http://git-wip-us.apache.org/repos/asf/hive/blob/6f5c1135/ql/src/test/results/clientpositive/auto_sortmerge_join_9.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/auto_sortmerge_join_9.q.out b/ql/src/test/results/clientpositive/auto_sortmerge_join_9.q.out deleted file mode 100644 index 70c820f..0000000 --- a/ql/src/test/results/clientpositive/auto_sortmerge_join_9.q.out +++ /dev/null @@ -1,4820 +0,0 @@ -PREHOOK: query: -- SORT_QUERY_RESULTS - -CREATE TABLE tbl1(key int, value string) CLUSTERED BY (key) SORTED BY (key) INTO 2 BUCKETS -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@tbl1 -POSTHOOK: query: -- SORT_QUERY_RESULTS - -CREATE TABLE tbl1(key int, value string) CLUSTERED BY (key) SORTED BY (key) INTO 2 BUCKETS -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@tbl1 -PREHOOK: query: CREATE TABLE tbl2(key int, value string) CLUSTERED BY (key) SORTED BY (key) INTO 2 BUCKETS -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@tbl2 -POSTHOOK: query: CREATE TABLE tbl2(key int, value string) CLUSTERED BY (key) SORTED BY (key) INTO 2 BUCKETS -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@tbl2 -PREHOOK: query: insert overwrite table tbl1 -select * from src where key < 10 -PREHOOK: type: QUERY -PREHOOK: Input: default@src -PREHOOK: Output: default@tbl1 -POSTHOOK: query: insert overwrite table tbl1 -select * from src where key < 10 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -POSTHOOK: Output: default@tbl1 -POSTHOOK: Lineage: tbl1.key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: tbl1.value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] -PREHOOK: query: insert overwrite table tbl2 -select * from src where key < 10 -PREHOOK: type: QUERY -PREHOOK: Input: default@src -PREHOOK: Output: default@tbl2 -POSTHOOK: query: insert overwrite table tbl2 -select * from src where key < 10 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -POSTHOOK: Output: default@tbl2 -POSTHOOK: Lineage: tbl2.key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: tbl2.value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] -PREHOOK: query: -- The join is being performed as part of sub-query. It should be converted to a sort-merge join -explain -select count(*) from ( - select a.key as key, a.value as val1, b.value as val2 from tbl1 a join tbl2 b on a.key = b.key -) subq1 -PREHOOK: type: QUERY -POSTHOOK: query: -- The join is being performed as part of sub-query. It should be converted to a sort-merge join -explain -select count(*) from ( - select a.key as key, a.value as val1, b.value as val2 from tbl1 a join tbl2 b on a.key = b.key -) subq1 -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: a - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE - Sorted Merge Bucket Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Reduce Output Operator - sort order: - value expressions: _col0 (type: bigint) - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0) - mode: mergepartial - outputColumnNames: _col0 - File Output Operator - compressed: false - 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 count(*) from ( - select a.key as key, a.value as val1, b.value as val2 from tbl1 a join tbl2 b on a.key = b.key -) subq1 -PREHOOK: type: QUERY -PREHOOK: Input: default@tbl1 -PREHOOK: Input: default@tbl2 -#### A masked pattern was here #### -POSTHOOK: query: select count(*) from ( - select a.key as key, a.value as val1, b.value as val2 from tbl1 a join tbl2 b on a.key = b.key -) subq1 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@tbl1 -POSTHOOK: Input: default@tbl2 -#### A masked pattern was here #### -22 -PREHOOK: query: -- The join is being performed as part of sub-query. It should be converted to a sort-merge join -explain -select key, count(*) from -( - select a.key as key, a.value as val1, b.value as val2 from tbl1 a join tbl2 b on a.key = b.key -) subq1 -group by key -PREHOOK: type: QUERY -POSTHOOK: query: -- The join is being performed as part of sub-query. It should be converted to a sort-merge join -explain -select key, count(*) from -( - select a.key as key, a.value as val1, b.value as val2 from tbl1 a join tbl2 b on a.key = b.key -) subq1 -group by key -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: a - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE - Sorted Merge Bucket Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0 - Group By Operator - aggregations: count() - keys: _col0 (type: int) - mode: hash - outputColumnNames: _col0, _col1 - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - value expressions: _col1 (type: bigint) - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0) - keys: KEY._col0 (type: int) - mode: mergepartial - outputColumnNames: _col0, _col1 - File Output Operator - compressed: false - 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 key, count(*) from -( - select a.key as key, a.value as val1, b.value as val2 from tbl1 a join tbl2 b on a.key = b.key -) subq1 -group by key -PREHOOK: type: QUERY -PREHOOK: Input: default@tbl1 -PREHOOK: Input: default@tbl2 -#### A masked pattern was here #### -POSTHOOK: query: select key, count(*) from -( - select a.key as key, a.value as val1, b.value as val2 from tbl1 a join tbl2 b on a.key = b.key -) subq1 -group by key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@tbl1 -POSTHOOK: Input: default@tbl2 -#### A masked pattern was here #### -0 9 -2 1 -4 1 -5 9 -8 1 -9 1 -PREHOOK: query: -- The join is being performed as part of more than one sub-query. It should be converted to a sort-merge join -explain -select count(*) from -( - select key, count(*) from - ( - select a.key as key, a.value as val1, b.value as val2 from tbl1 a join tbl2 b on a.key = b.key - ) subq1 - group by key -) subq2 -PREHOOK: type: QUERY -POSTHOOK: query: -- The join is being performed as part of more than one sub-query. It should be converted to a sort-merge join -explain -select count(*) from -( - select key, count(*) from - ( - select