns:_col0 (type: string) sort order:+ Statistics:Num rows: 6 Data size: 1104 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator [GBY_15] + Group By Operator [GBY_14] keys:_col0 (type: string) outputColumnNames:["_col0"] Statistics:Num rows: 6 Data size: 1104 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator [SEL_12] + Select Operator [SEL_11] outputColumnNames:["_col0"] Statistics:Num rows: 13 Data size: 2392 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator [FIL_26] + Filter Operator [FIL_25] predicate:first_value_window_0 is not null (type: boolean) Statistics:Num rows: 13 Data size: 6383 Basic stats: COMPLETE Column stats: COMPLETE - PTF Operator [PTF_11] + PTF Operator [PTF_10] Function definitions:[{"Input definition":{"type:":"WINDOWING"}},{"name:":"windowingtablefunction","order by:":"_col5","partition by:":"_col2"}] Statistics:Num rows: 26 Data size: 12766 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator [SEL_10] + Select Operator [SEL_9] | outputColumnNames:["_col1","_col2","_col5"] | Statistics:Num rows: 26 Data size: 12766 Basic stats: COMPLETE Column stats: COMPLETE |<-Map 4 [SIMPLE_EDGE] - Reduce Output Operator [RS_9] + Reduce Output Operator [RS_8] key expressions:p_mfgr (type: string), p_size (type: int) Map-reduce partition columns:p_mfgr (type: string) sort order:++ Statistics:Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: COMPLETE value expressions:p_name (type: string) - TableScan [TS_8] + TableScan [TS_7] alias:part Statistics:Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: COMPLETE @@ -3744,59 +3742,59 @@ Stage-0 limit:-1 Stage-1 Reducer 4 - File Output Operator [FS_29] + File Output Operator [FS_28] compressed:false Statistics:Num rows: 302 Data size: 53756 Basic stats: COMPLETE Column stats: NONE table:{"input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat","serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe"} - Select Operator [SEL_28] + Select Operator [SEL_27] | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 302 Data size: 53756 Basic stats: COMPLETE Column stats: NONE |<-Reducer 3 [SIMPLE_EDGE] - Reduce Output Operator [RS_27] + Reduce Output Operator [RS_26] key expressions:_col0 (type: string) sort order:+ Statistics:Num rows: 302 Data size: 53756 Basic stats: COMPLETE Column stats: NONE value expressions:_col1 (type: string) - Select Operator [SEL_26] + Select Operator [SEL_25] outputColumnNames:["_col0","_col1"] Statistics:Num rows: 302 Data size: 53756 Basic stats: COMPLETE Column stats: NONE - Filter Operator [FIL_32] + Filter Operator [FIL_31] predicate:_col3 is null (type: boolean) Statistics:Num rows: 302 Data size: 53756 Basic stats: COMPLETE Column stats: NONE - Merge Join Operator [MERGEJOIN_37] + Merge Join Operator [MERGEJOIN_36] | condition map:[{"":"Left Outer Join0 to 1"}] | keys:{"0":"_col0 (type: string)","1":"_col0 (type: string)"} | outputColumnNames:["_col0","_col1","_col3"] | Statistics:Num rows: 605 Data size: 107690 Basic stats: COMPLETE Column stats: NONE |<-Map 7 [SIMPLE_EDGE] - | Reduce Output Operator [RS_23] + | Reduce Output Operator [RS_22] | key expressions:_col0 (type: string) | Map-reduce partition columns:_col0 (type: string) | sort order:+ | Statistics:Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE - | Select Operator [SEL_17] + | Select Operator [SEL_16] | outputColumnNames:["_col0"] | Statistics:Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE - | Filter Operator [FIL_35] + | Filter Operator [FIL_34] | predicate:(key > '2') (type: boolean) | Statistics:Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE - | TableScan [TS_15] + | TableScan [TS_14] | alias:src_cbo | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE |<-Reducer 2 [SIMPLE_EDGE] - Reduce Output Operator [RS_22] + Reduce Output Operator [RS_21] key expressions:_col0 (type: string) Map-reduce partition columns:_col0 (type: string) sort order:+ Statistics:Num rows: 550 Data size: 97900 Basic stats: COMPLETE Column stats: NONE value expressions:_col1 (type: string) - Merge Join Operator [MERGEJOIN_36] + Merge Join Operator [MERGEJOIN_35] | condition map:[{"":"Inner Join 0 to 1"}] | keys:{} | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 550 Data size: 97900 Basic stats: COMPLETE Column stats: NONE |<-Map 1 [SIMPLE_EDGE] - | Reduce Output Operator [RS_19] + | Reduce Output Operator [RS_18] | sort order: | Statistics:Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE | value expressions:_col0 (type: string), _col1 (type: string) @@ -3807,30 +3805,30 @@ Stage-0 | alias:src_cbo | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE |<-Reducer 6 [SIMPLE_EDGE] - Reduce Output Operator [RS_20] + Reduce Output Operator [RS_19] sort order: Statistics:Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE - Select Operator [SEL_12] + Select Operator [SEL_11] Statistics:Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE - Filter Operator [FIL_33] + Filter Operator [FIL_32] predicate:(_col0 = 0) (type: boolean) Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator [GBY_11] + Group By Operator [GBY_10] | aggregations:["count(VALUE._col0)"] | outputColumnNames:["_col0"] | Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE |<-Map 5 [SIMPLE_EDGE] - Reduce Output Operator [RS_10] + Reduce Output Operator [RS_9] sort order: Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions:_col0 (type: bigint) - Group By Operator [GBY_9] + Group By Operator [GBY_8] aggregations:["count()"] outputColumnNames:["_col0"] Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Select Operator [SEL_5] Statistics:Num rows: 1 Data size: 87 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator [FIL_34] + Filter Operator [FIL_33] predicate:((key > '2') and key is null) (type: boolean) Statistics:Num rows: 1 Data size: 87 Basic stats: COMPLETE Column stats: COMPLETE TableScan [TS_3] @@ -3865,50 +3863,50 @@ Stage-0 limit:-1 Stage-1 Reducer 3 - File Output Operator [FS_27] + File Output Operator [FS_26] compressed:false Statistics:Num rows: 15 Data size: 3507 Basic stats: COMPLETE Column stats: NONE table:{"input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat","serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe"} - Select Operator [SEL_26] + Select Operator [SEL_25] outputColumnNames:["_col0","_col1","_col2"] Statistics:Num rows: 15 Data size: 3507 Basic stats: COMPLETE Column stats: NONE - Filter Operator [FIL_30] + Filter Operator [FIL_29] predicate:_col4 is null (type: boolean) Statistics:Num rows: 15 Data size: 3507 Basic stats: COMPLETE Column stats: NONE - Merge Join Operator [MERGEJOIN_35] + Merge Join Operator [MERGEJOIN_34] | condition map:[{"":"Left Outer Join0 to 1"}] | keys:{"0":"_col0 (type: string), _col1 (type: string)","1":"_col0 (type: string), _col1 (type: string)"} | outputColumnNames:["_col0","_col1","_col2","_col4"] | Statistics:Num rows: 30 Data size: 7014 Basic stats: COMPLETE Column stats: NONE |<-Map 6 [SIMPLE_EDGE] - | Reduce Output Operator [RS_23] + | Reduce Output Operator [RS_22] | key expressions:_col0 (type: string), _col1 (type: string) | Map-reduce partition columns:_col0 (type: string), _col1 (type: string) | sort order:++ | Statistics:Num rows: 8 Data size: 1752 Basic stats: COMPLETE Column stats: COMPLETE - | Select Operator [SEL_17] + | Select Operator [SEL_16] | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 8 Data size: 1752 Basic stats: COMPLETE Column stats: COMPLETE - | Filter Operator [FIL_33] + | Filter Operator [FIL_32] | predicate:(p_size < 10) (type: boolean) | Statistics:Num rows: 8 Data size: 1784 Basic stats: COMPLETE Column stats: COMPLETE - | TableScan [TS_15] + | TableScan [TS_14] | alias:b | Statistics:Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: COMPLETE |<-Reducer 2 [SIMPLE_EDGE] - Reduce Output Operator [RS_22] + Reduce Output Operator [RS_21] key expressions:_col0 (type: string), _col1 (type: string) Map-reduce partition columns:_col0 (type: string), _col1 (type: string) sort order:++ Statistics:Num rows: 28 Data size: 6377 Basic stats: COMPLETE Column stats: NONE value expressions:_col2 (type: int) - Merge Join Operator [MERGEJOIN_34] + Merge Join Operator [MERGEJOIN_33] | condition map:[{"":"Inner Join 0 to 1"}] | keys:{} | outputColumnNames:["_col0","_col1","_col2"] | Statistics:Num rows: 28 Data size: 6377 Basic stats: COMPLETE Column stats: NONE |<-Map 1 [SIMPLE_EDGE] - | Reduce Output Operator [RS_19] + | Reduce Output Operator [RS_18] | sort order: | Statistics:Num rows: 26 Data size: 5798 Basic stats: COMPLETE Column stats: COMPLETE | value expressions:_col0 (type: string), _col1 (type: string), _col2 (type: int) @@ -3919,30 +3917,30 @@ Stage-0 | alias:b | Statistics:Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: COMPLETE |<-Reducer 5 [SIMPLE_EDGE] - Reduce Output Operator [RS_20] + Reduce Output Operator [RS_19] sort order: Statistics:Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE - Select Operator [SEL_12] + Select Operator [SEL_11] Statistics:Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE - Filter Operator [FIL_31] + Filter Operator [FIL_30] predicate:(_col0 = 0) (type: boolean) Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator [GBY_11] + Group By Operator [GBY_10] | aggregations:["count(VALUE._col0)"] | outputColumnNames:["_col0"] | Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE |<-Map 4 [SIMPLE_EDGE] - Reduce Output Operator [RS_10] + Reduce Output Operator [RS_9] sort order: Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions:_col0 (type: bigint) - Group By Operator [GBY_9] + Group By Operator [GBY_8] aggregations:["count()"] outputColumnNames:["_col0"] Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Select Operator [SEL_5] Statistics:Num rows: 1 Data size: 223 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator [FIL_32] + Filter Operator [FIL_31] predicate:((p_size < 10) and (p_name is null or p_mfgr is null)) (type: boolean) Statistics:Num rows: 1 Data size: 223 Basic stats: COMPLETE Column stats: COMPLETE TableScan [TS_3] @@ -3979,39 +3977,39 @@ Stage-0 limit:-1 Stage-1 Reducer 4 - File Output Operator [FS_39] + File Output Operator [FS_38] compressed:false Statistics:Num rows: 1 Data size: 146 Basic stats: COMPLETE Column stats: NONE table:{"input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat","serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe"} - Select Operator [SEL_38] + Select Operator [SEL_37] | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 1 Data size: 146 Basic stats: COMPLETE Column stats: NONE |<-Reducer 3 [SIMPLE_EDGE] - Reduce Output Operator [RS_37] + Reduce Output Operator [RS_36] key expressions:_col0 (type: string) sort order:+ Statistics:Num rows: 1 Data size: 146 Basic stats: COMPLETE Column stats: NONE value expressions:_col1 (type: int) - Merge Join Operator [MERGEJOIN_49] + Merge Join Operator [MERGEJOIN_48] | condition map:[{"":"Inner Join 0 to 1"}] | keys:{} | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 1 Data size: 146 Basic stats: COMPLETE Column stats: NONE |<-Reducer 2 [SIMPLE_EDGE] - | Reduce Output Operator [RS_31] + | Reduce Output Operator [RS_30] | sort order: | Statistics:Num rows: 1 Data size: 133 Basic stats: COMPLETE Column stats: COMPLETE | value expressions:_col0 (type: string), _col1 (type: int) - | Filter Operator [FIL_42] + | Filter Operator [FIL_41] | predicate:_col2 is null (type: boolean) | Statistics:Num rows: 1 Data size: 133 Basic stats: COMPLETE Column stats: COMPLETE - | Merge Join Operator [MERGEJOIN_48] + | Merge Join Operator [MERGEJOIN_47] | | condition map:[{"":"Left Outer Join0 to 1"}] | | keys:{"0":"UDFToDouble(_col1) (type: double)","1":"_col0 (type: double)"} | | outputColumnNames:["_col0","_col1","_col2"] | | Statistics:Num rows: 1 Data size: 133 Basic stats: COMPLETE Column stats: COMPLETE | |<-Map 1 [SIMPLE_EDGE] - | | Reduce Output Operator [RS_28] + | | Reduce Output Operator [RS_27] | | key expressions:UDFToDouble(_col1) (type: double) | | Map-reduce partition columns:UDFToDouble(_col1) (type: double) | | sort order:+ @@ -4024,73 +4022,67 @@ Stage-0 | | alias:part | | Statistics:Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: COMPLETE | |<-Reducer 6 [SIMPLE_EDGE] - | Reduce Output Operator [RS_29] + | Reduce Output Operator [RS_28] | key expressions:_col0 (type: double) | Map-reduce partition columns:_col0 (type: double) | sort order:+ | Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - | Group By Operator [GBY_9] + | Group By Operator [GBY_8] | | aggregations:["avg(VALUE._col0)"] | | outputColumnNames:["_col0"] | | Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE | |<-Map 5 [SIMPLE_EDGE] - | Reduce Output Operator [RS_8] + | Reduce Output Operator [RS_7] | sort order: | Statistics:Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE | value expressions:_col0 (type: struct) - | Group By Operator [GBY_7] - | aggregations:["avg(_col0)"] + | Group By Operator [GBY_6] + | aggregations:["avg(p_size)"] | outputColumnNames:["_col0"] | Statistics:Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE - | Select Operator [SEL_5] - | outputColumnNames:["_col0"] + | Filter Operator [FIL_43] + | predicate:(p_size < 10) (type: boolean) | Statistics:Num rows: 8 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE - | Filter Operator [FIL_44] - | predicate:(p_size < 10) (type: boolean) - | Statistics:Num rows: 8 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE - | TableScan [TS_3] - | alias:part - | Statistics:Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: COMPLETE + | TableScan [TS_3] + | alias:part + | Statistics:Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: COMPLETE |<-Reducer 8 [SIMPLE_EDGE] - Reduce Output Operator [RS_32] + Reduce Output Operator [RS_31] sort order: Statistics:Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE - Select Operator [SEL_24] + Select Operator [SEL_23] Statistics:Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE - Filter Operator [FIL_45] + Filter Operator [FIL_44] predicate:(_col0 = 0) (type: boolean) Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator [GBY_23] + Group By Operator [GBY_22] aggregations:["count()"] outputColumnNames:["_col0"] Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator [SEL_18] + Select Operator [SEL_16] Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator [FIL_46] + Filter Operator [FIL_45] predicate:_col0 is null (type: boolean) Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator [GBY_17] + Group By Operator [GBY_15] | aggregations:["avg(VALUE._col0)"] | outputColumnNames:["_col0"] | Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE |<-Map 7 [SIMPLE_EDGE] - Reduce Output Operator [RS_16] + Reduce Output Operator [RS_14] sort order: Statistics:Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE value expressions:_col0 (type: struct) - Group By Operator [GBY_15] - aggregations:["avg(_col0)"] + Group By Operator [GBY_13] + aggregations:["avg(p_size)"] outputColumnNames:["_col0"] Statistics:Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE - Select Operator [SEL_13] - outputColumnNames:["_col0"] + Filter Operator [FIL_46] + predicate:(p_size < 10) (type: boolean) Statistics:Num rows: 8 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator [FIL_47] - predicate:(p_size < 10) (type: boolean) - Statistics:Num rows: 8 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE - TableScan [TS_11] - alias:part - Statistics:Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: COMPLETE + TableScan [TS_10] + alias:part + Statistics:Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: COMPLETE PREHOOK: query: explain select b.p_mfgr, min(p_retailprice) from part b @@ -4128,152 +4120,149 @@ Stage-0 limit:-1 Stage-1 Reducer 5 - File Output Operator [FS_44] + File Output Operator [FS_40] compressed:false Statistics:Num rows: 2 Data size: 256 Basic stats: COMPLETE Column stats: NONE table:{"input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat","serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe"} - Select Operator [SEL_43] + Select Operator [SEL_39] | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 2 Data size: 256 Basic stats: COMPLETE Column stats: NONE |<-Reducer 4 [SIMPLE_EDGE] - Reduce Output Operator [RS_42] + Reduce Output Operator [RS_38] key expressions:_col0 (type: string) sort order:+ Statistics:Num rows: 2 Data size: 256 Basic stats: COMPLETE Column stats: NONE value expressions:_col1 (type: double) - Select Operator [SEL_41] + Select Operator [SEL_37] outputColumnNames:["_col0","_col1"] Statistics:Num rows: 2 Data size: 256 Basic stats: COMPLETE Column stats: NONE - Filter Operator [FIL_47] + Filter Operator [FIL_43] predicate:_col3 is null (type: boolean) Statistics:Num rows: 2 Data size: 256 Basic stats: COMPLETE Column stats: NONE - Merge Join Operator [MERGEJOIN_53] + Merge Join Operator [MERGEJOIN_49] | condition map:[{"":"Left Outer Join0 to 1"}] | keys:{"0":"_col0 (type: string), _col1 (type: double)","1":"_col0 (type: string), _col1 (type: double)"} | outputColumnNames:["_col0","_col1","_col3"] | Statistics:Num rows: 5 Data size: 641 Basic stats: COMPLETE Column stats: NONE |<-Reducer 10 [SIMPLE_EDGE] - | Reduce Output Operator [RS_38] + | Reduce Output Operator [RS_34] | key expressions:_col0 (type: string), _col1 (type: double) | Map-reduce partition columns:_col0 (type: string), _col1 (type: double) | sort order:++ | Statistics:Num rows: 1 Data size: 106 Basic stats: COMPLETE Column stats: COMPLETE - | Select Operator [SEL_32] + | Select Operator [SEL_28] | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 1 Data size: 106 Basic stats: COMPLETE Column stats: COMPLETE - | Filter Operator [FIL_50] + | Filter Operator [FIL_46] | predicate:((_col2 - _col1) > 600.0) (type: boolean) | Statistics:Num rows: 1 Data size: 114 Basic stats: COMPLETE Column stats: COMPLETE - | Group By Operator [GBY_30] + | Group By Operator [GBY_26] | | aggregations:["min(VALUE._col0)","max(VALUE._col1)"] | | keys:KEY._col0 (type: string) | | outputColumnNames:["_col0","_col1","_col2"] | | Statistics:Num rows: 5 Data size: 570 Basic stats: COMPLETE Column stats: COMPLETE | |<-Map 9 [SIMPLE_EDGE] - | Reduce Output Operator [RS_29] + | Reduce Output Operator [RS_25] | key expressions:_col0 (type: string) | Map-reduce partition columns:_col0 (type: string) | sort order:+ | Statistics:Num rows: 5 Data size: 570 Basic stats: COMPLETE Column stats: COMPLETE | value expressions:_col1 (type: double), _col2 (type: double) - | Group By Operator [GBY_28] - | aggregations:["min(_col1)","max(_col1)"] - | keys:_col0 (type: string) + | Group By Operator [GBY_24] + | aggregations:["min(p_retailprice)","max(p_retailprice)"] + | keys:p_mfgr (type: string) | outputColumnNames:["_col0","_col1","_col2"] | Statistics:Num rows: 5 Data size: 570 Basic stats: COMPLETE Column stats: COMPLETE - | Select Operator [SEL_26] - | outputColumnNames:["_col0","_col1"] + | TableScan [TS_22] + | alias:b | Statistics:Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: COMPLETE - | TableScan [TS_25] - | alias:b - | Statistics:Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: COMPLETE |<-Reducer 3 [SIMPLE_EDGE] - Reduce Output Operator [RS_37] + Reduce Output Operator [RS_33] key expressions:_col0 (type: string), _col1 (type: double) Map-reduce partition columns:_col0 (type: string), _col1 (type: double) sort order:++ Statistics:Num rows: 5 Data size: 583 Basic stats: COMPLETE Column stats: NONE - Merge Join Operator [MERGEJOIN_52] + Merge Join Operator [MERGEJOIN_48] | condition map:[{"":"Inner Join 0 to 1"}] | keys:{} | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 5 Data size: 583 Basic stats: COMPLETE Column stats: NONE |<-Reducer 2 [SIMPLE_EDGE] - | Reduce Output Operator [RS_34] + | Reduce Output Operator [RS_30] | sort order: | Statistics:Num rows: 5 Data size: 530 Basic stats: COMPLETE Column stats: COMPLETE | value expressions:_col0 (type: string), _col1 (type: double) - | Group By Operator [GBY_6] + | Group By Operator [GBY_5] | | aggregations:["min(VALUE._col0)"] | | keys:KEY._col0 (type: string) | | outputColumnNames:["_col0","_col1"] | | Statistics:Num rows: 5 Data size: 530 Basic stats: COMPLETE Column stats: COMPLETE | |<-Map 1 [SIMPLE_EDGE] - | Reduce Output Operator [RS_5] + | Reduce Output Operator [RS_4] | key expressions:_col0 (type: string) | Map-reduce partition columns:_col0 (type: string) | sort order:+ | Statistics:Num rows: 5 Data size: 530 Basic stats: COMPLETE Column stats: COMPLETE | value expressions:_col1 (type: double) - | Group By Operator [GBY_4] - | aggregations:["min(_col1)"] - | keys:_col0 (type: string) + | Group By Operator [GBY_3] + | aggregations:["min(p_retailprice)"] + | keys:p_mfgr (type: string) | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 5 Data size: 530 Basic stats: COMPLETE Column stats: COMPLETE | Select Operator [SEL_2] - | outputColumnNames:["_col0","_col1"] + | outputColumnNames:["p_mfgr","p_retailprice"] | Statistics:Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: COMPLETE | TableScan [TS_0] | alias:b | Statistics:Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: COMPLETE |<-Reducer 8 [SIMPLE_EDGE] - Reduce Output Operator [RS_35] + Reduce Output Operator [RS_31] sort order: Statistics:Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE - Select Operator [SEL_22] + Select Operator [SEL_19] Statistics:Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: COMPLETE - Filter Operator [FIL_48] + Filter Operator [FIL_44] predicate:(_col0 = 0) (type: boolean) Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator [GBY_21] + Group By Operator [GBY_18] | aggregations:["count(VALUE._col0)"] | outputColumnNames:["_col0"] | Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE |<-Reducer 7 [SIMPLE_EDGE] - Reduce Output Operator [RS_20] + Reduce Output Operator [RS_17] sort order: Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions:_col0 (type: bigint) - Group By Operator [GBY_19] + Group By Operator [GBY_16] aggregations:["count()"] outputColumnNames:["_col0"] Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator [SEL_15] + Select Operator [SEL_13] Statistics:Num rows: 1 Data size: 114 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator [FIL_49] + Filter Operator [FIL_45] predicate:((_col0 is null or _col1 is null) and ((_col2 - _col1) > 600.0)) (type: boolean) Statistics:Num rows: 1 Data size: 114 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator [GBY_13] + Group By Operator [GBY_11] | aggregations:["min(VALUE._col0)","max(VALUE._col1)"] | keys:KEY._col0 (type: string) | outputColumnNames:["_col0","_col1","_col2"] | Statistics:Num rows: 5 Data size: 570 Basic stats: COMPLETE Column stats: COMPLETE |<-Map 6 [SIMPLE_EDGE] - Reduce Output Operator [RS_12] + Reduce Output Operator [RS_10] key expressions:_col0 (type: string) Map-reduce partition columns:_col0 (type: string) sort order:+ Statistics:Num rows: 5 Data size: 570 Basic stats: COMPLETE Column stats: COMPLETE value expressions:_col1 (type: double), _col2 (type: double) - Group By Operator [GBY_11] - aggregations:["min(_col1)","max(_col1)"] - keys:_col0 (type: string) + Group By Operator [GBY_9] + aggregations:["min(p_retailprice)","max(p_retailprice)"] + keys:p_mfgr (type: string) outputColumnNames:["_col0","_col1","_col2"] Statistics:Num rows: 5 Data size: 570 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator [SEL_9] - outputColumnNames:["_col0","_col1"] + Select Operator [SEL_8] + outputColumnNames:["p_mfgr","p_retailprice"] Statistics:Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: COMPLETE - TableScan [TS_8] + TableScan [TS_7] alias:b Statistics:Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: COMPLETE @@ -4864,29 +4853,29 @@ Stage-0 limit:-1 Stage-1 Reducer 2 - File Output Operator [FS_7] + File Output Operator [FS_6] compressed:false Statistics:Num rows: 2 Data size: 39 Basic stats: COMPLETE Column stats: NONE table:{"input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat","serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe"} - Group By Operator [GBY_5] + Group By Operator [GBY_4] | aggregations:["count(DISTINCT KEY._col1:0._col0)","count(DISTINCT KEY._col1:1._col0)","sum(VALUE._col2)"] | keys:KEY._col0 (type: int) | outputColumnNames:["_col0","_col1","_col2","_col3"] | Statistics:Num rows: 2 Data size: 39 Basic stats: COMPLETE Column stats: NONE |<-Map 1 [SIMPLE_EDGE] - Reduce Output Operator [RS_4] + Reduce Output Operator [RS_3] key expressions:_col0 (type: int), _col1 (type: int), _col2 (type: int) Map-reduce partition columns:_col0 (type: int) sort order:+++ Statistics:Num rows: 4 Data size: 78 Basic stats: COMPLETE Column stats: NONE value expressions:_col5 (type: bigint) - Group By Operator [GBY_3] - aggregations:["count(DISTINCT _col1)","count(DISTINCT _col2)","sum(_col3)"] - keys:_col0 (type: int), _col1 (type: int), _col2 (type: int) + Group By Operator [GBY_2] + aggregations:["count(DISTINCT b)","count(DISTINCT c)","sum(d)"] + keys:a (type: int), b (type: int), c (type: int) outputColumnNames:["_col0","_col1","_col2","_col3","_col4","_col5"] Statistics:Num rows: 4 Data size: 78 Basic stats: COMPLETE Column stats: NONE Select Operator [SEL_1] - outputColumnNames:["_col0","_col1","_col2","_col3"] + outputColumnNames:["a","b","c","d"] Statistics:Num rows: 4 Data size: 78 Basic stats: COMPLETE Column stats: NONE TableScan [TS_0] alias:abcd @@ -4906,24 +4895,24 @@ Stage-0 limit:-1 Stage-1 Reducer 2 - File Output Operator [FS_6] + File Output Operator [FS_5] compressed:false Statistics:Num rows: 2 Data size: 39 Basic stats: COMPLETE Column stats: NONE table:{"input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat","serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe"} - Group By Operator [GBY_4] + Group By Operator [GBY_3] | aggregations:["count(DISTINCT KEY._col1:0._col0)","count(DISTINCT KEY._col1:1._col0)","sum(VALUE._col0)"] | keys:KEY._col0 (type: int) | outputColumnNames:["_col0","_col1","_col2","_col3"] | Statistics:Num rows: 2 Data size: 39 Basic stats: COMPLETE Column stats: NONE |<-Map 1 [SIMPLE_EDGE] - Reduce Output Operator [RS_3] - key expressions:_col0 (type: int), _col1 (type: int), _col2 (type: int) - Map-reduce partition columns:_col0 (type: int) + Reduce Output Operator [RS_2] + key expressions:a (type: int), b (type: int), c (type: int) + Map-reduce partition columns:a (type: int) sort order:+++ Statistics:Num rows: 4 Data size: 78 Basic stats: COMPLETE Column stats: NONE - value expressions:_col3 (type: int) + value expressions:d (type: int) Select Operator [SEL_1] - outputColumnNames:["_col0","_col1","_col2","_col3"] + outputColumnNames:["a","b","c","d"] Statistics:Num rows: 4 Data size: 78 Basic stats: COMPLETE Column stats: NONE TableScan [TS_0] alias:abcd @@ -8013,32 +8002,32 @@ Stage-0 limit:-1 Stage-1 Reducer 3 - File Output Operator [FS_8] + File Output Operator [FS_7] compressed:true Statistics:Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE table:{"input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat","serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe"} - Group By Operator [GBY_6] + Group By Operator [GBY_5] | keys:KEY._col0 (type: string), KEY._col1 (type: string) | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE |<-Reducer 2 [SIMPLE_EDGE] - Reduce Output Operator [RS_5] + Reduce Output Operator [RS_4] key expressions:_col0 (type: string), _col1 (type: string) Map-reduce partition columns:_col0 (type: string), _col1 (type: string) sort order:++ Statistics:Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator [GBY_4] + Group By Operator [GBY_3] | keys:KEY._col0 (type: string), KEY._col1 (type: string) | outputColumnNames:["_col0","_col1"] | Statistics:Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE |<-Map 1 [SIMPLE_EDGE] - Reduce Output Operator [RS_3] - key expressions:_col0 (type: string), _col1 (type: string) + Reduce Output Operator [RS_2] + key expressions:key (type: string), value (type: string) Map-reduce partition columns:rand() (type: double) sort order:++ Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE Select Operator [SEL_1] - outputColumnNames:["_col0","_col1"] + outputColumnNames:["key","value"] Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE TableScan [TS_0] alias:src diff --git a/ql/src/test/results/clientpositive/llap/explainuser_2.q.out b/ql/src/test/results/clientpositive/llap/explainuser_2.q.out index 8156789..57fcc3c 100644 --- a/ql/src/test/results/clientpositive/llap/explainuser_2.q.out +++ b/ql/src/test/results/clientpositive/llap/explainuser_2.q.out @@ -335,245 +335,248 @@ Stage-0 limit:100 Stage-1 Reducer 5 - File Output Operator [FS_69] + File Output Operator [FS_68] compressed:false Statistics:Num rows: 100 Data size: 1000 Basic stats: COMPLETE Column stats: NONE