http://git-wip-us.apache.org/repos/asf/hive/blob/1f258e96/ql/src/test/results/clientpositive/llap/correlationoptimizer2.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/llap/correlationoptimizer2.q.out b/ql/src/test/results/clientpositive/llap/correlationoptimizer2.q.out new file mode 100644 index 0000000..dfb4804 --- /dev/null +++ b/ql/src/test/results/clientpositive/llap/correlationoptimizer2.q.out @@ -0,0 +1,2130 @@ +PREHOOK: query: -- In this query, subquery a and b both have a GroupByOperator and the a and b will be +-- joined. The key of JoinOperator is the same with both keys of GroupByOperators in subquery +-- a and b. When Correlation Optimizer is turned off, we have four MR jobs. +-- When Correlation Optimizer is turned on, 2 MR jobs will be generated. +-- The first job will evaluate subquery tmp (including subquery a, b, and the JoinOperator on a +-- and b). +EXPLAIN +SELECT SUM(HASH(key1)), SUM(HASH(cnt1)), SUM(HASH(key2)), SUM(HASH(cnt2)) +FROM (SELECT a.key AS key1, a.cnt AS cnt1, b.key AS key2, b.cnt AS cnt2 + FROM (SELECT x.key as key, count(x.value) AS cnt FROM src x group by x.key) a + JOIN (SELECT y.key as key, count(y.value) AS cnt FROM src1 y group by y.key) b + ON (a.key = b.key)) tmp +PREHOOK: type: QUERY +POSTHOOK: query: -- In this query, subquery a and b both have a GroupByOperator and the a and b will be +-- joined. The key of JoinOperator is the same with both keys of GroupByOperators in subquery +-- a and b. When Correlation Optimizer is turned off, we have four MR jobs. +-- When Correlation Optimizer is turned on, 2 MR jobs will be generated. +-- The first job will evaluate subquery tmp (including subquery a, b, and the JoinOperator on a +-- and b). +EXPLAIN +SELECT SUM(HASH(key1)), SUM(HASH(cnt1)), SUM(HASH(key2)), SUM(HASH(cnt2)) +FROM (SELECT a.key AS key1, a.cnt AS cnt1, b.key AS key2, b.cnt AS cnt2 + FROM (SELECT x.key as key, count(x.value) AS cnt FROM src x group by x.key) a + JOIN (SELECT y.key as key, count(y.value) AS cnt FROM src1 y group by y.key) b + ON (a.key = b.key)) tmp +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) + Reducer 3 <- Reducer 2 (SIMPLE_EDGE), Reducer 6 (SIMPLE_EDGE) + Reducer 4 <- Reducer 3 (SIMPLE_EDGE) + Reducer 6 <- Map 5 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: x + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: count(value) + keys: key (type: string) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 205 Data size: 19475 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 205 Data size: 19475 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: bigint) + Execution mode: llap + LLAP IO: no inputs + Map 5 + Map Operator Tree: + TableScan + alias: y + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: count(value) + keys: key (type: string) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 12 Data size: 1128 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 12 Data size: 1128 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: bigint) + Execution mode: llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + keys: KEY._col0 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 205 Data size: 19475 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 205 Data size: 19475 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: bigint) + Reducer 3 + Execution mode: llap + Reduce Operator Tree: + Merge 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: 12 Data size: 2268 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: hash(_col0) (type: int), hash(_col1) (type: int), hash(_col2) (type: int), hash(_col3) (type: int) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 12 Data size: 2268 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: sum(_col0), sum(_col1), sum(_col2), sum(_col3) + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: bigint), _col1 (type: bigint), _col2 (type: bigint), _col3 (type: bigint) + Reducer 4 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: sum(VALUE._col0), sum(VALUE._col1), sum(VALUE._col2), sum(VALUE._col3) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Reducer 6 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + keys: KEY._col0 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 12 Data size: 1128 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 12 Data size: 1128 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: bigint) + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: SELECT SUM(HASH(key1)), SUM(HASH(cnt1)), SUM(HASH(key2)), SUM(HASH(cnt2)) +FROM (SELECT a.key AS key1, a.cnt AS cnt1, b.key AS key2, b.cnt AS cnt2 + FROM (SELECT x.key as key, count(x.value) AS cnt FROM src x group by x.key) a + JOIN (SELECT y.key as key, count(y.value) AS cnt FROM src1 y group by y.key) b + ON (a.key = b.key)) tmp +PREHOOK: type: QUERY +PREHOOK: Input: default@src +PREHOOK: Input: default@src1 +#### A masked pattern was here #### +POSTHOOK: query: SELECT SUM(HASH(key1)), SUM(HASH(cnt1)), SUM(HASH(key2)), SUM(HASH(cnt2)) +FROM (SELECT a.key AS key1, a.cnt AS cnt1, b.key AS key2, b.cnt AS cnt2 + FROM (SELECT x.key as key, count(x.value) AS cnt FROM src x group by x.key) a + JOIN (SELECT y.key as key, count(y.value) AS cnt FROM src1 y group by y.key) b + ON (a.key = b.key)) tmp +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +POSTHOOK: Input: default@src1 +#### A masked pattern was here #### +652447 37 652447 15 +PREHOOK: query: EXPLAIN +SELECT SUM(HASH(key1)), SUM(HASH(cnt1)), SUM(HASH(key2)), SUM(HASH(cnt2)) +FROM (SELECT a.key AS key1, a.cnt AS cnt1, b.key AS key2, b.cnt AS cnt2 + FROM (SELECT x.key as key, count(x.value) AS cnt