Repository: hive Updated Branches: refs/heads/master 2cabb8da1 -> 5c02fee28
http://git-wip-us.apache.org/repos/asf/hive/blob/5c02fee2/ql/src/test/results/clientpositive/stat_estimate_drill.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/stat_estimate_drill.q.out b/ql/src/test/results/clientpositive/stat_estimate_drill.q.out new file mode 100644 index 0000000..8a008c8 --- /dev/null +++ b/ql/src/test/results/clientpositive/stat_estimate_drill.q.out @@ -0,0 +1,526 @@ +PREHOOK: query: drop table if exists t1 +PREHOOK: type: DROPTABLE +POSTHOOK: query: drop table if exists t1 +POSTHOOK: type: DROPTABLE +PREHOOK: query: drop table if exists t8 +PREHOOK: type: DROPTABLE +POSTHOOK: query: drop table if exists t8 +POSTHOOK: type: DROPTABLE +PREHOOK: query: create table t1 (a integer) +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@t1 +POSTHOOK: query: create table t1 (a integer) +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@t1 +PREHOOK: query: create table t3 (a integer,b integer,c integer) +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@t3 +POSTHOOK: query: create table t3 (a integer,b integer,c integer) +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@t3 +PREHOOK: query: insert into t1 values (1),(2),(3),(4),(5),(6),(7),(8),(9),(0) +PREHOOK: type: QUERY +PREHOOK: Input: _dummy_database@_dummy_table +PREHOOK: Output: default@t1 +POSTHOOK: query: insert into t1 values (1),(2),(3),(4),(5),(6),(7),(8),(9),(0) +POSTHOOK: type: QUERY +POSTHOOK: Input: _dummy_database@_dummy_table +POSTHOOK: Output: default@t1 +POSTHOOK: Lineage: t1.a SCRIPT [] +Warning: Shuffle Join JOIN[9][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Stage-1:MAPRED' is a cross product +PREHOOK: query: insert into t3 + select x1.a as a,x2.a as b,x3.a as c from + t1 x1 + join t1 x2 + join t1 x3 +PREHOOK: type: QUERY +PREHOOK: Input: default@t1 +PREHOOK: Output: default@t3 +POSTHOOK: query: insert into t3 + select x1.a as a,x2.a as b,x3.a as c from + t1 x1 + join t1 x2 + join t1 x3 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t1 +POSTHOOK: Output: default@t3 +POSTHOOK: Lineage: t3.a SIMPLE [(t1)x1.FieldSchema(name:a, type:int, comment:null), ] +POSTHOOK: Lineage: t3.b SIMPLE [(t1)x2.FieldSchema(name:a, type:int, comment:null), ] +POSTHOOK: Lineage: t3.c SIMPLE [(t1)x3.FieldSchema(name:a, type:int, comment:null), ] +PREHOOK: query: analyze table t3 compute statistics for columns +PREHOOK: type: ANALYZE_TABLE +PREHOOK: Input: default@t3 +PREHOOK: Output: default@t3 +#### A masked pattern was here #### +POSTHOOK: query: analyze table t3 compute statistics for columns +POSTHOOK: type: ANALYZE_TABLE +POSTHOOK: Input: default@t3 +POSTHOOK: Output: default@t3 +#### A masked pattern was here #### +PREHOOK: query: select sum(a) from t3 where b in (2,3) group by b +PREHOOK: type: QUERY +PREHOOK: Input: default@t3 +#### A masked pattern was here #### +POSTHOOK: query: select sum(a) from t3 where b in (2,3) group by b +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t3 +#### A masked pattern was here #### +PREHOOK: query: explain analyze select sum(a) from t3 where b in (2,3) group by b +PREHOOK: type: QUERY +POSTHOOK: query: explain analyze select sum(a) from t3 where b in (2,3) group by b +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Map Reduce + Map Operator Tree: + TableScan + alias: t3 + filterExpr: (b) IN (2, 3) (type: boolean) + Statistics: Num rows: 1000/1000 Data size: 8000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (b) IN (2, 3) (type: boolean) + Statistics: Num rows: 200/200 Data size: 1600 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: sum(a) + keys: b (type: int) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 2/2 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 2/2 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: bigint) + Execution mode: vectorized + Reduce Operator Tree: + Group By Operator + aggregations: sum(VALUE._col0) + keys: KEY._col0 (type: int) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 2/2 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col1 (type: bigint) + outputColumnNames: _col0 + Statistics: Num rows: 2/2 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 2/2 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: select sum(a) from t3 where a=1 or a=2 group by b +PREHOOK: type: QUERY +PREHOOK: Input: default@t3 +#### A masked pattern was here #### +POSTHOOK: query: select sum(a) from