table:{"input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat","serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe"} - Limit [LIM_68] + Limit [LIM_67] Number of rows:100 Statistics:Num rows: 100 Data size: 1000 Basic stats: COMPLETE Column stats: NONE - Select Operator [SEL_67] + Select Operator [SEL_66] | outputColumnNames:["_col0","_col1","_col2","_col3","_col4","_col5"] | Statistics:Num rows: 402 Data size: 4276 Basic stats: COMPLETE Column stats: NONE |<-Reducer 4 [SIMPLE_EDGE] - Reduce Output Operator [RS_66] + Reduce Output Operator [RS_65] key expressions:_col0 (type: string), _col1 (type: string), _col2 (type: string) sort order:+++ Statistics:Num rows: 402 Data size: 4276 Basic stats: COMPLETE Column stats: NONE value expressions:_col3 (type: bigint), _col4 (type: bigint), _col5 (type: bigint) - Group By Operator [GBY_64] - | aggregations:["count(VALUE._col0)","count(VALUE._col1)","count(VALUE._col2)"] - | keys:KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: string) - | outputColumnNames:["_col0","_col1","_col2","_col3","_col4","_col5"] - | Statistics:Num rows: 402 Data size: 4276 Basic stats: COMPLETE Column stats: NONE - |<-Reducer 3 [SIMPLE_EDGE] - Reduce Output Operator [RS_63] - key expressions:_col0 (type: string), _col1 (type: string), _col2 (type: string) - Map-reduce partition columns:_col0 (type: string), _col1 (type: string), _col2 (type: string) - sort order:+++ - Statistics:Num rows: 804 Data size: 8552 Basic stats: COMPLETE Column stats: NONE - value expressions:_col3 (type: bigint), _col4 (type: bigint), _col5 (type: bigint) - Group By Operator [GBY_62] - aggregations:["count(_col3)","count(_col4)","count(_col5)"] - keys:_col0 (type: string), _col1 (type: string), _col2 (type: string) - outputColumnNames:["_col0","_col1","_col2","_col3","_col4","_col5"] + Select Operator [SEL_64] + outputColumnNames:["_col0","_col1","_col2","_col3","_col4","_col5"] + Statistics:Num rows: 402 Data size: 4276 Basic stats: COMPLETE Column stats: NONE + Group By Operator [GBY_63] + | aggregations:["count(VALUE._col0)","count(VALUE._col1)","count(VALUE._col2)"] + | keys:KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: string) + | outputColumnNames:["_col0","_col1","_col2","_col3","_col4","_col5"] + | Statistics:Num rows: 402 Data size: 4276 Basic stats: COMPLETE Column stats: NONE + |<-Reducer 3 [SIMPLE_EDGE] + Reduce Output Operator [RS_62] + key expressions:_col0 (type: string), _col1 (type: string), _col2 (type: string) + Map-reduce partition columns:_col0 (type: string), _col1 (type: string), _col2 (type: string) + sort order:+++ Statistics:Num rows: 804 Data size: 8552 Basic stats: COMPLETE Column stats: NONE - Select Operator [SEL_60] + value expressions:_col3 (type: bigint), _col4 (type: bigint), _col5 (type: bigint) + Group By Operator [GBY_61] + aggregations:["count(_col13)","count(_col21)","count(_col3)"] + keys:_col2 (type: string), _col12 (type: string), _col20 (type: string) outputColumnNames:["_col0","_col1","_col2","_col3","_col4","_col5"] Statistics:Num rows: 804 Data size: 8552 Basic stats: COMPLETE Column stats: NONE - Merge Join Operator [MERGEJOIN_111] - | condition map:[{"":"Inner Join 0 to 1"}] - | keys:{"0":"_col1 (type: string), _col3 (type: string)","1":"_col15 (type: string), _col17 (type: string)"} - | outputColumnNames:["_col2","_col3","_col12","_col13","_col20","_col21"] - | Statistics:Num rows: 804 Data size: 8552 Basic stats: COMPLETE Column stats: NONE - |<-Reducer 11 [SIMPLE_EDGE] - | Reduce Output Operator [RS_58] - | key expressions:_col15 (type: string), _col17 (type: string) - | Map-reduce partition columns:_col15 (type: string), _col17 (type: string) - | sort order:++ - | Statistics:Num rows: 731 Data size: 7775 Basic stats: COMPLETE Column stats: NONE - | value expressions:_col6 (type: string), _col7 (type: string), _col14 (type: string) - | Select Operator [SEL_49] - | outputColumnNames:["_col14","_col15","_col17","_col6","_col7"] - | Statistics:Num rows: 731 Data size: 7775 Basic stats: COMPLETE Column stats: NONE - | Merge Join Operator [MERGEJOIN_110] - | | condition map:[{"":"Inner Join 0 to 1"}] - | | keys:{"0":"_col4 (type: string), _col6 (type: string)","1":"_col2 (type: string), _col4 (type: string)"} - | | outputColumnNames:["_col2","_col3","_col14","_col15","_col17"] - | | Statistics:Num rows: 731 Data size: 7775 Basic stats: COMPLETE Column stats: NONE - | |<-Reducer 10 [SIMPLE_EDGE] - | | Reduce Output Operator [RS_45] - | | key expressions:_col4 (type: string), _col6 (type: string) - | | Map-reduce partition columns:_col4 (type: string), _col6 (type: string) - | | sort order:++ - | | Statistics:Num rows: 665 Data size: 7069 Basic stats: COMPLETE Column stats: NONE - | | value expressions:_col2 (type: string), _col3 (type: string) - | | Merge Join Operator [MERGEJOIN_108] - | | | condition map:[{"":"Inner Join 0 to 1"}] - | | | keys:{"0":"_col3 (type: string)","1":"_col1 (type: string)"} - | | | outputColumnNames:["_col2","_col3","_col4","_col6"] - | | | Statistics:Num rows: 665 Data size: 7069 Basic stats: COMPLETE Column stats: NONE - | | |<-Map 14 [SIMPLE_EDGE] - | | | Reduce Output Operator [RS_42] - | | | key expressions:_col1 (type: string) - | | | Map-reduce partition columns:_col1 (type: string) - | | | sort order:+ - | | | Statistics:Num rows: 6 Data size: 45 Basic stats: COMPLETE Column stats: NONE - | | | Select Operator [SEL_16] - | | | outputColumnNames:["_col1"] - | | | Statistics:Num rows: 6 Data size: 45 Basic stats: COMPLETE Column stats: NONE - | | | Filter Operator [FIL_102] - | | | predicate:((key = 'src1key') and value is not null) (type: boolean) - | | | Statistics:Num rows: 6 Data size: 45 Basic stats: COMPLETE Column stats: NONE - | | | TableScan [TS_14] - | | | alias:src1 - | | | Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - | | |<-Reducer 9 [SIMPLE_EDGE] - | | Reduce Output Operator [RS_40] - | | key expressions:_col3 (type: string) - | | Map-reduce partition columns:_col3 (type: string) - | | sort order:+ - | | Statistics:Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE - | | value expressions:_col2 (type: string), _col4 (type: string), _col6 (type: string) - | | Merge Join Operator [MERGEJOIN_107] - | | | condition map:[{"":"Inner Join 0 to 1"}] - | | | keys:{"0":"_col2 (type: string)","1":"_col0 (type: string)"} - | | | outputColumnNames:["_col2","_col3","_col4","_col6"] - | | | Statistics:Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE - | | |<-Map 13 [SIMPLE_EDGE] - | | | Reduce Output Operator [RS_37] - | | | key expressions:_col0 (type: string) - | | | Map-reduce partition columns:_col0 (type: string) - | | | sort order:+ - | | | Statistics:Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE - | | | Select Operator [SEL_13] - | | | outputColumnNames:["_col0"] - | | | Statistics:Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE - | | | Filter Operator [FIL_101] - | | | predicate:((value = 'd1value') and key is not null) (type: boolean) - | | | Statistics:Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE - | | | TableScan [TS_11] - | | | alias:d1 - | | | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - | | |<-Reducer 8 [SIMPLE_EDGE] - | | Reduce Output Operator [RS_35] - | | key expressions:_col2 (type: string) - | | Map-reduce partition columns:_col2 (type: string) - | | sort order:+ - | | Statistics:Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE - | | value expressions:_col3 (type: string), _col4 (type: string), _col6 (type: string) - | | Merge Join Operator [MERGEJOIN_106] - | | | condition map:[{"":"Inner Join 0 to 1"}] - | | | keys:{"0":"_col1 (type: string)","1":"_col3 (type: string)"} - | | | outputColumnNames:["_col2","_col3","_col4","_col6"] - | | | Statistics:Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE - | | |<-Map 12 [SIMPLE_EDGE] - | | | Reduce Output Operator [RS_32] - | | | key expressions:_col3 (type: string) - | | | Map-reduce partition columns:_col3 (type: string) - | | | sort order:+ - | | | Statistics:Num rows: 2 Data size: 69 Basic stats: COMPLETE Column stats: NONE - | | | value expressions:_col0 (type: string), _col1 (type: string), _col2 (type: string), _col4 (type: string) - | | | Select Operator [SEL_10] - | | | outputColumnNames:["_col0","_col1","_col2","_col3","_col4"] - | | | Statistics:Num rows: 2 Data size: 69 Basic stats: COMPLETE Column stats: NONE - | | | Filter Operator [FIL_100] - | | | predicate:((((((v3 = 'ssv3') and v2 is not null) and k1 is not null) and v1 is not null) and k2 is not null) and k3 is not null) (type: boolean) - | | | Statistics:Num rows: 2 Data size: 69 Basic stats: COMPLETE Column stats: NONE - | | | TableScan [TS_8] - | | | alias:ss - | | | Statistics:Num rows: 85 Data size: 2945 Basic stats: COMPLETE Column stats: NONE - | | |<-Map 7 [SIMPLE_EDGE] - | | Reduce Output Operator [RS_30] - | | key expressions:_col1 (type: string) - | | Map-reduce partition columns:_col1 (type: string) - | | sort order:+ - | | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - | | Select Operator [SEL_7] - | | outputColumnNames:["_col1"] - | | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - | | Filter Operator [FIL_99] - | | predicate:((key = 'srcpartkey') and value is not null) (type: boolean) - | | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - | | TableScan [TS_5] - | | alias:srcpart - | | Statistics:Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - | |<-Reducer 16 [SIMPLE_EDGE] - | Reduce Output Operator [RS_47] - | key expressions:_col2 (type: string), _col4 (type: string) - | Map-reduce partition columns:_col2 (type: string), _col4 (type: string) - | sort order:++ - | Statistics:Num rows: 137 Data size: 1460 Basic stats: COMPLETE Column stats: NONE - | value expressions:_col3 (type: string), _col5 (type: string) - | Merge Join Operator [MERGEJOIN_109] - | | condition map:[{"":"Inner Join 0 to 1"}] - | | keys:{"0":"_col0 (type: string)","1":"_col0 (type: string)"} - | | outputColumnNames:["_col2","_col3","_col4","_col5"] - | | Statistics:Num rows: 137 Data size: 1460 Basic stats: COMPLETE Column stats: NONE - | |<-Map 15 [SIMPLE_EDGE] - | | Reduce Output Operator [RS_24] - | | key expressions:_col0 (type: string) - | | Map-reduce partition columns:_col0 (type: string) - | | sort order:+ - | | Statistics:Num rows: 2 Data size: 69 Basic stats: COMPLETE Column stats: NONE - | | value expressions:_col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string) - | | Select Operator [SEL_19] - | | outputColumnNames:["_col0","_col2","_col3","_col4","_col5"] - | | Statistics:Num rows: 2 Data size: 69 Basic stats: COMPLETE Column stats: NONE - | | Filter Operator [FIL_103] - | | predicate:((((((v1 = 'srv1') and k1 is not null) and k2 is not null) and k3 is not null) and v2 is not null) and v3 is not null) (type: boolean) - | | Statistics:Num rows: 2 Data size: 69 Basic stats: COMPLETE Column stats: NONE - | | TableScan [TS_17] - | | alias:sr - | | Statistics:Num rows: 85 Data size: 2945 Basic stats: COMPLETE Column stats: NONE - | |<-Map 17 [SIMPLE_EDGE] - | Reduce Output Operator [RS_26] - | key expressions:_col0 (type: string) - | Map-reduce partition columns:_col0 (type: string) - | sort order:+ - | Statistics:Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE - | Select Operator [SEL_22] - | outputColumnNames:["_col0"] - | Statistics:Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE - | Filter Operator [FIL_104] - | predicate:((value) IN ('2000Q1', '2000Q2', '2000Q3') and key is not null) (type: boolean) - | Statistics:Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE - | TableScan [TS_20] - | alias:d1 - | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - |<-Reducer 2 [SIMPLE_EDGE] - Reduce Output Operator [RS_56] - key expressions:_col1 (type: string), _col3 (type: string) - Map-reduce partition columns:_col1 (type: string), _col3 (type: string) - sort order:++ - Statistics:Num rows: 137 Data size: 1460 Basic stats: COMPLETE Column stats: NONE - value expressions:_col2 (type: string) - Merge Join Operator [MERGEJOIN_105] - | condition map:[{"":"Inner Join 0 to 1"}] - | keys:{"0":"_col0 (type: string)","1":"_col0 (type: string)"} - | outputColumnNames:["_col1","_col2","_col3"] - | Statistics:Num rows: 137 Data size: 1460 Basic stats: COMPLETE Column stats: NONE - |<-Map 1 [SIMPLE_EDGE] - | Reduce Output Operator [RS_51] - | key expressions:_col0 (type: string) - | Map-reduce partition columns:_col0 (type: string) - | sort order:+ - | Statistics:Num rows: 22 Data size: 762 Basic stats: COMPLETE Column stats: NONE - | value expressions:_col1 (type: string), _col2 (type: string), _col3 (type: string) - | Select Operator [SEL_1] - | outputColumnNames:["_col0","_col1","_col2","_col3"] - | Statistics:Num rows: 22 Data size: 762 Basic stats: COMPLETE Column stats: NONE - | Filter Operator [FIL_97] - | predicate:((k1 is not null and v2 is not null) and v3 is not null) (type: boolean) - | Statistics:Num rows: 22 Data size: 762 Basic stats: COMPLETE Column stats: NONE - | TableScan [TS_0] - | alias:cs - | Statistics:Num rows: 170 Data size: 5890 Basic stats: COMPLETE Column stats: NONE - |<-Map 6 [SIMPLE_EDGE] - Reduce Output Operator [RS_53] - key expressions:_col0 (type: string) - Map-reduce partition columns:_col0 (type: string) - sort order:+ - Statistics:Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE - Select Operator [SEL_4] - outputColumnNames:["_col0"] + Select Operator [SEL_60] + outputColumnNames:["_col2","_col12","_col20","_col13","_col21","_col3"] + Statistics:Num rows: 804 Data size: 8552 Basic stats: COMPLETE Column stats: NONE + Merge Join Operator [MERGEJOIN_110] + | condition map:[{"":"Inner Join 0 to 1"}] + | keys:{"0":"_col1 (type: string), _col3 (type: string)","1":"_col15 (type: string), _col17 (type: string)"} + | outputColumnNames:["_col2","_col3","_col12","_col13","_col20","_col21"] + | Statistics:Num rows: 804 Data size: 8552 Basic stats: COMPLETE Column stats: NONE + |<-Reducer 11 [SIMPLE_EDGE] + | Reduce Output Operator [RS_58] + | key expressions:_col15 (type: string), _col17 (type: string) + | Map-reduce partition columns:_col15 (type: string), _col17 (type: string) + | sort order:++ + | Statistics:Num rows: 731 Data size: 7775 Basic stats: COMPLETE Column stats: NONE + | value expressions:_col6 (type: string), _col7 (type: string), _col14 (type: string) + | Select Operator [SEL_49] + | outputColumnNames:["_col14","_col15","_col17","_col6","_col7"] + | Statistics:Num rows: 731 Data size: 7775 Basic stats: COMPLETE Column stats: NONE + | Merge Join Operator [MERGEJOIN_109] + | | condition map:[{"":"Inner Join 0 to 1"}] + | | keys:{"0":"_col4 (type: string), _col6 (type: string)","1":"_col2 (type: string), _col4 (type: string)"} + | | outputColumnNames:["_col2","_col3","_col14","_col15","_col17"] + | | Statistics:Num rows: 731 Data size: 7775 Basic stats: COMPLETE Column stats: NONE + | |<-Reducer 10 [SIMPLE_EDGE] + | | Reduce Output Operator [RS_45] + | | key expressions:_col4 (type: string), _col6 (type: string) + | | Map-reduce partition columns:_col4 (type: string), _col6 (type: string) + | | sort order:++ + | | Statistics:Num rows: 665 Data size: 7069 Basic stats: COMPLETE Column stats: NONE + | | value expressions:_col2 (type: string), _col3 (type: string) + | | Merge Join Operator [MERGEJOIN_107] + | | | condition map:[{"":"Inner Join 0 to 1"}] + | | | keys:{"0":"_col3 (type: string)","1":"_col1 (type: string)"} + | | | outputColumnNames:["_col2","_col3","_col4","_col6"] + | | | Statistics:Num rows: 665 Data size: 7069 Basic stats: COMPLETE Column stats: NONE + | | |<-Map 14 [SIMPLE_EDGE] + | | | Reduce Output Operator [RS_42] + | | | key expressions:_col1 (type: string) + | | | Map-reduce partition columns:_col1 (type: string) + | | | sort order:+ + | | | Statistics:Num rows: 6 Data size: 45 Basic stats: COMPLETE Column stats: NONE + | | | Select Operator [SEL_16] + | | | outputColumnNames:["_col1"] + | | | Statistics:Num rows: 6 Data size: 45 Basic stats: COMPLETE Column stats: NONE + | | | Filter Operator [FIL_101] + | | | predicate:((key = 'src1key') and value is not null) (type: boolean) + | | | Statistics:Num rows: 6 Data size: 45 Basic stats: COMPLETE Column stats: NONE + | | | TableScan [TS_14] + | | | alias:src1 + | | | Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + | | |<-Reducer 9 [SIMPLE_EDGE] + | | Reduce Output Operator [RS_40] + | | key expressions:_col3 (type: string) + | | Map-reduce partition columns:_col3 (type: string) + | | sort order:+ + | | Statistics:Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE + | | value expressions:_col2 (type: string), _col4 (type: string), _col6 (type: string) + | | Merge Join Operator [MERGEJOIN_106] + | | | condition map:[{"":"Inner Join 0 to 1"}] + | | | keys:{"0":"_col2 (type: string)","1":"_col0 (type: string)"} + | | | outputColumnNames:["_col2","_col3","_col4","_col6"] + | | | Statistics:Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE + | | |<-Map 13 [SIMPLE_EDGE] + | | | Reduce Output Operator [RS_37] + | | | key expressions:_col0 (type: string) + | | | Map-reduce partition columns:_col0 (type: string) + | | | sort order:+ + | | | Statistics:Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE + | | | Select Operator [SEL_13] + | | | outputColumnNames:["_col0"] + | | | Statistics:Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE + | | | Filter Operator [FIL_100] + | | | predicate:((value = 'd1value') and key is not null) (type: boolean) + | | | Statistics:Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE + | | | TableScan [TS_11] + | | | alias:d1 + | | | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + | | |<-Reducer 8 [SIMPLE_EDGE] + | | Reduce Output Operator [RS_35] + | | key expressions:_col2 (type: string) + | | Map-reduce partition columns:_col2 (type: string) + | | sort order:+ + | | Statistics:Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + | | value expressions:_col3 (type: string), _col4 (type: string), _col6 (type: string) + | | Merge Join Operator [MERGEJOIN_105] + | | | condition map:[{"":"Inner Join 0 to 1"}] + | | | keys:{"0":"_col1 (type: string)","1":"_col3 (type: string)"} + | | | outputColumnNames:["_col2","_col3","_col4","_col6"] + | | | Statistics:Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + | | |<-Map 12 [SIMPLE_EDGE] + | | | Reduce Output Operator [RS_32] + | | | key expressions:_col3 (type: string) + | | | Map-reduce partition columns:_col3 (type: string) + | | | sort order:+ + | | | Statistics:Num rows: 2 Data size: 69 Basic stats: COMPLETE Column stats: NONE + | | | value expressions:_col0 (type: string), _col1 (type: string), _col2 (type: string), _col4 (type: string) + | | | Select Operator [SEL_10] + | | | outputColumnNames:["_col0","_col1","_col2","_col3","_col4"] + | | | Statistics:Num rows: 2 Data size: 69 Basic stats: COMPLETE Column stats: NONE + | | | Filter Operator [FIL_99] + | | | predicate:((((((v3 = 'ssv3') and v2 is not null) and k1 is not null) and v1 is not null) and k2 is not null) and k3 is not null) (type: boolean) + | | | Statistics:Num rows: 2 Data size: 69 Basic stats: COMPLETE Column stats: NONE + | | | TableScan [TS_8] + | | | alias:ss + | | | Statistics:Num rows: 85 Data size: 2945 Basic stats: COMPLETE Column stats: NONE + | | |<-Map 7 [SIMPLE_EDGE] + | | Reduce Output Operator [RS_30] + | | key expressions:_col1 (type: string) + | | Map-reduce partition columns:_col1 (type: string) + | | sort order:+ + | | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + | | Select Operator [SEL_7] + | | outputColumnNames:["_col1"] + | | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + | | Filter Operator [FIL_98] + | | predicate:((key = 'srcpartkey') and value is not null) (type: boolean) + | | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + | | TableScan [TS_5] + | | alias:srcpart + | | Statistics:Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + | |<-Reducer 16 [SIMPLE_EDGE] + | Reduce Output Operator [RS_47] + | key expressions:_col2 (type: string), _col4 (type: string) + | Map-reduce partition columns:_col2 (type: string), _col4 (type: string) + | sort order:++ + | Statistics:Num rows: 137 Data size: 1460 Basic stats: COMPLETE Column stats: NONE + | value expressions:_col3 (type: string), _col5 (type: string) + | Merge Join Operator [MERGEJOIN_108] + | | condition map:[{"":"Inner Join 0 to 1"}] + | | keys:{"0":"_col0 (type: string)","1":"_col0 (type: string)"} + | | outputColumnNames:["_col2","_col3","_col4","_col5"] + | | Statistics:Num rows: 137 Data size: 1460 Basic stats: COMPLETE Column stats: NONE + | |<-Map 15 [SIMPLE_EDGE] + | | Reduce Output Operator [RS_24] + | | key expressions:_col0 (type: string) + | | Map-reduce partition columns:_col0 (type: string) + | | sort order:+ + | | Statistics:Num rows: 2 Data size: 69 Basic stats: COMPLETE Column stats: NONE + | | value expressions:_col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string) + | | Select Operator [SEL_19] + | | outputColumnNames:["_col0","_col2","_col3","_col4","_col5"] + | | Statistics:Num rows: 2 Data size: 69 Basic stats: COMPLETE Column stats: NONE + | | Filter Operator [FIL_102] + | | predicate:((((((v1 = 'srv1') and k1 is not null) and k2 is not null) and k3 is not null) and v2 is not null) and v3 is not null) (type: boolean) + | | Statistics:Num rows: 2 Data size: 69 Basic stats: COMPLETE Column stats: NONE + | | TableScan [TS_17] + | | alias:sr + | | Statistics:Num rows: 85 Data size: 2945 Basic stats: COMPLETE Column stats: NONE + | |<-Map 17 [SIMPLE_EDGE] + | Reduce Output Operator [RS_26] + | key expressions:_col0 (type: string) + | Map-reduce partition columns:_col0 (type: string) + | sort order:+ + | Statistics:Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE + | Select Operator [SEL_22] + | outputColumnNames:["_col0"] + | Statistics:Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE + | Filter Operator [FIL_103] + | predicate:((value) IN ('2000Q1', '2000Q2', '2000Q3') and key is not null) (type: boolean) + | Statistics:Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE + | TableScan [TS_20] + | alias:d1 + | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + |<-Reducer 2 [SIMPLE_EDGE] + Reduce Output Operator [RS_56] + key expressions:_col1 (type: string), _col3 (type: string) + Map-reduce partition columns:_col1 (type: string), _col3 (type: string) + sort order:++ + Statistics:Num rows: 137 Data size: 1460 Basic stats: COMPLETE Column stats: NONE + value expressions:_col2 (type: string) + Merge Join Operator [MERGEJOIN_104] + | condition map:[{"":"Inner Join 0 to 1"}] + | keys:{"0":"_col0 (type: string)","1":"_col0 (type: string)"} + | outputColumnNames:["_col1","_col2","_col3"] + | Statistics:Num rows: 137 Data size: 1460 Basic stats: COMPLETE Column stats: NONE + |<-Map 1 [SIMPLE_EDGE] + | Reduce Output Operator [RS_51] + | key expressions:_col0 (type: string) + | Map-reduce partition columns:_col0 (type: string) + | sort order:+ + | Statistics:Num rows: 22 Data size: 762 Basic stats: COMPLETE Column stats: NONE + | value expressions:_col1 (type: string), _col2 (type: string), _col3 (type: string) + | Select Operator [SEL_1] + | outputColumnNames:["_col0","_col1","_col2","_col3"] + | Statistics:Num rows: 22 Data size: 762 Basic stats: COMPLETE Column stats: NONE + | Filter Operator [FIL_96] + | predicate:((k1 is not null and v2 is not null) and v3 is not null) (type: boolean) + | Statistics:Num rows: 22 Data size: 762 Basic stats: COMPLETE Column stats: NONE + | TableScan [TS_0] + | alias:cs + | Statistics:Num rows: 170 Data size: 5890 Basic stats: COMPLETE Column stats: NONE + |<-Map 6 [SIMPLE_EDGE] + Reduce Output Operator [RS_53] + key expressions:_col0 (type: string) + Map-reduce partition columns:_col0 (type: string) + sort order:+ Statistics:Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE - Filter Operator [FIL_98] - predicate:((value) IN ('2000Q1', '2000Q2', '2000Q3') and key is not null) (type: boolean) + Select Operator [SEL_4] + outputColumnNames:["_col0"] Statistics:Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE - TableScan [TS_2] - alias:d1 - Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Filter Operator [FIL_97] + predicate:((value) IN ('2000Q1', '2000Q2', '2000Q3') and key is not null) (type: boolean) + Statistics:Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE + TableScan [TS_2] + alias:d1 + Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE PREHOOK: query: explain SELECT x.key, z.value, y.value @@ -1522,199 +1525,202 @@ Stage-0 limit:100 Stage-1 Reducer 5 - File Output Operator [FS_69] + File Output Operator [FS_68] compressed:false Statistics:Num rows: 100 Data size: 1000 Basic stats: COMPLETE Column stats: NONE table:{"input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat","serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe"} - Limit [LIM_68] + Limit [LIM_67] Number of rows:100 Statistics:Num rows: 100 Data size: 1000 Basic stats: COMPLETE Column stats: NONE - Select Operator [SEL_67] + Select Operator [SEL_66] | outputColumnNames:["_col0","_col1","_col2","_col3","_col4","_col5"] | Statistics:Num rows: 402 Data size: 4276 Basic stats: COMPLETE Column stats: NONE |<-Reducer 4 [SIMPLE_EDGE] - Reduce Output Operator [RS_66] + Reduce Output Operator [RS_65] key expressions:_col0 (type: string), _col1 (type: string), _col2 (type: string) sort order:+++ Statistics:Num rows: 402 Data size: 4276 Basic stats: COMPLETE Column stats: NONE value expressions:_col3 (type: bigint), _col4 (type: bigint), _col5 (type: bigint) - Group By Operator [GBY_64] - | aggregations:["count(VALUE._col0)","count(VALUE._col1)","count(VALUE._col2)"] - | keys:KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: string) - | outputColumnNames:["_col0","_col1","_col2","_col3","_col4","_col5"] - | Statistics:Num rows: 402 Data size: 4276 Basic stats: COMPLETE Column stats: NONE - |<-Map 3 [SIMPLE_EDGE] - Reduce Output Operator [RS_63] - key expressions:_col0 (type: string), _col1 (type: string), _col2 (type: string) - Map-reduce partition columns:_col0 (type: string), _col1 (type: string), _col2 (type: string) - sort order:+++ - Statistics:Num rows: 804 Data size: 8552 Basic stats: COMPLETE Column stats: NONE - value expressions:_col3 (type: bigint), _col4 (type: bigint), _col5 (type: bigint) - Group By Operator [GBY_62] - aggregations:["count(_col3)","count(_col4)","count(_col5)"] - keys:_col0 (type: string), _col1 (type: string), _col2 (type: string) - outputColumnNames:["_col0","_col1","_col2","_col3","_col4","_col5"] + Select Operator [SEL_64] + outputColumnNames:["_col0","_col1","_col2","_col3","_col4","_col5"] + Statistics:Num rows: 402 Data size: 4276 Basic stats: COMPLETE Column stats: NONE + Group By Operator [GBY_63] + | aggregations:["count(VALUE._col0)","count(VALUE._col1)","count(VALUE._col2)"] + | keys:KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: string) + | outputColumnNames:["_col0","_col1","_col2","_col3","_col4","_col5"] + | Statistics:Num rows: 402 Data size: 4276 Basic stats: COMPLETE Column stats: NONE + |<-Map 3 [SIMPLE_EDGE] + Reduce Output Operator [RS_62] + key expressions:_col0 (type: string), _col1 (type: string), _col2 (type: string) + Map-reduce partition columns:_col0 (type: string), _col1 (type: string), _col2 (type: string) + sort order:+++ Statistics:Num rows: 804 Data size: 8552 Basic stats: COMPLETE Column stats: NONE - Select Operator [SEL_60] + value expressions:_col3 (type: bigint), _col4 (type: bigint), _col5 (type: bigint) + Group By Operator [GBY_61] + aggregations:["count(_col13)","count(_col21)","count(_col3)"] + keys:_col2 (type: string), _col12 (type: string), _col20 (type: string) outputColumnNames:["_col0","_col1","_col2","_col3","_col4","_col5"] Statistics:Num rows: 804 Data size: 8552 Basic stats: COMPLETE Column stats: NONE - Map Join Operator [MAPJOIN_111] - | condition map:[{"":"Inner Join 0 to 1"}] - | keys:{"Map 2":"_col1 (type: string), _col3 (type: string)","Map 3":"_col15 (type: string), _col17 (type: string)"} - | outputColumnNames:["_col2","_col3","_col12","_col13","_col20","_col21"] - | Statistics:Num rows: 804 Data size: 8552 Basic stats: COMPLETE Column stats: NONE - |<-Map 2 [BROADCAST_EDGE] - | Reduce Output Operator [RS_56] - | key expressions:_col1 (type: string), _col3 (type: string) - | Map-reduce partition columns:_col1 (type: string), _col3 (type: string) - | sort order:++ - | Statistics:Num rows: 137 Data size: 1460 Basic stats: COMPLETE Column stats: NONE - | value expressions:_col2 (type: string) - | Map Join Operator [MAPJOIN_105] - | | condition map:[{"":"Inner Join 0 to 1"}] - | | keys:{"Map 1":"_col0 (type: string)","Map 2":"_col0 (type: string)"} - | | outputColumnNames:["_col1","_col2","_col3"] - | | Statistics:Num rows: 137 Data size: 1460 