FROM src x group by x.key) a + JOIN (SELECT y.key as key, count(y.value) AS cnt FROM src1 y group by y.key) b + ON (a.key = b.key)) tmp +PREHOOK: type: QUERY +POSTHOOK: query: EXPLAIN +SELECT SUM(HASH(key1)), SUM(HASH(cnt1)), SUM(HASH(key2)), SUM(HASH(cnt2)) +FROM (SELECT a.key AS key1, a.cnt AS cnt1, b.key AS key2, b.cnt AS cnt2 + FROM (SELECT x.key as key, count(x.value) AS cnt FROM src x group by x.key) a + JOIN (SELECT y.key as key, count(y.value) AS cnt FROM src1 y group by y.key) b + ON (a.key = b.key)) tmp +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) + Reducer 3 <- Reducer 2 (SIMPLE_EDGE), Reducer 6 (SIMPLE_EDGE) + Reducer 4 <- Reducer 3 (SIMPLE_EDGE) + Reducer 6 <- Map 5 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: x + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: count(value) + keys: key (type: string) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 205 Data size: 19475 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 205 Data size: 19475 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: bigint) + Execution mode: llap + LLAP IO: no inputs + Map 5 + Map Operator Tree: + TableScan + alias: y + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: count(value) + keys: key (type: string) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 12 Data size: 1128 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 12 Data size: 1128 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: bigint) + Execution mode: llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + keys: KEY._col0 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 205 Data size: 19475 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 205 Data size: 19475 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: bigint) + Reducer 3 + Execution mode: llap + Reduce Operator Tree: + Merge 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: 12 Data size: 2268 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: hash(_col0) (type: int), hash(_col1) (type: int), hash(_col2) (type: int), hash(_col3) (type: int) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 12 Data size: 2268 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: sum(_col0), sum(_col1), sum(_col2), sum(_col3) + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: bigint), _col1 (type: bigint), _col2 (type: bigint), _col3 (type: bigint) + Reducer 4 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: sum(VALUE._col0), sum(VALUE._col1), sum(VALUE._col2), sum(VALUE._col3) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Reducer 6 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + keys: KEY._col0 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 12 Data size: 1128 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 12 Data size: 1128 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: bigint) + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: SELECT SUM(HASH(key1)), SUM(HASH(cnt1)), SUM(HASH(key2)), SUM(HASH(cnt2)) +FROM (SELECT a.key AS key1, a.cnt AS cnt1, b.key AS key2, b.cnt AS cnt2 + FROM (SELECT x.key as key, count(x.value) AS cnt FROM src x group by x.key) a + JOIN (SELECT y.key as key, count(y.value) AS cnt FROM src1 y group by y.key) b + ON (a.key = b.key)) tmp +PREHOOK: type: QUERY +PREHOOK: Input: default@src +PREHOOK: Input: default@src1 +#### A masked pattern was here #### +POSTHOOK: query: SELECT SUM(HASH(key1)), SUM(HASH(cnt1)), SUM(HASH(key2)), SUM(HASH(cnt2)) +FROM (SELECT a.key AS key1, a.cnt AS cnt1, b.key AS key2, b.cnt AS cnt2 + FROM (SELECT x.key as key, count(x.value) AS cnt FROM src x group by x.key) a + JOIN (SELECT y.key as key, count(y.value) AS cnt FROM src1 y group by y.key) b + ON (a.key = b.key)) tmp +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +POSTHOOK: Input: default@src1 +#### A masked pattern was here #### +652447 37 652447 15 +PREHOOK: query: -- Left Outer Join should be handled. +EXPLAIN +SELECT SUM(HASH(key1)), SUM(HASH(cnt1)), SUM(HASH(key2)), SUM(HASH(cnt2)) +FROM (SELECT a.key AS key1, a.cnt AS cnt1, b.key AS key2, b.cnt AS cnt2 + FROM (SELECT x.key as key, count(x.value) AS cnt FROM src x group by x.key) a + LEFT OUTER JOIN (SELECT y.key as key, count(y.value) AS cnt FROM src1 y group by y.key) b + ON (a.key = b.key)) tmp +PREHOOK: type: QUERY +POSTHOOK: query: -- Left Outer Join should be handled. +EXPLAIN +SELECT SUM(HASH(key1)), SUM(HASH(cnt1)), SUM(HASH(key2)), SUM(HASH(cnt2)) +FROM (SELECT a.key AS key1, a.cnt AS cnt1, b.key AS key2, b.cnt AS cnt2 + FROM (SELECT x.key as key, count(x.value) AS cnt FROM src x group by x.key) a + LEFT OUTER JOIN (SELECT y.key as key, count(y.value) AS cnt FROM src1 y group by y.key) b + ON (a.key = b.key)) tmp +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) + Reducer 3 <- Reducer 2 (SIMPLE_EDGE), Reducer 6 (SIMPLE_EDGE) + Reducer 4 <- Reducer 3 (SIMPLE_EDGE) + Reducer 6 <- Map 5 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: x + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: key, value + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: count(value) + keys: key (type: string) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 205 Data size: 19475 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 205 Data size: 19475 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: bigint) + Execution mode: llap + LLAP IO: no inputs + Map 5 + Map Operator Tree: + TableScan + alias: y + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: count(value) + keys: key (type: string) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 12 Data size: 1128 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 