t3 where a=1 or a=2 group by b +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t3 +#### A masked pattern was here #### +PREHOOK: query: explain analyze select sum(a) from t3 where a=1 or a=2 group by b +PREHOOK: type: QUERY +POSTHOOK: query: explain analyze select sum(a) from t3 where a=1 or a=2 group by b +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Map Reduce + Map Operator Tree: + TableScan + alias: t3 + filterExpr: ((a = 1) or (a = 2)) (type: boolean) + Statistics: Num rows: 1000/1000 Data size: 8000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: ((a = 1) or (a = 2)) (type: boolean) + Statistics: Num rows: 200/200 Data size: 1600 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: sum(a) + keys: b (type: int) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 10/10 Data size: 120 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 10/10 Data size: 120 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: bigint) + Execution mode: vectorized + Reduce Operator Tree: + Group By Operator + aggregations: sum(VALUE._col0) + keys: KEY._col0 (type: int) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 10/10 Data size: 120 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col1 (type: bigint) + outputColumnNames: _col0 + Statistics: Num rows: 10/10 Data size: 80 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 10/10 Data size: 80 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: select sum(a) from t3 where a=1 or (a=2 and b=3) group by b +PREHOOK: type: QUERY +PREHOOK: Input: default@t3 +#### A masked pattern was here #### +POSTHOOK: query: select sum(a) from t3 where a=1 or (a=2 and b=3) group by b +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t3 +#### A masked pattern was here #### +PREHOOK: query: explain analyze select sum(a) from t3 where a=1 or (a=2 and b=3) group by b +PREHOOK: type: QUERY +POSTHOOK: query: explain analyze select sum(a) from t3 where a=1 or (a=2 and b=3) group by b +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Map Reduce + Map Operator Tree: + TableScan + alias: t3 + filterExpr: ((a = 1) or ((a = 2) and (b = 3))) (type: boolean) + Statistics: Num rows: 1000/1000 Data size: 8000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (((a = 2) and (b = 3)) or (a = 1)) (type: boolean) + Statistics: Num rows: 110/110 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: sum(a) + keys: b (type: int) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 10/10 Data size: 120 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 10/10 Data size: 120 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: bigint) + Execution mode: vectorized + Reduce Operator Tree: + Group By Operator + aggregations: sum(VALUE._col0) + keys: KEY._col0 (type: int) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 10/10 Data size: 120 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col1 (type: bigint) + outputColumnNames: _col0 + Statistics: Num rows: 10/10 Data size: 80 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 10/10 Data size: 80 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: select sum(a) from t3 where a=1 group by b +PREHOOK: type: QUERY +PREHOOK: Input: default@t3 +#### A masked pattern was here #### +POSTHOOK: query: select sum(a) from t3 where a=1 group by b +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t3 +#### A masked pattern was here #### +PREHOOK: query: explain analyze select sum(a) from t3 where a=1 group by b +PREHOOK: type: QUERY +POSTHOOK: query: explain analyze select sum(a) from t3 where a=1 group by b +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Map Reduce + Map Operator Tree: + TableScan + alias: t3 + filterExpr: (a = 1) (type: boolean) + Statistics: Num rows: 1000/1000 Data size: 8000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (a = 1) (type: boolean) + Statistics: Num rows: 100/100 Data size: 800 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: b (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 100/100 Data size: 800 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: sum(1) + keys: _col0 (type: int) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 10/10 Data size: 120 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 10/10 Data size: 120 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: bigint) + Execution mode: vectorized + Reduce Operator Tree: + Group By Operator + aggregations: sum(VALUE._col0) + keys: KEY._col0 (type: int) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 10/10 Data size: 120 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col1 (type: bigint) + outputColumnNames: _col0 + Statistics: Num rows: 10/10 Data size: 80 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 10/10 Data size: 80 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: select sum(a) from t3 where a=1 and b=2 group by b +PREHOOK: type: QUERY +PREHOOK: Input: default@t3 +#### A masked pattern was here #### +POSTHOOK: query: select sum(a) from t3 where a=1 and b=2 group by b +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t3 +#### A masked pattern was here #### +PREHOOK: query: explain analyze select sum(a) from t3 where a=1 and b=2 group by b +PREHOOK: type: QUERY +POSTHOOK: query: explain analyze select sum(a) from t3 where a=1 and b=2 group by b +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Map Reduce + Map Operator Tree: + TableScan + alias: t3 + filterExpr: ((a = 1) and (b = 2)) (type: boolean) + Statistics: Num rows: 1000/1000 Data size: 8000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: ((a = 1) and (b = 2)) (type: boolean) + Statistics: Num rows: 10/10 Data size: 80 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + Statistics: Num rows: 10/10 Data size: 80 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: sum(1) + keys: 2 (type: int) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1/1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 1/1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: bigint) + Execution mode: vectorized + Reduce Operator Tree: + Group By Operator + aggregations: sum(VALUE._col0) + keys: KEY._col0 (type: int) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1/1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col1 (type: bigint) + outputColumnNames: _col0 + Statistics: Num rows: 1/1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1/1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: select sum(a) from t3 where a=1 and b=2 and c=3 group by b +PREHOOK: type: QUERY +PREHOOK: Input: default@t3 +#### A masked pattern was here #### +POSTHOOK: query: select sum(a) from t3 where a=1 and b=2 and c=3 group by b +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t3 +#### A masked pattern was here #### +PREHOOK: query: explain analyze select sum(a) from t3 where a=1 and b=2 and c=3 group by b +PREHOOK: type: QUERY +POSTHOOK: query: explain analyze select sum(a) from t3 where a=1 and b=2 and c=3 group by b +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Map Reduce + Map Operator Tree: + TableScan + alias: t3 + filterExpr: ((a = 1) and (b = 2) and (c = 3)) (type: boolean) + Statistics: Num rows: 1000/1000 Data size: 12000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: ((a = 1) and (b = 2) and (c = 3)) (type: boolean) + Statistics: Num rows: 1/1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + Statistics: Num rows: 1/1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: sum(1) + keys: 2 (type: int) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1/1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 1/1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: bigint) + Execution mode: vectorized + Reduce Operator Tree: + Group By Operator + aggregations: sum(VALUE._col0) + keys: KEY._col0 (type: int) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1/1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col1 (type: bigint) + outputColumnNames: _col0 + Statistics: Num rows: 1/1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1/1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: select sum(a) from t3 where (a=1 and b=2) or (a=2 and b=3) or (a=3 and b=4) group by b +PREHOOK: type: QUERY +PREHOOK: Input: default@t3 +#### A masked pattern was here #### +POSTHOOK: query: select sum(a) from t3 where (a=1 and b=2) or (a=2 and b=3) or (a=3 and b=4) group by b +POSTHOOK: type: QUERY +POSTHOOK: Input: default@t3 +#### A masked pattern was here #### +PREHOOK: query: explain analyze select sum(a) from t3 where (a=1 and b=2) or (a=2 and b=3) or (a=3 and b=4) group by b +PREHOOK: type: QUERY +POSTHOOK: query: explain analyze select sum(a) from t3 where (a=1 and b=2) or (a=2 and b=3) or (a=3 and b=4) group by b +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Map Reduce + Map Operator Tree: + TableScan + alias: t3 + filterExpr: (((a = 1) and (b = 2)) or ((a = 2) and (b = 