Basic stats: COMPLETE Column stats: NONE - | |<-Map 1 [BROADCAST_EDGE] - | | Reduce Output Operator [RS_51] - | | key expressions:_col0 (type: string) - | | Map-reduce partition columns:_col0 (type: string) - | | sort order:+ - | | Statistics:Num rows: 22 Data size: 762 Basic stats: COMPLETE Column stats: NONE - | | value expressions:_col1 (type: string), _col2 (type: string), _col3 (type: string) - | | Select Operator [SEL_1] - | | outputColumnNames:["_col0","_col1","_col2","_col3"] - | | Statistics:Num rows: 22 Data size: 762 Basic stats: COMPLETE Column stats: NONE - | | Filter Operator [FIL_97] - | | predicate:((k1 is not null and v2 is not null) and v3 is not null) (type: boolean) - | | Statistics:Num rows: 22 Data size: 762 Basic stats: COMPLETE Column stats: NONE - | | TableScan [TS_0] - | | alias:cs - | | Statistics:Num rows: 170 Data size: 5890 Basic stats: COMPLETE Column stats: NONE - | |<-Select Operator [SEL_4] - | outputColumnNames:["_col0"] - | Statistics:Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE - | Filter Operator [FIL_98] - | predicate:((value) IN ('2000Q1', '2000Q2', '2000Q3') and key is not null) (type: boolean) - | Statistics:Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE - | TableScan [TS_2] - | alias:d1 - | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - |<-Select Operator [SEL_49] - outputColumnNames:["_col14","_col15","_col17","_col6","_col7"] - Statistics:Num rows: 731 Data size: 7775 Basic stats: COMPLETE Column stats: NONE - Map Join Operator [MAPJOIN_110] - | condition map:[{"":"Inner Join 0 to 1"}] - | keys:{"Map 3":"_col4 (type: string), _col6 (type: string)","Map 10":"_col2 (type: string), _col4 (type: string)"} - | outputColumnNames:["_col2","_col3","_col14","_col15","_col17"] - | Statistics:Num rows: 731 Data size: 7775 Basic stats: COMPLETE Column stats: NONE - |<-Map 10 [BROADCAST_EDGE] - | Reduce Output Operator [RS_47] - | key expressions:_col2 (type: string), _col4 (type: string) - | Map-reduce partition columns:_col2 (type: string), _col4 (type: string) - | sort order:++ - | Statistics:Num rows: 137 Data size: 1460 Basic stats: COMPLETE Column stats: NONE - | value expressions:_col3 (type: string), _col5 (type: string) - | Map Join Operator [MAPJOIN_109] - | | condition map:[{"":"Inner Join 0 to 1"}] - | | keys:{"Map 9":"_col0 (type: string)","Map 10":"_col0 (type: string)"} - | | outputColumnNames:["_col2","_col3","_col4","_col5"] - | | Statistics:Num rows: 137 Data size: 1460 Basic stats: COMPLETE Column stats: NONE - | |<-Map 9 [BROADCAST_EDGE] - | | Reduce Output Operator [RS_24] - | | key expressions:_col0 (type: string) - | | Map-reduce partition columns:_col0 (type: string) - | | sort order:+ - | | Statistics:Num rows: 2 Data size: 69 Basic stats: COMPLETE Column stats: NONE - | | value expressions:_col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string) - | | Select Operator [SEL_19] - | | outputColumnNames:["_col0","_col2","_col3","_col4","_col5"] - | | Statistics:Num rows: 2 Data size: 69 Basic stats: COMPLETE Column stats: NONE - | | Filter Operator [FIL_103] - | | predicate:((((((v1 = 'srv1') and k1 is not null) and k2 is not null) and k3 is not null) and v2 is not null) and v3 is not null) (type: boolean) - | | Statistics:Num rows: 2 Data size: 69 Basic stats: COMPLETE Column stats: NONE - | | TableScan [TS_17] - | | alias:sr - | | Statistics:Num rows: 85 Data size: 2945 Basic stats: COMPLETE Column stats: NONE - | |<-Select Operator [SEL_22] - | outputColumnNames:["_col0"] - | Statistics:Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE - | Filter Operator [FIL_104] - | predicate:((value) IN ('2000Q1', '2000Q2', '2000Q3') and key is not null) (type: boolean) - | Statistics:Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE - | TableScan [TS_20] - | alias:d1 - | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - |<-Map Join Operator [MAPJOIN_108] + Select Operator [SEL_60] + outputColumnNames:["_col2","_col12","_col20","_col13","_col21","_col3"] + Statistics:Num rows: 804 Data size: 8552 Basic stats: COMPLETE Column stats: NONE + Map Join Operator [MAPJOIN_110] + | condition map:[{"":"Inner Join 0 to 1"}] + | keys:{"Map 2":"_col1 (type: string), _col3 (type: string)","Map 3":"_col15 (type: string), _col17 (type: string)"} + | outputColumnNames:["_col2","_col3","_col12","_col13","_col20","_col21"] + | Statistics:Num rows: 804 Data size: 8552 Basic stats: COMPLETE Column stats: NONE + |<-Map 2 [BROADCAST_EDGE] + | Reduce Output Operator [RS_56] + | key expressions:_col1 (type: string), _col3 (type: string) + | Map-reduce partition columns:_col1 (type: string), _col3 (type: string) + | sort order:++ + | Statistics:Num rows: 137 Data size: 1460 Basic stats: COMPLETE Column stats: NONE + | value expressions:_col2 (type: string) + | Map Join Operator [MAPJOIN_104] + | | condition map:[{"":"Inner Join 0 to 1"}] + | | keys:{"Map 1":"_col0 (type: string)","Map 2":"_col0 (type: string)"} + | | outputColumnNames:["_col1","_col2","_col3"] + | | Statistics:Num rows: 137 Data size: 1460 Basic stats: COMPLETE Column stats: NONE + | |<-Map 1 [BROADCAST_EDGE] + | | Reduce Output Operator [RS_51] + | | key expressions:_col0 (type: string) + | | Map-reduce partition columns:_col0 (type: string) + | | sort order:+ + | | Statistics:Num rows: 22 Data size: 762 Basic stats: COMPLETE Column stats: NONE + | | value expressions:_col1 (type: string), _col2 (type: string), _col3 (type: string) + | | Select Operator [SEL_1] + | | outputColumnNames:["_col0","_col1","_col2","_col3"] + | | Statistics:Num rows: 22 Data size: 762 Basic stats: COMPLETE Column stats: NONE + | | Filter Operator [FIL_96] + | | predicate:((k1 is not null and v2 is not null) and v3 is not null) (type: boolean) + | | Statistics:Num rows: 22 Data size: 762 Basic stats: COMPLETE Column stats: NONE + | | TableScan [TS_0] + | | alias:cs + | | Statistics:Num rows: 170 Data size: 5890 Basic stats: COMPLETE Column stats: NONE + | |<-Select Operator [SEL_4] + | outputColumnNames:["_col0"] + | Statistics:Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE + | Filter Operator [FIL_97] + | predicate:((value) IN ('2000Q1', '2000Q2', '2000Q3') and key is not null) (type: boolean) + | Statistics:Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE + | TableScan [TS_2] + | alias:d1 + | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + |<-Select Operator [SEL_49] + outputColumnNames:["_col14","_col15","_col17","_col6","_col7"] + Statistics:Num rows: 731 Data size: 7775 Basic stats: COMPLETE Column stats: NONE + Map Join Operator [MAPJOIN_109] | condition map:[{"":"Inner Join 0 to 1"}] - | keys:{"Map 3":"_col3 (type: string)","Map 8":"_col1 (type: string)"} - | outputColumnNames:["_col2","_col3","_col4","_col6"] - | Statistics:Num rows: 665 Data size: 7069 Basic stats: COMPLETE Column stats: NONE - |<-Map 8 [BROADCAST_EDGE] - | Reduce Output Operator [RS_42] - | key expressions:_col1 (type: string) - | Map-reduce partition columns:_col1 (type: string) - | sort order:+ - | Statistics:Num rows: 6 Data size: 45 Basic stats: COMPLETE Column stats: NONE - | Select Operator [SEL_16] - | outputColumnNames:["_col1"] - | Statistics:Num rows: 6 Data size: 45 Basic stats: COMPLETE Column stats: NONE - | Filter Operator [FIL_102] - | predicate:((key = 'src1key') and value is not null) (type: boolean) - | Statistics:Num rows: 6 Data size: 45 Basic stats: COMPLETE Column stats: NONE - | TableScan [TS_14] - | alias:src1 - | Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE + | keys:{"Map 3":"_col4 (type: string), _col6 (type: string)","Map 10":"_col2 (type: string), _col4 (type: string)"} + | outputColumnNames:["_col2","_col3","_col14","_col15","_col17"] + | Statistics:Num rows: 731 Data size: 7775 Basic stats: COMPLETE Column stats: NONE + |<-Map 10 [BROADCAST_EDGE] + | Reduce Output Operator [RS_47] + | key expressions:_col2 (type: string), _col4 (type: string) + | Map-reduce partition columns:_col2 (type: string), _col4 (type: string) + | sort order:++ + | Statistics:Num rows: 137 Data size: 1460 Basic stats: COMPLETE Column stats: NONE + | value expressions:_col3 (type: string), _col5 (type: string) + | Map Join Operator [MAPJOIN_108] + | | condition map:[{"":"Inner Join 0 to 1"}] + | | keys:{"Map 9":"_col0 (type: string)","Map 10":"_col0 (type: string)"} + | | outputColumnNames:["_col2","_col3","_col4","_col5"] + | | Statistics:Num rows: 137 Data size: 1460 Basic stats: COMPLETE Column stats: NONE + | |<-Map 9 [BROADCAST_EDGE] + | | Reduce Output Operator [RS_24] + | | key expressions:_col0 (type: string) + | | Map-reduce partition columns:_col0 (type: string) + | | sort order:+ + | | Statistics:Num rows: 2 Data size: 69 Basic stats: COMPLETE Column stats: NONE + | | value expressions:_col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string) + | | Select Operator [SEL_19] + | | outputColumnNames:["_col0","_col2","_col3","_col4","_col5"] + | | Statistics:Num rows: 2 Data size: 69 Basic stats: COMPLETE Column stats: NONE + | | Filter Operator [FIL_102] + | | predicate:((((((v1 = 'srv1') and k1 is not null) and k2 is not null) and k3 is not null) and v2 is not null) and v3 is not null) (type: boolean) + | | Statistics:Num rows: 2 Data size: 69 Basic stats: COMPLETE Column stats: NONE + | | TableScan [TS_17] + | | alias:sr + | | Statistics:Num rows: 85 Data size: 2945 Basic stats: COMPLETE Column stats: NONE + | |<-Select Operator [SEL_22] + | outputColumnNames:["_col0"] + | Statistics:Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE + | Filter Operator [FIL_103] + | predicate:((value) IN ('2000Q1', '2000Q2', '2000Q3') and key is not null) (type: boolean) + | Statistics:Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE + | TableScan [TS_20] + | alias:d1 + | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE |<-Map Join Operator [MAPJOIN_107] | condition map:[{"":"Inner Join 0 to 1"}] - | keys:{"Map 3":"_col2 (type: string)","Map 7":"_col0 (type: string)"} + | keys:{"Map 3":"_col3 (type: string)","Map 8":"_col1 (type: string)"} | outputColumnNames:["_col2","_col3","_col4","_col6"] - | Statistics:Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE - |<-Map 7 [BROADCAST_EDGE] - | Reduce Output Operator [RS_37] - | key expressions:_col0 (type: string) - | Map-reduce partition columns:_col0 (type: string) + | Statistics:Num rows: 665 Data size: 7069 Basic stats: COMPLETE Column stats: NONE + |<-Map 8 [BROADCAST_EDGE] + | Reduce Output Operator [RS_42] + | key expressions:_col1 (type: string) + | Map-reduce partition columns:_col1 (type: string) | sort order:+ - | Statistics:Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE - | Select Operator [SEL_13] - | outputColumnNames:["_col0"] - | Statistics:Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE + | Statistics:Num rows: 6 Data size: 45 Basic stats: COMPLETE Column stats: NONE + | Select Operator [SEL_16] + | outputColumnNames:["_col1"] + | Statistics:Num rows: 6 Data size: 45 Basic stats: COMPLETE Column stats: NONE | Filter Operator [FIL_101] - | predicate:((value = 'd1value') and key is not null) (type: boolean) - | Statistics:Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE - | TableScan [TS_11] - | alias:d1 - | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + | predicate:((key = 'src1key') and value is not null) (type: boolean) + | Statistics:Num rows: 6 Data size: 45 Basic stats: COMPLETE Column stats: NONE + | TableScan [TS_14] + | alias:src1 + | Statistics:Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE |<-Map Join Operator [MAPJOIN_106] | condition map:[{"":"Inner Join 0 to 1"}] - | keys:{"Map 3":"_col1 (type: string)","Map 6":"_col3 (type: string)"} + | keys:{"Map 3":"_col2 (type: string)","Map 7":"_col0 (type: string)"} | outputColumnNames:["_col2","_col3","_col4","_col6"] - | Statistics:Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE - |<-Map 6 [BROADCAST_EDGE] - | Reduce Output Operator [RS_32] - | key expressions:_col3 (type: string) - | Map-reduce partition columns:_col3 (type: string) + | Statistics:Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE + |<-Map 7 [BROADCAST_EDGE] + | Reduce Output Operator [RS_37] + | key expressions:_col0 (type: string) + | Map-reduce partition columns:_col0 (type: string) | sort order:+ - | Statistics:Num rows: 2 Data size: 69 Basic stats: COMPLETE Column stats: NONE - | value expressions:_col0 (type: string), _col1 (type: string), _col2 (type: string), _col4 (type: string) - | Select Operator [SEL_10] - | outputColumnNames:["_col0","_col1","_col2","_col3","_col4"] - | Statistics:Num rows: 2 Data size: 69 Basic stats: COMPLETE Column stats: NONE + | Statistics:Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE + | Select Operator [SEL_13] + | outputColumnNames:["_col0"] + | Statistics:Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE | Filter Operator [FIL_100] - | predicate:((((((v3 = 'ssv3') and v2 is not null) and k1 is not null) and v1 is not null) and k2 is not null) and k3 is not null) (type: boolean) - | Statistics:Num rows: 2 Data size: 69 Basic stats: COMPLETE Column stats: NONE - | TableScan [TS_8] - | alias:ss - | Statistics:Num rows: 85 Data size: 2945 Basic stats: COMPLETE Column stats: NONE - |<-Select Operator [SEL_7] - outputColumnNames:["_col1"] - Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Filter Operator [FIL_99] - predicate:((key = 'srcpartkey') and value is not null) (type: boolean) + | predicate:((value = 'd1value') and key is not null) (type: boolean) + | Statistics:Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE + | TableScan [TS_11] + | alias:d1 + | Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + |<-Map Join Operator [MAPJOIN_105] + | condition map:[{"":"Inner Join 0 to 1"}] + | keys:{"Map 3":"_col1 (type: string)","Map 6":"_col3 (type: string)"} + | outputColumnNames:["_col2","_col3","_col4","_col6"] + | Statistics:Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + |<-Map 6 [BROADCAST_EDGE] + | Reduce Output Operator [RS_32] + | key expressions:_col3 (type: string) + | Map-reduce partition columns:_col3 (type: string) + | sort order:+ + | Statistics:Num rows: 2 Data size: 69 Basic stats: COMPLETE Column stats: NONE + | value expressions:_col0 (type: string), _col1 (type: string), _col2 (type: string), _col4 (type: string) + | Select Operator [SEL_10] + | outputColumnNames:["_col0","_col1","_col2","_col3","_col4"] + | Statistics:Num rows: 2 Data size: 69 Basic stats: COMPLETE Column stats: NONE + | Filter Operator [FIL_99] + | predicate:((((((v3 = 'ssv3') and v2 is not null) and k1 is not null) and v1 is not null) and k2 is not null) and k3 is not null) (type: boolean) + | Statistics:Num rows: 2 Data size: 69 Basic stats: COMPLETE Column stats: NONE + | TableScan [TS_8] + | alias:ss + | Statistics:Num rows: 85 Data size: 2945 Basic stats: COMPLETE Column stats: NONE + |<-Select Operator [SEL_7] + outputColumnNames:["_col1"] Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - TableScan [TS_5] - alias:srcpart - Statistics:Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Filter Operator [FIL_98] + predicate:((key = 'srcpartkey') and value is not null) (type: boolean) + Statistics:Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + TableScan [TS_5] + alias:srcpart + Statistics:Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE PREHOOK: query: explain SELECT x.key, z.value, y.value diff --git a/ql/src/test/results/clientpositive/llap/having.q.out b/ql/src/test/results/clientpositive/llap/having.q.out index 28a515d..026fdbf 100644 --- a/ql/src/test/results/clientpositive/llap/having.q.out +++ b/ql/src/test/results/clientpositive/llap/having.q.out @@ -112,22 +112,18 @@ STAGE PLANS: Filter Operator predicate: (UDFToDouble(key) <> 302.0) (type: boolean) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), value (type: string) + Group By Operator + aggregations: max(value) + keys: key (type: string) + mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: max(_col1) - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1 + Reduce Output Operator + 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 - Reduce Output Operator - 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: _col1 (type: string) + value expressions: _col1 (type: string) Execution mode: llap Reducer 2 Execution mode: uber @@ -490,11 +486,11 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: max(_col1) - keys: _col0 (type: string) + aggregations: max(value) + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -765,22 +761,18 @@ STAGE PLANS: Filter Operator predicate: (UDFToDouble(key) > 300.0) (type: boolean) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), value (type: string) + Group By Operator + aggregations: max(value) + keys: key (type: string) + mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: max(_col1) - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1 + 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 - 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 - value expressions: _col1 (type: string) + value expressions: _col1 (type: string) Execution mode: llap Reducer 2 Execution mode: uber @@ -967,11 +959,11 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: max(_col1) - keys: _col0 (type: string) + aggregations: max(value) + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -1237,11 +1229,11 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(_col1) - keys: _col0 (type: string) + aggregations: count(value) + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE diff --git a/ql/src/test/results/clientpositive/llap/limit_pushdown.q.out b/ql/src/test/results/clientpositive/llap/limit_pushdown.q.out index 9119780..e39ac18 100644 --- a/ql/src/test/results/clientpositive/llap/limit_pushdown.q.out +++ b/ql/src/test/results/clientpositive/llap/limit_pushdown.q.out @@ -392,10 +392,10 @@ STAGE PLANS: Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cdouble (type: double) - outputColumnNames: _col0 + outputColumnNames: cdouble Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: _col0 (type: double) + keys: cdouble (type: double) mode: hash outputColumnNames: _col0 Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE @@ -483,10 +483,10 @@ STAGE PLANS: Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctinyint (type: tinyint), cdouble (type: double) - outputColumnNames: _col0, _col1 + outputColumnNames: ctinyint, cdouble Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: _col0 (type: tinyint), _col1 (type: double) + keys: ctinyint (type: tinyint), cdouble (type: double) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE @@ -579,10 +579,10 @@ STAGE PLANS: Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctinyint (type: tinyint), cdouble (type: double) - outputColumnNames: _col0, _col1 + outputColumnNames: ctinyint, cdouble Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: _col0 (type: tinyint), _col1 (type: double) + keys: ctinyint (type: tinyint), cdouble (type: double) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE @@ -677,11 +677,11 @@ STAGE PLANS: Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctinyint (type: tinyint), cstring1 (type: string), cstring2 (type: string) - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: ctinyint, cstring1, cstring2 Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(DISTINCT _col1), count(DISTINCT _col2) - keys: _col0 (type: tinyint), _col1 (type: string), _col2 (type: string) + aggregations: count(DISTINCT cstring1), count(DISTINCT cstring2) + keys: ctinyint (type: tinyint), cstring1 (type: string), cstring2 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4 Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE @@ -799,11 +799,11 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: value (type: string), key (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: value, key Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(_col1) - keys: _col0 (type: string) + aggregations: sum(key) + keys: value (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -1067,16 +1067,16 @@ STAGE PLANS: alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: value (type: string), key (type: string) - outputColumnNames: _col0, _col1 + expressions: key (type: string), value (type: string) + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: value (type: string) sort order: + - Map-reduce partition columns: _col0 (type: string) + Map-reduce partition columns: value (type: string) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE TopN Hash Memory Usage: 0.3 - value expressions: _col1 (type: string) + value expressions: key (type: string) Execution mode: llap Reducer 2 Execution mode: uber diff --git a/ql/src/test/results/clientpositive/llap/mapjoin_mapjoin.q.out b/ql/src/test/results/clientpositive/llap/mapjoin_mapjoin.q.out index 17be306..236f0ed 100644 --- a/ql/src/test/results/clientpositive/llap/mapjoin_mapjoin.q.out +++ b/ql/src/test/results/clientpositive/llap/mapjoin_mapjoin.q.out @@ -623,22 +623,18 @@ STAGE PLANS: 1 Map 4 Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE HybridGraceHashJoin: true - Select Operator - expressions: _col2 (type: string) - outputColumnNames: _col0 + Group By Operator + aggregations: count() + keys: _col2 (type: string) + mode: hash + outputColumnNames: _col0, _col1 Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1 + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 605 Data size: 6427 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: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) + value expressions: _col1 (type: bigint) Execution mode: llap Map 3 Map Operator Tree: diff --git a/ql/src/test/results/clientpositive/llap/metadata_only_queries.q.out b/ql/src/test/results/clientpositive/llap/metadata_only_queries.q.out index bacbff3..ed3179d 100644 --- a/ql/src/test/results/clientpositive/llap/metadata_only_queries.q.out +++ b/ql/src/test/results/clientpositive/llap/metadata_only_queries.q.out @@ -452,10 +452,10 @@ STAGE PLANS: Statistics: Num rows: 9489 Data size: 978785 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ts (type: timestamp) - outputColumnNames: _col0 + outputColumnNames: ts Statistics: Num rows: 9489 Data size: 978785 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(_col0) + aggregations: count(ts) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE diff --git a/ql/src/test/results/clientpositive/llap/metadataonly1.q.out b/ql/src/test/results/clientpositive/llap/metadataonly1.q.out index d569a23..40f122a 100644 --- a/ql/src/test/results/clientpositive/llap/metadataonly1.q.out +++ b/ql/src/test/results/clientpositive/llap/metadataonly1.q.out @@ -48,10 +48,10 @@ STAGE PLANS: GatherStats: false Select Operator expressions: ds (type: string) - outputColumnNames: _col0 + outputColumnNames: ds Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Group By Operator - aggregations: max(_col0) + aggregations: max(ds) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 84 Basic stats: COMPLETE Column stats: NONE @@ -157,10 +157,10 @@ STAGE PLANS: GatherStats: false Select Operator expressions: ds (type: string) - outputColumnNames: _col0 + outputColumnNames: ds Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Group By Operator - aggregations: max(_col0) + aggregations: max(ds) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 84 Basic stats: COMPLETE Column stats: NONE @@ -304,11 +304,11 @@ STAGE PLANS: GatherStats: false Select Operator expressions: ds (type: string) - outputColumnNames: _col0 + outputColumnNames: ds Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Group By Operator - aggregations: count(DISTINCT _col0) - keys: _col0 (type: string) + aggregations: count(DISTINCT ds) + keys: ds (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE @@ -452,10 +452,10 @@ STAGE PLANS: GatherStats: false Select Operator expressions: ds (type: string) - outputColumnNames: _col0 + outputColumnNames: ds Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Group By Operator - aggregations: count(_col0) + aggregations: count(ds) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -743,10 +743,10 @@ STAGE PLANS: GatherStats: false Select Operator expressions: ds (type: string) - outputColumnNames: _col0 + outputColumnNames: ds Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Group By Operator - aggregations: max(_col0) + aggregations: max(ds) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 84 Basic stats: COMPLETE Column stats: NONE @@ -1028,11 +1028,11 @@ STAGE PLANS: GatherStats: false Select Operator expressions: ds (type: string), hr (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: ds, hr Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Group By Operator - aggregations: count(DISTINCT _col1) - keys: _col0 (type: string), _col1 (type: string) + aggregations: count(DISTINCT hr) + keys: ds (type: string), hr (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE @@ -1273,11 +1273,11 @@ STAGE PLANS: GatherStats: false Select Operator expressions: ds (type: string), hr (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: ds, hr Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Group By Operator - aggregations: count(_col1) - keys: _col0 (type: string) + aggregations: count(hr) + keys: ds (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE @@ -1514,10 +1514,10 @@ STAGE PLANS: GatherStats: false Select Operator expressions: ds (type: string) - outputColumnNames: _col0 + outputColumnNames: ds Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Group By Operator - aggregations: max(_col0) + aggregations: max(ds) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 84 Basic stats: COMPLETE Column stats: NONE @@ -1761,11 +1761,11 @@ STAGE PLANS: GatherStats: false Select Operator expressions: ds (type: string), hr (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: ds, hr Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Group By Operator - aggregations: count(DISTINCT _col1) - keys: _col0 (type: string), _col1 (type: string) + aggregations: count(DISTINCT hr) + keys: ds (type: string), hr (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE diff --git a/ql/src/test/results/clientpositive/llap/mrr.q.out b/ql/src/test/results/clientpositive/llap/mrr.q.out index f507e4b..d0200d2 100644 --- a/ql/src/test/results/clientpositive/llap/mrr.q.out +++ b/ql/src/test/results/clientpositive/llap/mrr.q.out @@ -27,11 +27,11 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(_col1) - keys: _col0 (type: string) + aggregations: count(value) + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -1314,22 +1314,18 @@ STAGE PLANS: Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), value (type: string) + Group By Operator + aggregations: count(value) + keys: key (type: string) + mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(_col1) - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1 + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 250 Data size: 2656 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: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) + value expressions: _col1 (type: bigint) Execution mode: llap Map 6 Map Operator Tree: @@ -1339,22 +1335,18 @@ STAGE PLANS: Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), value (type: string) + Group By Operator + aggregations: count(value) + keys: key (type: string) + mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(_col1) - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1 + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 250 Data size: 2656 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: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) + value expressions: _col1 (type: bigint) Execution mode: llap Map 9 Map Operator Tree: @@ -1364,22 +1356,18 @@ STAGE PLANS: Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), value (type: string) + Group By Operator + aggregations: count(value) + keys: key (type: string) + mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(_col1) - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1 + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 250 Data size: 2656 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: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) + value expressions: _col1 (type: bigint) Execution mode: llap Reducer 10 Execution mode: llap @@ -1713,22 +1701,18 @@ STAGE PLANS: Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), value (type: string) + Group By Operator + aggregations: count(value) + keys: key (type: string) + mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(_col1) - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1 + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 250 Data size: 2656 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: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) + value expressions: _col1 (type: bigint) Execution mode: llap Map 3 Map Operator Tree: diff --git a/ql/src/test/results/clientpositive/llap/selectDistinctStar.q.out b/ql/src/test/results/clientpositive/llap/selectDistinctStar.q.out index fa3cf92..663d999 100644 --- a/ql/src/test/results/clientpositive/llap/selectDistinctStar.q.out +++ b/ql/src/test/results/clientpositive/llap/selectDistinctStar.q.out @@ -24,10 +24,10 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: _col0 (type: string), _col1 (type: string) + keys: key (type: string), value (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -720,20 +720,16 @@ STAGE PLANS: Filter Operator predicate: (key < '3') (type: boolean) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), value (type: string) + Group By Operator + keys: key (type: string), value (type: string) + mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string), _col1 (type: string) - mode: hash - outputColumnNames: _col0, _col1 + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string) + sort order: ++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string) - sort order: ++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Execution mode: llap Reducer 2 Execution mode: uber @@ -2481,10 +2477,10 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + outputColumnNames: key, value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: _col0 (type: string), _col1 (type: string) + keys: key (type: string), value (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -3173,20 +3169,16 @@ STAGE PLANS: Filter Operator predicate: (key < '3') (type: boolean) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), value (type: string) + Group By Operator + keys: key (type: string), value (type: string) + mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string), _col1 (type: string) - mode: hash - outputColumnNames: _col0, _col1 + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string) + sort order: ++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string) - sort order: ++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Execution mode: llap Reducer 2 Execution mode: uber diff --git a/ql/src/test/results/clientpositive/llap/show_create_database.q.out b/ql/src/test/results/clientpositive/llap/show_create_database.q.out new file mode 100644 index 0000000..4755d2d --- /dev/null +++ b/ql/src/test/results/clientpositive/llap/show_create_database.q.out @@ -0,0 +1,19 @@ +PREHOOK: query: CREATE DATABASE some_database comment 'for show create db test' WITH DBPROPERTIES ('somekey'='somevalue') +PREHOOK: type: CREATEDATABASE +PREHOOK: Output: database:some_database +POSTHOOK: query: CREATE DATABASE some_database comment 'for show create db test' WITH DBPROPERTIES ('somekey'='somevalue') +POSTHOOK: type: CREATEDATABASE +POSTHOOK: Output: database:some_database +PREHOOK: query: SHOW CREATE DATABASE some_database +PREHOOK: type: SHOW_CREATEDATABASE +PREHOOK: Input: database:some_database +POSTHOOK: query: SHOW CREATE DATABASE some_database +POSTHOOK: type: SHOW_CREATEDATABASE +POSTHOOK: Input: database:some_database +CREATE DATABASE `some_database` +COMMENT + 'for show create db test' +LOCATION +#### A masked pattern was here #### +WITH DBPROPERTIES ( + 'somekey'='somevalue') diff --git a/ql/src/test/results/clientpositive/llap/stats_only_null.q.out b/ql/src/test/results/clientpositive/llap/stats_only_null.q.out index 1336b79..bf3a6b0 100644 --- a/ql/src/test/results/clientpositive/llap/stats_only_null.q.out +++ b/ql/src/test/results/clientpositive/llap/stats_only_null.q.out @@ -90,10 +90,10 @@ STAGE PLANS: Statistics: Num rows: 10 Data size: 120 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: a (type: double), b (type: int), c (type: string), d (type: smallint) - outputColumnNames: _col0, _col1, _col2, _col3 + outputColumnNames: a, b, c, d Statistics: Num rows: 10 Data size: 120 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(), count(_col0), count(_col1), count(_col2), count(_col3) + aggregations: count(), count(a), count(b), count(c), count(d) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4 Statistics: Num rows: 1 Data size: 40 Basic stats: COMPLETE Column stats: NONE @@ -148,10 +148,10 @@ STAGE PLANS: Statistics: Num rows: 10 Data size: 120 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: a (type: double), b (type: int), c (type: string), d (type: smallint) - outputColumnNames: _col0, _col1, _col2, _col3 + outputColumnNames: a, b, c, d Statistics: Num rows: 10 Data size: 120 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(), count(_col0), count(_col1), count(_col2), count(_col3) + aggregations: count(), count(a), count(b), count(c), count(d) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4 Statistics: Num rows: 1 Data size: 40 Basic stats: COMPLETE Column stats: NONE diff --git a/ql/src/test/results/clientpositive/llap/subquery_in.q.out b/ql/src/test/results/clientpositive/llap/subquery_in.q.out index daa26e9..034557f 100644 --- a/ql/src/test/results/clientpositive/llap/subquery_in.q.out +++ b/ql/src/test/results/clientpositive/llap/subquery_in.q.out @@ -663,20 +663,16 @@ STAGE PLANS: Filter Operator predicate: ((key > '9') and value is not null) (type: boolean) Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), value (type: string) + Group By Operator + keys: key (type: string), value (type: string) + mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string), _col1 (type: string) - mode: hash - outputColumnNames: _col0, _col1 + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string) + sort order: ++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string) Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string) - sort order: ++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE Execution mode: llap Reducer 2 Execution mode: llap @@ -851,20 +847,16 @@ STAGE PLANS: Filter Operator predicate: l_partkey is not null (type: boolean) Statistics: Num rows: 50 Data size: 5999 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: l_partkey (type: int) + Group By Operator + keys: l_partkey (type: int) + mode: hash outputColumnNames: _col0 Statistics: Num rows: 50 Data size: 5999 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: int) - mode: hash - outputColumnNames: _col0 + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) Statistics: Num rows: 50 Data size: 5999 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: 50 Data size: 5999 Basic stats: COMPLETE Column stats: NONE Execution mode: llap Reducer 2 Execution mode: llap diff --git a/ql/src/test/results/clientpositive/llap/tez_dml.q.out b/ql/src/test/results/clientpositive/llap/tez_dml.q.out index 2254d10..a87ccf3 100644 --- a/ql/src/test/results/clientpositive/llap/tez_dml.q.out +++ b/ql/src/test/results/clientpositive/llap/tez_dml.q.out @@ -30,11 +30,11 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: value (type: string) - outputColumnNames: _col0 + outputColumnNames: value Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(_col0) - keys: _col0 (type: string) + aggregations: count(value) + keys: value (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE diff --git a/ql/src/test/results/clientpositive/llap/union5.q.out b/ql/src/test/results/clientpositive/llap/union5.q.out index 5a5c290..bc3821b 100644 --- a/ql/src/test/results/clientpositive/llap/union5.q.out +++ b/ql/src/test/results/clientpositive/llap/union5.q.out @@ -31,34 +31,38 @@ STAGE PLANS: Map Operator Tree: TableScan alias: s1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE + 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: COMPLETE + expressions: key (type: string) + outputColumnNames: key + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count(key) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + 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: COMPLETE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: bigint) Execution mode: llap Map 5 Map Operator Tree: TableScan alias: s1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE + 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: COMPLETE + expressions: key (type: string) + outputColumnNames: key + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count(key) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + 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: COMPLETE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: bigint) Execution mode: llap Reducer 2 @@ -68,22 +72,22 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: 'tst1' (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 88 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count(1) keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 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: 1 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) Reducer 4 Execution mode: uber @@ -93,10 +97,10 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -108,22 +112,22 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: 'tst2' (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 88 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count(1) keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 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: 1 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) Union 3 Vertex: Union 3 diff --git a/ql/src/test/results/clientpositive/llap/union7.q.out b/ql/src/test/results/clientpositive/llap/union7.q.out index 6aa6676..a301cad 100644 --- a/ql/src/test/results/clientpositive/llap/union7.q.out +++ b/ql/src/test/results/clientpositive/llap/union7.q.out @@ -31,17 +31,19 @@ STAGE PLANS: Map Operator Tree: TableScan alias: s1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE + 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: COMPLETE + expressions: key (type: string) + outputColumnNames: key + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(1) + aggregations: count(key) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + 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: COMPLETE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: bigint) Execution mode: llap Map 5 @@ -58,12 +60,12 @@ STAGE PLANS: keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 26 Data size: 199 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 26 Data size: 199 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) Execution mode: llap Reducer 2 @@ -73,22 +75,22 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: 'tst1' (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 88 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count(1) keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 26 Data size: 199 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 26 Data size: 199 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) Reducer 4 Execution mode: uber @@ -98,10 +100,10 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat diff --git a/ql/src/test/results/clientpositive/llap/unionDistinct_1.q.out b/ql/src/test/results/clientpositive/llap/unionDistinct_1.q.out index c18b460..7e5fe2d 100644 --- a/ql/src/test/results/clientpositive/llap/unionDistinct_1.q.out +++ b/ql/src/test/results/clientpositive/llap/unionDistinct_1.q.out @@ -14290,11 +14290,11 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() - keys: _col0 (type: string) + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -14436,11 +14436,11 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() - keys: _col0 (type: string) + keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE @@ -14631,6 +14631,38 @@ POSTHOOK: Lineage: src10_3.key SIMPLE [(src)src.FieldSchema(name:key, type:strin POSTHOOK: Lineage: src10_3.value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] POSTHOOK: Lineage: src10_4.key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] POSTHOOK: Lineage: src10_4.value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] +PREHOOK: query: analyze table src10_1 compute statistics +PREHOOK: type: QUERY +PREHOOK: Input: default@src10_1 +PREHOOK: Output: default@src10_1 +POSTHOOK: query: analyze table src10_1 compute statistics +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src10_1 +POSTHOOK: Output: default@src10_1 +PREHOOK: query: analyze table src10_2 compute statistics +PREHOOK: type: QUERY +PREHOOK: Input: default@src10_2 +PREHOOK: Output: default@src10_2 +POSTHOOK: query: analyze table src10_2 compute statistics +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src10_2 +POSTHOOK: Output: default@src10_2 +PREHOOK: query: analyze table src10_3 compute statistics +PREHOOK: type: QUERY +PREHOOK: Input: default@src10_3 +PREHOOK: Output: default@src10_3 +POSTHOOK: query: analyze table src10_3 compute statistics +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src10_3 +POSTHOOK: Output: default@src10_3 +PREHOOK: query: analyze table src10_4 compute statistics +PREHOOK: type: QUERY +PREHOOK: Input: default@src10_4 +PREHOOK: Output: default@src10_4 +POSTHOOK: query: analyze table src10_4 compute statistics +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src10_4 +POSTHOOK: Output: default@src10_4 PREHOOK: query: -- When we convert the Join of sub1 and sub0 into a MapJoin, -- we can use a single MR job to evaluate this entire query. explain @@ -14669,14 +14701,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src10_1 - Statistics: Num rows: 1 Data size: 114 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 114 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 52 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 114 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 52 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 @@ -14686,76 +14718,76 @@ STAGE PLANS: outputColumnNames: _col0, _col1 input vertices: 1 Map 5 - Statistics: Num rows: 1 Data size: 125 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 57 Basic stats: COMPLETE Column stats: NONE HybridGraceHashJoin: true Group By Operator keys: _col0 (type: string), _col1 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 2 Data size: 239 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 15 Data size: 161 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 2 Data size: 239 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 15 Data size: 161 Basic stats: COMPLETE Column stats: NONE Execution mode: llap Map 5 Map Operator Tree: TableScan alias: src10_2 - Statistics: Num rows: 1 Data size: 114 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 114 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 52 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 114 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 52 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 114 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 52 Basic stats: COMPLETE Column stats: NONE Execution mode: llap Map 6 Map Operator Tree: TableScan alias: src10_3 - Statistics: Num rows: 1 Data size: 114 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 114 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE Group By Operator keys: _col0 (type: string), _col1 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 2 Data size: 228 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 208 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 2 Data size: 228 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 208 Basic stats: COMPLETE Column stats: NONE Execution mode: llap Map 9 Map Operator Tree: TableScan alias: src10_4 - Statistics: Num rows: 1 Data size: 114 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 114 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE Group By Operator keys: _col0 (type: string), _col1 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 2 Data size: 228 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 208 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 2 Data size: 228 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 208 Basic stats: COMPLETE Column stats: NONE Execution mode: llap Reducer 3 Execution mode: llap @@ -14764,11 +14796,11 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 119 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 7 Data size: 75 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + - Statistics: Num rows: 1 Data size: 119 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 7 Data size: 75 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) Reducer 4 Execution mode: uber @@ -14776,10 +14808,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 119 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 7 Data size: 75 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 119 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 7 Data size: 75 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -14791,17 +14823,17 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 114 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE Group By Operator keys: _col0 (type: string), _col1 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 2 Data size: 239 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 15 Data size: 161 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 2 Data size: 239 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 15 Data size: 161 Basic stats: COMPLETE Column stats: NONE Union 2 Vertex: Union 2 Union 7 @@ -14887,78 +14919,78 @@ STAGE PLANS: Map Operator Tree: TableScan alias: src10_1 - Statistics: Num rows: 1 Data size: 114 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 114 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 52 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 114 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 52 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 114 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 52 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) Execution mode: llap Map 10 Map Operator Tree: TableScan alias: src10_4 - Statistics: Num rows: 1 Data size: 114 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 114 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE Group By Operator keys: _col0 (type: string), _col1 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 2 Data size: 228 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 208 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 2 Data size: 228 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 208 Basic stats: COMPLETE Column stats: NONE Execution mode: llap Map 6 Map Operator Tree: TableScan alias: src10_2 - Statistics: Num rows: 1 Data size: 114 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 114 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 52 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 114 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 52 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 114 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 52 Basic stats: COMPLETE Column stats: NONE Execution mode: llap Map 7 Map Operator Tree: TableScan alias: src10_3 - Statistics: Num rows: 1 Data size: 114 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 114 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE Group By Operator keys: _col0 (type: string), _col1 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 2 Data size: 228 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 208 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 2 Data size: 228 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 20 Data size: 208 Basic stats: COMPLETE Column stats: NONE Execution mode: llap Reducer 2 Execution mode: llap @@ -14970,17 +15002,17 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 125 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 57 Basic stats: COMPLETE Column stats: NONE Group By Operator keys: _col0 (type: string), _col1 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 2 Data size: 239 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 15 Data size: 161 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 2 Data size: 239 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 15 Data size: 161 Basic stats: COMPLETE Column stats: NONE Reducer 4 Execution mode: llap Reduce Operator Tree: @@ -14988,11 +15020,11 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 119 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 7 Data size: 75 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + - Statistics: Num rows: 1 Data size: 119 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 7 Data size: 75 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) Reducer 5 Execution mode: uber @@ -15000,10 +15032,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 119 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 7 Data size: 75 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 119 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 7 Data size: 75 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -15015,17 +15047,17 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 114 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 104 Basic stats: COMPLETE Column stats: NONE Group By Operator keys: _col0 (type: string), _col1 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 2 Data size: 239 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 15 Data size: 161 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 2 Data size: 239 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 15 Data size: 161 Basic stats: COMPLETE Column stats: NONE Union 3 Vertex: Union 3 Union 8 diff --git a/ql/src/test/results/clientpositive/llap/union_fast_stats.q.out b/ql/src/test/results/clientpositive/llap/union_fast_stats.q.out new file mode 100644 index 0000000..d0d82a0 --- /dev/null +++ b/ql/src/test/results/clientpositive/llap/union_fast_stats.q.out @@ -0,0 +1,526 @@ +PREHOOK: query: drop table small_alltypesorc1a +PREHOOK: type: DROPTABLE +POSTHOOK: query: drop table small_alltypesorc1a +POSTHOOK: type: DROPTABLE +PREHOOK: query: drop table small_alltypesorc2a +PREHOOK: type: DROPTABLE +POSTHOOK: query: drop table small_alltypesorc2a +POSTHOOK: type: DROPTABLE +PREHOOK: query: drop table small_alltypesorc3a +PREHOOK: type: DROPTABLE +POSTHOOK: query: drop table small_alltypesorc3a +POSTHOOK: type: DROPTABLE +PREHOOK: query: drop table small_alltypesorc4a +PREHOOK: type: DROPTABLE +POSTHOOK: query: drop table small_alltypesorc4a +POSTHOOK: type: DROPTABLE +PREHOOK: query: drop table small_alltypesorc_a +PREHOOK: type: DROPTABLE +POSTHOOK: query: drop table small_alltypesorc_a +POSTHOOK: type: DROPTABLE +PREHOOK: query: create table small_alltypesorc1a as select * from alltypesorc where cint is not null and ctinyint is not null order by ctinyint, csmallint, cint, cbigint, cfloat, cdouble, cstring1, cstring2, ctimestamp1, ctimestamp2, cboolean1, cboolean2 limit 5 +PREHOOK: type: CREATETABLE_AS_SELECT +PREHOOK: Input: default@alltypesorc +PREHOOK: Output: database:default +PREHOOK: Output: default@small_alltypesorc1a +POSTHOOK: query: create table small_alltypesorc1a as select * from alltypesorc where cint is not null and ctinyint is not null order by ctinyint, csmallint, cint, cbigint, cfloat, cdouble, cstring1, cstring2, ctimestamp1, ctimestamp2, cboolean1, cboolean2 limit 5 +POSTHOOK: type: CREATETABLE_AS_SELECT +POSTHOOK: Input: default@alltypesorc +POSTHOOK: Output: database:default +POSTHOOK: Output: default@small_alltypesorc1a +PREHOOK: query: create table small_alltypesorc2a as select * from alltypesorc where cint is null and ctinyint is not null order by ctinyint, csmallint, cint, cbigint, cfloat, cdouble, cstring1, cstring2, ctimestamp1, ctimestamp2, cboolean1, cboolean2 limit 5 +PREHOOK: type: CREATETABLE_AS_SELECT +PREHOOK: Input: default@alltypesorc +PREHOOK: Output: database:default +PREHOOK: Output: default@small_alltypesorc2a +POSTHOOK: query: create table small_alltypesorc2a as select * from alltypesorc where cint is null and ctinyint is not null order by ctinyint, csmallint, cint, cbigint, cfloat, cdouble, cstring1, cstring2, ctimestamp1, ctimestamp2, cboolean1, cboolean2 limit 5 +POSTHOOK: type: CREATETABLE_AS_SELECT +POSTHOOK: Input: default@alltypesorc +POSTHOOK: Output: database:default +POSTHOOK: Output: default@small_alltypesorc2a +PREHOOK: query: create table small_alltypesorc3a as select * from alltypesorc where cint is not null and ctinyint is null order by ctinyint, csmallint, cint, cbigint, cfloat, cdouble, cstring1, cstring2, ctimestamp1, ctimestamp2, cboolean1, cboolean2 limit 5 +PREHOOK: type: CREATETABLE_AS_SELECT +PREHOOK: Input: default@alltypesorc +PREHOOK: Output: database:default +PREHOOK: Output: default@small_alltypesorc3a +POSTHOOK: query: create table small_alltypesorc3a as select * from alltypesorc where cint is not null and ctinyint is null order by ctinyint, csmallint, cint, cbigint, cfloat, cdouble, cstring1, cstring2, ctimestamp1, ctimestamp2, cboolean1, cboolean2 limit 5 +POSTHOOK: type: CREATETABLE_AS_SELECT +POSTHOOK: Input: default@alltypesorc +POSTHOOK: Output: database:default +POSTHOOK: Output: default@small_alltypesorc3a +PREHOOK: query: create table small_alltypesorc4a as select * from alltypesorc where cint is null and ctinyint is null order by ctinyint, csmallint, cint, cbigint, cfloat, cdouble, cstring1, cstring2, ctimestamp1, ctimestamp2, cboolean1, cboolean2 limit 5 +PREHOOK: type: CREATETABLE_AS_SELECT +PREHOOK: Input: default@alltypesorc +PREHOOK: Output: database:default +PREHOOK: Output: default@small_alltypesorc4a +POSTHOOK: query: create table small_alltypesorc4a as select * from alltypesorc where cint is null and ctinyint is null order by ctinyint, csmallint, cint, cbigint, cfloat, cdouble, cstring1, cstring2, ctimestamp1, ctimestamp2, cboolean1, cboolean2 limit 5 +POSTHOOK: type: CREATETABLE_AS_SELECT +POSTHOOK: Input: default@alltypesorc +POSTHOOK: Output: database:default +POSTHOOK: Output: default@small_alltypesorc4a +PREHOOK: query: create table small_alltypesorc_a stored as orc as select * from +(select * from (select * from small_alltypesorc1a) sq1 + union all + select * from (select * from small_alltypesorc2a) sq2 + union all + select * from (select * from small_alltypesorc3a) sq3 + union all + select * from (select * from small_alltypesorc4a) sq4) q +PREHOOK: type: CREATETABLE_AS_SELECT +PREHOOK: Input: default@small_alltypesorc1a +PREHOOK: Input: default@small_alltypesorc2a +PREHOOK: Input: default@small_alltypesorc3a +PREHOOK: Input: default@small_alltypesorc4a +PREHOOK: Output: database:default +PREHOOK: Output: default@small_alltypesorc_a +POSTHOOK: query: create table small_alltypesorc_a stored as orc as select * from +(select * from (select * from small_alltypesorc1a) sq1 + union all + select * from (select * from small_alltypesorc2a) sq2 + union all + select * from (select * from small_alltypesorc3a) sq3 + union all + select * from (select * from small_alltypesorc4a) sq4) q +POSTHOOK: type: CREATETABLE_AS_SELECT +POSTHOOK: Input: default@small_alltypesorc1a +POSTHOOK: Input: default@small_alltypesorc2a +POSTHOOK: Input: default@small_alltypesorc3a +POSTHOOK: Input: default@small_alltypesorc4a +POSTHOOK: Output: database:default +POSTHOOK: Output: default@small_alltypesorc_a +PREHOOK: query: desc formatted small_alltypesorc_a +PREHOOK: type: DESCTABLE +PREHOOK: Input: default@small_alltypesorc_a +POSTHOOK: query: desc formatted small_alltypesorc_a +POSTHOOK: type: DESCTABLE +POSTHOOK: Input: default@small_alltypesorc_a +# col_name data_type comment + +ctinyint tinyint +csmallint smallint +cint int +cbigint bigint +cfloat float +cdouble double +cstring1 string +cstring2 string +ctimestamp1 timestamp +ctimestamp2 timestamp +cboolean1 boolean +cboolean2 boolean + +# Detailed Table Information +Database: default +#### A masked pattern was here #### +Retention: 0 +#### A masked pattern was here #### +Table Type: MANAGED_TABLE +Table Parameters: + COLUMN_STATS_ACCURATE true + numFiles 4 + numRows 0 + rawDataSize 0 + totalSize 3915 +#### A masked pattern was here #### + +# Storage Information +SerDe Library: org.apache.hadoop.hive.ql.io.orc.OrcSerde +InputFormat: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat +OutputFormat: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat +Compressed: No +Num Buckets: -1 +Bucket Columns: [] +Sort Columns: [] +Storage Desc Params: + serialization.format 1 +PREHOOK: query: ANALYZE TABLE small_alltypesorc_a COMPUTE STATISTICS +PREHOOK: type: QUERY +PREHOOK: Input: default@small_alltypesorc_a +PREHOOK: Output: default@small_alltypesorc_a +POSTHOOK: query: ANALYZE TABLE small_alltypesorc_a COMPUTE STATISTICS +POSTHOOK: type: QUERY +POSTHOOK: Input: default@small_alltypesorc_a +POSTHOOK: Output: default@small_alltypesorc_a +PREHOOK: query: desc formatted small_alltypesorc_a +PREHOOK: type: DESCTABLE +PREHOOK: Input: default@small_alltypesorc_a +POSTHOOK: query: desc formatted small_alltypesorc_a +POSTHOOK: type: DESCTABLE +POSTHOOK: Input: default@small_alltypesorc_a +# col_name data_type comment + +ctinyint