a.key as key, a.value as val1, b.value as val2 from tbl1 a join tbl2 b on a.key = b.key - ) subq1 - group by key -) subq2 -POSTHOOK: type: QUERY -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-2 depends on stages: Stage-1 - Stage-0 depends on stages: Stage-2 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: a - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE - Sorted Merge Bucket Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0 - 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) - Reduce Operator Tree: - Group By Operator - keys: KEY._col0 (type: int) - mode: mergepartial - outputColumnNames: _col0 - Select Operator - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - sort order: - value expressions: _col0 (type: bigint) - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0) - mode: mergepartial - outputColumnNames: _col0 - File Output Operator - compressed: false - 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 count(*) from -( - select key, count(*) from - ( - select a.key as key, a.value as val1, b.value as val2 from tbl1 a join tbl2 b on a.key = b.key - ) subq1 - group by key -) subq2 -PREHOOK: type: QUERY -PREHOOK: Input: default@tbl1 -PREHOOK: Input: default@tbl2 -#### A masked pattern was here #### -POSTHOOK: query: select count(*) from -( - select key, count(*) from - ( - select a.key as key, a.value as val1, b.value as val2 from tbl1 a join tbl2 b on a.key = b.key - ) subq1 - group by key -) subq2 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@tbl1 -POSTHOOK: Input: default@tbl2 -#### A masked pattern was here #### -6 -PREHOOK: query: -- A join is being performed across different sub-queries, where a join is being performed in each of them. --- Each sub-query should be converted to a sort-merge join. -explain -select src1.key, src1.cnt1, src2.cnt1 from -( - select key, count(*) as cnt1 from - ( - select a.key as key, a.value as val1, b.value as val2 from tbl1 a join tbl2 b on a.key = b.key - ) subq1 group by key -) src1 -join -( - select key, count(*) as cnt1 from - ( - select a.key as key, a.value as val1, b.value as val2 from tbl1 a join tbl2 b on a.key = b.key - ) subq2 group by key -) src2 -on src1.key = src2.key -PREHOOK: type: QUERY -POSTHOOK: query: -- A join is being performed across different sub-queries, where a join is being performed in each of them. --- Each sub-query should be converted to a sort-merge join. -explain -select src1.key, src1.cnt1, src2.cnt1 from -( - select key, count(*) as cnt1 from - ( - select a.key as key, a.value as val1, b.value as val2 from tbl1 a join tbl2 b on a.key = b.key - ) subq1 group by key -) src1 -join -( - select key, count(*) as cnt1 from - ( - select a.key as key, a.value as val1, b.value as val2 from tbl1 a join tbl2 b on a.key = b.key - ) subq2 group by key -) src2 -on src1.key = src2.key -POSTHOOK: type: QUERY -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-8 depends on stages: Stage-1, Stage-4 , consists of Stage-9, Stage-10, Stage-2 - Stage-9 has a backup stage: Stage-2 - Stage-6 depends on stages: Stage-9 - Stage-10 has a backup stage: Stage-2 - Stage-7 depends on stages: Stage-10 - Stage-2 - Stage-4 is a root stage - Stage-0 depends on stages: Stage-6, Stage-7, Stage-2 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: a - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE - Sorted Merge Bucket Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0 - Group By Operator - aggregations: count() - keys: _col0 (type: int) - mode: hash - outputColumnNames: _col0, _col1 - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - value expressions: _col1 (type: bigint) - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0) - keys: KEY._col0 (type: int) - mode: mergepartial - outputColumnNames: _col0, _col1 - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-8 - Conditional Operator - - Stage: Stage-9 - Map Reduce Local Work - Alias -> Map Local Tables: - $INTNAME1 - Fetch Operator - limit: -1 - Alias -> Map Local Operator Tree: - $INTNAME1 - TableScan - HashTable Sink Operator - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - - Stage: Stage-6 - Map Reduce - Map Operator Tree: - TableScan - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0, _col1, _col3 - Select Operator - expressions: _col0 (type: int), _col1 (type: bigint), _col3 (type: bigint) - outputColumnNames: _col0, _col1, _col2 - File Output Operator - compressed: false - 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 - Local Work: - Map Reduce Local Work - - Stage: Stage-10 - Map Reduce Local Work - Alias -> Map Local Tables: - $INTNAME - Fetch Operator - limit: -1 - Alias -> Map Local Operator Tree: - $INTNAME - TableScan - HashTable Sink Operator - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - - Stage: Stage-7 - Map Reduce - Map Operator Tree: - TableScan - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0, _col1, _col3 - Select Operator - expressions: _col0 (type: int), _col1 (type: bigint), _col3 (type: bigint) - outputColumnNames: _col0, _col1, _col2 - File Output Operator - compressed: false - 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 - Local Work: - Map Reduce Local Work - - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - value expressions: _col1 (type: bigint) - TableScan - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - value expressions: _col1 (type: bigint) - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0, _col1, _col3 - Select Operator - expressions: _col0 (type: int), _col1 (type: bigint), _col3 (type: bigint) - outputColumnNames: _col0, _col1, _col2 - File Output Operator - compressed: false - 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-4 - Map Reduce - Map Operator Tree: - TableScan - alias: a - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE - Sorted Merge Bucket Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0 - Group By Operator - aggregations: count() - keys: _col0 (type: int) - mode: hash - outputColumnNames: _col0, _col1 - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - value expressions: _col1 (type: bigint) - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0) - keys: KEY._col0 (type: int) - mode: mergepartial - outputColumnNames: _col0, _col1 - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: select src1.key, src1.cnt1, src2.cnt1 from -( - select key, count(*) as cnt1 from - ( - select a.key as key, a.value as val1, b.value as val2 from tbl1 a join tbl2 b on a.key = b.key - ) subq1 group by key -) src1 -join -( - select key, count(*) as cnt1 from - ( - select a.key as key, a.value as val1, b.value as val2 from tbl1 a join tbl2 b on a.key = b.key - ) subq2 group by key -) src2 -on src1.key = src2.key -PREHOOK: type: QUERY -PREHOOK: Input: default@tbl1 -PREHOOK: Input: default@tbl2 -#### A masked pattern was here #### -POSTHOOK: query: select src1.key, src1.cnt1, src2.cnt1 from -( - select key, count(*) as cnt1 from - ( - select a.key as key, a.value as val1, b.value as val2 from tbl1 a join tbl2 b on a.key = b.key - ) subq1 group by key -) src1 -join -( - select key, count(*) as cnt1 from - ( - select a.key as key, a.value as val1, b.value as val2 from tbl1 a join tbl2 b on a.key = b.key - ) subq2 group by key -) src2 -on src1.key = src2.key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@tbl1 -POSTHOOK: Input: default@tbl2 -#### A masked pattern was here #### -0 9 9 -2 1 1 -4 1 1 -5 9 9 -8 1 1 -9 1 1 -PREHOOK: query: -- The subquery itself is being joined. Since the sub-query only contains selects and filters, it should --- be converted to a sort-merge join. -explain -select count(*) from - (select a.key as key, a.value as value from tbl1 a where key < 6) subq1 - join - (select a.key as key, a.value as value from tbl2 a where key < 6) subq2 - on subq1.key = subq2.key -PREHOOK: type: QUERY -POSTHOOK: query: -- The subquery itself is being joined. Since the sub-query only contains selects and filters, it should --- be converted to a sort-merge join. -explain -select count(*) from - (select a.key as key, a.value as value from tbl1 a where key < 6) subq1 - join - (select a.key as key, a.value as value from tbl2 a where key < 6) subq2 - on subq1.key = subq2.key -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: a - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (key < 6) (type: boolean) - Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE - Sorted Merge Bucket Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Reduce Output Operator - sort order: - value expressions: _col0 (type: bigint) - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0) - mode: mergepartial - outputColumnNames: _col0 - File Output Operator - compressed: false - 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 count(*) from - (select a.key as key, a.value as value from tbl1 a where key < 6) subq1 - join - (select a.key as key, a.value as value from tbl2 a where key < 6) subq2 - on subq1.key = subq2.key -PREHOOK: type: QUERY -PREHOOK: Input: default@tbl1 -PREHOOK: Input: default@tbl2 -#### A masked pattern was here #### -POSTHOOK: query: select count(*) from - (select a.key as key, a.value as value from tbl1 a where key < 6) subq1 - join - (select a.key as key, a.value as value from tbl2 a where key < 6) subq2 - on subq1.key = subq2.key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@tbl1 -POSTHOOK: Input: default@tbl2 -#### A masked pattern was here #### -20 -PREHOOK: query: -- The subquery itself is being joined. Since the sub-query only contains selects and filters, it should --- be converted to a sort-merge join, although there is more than one level of sub-query -explain -select count(*) from - ( - select * from - ( - select a.key as key, a.value as value from tbl1 a where key < 8 - ) subq1 - where key < 6 - ) subq2 - join tbl2 b - on subq2.key = b.key -PREHOOK: type: QUERY -POSTHOOK: query: -- The subquery itself is being joined. Since the sub-query only contains selects and filters, it should --- be converted to a sort-merge join, although there is more than one level of sub-query -explain -select count(*) from - ( - select * from - ( - select a.key as key, a.value as value from tbl1 a where key < 8 - ) subq1 - where key < 6 - ) subq2 - join tbl2 b - on subq2.key = b.key -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: a - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: ((key < 8) and (key < 6)) (type: boolean) - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE - Sorted Merge Bucket Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Reduce Output Operator - sort order: - value expressions: _col0 (type: bigint) - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0) - mode: mergepartial - outputColumnNames: _col0 - File Output Operator - compressed: false - 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 count(*) from - ( - select * from - ( - select a.key as key, a.value as value from tbl1 a where key < 8 - ) subq1 - where key < 6 - ) subq2 - join tbl2 b - on subq2.key = b.key -PREHOOK: type: QUERY -PREHOOK: Input: default@tbl1 -PREHOOK: Input: default@tbl2 -#### A masked pattern was here #### -POSTHOOK: query: select count(*) from - ( - select * from - ( - select a.key as key, a.value as value from tbl1 a where key < 8 - ) subq1 - where key < 6 - ) subq2 - join tbl2 b - on subq2.key = b.key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@tbl1 -POSTHOOK: Input: default@tbl2 -#### A masked pattern was here #### -20 -PREHOOK: query: -- Both the tables are nested sub-queries i.e more then 1 level of sub-query. --- The join should be converted to a sort-merge join -explain -select count(*) from - ( - select * from - ( - select a.key as key, a.value as value from tbl1 a where key < 8 - ) subq1 - where key < 6 - ) subq2 - join - ( - select * from - ( - select a.key as key, a.value as value from tbl1 a where key < 8 - ) subq3 - where key < 6 - ) subq4 - on subq2.key = subq4.key -PREHOOK: type: QUERY -POSTHOOK: query: -- Both the tables are nested sub-queries i.e more then 1 level of sub-query. --- The join should be converted to a sort-merge join -explain -select count(*) from - ( - select * from - ( - select a.key as key, a.value as value from tbl1 a where key < 8 - ) subq1 - where key < 6 - ) subq2 - join - ( - select * from - ( - select a.key as key, a.value as value from tbl1 a where key < 8 - ) subq3 - where key < 6 - ) subq4 - on subq2.key = subq4.key -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: a - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: ((key < 8) and (key < 6)) (type: boolean) - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE - Sorted Merge Bucket Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Reduce Output Operator - sort order: - value expressions: _col0 (type: bigint) - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0) - mode: mergepartial - outputColumnNames: _col0 - File Output Operator - compressed: false - 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 count(*) from - ( - select * from - ( - select a.key as key, a.value as value from tbl1 a where key < 8 - ) subq1 - where key < 6 - ) subq2 - join - ( - select * from - ( - select a.key as key, a.value as value from tbl1 a where key < 8 - ) subq3 - where key < 6 - ) subq4 - on subq2.key = subq4.key -PREHOOK: type: QUERY -PREHOOK: Input: default@tbl1 -#### A masked pattern was here #### -POSTHOOK: query: select count(*) from - ( - select * from - ( - select a.key as key, a.value as value from tbl1 a where key < 8 - ) subq1 - where key < 6 - ) subq2 - join - ( - select * from - ( - select a.key as key, a.value as value from tbl1 a where key < 8 - ) subq3 - where key < 6 - ) subq4 - on subq2.key = subq4.key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@tbl1 -#### A masked pattern was here #### -20 -PREHOOK: query: -- The subquery itself is being joined. Since the sub-query only contains selects and filters and the join key --- is not getting modified, it should be converted to a sort-merge join. Note that the sub-query modifies one --- item, but that is not part of the join key. -explain -select count(*) from - (select a.key as key, concat(a.value, a.value) as value from tbl1 a where key < 8) subq1 - join - (select a.key as key, concat(a.value, a.value) as value from tbl2 a where key < 8) subq2 - on subq1.key = subq2.key -PREHOOK: type: QUERY -POSTHOOK: query: -- The subquery itself is being joined. Since the sub-query only contains selects and filters and the join key --- is not getting modified, it should be converted to a sort-merge join. Note that the sub-query modifies one --- item, but that is not part of the join key. -explain -select count(*) from - (select a.key as key, concat(a.value, a.value) as value from tbl1 a where key < 8) subq1 - join - (select a.key as key, concat(a.value, a.value) as value from tbl2 a where key < 8) subq2 - on subq1.key = subq2.key -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: a - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (key < 8) (type: boolean) - Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE - Sorted Merge Bucket Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Reduce Output Operator - sort order: - value expressions: _col0 (type: bigint) - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0) - mode: mergepartial - outputColumnNames: _col0 - File Output Operator - compressed: false - 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 count(*) from - (select a.key as key, concat(a.value, a.value) as value from tbl1 a where key < 8) subq1 - join - (select a.key as key, concat(a.value, a.value) as value from tbl2 a where key < 8) subq2 - on subq1.key = subq2.key -PREHOOK: type: QUERY -PREHOOK: Input: default@tbl1 -PREHOOK: Input: default@tbl2 -#### A masked pattern was here #### -POSTHOOK: query: select count(*) from - (select a.key as key, concat(a.value, a.value) as value from tbl1 a where key < 8) subq1 - join - (select a.key as key, concat(a.value, a.value) as value from tbl2 a where key < 8) subq2 - on subq1.key = subq2.key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@tbl1 -POSTHOOK: Input: default@tbl2 -#### A masked pattern was here #### -20 -PREHOOK: query: -- Since the join key is modified by the sub-query, neither sort-merge join not bucketized mapside --- join should be performed -explain -select count(*) from - (select a.key +1 as key, concat(a.value, a.value) as value from tbl1 a) subq1 - join - (select a.key +1 as key, concat(a.value, a.value) as value from tbl2 a) subq2 - on subq1.key = subq2.key -PREHOOK: type: QUERY -POSTHOOK: query: -- Since the join key is modified by the sub-query, neither sort-merge join not bucketized mapside --- join should be performed -explain -select count(*) from - (select a.key +1 as key, concat(a.value, a.value) as value from tbl1 a) subq1 - join - (select a.key +1 as key, concat(a.value, a.value) as value from tbl2 a) subq2 - on subq1.key = subq2.key -POSTHOOK: type: QUERY -STAGE DEPENDENCIES: - Stage-5 is a root stage - Stage-2 depends on stages: Stage-5 - Stage-0 depends on stages: Stage-2 - -STAGE PLANS: - Stage: Stage-5 - Map Reduce Local Work - Alias -> Map Local Tables: - $hdt$_0:a - Fetch Operator - limit: -1 - Alias -> Map Local Operator Tree: - $hdt$_0:a - TableScan - alias: a - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (key + 1) is not null (type: boolean) - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: (key + 1) (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE - HashTable Sink Operator - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - alias: a - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (key + 1) is not null (type: boolean) - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: (key + 1) (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - Statistics: Num rows: 11 Data size: 77 