You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@hive.apache.org by sp...@apache.org on 2015/05/20 18:01:35 UTC
[16/50] [abbrv] hive git commit: HIVE-10565: Native Vector Map Join
doesn't handle filtering and matching on LEFT OUTER JOIN repeated key
correctly (Matt McCline via Gunther Hagleitner)
http://git-wip-us.apache.org/repos/asf/hive/blob/2b9f2f5e/ql/src/test/results/clientpositive/vector_join30.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/vector_join30.q.out b/ql/src/test/results/clientpositive/vector_join30.q.out
new file mode 100644
index 0000000..57f9aeb
--- /dev/null
+++ b/ql/src/test/results/clientpositive/vector_join30.q.out
@@ -0,0 +1,2194 @@
+PREHOOK: query: -- SORT_QUERY_RESULTS
+
+CREATE TABLE orcsrc STORED AS ORC AS SELECT * FROM src
+PREHOOK: type: CREATETABLE_AS_SELECT
+PREHOOK: Input: default@src
+PREHOOK: Output: database:default
+PREHOOK: Output: default@orcsrc
+POSTHOOK: query: -- SORT_QUERY_RESULTS
+
+CREATE TABLE orcsrc STORED AS ORC AS SELECT * FROM src
+POSTHOOK: type: CREATETABLE_AS_SELECT
+POSTHOOK: Input: default@src
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@orcsrc
+PREHOOK: query: explain
+FROM
+(SELECT orcsrc.* FROM orcsrc sort by key) x
+JOIN
+(SELECT orcsrc.* FROM orcsrc sort by value) Y
+ON (x.key = Y.key)
+select sum(hash(Y.key,Y.value))
+PREHOOK: type: QUERY
+POSTHOOK: query: explain
+FROM
+(SELECT orcsrc.* FROM orcsrc sort by key) x
+JOIN
+(SELECT orcsrc.* FROM orcsrc sort by value) Y
+ON (x.key = Y.key)
+select sum(hash(Y.key,Y.value))
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-7 depends on stages: Stage-1, Stage-4 , consists of Stage-8, Stage-9, Stage-2
+ Stage-8 has a backup stage: Stage-2
+ Stage-5 depends on stages: Stage-8
+ Stage-3 depends on stages: Stage-2, Stage-5, Stage-6
+ Stage-9 has a backup stage: Stage-2
+ Stage-6 depends on stages: Stage-9
+ Stage-2
+ Stage-4 is a root stage
+ Stage-0 depends on stages: Stage-3
+
+STAGE PLANS:
+ Stage: Stage-1
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ alias: orcsrc
+ Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: key is not null (type: boolean)
+ Statistics: Num rows: 250 Data size: 44000 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: key (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 250 Data size: 44000 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ sort order: +
+ Statistics: Num rows: 250 Data size: 44000 Basic stats: COMPLETE Column stats: NONE
+ Execution mode: vectorized
+ Reduce Operator Tree:
+ Select Operator
+ expressions: KEY.reducesinkkey0 (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 250 Data size: 44000 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+
+ Stage: Stage-7
+ Conditional Operator
+
+ Stage: Stage-8
+ Map Reduce Local Work
+ Alias -> Map Local Tables:
+ $INTNAME1
+ Fetch Operator
+ limit: -1
+ Alias -> Map Local Operator Tree:
+ $INTNAME1
+ TableScan
+ HashTable Sink Operator
+ keys:
+ 0 _col0 (type: string)
+ 1 _col0 (type: string)
+
+ Stage: Stage-5
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col0 (type: string)
+ 1 _col0 (type: string)
+ outputColumnNames: _col2, _col3
+ Group By Operator
+ aggregations: sum(hash(_col2,_col3))
+ mode: hash
+ outputColumnNames: _col0
+ File Output Operator
+ compressed: false
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+ Local Work:
+ Map Reduce Local Work
+
+ Stage: Stage-3
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: bigint)
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: sum(VALUE._col0)
+ mode: mergepartial
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ Stage: Stage-9
+ Map Reduce Local Work
+ Alias -> Map Local Tables:
+ $INTNAME
+ Fetch Operator
+ limit: -1
+ Alias -> Map Local Operator Tree:
+ $INTNAME
+ TableScan