tinyint +csmallint smallint +cint int +cbigint bigint +cfloat float +cdouble double +cstring1 string +cstring2 string +ctimestamp1 timestamp +ctimestamp2 timestamp +cboolean1 boolean +cboolean2 boolean + +# Detailed Table Information +Database: default +#### A masked pattern was here #### +Retention: 0 +#### A masked pattern was here #### +Table Type: MANAGED_TABLE +Table Parameters: + COLUMN_STATS_ACCURATE true + numFiles 4 + numRows 15 + rawDataSize 3483 + totalSize 3915 +#### A masked pattern was here #### + +# Storage Information +SerDe Library: org.apache.hadoop.hive.ql.io.orc.OrcSerde +InputFormat: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat +OutputFormat: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat +Compressed: No +Num Buckets: -1 +Bucket Columns: [] +Sort Columns: [] +Storage Desc Params: + serialization.format 1 +PREHOOK: query: insert into table small_alltypesorc_a select * from small_alltypesorc1a +PREHOOK: type: QUERY +PREHOOK: Input: default@small_alltypesorc1a +PREHOOK: Output: default@small_alltypesorc_a +POSTHOOK: query: insert into table small_alltypesorc_a select * from small_alltypesorc1a +POSTHOOK: type: QUERY +POSTHOOK: Input: default@small_alltypesorc1a +POSTHOOK: Output: default@small_alltypesorc_a +POSTHOOK: Lineage: small_alltypesorc_a.cbigint SIMPLE [(small_alltypesorc1a)small_alltypesorc1a.FieldSchema(name:cbigint, type:bigint, comment:null), ] +POSTHOOK: Lineage: small_alltypesorc_a.cboolean1 SIMPLE [(small_alltypesorc1a)small_alltypesorc1a.FieldSchema(name:cboolean1, type:boolean, comment:null), ] +POSTHOOK: Lineage: small_alltypesorc_a.cboolean2 SIMPLE [(small_alltypesorc1a)small_alltypesorc1a.FieldSchema(name:cboolean2, type:boolean, comment:null), ] +POSTHOOK: Lineage: small_alltypesorc_a.cdouble SIMPLE [(small_alltypesorc1a)small_alltypesorc1a.FieldSchema(name:cdouble, type:double, comment:null), ] +POSTHOOK: Lineage: small_alltypesorc_a.cfloat SIMPLE [(small_alltypesorc1a)small_alltypesorc1a.FieldSchema(name:cfloat, type:float, comment:null), ] +POSTHOOK: Lineage: small_alltypesorc_a.cint SIMPLE [(small_alltypesorc1a)small_alltypesorc1a.FieldSchema(name:cint, type:int, comment:null), ] +POSTHOOK: Lineage: small_alltypesorc_a.csmallint SIMPLE [(small_alltypesorc1a)small_alltypesorc1a.FieldSchema(name:csmallint, type:smallint, comment:null), ] +POSTHOOK: Lineage: small_alltypesorc_a.cstring1 SIMPLE [(small_alltypesorc1a)small_alltypesorc1a.FieldSchema(name:cstring1, type:string, comment:null), ] +POSTHOOK: Lineage: small_alltypesorc_a.cstring2 SIMPLE [(small_alltypesorc1a)small_alltypesorc1a.FieldSchema(name:cstring2, type:string, comment:null), ] +POSTHOOK: Lineage: small_alltypesorc_a.ctimestamp1 SIMPLE [(small_alltypesorc1a)small_alltypesorc1a.FieldSchema(name:ctimestamp1, type:timestamp, comment:null), ] +POSTHOOK: Lineage: small_alltypesorc_a.ctimestamp2 SIMPLE [(small_alltypesorc1a)small_alltypesorc1a.FieldSchema(name:ctimestamp2, type:timestamp, comment:null), ] +POSTHOOK: Lineage: small_alltypesorc_a.ctinyint SIMPLE [(small_alltypesorc1a)small_alltypesorc1a.FieldSchema(name:ctinyint, type:tinyint, comment:null), ] +PREHOOK: query: desc formatted small_alltypesorc_a +PREHOOK: type: DESCTABLE +PREHOOK: Input: default@small_alltypesorc_a +POSTHOOK: query: desc formatted small_alltypesorc_a +POSTHOOK: type: DESCTABLE +POSTHOOK: Input: default@small_alltypesorc_a +# col_name data_type comment + +ctinyint tinyint +csmallint smallint +cint int +cbigint bigint +cfloat float +cdouble double +cstring1 string +cstring2 string +ctimestamp1 timestamp +ctimestamp2 timestamp +cboolean1 boolean +cboolean2 boolean + +# Detailed Table Information +Database: default +#### A masked pattern was here #### +Retention: 0 +#### A masked pattern was here #### +Table Type: MANAGED_TABLE +Table Parameters: + COLUMN_STATS_ACCURATE true + numFiles 5 + numRows 20 + rawDataSize 4552 + totalSize 5225 +#### A masked pattern was here #### + +# Storage Information +SerDe Library: org.apache.hadoop.hive.ql.io.orc.OrcSerde +InputFormat: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat +OutputFormat: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat +Compressed: No +Num Buckets: -1 +Bucket Columns: [] +Sort Columns: [] +Storage Desc Params: + serialization.format 1 +PREHOOK: query: drop table small_alltypesorc1a +PREHOOK: type: DROPTABLE +PREHOOK: Input: default@small_alltypesorc1a +PREHOOK: Output: default@small_alltypesorc1a +POSTHOOK: query: drop table small_alltypesorc1a +POSTHOOK: type: DROPTABLE +POSTHOOK: Input: default@small_alltypesorc1a +POSTHOOK: Output: default@small_alltypesorc1a +PREHOOK: query: drop table small_alltypesorc2a +PREHOOK: type: DROPTABLE +PREHOOK: Input: default@small_alltypesorc2a +PREHOOK: Output: default@small_alltypesorc2a +POSTHOOK: query: drop table small_alltypesorc2a +POSTHOOK: type: DROPTABLE +POSTHOOK: Input: default@small_alltypesorc2a +POSTHOOK: Output: default@small_alltypesorc2a +PREHOOK: query: drop table small_alltypesorc3a +PREHOOK: type: DROPTABLE +PREHOOK: Input: default@small_alltypesorc3a +PREHOOK: Output: default@small_alltypesorc3a +POSTHOOK: query: drop table small_alltypesorc3a +POSTHOOK: type: DROPTABLE +POSTHOOK: Input: default@small_alltypesorc3a +POSTHOOK: Output: default@small_alltypesorc3a +PREHOOK: query: drop table small_alltypesorc4a +PREHOOK: type: DROPTABLE +PREHOOK: Input: default@small_alltypesorc4a +PREHOOK: Output: default@small_alltypesorc4a +POSTHOOK: query: drop table small_alltypesorc4a +POSTHOOK: type: DROPTABLE +POSTHOOK: Input: default@small_alltypesorc4a +POSTHOOK: Output: default@small_alltypesorc4a +PREHOOK: query: drop table small_alltypesorc_a +PREHOOK: type: DROPTABLE +PREHOOK: Input: default@small_alltypesorc_a +PREHOOK: Output: default@small_alltypesorc_a +POSTHOOK: query: drop table small_alltypesorc_a +POSTHOOK: type: DROPTABLE +POSTHOOK: Input: default@small_alltypesorc_a +POSTHOOK: Output: default@small_alltypesorc_a +PREHOOK: query: create table small_alltypesorc1a as select * from alltypesorc where cint is not null and ctinyint is not null order by ctinyint, csmallint, cint, cbigint, cfloat, cdouble, cstring1, cstring2, ctimestamp1, ctimestamp2, cboolean1, cboolean2 limit 5 +PREHOOK: type: CREATETABLE_AS_SELECT +PREHOOK: Input: default@alltypesorc +PREHOOK: Output: database:default +PREHOOK: Output: default@small_alltypesorc1a +POSTHOOK: query: create table small_alltypesorc1a as select * from alltypesorc where cint is not null and ctinyint is not null order by ctinyint, csmallint, cint, cbigint, cfloat, cdouble, cstring1, cstring2, ctimestamp1, ctimestamp2, cboolean1, cboolean2 limit 5 +POSTHOOK: type: CREATETABLE_AS_SELECT +POSTHOOK: Input: default@alltypesorc +POSTHOOK: Output: database:default +POSTHOOK: Output: default@small_alltypesorc1a +PREHOOK: query: create table small_alltypesorc2a as select * from alltypesorc where cint is null and ctinyint is not null order by ctinyint, csmallint, cint, cbigint, cfloat, cdouble, cstring1, cstring2, ctimestamp1, ctimestamp2, cboolean1, cboolean2 limit 5 +PREHOOK: type: CREATETABLE_AS_SELECT +PREHOOK: Input: default@alltypesorc +PREHOOK: Output: database:default +PREHOOK: Output: default@small_alltypesorc2a +POSTHOOK: query: create table small_alltypesorc2a as select * from alltypesorc where cint is null and ctinyint is not null order by ctinyint, csmallint, cint, cbigint, cfloat, cdouble, cstring1, cstring2, ctimestamp1, ctimestamp2, cboolean1, cboolean2 limit 5 +POSTHOOK: type: CREATETABLE_AS_SELECT +POSTHOOK: Input: default@alltypesorc +POSTHOOK: Output: database:default +POSTHOOK: Output: default@small_alltypesorc2a +PREHOOK: query: create table small_alltypesorc3a as select * from alltypesorc where cint is not null and ctinyint is null order by ctinyint, csmallint, cint, cbigint, cfloat, cdouble, cstring1, cstring2, ctimestamp1, ctimestamp2, cboolean1, cboolean2 limit 5 +PREHOOK: type: CREATETABLE_AS_SELECT +PREHOOK: Input: default@alltypesorc +PREHOOK: Output: database:default +PREHOOK: Output: default@small_alltypesorc3a +POSTHOOK: query: create table small_alltypesorc3a as select * from alltypesorc where cint is not null and ctinyint is null order by ctinyint, csmallint, cint, cbigint, cfloat, cdouble, cstring1, cstring2, ctimestamp1, ctimestamp2, cboolean1, cboolean2 limit 5 +POSTHOOK: type: CREATETABLE_AS_SELECT +POSTHOOK: Input: default@alltypesorc +POSTHOOK: Output: database:default +POSTHOOK: Output: default@small_alltypesorc3a +PREHOOK: query: create table small_alltypesorc4a as select * from alltypesorc where cint is null and ctinyint is null order by ctinyint, csmallint, cint, cbigint, cfloat, cdouble, cstring1, cstring2, ctimestamp1, ctimestamp2, cboolean1, cboolean2 limit 5 +PREHOOK: type: CREATETABLE_AS_SELECT +PREHOOK: Input: default@alltypesorc +PREHOOK: Output: database:default +PREHOOK: Output: default@small_alltypesorc4a +POSTHOOK: query: create table small_alltypesorc4a as select * from alltypesorc where cint is null and ctinyint is null order by ctinyint, csmallint, cint, cbigint, cfloat, cdouble, cstring1, cstring2, ctimestamp1, ctimestamp2, cboolean1, cboolean2 limit 5 +POSTHOOK: type: CREATETABLE_AS_SELECT +POSTHOOK: Input: default@alltypesorc +POSTHOOK: Output: database:default +POSTHOOK: Output: default@small_alltypesorc4a +PREHOOK: query: create table small_alltypesorc_a stored as orc as select * from +(select * from (select * from small_alltypesorc1a) sq1 + union all + select * from (select * from small_alltypesorc2a) sq2 + union all + select * from (select * from small_alltypesorc3a) sq3 + union all + select * from (select * from small_alltypesorc4a) sq4) q +PREHOOK: type: CREATETABLE_AS_SELECT +PREHOOK: Input: default@small_alltypesorc1a +PREHOOK: Input: default@small_alltypesorc2a +PREHOOK: Input: default@small_alltypesorc3a +PREHOOK: Input: default@small_alltypesorc4a +PREHOOK: Output: database:default +PREHOOK: Output: default@small_alltypesorc_a +POSTHOOK: query: create table small_alltypesorc_a stored as orc as select * from +(select * from (select * from small_alltypesorc1a) sq1 + union all + select * from (select * from small_alltypesorc2a) sq2 + union all + select * from (select * from small_alltypesorc3a) sq3 + union all + select * from (select * from small_alltypesorc4a) sq4) q +POSTHOOK: type: CREATETABLE_AS_SELECT +POSTHOOK: Input: default@small_alltypesorc1a +POSTHOOK: Input: default@small_alltypesorc2a +POSTHOOK: Input: default@small_alltypesorc3a +POSTHOOK: Input: default@small_alltypesorc4a +POSTHOOK: Output: database:default +POSTHOOK: Output: default@small_alltypesorc_a +PREHOOK: query: desc formatted small_alltypesorc_a +PREHOOK: type: DESCTABLE +PREHOOK: Input: default@small_alltypesorc_a +POSTHOOK: query: desc formatted small_alltypesorc_a +POSTHOOK: type: DESCTABLE +POSTHOOK: Input: default@small_alltypesorc_a +# col_name data_type comment + +ctinyint tinyint +csmallint smallint +cint int +cbigint bigint +cfloat float +cdouble double +cstring1 string +cstring2 string +ctimestamp1 timestamp +ctimestamp2 timestamp +cboolean1 boolean +cboolean2 boolean + +# Detailed Table Information +Database: default +#### A masked pattern was here #### +Retention: 0 +#### A masked pattern was here #### +Table Type: MANAGED_TABLE +Table Parameters: + COLUMN_STATS_ACCURATE true + numFiles 1 + numRows 5 + rawDataSize 1069 + totalSize 3177 +#### A masked pattern was here #### + +# Storage Information +SerDe Library: org.apache.hadoop.hive.ql.io.orc.OrcSerde +InputFormat: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat +OutputFormat: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat +Compressed: No +Num Buckets: -1 +Bucket Columns: [] +Sort Columns: [] +Storage Desc Params: + serialization.format 1 +PREHOOK: query: ANALYZE TABLE small_alltypesorc_a COMPUTE STATISTICS +PREHOOK: type: QUERY +PREHOOK: Input: default@small_alltypesorc_a +PREHOOK: Output: default@small_alltypesorc_a +POSTHOOK: query: ANALYZE TABLE small_alltypesorc_a COMPUTE STATISTICS +POSTHOOK: type: QUERY +POSTHOOK: Input: default@small_alltypesorc_a +POSTHOOK: Output: default@small_alltypesorc_a +PREHOOK: query: desc formatted small_alltypesorc_a +PREHOOK: type: DESCTABLE +PREHOOK: Input: default@small_alltypesorc_a +POSTHOOK: query: desc formatted small_alltypesorc_a +POSTHOOK: type: DESCTABLE +POSTHOOK: Input: default@small_alltypesorc_a +# col_name data_type comment + +ctinyint tinyint +csmallint smallint +cint int +cbigint bigint +cfloat float +cdouble double +cstring1 string +cstring2 string +ctimestamp1 timestamp +ctimestamp2 timestamp +cboolean1 boolean +cboolean2 boolean + +# Detailed Table Information +Database: default +#### A masked pattern was here #### +Retention: 0 +#### A masked pattern was here #### +Table Type: MANAGED_TABLE +Table Parameters: + COLUMN_STATS_ACCURATE true + numFiles 1 + numRows 15 + rawDataSize 3320 + totalSize 3177 +#### A masked pattern was here #### + +# Storage Information +SerDe Library: org.apache.hadoop.hive.ql.io.orc.OrcSerde +InputFormat: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat +OutputFormat: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat +Compressed: No +Num Buckets: -1 +Bucket Columns: [] +Sort Columns: [] +Storage Desc Params: + serialization.format 1 +PREHOOK: query: insert into table small_alltypesorc_a select * from small_alltypesorc1a +PREHOOK: type: QUERY +PREHOOK: Input: default@small_alltypesorc1a +PREHOOK: Output: default@small_alltypesorc_a +POSTHOOK: query: insert into table small_alltypesorc_a select * from small_alltypesorc1a +POSTHOOK: type: QUERY +POSTHOOK: Input: default@small_alltypesorc1a +POSTHOOK: Output: default@small_alltypesorc_a +POSTHOOK: Lineage: small_alltypesorc_a.cbigint SIMPLE [(small_alltypesorc1a)small_alltypesorc1a.FieldSchema(name:cbigint, type:bigint, comment:null), ] +POSTHOOK: Lineage: small_alltypesorc_a.cboolean1 SIMPLE [(small_alltypesorc1a)small_alltypesorc1a.FieldSchema(name:cboolean1, type:boolean, comment:null), ] +POSTHOOK: Lineage: small_alltypesorc_a.cboolean2 SIMPLE [(small_alltypesorc1a)small_alltypesorc1a.FieldSchema(name:cboolean2, type:boolean, comment:null), ] +POSTHOOK: Lineage: small_alltypesorc_a.cdouble SIMPLE [(small_alltypesorc1a)small_alltypesorc1a.FieldSchema(name:cdouble, type:double, comment:null), ] +POSTHOOK: Lineage: small_alltypesorc_a.cfloat SIMPLE [(small_alltypesorc1a)small_alltypesorc1a.FieldSchema(name:cfloat, type:float, comment:null), ] +POSTHOOK: Lineage: small_alltypesorc_a.cint SIMPLE [(small_alltypesorc1a)small_alltypesorc1a.FieldSchema(name:cint, type:int, comment:null), ] +POSTHOOK: Lineage: small_alltypesorc_a.csmallint SIMPLE [(small_alltypesorc1a)small_alltypesorc1a.FieldSchema(name:csmallint, type:smallint, comment:null), ] +POSTHOOK: Lineage: small_alltypesorc_a.cstring1 SIMPLE [(small_alltypesorc1a)small_alltypesorc1a.FieldSchema(name:cstring1, type:string, comment:null), ] +POSTHOOK: Lineage: small_alltypesorc_a.cstring2 SIMPLE [(small_alltypesorc1a)small_alltypesorc1a.FieldSchema(name:cstring2, type:string, comment:null), ] +POSTHOOK: Lineage: small_alltypesorc_a.ctimestamp1 SIMPLE [(small_alltypesorc1a)small_alltypesorc1a.FieldSchema(name:ctimestamp1, type:timestamp, comment:null), ] +POSTHOOK: Lineage: small_alltypesorc_a.ctimestamp2 SIMPLE [(small_alltypesorc1a)small_alltypesorc1a.FieldSchema(name:ctimestamp2, type:timestamp, comment:null), ] +POSTHOOK: Lineage: small_alltypesorc_a.ctinyint SIMPLE [(small_alltypesorc1a)small_alltypesorc1a.FieldSchema(name:ctinyint, type:tinyint, comment:null), ] +PREHOOK: query: desc formatted small_alltypesorc_a +PREHOOK: type: DESCTABLE +PREHOOK: Input: default@small_alltypesorc_a +POSTHOOK: query: desc formatted small_alltypesorc_a +POSTHOOK: type: DESCTABLE +POSTHOOK: Input: default@small_alltypesorc_a +# col_name data_type comment + +ctinyint tinyint +csmallint smallint +cint int +cbigint bigint +cfloat float +cdouble double +cstring1 string +cstring2 string +ctimestamp1 timestamp +ctimestamp2 timestamp +cboolean1 boolean +cboolean2 boolean + +# Detailed Table Information +Database: default +#### A masked pattern was here #### +Retention: 0 +#### A masked pattern was here #### +Table Type: MANAGED_TABLE +Table Parameters: + COLUMN_STATS_ACCURATE true + numFiles 2 + numRows 20 + rawDataSize 4389 + totalSize 4487 +#### A masked pattern was here #### + +# Storage Information +SerDe Library: org.apache.hadoop.hive.ql.io.orc.OrcSerde +InputFormat: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat +OutputFormat: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat +Compressed: No +Num Buckets: -1 +Bucket Columns: [] +Sort Columns: [] +Storage Desc Params: + serialization.format 1 diff --git a/ql/src/test/results/clientpositive/llap/vector_aggregate_9.q.out b/ql/src/test/results/clientpositive/llap/vector_aggregate_9.q.out index 3624854..c086bcb 100644 --- a/ql/src/test/results/clientpositive/llap/vector_aggregate_9.q.out +++ b/ql/src/test/results/clientpositive/llap/vector_aggregate_9.q.out @@ -125,10 +125,10 @@ STAGE PLANS: Statistics: Num rows: 2000 Data size: 918712 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: dc (type: decimal(38,18)) - outputColumnNames: _col0 + outputColumnNames: dc Statistics: Num rows: 2000 Data size: 918712 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: min(_col0), max(_col0), sum(_col0), avg(_col0) + aggregations: min(dc), max(dc), sum(dc), avg(dc) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 1 Data size: 336 Basic stats: COMPLETE Column stats: NONE diff --git a/ql/src/test/results/clientpositive/llap/vector_binary_join_groupby.q.out b/ql/src/test/results/clientpositive/llap/vector_binary_join_groupby.q.out index 5671343..acf7149 100644 --- a/ql/src/test/results/clientpositive/llap/vector_binary_join_groupby.q.out +++ b/ql/src/test/results/clientpositive/llap/vector_binary_join_groupby.q.out @@ -223,11 +223,11 @@ STAGE PLANS: Statistics: Num rows: 100 Data size: 29638 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: bin (type: binary) - outputColumnNames: _col0 + outputColumnNames: bin Statistics: Num rows: 100 Data size: 29638 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() - keys: _col0 (type: binary) + keys: bin (type: binary) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 100 Data size: 29638 Basic stats: COMPLETE Column stats: NONE diff --git a/ql/src/test/results/clientpositive/llap/vector_char_cast.q.out b/ql/src/test/results/clientpositive/llap/vector_char_cast.q.out new file mode 100644 index 0000000..dbeae74 --- /dev/null +++ b/ql/src/test/results/clientpositive/llap/vector_char_cast.q.out @@ -0,0 +1,35 @@ +PREHOOK: query: create table s1(id smallint) stored as orc +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@s1 +POSTHOOK: query: create table s1(id smallint) stored as orc +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@s1 +PREHOOK: query: insert into table s1 values (1000),(1001),(1002),(1003),(1000) +PREHOOK: type: QUERY +PREHOOK: Input: default@values__tmp__table__1 +PREHOOK: Output: default@s1 +POSTHOOK: query: insert into table s1 values (1000),(1001),(1002),(1003),(1000) +POSTHOOK: type: QUERY +POSTHOOK: Input: default@values__tmp__table__1 +POSTHOOK: Output: default@s1 +POSTHOOK: Lineage: s1.id EXPRESSION [(values__tmp__table__1)values__tmp__table__1.FieldSchema(name:tmp_values_col1, type:string, comment:), ] +PREHOOK: query: select count(1) from s1 where cast(id as char(4))='1000' +PREHOOK: type: QUERY +PREHOOK: Input: default@s1 +#### A masked pattern was here #### +POSTHOOK: query: select count(1) from s1 where cast(id as char(4))='1000' +POSTHOOK: type: QUERY +POSTHOOK: Input: default@s1 +#### A masked pattern was here #### +2 +PREHOOK: query: select count(1) from s1 where cast(id as char(4))='1000' +PREHOOK: type: QUERY +PREHOOK: Input: default@s1 +#### A masked pattern was here #### +POSTHOOK: query: select count(1) from s1 where cast(id as char(4))='1000' +POSTHOOK: type: QUERY +POSTHOOK: Input: default@s1 +#### A masked pattern was here #### +2 diff --git a/ql/src/test/results/clientpositive/llap/vector_count_distinct.q.out b/ql/src/test/results/clientpositive/llap/vector_count_distinct.q.out index c8f9c2c..95c2bc5 100644 --- a/ql/src/test/results/clientpositive/llap/vector_count_distinct.q.out +++ b/ql/src/test/results/clientpositive/llap/vector_count_distinct.q.out @@ -1258,10 +1258,10 @@ STAGE PLANS: Statistics: Num rows: 2000 Data size: 3504000 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ws_order_number (type: int) - outputColumnNames: _col0 + outputColumnNames: ws_order_number Statistics: Num rows: 2000 Data size: 3504000 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: _col0 (type: int) + keys: ws_order_number (type: int) mode: hash outputColumnNames: _col0 Statistics: Num rows: 2000 Data size: 3504000 Basic stats: COMPLETE Column stats: NONE diff --git a/ql/src/test/results/clientpositive/llap/vector_decimal_aggregate.q.out b/ql/src/test/results/clientpositive/llap/vector_decimal_aggregate.q.out index c0df9ab..8bcac50 100644 --- a/ql/src/test/results/clientpositive/llap/vector_decimal_aggregate.q.out +++ b/ql/src/test/results/clientpositive/llap/vector_decimal_aggregate.q.out @@ -54,11 +54,11 @@ STAGE PLANS: Statistics: Num rows: 12288 Data size: 2165060 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cint (type: int), cdecimal1 (type: decimal(20,10)), cdecimal2 (type: decimal(23,14)) - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: cint, cdecimal1, cdecimal2 Statistics: Num rows: 12288 Data size: 2165060 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(_col1), max(_col1), min(_col1), sum(_col1), count(_col2), max(_col2), min(_col2), sum(_col2), count() - keys: _col0 (type: int) + aggregations: count(cdecimal1), max(cdecimal1), min(cdecimal1), sum(cdecimal1), count(cdecimal2), max(cdecimal2), min(cdecimal2), sum(cdecimal2), count() + keys: cint (type: int) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9 Statistics: Num rows: 12288 Data size: 2165060 Basic stats: COMPLETE Column stats: NONE @@ -159,11 +159,11 @@ STAGE PLANS: Statistics: Num rows: 12288 Data size: 2165060 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cint (type: int), cdecimal1 (type: decimal(20,10)), cdecimal2 (type: decimal(23,14)) - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: cint, cdecimal1, cdecimal2 Statistics: Num rows: 12288 Data size: 2165060 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(_col1), max(_col1), min(_col1), sum(_col1), avg(_col1), stddev_pop(_col1), stddev_samp(_col1), count(_col2), max(_col2), min(_col2), sum(_col2), avg(_col2), stddev_pop(_col2), stddev_samp(_col2), count() - keys: _col0 (type: int) + aggregations: count(cdecimal1), max(cdecimal1), min(cdecimal1), sum(cdecimal1), avg(cdecimal1), stddev_pop(cdecimal1), stddev_samp(cdecimal1), count(cdecimal2), max(cdecimal2), min(cdecimal2), sum(cdecimal2), avg(cdecimal2), stddev_pop(cdecimal2), stddev_samp(cdecimal2), count() + keys: cint (type: int) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15 Statistics: Num rows: 12288 Data size: 2165060 Basic stats: COMPLETE Column stats: NONE diff --git a/ql/src/test/results/clientpositive/llap/vector_decimal_precision.q.out b/ql/src/test/results/clientpositive/llap/vector_decimal_precision.q.out index 2cf76a3..4287a73 100644 --- a/ql/src/test/results/clientpositive/llap/vector_decimal_precision.q.out +++ b/ql/src/test/results/clientpositive/llap/vector_decimal_precision.q.out @@ -567,10 +567,10 @@ STAGE PLANS: Statistics: Num rows: 75 Data size: 3472 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: dec (type: decimal(20,10)) - outputColumnNames: _col0 + outputColumnNames: dec Statistics: Num rows: 75 Data size: 3472 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: avg(_col0), sum(_col0) + aggregations: avg(dec), sum(dec) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE diff --git a/ql/src/test/results/clientpositive/llap/vector_decimal_udf.q.out b/ql/src/test/results/clientpositive/llap/vector_decimal_udf.q.out index 15957e6..66303c3 100644 --- a/ql/src/test/results/clientpositive/llap/vector_decimal_udf.q.out +++ b/ql/src/test/results/clientpositive/llap/vector_decimal_udf.q.out @@ -1640,11 +1640,11 @@ STAGE PLANS: Statistics: Num rows: 38 Data size: 4296 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: value (type: int), key (type: decimal(20,10)) - outputColumnNames: _col0, _col1 + outputColumnNames: value, key Statistics: Num rows: 38 Data size: 4296 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(_col1), count(_col1), avg(_col1) - keys: _col0 (type: int) + aggregations: sum(key), count(key), avg(key) + keys: value (type: int) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 38 Data size: 4296 Basic stats: COMPLETE Column stats: NONE @@ -2320,11 +2320,11 @@ STAGE PLANS: Statistics: Num rows: 38 Data size: 4296 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: value (type: int), key (type: decimal(20,10)) - outputColumnNames: _col0, _col1 + outputColumnNames: value, key Statistics: Num rows: 38 Data size: 4296 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: stddev(_col1), variance(_col1) - keys: _col0 (type: int) + aggregations: stddev(key), variance(key) + keys: value (type: int) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 38 Data size: 4296 Basic stats: COMPLETE Column stats: NONE @@ -2407,11 +2407,11 @@ STAGE PLANS: Statistics: Num rows: 38 Data size: 4296 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: value (type: int), key (type: decimal(20,10)) - outputColumnNames: _col0, _col1 + outputColumnNames: value, key Statistics: Num rows: 38 Data size: 4296 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: stddev_samp(_col1), var_samp(_col1) - keys: _col0 (type: int) + aggregations: stddev_samp(key), var_samp(key) + keys: value (type: int) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 38 Data size: 4296 Basic stats: COMPLETE Column stats: NONE @@ -2561,10 +2561,10 @@ STAGE PLANS: Statistics: Num rows: 38 Data size: 4296 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: decimal(20,10)) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 38 Data size: 4296 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: min(_col0) + aggregations: min(key) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE @@ -2628,10 +2628,10 @@ STAGE PLANS: Statistics: Num rows: 38 Data size: 4296 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: decimal(20,10)) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 38 Data size: 4296 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: max(_col0) + aggregations: max(key) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE @@ -2695,10 +2695,10 @@ STAGE PLANS: Statistics: Num rows: 38 Data size: 4296 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: decimal(20,10)) - outputColumnNames: _col0 + outputColumnNames: key Statistics: Num rows: 38 Data size: 4296 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(_col0) + aggregations: count(key) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE diff --git a/ql/src/test/results/clientpositive/llap/vector_distinct_2.q.out b/ql/src/test/results/clientpositive/llap/vector_distinct_2.q.out index 3b8e5cd..4a758cb 100644 --- a/ql/src/test/results/clientpositive/llap/vector_distinct_2.q.out +++ b/ql/src/test/results/clientpositive/llap/vector_distinct_2.q.out @@ -128,35 +128,39 @@ STAGE PLANS: alias: vectortab2korc Statistics: Num rows: 2000 Data size: 918712 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: s (type: string), t (type: tinyint) - outputColumnNames: _col0, _col1 + expressions: t (type: tinyint), s (type: string) + outputColumnNames: t, s Statistics: Num rows: 2000 Data size: 918712 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: _col0 (type: string), _col1 (type: tinyint) + keys: t (type: tinyint), s (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 2000 Data size: 918712 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: tinyint) + key expressions: _col0 (type: tinyint), _col1 (type: string) sort order: ++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: tinyint) + Map-reduce partition columns: _col0 (type: tinyint), _col1 (type: string) Statistics: Num rows: 2000 Data size: 918712 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized, llap Reducer 2 Execution mode: vectorized, uber Reduce Operator Tree: Group By Operator - keys: KEY._col0 (type: string), KEY._col1 (type: tinyint) + keys: KEY._col0 (type: tinyint), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 Statistics: Num rows: 1000 Data size: 459356 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col1 (type: string), _col0 (type: tinyint) + outputColumnNames: _col0, _col1 Statistics: Num rows: 1000 Data size: 459356 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 1000 Data size: 459356 