http://git-wip-us.apache.org/repos/asf/hive/blob/6f5c1135/ql/src/test/results/clientpositive/correlationoptimizer6.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/correlationoptimizer6.q.out b/ql/src/test/results/clientpositive/correlationoptimizer6.q.out deleted file mode 100644 index 3ae73fc..0000000 --- a/ql/src/test/results/clientpositive/correlationoptimizer6.q.out +++ /dev/null @@ -1,3918 +0,0 @@ -PREHOOK: query: -- SORT_QUERY_RESULTS - --- When Correlation Optimizer is turned off, 6 MR jobs are needed. --- When Correlation Optimizer is turned on, 2 MR jobs are needed. --- The first job will evaluate subquery xx, subquery yy, and xx join yy. -EXPLAIN -SELECT xx.key, xx.cnt, yy.key, yy.cnt -FROM -(SELECT x.key as key, count(1) as cnt FROM src1 x JOIN src1 y ON (x.key = y.key) group by x.key) xx -JOIN -(SELECT x.key as key, count(1) as cnt FROM src x JOIN src y ON (x.key = y.key) group by x.key) yy -ON xx.key=yy.key -PREHOOK: type: QUERY -POSTHOOK: query: -- SORT_QUERY_RESULTS - --- When Correlation Optimizer is turned off, 6 MR jobs are needed. --- When Correlation Optimizer is turned on, 2 MR jobs are needed. --- The first job will evaluate subquery xx, subquery yy, and xx join yy. -EXPLAIN -SELECT xx.key, xx.cnt, yy.key, yy.cnt -FROM -(SELECT x.key as key, count(1) as cnt FROM src1 x JOIN src1 y ON (x.key = y.key) group by x.key) xx -JOIN -(SELECT x.key as key, count(1) as cnt FROM src x JOIN src y ON (x.key = y.key) group by x.key) yy -ON xx.key=yy.key -POSTHOOK: type: QUERY -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-2 depends on stages: Stage-1 - Stage-3 depends on stages: Stage-2, Stage-6 - Stage-5 is a root stage - Stage-6 depends on stages: Stage-5 - Stage-0 depends on stages: Stage-3 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: x - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - TableScan - alias: y - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 27 Data size: 210 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(1) - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 27 Data size: 210 Basic stats: COMPLETE Column stats: NONE - 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 - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 27 Data size: 210 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0) - keys: KEY._col0 (type: string) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 13 Data size: 101 Basic stats: COMPLETE Column stats: NONE - 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-3 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 13 Data size: 101 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) - TableScan - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 302 Data size: 3213 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-5 - Map Reduce - Map Operator Tree: - TableScan - alias: x - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - TableScan - alias: y - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(1) - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE - 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-6 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0) - keys: KEY._col0 (type: string) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - 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 xx.key, xx.cnt, yy.key, yy.cnt -FROM -(SELECT x.key as key, count(1) as cnt FROM src1 x JOIN src1 y ON (x.key = y.key) group by x.key) xx -JOIN -(SELECT x.key as key, count(1) as cnt FROM src x JOIN src y ON (x.key = y.key) group by x.key) yy -ON xx.key=yy.key -PREHOOK: type: QUERY -PREHOOK: Input: default@src -PREHOOK: Input: default@src1 -#### A masked pattern was here #### -POSTHOOK: query: SELECT xx.key, xx.cnt, yy.key, yy.cnt -FROM -(SELECT x.key as key, count(1) as cnt FROM src1 x JOIN src1 y ON (x.key = y.key) group by x.key) xx -JOIN -(SELECT x.key as key, count(1) as cnt FROM src x JOIN src y ON (x.key = y.key) group by x.key) yy -ON xx.key=yy.key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -POSTHOOK: Input: default@src1 -#### A masked pattern was here #### -128 1 128 9 -146 1 146 4 -150 1 150 1 -213 1 213 4 -224 1 224 4 -238 1 238 4 -255 1 255 4 -273 1 273 9 -278 1 278 4 -311 1 311 9 -369 1 369 9 -401 1 401 25 -406 1 406 16 -66 1 66 1 -98 1 98 4 -PREHOOK: query: EXPLAIN -SELECT xx.key, xx.cnt, yy.key, yy.cnt -FROM -(SELECT x.key as key, count(1) as cnt FROM src1 x JOIN src1 y ON (x.key = y.key) group by x.key) xx -JOIN -(SELECT x.key as key, count(1) as cnt FROM src x JOIN src y ON (x.key = y.key) group by x.key) yy -ON xx.key=yy.key -PREHOOK: type: QUERY -POSTHOOK: query: EXPLAIN -SELECT xx.key, xx.cnt, yy.key, yy.cnt -FROM -(SELECT x.key as key, count(1) as cnt FROM src1 x JOIN src1 y ON (x.key = y.key) group by x.key) xx -JOIN -(SELECT x.key as key, count(1) as cnt FROM src x JOIN src y ON (x.key = y.key) group by x.key) yy -ON xx.key=yy.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: x - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - TableScan - alias: y - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - TableScan - alias: x - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - TableScan - alias: y - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Reduce Operator Tree: - Demux Operator - Statistics: Num rows: 1050 Data size: 11006 Basic stats: COMPLETE Column stats: NONE - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - Mux Operator - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - Group By Operator - aggregations: count(1) - keys: _col0 (type: string) - mode: complete - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - Mux Operator - Statistics: Num rows: 2 Data size: 0 Basic stats: PARTIAL Column stats: NONE - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE 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 - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - Mux Operator - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - Group By Operator - aggregations: count(1) - keys: _col0 (type: string) - mode: complete - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - Mux Operator - Statistics: Num rows: 2 Data size: 0 Basic stats: PARTIAL Column stats: NONE - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE 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 xx.key, xx.cnt, yy.key, yy.cnt -FROM -(SELECT x.key as key, count(1) as cnt FROM src1 x JOIN src1 y ON (x.key = y.key) group by x.key) xx -JOIN -(SELECT x.key as key, count(1) as cnt FROM src x JOIN src y ON (x.key = y.key) group by x.key) yy -ON xx.key=yy.key -PREHOOK: type: QUERY -PREHOOK: Input: default@src -PREHOOK: Input: default@src1 -#### A masked pattern was here #### -POSTHOOK: query: SELECT xx.key, xx.cnt, yy.key, yy.cnt -FROM -(SELECT x.key as key, count(1) as cnt FROM src1 x JOIN src1 y ON (x.key = y.key) group by x.key) xx -JOIN -(SELECT x.key as key, count(1) as cnt FROM src x JOIN src y ON (x.key = y.key) group by x.key) yy -ON xx.key=yy.key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -POSTHOOK: Input: default@src1 -#### A masked pattern was here #### -128 1 128 9 -146 1 146 4 -150 1 150 1 -213 1 213 4 -224 1 224 4 -238 1 238 4 -255 1 255 4 -273 1 273 9 -278 1 278 4 -311 1 311 9 -369 1 369 9 -401 1 401 25 -406 1 406 16 -66 1 66 1 -98 1 98 4 -PREHOOK: query: -- Enable hive.auto.convert.join. -EXPLAIN -SELECT xx.key, xx.cnt, yy.key, yy.cnt -FROM -(SELECT x.key as key, count(1) as cnt FROM src1 x JOIN src1 y ON (x.key = y.key) group by x.key) xx -JOIN -(SELECT x.key as key, count(1) as cnt FROM src x JOIN src y ON (x.key = y.key) group by x.key) yy -ON xx.key=yy.key -PREHOOK: type: QUERY -POSTHOOK: query: -- Enable hive.auto.convert.join. -EXPLAIN -SELECT xx.key, xx.cnt, yy.key, yy.cnt -FROM -(SELECT x.key as key, count(1) as cnt FROM src1 x JOIN src1 y ON (x.key = y.key) group by x.key) xx -JOIN -(SELECT x.key as key, count(1) as cnt FROM src x JOIN src y ON (x.key = y.key) group by x.key) yy -ON xx.key=yy.key -POSTHOOK: type: QUERY -STAGE DEPENDENCIES: - Stage-8 is a root stage - Stage-2 depends on stages: Stage-8 - Stage-0 depends