3)) or ((a = 3) and (b = 4))) (type: boolean) + Statistics: Num rows: 1000/1000 Data size: 8000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: (((a = 1) and (b = 2)) or ((a = 2) and (b = 3)) or ((a = 3) and (b = 4))) (type: boolean) + Statistics: Num rows: 30/30 Data size: 240 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: sum(a) + keys: b (type: int) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 10/3 Data size: 120 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 10/3 Data size: 120 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: bigint) + Execution mode: vectorized + Reduce Operator Tree: + Group By Operator + aggregations: sum(VALUE._col0) + keys: KEY._col0 (type: int) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 10/3 Data size: 120 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col1 (type: bigint) + outputColumnNames: _col0 + Statistics: Num rows: 10/3 Data size: 80 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 10/3 Data size: 80 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + http://git-wip-us.apache.org/repos/asf/hive/blob/5c02fee2/ql/src/test/results/clientpositive/stat_estimate_related_col.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/stat_estimate_related_col.q.out b/ql/src/test/results/clientpositive/stat_estimate_related_col.q.out index 669adaf..2a2b7a8 100644 --- a/ql/src/test/results/clientpositive/stat_estimate_related_col.q.out +++ b/ql/src/test/results/clientpositive/stat_estimate_related_col.q.out @@ -160,25 +160,25 @@ STAGE PLANS: Statistics: Num rows: 8/8 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: a (type: int) - outputColumnNames: _col1 + outputColumnNames: a Statistics: Num rows: 8/8 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: sum(_col1) + aggregations: sum(a) keys: 2 (type: int) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1/1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator - key expressions: _col0 (type: int) + key expressions: 2 (type: int) sort order: + - Map-reduce partition columns: _col0 (type: int) + Map-reduce partition columns: 2 (type: int) Statistics: Num rows: 1/1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Execution mode: vectorized Reduce Operator Tree: Group By Operator aggregations: sum(VALUE._col0) - keys: KEY._col0 (type: int) + keys: 2 (type: int) mode: mergepartial outputColumnNames: _col0, _col1 Statistics: Num rows: 1/1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE @@ -222,32 +222,32 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t1 - filterExpr: (b = 2) (type: boolean) + filterExpr: ((2 = b) and (b = 2)) (type: boolean) Statistics: Num rows: 5/5 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: (b = 2) (type: boolean) + predicate: ((2 = b) and (b = 2)) (type: boolean) Statistics: Num rows: 1/1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: a (type: int) - outputColumnNames: _col1 + outputColumnNames: a Statistics: Num rows: 1/1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: sum(_col1) + aggregations: sum(a) keys: 2 (type: int) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1/1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator - key expressions: _col0 (type: int) + key expressions: 2 (type: int) sort order: + - Map-reduce partition columns: _col0 (type: int) + Map-reduce partition columns: 2 (type: int) Statistics: Num rows: 1/1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Execution mode: vectorized Reduce Operator Tree: Group By Operator aggregations: sum(VALUE._col0) - keys: KEY._col0 (type: int) + keys: 2 (type: int) mode: mergepartial outputColumnNames: _col0, _col1 Statistics: Num rows: 1/1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE @@ -298,25 +298,25 @@ STAGE PLANS: Statistics: Num rows: 1/1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: a (type: int) - outputColumnNames: _col1 + outputColumnNames: a Statistics: Num rows: 1/1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: sum(_col1) + aggregations: sum(a) keys: 2 (type: int) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1/1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator - key expressions: _col0 (type: int) + key expressions: 2 (type: int) sort order: + - Map-reduce partition columns: _col0 (type: int) + Map-reduce partition columns: 2 (type: int) Statistics: Num rows: 1/1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Execution mode: vectorized Reduce