12 Data size: 1128 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: bigint) + Execution mode: llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + keys: KEY._col0 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 205 Data size: 19475 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 205 Data size: 19475 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: bigint) + Reducer 3 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Left Outer Join0 to 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 205 Data size: 38745 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: hash(_col0) (type: int), hash(_col1) (type: int), hash(_col2) (type: int), hash(_col3) (type: int) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 205 Data size: 38745 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: sum(_col0), sum(_col1), sum(_col2), sum(_col3) + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: bigint), _col1 (type: bigint), _col2 (type: bigint), _col3 (type: bigint) + Reducer 4 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: sum(VALUE._col0), sum(VALUE._col1), sum(VALUE._col2), sum(VALUE._col3) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Reducer 6 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + keys: KEY._col0 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 12 Data size: 1128 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 12 Data size: 1128 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: bigint) + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: SELECT SUM(HASH(key1)), SUM(HASH(cnt1)), SUM(HASH(key2)), SUM(HASH(cnt2)) +FROM (SELECT a.key AS key1, a.cnt AS cnt1, b.key AS key2, b.cnt AS cnt2 + FROM (SELECT x.key as key, count(x.value) AS cnt FROM src x group by x.key) a + LEFT OUTER JOIN (SELECT y.key as key, count(y.value) AS cnt FROM src1 y group by y.key) b + ON (a.key = b.key)) tmp +PREHOOK: type: QUERY +PREHOOK: Input: default@src +PREHOOK: Input: default@src1 +#### A masked pattern was here #### +POSTHOOK: query: SELECT SUM(HASH(key1)), SUM(HASH(cnt1)), SUM(HASH(key2)), SUM(HASH(cnt2)) +FROM (SELECT a.key AS key1, a.cnt AS cnt1, b.key AS key2, b.cnt AS cnt2 + FROM (SELECT x.key as key, count(x.value) AS cnt FROM src x group by x.key) a + LEFT OUTER JOIN (SELECT y.key as key, count(y.value) AS cnt FROM src1 y group by y.key) b + ON (a.key = b.key)) tmp +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +POSTHOOK: Input: default@src1 +#### A masked pattern was here #### +12744278 500 652447 15 +PREHOOK: query: EXPLAIN +SELECT SUM(HASH(key1)), SUM(HASH(cnt1)), SUM(HASH(key2)), SUM(HASH(cnt2)) +FROM (SELECT a.key AS key1, a.cnt AS cnt1, b.key AS key2, b.cnt AS cnt2 + FROM (SELECT x.key as key, count(x.value) AS cnt FROM src x group by x.key) a + LEFT OUTER JOIN (SELECT y.key as key, count(y.value) AS cnt FROM src1 y group by y.key) b + ON (a.key = b.key)) tmp +PREHOOK: type: QUERY +POSTHOOK: query: EXPLAIN +SELECT SUM(HASH(key1)), SUM(HASH(cnt1)), SUM(HASH(key2)), SUM(HASH(cnt2)) +FROM (SELECT a.key AS key1, a.cnt AS cnt1, b.key AS key2, b.cnt AS cnt2 + FROM (SELECT x.key as key, count(x.value) AS cnt FROM src x group by x.key) a + LEFT OUTER JOIN (SELECT y.key as key, count(y.value) AS cnt FROM src1 y group by y.key) b + ON (a.key = b.key)) tmp +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) + Reducer 3 <- Reducer 2 (SIMPLE_EDGE), Reducer 6 (SIMPLE_EDGE) + Reducer 4 <- Reducer 3 (SIMPLE_EDGE) + Reducer 6 <- Map 5 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: x + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: key, value + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: count(value) + keys: key (type: string) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 205 Data size: 19475 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 205 Data size: 19475 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: bigint) + Execution mode: llap + LLAP IO: no inputs + Map 5 + Map Operator Tree: + TableScan + alias: y + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: count(value) + keys: key (type: string) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 12 Data size: 1128 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 12 Data size: 1128 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: bigint) + Execution mode: llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + keys: KEY._col0 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 205 Data size: 19475 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 205 Data size: 19475 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: bigint) + Reducer 3 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Left Outer Join0 to 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 205 Data size: 38745 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: hash(_col0) (type: int), hash(_col1) (type: int), hash(_col2) (type: int), hash(_col3) (type: int) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 205 Data size: 38745 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: sum(_col0), sum(_col1), sum(_col2), sum(_col3) + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: bigint), _col1 (type: bigint), _col2 (type: bigint), _col3 (type: bigint) + Reducer 4 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: sum(VALUE._col0), sum(VALUE._col1), sum(VALUE._col2), sum(VALUE._col3) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Reducer 6 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + keys: KEY._col0 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 12 Data size: 1128 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 