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: bigint) - Local Work: - Map Reduce Local Work - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0) - mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: select count(*) from - (select a.key +1 as key, concat(a.value, a.value) as value from tbl1 a) subq1 - join - (select a.key +1 as key, concat(a.value, a.value) as value from tbl2 a) subq2 - on subq1.key = subq2.key -PREHOOK: type: QUERY -PREHOOK: Input: default@tbl1 -PREHOOK: Input: default@tbl2 -#### A masked pattern was here #### -POSTHOOK: query: select count(*) from - (select a.key +1 as key, concat(a.value, a.value) as value from tbl1 a) subq1 - join - (select a.key +1 as key, concat(a.value, a.value) as value from tbl2 a) subq2 - on subq1.key = subq2.key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@tbl1 -POSTHOOK: Input: default@tbl2 -#### A masked pattern was here #### -22 -PREHOOK: query: -- The left table is a sub-query and the right table is not. --- It should be converted to a sort-merge join. -explain -select count(*) from - (select a.key as key, a.value as value from tbl1 a where key < 6) subq1 - join tbl2 a on subq1.key = a.key -PREHOOK: type: QUERY -POSTHOOK: query: -- The left table is a sub-query and the right table is not. --- It should be converted to a sort-merge join. -explain -select count(*) from - (select a.key as key, a.value as value from tbl1 a where key < 6) subq1 - join tbl2 a on subq1.key = a.key -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: a - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (key < 6) (type: boolean) - Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE - Sorted Merge Bucket Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Reduce Output Operator - sort order: - value expressions: _col0 (type: bigint) - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0) - mode: mergepartial - outputColumnNames: _col0 - File Output Operator - compressed: false - 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 count(*) from - (select a.key as key, a.value as value from tbl1 a where key < 6) subq1 - join tbl2 a on subq1.key = a.key -PREHOOK: type: QUERY -PREHOOK: Input: default@tbl1 -PREHOOK: Input: default@tbl2 -#### A masked pattern was here #### -POSTHOOK: query: select count(*) from - (select a.key as key, a.value as value from tbl1 a where key < 6) subq1 - join tbl2 a on subq1.key = a.key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@tbl1 -POSTHOOK: Input: default@tbl2 -#### A masked pattern was here #### -20 -PREHOOK: query: -- The right table is a sub-query and the left table is not. --- It should be converted to a sort-merge join. -explain -select count(*) from tbl1 a - join - (select a.key as key, a.value as value from tbl2 a where key < 6) subq1 - on a.key = subq1.key -PREHOOK: type: QUERY -POSTHOOK: query: -- The right table is a sub-query and the left table is not. --- It should be converted to a sort-merge join. -explain -select count(*) from tbl1 a - join - (select a.key as key, a.value as value from tbl2 a where key < 6) subq1 - on a.key = subq1.key -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: a - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (key < 6) (type: boolean) - Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE - Sorted Merge Bucket Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Reduce Output Operator - sort order: - value expressions: _col0 (type: bigint) - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0) - mode: mergepartial - outputColumnNames: _col0 - File Output Operator - compressed: false - 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 count(*) from tbl1 a - join - (select a.key as key, a.value as value from tbl2 a where key < 6) subq1 - on a.key = subq1.key -PREHOOK: type: QUERY -PREHOOK: Input: default@tbl1 -PREHOOK: Input: default@tbl2 -#### A masked pattern was here #### -POSTHOOK: query: select count(*) from tbl1 a - join - (select a.key as key, a.value as value from tbl2 a where key < 6) subq1 - on a.key = subq1.key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@tbl1 -POSTHOOK: Input: default@tbl2 -#### A masked pattern was here #### -20 -PREHOOK: query: -- There are more than 2 inputs to the join, all of them being sub-queries. --- It should be converted to to a sort-merge join -explain -select count(*) from - (select a.key as key, a.value as value from tbl1 a where key < 6) subq1 - join - (select a.key as key, a.value as value from tbl2 a where key < 6) subq2 - on (subq1.key = subq2.key) - join - (select a.key as key, a.value as value from tbl2 a where key < 6) subq3 - on (subq1.key = subq3.key) -PREHOOK: type: QUERY -POSTHOOK: query: -- There are more than 2 inputs to the join, all of them being sub-queries. --- It should be converted to to a sort-merge join -explain -select count(*) from - (select a.key as key, a.value as value from tbl1 a where key < 6) subq1 - join - (select a.key as key, a.value as value from tbl2 a where key < 6) subq2 - on (subq1.key = subq2.key) - join - (select a.key as key, a.value as value from tbl2 a where key < 6) subq3 - on (subq1.key = subq3.key) -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: a - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (key < 6) (type: boolean) - Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE - Sorted Merge Bucket Map Join Operator - condition map: - Inner Join 0 to 1 - Inner Join 0 to 2 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - 2 _col0 (type: int) - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Reduce Output Operator - sort order: - value expressions: _col0 (type: bigint) - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0) - mode: mergepartial - outputColumnNames: _col0 - File Output Operator - compressed: false - 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 count(*) from - (select a.key as key, a.value as value from tbl1 a where key < 6) subq1 - join - (select a.key as