You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@hive.apache.org by pr...@apache.org on 2016/10/12 07:27:41 UTC
[28/37] hive git commit: HIVE-14877: Move slow CliDriver tests to
MiniLlap (Prasanth Jayachandran reviewed by Siddharth Seth)
http://git-wip-us.apache.org/repos/asf/hive/blob/1f258e96/ql/src/test/results/clientpositive/llap/correlationoptimizer6.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/correlationoptimizer6.q.out b/ql/src/test/results/clientpositive/llap/correlationoptimizer6.q.out
new file mode 100644
index 0000000..cf66d25
--- /dev/null
+++ b/ql/src/test/results/clientpositive/llap/correlationoptimizer6.q.out
@@ -0,0 +1,3994 @@
+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-0 depends on stages: Stage-1
+
+STAGE PLANS:
+ Stage: Stage-1
+ Tez
+#### A masked pattern was here ####
+ Edges:
+ Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 5 (SIMPLE_EDGE)
+ Reducer 3 <- Reducer 2 (SIMPLE_EDGE)
+ Reducer 4 <- Reducer 3 (SIMPLE_EDGE), Reducer 8 (SIMPLE_EDGE)
+ Reducer 7 <- Map 6 (SIMPLE_EDGE), Map 9 (SIMPLE_EDGE)
+ Reducer 8 <- Reducer 7 (SIMPLE_EDGE)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: x
+ Statistics: Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE
+ Filter Operator
+ predicate: key is not null (type: boolean)
+ Statistics: Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: key (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 25 Data size: 2150 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: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE
+ Execution mode: llap
+ LLAP IO: no inputs
+ Map 5
+ Map Operator Tree:
+ TableScan
+ alias: y
+ Statistics: Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE
+ Filter Operator
+ predicate: key is not null (type: boolean)
+ Statistics: Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: key (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 25 Data size: 2150 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: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE
+ Execution mode: llap
+ LLAP IO: no inputs
+ Map 6
+ Map Operator Tree:
+ TableScan
+ alias: x
+ Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
+ Filter Operator
+ predicate: key is not null (type: boolean)
+ Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: key (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 500 Data size: 43500 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: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
+ Execution mode: llap
+ LLAP IO: no inputs
+ Map 9
+ Map Operator Tree:
+ TableScan
+ alias: y
+ Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
+ Filter Operator
+ predicate: key is not null (type: boolean)
+ Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: key (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 500 Data size: 43500 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: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
+ Execution mode: llap
+ LLAP IO: no inputs
+ Reducer 2
+ 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
+ Statistics: Num rows: 44 Data size: 3784 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: 1316 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: 1316 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col1 (type: bigint)
+ Reducer 3
+ 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: 1316 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: 1316 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col1 (type: bigint)
+ Reducer 4
+ 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: 14 Data size: 2646 Basic stats: COMPLETE Column stats: COMPLETE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 14 Data size: 2646 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:
+ Merge Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col0 (type: string)
+ 1 _col0 (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 1219 Data size: 106053 Basic stats: COMPLETE Column stats: COMPLETE
+ Group By Operator
+ aggregations: count(1)
+ keys: _col0 (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)
+ Reducer 8
+ 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)
+
+ 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
+ Tez
+#### A masked pattern was here ####
+ Edges:
+ Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 5 (SIMPLE_EDGE)
+ Reducer 3 <- Reducer 2 (SIMPLE_EDGE)
+ Reducer 4 <- Reducer 3 (SIMPLE_EDGE), Reducer 8 (SIMPLE_EDGE)
+ Reducer 7 <- Map 6 (SIMPLE_EDGE), Map 9 (SIMPLE_EDGE)
+ Reducer 8 <- Reducer 7 (SIMPLE_EDGE)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: x
+ Statistics: Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE
+ Filter Operator
+ predicate: key is not null (type: boolean)
+ Statistics: Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: key (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 25 Data size: 2150 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: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE
+ Execution mode: llap
+ LLAP IO: no inputs
+ Map 5
+ Map Operator Tree:
+ TableScan
+ alias: y
+ Statistics: Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE
+ Filter Operator
+ predicate: key is not null (type: boolean)
+ Statistics: Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: key (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 25 Data size: 2150 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: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE
+ Execution mode: llap
+ LLAP IO: no inputs
+ Map 6
+ Map Operator Tree:
+ TableScan
+ alias: x
+ Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
+ Filter Operator
+ predicate: key is not null (type: boolean)
+ Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: key (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 500 Data size: 43500 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: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
+ Execution mode: llap
+ LLAP IO: no inputs
+ Map 9
+ Map Operator Tree:
+ TableScan
+ alias: y
+ Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
+ Filter Operator
+ predicate: key is not null (type: boolean)
+ Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: key (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 500 Data size: 43500 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: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
+ Execution mode: llap
+ LLAP IO: no inputs
+ Reducer 2
+ 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
+ Statistics: Num rows: 44 Data size: 3784 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: 1316 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: 1316 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col1 (type: bigint)