on stages: Stage-2 - -STAGE PLANS: - Stage: Stage-8 - Map Reduce Local Work - Alias -> Map Local Tables: - $hdt$_0:$hdt$_0:$hdt$_0:x - Fetch Operator - limit: -1 - $hdt$_1:$hdt$_1:$hdt$_1:x - Fetch Operator - limit: -1 - Alias -> Map Local Operator Tree: - $hdt$_0:$hdt$_0:$hdt$_0:x - TableScan - alias: x - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - HashTable Sink Operator - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - $hdt$_1:$hdt$_1:$hdt$_1:x - TableScan - alias: x - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - HashTable Sink Operator - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - alias: y - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 27 Data size: 210 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(1) - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 27 Data size: 210 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 27 Data size: 210 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) - TableScan - alias: y - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(1) - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) - Local Work: - Map Reduce Local Work - Reduce Operator Tree: - Demux Operator - Statistics: Num rows: 577 Data size: 6053 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(VALUE._col0) - keys: KEY._col0 (type: string) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 288 Data size: 3021 Basic stats: COMPLETE Column stats: NONE - Mux Operator - Statistics: Num rows: 576 Data size: 6042 Basic stats: COMPLETE Column stats: NONE - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE 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 - Group By Operator - aggregations: count(VALUE._col0) - keys: KEY._col0 (type: string) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 288 Data size: 3021 Basic stats: COMPLETE Column stats: NONE - Mux Operator - Statistics: Num rows: 576 Data size: 6042 Basic stats: COMPLETE Column stats: NONE - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE 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 xx.key, xx.cnt, yy.key, yy.cnt -FROM -(SELECT x.key as key, count(1) as cnt FROM src1 x JOIN src1 y ON (x.key = y.key) group by x.key) xx -JOIN -(SELECT x.key as key, count(1) as cnt FROM src x JOIN src y ON (x.key = y.key) group by x.key) yy -ON xx.key=yy.key -PREHOOK: type: QUERY -PREHOOK: Input: default@src -PREHOOK: Input: default@src1 -#### A masked pattern was here #### -POSTHOOK: query: SELECT xx.key, xx.cnt, yy.key, yy.cnt -FROM -(SELECT x.key as key, count(1) as cnt FROM src1 x JOIN src1 y ON (x.key = y.key) group by x.key) xx -JOIN -(SELECT x.key as key, count(1) as cnt FROM src x JOIN src y ON (x.key = y.key) group by x.key) yy -ON xx.key=yy.key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -POSTHOOK: Input: default@src1 -#### A masked pattern was here #### -128 1 128 9 -146 1 146 4 -150 1 150 1 -213 1 213 4 -224 1 224 4 -238 1 238 4 -255 1 255 4 -273 1 273 9 -278 1 278 4 -311 1 311 9 -369 1 369 9 -401 1 401 25 -406 1 406 16 -66 1 66 1 -98 1 98 4 -PREHOOK: query: -- When Correlation Optimizer is turned off, 3 MR jobs are needed. --- When Correlation Optimizer is turned on, 2 MR jobs are needed. --- The first job will evaluate subquery yy and xx join yy. -EXPLAIN -SELECT xx.key, yy.key, yy.cnt -FROM src1 xx -JOIN -(SELECT x.key as key, count(1) as cnt FROM src x GROUP BY x.key) yy -ON xx.key=yy.key -PREHOOK: type: QUERY -POSTHOOK: query: -- When Correlation Optimizer is turned off, 3 MR jobs are needed. --- When Correlation Optimizer is turned on, 2 MR jobs are needed. --- The first job will evaluate subquery yy and xx join yy. -EXPLAIN -SELECT xx.key, yy.key, yy.cnt -FROM src1 xx -JOIN -(SELECT x.key as key, count(1) as cnt FROM src x GROUP BY x.key) yy -ON xx.key=yy.key -POSTHOOK: type: QUERY -STAGE DEPENDENCIES: - Stage-2 is a root stage - Stage-1 depends on stages: Stage-2 - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - alias: x - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(1) - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0) - keys: KEY._col0 (type: string) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - 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: xx - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - TableScan - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 275 Data size: 2921 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 xx.key, yy.key, yy.cnt -FROM src1 xx -JOIN -(SELECT x.key as key, count(1) as cnt FROM src x GROUP BY x.key) yy -ON xx.key=yy.key -PREHOOK: type: QUERY -PREHOOK: Input: default@src -PREHOOK: Input: default@src1 -#### A masked pattern was here #### -POSTHOOK: query: SELECT xx.key, yy.key, yy.cnt -FROM src1 xx -JOIN -(SELECT x.key as key, count(1) as cnt FROM src x GROUP BY x.key) yy -ON xx.key=yy.key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -POSTHOOK: Input: default@src1 -#### A masked pattern was here #### -128 128 3 -146 146 2 -150 150 1 -213 213 2 -224 224 2 -238 238 2 -255 255 2 -273 273 3 -278 278 2 -311 311 3 -369 369 3 -401 401 5 -406 406 4 -66 66 1 -98 98 2 -PREHOOK: query: EXPLAIN -SELECT xx.key, yy.key, yy.cnt -FROM src1 xx -JOIN -(SELECT x.key as key, count(1) as cnt FROM src x GROUP BY x.key) yy -ON xx.key=yy.key -PREHOOK: type: QUERY -POSTHOOK: query: EXPLAIN -SELECT xx.key, yy.key, yy.cnt -FROM src1 xx -JOIN -(SELECT x.key as key, count(1) as cnt FROM src x GROUP BY x.key) yy -ON xx.key=yy.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: xx - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - TableScan - alias: x - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(1) - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) - Reduce Operator Tree: - Demux Operator - Statistics: Num rows: 525 Data size: 5503 Basic stats: COMPLETE Column stats: NONE - Mux Operator - Statistics: Num rows: 787 Data size: 8249 Basic stats: COMPLETE Column stats: NONE - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE 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 - Group By Operator - aggregations: count(VALUE._col0) - keys: KEY._col0 (type: string) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 262 Data size: 2746 Basic stats: COMPLETE Column stats: NONE - Mux Operator - Statistics: Num rows: 787 Data size: 8249 Basic stats: COMPLETE Column stats: NONE - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE 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 xx.key, yy.key, yy.cnt -FROM src1 xx -JOIN -(SELECT x.key as key, count(1) as cnt FROM src x GROUP BY x.key) yy -ON xx.key=yy.key -PREHOOK: type: QUERY -PREHOOK: Input: default@src -PREHOOK: Input: default@src1 -#### A masked pattern was here #### -POSTHOOK: query: SELECT xx.key, yy.key, yy.cnt -FROM src1 xx -JOIN -(SELECT x.key as key, count(1) as cnt FROM src x GROUP BY x.key) yy -ON xx.key=yy.key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -POSTHOOK: Input: default@src1 -#### A masked pattern was here #### -128 128 3 -146 146 2 -150 150 1 -213 213 2 -224 224 2 -238 238 2 -255 255 2 -273 273 3 -278 278 2 -311 311 3 -369 369 3 -401 401 5 -406 406 4 -66 66 1 -98 98 2 -PREHOOK: query: -- When Correlation Optimizer is turned off, 4 MR jobs are needed. --- When Correlation Optimizer is turned on, 2 MR jobs are needed. --- The first job will evaluate subquery yy and xx join yy. -EXPLAIN -SELECT xx.key, yy.key, yy.cnt -FROM src1 xx -JOIN -(SELECT x.key as key, count(1) as cnt FROM src x JOIN src y ON (x.key = y.key) group by x.key) yy -ON xx.key=yy.key -PREHOOK: type: QUERY -POSTHOOK: query: -- When Correlation Optimizer is turned off, 4 MR jobs are needed. --- When Correlation Optimizer is turned on, 2 MR jobs are needed. --- The first job will evaluate subquery yy and xx join yy. -EXPLAIN -SELECT xx.key, yy.key, yy.cnt -FROM src1 xx -JOIN -(SELECT x.key as key, count(1) as cnt FROM src x JOIN src y ON (x.key = y.key) group by x.key) yy -ON xx.key=yy.key -POSTHOOK: type: QUERY -STAGE DEPENDENCIES: - Stage-2 is a root stage - Stage-3 depends on stages: Stage-2 - Stage-1 depends on stages: Stage-3 - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-2 - Map Reduce - Map Operator Tree: - TableScan - alias: x - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - TableScan - alias: y - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(1) - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE - 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-3 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0) - keys: KEY._col0 (type: string) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - 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: xx - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - TableScan - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 302 Data size: 3213 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 xx.key, yy.key, yy.cnt -FROM src1 xx -JOIN -(SELECT x.key as key, count(1) as cnt FROM src x JOIN src y ON (x.key = y.key) group by x.key) yy -ON xx.key=yy.key -PREHOOK: type: QUERY -PREHOOK: Input: default@src -PREHOOK: Input: default@src1 -#### A masked pattern was here #### -POSTHOOK: query: SELECT xx.key, yy.key, yy.cnt -FROM src1 xx -JOIN -(SELECT x.key as key, count(1) as cnt FROM src x JOIN src y ON (x.key = y.key) group by x.key) yy -ON xx.key=yy.key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -POSTHOOK: Input: default@src1 -#### A masked pattern was here #### -128 128 9 -146 146 4 -150 150 1 -213 213 4 -224 224 4 -238 238 4 -255 255 4 -273 273 9 -278 278 4 -311 311 9 -369 369 9 -401 401 25 -406 406 16 -66 66 1 -98 98 4 -PREHOOK: query: EXPLAIN -SELECT xx.key, yy.key, yy.cnt -FROM src1 xx -JOIN -(SELECT x.key as key, count(1) as cnt FROM src x JOIN src y ON (x.key = y.key) group by x.key) yy -ON xx.key=yy.key -PREHOOK: type: QUERY -POSTHOOK: query: EXPLAIN -SELECT xx.key, yy.key, yy.cnt -FROM src1 xx -JOIN -(SELECT x.key as key, count(1) as cnt FROM src x JOIN src y ON (x.key = y.key) group by x.key) yy -ON xx.key=yy.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: xx - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - TableScan - alias: x - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - TableScan - alias: y - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Reduce Operator Tree: - Demux Operator - Statistics: Num rows: 1025 Data size: 10815 Basic stats: COMPLETE Column stats: NONE - Mux Operator - Statistics: Num rows: 1026 Data size: 10815 Basic stats: COMPLETE Column stats: NONE - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE 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 - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - Mux Operator - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - Group By Operator - aggregations: count(1) - keys: _col0 (type: string) - mode: complete - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - Mux Operator - Statistics: Num rows: 1026 Data size: 10815 Basic stats: COMPLETE Column stats: NONE - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE 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 xx.key, yy.key, yy.cnt -FROM src1 xx -JOIN -(SELECT x.key as key, count(1) as cnt FROM src x JOIN src y ON (x.key = y.key) group by x.key) yy -ON xx.key=yy.key -PREHOOK: type: QUERY -PREHOOK: Input: default@src -PREHOOK: Input: default@src1 -#### A masked pattern was here #### -POSTHOOK: query: SELECT xx.key, yy.key, yy.cnt -FROM src1 xx -JOIN -(SELECT x.key as key, count(1) as cnt FROM src x JOIN src y ON (x.key = y.key) group by x.key) yy -ON xx.key=yy.key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -POSTHOOK: Input: default@src1 -#### A masked pattern was here #### -128 128 9 -146 146 4 -150 150 1 -213 213 4 -224 224 4 -238 238 4 -255 255 4 -273 273 9 -278 278 4 -311 311 9 -369 369 9 -401 401 25 -406 406 16 -66 66 1 -98 98 4 -PREHOOK: query: -- When Correlation Optimizer is turned off, 4 MR jobs are needed. --- When Correlation Optimizer is turned on, 2 MR jobs are needed. --- The first job will evaluate subquery xx and xx join yy. -EXPLAIN -SELECT xx.key, xx.cnt, yy.key -FROM -(SELECT x.key as key, count(1) as cnt FROM