Operator Tree: Group By Operator aggregations: sum(VALUE._col0) - keys: KEY._col0 (type: int) + keys: 2 (type: int) mode: mergepartial outputColumnNames: _col0, _col1 Statistics: Num rows: 1/1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE @@ -367,25 +367,25 @@ STAGE PLANS: Statistics: Num rows: 8/8 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: a (type: int) - outputColumnNames: _col1 + outputColumnNames: a Statistics: Num rows: 8/8 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: sum(_col1) + aggregations: sum(a) keys: 2 (type: int) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1/1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator - key expressions: _col0 (type: int) + key expressions: 2 (type: int) sort order: + - Map-reduce partition columns: _col0 (type: int) + Map-reduce partition columns: 2 (type: int) Statistics: Num rows: 1/1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Execution mode: vectorized Reduce Operator Tree: Group By Operator aggregations: sum(VALUE._col0) - keys: KEY._col0 (type: int) + keys: 2 (type: int) mode: mergepartial outputColumnNames: _col0, _col1 Statistics: Num rows: 1/1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE @@ -407,7 +407,6 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Shuffle Join JOIN[8][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product PREHOOK: query: select count(*) from t8 ta, t8 tb where ta.a = tb.b and ta.a=3 PREHOOK: type: QUERY PREHOOK: Input: default@t8 @@ -416,7 +415,6 @@ POSTHOOK: query: select count(*) from t8 ta, t8 tb where ta.a = tb.b and ta.a=3 POSTHOOK: type: QUERY POSTHOOK: Input: default@t8 #### A masked pattern was here #### -Warning: Shuffle Join JOIN[8][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product PREHOOK: query: explain analyze select count(*) from t8 ta, t8 tb where ta.a = tb.b and ta.a=3 PREHOOK: type: QUERY POSTHOOK: query: explain analyze select count(*) from t8 ta, t8 tb where ta.a = tb.b and ta.a=3 @@ -437,11 +435,11 @@ STAGE PLANS: Filter Operator predicate: (a = 3) (type: boolean) Statistics: Num rows: 8/8 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator + Reduce Output Operator + key expressions: 3 (type: int) + sort order: + + Map-reduce partition columns: 3 (type: int) Statistics: Num rows: 8/8 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - sort order: - Statistics: Num rows: 8/8 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE TableScan alias: tb filterExpr: (b = 3) (type: boolean) @@ -449,18 +447,18 @@ STAGE PLANS: Filter Operator predicate: (b = 3) (type: boolean) Statistics: Num rows: 8/8 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator + Reduce Output Operator + key expressions: 3 (type: int) + sort order: + + Map-reduce partition columns: 3 (type: int) Statistics: Num rows: 8/8 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - sort order: - Statistics: Num rows: 8/8 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 - 1 + 0 a (type: int) + 1 b (type: int) Statistics: Num rows: 64/64 Data size: 512 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() @@ -525,32 +523,32 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t8 - filterExpr: ((b) IN (1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50) and (b = 2)) (type: boolean) + filterExpr: ((b) IN (1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50) and (b = 2) and (2 = b)) (type: boolean) Statistics: Num rows: 40/40 Data size: 320 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: ((b = 2) and (b) IN (1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50)) (type: boolean) + predicate: ((2 = b) and (b = 2) and (b) IN (1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50)) (type: boolean) Statistics: Num rows: 8/8 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: a (type: int) - outputColumnNames: _col1 + outputColumnNames: a Statistics: Num rows: 8/8 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: sum(_col1) + aggregations: sum(a) keys: 2 (type: int) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1/1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator - key expressions: _col0 (type: int) + key expressions: 2 (type: int) sort order: + - Map-reduce partition columns: _col0 (type: int) + Map-reduce partition columns: 2 (type: int) Statistics: Num rows: 1/1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Execution mode: vectorized Reduce Operator Tree: Group By