+ Reducer 3
+ 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: 1316 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: 1316 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col1 (type: bigint)
+ Reducer 4
+ 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: 14 Data size: 2646 Basic stats: COMPLETE Column stats: COMPLETE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 14 Data size: 2646 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:
+ Merge Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col0 (type: string)
+ 1 _col0 (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 1219 Data size: 106053 Basic stats: COMPLETE Column stats: COMPLETE
+ Group By Operator
+ aggregations: count(1)
+ keys: _col0 (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)
+ Reducer 8
+ 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)
+
+ 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-1 is a root stage
+ Stage-0 depends on stages: Stage-1
+
+STAGE PLANS:
+ Stage: Stage-1
+ Tez
+#### A masked pattern was here ####
+ Edges:
+ Map 1 <- Map 3 (BROADCAST_EDGE)
+ Map 4 <- Map 6 (BROADCAST_EDGE)
+ Reducer 2 <- Map 1 (SIMPLE_EDGE)
+ Reducer 5 <- Map 4 (SIMPLE_EDGE), Reducer 2 (BROADCAST_EDGE)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: x
+ Statistics: Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE
+ Filter Operator
+ predicate: key is not null (type: boolean)
+ Statistics: Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: key (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col0 (type: string)
+ 1 _col0 (type: string)
+ outputColumnNames: _col0
+ input vertices:
+ 1 Map 3
+ Statistics: Num rows: 44 Data size: 3784 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: 1316 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: 1316 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col1 (type: bigint)
+ Execution mode: llap
+ LLAP IO: no inputs
+ Map 3
+ Map Operator Tree:
+ TableScan
+ alias: y
+ Statistics: Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE
+ Filter Operator
+ predicate: key is not null (type: boolean)
+ Statistics: Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: key (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 25 Data size: 2150 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: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE
+ Execution mode: llap
+ LLAP IO: no inputs
+ Map 4
+ Map Operator Tree:
+ TableScan
+ alias: x
+ Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
+ Filter Operator
+ predicate: key is not null (type: boolean)
+ Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: key (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col0 (type: string)
+ 1 _col0 (type: string)
+ outputColumnNames: _col0
+ input vertices:
+ 1 Map 6
+ Statistics: Num rows: 1219 Data size: 106053 Basic stats: COMPLETE Column stats: COMPLETE
+ Group By Operator
+ aggregations: count(1)
+ keys: _col0 (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 6
+ Map Operator Tree:
+ TableScan
+ alias: y
+ Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
+ Filter Operator
+ predicate: key is not null (type: boolean)
+ Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: key (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 500 Data size: 43500 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: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
+ 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: 14 Data size: 1316 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: 1316 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col1 (type: bigint)
+ Reducer 5
+ 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
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col0 (type: string)
+ 1 _col0 (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3
+ input vertices:
+ 0 Reducer 2
+ Statistics: Num rows: 14 Data size: 2646 Basic stats: COMPLETE Column stats: COMPLETE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 14 Data size: 2646 Basic stats: COMPLETE Column stats: COMPLETE
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ ListSink
+
+PREHOOK: query: SELECT 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-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 4 (SIMPLE_EDGE)
+ Reducer 4 <- Map 3 (SIMPLE_EDGE)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: xx
+ Statistics: Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE
+ Filter Operator
+ predicate: key is not null (type: boolean)
+ Statistics: Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: key (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 25 Data size: 2150 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: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE
+ Execution mode: llap
+ LLAP IO: no inputs
+ Map 3
+ Map Operator Tree:
+ TableScan
+ alias: x
+ Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
+ Filter Operator
+ predicate: key is not null (type: boolean)
+ Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: key (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
+ Group By Operator
+ aggregations: count(1)
+ keys: _col0 (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
+ Reducer 2
+ 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
+ Statistics: Num rows: 25 Data size: 4525 Basic stats: COMPLETE Column stats: COMPLETE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 25 Data size: 4525 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 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: 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)
+
+ 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
+ Tez
+#### A masked pattern was here ####
+ Edges:
+ Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 4 (SIMPLE_EDGE)
+ Reducer 4 <- Map 3 (SIMPLE_EDGE)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: xx
+ Statistics: Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE
+ Filter Operator
+ predicate: key is not null (type: boolean)
+ Statistics: Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: key (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 25 Data size: 2150 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: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE
+ Execution mode: llap
+ LLAP IO: no inputs
+ Map 3
+ Map Operator Tree:
+ TableScan
+ alias: x
+ Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
+ Filter Operator
+ predicate: key is not null (type: boolean)
+ Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: key (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
+ Group By Operator