12 Data size: 1128 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: bigint) + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: SELECT SUM(HASH(key1)), SUM(HASH(cnt1)), SUM(HASH(key2)), SUM(HASH(cnt2)) +FROM (SELECT a.key AS key1, a.cnt AS cnt1, b.key AS key2, b.cnt AS cnt2 + FROM (SELECT x.key as key, count(x.value) AS cnt FROM src x group by x.key) a + LEFT OUTER JOIN (SELECT y.key as key, count(y.value) AS cnt FROM src1 y group by y.key) b + ON (a.key = b.key)) tmp +PREHOOK: type: QUERY +PREHOOK: Input: default@src +PREHOOK: Input: default@src1 +#### A masked pattern was here #### +POSTHOOK: query: SELECT SUM(HASH(key1)), SUM(HASH(cnt1)), SUM(HASH(key2)), SUM(HASH(cnt2)) +FROM (SELECT a.key AS key1, a.cnt AS cnt1, b.key AS key2, b.cnt AS cnt2 + FROM (SELECT x.key as key, count(x.value) AS cnt FROM src x group by x.key) a + LEFT OUTER JOIN (SELECT y.key as key, count(y.value) AS cnt FROM src1 y group by y.key) b + ON (a.key = b.key)) tmp +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +POSTHOOK: Input: default@src1 +#### A masked pattern was here #### +12744278 500 652447 15 +PREHOOK: query: -- Right Outer Join should be handled. +EXPLAIN +SELECT SUM(HASH(key1)), SUM(HASH(cnt1)), SUM(HASH(key2)), SUM(HASH(cnt2)) +FROM (SELECT a.key AS key1, a.cnt AS cnt1, b.key AS key2, b.cnt AS cnt2 + FROM (SELECT x.key as key, count(x.value) AS cnt FROM src x group by x.key) a + RIGHT OUTER JOIN (SELECT y.key as key, count(y.value) AS cnt FROM src1 y group by y.key) b + ON (a.key = b.key)) tmp +PREHOOK: type: QUERY +POSTHOOK: query: -- Right Outer Join should be handled. +EXPLAIN +SELECT SUM(HASH(key1)), SUM(HASH(cnt1)), SUM(HASH(key2)), SUM(HASH(cnt2)) +FROM (SELECT a.key AS key1, a.cnt AS cnt1, b.key AS key2, b.cnt AS cnt2 + FROM (SELECT x.key as key, count(x.value) AS cnt FROM src x group by x.key) a + RIGHT OUTER JOIN (SELECT y.key as key, count(y.value) AS cnt FROM src1 y group by y.key) b + ON (a.key = b.key)) tmp +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) + Reducer 3 <- Reducer 2 (SIMPLE_EDGE), Reducer 6 (SIMPLE_EDGE) + Reducer 4 <- Reducer 3 (SIMPLE_EDGE) + Reducer 6 <- Map 5 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: x + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: count(value) + keys: key (type: string) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 205 Data size: 19475 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 205 Data size: 19475 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: bigint) + Execution mode: llap + LLAP IO: no inputs + Map 5 + Map Operator Tree: + TableScan + alias: y + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: key, value + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: count(value) + keys: key (type: string) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 12 Data size: 1128 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 12 Data size: 1128 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: bigint) + Execution mode: llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + keys: KEY._col0 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 205 Data size: 19475 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 205 Data size: 19475 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: bigint) + Reducer 3 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Right Outer Join0 to 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 12 Data size: 2268 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: hash(_col0) (type: int), hash(_col1) (type: int), hash(_col2) (type: int), hash(_col3) (type: int) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 12 Data size: 2268 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: sum(_col0), sum(_col1), sum(_col2), sum(_col3) + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: bigint), _col1 (type: bigint), _col2 (type: bigint), _col3 (type: bigint) + Reducer 4 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: sum(VALUE._col0), sum(VALUE._col1), sum(VALUE._col2), sum(VALUE._col3) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Reducer 6 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + keys: KEY._col0 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 12 Data size: 1128 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 12 Data size: 1128 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: bigint) + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: SELECT SUM(HASH(key1)), SUM(HASH(cnt1)), SUM(HASH(key2)), SUM(HASH(cnt2)) +FROM (SELECT a.key AS key1, a.cnt AS cnt1, b.key AS key2, b.cnt AS cnt2 + FROM (SELECT x.key as key, count(x.value) AS cnt FROM src x group by x.key) a + RIGHT OUTER JOIN (SELECT y.key as key, count(y.value) AS cnt FROM src1 y group by y.key) b + ON (a.key = b.key)) tmp +PREHOOK: type: QUERY +PREHOOK: Input: default@src +PREHOOK: Input: default@src1 +#### A masked pattern was here #### +POSTHOOK: query: SELECT SUM(HASH(key1)), SUM(HASH(cnt1)), SUM(HASH(key2)), SUM(HASH(cnt2)) +FROM (SELECT a.key AS key1, a.cnt AS cnt1, b.key AS key2, b.cnt AS cnt2 + FROM (SELECT x.key as key, count(x.value) AS cnt FROM src x group by x.key) a + RIGHT OUTER JOIN (SELECT y.key as key, count(y.value) AS cnt FROM src1 y group by y.key) b + ON (a.key = b.key)) tmp +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +POSTHOOK: Input: default@src1 +#### A masked pattern was here #### +652447 37 652447 25 +PREHOOK: query: EXPLAIN +SELECT SUM(HASH(key1)), SUM(HASH(cnt1)), SUM(HASH(key2)), SUM(HASH(cnt2)) +FROM (SELECT a.key AS key1, a.cnt AS cnt1, b.key AS key2, b.cnt AS cnt2 + FROM (SELECT x.key as