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/llap/vector_groupby_3.q.out b/ql/src/test/results/clientpositive/llap/vector_groupby_3.q.out index 93c5ce1..7c34c09 100644 --- a/ql/src/test/results/clientpositive/llap/vector_groupby_3.q.out +++ b/ql/src/test/results/clientpositive/llap/vector_groupby_3.q.out @@ -128,19 +128,19 @@ STAGE PLANS: alias: vectortab2korc Statistics: Num rows: 2000 Data size: 918712 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: s (type: string), t (type: tinyint), b (type: bigint) - outputColumnNames: _col0, _col1, _col2 + expressions: t (type: tinyint), s (type: string), b (type: bigint) + outputColumnNames: t, s, b Statistics: Num rows: 2000 Data size: 918712 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: max(_col2) - keys: _col0 (type: string), _col1 (type: tinyint) + aggregations: max(b) + keys: t (type: tinyint), s (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 2000 Data size: 918712 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: tinyint) + key expressions: _col0 (type: tinyint), _col1 (type: string) sort order: ++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: tinyint) + Map-reduce partition columns: _col0 (type: tinyint), _col1 (type: string) Statistics: Num rows: 2000 Data size: 918712 Basic stats: COMPLETE Column stats: NONE value expressions: _col2 (type: bigint) Execution mode: vectorized, llap @@ -149,17 +149,21 @@ STAGE PLANS: Reduce Operator Tree: Group By Operator aggregations: max(VALUE._col0) - keys: KEY._col0 (type: string), KEY._col1 (type: tinyint) + keys: KEY._col0 (type: tinyint), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 1000 Data size: 459356 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col1 (type: string), _col0 (type: tinyint), _col2 (type: bigint) + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 1000 Data size: 459356 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + File Output Operator + compressed: false + Statistics: Num rows: 1000 Data size: 459356 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/llap/vector_groupby_reduce.q.out b/ql/src/test/results/clientpositive/llap/vector_groupby_reduce.q.out index c344a97..9a8379a 100644 --- a/ql/src/test/results/clientpositive/llap/vector_groupby_reduce.q.out +++ b/ql/src/test/results/clientpositive/llap/vector_groupby_reduce.q.out @@ -245,10 +245,10 @@ STAGE PLANS: Statistics: Num rows: 1000 Data size: 88276 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ss_ticket_number (type: int) - outputColumnNames: _col0 + outputColumnNames: ss_ticket_number Statistics: Num rows: 1000 Data size: 88276 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: _col0 (type: int) + keys: ss_ticket_number (type: int) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1000 Data size: 88276 Basic stats: COMPLETE Column stats: NONE @@ -369,10 +369,10 @@ STAGE PLANS: Statistics: Num rows: 1000 Data size: 88276 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ss_ticket_number (type: int) - outputColumnNames: _col0 + outputColumnNames: ss_ticket_number Statistics: Num rows: 1000 Data size: 88276 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: _col0 (type: int) + keys: ss_ticket_number (type: int) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1000 Data size: 88276 Basic stats: COMPLETE Column stats: NONE diff --git a/ql/src/test/results/clientpositive/llap/vector_grouping_sets.q.out b/ql/src/test/results/clientpositive/llap/vector_grouping_sets.q.out index d092c92..81fc754 100644 --- a/ql/src/test/results/clientpositive/llap/vector_grouping_sets.q.out +++ b/ql/src/test/results/clientpositive/llap/vector_grouping_sets.q.out @@ -126,10 +126,10 @@ STAGE PLANS: Statistics: Num rows: 12 Data size: 25632 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: s_store_id (type: string) - outputColumnNames: _col0 + outputColumnNames: s_store_id Statistics: Num rows: 12 Data size: 25632 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: _col0 (type: string), '0' (type: string) + keys: s_store_id (type: string), '0' (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 24 Data size: 51264 Basic stats: COMPLETE Column stats: NONE @@ -209,10 +209,10 @@ STAGE PLANS: Statistics: Num rows: 12 Data size: 25632 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: s_store_id (type: string) - outputColumnNames: _col0 + outputColumnNames: s_store_id Statistics: Num rows: 12 Data size: 25632 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: _col0 (type: string), '0' (type: string) + keys: s_store_id (type: string), '0' (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 24 Data size: 51264 Basic stats: COMPLETE Column stats: NONE diff --git a/ql/src/test/results/clientpositive/llap/vector_mapjoin_reduce.q.out b/ql/src/test/results/clientpositive/llap/vector_mapjoin_reduce.q.out index 4770f53..e4946aa 100644 --- a/ql/src/test/results/clientpositive/llap/vector_mapjoin_reduce.q.out +++ b/ql/src/test/results/clientpositive/llap/vector_mapjoin_reduce.q.out @@ -111,20 +111,16 @@ STAGE PLANS: Filter Operator predicate: l_partkey is not null (type: boolean) Statistics: Num rows: 50 Data size: 5999 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: l_partkey (type: int) + Group By Operator + keys: l_partkey (type: int) + mode: hash outputColumnNames: _col0 Statistics: Num rows: 50 Data size: 5999 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: int) - mode: hash - outputColumnNames: _col0 + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) Statistics: Num rows: 50 Data size: 5999 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: 50 Data size: 5999 Basic stats: COMPLETE Column stats: NONE Execution mode: llap Reducer 4 Execution mode: vectorized, llap @@ -257,20 +253,16 @@ STAGE PLANS: Filter Operator predicate: l_partkey is not null (type: boolean) Statistics: Num rows: 50 Data size: 5999 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: l_partkey (type: int) + Group By Operator + keys: l_partkey (type: int) + mode: hash outputColumnNames: _col0 Statistics: Num rows: 50 Data size: 5999 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: int) - mode: hash - outputColumnNames: _col0 + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) Statistics: Num rows: 50 Data size: 5999 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: 50 Data size: 5999 Basic stats: COMPLETE Column stats: NONE Execution mode: llap Reducer 4 Execution mode: vectorized, uber diff --git a/ql/src/test/results/clientpositive/llap/vector_orderby_5.q.out b/ql/src/test/results/clientpositive/llap/vector_orderby_5.q.out index 4c79485..4ff8e99 100644 --- a/ql/src/test/results/clientpositive/llap/vector_orderby_5.q.out +++ b/ql/src/test/results/clientpositive/llap/vector_orderby_5.q.out @@ -126,11 +126,11 @@ STAGE PLANS: Statistics: Num rows: 2000 Data size: 918712 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: bo (type: boolean), b (type: bigint) - outputColumnNames: _col0, _col1 + outputColumnNames: bo, b Statistics: Num rows: 2000 Data size: 918712 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: max(_col1) - keys: _col0 (type: boolean) + aggregations: max(b) + keys: bo (type: boolean) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 2000 Data size: 918712 Basic stats: COMPLETE Column stats: NONE diff --git a/ql/src/test/results/clientpositive/llap/vector_outer_join2.q.out b/ql/src/test/results/clientpositive/llap/vector_outer_join2.q.out index 448c1cc..6904db2 100644 --- a/ql/src/test/results/clientpositive/llap/vector_outer_join2.q.out +++ b/ql/src/test/results/clientpositive/llap/vector_outer_join2.q.out @@ -227,19 +227,15 @@ STAGE PLANS: 1 Map 4 Statistics: Num rows: 24 Data size: 5361 Basic stats: COMPLETE Column stats: NONE HybridGraceHashJoin: true - Select Operator - expressions: _col1 (type: bigint) - outputColumnNames: _col0 - Statistics: Num rows: 24 Data size: 5361 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(), sum(_col0) - mode: hash - outputColumnNames: _col0, _col1 + Group By Operator + aggregations: count(), sum(_col1) + mode: hash + 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 - 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: _col0 (type: bigint), _col1 (type: bigint) Execution mode: vectorized, llap Map 3 Map Operator Tree: diff --git a/ql/src/test/results/clientpositive/llap/vector_partition_diff_num_cols.q.out b/ql/src/test/results/clientpositive/llap/vector_partition_diff_num_cols.q.out index 230aba2..dd519fe 100644 --- a/ql/src/test/results/clientpositive/llap/vector_partition_diff_num_cols.q.out +++ b/ql/src/test/results/clientpositive/llap/vector_partition_diff_num_cols.q.out @@ -100,10 +100,10 @@ STAGE PLANS: Statistics: Num rows: 200 Data size: 3176 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: inv_quantity_on_hand (type: int) - outputColumnNames: _col0 + outputColumnNames: inv_quantity_on_hand Statistics: Num rows: 200 Data size: 3176 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(_col0) + aggregations: sum(inv_quantity_on_hand) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -226,10 +226,10 @@ STAGE PLANS: Statistics: Num rows: 200 Data size: 11876 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: inv_quantity_on_hand (type: int) - outputColumnNames: _col0 + outputColumnNames: inv_quantity_on_hand Statistics: Num rows: 200 Data size: 11876 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(_col0) + aggregations: sum(inv_quantity_on_hand) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -354,10 +354,10 @@ STAGE PLANS: Statistics: Num rows: 200 Data size: 3176 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: inv_quantity_on_hand (type: int) - outputColumnNames: _col0 + outputColumnNames: inv_quantity_on_hand Statistics: Num rows: 200 Data size: 3176 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(_col0) + aggregations: sum(inv_quantity_on_hand) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -463,10 +463,10 @@ STAGE PLANS: Statistics: Num rows: 200 Data size: 3176 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: inv_quantity_on_hand (type: int) - outputColumnNames: _col0 + outputColumnNames: inv_quantity_on_hand Statistics: Num rows: 200 Data size: 3176 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(_col0) + aggregations: sum(inv_quantity_on_hand) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -578,10 +578,10 @@ STAGE PLANS: Statistics: Num rows: 200 Data size: 3176 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: inv_quantity_on_hand (type: int) - outputColumnNames: _col0 + outputColumnNames: inv_quantity_on_hand Statistics: Num rows: 200 Data size: 3176 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(_col0) + aggregations: sum(inv_quantity_on_hand) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE diff --git a/ql/src/test/results/clientpositive/llap/vector_partitioned_date_time.q.out b/ql/src/test/results/clientpositive/llap/vector_partitioned_date_time.q.out index 87d75c2..a79aa17 100644 --- a/ql/src/test/results/clientpositive/llap/vector_partitioned_date_time.q.out +++ b/ql/src/test/results/clientpositive/llap/vector_partitioned_date_time.q.out @@ -379,11 +379,11 @@ STAGE PLANS: Statistics: Num rows: 137 Data size: 39456 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: fl_date (type: date) - outputColumnNames: _col0 + outputColumnNames: fl_date Statistics: Num rows: 137 Data size: 39456 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() - keys: _col0 (type: date) + keys: fl_date (type: date) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 137 Data size: 39456 Basic stats: COMPLETE Column stats: NONE @@ -1159,11 +1159,11 @@ STAGE PLANS: Statistics: Num rows: 137 Data size: 31776 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: fl_date (type: date) - outputColumnNames: _col0 + outputColumnNames: fl_date Statistics: Num rows: 137 Data size: 31776 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() - keys: _col0 (type: date) + keys: fl_date (type: date) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 137 Data size: 31776 Basic stats: COMPLETE Column stats: NONE @@ -1963,11 +1963,11 @@ STAGE PLANS: Statistics: Num rows: 137 Data size: 33968 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: fl_time (type: timestamp) - outputColumnNames: _col0 + outputColumnNames: fl_time Statistics: Num rows: 137 Data size: 33968 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() - keys: _col0 (type: timestamp) + keys: fl_time (type: timestamp) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 137 Data size: 33968 Basic stats: COMPLETE Column stats: NONE diff --git a/ql/src/test/results/clientpositive/llap/vector_reduce_groupby_decimal.q.out b/ql/src/test/results/clientpositive/llap/vector_reduce_groupby_decimal.q.out index 55d0544..a32c246 100644 --- a/ql/src/test/results/clientpositive/llap/vector_reduce_groupby_decimal.q.out +++ b/ql/src/test/results/clientpositive/llap/vector_reduce_groupby_decimal.q.out @@ -44,22 +44,18 @@ STAGE PLANS: Filter Operator predicate: (cdecimal1 is not null and cdecimal2 is not null) (type: boolean) Statistics: Num rows: 1526 Data size: 360136 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: cint (type: int), cdouble (type: double), cdecimal1 (type: decimal(20,10)), cdecimal2 (type: decimal(23,14)) - outputColumnNames: _col0, _col1, _col2, _col3 + Group By Operator + aggregations: min(cdecimal1) + keys: cint (type: int), cdouble (type: double), cdecimal1 (type: decimal(20,10)), cdecimal2 (type: decimal(23,14)) + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3, _col4 Statistics: Num rows: 1526 Data size: 360136 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: min(_col2) - keys: _col0 (type: int), _col1 (type: double), _col2 (type: decimal(20,10)), _col3 (type: decimal(23,14)) - mode: hash - outputColumnNames: _col0, _col1, _col2, _col3, _col4 + Reduce Output Operator + key expressions: _col0 (type: int), _col1 (type: double), _col2 (type: decimal(20,10)), _col3 (type: decimal(23,14)) + sort order: ++++ + Map-reduce partition columns: _col0 (type: int), _col1 (type: double), _col2 (type: decimal(20,10)), _col3 (type: decimal(23,14)) Statistics: Num rows: 1526 Data size: 360136 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int), _col1 (type: double), _col2 (type: decimal(20,10)), _col3 (type: decimal(23,14)) - sort order: ++++ - Map-reduce partition columns: _col0 (type: int), _col1 (type: double), _col2 (type: decimal(20,10)), _col3 (type: decimal(23,14)) - Statistics: Num rows: 1526 Data size: 360136 Basic stats: COMPLETE Column stats: NONE - value expressions: _col4 (type: decimal(20,10)) + value expressions: _col4 (type: decimal(20,10)) Execution mode: vectorized, llap Reducer 2 Execution mode: vectorized, llap diff --git a/ql/src/test/results/clientpositive/llap/vectorization_0.q.out b/ql/src/test/results/clientpositive/llap/vectorization_0.q.out index 269c6ac..85ed627 100644 --- a/ql/src/test/results/clientpositive/llap/vectorization_0.q.out +++ b/ql/src/test/results/clientpositive/llap/vectorization_0.q.out @@ -133,10 +133,10 @@ STAGE PLANS: Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctinyint (type: tinyint) - outputColumnNames: _col0 + outputColumnNames: ctinyint Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(_col0) + aggregations: sum(ctinyint) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -440,10 +440,10 @@ STAGE PLANS: Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cbigint (type: bigint) - outputColumnNames: _col0 + outputColumnNames: cbigint Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(_col0) + aggregations: sum(cbigint) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -747,10 +747,10 @@ STAGE PLANS: Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cfloat (type: float) - outputColumnNames: _col0 + outputColumnNames: cfloat Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(_col0) + aggregations: sum(cfloat) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -1001,10 +1001,10 @@ STAGE PLANS: Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cbigint (type: bigint), cfloat (type: float), ctinyint (type: tinyint) - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: cbigint, cfloat, ctinyint Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: avg(_col0), stddev_pop(_col0), var_samp(_col0), count(), sum(_col1), min(_col2) + aggregations: avg(cbigint), stddev_pop(cbigint), var_samp(cbigint), count(), sum(cfloat), min(ctinyint) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 Statistics: Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: NONE diff --git a/ql/src/test/results/clientpositive/llap/vectorization_13.q.out b/ql/src/test/results/clientpositive/llap/vectorization_13.q.out index f6aefa4..23e0f5f 100644 --- a/ql/src/test/results/clientpositive/llap/vectorization_13.q.out +++ b/ql/src/test/results/clientpositive/llap/vectorization_13.q.out @@ -89,19 +89,19 @@ STAGE PLANS: predicate: (((cfloat < 3569.0) and (10.175 >= cdouble) and (cboolean1 <> 1)) or ((UDFToDouble(ctimestamp1) > 11.0) and (UDFToDouble(ctimestamp2) <> 12.0) and (UDFToDouble(ctinyint) < 9763215.5639))) (type: boolean) Statistics: Num rows: 2730 Data size: 586959 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: cboolean1 (type: boolean), ctinyint (type: tinyint), ctimestamp1 (type: timestamp), cfloat (type: float), cstring1 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4 + expressions: ctinyint (type: tinyint), cfloat (type: float), cstring1 (type: string), ctimestamp1 (type: timestamp), cboolean1 (type: boolean) + outputColumnNames: ctinyint, cfloat, cstring1, ctimestamp1, cboolean1 Statistics: Num rows: 2730 Data size: 586959 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: max(_col1), sum(_col3), stddev_pop(_col3), stddev_pop(_col1), max(_col3), min(_col1) - keys: _col0 (type: boolean), _col1 (type: tinyint), _col2 (type: timestamp), _col3 (type: float), _col4 (type: string) + aggregations: max(ctinyint), sum(cfloat), stddev_pop(cfloat), stddev_pop(ctinyint), max(cfloat), min(ctinyint) + keys: ctinyint (type: tinyint), cfloat (type: float), cstring1 (type: string), ctimestamp1 (type: timestamp), cboolean1 (type: boolean) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10 Statistics: Num rows: 2730 Data size: 586959 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: boolean), _col1 (type: tinyint), _col2 (type: timestamp), _col3 (type: float), _col4 (type: string) + key expressions: _col0 (type: tinyint), _col1 (type: float), _col2 (type: string), _col3 (type: timestamp), _col4 (type: boolean) sort order: +++++ - Map-reduce partition columns: _col0 (type: boolean), _col1 (type: tinyint), _col2 (type: timestamp), _col3 (type: float), _col4 (type: string) + Map-reduce partition columns: _col0 (type: tinyint), _col1 (type: float), _col2 (type: string), _col3 (type: timestamp), _col4 (type: boolean) Statistics: Num rows: 2730 Data size: 586959 Basic stats: COMPLETE Column stats: NONE value expressions: _col5 (type: tinyint), _col6 (type: double), _col7 (type: struct), _col8 (type: struct), _col9 (type: float), _col10 (type: tinyint) Execution mode: vectorized, llap @@ -110,12 +110,12 @@ STAGE PLANS: Reduce Operator Tree: Group By Operator aggregations: max(VALUE._col0), sum(VALUE._col1), stddev_pop(VALUE._col2), stddev_pop(VALUE._col3), max(VALUE._col4), min(VALUE._col5) - keys: KEY._col0 (type: boolean), KEY._col1 (type: tinyint), KEY._col2 (type: timestamp), KEY._col3 (type: float), KEY._col4 (type: string) + keys: KEY._col0 (type: tinyint), KEY._col1 (type: float), KEY._col2 (type: string), KEY._col3 (type: timestamp), KEY._col4 (type: boolean) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10 Statistics: Num rows: 1365 Data size: 293479 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: boolean), _col1 (type: tinyint), _col2 (type: timestamp), _col3 (type: float), _col4 (type: string), (- _col1) (type: tinyint), _col5 (type: tinyint), ((- _col1) + _col5) (type: tinyint), _col6 (type: double), (_col6 * UDFToDouble(((- _col1) + _col5))) (type: double), (- _col6) (type: double), (79.553 * UDFToDouble(_col3)) (type: double), _col7 (type: double), (- _col6) (type: double), _col8 (type: double), (UDFToDouble(((- _col1) + _col5)) - 10.175) (type: double), (- (- _col6)) (type: double), (-26.28 / (- (- _col6))) (type: double), _col9 (type: float), ((_col6 * UDFToDouble(((- _col1) + _col5))) / UDFToDouble(_col1)) (type: double), _col10 (type: tinyint) + expressions: _col4 (type: boolean), _col0 (type: tinyint), _col3 (type: timestamp), _col1 (type: float), _col2 (type: string), (- _col0) (type: tinyint), _col5 (type: tinyint), ((- _col0) + _col5) (type: tinyint), _col6 (type: double), (_col6 * UDFToDouble(((- _col0) + _col5))) (type: double), (- _col6) (type: double), (79.553 * UDFToDouble(_col1)) (type: double), _col7 (type: double), (- _col6) (type: double), _col8 (type: double), (UDFToDouble(((- _col0) + _col5)) - 10.175) (type: double), (- (- _col6)) (type: double), (-26.28 / (- (- _col6))) (type: double), _col9 (type: float), ((_col6 * UDFToDouble(((- _col0) + _col5))) / UDFToDouble(_col0)) (type: double), _col10 (type: tinyint) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20 Statistics: Num rows: 1365 Data size: 293479 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator @@ -343,19 +343,19 @@ STAGE PLANS: predicate: (((cfloat < 3569.0) and (10.175 >= cdouble) and (cboolean1 <> 1)) or ((UDFToDouble(ctimestamp1) > -1.388) and (UDFToDouble(ctimestamp2) <> -1.3359999999999999) and (UDFToDouble(ctinyint) < 9763215.5639))) (type: boolean) Statistics: Num rows: 2730 Data size: 586959 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: cboolean1 (type: boolean), ctinyint (type: tinyint), ctimestamp1 (type: timestamp), cfloat (type: float), cstring1 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4 + expressions: ctinyint (type: tinyint), cfloat (type: float), cstring1 (type: string), ctimestamp1 (type: timestamp), cboolean1 (type: boolean) + outputColumnNames: ctinyint, cfloat, cstring1, ctimestamp1, cboolean1 Statistics: Num rows: 2730 Data size: 586959 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: max(_col1), sum(_col3), stddev_pop(_col3), stddev_pop(_col1), max(_col3), min(_col1) - keys: _col0 (type: boolean), _col1 (type: tinyint), _col2 (type: timestamp), _col3 (type: float), _col4 (type: string) + aggregations: max(ctinyint), sum(cfloat), stddev_pop(cfloat), stddev_pop(ctinyint), max(cfloat), min(ctinyint) + keys: ctinyint (type: tinyint), cfloat (type: float), cstring1 (type: string), ctimestamp1 (type: timestamp), cboolean1 (type: boolean) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10 Statistics: Num rows: 2730 Data size: 586959 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: boolean), _col1 (type: tinyint), _col2 (type: timestamp), _col3 (type: float), _col4 (type: string) + key expressions: _col0 (type: tinyint), _col1 (type: float), _col2 (type: string), _col3 (type: timestamp), _col4 (type: boolean) sort order: +++++ - Map-reduce partition columns: _col0 (type: boolean), _col1 (type: tinyint), _col2 (type: timestamp), _col3 (type: float), _col4 (type: string) + Map-reduce partition columns: _col0 (type: tinyint), _col1 (type: float), _col2 (type: string), _col3 (type: timestamp), _col4 (type: boolean) Statistics: Num rows: 2730 Data size: 586959 Basic stats: COMPLETE Column stats: NONE value expressions: _col5 (type: tinyint), _col6 (type: double), _col7 (type: struct), _col8 (type: struct), _col9 (type: float), _col10 (type: tinyint) Execution mode: vectorized, llap @@ -364,12 +364,12 @@ STAGE PLANS: Reduce Operator Tree: Group By Operator aggregations: max(VALUE._col0), sum(VALUE._col1), stddev_pop(VALUE._col2), stddev_pop(VALUE._col3), max(VALUE._col4), min(VALUE._col5) - keys: KEY._col0 (type: boolean), KEY._col1 (type: tinyint), KEY._col2 (type: timestamp), KEY._col3 (type: float), KEY._col4 (type: string) + keys: KEY._col0 (type: tinyint), KEY._col1 (type: float), KEY._col2 (type: string), KEY._col3 (type: timestamp), KEY._col4 (type: boolean) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10 Statistics: Num rows: 1365 Data size: 293479 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: boolean), _col1 (type: tinyint), _col2 (type: timestamp), _col3 (type: float), _col4 (type: string), (- _col1) (type: tinyint), _col5 (type: tinyint), ((- _col1) + _col5) (type: tinyint), _col6 (type: double), (_col6 * UDFToDouble(((- _col1) + _col5))) (type: double), (- _col6) (type: double), (79.553 * UDFToDouble(_col3)) (type: double), _col7 (type: double), (- _col6) (type: double), _col8 (type: double), (UDFToDouble(((- _col1) + _col5)) - 10.175) (type: double), (- (- _col6)) (type: double), (-26.28 / (- (- _col6))) (type: double), _col9 (type: float), ((_col6 * UDFToDouble(((- _col1) + _col5))) / UDFToDouble(_col1)) (type: double), _col10 (type: tinyint) + expressions: _col4 (type: boolean), _col0 (type: tinyint), _col3 (type: timestamp), _col1 (type: float), _col2 (type: string), (- _col0) (type: tinyint), _col5 (type: tinyint), ((- _col0) + _col5) (type: tinyint), _col6 (type: double), (_col6 * UDFToDouble(((- _col0) + _col5))) (type: double), (- _col6) (type: double), (79.553 * UDFToDouble(_col1)) (type: double), _col7 (type: double), (- _col6) (type: double), _col8 (type: double), (UDFToDouble(((- _col0) + _col5)) - 10.175) (type: double), (- (- _col6)) (type: double), (-26.28 / (- (- _col6))) (type: double), _col9 (type: float), ((_col6 * UDFToDouble(((- _col0) + _col5))) / UDFToDouble(_col0)) (type: double), _col10 (type: tinyint) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20 Statistics: Num rows: 1365 Data size: 293479 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator diff --git a/ql/src/test/results/clientpositive/llap/vectorization_15.q.out b/ql/src/test/results/clientpositive/llap/vectorization_15.q.out index 0b48cd6..062b63d 100644 --- a/ql/src/test/results/clientpositive/llap/vectorization_15.q.out +++ b/ql/src/test/results/clientpositive/llap/vectorization_15.q.out @@ -85,19 +85,19 @@ STAGE PLANS: predicate: ((cstring2 like '%ss%') or (cstring1 like '10%') or ((cint >= -75) and (UDFToShort(ctinyint) = csmallint) and (cdouble >= -3728.0))) (type: boolean) Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: cfloat (type: float), cboolean1 (type: boolean), cdouble (type: double), cstring1 (type: string), ctinyint (type: tinyint), cint (type: int), ctimestamp1 (type: timestamp) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 + expressions: ctinyint (type: tinyint), cint (type: int), cfloat (type: float), cdouble (type: double), cstring1 (type: string), ctimestamp1 (type: timestamp), cboolean1 (type: boolean) + outputColumnNames: ctinyint, cint, cfloat, cdouble, cstring1, ctimestamp1, cboolean1 Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: stddev_samp(_col0), min(_col2), stddev_samp(_col4), var_pop(_col4), var_samp(_col5), stddev_pop(_col5) - keys: _col0 (type: float), _col1 (type: boolean), _col2 (type: double), _col3 (type: string), _col4 (type: tinyint), _col5 (type: int), _col6 (type: timestamp) + aggregations: stddev_samp(cfloat), min(cdouble), stddev_samp(ctinyint), var_pop(ctinyint), var_samp(cint), stddev_pop(cint) + keys: ctinyint (type: tinyint), cint (type: int), cfloat (type: float), cdouble (type: double), cstring1 (type: string), ctimestamp1 (type: timestamp), cboolean1 (type: boolean) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12 Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: float), _col1 (type: boolean), _col2 (type: double), _col3 (type: string), _col4 (type: tinyint), _col5 (type: int), _col6 (type: timestamp) + key expressions: _col0 (type: tinyint), _col1 (type: int), _col2 (type: float), _col3 (type: double), _col4 (type: string), _col5 (type: timestamp), _col6 (type: boolean) sort order: +++++++ - Map-reduce partition columns: _col0 (type: float), _col1 (type: boolean), _col2 (type: double), _col3 (type: string), _col4 (type: tinyint), _col5 (type: int), _col6 (type: timestamp) + Map-reduce partition columns: _col0 (type: tinyint), _col1 (type: int), _col2 (type: float), _col3 (type: double), _col4 (type: string), _col5 (type: timestamp), _col6 (type: boolean) Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE value expressions: _col7 (type: struct), _col8 (type: double), _col9 (type: struct), _col10 (type: struct), _col11 (type: struct), _col12 (type: struct) Execution mode: vectorized, llap @@ -106,12 +106,12 @@ STAGE PLANS: Reduce Operator Tree: Group By Operator aggregations: stddev_samp(VALUE._col0), min(VALUE._col1), stddev_samp(VALUE._col2), var_pop(VALUE._col3), var_samp(VALUE._col4), stddev_pop(VALUE._col5) - keys: KEY._col0 (type: float), KEY._col1 (type: boolean), KEY._col2 (type: double), KEY._col3 (type: string), KEY._col4 (type: tinyint), KEY._col5 (type: int), KEY._col6 (type: timestamp) + keys: KEY._col0 (type: tinyint), KEY._col1 (type: int), KEY._col2 (type: float), KEY._col3 (type: double), KEY._col4 (type: string), KEY._col5 (type: timestamp), KEY._col6 (type: boolean) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12 Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: float), _col1 (type: boolean), _col2 (type: double), _col3 (type: string), _col4 (type: tinyint), _col5 (type: int), _col6 (type: timestamp), _col7 (type: double), (-26.28 - UDFToDouble(_col5)) (type: double), _col8 (type: double), (_col2 * 79.553) (type: double), (33.0 % _col0) (type: float), _col9 (type: double), _col10 (type: double), (-23.0 % _col2) (type: double), (- _col4) (type: tinyint), _col11 (type: double), (UDFToFloat(_col5) - _col0) (type: float), (-23 % UDFToInteger(_col4)) (type: int), (- (-26.28 - UDFToDouble(_col5))) (type: double), _col12 (type: double) + expressions: _col2 (type: float), _col6 (type: boolean), _col3 (type: double), _col4 (type: string), _col0 (type: tinyint), _col1 (type: int), _col5 (type: timestamp), _col7 (type: double), (-26.28 - UDFToDouble(_col1)) (type: double), _col8 (type: double), (_col3 * 79.553) (type: double), (33.0 % _col2) (type: float), _col9 (type: double), _col10 (type: double), (-23.0 % _col3) (type: double), (- _col0) (type: tinyint), _col11 (type: double), (UDFToFloat(_col1) - _col2) (type: float), (-23 % UDFToInteger(_col0)) (type: int), (- (-26.28 - UDFToDouble(_col1))) (type: double), _col12 (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20 Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator diff --git a/ql/src/test/results/clientpositive/llap/vectorization_16.q.out b/ql/src/test/results/clientpositive/llap/vectorization_16.q.out index 501f3fa..c1cdfe8 100644 --- a/ql/src/test/results/clientpositive/llap/vectorization_16.q.out +++ b/ql/src/test/results/clientpositive/llap/vectorization_16.q.out @@ -62,19 +62,19 @@ STAGE PLANS: predicate: ((cstring2 like '%b%') and ((cdouble >= -1.389) or (cstring1 < 'a'))) (type: boolean) Statistics: Num rows: 4096 Data size: 880654 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: cstring1 (type: string), cdouble (type: double), ctimestamp1 (type: timestamp) - outputColumnNames: _col0, _col1, _col2 + expressions: cdouble (type: double), cstring1 (type: string), ctimestamp1 (type: timestamp) + outputColumnNames: cdouble, cstring1, ctimestamp1 Statistics: Num rows: 4096 Data size: 880654 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(_col1), stddev_samp(_col1), min(_col1) - keys: _col0 (type: string), _col1 (type: double), _col2 (type: timestamp) + aggregations: count(cdouble), stddev_samp(cdouble), min(cdouble) + keys: cdouble (type: double), cstring1 (type: string), ctimestamp1 (type: timestamp) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 Statistics: Num rows: 4096 Data size: 880654 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: double), _col2 (type: timestamp) + key expressions: _col0 (type: double), _col1 (type: string), _col2 (type: timestamp) sort order: +++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: double), _col2 (type: timestamp) + Map-reduce partition columns: _col0 (type: double), _col1 (type: string), _col2 (type: timestamp) Statistics: Num rows: 4096 Data size: 880654 Basic stats: COMPLETE Column stats: NONE value expressions: _col3 (type: bigint), _col4 (type: struct), _col5 (type: double) Execution mode: vectorized, llap @@ -83,12 +83,12 @@ STAGE PLANS: Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0), stddev_samp(VALUE._col1), min(VALUE._col2) - keys: KEY._col0 (type: string), KEY._col1 (type: double), KEY._col2 (type: timestamp) + keys: KEY._col0 (type: double), KEY._col1 (type: string), KEY._col2 (type: timestamp) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 Statistics: Num rows: 2048 Data size: 440327 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col1 (type: double), _col2 (type: timestamp), (_col1 - 9763215.5639) (type: double), (- (_col1 - 9763215.5639)) (type: double), _col3 (type: bigint), _col4 (type: double), (- _col4) (type: double), (_col4 * UDFToDouble(_col3)) (type: double), _col5 (type: double), (9763215.5639 / _col1) (type: double), (UDFToDouble(_col3) / -1.389) (type: double), _col4 (type: double) + expressions: _col1 (type: string), _col0 (type: double), _col2 (type: timestamp), (_col0 - 9763215.5639) (type: double), (- (_col0 - 9763215.5639)) (type: double), _col3 (type: bigint), _col4 (type: double), (- _col4) (type: double), (_col4 * UDFToDouble(_col3)) (type: double), _col5 (type: double), (9763215.5639 / _col0) (type: double), (UDFToDouble(_col3) / -1.389) (type: double), _col4 (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12 Statistics: Num rows: 2048 Data size: 440327 Basic stats: COMPLETE Column stats: NONE File Output Operator diff --git a/ql/src/test/results/clientpositive/llap/vectorization_9.q.out b/ql/src/test/results/clientpositive/llap/vectorization_9.q.out index 501f3fa..c1cdfe8 100644 --- a/ql/src/test/results/clientpositive/llap/vectorization_9.q.out +++ b/ql/src/test/results/clientpositive/llap/vectorization_9.q.out @@ -62,19 +62,19 @@ STAGE PLANS: predicate: ((cstring2 like '%b%') and ((cdouble >= -1.389) or (cstring1 < 'a'))) (type: boolean) Statistics: Num rows: 4096 Data size: 880654 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: cstring1 (type: string), cdouble (type: double), ctimestamp1 (type: timestamp) - outputColumnNames: _col0, _col1, _col2 + expressions: cdouble (type: double), cstring1 (type: string), ctimestamp1 (type: timestamp) + outputColumnNames: cdouble, cstring1, ctimestamp1 Statistics: Num rows: 4096 Data size: 880654 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(_col1), stddev_samp(_col1), min(_col1) - keys: _col0 (type: string), _col1 (type: double), _col2 (type: timestamp) + aggregations: count(cdouble), stddev_samp(cdouble), min(cdouble) + keys: cdouble (type: double), cstring1 (type: string), ctimestamp1 (type: timestamp) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 Statistics: Num rows: 4096 Data size: 880654 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: double), _col2 (type: timestamp) + key expressions: _col0 (type: double), _col1 (type: string), _col2 (type: timestamp) sort order: +++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: double), _col2 (type: timestamp) + Map-reduce partition columns: _col0 (type: double), _col1 (type: string), _col2 (type: timestamp) Statistics: Num rows: 4096 Data size: 880654 Basic stats: COMPLETE Column stats: NONE value expressions: _col3 (type: bigint), _col4 (type: struct), _col5 (type: double) Execution mode: vectorized, llap @@ -83,12 +83,12 @@ STAGE PLANS: Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0), stddev_samp(VALUE._col1), min(VALUE._col2) - keys: KEY._col0 (type: string), KEY._col1 (type: double), KEY._col2 (type: timestamp) + keys: KEY._col0 (type: double), KEY._col1 (type: string), KEY._col2 (type: timestamp) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 Statistics: Num rows: 2048 Data size: 440327 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col1 (type: double), _col2 (type: timestamp), (_col1 - 9763215.5639) (type: double), (- (_col1 - 9763215.5639)) (type: double), _col3 (type: bigint), _col4 (type: double), (- _col4) (type: double), (_col4 * UDFToDouble(_col3)) (type: double), _col5 (type: double), (9763215.5639 / _col1) (type: double), (UDFToDouble(_col3) / -1.389) (type: double), _col4 (type: double) + expressions: _col1 (type: string), _col0 (type: double), _col2 (type: timestamp), (_col0 - 9763215.5639) (type: double), (- (_col0 - 9763215.5639)) (type: double), _col3 (type: bigint), _col4 (type: double), (- _col4) (type: double), (_col4 * UDFToDouble(_col3)) (type: double), _col5 (type: double), (9763215.5639 / _col0) (type: double), (UDFToDouble(_col3) / -1.389) (type: double), _col4 (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12 Statistics: Num rows: 2048 Data size: 440327 Basic stats: COMPLETE Column stats: NONE File Output Operator diff --git a/ql/src/test/results/clientpositive/llap/vectorization_limit.q.out b/ql/src/test/results/clientpositive/llap/vectorization_limit.q.out index ece6719..1d2f8dd 100644 --- a/ql/src/test/results/clientpositive/llap/vectorization_limit.q.out +++ b/ql/src/test/results/clientpositive/llap/vectorization_limit.q.out @@ -252,10 +252,10 @@ STAGE PLANS: Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctinyint (type: tinyint) - outputColumnNames: _col0 + outputColumnNames: ctinyint Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: _col0 (type: tinyint) + keys: ctinyint (type: tinyint) mode: hash outputColumnNames: _col0 Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE @@ -343,10 +343,10 @@ STAGE PLANS: Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctinyint (type: tinyint), cdouble (type: double) - outputColumnNames: _col0, _col1 + outputColumnNames: ctinyint, cdouble Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: _col0 (type: tinyint), _col1 (type: double) + keys: ctinyint (type: tinyint), cdouble (type: double) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE @@ -471,11 +471,11 @@ STAGE PLANS: Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cdouble (type: double), ctinyint (type: tinyint) - outputColumnNames: _col0, _col1 + outputColumnNames: cdouble, ctinyint Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(_col1) - keys: _col0 (type: double) + aggregations: sum(ctinyint) + keys: cdouble (type: double) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE diff --git a/ql/src/test/results/clientpositive/llap/vectorization_pushdown.q.out b/ql/src/test/results/clientpositive/llap/vectorization_pushdown.q.out index a02cd59..6ae1d71 100644 --- a/ql/src/test/results/clientpositive/llap/vectorization_pushdown.q.out +++ b/ql/src/test/results/clientpositive/llap/vectorization_pushdown.q.out @@ -25,10 +25,10 @@ STAGE PLANS: Statistics: Num rows: 4096 Data size: 880654 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cbigint (type: bigint) - outputColumnNames: _col0 + outputColumnNames: cbigint Statistics: Num rows: 4096 Data size: 880654 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: avg(_col0) + aggregations: avg(cbigint) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE diff --git a/ql/src/test/results/clientpositive/llap/vectorization_short_regress.q.out b/ql/src/test/results/clientpositive/llap/vectorization_short_regress.q.out index d5ea930..82f5b12 100644 --- a/ql/src/test/results/clientpositive/llap/vectorization_short_regress.q.out +++ b/ql/src/test/results/clientpositive/llap/vectorization_short_regress.q.out @@ -156,10 +156,10 @@ STAGE PLANS: Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cint (type: int), cdouble (type: double), csmallint (type: smallint), cfloat (type: float), ctinyint (type: tinyint) - outputColumnNames: _col0, _col1, _col2, _col3, _col4 + outputColumnNames: cint, cdouble, csmallint, cfloat, ctinyint Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: avg(_col0), sum(_col1), stddev_pop(_col0), stddev_samp(_col2), var_samp(_col0), avg(_col3), stddev_samp(_col0), min(_col4), count(_col2) + aggregations: avg(cint), sum(cdouble), stddev_pop(cint), stddev_samp(csmallint), var_samp(cint), avg(cfloat), stddev_samp(cint), min(ctinyint), count(csmallint) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 Statistics: Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: NONE @@ -369,10 +369,10 @@ STAGE PLANS: Statistics: Num rows: 6826 Data size: 1467614 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cint (type: int), cbigint (type: bigint), csmallint (type: smallint), cdouble (type: double), ctinyint (type: tinyint) - outputColumnNames: _col0, _col1, _col2, _col3, _col4 + outputColumnNames: cint, cbigint, csmallint, cdouble, ctinyint Statistics: Num rows: 6826 Data size: 1467614 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: max(_col0), var_pop(_col1), stddev_pop(_col2), max(_col3), avg(_col4), min(_col0), min(_col3), stddev_samp(_col2), var_samp(_col0) + aggregations: max(cint), var_pop(cbigint), stddev_pop(csmallint), max(cdouble), avg(ctinyint), min(cint), min(cdouble), stddev_samp(csmallint), var_samp(cint) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE @@ -573,10 +573,10 @@ STAGE PLANS: Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cbigint (type: bigint), ctinyint (type: tinyint), csmallint (type: smallint), cint (type: int), cdouble (type: double) - outputColumnNames: _col0, _col1, _col2, _col3, _col4 + outputColumnNames: cbigint, ctinyint, csmallint, cint, cdouble Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: var_pop(_col0), count(), max(_col1), stddev_pop(_col2), max(_col3), stddev_samp(_col4), count(_col1), avg(_col1) + aggregations: var_pop(cbigint), count(), max(ctinyint), stddev_pop(csmallint), max(cint), stddev_samp(cdouble), count(ctinyint), avg(ctinyint) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE @@ -756,10 +756,10 @@ STAGE PLANS: Statistics: Num rows: 8874 Data size: 1907941 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctinyint (type: tinyint), cbigint (type: bigint), cint (type: int), cfloat (type: float) - outputColumnNames: _col0, _col1, _col2, _col3 + outputColumnNames: ctinyint, cbigint, cint, cfloat Statistics: Num rows: 8874 Data size: 1907941 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: avg(_col0), max(_col1), stddev_samp(_col2), var_pop(_col2), var_pop(_col1), max(_col3) + aggregations: avg(ctinyint), max(cbigint), stddev_samp(cint), var_pop(cint), var_pop(cbigint), max(cfloat) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE @@ -1886,11 +1886,11 @@ STAGE PLANS: Statistics: Num rows: 2503 Data size: 538153 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: csmallint (type: smallint), cbigint (type: bigint), ctinyint (type: tinyint) - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: csmallint, cbigint, ctinyint Statistics: Num rows: 2503 Data size: 538153 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: stddev_samp(_col0), sum(_col1), var_pop(_col2), count() - keys: _col0 (type: smallint) + aggregations: stddev_samp(csmallint), sum(cbigint), var_pop(ctinyint), count() + keys: csmallint (type: smallint) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4 Statistics: Num rows: 2503 Data size: 538153 Basic stats: COMPLETE Column stats: NONE @@ -2094,11 +2094,11 @@ STAGE PLANS: Statistics: Num rows: 2654 Data size: 570619 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cdouble (type: double), cfloat (type: float) - outputColumnNames: _col0, _col1 + outputColumnNames: cdouble, cfloat Statistics: Num rows: 2654 Data size: 570619 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: var_samp(_col0), count(_col1), sum(_col1), var_pop(_col0), stddev_pop(_col0), sum(_col0) - keys: _col0 (type: double) + aggregations: var_samp(cdouble), count(cfloat), sum(cfloat), var_pop(cdouble), stddev_pop(cdouble), sum(cdouble) + keys: cdouble (type: double) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 Statistics: Num rows: 2654 Data size: 570619 Basic stats: COMPLETE Column stats: NONE @@ -2349,19 +2349,19 @@ STAGE PLANS: predicate: ((UDFToDouble(ctimestamp1) <> 0.0) and (((-257 <> UDFToInteger(ctinyint)) and cboolean2 is not null and cstring1 regexp '.*ss' and (-3.0 < UDFToDouble(ctimestamp1))) or (UDFToDouble(ctimestamp2) = -5.0) or ((UDFToDouble(ctimestamp1) < 0.0) and (cstring2 like '%b%')) or (cdouble = UDFToDouble(cint)) or (cboolean1 is null and (cfloat < UDFToFloat(cint))))) (type: boolean) Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: ctimestamp1 (type: timestamp), cstring1 (type: string), cint (type: int), csmallint (type: smallint), ctinyint (type: tinyint), cfloat (type: float), cdouble (type: double) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 + expressions: cstring1 (type: string), ctimestamp1 (type: timestamp), cint (type: int), csmallint (type: smallint), ctinyint (type: tinyint), cfloat (type: float), cdouble (type: double) + outputColumnNames: cstring1, ctimestamp1, cint, csmallint, ctinyint, cfloat, cdouble Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: stddev_pop(_col2), avg(_col3), count(), min(_col4), var_samp(_col3), var_pop(_col5), avg(_col2), var_samp(_col5), avg(_col5), min(_col6), var_pop(_col3), stddev_pop(_col4), sum(_col2) - keys: _col0 (type: timestamp), _col1 (type: string) + aggregations: stddev_pop(cint), avg(csmallint), count(), min(ctinyint), var_samp(csmallint), var_pop(cfloat), avg(cint), var_samp(cfloat), avg(cfloat), min(cdouble), var_pop(csmallint), stddev_pop(ctinyint), sum(cint) + keys: cstring1 (type: string), ctimestamp1 (type: timestamp) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14 Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: timestamp), _col1 (type: string) + key expressions: _col0 (type: string), _col1 (type: timestamp) sort order: ++ - Map-reduce partition columns: _col0 (type: timestamp), _col1 (type: string) + Map-reduce partition columns: _col0 (type: string), _col1 (type: timestamp) Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE value expressions: _col2 (type: struct), _col3 (type: struct), _col4 (type: bigint), _col5 (type: tinyint), _col6 (type: struct), _col7 (type: struct), _col8 (type: struct), _col9 (type: struct), _col10 (type: struct), _col11 (type: double), _col12 (type: struct), _col13 (type: struct), _col14 (type: bigint) Execution mode: vectorized, llap @@ -2370,12 +2370,12 @@ STAGE PLANS: Reduce Operator Tree: Group By Operator aggregations: stddev_pop(VALUE._col0), avg(VALUE._col1), count(VALUE._col2), min(VALUE._col3), var_samp(VALUE._col4), var_pop(VALUE._col5), avg(VALUE._col6), var_samp(VALUE._col7), avg(VALUE._col8), min(VALUE._col9), var_pop(VALUE._col10), stddev_pop(VALUE._col11), sum(VALUE._col12) - keys: KEY._col0 (type: timestamp), KEY._col1 (type: string) + keys: KEY._col0 (type: string), KEY._col1 (type: timestamp) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14 Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: timestamp), _col1 (type: string), _col2 (type: double), (_col2 * 10.175) (type: double), (- _col2) (type: double), _col3 (type: double), (- _col2) (type: double), (-26.28 - _col2) (type: double), _col4 (type: bigint), (- _col4) (type: bigint), ((-26.28 - _col2) * (- _col2)) (type: double), _col5 (type: tinyint), (((-26.28 - _col2) * (- _col2)) * UDFToDouble((- _col4))) (type: double), (- (_col2 * 10.175)) (type: double), _col6 (type: double), (_col6 + (((-26.28 - _col2) * (- _col2)) * UDFToDouble((- _col4)))) (type: double), (- (- _col2)) (type: double), (UDFToDouble((- _col4)) / _col2) (type: double), _col7 (type: double), (10.175 / _col3) (type: double), _col8 (type: double), _col9 (type: double), ((_col6 + (((-26.28 - _col2) * (- _col2)) * UDFToDouble((- _col4)))) - (((-26.28 - _col2) * (- _col2)) * UDFToDouble((- _col4)))) (type: double), (- (- (_col2 * 10.175))) (type: double), _col10 (type: double), (((_col6 + (((-26.28 - _col2) * (- _col2)) * UDFToDouble((- _col4)))) - (((-26.28 - _col2) * (- _col2)) * UDFToDouble((- _col4)))) * 10.175) (type: double), (10.175 % (10.175 / _col3)) (type: double), (- _col5) (type: tinyint), _col11 (type: double), _col12 (type: double), (- ((-26.28 - _col2) * (- _col2))) (type: double), ((- _col2) % _col10) (type: double), (-26.28 / UDFToDouble((- _col5))) (type: double), _col13 (type: double), _col14 (type: bigint), ((_col6 + (((-26.28 - _col2) * (- _col2)) * UDFToDouble((- _col4)))) / _col7) (type: double), (- (- _col4)) (type: bigint), _col4 (type: bigint), ((_col6 + (((-26.28 - _col2) * (- _col2)) * UDFToDouble((- _col4)))) % -26.28) (type: double) + expressions: _col1 (type: timestamp), _col0 (type: string), _col2 (type: double), (_col2 * 10.175) (type: double), (- _col2) (type: double), _col3 (type: double), (- _col2) (type: double), (-26.28 - _col2) (type: double), _col4 (type: bigint), (- _col4) (type: bigint), ((-26.28 - _col2) * (- _col2)) (type: double), _col5 (type: tinyint), (((-26.28 - _col2) * (- _col2)) * UDFToDouble((- _col4))) (type: double), (- (_col2 * 10.175)) (type: double), _col6 (type: double), (_col6 + (((-26.28 - _col2) * (- _col2)) * UDFToDouble((- _col4)))) (type: double), (- (- _col2)) (type: double), (UDFToDouble((- _col4)) / _col2) (type: double), _col7 (type: double), (10.175 / _col3) (type: double), _col8 (type: double), _col9 (type: double), ((_col6 + (((-26.28 - _col2) * (- _col2)) * UDFToDouble((- _col4)))) - (((-26.28 - _col2) * (- _col2)) * UDFToDouble((- _col4)))) (type: double), (- (- (_col2 * 10.175))) (type: double), _col10 (type: double), (((_col6 + (((-26.28 - _col2) * (- _col2)) * UDFToDouble((- _col4)))) - (((-26.28 - _col2) * (- _col2)) * UDFToDouble((- _col4)))) * 10.175) (type: double), (10.175 % (10.175 / _col3)) (type: double), (- _col5) (type: tinyint), _col11 (type: double), _col12 (type: double), (- ((-26.28 - _col2) * (- _col2))) (type: double), ((- _col2) % _col10) (type: double), (-26.28 / UDFToDouble((- _col5))) (type: double), _col13 (type: double), _col14 (type: bigint), ((_col6 + (((-26.28 - _col2) * (- _col2)) * UDFToDouble((- _col4)))) / _col7) (type: double), (- (- _col4)) (type: bigint), _col4 (type: bigint), ((_col6 + (((-26.28 - _col2) * (- _col2)) * UDFToDouble((- _col4)))) % -26.28) (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25, _col26, _col27, _col28, _col29, _col30, _col31, _col32, _col33, _col34, _col35, _col36, _col37, _col38 Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator @@ -2683,11 +2683,11 @@ STAGE PLANS: Statistics: Num rows: 4778 Data size: 1027287 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cboolean1 (type: boolean), cfloat (type: float), cbigint (type: bigint), cint (type: int), cdouble (type: double), ctinyint (type: tinyint), csmallint (type: smallint) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 + outputColumnNames: cboolean1, cfloat, cbigint, cint, cdouble, ctinyint, csmallint Statistics: Num rows: 4778 Data size: 1027287 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: max(_col1), sum(_col2), var_samp(_col3), avg(_col4), min(_col2), var_pop(_col2), sum(_col3), stddev_samp(_col5), stddev_pop(_col6), avg(_col3) - keys: _col0 (type: boolean) + aggregations: max(cfloat), sum(cbigint), var_samp(cint), avg(cdouble), min(cbigint), var_pop(cbigint), sum(cint), stddev_samp(ctinyint), stddev_pop(csmallint), avg(cint) + keys: cboolean1 (type: boolean) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10 Statistics: Num rows: 4778 Data size: 1027287 Basic stats: COMPLETE Column stats: NONE @@ -2923,10 +2923,10 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: i (type: int) - outputColumnNames: _col0 + outputColumnNames: i Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Group By Operator - aggregations: count(_col0) + aggregations: count(i) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -3101,10 +3101,10 @@ STAGE PLANS: Statistics: Num rows: 12288 Data size: 168 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctinyint (type: tinyint) - outputColumnNames: _col0 + outputColumnNames: ctinyint Statistics: Num rows: 12288 Data size: 168 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(_col0) + aggregations: count(ctinyint) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -3168,10 +3168,10 @@ STAGE PLANS: Statistics: Num rows: 12288 Data size: 168 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cint (type: int) - outputColumnNames: _col0 + outputColumnNames: cint Statistics: Num rows: 12288 Data size: 168 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(_col0) + aggregations: count(cint) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -3235,10 +3235,10 @@ STAGE PLANS: Statistics: Num rows: 12288 Data size: 168 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cfloat (type: float) - outputColumnNames: _col0 + outputColumnNames: cfloat Statistics: Num rows: 12288 Data size: 168 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(_col0) + aggregations: count(cfloat) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -3302,10 +3302,10 @@ STAGE PLANS: Statistics: Num rows: 12288 Data size: 168 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cstring1 (type: string) - outputColumnNames: _col0 + outputColumnNames: cstring1 Statistics: Num rows: 12288 Data size: 168 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(_col0) + aggregations: count(cstring1) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -3369,10 +3369,10 @@ STAGE PLANS: Statistics: Num rows: 12288 Data size: 168 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cboolean1 (type: boolean) - outputColumnNames: _col0 + outputColumnNames: cboolean1 Statistics: Num rows: 12288 Data size: 168 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(_col0) + aggregations: count(cboolean1) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE diff --git a/ql/src/test/results/clientpositive/llap/vectorized_distinct_gby.q.out b/ql/src/test/results/clientpositive/llap/vectorized_distinct_gby.q.out index df4a301..67dea8e 100644 --- a/ql/src/test/results/clientpositive/llap/vectorized_distinct_gby.q.out +++ b/ql/src/test/results/clientpositive/llap/vectorized_distinct_gby.q.out @@ -38,10 +38,10 @@ STAGE PLANS: Statistics: Num rows: 5 Data size: 40 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: a (type: int) - outputColumnNames: _col0 + outputColumnNames: a Statistics: Num rows: 5 Data size: 40 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: _col0 (type: int) + keys: a (type: int) mode: final outputColumnNames: _col0 Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: NONE @@ -109,10 +109,10 @@ STAGE PLANS: Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cint (type: int) - outputColumnNames: _col0 + outputColumnNames: cint Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: _col0 (type: int) + keys: cint (type: int) mode: hash outputColumnNames: _col0 Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE 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 41331e7..182d6f7 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 @@ -59,10 +59,10 @@ STAGE PLANS: Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ds (type: string) - outputColumnNames: _col0 + outputColumnNames: ds Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: _col0 (type: string) + keys: ds (type: string) mode: hash outputColumnNames: _col0 Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE @@ -1831,7 +1831,7 @@ 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[23][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product +Warning: Shuffle Join MERGEJOIN[21][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 @@ -1871,10 +1871,10 @@ STAGE PLANS: Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: '2008-04-08' (type: string) - outputColumnNames: _col0 + outputColumnNames: ds Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: _col0 (type: string) + keys: ds (type: string) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE @@ -1938,7 +1938,7 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Shuffle Join MERGEJOIN[23][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product +Warning: Shuffle Join MERGEJOIN[21][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 @@ -2835,10 +2835,10 @@ STAGE PLANS: Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ds (type: string) - outputColumnNames: _col0 + outputColumnNames: ds Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: max(_col0) + aggregations: max(ds) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 84 Basic stats: COMPLETE Column stats: NONE @@ -2854,10 +2854,10 @@ STAGE PLANS: Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ds (type: string) - outputColumnNames: _col0 + outputColumnNames: ds Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: min(_col0) + aggregations: min(ds) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 84 Basic stats: COMPLETE Column stats: NONE @@ -3039,10 +3039,10 @@ STAGE PLANS: Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ds (type: string) - outputColumnNames: _col0 + outputColumnNames: ds Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: max(_col0) + aggregations: max(ds) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 84 Basic stats: COMPLETE Column stats: NONE @@ -3058,10 +3058,10 @@ STAGE PLANS: Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ds (type: string) - outputColumnNames: _col0 + outputColumnNames: ds Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: min(_col0) + aggregations: min(ds) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 84 Basic stats: COMPLETE Column stats: NONE @@ -3230,20 +3230,16 @@ STAGE PLANS: alias: srcpart filterExpr: ds is not null (type: boolean) Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: ds (type: string) + Group