Operator aggregations: sum(VALUE._col0) - keys: KEY._col0 (type: int) + keys: 2 (type: int) mode: mergepartial outputColumnNames: _col0, _col1 Statistics: Num rows: 1/1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE @@ -594,32 +592,32 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t8 - filterExpr: (b = 2) (type: boolean) + filterExpr: ((b = 2) and ((b = 1) or (b = 2))) (type: boolean) Statistics: Num rows: 40/40 Data size: 320 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: (b = 2) (type: boolean) + predicate: (((b = 1) or (b = 2)) and (b = 2)) (type: boolean) Statistics: Num rows: 8/8 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: a (type: int) - outputColumnNames: _col1 + outputColumnNames: a Statistics: Num rows: 8/8 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: sum(_col1) + aggregations: sum(a) keys: 2 (type: int) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1/1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator - key expressions: _col0 (type: int) + key expressions: 2 (type: int) sort order: + - Map-reduce partition columns: _col0 (type: int) + Map-reduce partition columns: 2 (type: int) Statistics: Num rows: 1/1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Execution mode: vectorized Reduce Operator Tree: Group By Operator aggregations: sum(VALUE._col0) - keys: KEY._col0 (type: int) + keys: 2 (type: int) mode: mergepartial outputColumnNames: _col0, _col1 Statistics: Num rows: 1/1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE @@ -663,27 +661,32 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t8 - Statistics: Num rows: 40/1 Data size: 320 Basic stats: COMPLETE Column stats: COMPLETE + filterExpr: ((b = 2) and ((b = 1) or (b = 2)) and ((b = 1) or (b = 3))) (type: boolean) + Statistics: Num rows: 40/40 Data size: 320 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: false (type: boolean) - Statistics: Num rows: 1/0 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: sum(a) - keys: b (type: int) - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1/0 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) + predicate: (((b = 1) or (b = 2)) and ((b = 1) or (b = 3)) and (b = 2)) (type: boolean) + Statistics: Num rows: 8/0 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: a (type: int) + outputColumnNames: a + Statistics: Num rows: 8/0 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: sum(a) + keys: 2 (type: int) + mode: hash + outputColumnNames: _col0, _col1 Statistics: Num rows: 1/0 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: bigint) + Reduce Output Operator + key expressions: 2 (type: int) + sort order: + + Map-reduce partition columns: 2 (type: int) + Statistics: Num rows: 1/0 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: bigint) Execution mode: vectorized Reduce Operator Tree: Group By Operator aggregations: sum(VALUE._col0) - keys: KEY._col0 (type: int) + keys: 2 (type: int) mode: mergepartial outputColumnNames: _col0, _col1 Statistics: Num rows: 1/0 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE @@ -743,30 +746,32 @@ STAGE PLANS: Map Operator Tree: TableScan alias: t8 - filterExpr: ((b = 2) and (a = 3)) (type: boolean) + filterExpr: ((b = 2) and ((b = 1) or (b = 2)) and (a = 3) and ((a = 3) or (a = 4))) (type: boolean) Statistics: Num rows: 40/40 Data size: 320 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: ((a = 3) and (b = 2)) (type: boolean) - Statistics: Num rows: 8/0 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE + predicate: (((a = 3) or (a = 4)) and ((b = 1) or (b = 2)) and (a = 3) and (b = 2)) (type: boolean) + Statistics: Num rows: 2/0 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - Statistics: Num rows: 8/0 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE + expressions: 3 (type: int) + outputColumnNames: a + Statistics: Num rows: 2/0 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: sum(3) + aggregations: sum(a) keys: 2 (type: int) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 1/0 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator - key expressions: _col0 (type: int) + key expressions: 2 (type: int) sort order: + - Map-reduce partition columns: _col0 (type: int) + Map-reduce partition columns: 2 (type: int) Statistics: Num rows: 1/0 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Execution mode: vectorized Reduce Operator Tree: Group By Operator aggregations: sum(VALUE._col0) - keys: KEY._col0 (type: int) + keys: 2 (type: int) mode: mergepartial outputColumnNames: _col0, _col1 Statistics: Num rows: 1/0 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE http://git-wip-us.apache.org/repos/asf/hive/blob/5c02fee2/ql/src/test/results/clientpositive/tez/explainanalyze_1.