src1 x JOIN src1 y ON (x.key = y.key) group by x.key) xx -JOIN src yy -ON xx.key=yy.key -PREHOOK: type: QUERY -POSTHOOK: query: -- When Correlation Optimizer is turned off, 4 MR jobs are needed. --- When Correlation Optimizer is turned on, 2 MR jobs are needed. --- The first job will evaluate subquery xx and xx join yy. -EXPLAIN -SELECT xx.key, xx.cnt, yy.key -FROM -(SELECT x.key as key, count(1) as cnt FROM src1 x JOIN src1 y ON (x.key = y.key) group by x.key) xx -JOIN src yy -ON xx.key=yy.key -POSTHOOK: type: QUERY -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-2 depends on stages: Stage-1 - Stage-3 depends on stages: Stage-2 - Stage-0 depends on stages: Stage-3 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: x - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - TableScan - alias: y - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 27 Data size: 210 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(1) - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 27 Data size: 210 Basic stats: COMPLETE Column stats: NONE - 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 - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 27 Data size: 210 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0) - keys: KEY._col0 (type: string) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 13 Data size: 101 Basic stats: COMPLETE Column stats: NONE - 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-3 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 13 Data size: 101 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) - TableScan - alias: yy - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 550 Data size: 5843 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 xx.key, xx.cnt, yy.key -FROM -(SELECT x.key as key, count(1) as cnt FROM src1 x JOIN src1 y ON (x.key = y.key) group by x.key) xx -JOIN src yy -ON xx.key=yy.key -PREHOOK: type: QUERY -PREHOOK: Input: default@src -PREHOOK: Input: default@src1 -#### A masked pattern was here #### -POSTHOOK: query: SELECT xx.key, xx.cnt, yy.key -FROM -(SELECT x.key as key, count(1) as cnt FROM src1 x JOIN src1 y ON (x.key = y.key) group by x.key) xx -JOIN src yy -ON xx.key=yy.key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -POSTHOOK: Input: default@src1 -#### A masked pattern was here #### -128 1 128 -128 1 128 -128 1 128 -146 1 146 -146 1 146 -150 1 150 -213 1 213 -213 1 213 -224 1 224 -224 1 224 -238 1 238 -238 1 238 -255 1 255 -255 1 255 -273 1 273 -273 1 273 -273 1 273 -278 1 278 -278 1 278 -311 1 311 -311 1 311 -311 1 311 -369 1 369 -369 1 369 -369 1 369 -401 1 401 -401 1 401 -401 1 401 -401 1 401 -401 1 401 -406 1 406 -406 1 406 -406 1 406 -406 1 406 -66 1 66 -98 1 98 -98 1 98 -PREHOOK: query: EXPLAIN -SELECT xx.key, xx.cnt, yy.key -FROM -(SELECT x.key as key, count(1) as cnt FROM src1 x JOIN src1 y ON (x.key = y.key) group by x.key) xx -JOIN src yy -ON xx.key=yy.key -PREHOOK: type: QUERY -POSTHOOK: query: EXPLAIN -SELECT xx.key, xx.cnt, yy.key -FROM -(SELECT x.key as key, count(1) as cnt FROM src1 x JOIN src1 y ON (x.key = y.key) group by x.key) xx -JOIN src yy -ON xx.key=yy.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: x - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - TableScan - alias: y - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - TableScan - alias: yy - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Reduce Operator Tree: - Demux Operator - Statistics: Num rows: 550 Data size: 5694 Basic stats: COMPLETE Column stats: NONE - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - Mux Operator - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - Group By Operator - aggregations: count(1) - keys: _col0 (type: string) - mode: complete - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - Mux Operator - Statistics: Num rows: 551 Data size: 5694 Basic stats: COMPLETE Column stats: NONE - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE 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 - Mux Operator - Statistics: Num rows: 551 