key, count(x.value) AS cnt FROM src x group by x.key) a + RIGHT OUTER JOIN (SELECT y.key as key, count(y.value) AS cnt FROM src1 y group by y.key) b + ON (a.key = b.key)) tmp +PREHOOK: type: QUERY +POSTHOOK: query: EXPLAIN +SELECT SUM(HASH(key1)), SUM(HASH(cnt1)), SUM(HASH(key2)), SUM(HASH(cnt2)) +FROM (SELECT a.key AS key1, a.cnt AS cnt1, b.key AS key2, b.cnt AS cnt2 + FROM (SELECT x.key as key, count(x.value) AS cnt FROM src x group by x.key) a + RIGHT OUTER JOIN (SELECT y.key as key, count(y.value) AS cnt FROM src1 y group by y.key) b + ON (a.key = b.key)) tmp +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) + Reducer 3 <- Reducer 2 (SIMPLE_EDGE), Reducer 6 (SIMPLE_EDGE) + Reducer 4 <- Reducer 3 (SIMPLE_EDGE) + Reducer 6 <- Map 5 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: x + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: count(value) + keys: key (type: string) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 205 Data size: 19475 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 205 Data size: 19475 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: bigint) + Execution mode: llap + LLAP IO: no inputs + Map 5 + Map Operator Tree: + TableScan + alias: y + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: key, value + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: count(value) + keys: key (type: string) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 12 Data size: 1128 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 12 Data size: 1128 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: bigint) + Execution mode: llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + keys: KEY._col0 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 205 Data size: 19475 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 205 Data size: 19475 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: bigint) + Reducer 3 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Right Outer Join0 to 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 12 Data size: 2268 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: hash(_col0) (type: int), hash(_col1) (type: int), hash(_col2) (type: int), hash(_col3) (type: int) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 12 Data size: 2268 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: sum(_col0), sum(_col1), sum(_col2), sum(_col3) + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: bigint), _col1 (type: bigint), _col2 (type: bigint), _col3 (type: bigint) + Reducer 4 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: sum(VALUE._col0), sum(VALUE._col1), sum(VALUE._col2), sum(VALUE._col3) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Reducer 6 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + keys: KEY._col0 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 12 Data size: 1128 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 12 Data size: 1128 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: bigint) + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: SELECT SUM(HASH(key1)), SUM(HASH(cnt1)), SUM(HASH(key2)), SUM(HASH(cnt2)) +FROM (SELECT a.key AS key1, a.cnt AS cnt1, b.key AS key2, b.cnt AS cnt2 + FROM (SELECT x.key as key, count(x.value) AS cnt FROM src x group by x.key) a + RIGHT OUTER JOIN (SELECT y.key as key, count(y.value) AS cnt FROM src1 y group by y.key) b + ON (a.key = b.key)) tmp +PREHOOK: type: QUERY +PREHOOK: Input: default@src +PREHOOK: Input: default@src1 +#### A masked pattern was here #### +POSTHOOK: query: SELECT SUM(HASH(key1)), SUM(HASH(cnt1)), SUM(HASH(key2)), SUM(HASH(cnt2)) +FROM (SELECT a.key AS key1, a.cnt AS cnt1, b.key AS key2, b.cnt AS cnt2 + FROM (SELECT x.key as key, count(x.value) AS cnt FROM src x group by x.key) a + RIGHT OUTER JOIN (SELECT y.key as key, count(y.value) AS cnt FROM src1 y group by y.key) b + ON (a.key = b.key)) tmp +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +POSTHOOK: Input: default@src1 +#### A masked pattern was here #### +652447 37 652447 25 +PREHOOK: query: -- Full Outer Join should be handled. +EXPLAIN +SELECT SUM(HASH(key1)), SUM(HASH(cnt1)), SUM(HASH(key2)), SUM(HASH(cnt2)) +FROM (SELECT a.key AS key1, a.cnt AS cnt1, b.key AS key2, b.cnt AS cnt2 + FROM (SELECT x.key as key, count(x.value) AS cnt FROM src x group by x.key) a + FULL OUTER JOIN (SELECT y.key as key, count(y.value) AS cnt FROM src1 y group by y.key) b + ON (a.key = b.key)) tmp +PREHOOK: type: QUERY +POSTHOOK: query: -- Full Outer Join should be handled. +EXPLAIN +SELECT SUM(HASH(key1)), SUM(HASH(cnt1)), SUM(HASH(key2)), SUM(HASH(cnt2)) +FROM (SELECT a.key AS key1, a.cnt AS cnt1, b.key AS key2, b.cnt AS cnt2 + FROM (SELECT x.key as key, count(x.value) AS cnt FROM src x group by x.key) a + FULL OUTER JOIN (SELECT y.key as key, count(y.value) AS cnt FROM src1 y group by y.key) b + ON (a.key = b.key)) tmp +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) + Reducer 3 <- Reducer 2 (SIMPLE_EDGE), Reducer 6 (SIMPLE_EDGE) + Reducer 4 <- Reducer 3 (SIMPLE_EDGE) + Reducer 6 <- Map 5 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: x + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: key, value + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: count(value) + keys: key (type: string) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 205 Data size: 19475 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 205 Data size: 19475 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: bigint) + Execution mode: llap + LLAP IO: no inputs + Map 5 + Map Operator Tree: + TableScan + alias: y + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: key, value + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: count(value) + keys: key (type: string) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 12 Data size: 1128 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 12 Data size: 1128 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: bigint) + Execution mode: llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + keys: KEY._col0 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 205 Data size: 19475 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 205 Data size: 19475 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: bigint) + Reducer 3 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Outer Join 0 to 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 217 Data size: 41013 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: hash(_col0) (type: int), hash(_col1) (type: int), hash(_col2) (type: int), hash(_col3) (type: int) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 217 Data size: 41013 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: sum(_col0), sum(_col1), sum(_col2), sum(_col3) + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: bigint), _col1 (type: bigint), _col2 (type: bigint), _col3 (type: bigint) + Reducer 4 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: sum(VALUE._col0), sum(VALUE._col1), sum(VALUE._col2), sum(VALUE._col3) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Reducer 6 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + keys: KEY._col0 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 12 Data size: 1128 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 12 Data size: 1128 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: bigint) + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: SELECT SUM(HASH(key1)), SUM(HASH(cnt1)), SUM(HASH(key2)), SUM(HASH(cnt2)) +FROM (SELECT a.key AS key1, a.cnt AS cnt1, b.key AS key2, b.cnt AS cnt2 + FROM (SELECT x.key as key, count(x.value) AS cnt FROM src x group by x.key) a + FULL OUTER JOIN (SELECT y.key as key, count(y.value) AS cnt FROM src1 y group by y.key) b + ON (a.key = b.key)) tmp +PREHOOK: type: QUERY +PREHOOK: Input: default@src +PREHOOK: Input: default@src1 +#### A masked pattern was here #### +POSTHOOK: query: SELECT SUM(HASH(key1)), SUM(HASH(cnt1)), SUM(HASH(key2)), SUM(HASH(cnt2)) +FROM (SELECT a.key AS key1, a.cnt AS cnt1, b.key AS key2, b.cnt AS cnt2 + FROM (SELECT x.key as key, count(x.value) AS cnt FROM src x group by x.key) a + FULL OUTER JOIN (SELECT y.key as key, count(y.value) AS cnt FROM src1 y group by y.key) b + ON (a.key = b.key)) tmp +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +POSTHOOK: Input: default@src1 +#### A masked pattern was here #### +12744278 500 652447 25 +PREHOOK: query: EXPLAIN +SELECT SUM(HASH(key1)), SUM(HASH(cnt1)), SUM(HASH(key2)), SUM(HASH(cnt2)) +FROM (SELECT a.key AS key1, a.cnt AS cnt1, b.key AS key2, b.cnt AS cnt2 + FROM (SELECT x.key as key, count(x.value) AS cnt FROM src x group by x.key) a + FULL OUTER JOIN (SELECT y.key as key, count(y.value) AS cnt FROM src1 y group by y.key) b + ON (a.key = b.key)) tmp +PREHOOK: type: QUERY +POSTHOOK: query: EXPLAIN +SELECT SUM(HASH(key1)), SUM(HASH(cnt1)), SUM(HASH(key2)), SUM(HASH(cnt2)) +FROM (SELECT a.key AS key1, a.cnt AS cnt1, b.key AS key2, b.cnt AS cnt2 + FROM (SELECT x.key as key, count(x.value) AS cnt FROM src x group by x.key) a + FULL OUTER JOIN (SELECT y.key as key, count(y.value) AS cnt FROM src1 y group by y.key) b + ON (a.key = b.key)) tmp +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) + Reducer 3 <- Reducer 2 (SIMPLE_EDGE), Reducer 6 (SIMPLE_EDGE) + Reducer 4 <- Reducer 3 (SIMPLE_EDGE) + Reducer 6 <- Map 5 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: x + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: key, value + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: count(value) + keys: key (type: string) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 205 Data size: 19475 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 205 Data size: 19475 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: bigint) + Execution mode: llap + LLAP IO: no inputs + Map 5 + Map Operator Tree: + TableScan + alias: y + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: key, value + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: count(value) + keys: key (type: string) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 12 Data size: 1128 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 12 Data size: 1128 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: bigint) + Execution mode: llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + keys: KEY._col0 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 205 Data size: 19475 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 205 Data size: 19475 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: bigint) + Reducer 3 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Outer Join 0 to 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 217 Data size: 41013 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: hash(_col0) (type: int), hash(_col1) (type: int), hash(_col2) (type: int), hash(_col3) (type: int) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 217 Data size: 41013 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: sum(_col0), sum(_col1), sum(_col2), sum(_col3) + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: bigint), _col1 (type: bigint), _col2 (type: bigint), _col3 (type: bigint) + Reducer 4 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: sum(VALUE._col0), sum(VALUE._col1), sum(VALUE._col2), sum(VALUE._col3) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Reducer 6 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + keys: KEY._col0 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 12 Data size: 1128 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 12 Data size: 1128 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: bigint) + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: SELECT SUM(HASH(key1)), SUM(HASH(cnt1)), SUM(HASH(key2)), SUM(HASH(cnt2)) +FROM (SELECT a.key AS key1, a.cnt AS cnt1, b.key AS key2, b.cnt AS cnt2 + FROM (SELECT x.key as key, count(x.value) AS cnt FROM src x group by x.key) a + FULL OUTER JOIN (SELECT y.key as key, count(y.value) AS cnt FROM src1 y group by y.key) b + ON (a.key = b.key)) tmp +PREHOOK: type: QUERY +PREHOOK: Input: default@src +PREHOOK: Input: default@src1 +#### A masked pattern was here #### +POSTHOOK: query: SELECT SUM(HASH(key1)), SUM(HASH(cnt1)), SUM(HASH(key2)), SUM(HASH(cnt2)) +FROM (SELECT a.key AS key1, a.cnt AS cnt1, b.key AS key2, b.cnt AS cnt2 + FROM (SELECT x.key as key, count(x.value) AS cnt FROM src x group by x.key) a + FULL OUTER JOIN (SELECT y.key as key, count(y.value) AS cnt FROM src1 y group by y.key) b + ON (a.key = b.key)) tmp +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +POSTHOOK: Input: default@src1 +#### A masked pattern was here #### +12744278 500 652447 25 +PREHOOK: query: EXPLAIN +SELECT SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt)) +FROM (SELECT a.key AS key, count(1) AS cnt + FROM (SELECT x.key as key, count(x.value) AS cnt FROM src x group by x.key) a + FULL OUTER JOIN (SELECT y.key as key, count(y.value) AS cnt FROM src1 y group by y.key) b + ON (a.key = b.key) + GROUP BY a.key) tmp +PREHOOK: type: QUERY +POSTHOOK: query: EXPLAIN +SELECT SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt)) +FROM (SELECT a.key AS key, count(1) AS cnt + FROM (SELECT x.key as key, count(x.value) AS cnt FROM src x group by x.key) a + FULL OUTER JOIN (SELECT y.key as key, count(y.value) AS cnt FROM src1 y group by y.key) b + ON (a.key = b.key) + GROUP BY a.key) tmp +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) + Reducer 3 <- Reducer 2 (SIMPLE_EDGE), Reducer 7 (SIMPLE_EDGE) + Reducer 4 <- Reducer 3 (SIMPLE_EDGE) + Reducer 5 <- Reducer 4 (SIMPLE_EDGE) + Reducer 7 <- Map 6 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: x + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string) + outputColumnNames: key + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + keys: key (type: string) + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 205 Data size: 17835 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 205 Data size: 17835 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: llap + LLAP IO: no inputs + Map 6 + Map Operator Tree: + TableScan + alias: y + Statistics: Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string) + outputColumnNames: key + Statistics: Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + keys: key (type: string) + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 12 Data size: 1032 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 12 Data size: 1032 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + keys: KEY._col0 (type: string) + mode: mergepartial + outputColumnNames: _col0 + Statistics: Num rows: 205 Data size: 17835 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 205 Data size: 17835 Basic stats: COMPLETE Column stats: COMPLETE + Reducer 3 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Outer Join 0 to 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 217 Data size: 18879 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: count(1) + keys: _col0 (type: string) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 14 Data size: 1330 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 14 Data size: 1330 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: bigint) + Reducer 4 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + keys: KEY._col0 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 14 Data size: 1330 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: hash(_col0) (type: int), hash(_col1) (type: int) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 14 Data size: 1330 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: sum(_col0), sum(_col1) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: bigint), _col1 (type: bigint) + Reducer 5 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: sum(VALUE._col0), sum(VALUE._col1) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Reducer 7 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + keys: KEY._col0 (type: string) + mode: mergepartial + outputColumnNames: _col0 + Statistics: Num rows: 12 Data size: 1032 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 12 Data size: 1032 Basic stats: COMPLETE Column stats: COMPLETE + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: SELECT SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt)) +FROM (SELECT a.key AS key, count(1) AS cnt + FROM (SELECT x.key as key, count(x.value) AS cnt FROM src x group by x.key) a + FULL OUTER JOIN (SELECT y.key as key, count(y.value) AS cnt FROM src1 y group by y.key) b + ON (a.key = b.key) + GROUP BY a.key) tmp +PREHOOK: type: QUERY +PREHOOK: Input: default@src +PREHOOK: Input: default@src1 +#### A masked pattern was here #### +POSTHOOK: query: SELECT SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt)) +FROM (SELECT a.key AS key, count(1) AS cnt + FROM (SELECT x.key as key, count(x.value) AS cnt FROM src x group by