By Operator + keys: ds (type: string) + mode: hash outputColumnNames: _col0 Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 + 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 - 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 Execution mode: llap Map 10 Map Operator Tree: @@ -3252,10 +3248,10 @@ STAGE PLANS: Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ds (type: string) - outputColumnNames: _col0 + outputColumnNames: ds Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: min(_col0) + aggregations: min(ds) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 84 Basic stats: COMPLETE Column stats: NONE @@ -3270,20 +3266,16 @@ STAGE PLANS: alias: srcpart filterExpr: ds is not null (type: boolean) Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: ds (type: string) + Group By Operator + keys: ds (type: string) + mode: hash outputColumnNames: _col0 Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0 + 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 - 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 Execution mode: llap Map 7 Map Operator Tree: @@ -3292,10 +3284,10 @@ STAGE PLANS: Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ds (type: string) - outputColumnNames: _col0 + outputColumnNames: ds Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: max(_col0) + aggregations: max(ds) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 84 Basic stats: COMPLETE Column stats: NONE @@ -4270,7 +4262,7 @@ 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[23][bigTable=?] in task 'Map 1' is a cross product +Warning: Map Join MAPJOIN[21][bigTable=?] in task 'Map 1' 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 @@ -4326,10 +4318,10 @@ STAGE PLANS: Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: '2008-04-08' (type: string) - outputColumnNames: _col0 + outputColumnNames: ds Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Group By Operator - keys: _col0 (type: string) + keys: ds (type: string) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE @@ -4374,7 +4366,7 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Map Join MAPJOIN[23][bigTable=?] in task 'Map 1' is a cross product +Warning: Map Join MAPJOIN[21][bigTable=?] in task 'Map 1' 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 @@ -4984,10 +4976,10 @@ STAGE PLANS: Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ds (type: string) - outputColumnNames: _col0 + outputColumnNames: ds Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: max(_col0) + aggregations: max(ds) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 84 Basic stats: COMPLETE Column stats: NONE @@ -5003,10 +4995,10 @@ STAGE PLANS: Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ds (type: string) - outputColumnNames: _col0 + outputColumnNames: ds Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: min(_col0) + aggregations: min(ds) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 84 Basic stats: COMPLETE Column stats: NONE diff --git a/ql/src/test/results/clientpositive/llap/vectorized_nested_mapjoin.q.out b/ql/src/test/results/clientpositive/llap/vectorized_nested_mapjoin.q.out index b28ef86..899967b 100644 --- a/ql/src/test/results/clientpositive/llap/vectorized_nested_mapjoin.q.out +++ b/ql/src/test/results/clientpositive/llap/vectorized_nested_mapjoin.q.out @@ -75,19 +75,15 @@ STAGE PLANS: 1 Map 4 Statistics: Num rows: 7433 Data size: 1598388 Basic stats: COMPLETE Column stats: NONE HybridGraceHashJoin: true - Select Operator - expressions: _col1 (type: double) + Group By Operator + aggregations: sum(_col1) + mode: hash outputColumnNames: _col0 - Statistics: Num rows: 7433 Data size: 1598388 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: sum(_col0) - 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 - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: double) + value expressions: _col0 (type: double) Execution mode: vectorized, llap Map 4 Map Operator Tree: diff --git a/ql/src/test/results/clientpositive/llap/vectorized_parquet.q.out b/ql/src/test/results/clientpositive/llap/vectorized_parquet.q.out index 9ddbb91..dfb14d0 100644 --- a/ql/src/test/results/clientpositive/llap/vectorized_parquet.q.out +++ b/ql/src/test/results/clientpositive/llap/vectorized_parquet.q.out @@ -135,11 +135,11 @@ STAGE PLANS: Statistics: Num rows: 12288 Data size: 73728 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctinyint (type: tinyint), cint (type: int), csmallint (type: smallint), cstring1 (type: string), cfloat (type: float), cdouble (type: double) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + outputColumnNames: ctinyint, cint, csmallint, cstring1, cfloat, cdouble Statistics: Num rows: 12288 Data size: 73728 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: max(_col1), min(_col2), count(_col3), avg(_col4), stddev_pop(_col5) - keys: _col0 (type: tinyint) + aggregations: max(cint), min(csmallint), count(cstring1), avg(cfloat), stddev_pop(cdouble) + keys: ctinyint (type: tinyint) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 Statistics: Num rows: 12288 Data size: 73728 Basic stats: COMPLETE Column stats: NONE diff --git a/ql/src/test/results/clientpositive/llap/vectorized_timestamp_funcs.q.out b/ql/src/test/results/clientpositive/llap/vectorized_timestamp_funcs.q.out index 41a252d..b0fe5e2 100644 --- a/ql/src/test/results/clientpositive/llap/vectorized_timestamp_funcs.q.out +++ b/ql/src/test/results/clientpositive/llap/vectorized_timestamp_funcs.q.out @@ -644,10 +644,10 @@ STAGE PLANS: Statistics: Num rows: 40 Data size: 84 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctimestamp1 (type: timestamp) - outputColumnNames: _col0 + outputColumnNames: ctimestamp1 Statistics: Num rows: 40 Data size: 84 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: min(_col0), max(_col0), count(_col0), count() + aggregations: min(ctimestamp1), max(ctimestamp1), count(ctimestamp1), count() mode: hash outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: NONE @@ -725,10 +725,10 @@ STAGE PLANS: Statistics: Num rows: 40 Data size: 84 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctimestamp1 (type: timestamp) - outputColumnNames: _col0 + outputColumnNames: ctimestamp1 Statistics: Num rows: 40 Data size: 84 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(_col0) + aggregations: sum(ctimestamp1) mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE @@ -816,10 +816,10 @@ STAGE PLANS: Statistics: Num rows: 40 Data size: 84 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctimestamp1 (type: timestamp) - outputColumnNames: _col0 + outputColumnNames: ctimestamp1 Statistics: Num rows: 40 Data size: 84 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: avg(_col0), variance(_col0), var_pop(_col0), var_samp(_col0), std(_col0), stddev(_col0), stddev_pop(_col0), stddev_samp(_col0) + aggregations: avg(ctimestamp1), variance(ctimestamp1), var_pop(ctimestamp1), var_samp(ctimestamp1), std(ctimestamp1), stddev(ctimestamp1), stddev_pop(ctimestamp1), stddev_samp(ctimestamp1) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE diff --git a/ql/src/test/results/clientpositive/tez/unionDistinct_1.q.out b/ql/src/test/results/clientpositive/tez/unionDistinct_1.q.out index bcae2fc..5ed3d9e 100644 --- a/ql/src/test/results/clientpositive/tez/unionDistinct_1.q.out +++ b/ql/src/test/results/clientpositive/tez/unionDistinct_1.q.out @@ -14393,6 +14393,38 @@ POSTHOOK: Lineage: src10_3.key SIMPLE [(src)src.FieldSchema(name:key, type:strin POSTHOOK: Lineage: src10_3.value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] POSTHOOK: Lineage: src10_4.key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] POSTHOOK: Lineage: src10_4.value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] +PREHOOK: query: analyze table src10_1 compute statistics +PREHOOK: type: QUERY +PREHOOK: Input: default@src10_1 +PREHOOK: Output: default@src10_1 +POSTHOOK: query: analyze table src10_1 compute statistics +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src10_1 +POSTHOOK: Output: default@src10_1 +PREHOOK: query: analyze table src10_2 compute statistics +PREHOOK: type: QUERY +PREHOOK: Input: default@src10_2 +PREHOOK: Output: default@src10_2 +POSTHOOK: query: analyze table src10_2 compute statistics +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src10_2 +POSTHOOK: Output: default@src10_2 +PREHOOK: query: analyze table src10_3 compute statistics +PREHOOK: type: QUERY +PREHOOK: Input: default@src10_3 +PREHOOK: Output: default@src10_3 +POSTHOOK: query: analyze table src10_3 compute statistics +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src10_3 +POSTHOOK: Output: default@src10_3 +PREHOOK: query: analyze table src10_4 compute statistics +PREHOOK: type: QUERY +PREHOOK: Input: default@src10_4 +PREHOOK: Output: default@src10_4 +POSTHOOK: query: analyze table src10_4 compute statistics +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src10_4 +POSTHOOK: Output: default@src10_4 PREHOOK: query: -- When we convert the Join of sub1 and sub0 into a MapJoin, -- we can use a single MR job to evaluate this entire query. explain diff --git a/ql/src/test/results/clientpositive/tez/union_view.q.out b/ql/src/test/results/clientpositive/tez/union_view.q.out index ae6d7c8..51c2785 100644 --- a/ql/src/test/results/clientpositive/tez/union_view.q.out +++ b/ql/src/test/results/clientpositive/tez/union_view.q.out @@ -270,16 +270,21 @@ STAGE PLANS: TableScan alias: src_union_1 filterExpr: ((key = 86) and (ds = '1')) (type: boolean) + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (key = 86) (type: boolean) + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: value (type: string) outputColumnNames: _col1 + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: 86 (type: int), _col1 (type: string), '1' (type: string) outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 252 Data size: 2656 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false + Statistics: Num rows: 252 Data size: 2656 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -289,16 +294,21 @@ STAGE PLANS: TableScan alias: src_union_2 filterExpr: ((key = 86) and (ds = '1')) (type: boolean) + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Filter Operator predicate: ((key = 86) and (ds = '1')) (type: boolean) + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: value (type: string) outputColumnNames: _col1 + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: 86 (type: int), _col1 (type: string), '1' (type: string) outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 252 Data size: 2656 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false + Statistics: Num rows: 252 Data size: 2656 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -308,16 +318,21 @@ STAGE PLANS: TableScan alias: src_union_3 filterExpr: ((key = 86) and (ds = '1')) (type: boolean) + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Filter Operator predicate: ((key = 86) and (ds = '1')) (type: boolean) + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: value (type: string) outputColumnNames: _col1 + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: 86 (type: int), _col1 (type: string), '1' (type: string) outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 252 Data size: 2656 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false + Statistics: Num rows: 252 Data size: 2656 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -349,16 +364,21 @@ STAGE PLANS: TableScan alias: src_union_1 filterExpr: ((key = 86) and (ds = '2')) (type: boolean) + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Filter Operator predicate: ((key = 86) and (ds = '2')) (type: boolean) + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: value (type: string) outputColumnNames: _col1 + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: 86 (type: int), _col1 (type: string), '2' (type: string) outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 502 Data size: 5312 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false + Statistics: Num rows: 502 Data size: 5312 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -368,16 +388,21 @@ STAGE PLANS: TableScan alias: src_union_2 filterExpr: ((key = 86) and (ds = '2')) (type: boolean) + Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (key = 86) (type: boolean) + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: value (type: string) outputColumnNames: _col1 + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: 86 (type: int), _col1 (type: string), '2' (type: string) outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 502 Data size: 5312 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false + Statistics: Num rows: 502 Data size: 5312 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -387,16 +412,21 @@ STAGE PLANS: TableScan alias: src_union_3 filterExpr: ((key = 86) and (ds = '2')) (type: boolean) + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Filter Operator predicate: ((key = 86) and (ds = '2')) (type: boolean) + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: value (type: string) outputColumnNames: _col1 + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: 86 (type: int), _col1 (type: string), '2' (type: string) outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 502 Data size: 5312 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false + Statistics: Num rows: 502 Data size: 5312 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -428,16 +458,21 @@ STAGE PLANS: TableScan alias: src_union_1 filterExpr: ((key = 86) and (ds = '3')) (type: boolean) + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Filter Operator predicate: ((key = 86) and (ds = '3')) (type: boolean) + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: value (type: string) outputColumnNames: _col1 + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: 86 (type: int), _col1 (type: string), '3' (type: string) outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 502 Data size: 5312 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false + Statistics: Num rows: 502 Data size: 5312 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -447,16 +482,21 @@ STAGE PLANS: TableScan alias: src_union_2 filterExpr: ((key = 86) and (ds = '3')) (type: boolean) + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Filter Operator predicate: ((key = 86) and (ds = '3')) (type: boolean) + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: value (type: string) outputColumnNames: _col1 + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: 86 (type: int), _col1 (type: string), '3' (type: string) outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 502 Data size: 5312 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false + Statistics: Num rows: 502 Data size: 5312 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -466,16 +506,21 @@ STAGE PLANS: TableScan alias: src_union_3 filterExpr: ((key = 86) and (ds = '3')) (type: boolean) + Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (key = 86) (type: boolean) + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: value (type: string) outputColumnNames: _col1 + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: 86 (type: int), _col1 (type: string), '3' (type: string) outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 502 Data size: 5312 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false + Statistics: Num rows: 502 Data size: 5312 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -508,51 +553,66 @@ STAGE PLANS: TableScan alias: src_union_1 filterExpr: ((key = 86) and ds is not null) (type: boolean) + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (key = 86) (type: boolean) + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: value (type: string), ds (type: string) outputColumnNames: _col1, _col2 + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col1 (type: string), _col2 (type: string) outputColumnNames: _col1, _col2 + Statistics: Num rows: 1250 Data size: 13280 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col2 (type: string) sort order: + + Statistics: Num rows: 1250 Data size: 13280 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) Map 4 Map Operator Tree: TableScan alias: src_union_2 filterExpr: ((key = 86) and ds is not null) (type: boolean) + Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (key = 86) (type: boolean) + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: value (type: string), ds (type: string) outputColumnNames: _col1, _col2 + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col1 (type: string), _col2 (type: string) outputColumnNames: _col1, _col2 + Statistics: Num rows: 1250 Data size: 13280 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col2 (type: string) sort order: + + Statistics: Num rows: 1250 Data size: 13280 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) Map 5 Map Operator Tree: TableScan alias: src_union_3 filterExpr: ((key = 86) and ds is not null) (type: boolean) + Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (key = 86) (type: boolean) + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: value (type: string), ds (type: string) outputColumnNames: _col1, _col2 + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col1 (type: string), _col2 (type: string) outputColumnNames: _col1, _col2 + Statistics: Num rows: 1250 Data size: 13280 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col2 (type: string) sort order: + + Statistics: Num rows: 1250 Data size: 13280 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) Reducer 3 Reduce Operator Tree: @@ -605,46 +665,69 @@ STAGE PLANS: TableScan alias: src_union_1 filterExpr: (ds = '1') (type: boolean) + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator + expressions: '1' (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator + Statistics: Num rows: 502 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count(1) 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) Map 4 Map Operator Tree: TableScan alias: src_union_2 filterExpr: (ds = '1') (type: boolean) + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Filter Operator predicate: (ds = '1') (type: boolean) + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator + expressions: '1' (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator + Statistics: Num rows: 502 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count(1) 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) Map 5 Map Operator Tree: TableScan alias: src_union_3 filterExpr: (ds = '1') (type: boolean) + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Filter Operator predicate: (ds = '1') (type: boolean) + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator + expressions: '1' (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator + Statistics: Num rows: 502 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count(1) 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 3 Reduce Operator Tree: @@ -688,46 +771,69 @@ STAGE PLANS: TableScan alias: src_union_1 filterExpr: (ds = '2') (type: boolean) + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Filter Operator predicate: (ds = '2') (type: boolean) + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator + expressions: '2' (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator + Statistics: Num rows: 1002 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count(1) 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) Map 4 Map Operator Tree: TableScan alias: src_union_2 filterExpr: (ds = '2') (type: boolean) + Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Select Operator + expressions: '2' (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Select Operator + Statistics: Num rows: 1002 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count(1) 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) Map 5 Map Operator Tree: TableScan alias: src_union_3 filterExpr: (ds = '2') (type: boolean) + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Filter Operator predicate: (ds = '2') (type: boolean) + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator + expressions: '2' (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator + Statistics: Num rows: 1002 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count(1) 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 3 Reduce Operator Tree: @@ -771,46 +877,69 @@ STAGE PLANS: TableScan alias: src_union_1 filterExpr: (ds = '3') (type: boolean) + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Filter Operator predicate: (ds = '3') (type: boolean) + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator + expressions: '3' (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator + Statistics: Num rows: 1002 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count(1) 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) Map 4 Map Operator Tree: TableScan alias: src_union_2 filterExpr: (ds = '3') (type: boolean) + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Filter Operator predicate: (ds = '3') (type: boolean) + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator + expressions: '3' (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator + Statistics: Num rows: 1002 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count(1) 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) Map 5 Map Operator Tree: TableScan alias: src_union_3 filterExpr: (ds = '3') (type: boolean) + Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Select Operator + expressions: '3' (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Select Operator + Statistics: Num rows: 1002 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count(1) 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 3 Reduce Operator Tree: @@ -856,16 +985,21 @@ STAGE PLANS: TableScan alias: src_union_1 filterExpr: ((key = 86) and (ds = '4')) (type: boolean) + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Filter Operator predicate: ((key = 86) and (ds = '4')) (type: boolean) + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: value (type: string) outputColumnNames: _col1 + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: 86 (type: int), _col1 (type: string), '4' (type: string) outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 252 Data size: 2656 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false + Statistics: Num rows: 252 Data size: 2656 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -875,16 +1009,21 @@ STAGE PLANS: TableScan alias: src_union_2 filterExpr: ((key = 86) and (ds = '4')) (type: boolean) + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Filter Operator predicate: ((key = 86) and (ds = '4')) (type: boolean) + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: value (type: string) outputColumnNames: _col1 + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator expressions: 86 (type: int), _col1 (type: string), '4' (type: string) outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 252 Data size: 2656 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false + Statistics: Num rows: 252 Data size: 2656 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -894,16 +1033,21 @@ STAGE PLANS: TableScan alias: src_union_3 filterExpr: ((key = 86) and (ds = '4')) (type: boolean) + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (key = 86) (type: boolean) + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: value (type: string) outputColumnNames: _col1 + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: 86 (type: int), _col1 (type: string), '4' (type: string) outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 252 Data size: 2656 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false + Statistics: Num rows: 252 Data size: 2656 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -937,46 +1081,69 @@ STAGE PLANS: TableScan alias: src_union_1 filterExpr: (ds = '4') (type: boolean) + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Filter Operator predicate: (ds = '4') (type: boolean) + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator + expressions: '4' (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator + Statistics: Num rows: 502 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count(1) 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) Map 4 Map Operator Tree: TableScan alias: src_union_2 filterExpr: (ds = '4') (type: boolean) + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Filter Operator predicate: (ds = '4') (type: boolean) + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator + expressions: '4' (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE Select Operator + Statistics: Num rows: 502 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count(1) 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) Map 5 Map Operator Tree: TableScan alias: src_union_3 filterExpr: (ds = '4') (type: boolean) + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator + expressions: '4' (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator + Statistics: Num rows: 502 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count(1) 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 3 Reduce Operator Tree: diff --git a/ql/src/test/results/clientpositive/unionDistinct_1.q.out b/ql/src/test/results/clientpositive/unionDistinct_1.q.out index 81c46da..4fb230d 100644 --- a/ql/src/test/results/clientpositive/unionDistinct_1.q.out +++ b/ql/src/test/results/clientpositive/unionDistinct_1.q.out @@ -15369,6 +15369,38 @@ POSTHOOK: Lineage: src10_3.key SIMPLE [(src)src.FieldSchema(name:key, type:strin POSTHOOK: Lineage: src10_3.value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] POSTHOOK: Lineage: src10_4.key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] POSTHOOK: Lineage: src10_4.value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] +PREHOOK: query: analyze table src10_1 compute statistics +PREHOOK: type: QUERY +PREHOOK: Input: default@src10_1 +PREHOOK: Output: default@src10_1 +POSTHOOK: query: analyze table src10_1 compute statistics +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src10_1 +POSTHOOK: Output: default@src10_1 +PREHOOK: query: analyze table src10_2 compute statistics +PREHOOK: type: QUERY +PREHOOK: Input: default@src10_2 +PREHOOK: Output: default@src10_2 +POSTHOOK: query: analyze table src10_2 compute statistics +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src10_2 +POSTHOOK: Output: default@src10_2 +PREHOOK: query: analyze table src10_3 compute statistics +PREHOOK: type: QUERY +PREHOOK: Input: default@src10_3 +PREHOOK: Output: default@src10_3 +POSTHOOK: query: analyze table src10_3 compute statistics +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src10_3 +POSTHOOK: Output: default@src10_3 +PREHOOK: query: analyze table src10_4 compute statistics +PREHOOK: type: QUERY +PREHOOK: Input: default@src10_4 +PREHOOK: Output: default@src10_4 +POSTHOOK: query: analyze table src10_4 compute statistics +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src10_4 +POSTHOOK: Output: default@src10_4 PREHOOK: query: -- When we convert the Join of sub1 and sub0 into a MapJoin, -- we can use a single MR job to evaluate this entire query. explain diff --git a/ql/src/test/results/clientpositive/vector_leftsemi_mapjoin.q.out b/ql/src/test/results/clientpositive/vector_leftsemi_mapjoin.q.out index 8502085..dcaabd2 100644 --- a/ql/src/test/results/clientpositive/vector_leftsemi_mapjoin.q.out +++ b/ql/src/test/results/clientpositive/vector_leftsemi_mapjoin.q.out @@ -102,6 +102,14 @@ POSTHOOK: Input: default@t3 8 val_4 8 val_8 9 val_9 +PREHOOK: query: analyze table t3 compute statistics +PREHOOK: type: QUERY +PREHOOK: Input: default@t3 +PREHOOK: Output: default@t3 +POSTHOOK: query: analyze table t3 compute statistics +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t3 +POSTHOOK: Output: default@t3 PREHOOK: query: create table t4 (key int, value string) stored as orc PREHOOK: type: CREATETABLE PREHOOK: Output: database:default diff --git a/ql/src/test/results/clientpositive/vector_multi_insert.q.out b/ql/src/test/results/clientpositive/vector_multi_insert.q.out index 4d10ee8..78456c7 100644 --- a/ql/src/test/results/clientpositive/vector_multi_insert.q.out +++ b/ql/src/test/results/clientpositive/vector_multi_insert.q.out @@ -56,6 +56,14 @@ POSTHOOK: query: create table orc_rn3 (rn int) POSTHOOK: type: CREATETABLE POSTHOOK: Output: database:default POSTHOOK: Output: default@orc_rn3 +PREHOOK: query: analyze table orc1 compute statistics +PREHOOK: type: QUERY +PREHOOK: Input: default@orc1 +PREHOOK: Output: default@orc1 +POSTHOOK: query: analyze table orc1 compute statistics +POSTHOOK: type: QUERY +POSTHOOK: Input: default@orc1 +POSTHOOK: Output: default@orc1 PREHOOK: query: explain from orc1 a insert overwrite table orc_rn1 select a.* where a.rn < 100 insert overwrite table orc_rn2 select a.* where a.rn >= 100 and a.rn < 1000