key, a.value as value from tbl2 a where key < 6) subq2 - on subq1.key = subq2.key - join - (select a.key as key, a.value as value from tbl2 a where key < 6) subq3 - on (subq1.key = subq3.key) -PREHOOK: type: QUERY -PREHOOK: Input: default@tbl1 -PREHOOK: Input: default@tbl2 -#### A masked pattern was here #### -POSTHOOK: query: select count(*) from - (select a.key as key, a.value as value from tbl1 a where key < 6) subq1 - join - (select a.key as key, a.value as value from tbl2 a where key < 6) subq2 - on subq1.key = subq2.key - join - (select a.key as key, a.value as value from tbl2 a where key < 6) subq3 - on (subq1.key = subq3.key) -POSTHOOK: type: QUERY -POSTHOOK: Input: default@tbl1 -POSTHOOK: Input: default@tbl2 -#### A masked pattern was here #### -56 -PREHOOK: query: -- The join is being performed on a nested sub-query, and an aggregation is performed after that. --- The join should be converted to a sort-merge join -explain -select count(*) from ( - select subq2.key as key, subq2.value as value1, b.value as value2 from - ( - select * from - ( - select a.key as key, a.value as value from tbl1 a where key < 8 - ) subq1 - where key < 6 - ) subq2 -join tbl2 b -on subq2.key = b.key) a -PREHOOK: type: QUERY -POSTHOOK: query: -- The join is being performed on a nested sub-query, and an aggregation is performed after that. --- The join should be converted to a sort-merge join -explain -select count(*) from ( - select subq2.key as key, subq2.value as value1, b.value as value2 from - ( - select * from - ( - select a.key as key, a.value as value from tbl1 a where key < 8 - ) subq1 - where key < 6 - ) subq2 -join tbl2 b -on subq2.key = b.key) a -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: a - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: ((key < 8) and (key < 6)) (type: boolean) - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE - Sorted Merge Bucket Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Reduce Output Operator - sort order: - value expressions: _col0 (type: bigint) - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0) - mode: mergepartial - outputColumnNames: _col0 - File Output Operator - compressed: false - 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 count(*) from ( - select subq2.key as key, subq2.value as value1, b.value as value2 from - ( - select * from - ( - select a.key as key, a.value as value from tbl1 a where key < 8 - ) subq1 - where key < 6 - ) subq2 -join tbl2 b -on subq2.key = b.key) a -PREHOOK: type: QUERY -PREHOOK: Input: default@tbl1 -PREHOOK: Input: default@tbl2 -#### A masked pattern was here #### -POSTHOOK: query: select count(*) from ( - select subq2.key as key, subq2.value as value1, b.value as value2 from - ( - select * from - ( - select a.key as key, a.value as value from tbl1 a where key < 8 - ) subq1 - where key < 6 - ) subq2 -join tbl2 b -on subq2.key = b.key) a -POSTHOOK: type: QUERY -POSTHOOK: Input: default@tbl1 -POSTHOOK: Input: default@tbl2 -#### A masked pattern was here #### -20 -PREHOOK: query: -- The join is being performed as part of sub-query. It should be converted to a sort-merge join -explain -select count(*) from ( - select a.key as key, a.value as val1, b.value as val2 from tbl1 a join tbl2 b on a.key = b.key -) subq1 -PREHOOK: type: QUERY -POSTHOOK: query: -- The join is being performed as part of sub-query. It should be converted to a sort-merge join -explain -select count(*) from ( - select a.key as key, a.value as val1, b.value as val2 from tbl1 a join tbl2 b on a.key = b.key -) subq1 -POSTHOOK: type: QUERY -STAGE DEPENDENCIES: - Stage-5 is a root stage , consists of Stage-6, Stage-7, Stage-1 - Stage-6 has a backup stage: Stage-1 - Stage-3 depends on stages: Stage-6 - Stage-7 has a backup stage: Stage-1 - Stage-4 depends on stages: Stage-7 - Stage-1 - Stage-0 depends on stages: Stage-3, Stage-4, Stage-1 - -STAGE PLANS: - Stage: Stage-5 - Conditional Operator - - Stage: Stage-6 - Map Reduce Local Work - Alias -> Map Local Tables: - $hdt$_1:b - Fetch Operator - limit: -1 - Alias -> Map Local Operator Tree: - $hdt$_1:b - TableScan - alias: b - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE - HashTable Sink Operator - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - - Stage: Stage-3 - Map Reduce - Map Operator Tree: - TableScan - alias: a - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Reduce Output Operator - sort order: - value expressions: _col0 (type: bigint) - Local Work: - Map Reduce Local Work - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0) - mode: mergepartial - outputColumnNames: _col0 - File Output Operator - compressed: false - 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-7 - Map Reduce Local Work - Alias -> Map Local Tables: - $hdt$_0:a - Fetch Operator - limit: -1 - Alias -> Map Local Operator Tree: - $hdt$_0:a - TableScan - alias: a - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE - HashTable Sink Operator - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - - Stage: Stage-4 - Map Reduce - Map Operator Tree: - TableScan - alias: b - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Reduce Output Operator - sort order: - value expressions: _col0 (type: bigint) - Local Work: - Map Reduce Local Work - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0) - mode: mergepartial - outputColumnNames: _col0 - File Output Operator - compressed: false - 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-1 - Map Reduce - Map Operator Tree: - TableScan - alias: a - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE - Sorted Merge Bucket Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Reduce Output Operator - sort order: - value expressions: _col0 (type: bigint) - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0) - mode: mergepartial - outputColumnNames: _col0 - File Output Operator - compressed: false - 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 count(*) from ( - select