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/tez/explainanalyze_1.q.out b/ql/src/test/results/clientpositive/tez/explainanalyze_1.q.out index 3ad2ba2..b9eefdb 100644 --- a/ql/src/test/results/clientpositive/tez/explainanalyze_1.q.out +++ b/ql/src/test/results/clientpositive/tez/explainanalyze_1.q.out @@ -298,7 +298,7 @@ Stage-0 Output:["_col0"],aggregations:["count()"] <-Reducer 2 [CUSTOM_SIMPLE_EDGE] PARTITION_ONLY_SHUFFLE [RS_10] - Merge Join Operator [MERGEJOIN_28] (rows=262/0 width=8) + Merge Join Operator [MERGEJOIN_28] (rows=166/0 width=8) Conds:RS_6._col0=RS_7._col0(Inner) <-Map 1 [SIMPLE_EDGE] SHUFFLE [RS_6] @@ -347,7 +347,7 @@ Stage-0 Output:["_col0"],aggregations:["count()"] <-Reducer 2 [CUSTOM_SIMPLE_EDGE] PARTITION_ONLY_SHUFFLE [RS_10] - Merge Join Operator [MERGEJOIN_28] (rows=262/1019 width=8) + Merge Join Operator [MERGEJOIN_28] (rows=166/1019 width=8) Conds:RS_6._col0=RS_7._col0(Inner) <-Map 1 [SIMPLE_EDGE] SHUFFLE [RS_6] http://git-wip-us.apache.org/repos/asf/hive/blob/5c02fee2/ql/src/test/results/clientpositive/tez/explainanalyze_4.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/tez/explainanalyze_4.q.out b/ql/src/test/results/clientpositive/tez/explainanalyze_4.q.out index d7d11d8..7d06030 100644 --- a/ql/src/test/results/clientpositive/tez/explainanalyze_4.q.out +++ b/ql/src/test/results/clientpositive/tez/explainanalyze_4.q.out @@ -44,11 +44,11 @@ Stage-0 Stage-1 Reducer 3 File Output Operator [FS_12] - Select Operator [SEL_11] (rows=2048/10 width=552) + Select Operator [SEL_11] (rows=1019/10 width=484) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14","_col15","_col16","_col17","_col18","_col19","_col20","_col21","_col22","_col23"] <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_10] - Merge Join Operator [MERGEJOIN_27] (rows=2048/10 width=552) + Merge Join Operator [MERGEJOIN_27] (rows=1019/10 width=484) Conds:RS_6._col2=RS_7._col2(Inner),Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14","_col15","_col16","_col17","_col18","_col19","_col20","_col21","_col22","_col23"] <-Map 1 [SIMPLE_EDGE] SHUFFLE [RS_6] @@ -143,7 +143,7 @@ Stage-0 Output:["_col0"],aggregations:["count()"] <-Reducer 2 [CUSTOM_SIMPLE_EDGE] PARTITION_ONLY_SHUFFLE [RS_10] - Merge Join Operator [MERGEJOIN_28] (rows=2048/10 width=8) + Merge Join Operator [MERGEJOIN_28] (rows=1019/10 width=8) Conds:RS_6._col0=RS_7._col0(Inner) <-Map 1 [SIMPLE_EDGE] SHUFFLE [RS_6] @@ -232,16 +232,16 @@ Stage-0 Stage-1 Reducer 4 File Output Operator [FS_15] - Select Operator [SEL_14] (rows=631/5 width=11) + Select Operator [SEL_14] (rows=1019/5 width=10) Output:["_col0","_col1"] <-Reducer 3 [SIMPLE_EDGE] SHUFFLE [RS_13] - Group By Operator [GBY_11] (rows=631/5 width=11) + Group By Operator [GBY_11] (rows=1019/5 width=10) Output:["_col0","_col1"],aggregations:["count()"],keys:KEY._col0 <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_10] PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_30] (rows=2048/10 width=3) + Merge Join Operator [MERGEJOIN_30] (rows=1019/10 width=2) Conds:RS_6._col1=RS_7._col0(Inner),Output:["_col0"] <-Map 1 [SIMPLE_EDGE] SHUFFLE [RS_6] http://git-wip-us.apache.org/repos/asf/hive/blob/5c02fee2/ql/src/test/results/clientpositive/tez/hybridgrace_hashjoin_1.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/tez/hybridgrace_hashjoin_1.q.out b/ql/src/test/results/clientpositive/tez/hybridgrace_hashjoin_1.q.out index 029f79c..851899d 100644 --- a/ql/src/test/results/clientpositive/tez/hybridgrace_hashjoin_1.q.out +++ b/ql/src/test/results/clientpositive/tez/hybridgrace_hashjoin_1.q.out @@ -298,7 +298,7 @@ STAGE PLANS: 1 _col0 (type: int) input vertices: 1 Map 3 - Statistics: Num rows: 18464 Data size: 147712 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 13785 Data size: 110280 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash @@ -415,7 +415,7 @@ STAGE PLANS: 1 _col0 (type: int) input vertices: 1 Map 3 - Statistics: Num rows: 18464 Data size: 147712 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 13785 Data size: 110280 Basic stats: COMPLETE Column stats: COMPLETE HybridGraceHashJoin: true Group By Operator aggregations: count()