Data size: 5694 Basic stats: COMPLETE Column stats: NONE - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE 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 xx.key, xx.cnt, yy.key -FROM -(SELECT x.key as key, count(1) as cnt FROM src1 x JOIN src1 y ON (x.key = y.key) group by x.key) xx -JOIN src yy -ON xx.key=yy.key -PREHOOK: type: QUERY -PREHOOK: Input: default@src -PREHOOK: Input: default@src1 -#### A masked pattern was here #### -POSTHOOK: query: SELECT xx.key, xx.cnt, yy.key -FROM -(SELECT x.key as key, count(1) as cnt FROM src1 x JOIN src1 y ON (x.key = y.key) group by x.key) xx -JOIN src yy -ON xx.key=yy.key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -POSTHOOK: Input: default@src1 -#### A masked pattern was here #### -128 1 128 -128 1 128 -128 1 128 -146 1 146 -146 1 146 -150 1 150 -213 1 213 -213 1 213 -224 1 224 -224 1 224 -238 1 238 -238 1 238 -255 1 255 -255 1 255 -273 1 273 -273 1 273 -273 1 273 -278 1 278 -278 1 278 -311 1 311 -311 1 311 -311 1 311 -369 1 369 -369 1 369 -369 1 369 -401 1 401 -401 1 401 -401 1 401 -401 1 401 -401 1 401 -406 1 406 -406 1 406 -406 1 406 -406 1 406 -66 1 66 -98 1 98 -98 1 98 -PREHOOK: query: -- When Correlation Optimizer is turned off, 4 MR jobs are needed. --- When Correlation Optimizer is turned on, 2 MR jobs are needed. --- The first job will evaluate subquery xx and xx join yy join zz. -EXPLAIN -SELECT xx.key, yy.key, yy.cnt -FROM src1 xx -JOIN src zz ON xx.key=zz.key -JOIN -(SELECT x.key as key, count(1) as cnt FROM src x JOIN src y ON (x.key = y.key) group by x.key) yy -ON zz.key=yy.key -PREHOOK: type: QUERY -POSTHOOK: query: -- When Correlation Optimizer is turned off, 4 MR jobs are needed. --- When Correlation Optimizer is turned on, 2 MR jobs are needed. --- The first job will evaluate subquery xx and xx join yy join zz. -EXPLAIN -SELECT xx.key, yy.key, yy.cnt -FROM src1 xx -JOIN src zz ON xx.key=zz.key -JOIN -(SELECT x.key as key, count(1) as cnt FROM src x JOIN src y ON (x.key = y.key) group by x.key) yy -ON zz.key=yy.key -POSTHOOK: type: QUERY -STAGE DEPENDENCIES: - Stage-3 is a root stage - Stage-4 depends on stages: Stage-3 - Stage-1 depends on stages: Stage-4 - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-3 - Map Reduce - Map Operator Tree: - TableScan - alias: x - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - TableScan - alias: y - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(1) - keys: _col0 (type: string) - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE - 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-4 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0) - keys: KEY._col0 (type: string) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - 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: zz - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - TableScan - alias: xx - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - TableScan - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - Inner Join 0 to 2 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - 2 _col0 (type: string) - outputColumnNames: _col1, _col2, _col3 - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col1 (type: string), _col2 (type: string), _col3 (type: bigint) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 1100 Data size: 11686 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 xx.key, yy.key, yy.cnt -FROM src1 xx -JOIN src zz ON xx.key=zz.key -JOIN -(SELECT x.key as key, count(1) as cnt FROM src x JOIN src y ON (x.key = y.key) group by x.key) yy -ON zz.key=yy.key -PREHOOK: type: QUERY -PREHOOK: Input: default@src -PREHOOK: Input: default@src1 -#### A masked pattern was here #### -POSTHOOK: query: SELECT xx.key, yy.key, yy.cnt -FROM src1 xx -JOIN src zz ON xx.key=zz.key -JOIN -(SELECT x.key as key, count(1) as cnt FROM src x JOIN src y ON (x.key = y.key) group by x.key) yy -ON zz.key=yy.key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -POSTHOOK: Input: default@src1 -#### A masked pattern was here #### -128 128 9 -128 128 9 -128 128 9 -146 146 