+ aggregations: count(1)
+ keys: _col0 (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
+ Reducer 2
+ 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
+ Statistics: Num rows: 25 Data size: 4525 Basic stats: COMPLETE Column stats: COMPLETE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 25 Data size: 4525 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 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: 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)
+
+ 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-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 5 (SIMPLE_EDGE)
+ Reducer 4 <- Map 3 (SIMPLE_EDGE), Map 6 (SIMPLE_EDGE)
+ Reducer 5 <- Reducer 4 (SIMPLE_EDGE)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: xx
+ Statistics: Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE
+ Filter Operator
+ predicate: key is not null (type: boolean)
+ Statistics: Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: key (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 25 Data size: 2150 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: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE
+ Execution mode: llap
+ LLAP IO: no inputs
+ Map 3
+ Map Operator Tree:
+ TableScan
+ alias: x
+ Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
+ Filter Operator
+ predicate: key is not null (type: boolean)
+ Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: key (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 500 Data size: 43500 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: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
+ Execution mode: llap
+ LLAP IO: no inputs
+ Map 6
+ Map Operator Tree:
+ TableScan
+ alias: y
+ Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
+ Filter Operator
+ predicate: key is not null (type: boolean)
+ Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: key (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 500 Data size: 43500 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: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
+ Execution mode: llap
+ LLAP IO: no inputs
+ Reducer 2
+ 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
+ Statistics: Num rows: 25 Data size: 4525 Basic stats: COMPLETE Column stats: COMPLETE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 25 Data size: 4525 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 4
+ 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
+ Statistics: Num rows: 1219 Data size: 106053 Basic stats: COMPLETE Column stats: COMPLETE
+ Group By Operator
+ aggregations: count(1)
+ keys: _col0 (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)
+ Reducer 5
+ 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)
+
+ 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
+ Tez
+#### A masked pattern was here ####
+ Edges:
+ Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 5 (SIMPLE_EDGE)
+ Reducer 4 <- Map 3 (SIMPLE_EDGE), Map 6 (SIMPLE_EDGE)
+ Reducer 5 <- Reducer 4 (SIMPLE_EDGE)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: xx
+ Statistics: Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE
+ Filter Operator
+ predicate: key is not null (type: boolean)
+ Statistics: Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: key (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 25 Data size: 2150 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: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE
+ Execution mode: llap
+ LLAP IO: no inputs
+ Map 3
+ Map Operator Tree:
+ TableScan
+ alias: x
+ Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
+ Filter Operator
+ predicate: key is not null (type: boolean)
+ Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: key (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 500 Data size: 43500 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: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
+ Execution mode: llap
+ LLAP IO: no inputs
+ Map 6
+ Map Operator Tree:
+ TableScan
+ alias: y
+ Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
+ Filter Operator
+ predicate: key is not null (type: boolean)
+ Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: key (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 500 Data size: 43500 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: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
+ Execution mode: llap
+ LLAP IO: no inputs
+ Reducer 2
+ 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
+ Statistics: Num rows: 25 Data size: 4525 Basic stats: COMPLETE Column stats: COMPLETE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 25 Data size: 4525 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 4
+ 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
+ Statistics: Num rows: 1219 Data size: 106053 Basic stats: COMPLETE Column stats: COMPLETE
+ Group By Operator
+ aggregations: count(1)
+ keys: _col0 (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)
+ Reducer 5
+ 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)
+
+ 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-0 depends on stages: Stage-1
+
+STAGE PLANS:
+ Stage: Stage-1
+ Tez
+#### A masked pattern was here ####
+ Edges:
+ Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 5 (SIMPLE_EDGE)
+ Reducer 3 <- Reducer 2 (SIMPLE_EDGE)
+ Reducer 4 <- Map 6 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: x
+ Statistics: Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE
+ Filter Operator
+ predicate: key is not null (type: boolean)
+ Statistics: Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: key (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 25 Data size: 2150 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: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE
+ Execution mode: llap
+ LLAP IO: no inputs
+ Map 5
+ Map Operator Tree:
+ TableScan
+ alias: y
+ Statistics: Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE
+ Filter Operator
+ predicate: key is not null (type: boolean)
+ Statistics: Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: key (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 25 Data size: 2150 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: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE
+ Execution mode: llap
+ LLAP IO: no inputs
+ Map 6
+ Map Operator Tree:
+ TableScan
+ alias: yy
+ Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
+ Filter Operator
+ predicate: key is not null (type: boolean)
+ Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: key (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 500 Data size: 43500 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: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