a.key as key, a.value as val1, b.value as val2 from tbl1 a join tbl2 b on a.key = b.key -) subq1 -PREHOOK: type: QUERY -PREHOOK: Input: default@tbl1 -PREHOOK: Input: default@tbl2 -#### A masked pattern was here #### -POSTHOOK: query: select count(*) from ( - select a.key as key, a.value as val1, b.value as val2 from tbl1 a join tbl2 b on a.key = b.key -) subq1 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@tbl1 -POSTHOOK: Input: default@tbl2 -#### A masked pattern was here #### -22 -PREHOOK: query: -- The join is being performed as part of sub-query. It should be converted to a sort-merge join -explain -select key, count(*) from -( - select a.key as key, a.value as val1, b.value as val2 from tbl1 a join tbl2 b on a.key = b.key -) subq1 -group by key -PREHOOK: type: QUERY -POSTHOOK: query: -- The join is being performed as part of sub-query. It should be converted to a sort-merge join -explain -select key, count(*) from -( - select a.key as key, a.value as val1, b.value as val2 from tbl1 a join tbl2 b on a.key = b.key -) subq1 -group by key -POSTHOOK: type: QUERY -STAGE DEPENDENCIES: - Stage-5 is a root stage , consists of Stage-6, Stage-7, Stage-1 - Stage-6 has a backup stage: Stage-1 - Stage-3 depends on stages: Stage-6 - Stage-7 has a backup stage: Stage-1 - Stage-4 depends on stages: Stage-7 - Stage-1 - Stage-0 depends on stages: Stage-3, Stage-4, Stage-1 - -STAGE PLANS: - Stage: Stage-5 - Conditional Operator - - Stage: Stage-6 - Map Reduce Local Work - Alias -> Map Local Tables: - $hdt$_1:b - Fetch Operator - limit: -1 - Alias -> Map Local Operator Tree: - $hdt$_1:b - TableScan - alias: b - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE - HashTable Sink Operator - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - - Stage: Stage-3 - Map Reduce - Map Operator Tree: - TableScan - alias: a - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0 - Group By Operator - aggregations: count() - keys: _col0 (type: int) - mode: hash - outputColumnNames: _col0, _col1 - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - value expressions: _col1 (type: bigint) - Local Work: - Map Reduce Local Work - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0) - keys: KEY._col0 (type: int) - mode: mergepartial - outputColumnNames: _col0, _col1 - File Output Operator - compressed: false - 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-7 - Map Reduce Local Work - Alias -> Map Local Tables: - $hdt$_0:a - Fetch Operator - limit: -1 - Alias -> Map Local Operator Tree: - $hdt$_0:a - TableScan - alias: a - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE - HashTable Sink Operator - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - - Stage: Stage-4 - Map Reduce - Map Operator Tree: - TableScan - alias: b - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0 - Group By Operator - aggregations: count() - keys: _col0 (type: int) - mode: hash - outputColumnNames: _col0, _col1 - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - value expressions: _col1 (type: bigint) - Local Work: - Map Reduce Local Work - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0) - keys: KEY._col0 (type: int) - mode: mergepartial - outputColumnNames: _col0, _col1 - File Output Operator - compressed: false - 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-1 - Map Reduce - Map Operator Tree: - TableScan - alias: a - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE - Sorted Merge Bucket Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0 - Group By Operator - aggregations: count() - keys: _col0 (type: int) - mode: hash - outputColumnNames: _col0, _col1 - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - value expressions: _col1 (type: bigint) - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0) - keys: KEY._col0 (type: int) - mode: mergepartial - outputColumnNames: _col0, _col1 - File Output Operator - compressed: false - 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 key, count(*) from -( - select a.key as key, a.value as val1, b.value as val2 from tbl1 a join tbl2 b on a.key = b.key -) subq1 -group by key -PREHOOK: type: QUERY -PREHOOK: Input: default@tbl1 -PREHOOK: Input: default@tbl2 -#### A masked pattern was here #### -POSTHOOK: query: select key, count(*) from -( - select a.key as key, a.value as val1, b.value as val2 from tbl1 a join tbl2 b on a.key = b.key -) subq1 -group by key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@tbl1 -POSTHOOK: Input: default@tbl2 -#### A masked pattern was here #### -0 9 -2 1 -4 1 -5 9 -8 1 -9 1 -PREHOOK: query: -- The join is being performed as part of more than one sub-query. It should be converted to a sort-merge join -explain -select count(*) from -( - select key, count(*) from - ( - select a.key as key, a.value as val1, b.value as val2 from tbl1 a join tbl2 b on a.key = b.key - ) subq1 - group by key -) subq2 -PREHOOK: type: QUERY -POSTHOOK: query: -- The join is being performed as part of more than one sub-query. It should be converted to a sort-merge join -explain -select count(*) from -( - select key, count(*) from - ( - select a.key as key, a.value as val1, b.value as val2 from tbl1 a join tbl2 b on a.key = b.key - ) subq1 - group by key -) subq2 -POSTHOOK: type: QUERY -STAGE DEPENDENCIES: - Stage-6 is a root stage , consists of Stage-7, Stage-8, Stage-1 - Stage-7 has a backup stage: Stage-1 - Stage-4 depends on stages: Stage-7 - Stage-2 depends on stages: Stage-1, Stage-4, Stage-5 - Stage-8 has a backup stage: Stage-1 - Stage-5 depends on stages: Stage-8 - Stage-1 - Stage-0 depends on stages: Stage-2 - -STAGE PLANS: - Stage: Stage-6 - Conditional Operator - - Stage: Stage-7 - Map Reduce Local Work - Alias -> Map Local Tables: - $hdt$_0:$hdt$_1:b - Fetch Operator - limit: -1 - Alias -> Map Local Operator Tree: - $hdt$_0:$hdt$_1:b - TableScan - alias: b - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE - HashTable Sink Operator - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - - Stage: Stage-4 - Map Reduce - Map Operator Tree: - TableScan - alias: a - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0 - 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) - Local Work: - Map Reduce Local Work - Reduce Operator Tree: - Group By Operator - keys: KEY._col0 (type: int) - mode: mergepartial - outputColumnNames: _col0 - Select Operator - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - sort order: - value expressions: _col0 (type: bigint) - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0) - mode: mergepartial - outputColumnNames: _col0 - File Output Operator - compressed: false - 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-8 - Map Reduce Local Work - Alias -> Map Local Tables: - $hdt$_0:$hdt$_0:a - Fetch Operator - limit: -1 - Alias -> Map Local Operator Tree: - $hdt$_0:$hdt$_0:a - TableScan - alias: a - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE - HashTable Sink Operator - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - - Stage: Stage-5 - Map Reduce - Map Operator Tree: - TableScan - alias: b - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0 - 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) - Local Work: - Map Reduce Local Work - Reduce Operator Tree: - Group By Operator - keys: KEY._col0 (type: int) - mode: mergepartial - outputColumnNames: _col0 - Select Operator - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: a - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE - Sorted Merge Bucket Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0 - 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) - Reduce Operator Tree: - Group By Operator - keys: KEY._col0 (type: int) - mode: mergepartial - outputColumnNames: _col0 - Select Operator - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: select count(*) from -( - select key, count(*) from - ( - select a.key as key, a.value as val1, b.value as val2 from tbl1 a join tbl2 b on a.key = b.key - ) subq1 - group by key -) subq2 -PREHOOK: type: QUERY -PREHOOK: Input: default@tbl1 -PREHOOK: Input: default@tbl2 -#### A masked pattern was here #### -POSTHOOK: query: select count(*) from -( - select key, count(*) from - ( - select a.key as key, a.value as val1, b.value as val2 from tbl1 a join tbl2 b on a.key = b.key - ) subq1 - group by key -) subq2 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@tbl1 -POSTHOOK: Input: default@tbl2 -#### A masked pattern was here #### -6 -PREHOOK: query: -- A join is being performed across different sub-queries, where a join is being performed in each of them. --- Each sub-query should be converted to a sort-merge join. -explain -select src1.key, src1.cnt1, src2.cnt1 from -( - select key, count(*) as cnt1 from - ( - select a.key as key, a.value as val1, b.value as val2 from tbl1 a join tbl2 b on a.key = b.key - ) subq1 group by key -) src1 -join -( - select key, count(*) as cnt1 from - ( - select a.key as key, a.value as val1, b.value as val2 from tbl1 a join tbl2 b on a.key = b.key - ) subq2 group by key -) src2 -on src1.key = src2.key -PREHOOK: type: QUERY -POSTHOOK: query: -- A join is being performed across different sub-queries, where a join is being performed in each of them. --- Each sub-query should be converted to a sort-merge join. -explain -select src1.key, src1.cnt1, src2.cnt1 from -( - select key, count(*) as cnt1 from - ( - select a.key as key, a.value as val1, b.value as val2 from tbl1 a join tbl2 b on a.key = b.key - ) subq1 group by key -) src1 -join -( - select key, count(*) as cnt1 from - ( - select a.key as key, a.value as val1, b.value as val2 from tbl1 a join tbl2 b on a.key = b.key - ) subq2 group by key -) src2 -on src1.key = src2.key -POSTHOOK: type: QUERY -STAGE DEPENDENCIES: - Stage-11 is a root stage , consists of Stage-17, Stage-18, Stage-1 - Stage-17 has a backup stage: Stage-1 - Stage-9 depends on stages: Stage-17 - Stage-8 depends on stages: Stage-1, Stage-4, Stage-9, Stage-10, Stage-12, Stage-13 , consists of Stage-15, Stage-16, Stage-2 - Stage-15 has a backup stage: Stage-2 - Stage-6 depends on stages: Stage-15 - Stage-16 has a backup stage: Stage-2 - Stage-7 depends on stages: Stage-16 - Stage-2 - Stage-18 has a backup stage: Stage-1 - Stage-10 depends on stages: Stage-18 - Stage-1 - Stage-14 is a root stage , consists of Stage-19, Stage-20, Stage-4 - Stage-19 has a backup stage: Stage-4 - Stage-12 depends on stages: Stage-19 - Stage-20 has a backup stage: Stage-4 - Stage-13 depends on stages: Stage-20 - Stage-4 - Stage-0 depends on stages: Stage-6, Stage-7, Stage-2 - -STAGE PLANS: - Stage: Stage-11 - Conditional Operator - - Stage: Stage-17 - Map Reduce Local Work - Alias -> Map Local Tables: - $hdt$_0:$hdt$_1:b - Fetch Operator - limit: -1 - Alias -> Map Local Operator Tree: - $hdt$_0:$hdt$_1:b - TableScan - alias: b - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE - HashTable Sink Operator - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - - Stage: Stage-9 - Map Reduce - Map Operator Tree: - TableScan - alias: a - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0 - Group By Operator - aggregations: count() - keys: _col0 (type: int) - mode: hash - outputColumnNames: _col0, _col1 - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - value expressions: _col1 (type: bigint) - Local Work: - Map Reduce Local Work - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0) - keys: KEY._col0 (type: int) - mode: mergepartial - outputColumnNames: _col0, _col1 - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - - Stage: Stage-8 - Conditional Operator - - Stage: Stage-15 - Map Reduce Local Work - Alias -> Map Local Tables: - $INTNAME1 - Fetch Operator - limit: -1 - Alias -> Map Local Operator Tree: - $INTNAME1 - TableScan - HashTable Sink Operator - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - - Stage: Stage-6 - Map Reduce - Map Operator Tree: - TableScan - Map Join Operator - con
<TRUNCATED>