x.key) a + FULL OUTER JOIN (SELECT y.key as key, count(y.value) AS cnt FROM src1 y group by y.key) b + ON (a.key = b.key) + GROUP BY a.key) tmp +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +POSTHOOK: Input: default@src1 +#### A masked pattern was here #### +12744278 310 +PREHOOK: query: -- After FULL OUTER JOIN, keys with null values are not grouped, right now, +-- we have to generate 2 MR jobs for tmp, 1 MR job for a join b and another for the +-- GroupByOperator on key. +EXPLAIN +SELECT SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt)) +FROM (SELECT a.key AS key, count(1) AS cnt + FROM (SELECT x.key as key, count(x.value) AS cnt FROM src x group by x.key) a + FULL OUTER JOIN (SELECT y.key as key, count(y.value) AS cnt FROM src1 y group by y.key) b + ON (a.key = b.key) + GROUP BY a.key) tmp +PREHOOK: type: QUERY +POSTHOOK: query: -- After FULL OUTER JOIN, keys with null values are not grouped, right now, +-- we have to generate 2 MR jobs for tmp, 1 MR job for a join b and another for the +-- GroupByOperator on key. +EXPLAIN +SELECT SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt)) +FROM (SELECT a.key AS key, count(1) AS cnt + FROM (SELECT x.key as key, count(x.value) AS cnt FROM src x group by x.key) a + FULL OUTER JOIN (SELECT y.key as key, count(y.value) AS cnt FROM src1 y group by y.key) b + ON (a.key = b.key) + GROUP BY a.key) tmp +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) + Reducer 3 <- Reducer 2 (SIMPLE_EDGE), Reducer 7 (SIMPLE_EDGE) + Reducer 4 <- Reducer 3 (SIMPLE_EDGE) + Reducer 5 <- Reducer 4 (SIMPLE_EDGE) + Reducer 7 <- Map 6 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: x + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string) + outputColumnNames: key + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + keys: key (type: string) + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 205 Data size: 17835 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 205 Data size: 17835 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: llap + LLAP IO: no inputs + Map 6 + Map Operator Tree: + TableScan + alias: y + Statistics: Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string) + outputColumnNames: key + Statistics: Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + keys: key (type: string) + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 12 Data size: 1032 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 12 Data size: 1032 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: llap + LLAP IO: no inputs + Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + keys: KEY._col0 (type: string) + mode: mergepartial + outputColumnNames: _col0 + Statistics: Num rows: 205 Data size: 17835 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 205 Data size: 17835 Basic stats: COMPLETE Column stats: COMPLETE + Reducer 3 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Outer Join 0 to 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 217 Data size: 18879 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: count(1) + keys: _col0 (type: string) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 14 Data size: 1330 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 14 Data size: 1330 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: bigint) + Reducer 4 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + keys: KEY._col0 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 14 Data size: 1330 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: hash(_col0) (type: int), hash(_col1) (type: int) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 14 Data size: 1330 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: sum(_col0), sum(_col1) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: bigint), _col1 (type: bigint) + Reducer 5 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: sum(VALUE._col0), sum(VALUE._col1) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Reducer 7 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + keys: KEY._col0 (type: string) + mode: mergepartial + outputColumnNames: _col0 + Statistics: Num rows: 12 Data size: 1032 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 12 Data size: 1032 Basic stats: COMPLETE Column stats: COMPLETE + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: SELECT SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt)) +FROM (SELECT a.key AS key, count(1) AS cnt + FROM (SELECT x.key as key, count(x.value) AS cnt FROM src x group by x.key) a + FULL OUTER JOIN (SELECT y.key as key, count(y.value) AS cnt FROM src1 y group by y.key) b + ON (a.key = b.key) + GROUP BY a.key) tmp +PREHOOK: type: QUERY +PREHOOK: Input: default@src +PREHOOK: Input: default@src1 +#### A masked pattern was here #### +POSTHOOK: query: SELECT SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt)) +FROM (SELECT a.key AS key, count(1) AS cnt + FROM (SELECT x.key as key, count(x.value) AS cnt FROM src x group by x.key) a + FULL OUTER JOIN (SELECT y.key as key, count(y.value) AS cnt FROM src1 y group by y.key) b + ON (a.key = b.key) + GROUP BY a.key) tmp +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +POSTHOOK: Input: default@src1 +#### A masked pattern was here #### +12744278 310 +PREHOOK: query: -- When Correlation Optimizer is turned off, we need 4 MR jobs. +-- When Correlation Optimizer is turned on, the subquery of tmp will be evaluated in +-- a single MR job (including the subquery a, the subquery b, and a join b). So, we +-- will have 2 MR jobs. +EXPLAIN +SELECT SUM(HASH(key1)), SUM(HASH(cnt1)), SUM(HASH(key2)), SUM(HASH(cnt2)) +FROM (SELECT a.key AS k
<TRUNCATED>