+ Execution mode: llap
+ LLAP IO: no inputs
+ Reducer 2
+ 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
+ Statistics: Num rows: 44 Data size: 3784 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: 1316 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: 1316 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col1 (type: bigint)
+ Reducer 3
+ 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: 1316 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: 1316 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col1 (type: bigint)
+ Reducer 4
+ 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
+ Statistics: Num rows: 34 Data size: 6154 Basic stats: COMPLETE Column stats: COMPLETE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 34 Data size: 6154 Basic stats: COMPLETE Column stats: COMPLETE
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ ListSink
+
+PREHOOK: query: SELECT 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
+ Tez
+#### A masked pattern was here ####
+ Edges:
+ Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 5 (SIMPLE_EDGE)
+ Reducer 3 <- Reducer 2 (SIMPLE_EDGE)
+ Reducer 4 <- Map 6 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: x
+ Statistics: Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE
+ Filter Operator
+ predicate: key is not null (type: boolean)
+ Statistics: Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: key (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 25 Data size: 2150 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: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE
+ Execution mode: llap
+ LLAP IO: no inputs
+ Map 5
+ Map Operator Tree:
+ TableScan
+ alias: y
+ Statistics: Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE
+ Filter Operator
+ predicate: key is not null (type: boolean)
+ Statistics: Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: key (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 25 Data size: 2150 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: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE
+ Execution mode: llap
+ LLAP IO: no inputs
+ Map 6
+ Map Operator Tree:
+ TableScan
+ alias: yy
+ Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
+ Filter Operator
+ predicate: key is not null (type: boolean)
+ Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: key (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 500 Data size: 43500 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: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
+ Execution mode: llap
+ LLAP IO: no inputs
+ Reducer 2
+ 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
+ Statistics: Num rows: 44 Data size: 3784 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: 1316 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: 1316 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col1 (type: bigint)
+ Reducer 3
+ 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: 1316 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: 1316 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col1 (type: bigint)
+ Reducer 4
+ 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
+ Statistics: Num rows: 34 Data size: 6154 Basic stats: COMPLETE Column stats: COMPLETE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 34 Data size: 6154 Basic stats: COMPLETE Column stats: COMPLETE
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ ListSink
+
+PREHOOK: query: SELECT 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-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), Map 3 (SIMPLE_EDGE), Reducer 6 (SIMPLE_EDGE)
+ Reducer 5 <- Map 4 (SIMPLE_EDGE), Map 7 (SIMPLE_EDGE)
+ Reducer 6 <- Reducer 5 (SIMPLE_EDGE)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: zz
+ Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
+ Filter Operator
+ predicate: key is not null (type: boolean)
+ Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: key (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 500 Data size: 43500 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: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
+ Execution mode: llap
+ LLAP IO: no inputs
+ Map 3
+ Map Operator Tree:
+ TableScan
+ alias: xx
+ Statistics: Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE
+ Filter Operator
+ predicate: key is not null (type: boolean)
+ Statistics: Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: key (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 25 Data size: 2150 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: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE
+ Execution mode: llap
+ LLAP IO: no inputs
+ Map 4
+ Map Operator Tree:
+ TableScan
+ alias: x
+ Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
+ Filter Operator
+ predicate: key is not null (type: boolean)
+ Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: key (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 500 Data size: 43500 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: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
+ Execution mode: llap
+ LLAP IO: no inputs
+ Map 7
+ Map Operator Tree:
+ TableScan
+ alias: y
+ Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
+ Filter Operator
+ predicate: key is not null (type: boolean)
+ Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: key (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 500 Data size: 43500 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: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
+ Execution mode: llap
+ LLAP IO: no inputs
+ Reducer 2
+ Execution mode: llap
+ Reduce Operator Tree:
+ Merge 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: 60 Data size: 10860 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: _col1 (type: string), _col2 (type: string), _col3 (type: bigint)
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 60 Data size: 10860 Basic stats: COMPLETE Column stats: COMPLETE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 60 Data size: 10860 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 5
+ 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
+ Statistics: Num rows: 1219 Data size: 106053 Basic stats: COMPLETE Column stats: COMPLETE
+ Group By Operator
+ aggregations: count(1)
+ keys: _col0 (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)
+ 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: 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)
+
+ 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
+ Tez
+#### A masked pattern was here ####
+ Edges:
+ Reducer 2 <- Map
<TRUNCATED>