4 -146 146 4 -150 150 1 -213 213 4 -213 213 4 -224 224 4 -224 224 4 -238 238 4 -238 238 4 -255 255 4 -255 255 4 -273 273 9 -273 273 9 -273 273 9 -278 278 4 -278 278 4 -311 311 9 -311 311 9 -311 311 9 -369 369 9 -369 369 9 -369 369 9 -401 401 25 -401 401 25 -401 401 25 -401 401 25 -401 401 25 -406 406 16 -406 406 16 -406 406 16 -406 406 16 -66 66 1 -98 98 4 -98 98 4 -PREHOOK: query: -- When Correlation Optimizer is turned off, 4 MR jobs are needed. --- When Correlation Optimizer is turned on, 2 MR jobs are needed. --- The first job will evaluate subquery yy and xx join yy join zz. -EXPLAIN -SELECT xx.key, yy.key, yy.cnt -FROM src1 xx -JOIN src zz ON xx.key=zz.key -JOIN -(SELECT x.key as key, count(1) as cnt FROM src x JOIN src y ON (x.key = y.key) group by x.key) yy -ON zz.key=yy.key -PREHOOK: type: QUERY -POSTHOOK: query: -- When Correlation Optimizer is turned off, 4 MR jobs are needed. --- When Correlation Optimizer is turned on, 2 MR jobs are needed. --- The first job will evaluate subquery yy and xx join yy join zz. -EXPLAIN -SELECT xx.key, yy.key, yy.cnt -FROM src1 xx -JOIN src zz ON xx.key=zz.key -JOIN -(SELECT x.key as key, count(1) as cnt FROM src x JOIN src y ON (x.key = y.key) group by x.key) yy -ON zz.key=yy.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: zz - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - TableScan - alias: xx - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - TableScan - alias: x - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - TableScan - alias: y - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Reduce Operator Tree: - Demux Operator - Statistics: Num rows: 1525 Data size: 16127 Basic stats: COMPLETE Column stats: NONE - Mux Operator - Statistics: Num rows: 3051 Data size: 32254 Basic stats: COMPLETE Column stats: NONE - Join Operator - condition map: - Inner Join 0 to 1 - Inner Join 0 to 2 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - 2 _col0 (type: string) - outputColumnNames: _col1, _col2, _col3 - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - Select Operator - expressions: _col1 (type: string), _col2 (type: string), _col3 (type: bigint) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE 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 - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - Mux Operator - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - Group By Operator - aggregations: count(1) - keys: _col0 (type: string) - mode: complete - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE - Mux Operator - Statistics: Num rows: 3051 Data size: 32254 Basic stats: COMPLETE Column stats: NONE - Join Operator - condition map: - Inner Join 0 to 1 - Inner Join 0 to 2 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - 2 _col0 (type: string) - outputColumnNames: _col1, _col2, _col3 - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - Select Operator - expressions: _col1 (type: string), _col2 (type: string), _col3 (type: bigint) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 0 Data size: 0 Basic stats: NONE 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 xx.key, yy.key, yy.cnt -FROM src1 xx -JOIN src zz ON xx.key=zz.key -JOIN -(SELECT x.key as key, count(1) as cnt FROM src x JOIN src y ON (x.key = y.key) group by x.key) yy -ON zz.key=yy.key -PREHOOK: type: QUERY -PREHOOK: Input: default@src -PREHOOK: Input: default@src1 -#### A masked pattern was here #### -POSTHOOK: query: SELECT xx.key, yy.key, yy.cnt -FROM src1 xx -JOIN src zz ON xx.key=zz.key -JOIN -(SELECT x.key as key, count(1) as cnt FROM src x JOIN src y ON (x.key = y.key) group by x.key) yy -ON zz.key=yy.key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -POSTHOOK: Input: default@src1 -#### A masked pattern was here #### -128 128 9 -128 128 9 -128 128 9 -146 146 4 -146 146 4 -150 150 1 -213 213 4 -213 213 4 -224 224 4 -224 224 4 -238 238 4 -238 238 4 -255 255 4 -255 255 4 -273 273 9 -273 273 9 -273 273 9 -278 278 4 -278 278 4 -311 311 9 -311 311 9 -311 311 9 -369 369 9 -369
<TRUNCATED>