+ HashTable Sink Operator
+ keys:
+ 0 _col0 (type: string)
+ 1 _col0 (type: string)
+
+ Stage: Stage-6
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col0 (type: string)
+ 1 _col0 (type: string)
+ outputColumnNames: _col2, _col3
+ Group By Operator
+ aggregations: sum(hash(_col2,_col3))
+ mode: hash
+ outputColumnNames: _col0
+ File Output Operator
+ compressed: false
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+ Local Work:
+ Map Reduce Local Work
+
+ Stage: Stage-2
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 250 Data size: 44000 Basic stats: COMPLETE Column stats: NONE
+ TableScan
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 250 Data size: 44000 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col1 (type: string)
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col0 (type: string)
+ 1 _col0 (type: string)
+ outputColumnNames: _col2, _col3
+ Statistics: Num rows: 275 Data size: 48400 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: sum(hash(_col2,_col3))
+ mode: hash
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+
+ Stage: Stage-4
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ alias: orcsrc
+ Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: key is not null (type: boolean)
+ Statistics: Num rows: 250 Data size: 44000 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: key (type: string), value (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 250 Data size: 44000 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col1 (type: string)
+ sort order: +
+ Statistics: Num rows: 250 Data size: 44000 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: string)
+ Execution mode: vectorized
+ Reduce Operator Tree:
+ Select Operator
+ expressions: VALUE._col0 (type: string), KEY.reducesinkkey0 (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 250 Data size: 44000 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ ListSink
+
+PREHOOK: query: FROM
+(SELECT orcsrc.* FROM orcsrc sort by key) x
+JOIN
+(SELECT orcsrc.* FROM orcsrc sort by value) Y
+ON (x.key = Y.key)
+select sum(hash(Y.key,Y.value))
+PREHOOK: type: QUERY
+PREHOOK: Input: default@orcsrc
+#### A masked pattern was here ####
+POSTHOOK: query: FROM
+(SELECT orcsrc.* FROM orcsrc sort by key) x
+JOIN
+(SELECT orcsrc.* FROM orcsrc sort by value) Y
+ON (x.key = Y.key)
+select sum(hash(Y.key,Y.value))
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@orcsrc
+#### A masked pattern was here ####
+103231310608
+PREHOOK: query: explain
+FROM
+(SELECT orcsrc.* FROM orcsrc sort by key) x
+LEFT OUTER JOIN
+(SELECT orcsrc.* FROM orcsrc sort by value) Y
+ON (x.key = Y.key)
+select sum(hash(Y.key,Y.value))
+PREHOOK: type: QUERY
+POSTHOOK: query: explain
+FROM
+(SELECT orcsrc.* FROM orcsrc sort by key) x
+LEFT OUTER JOIN
+(SELECT orcsrc.* FROM orcsrc sort by value) Y
+ON (x.key = Y.key)
+select sum(hash(Y.key,Y.value))
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-6 depends on stages: Stage-1, Stage-4 , consists of Stage-7, Stage-2
+ Stage-7 has a backup stage: Stage-2
+ Stage-5 depends on stages: Stage-7
+ Stage-3 depends on stages: Stage-2, Stage-5
+ Stage-2
+ Stage-4 is a root stage
+ Stage-0 depends on stages: Stage-3
+
+STAGE PLANS:
+ Stage: Stage-1
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ alias: orcsrc
+ Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: key (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ sort order: +
+ Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE
+ Execution mode: vectorized
+ Reduce Operator Tree:
+ Select Operator
+ expressions: KEY.reducesinkkey0 (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+
+ Stage: Stage-6
+ Conditional Operator
+
+ Stage: Stage-7
+ Map Reduce Local Work
+ Alias -> Map Local Tables:
+ $INTNAME1
+ Fetch Operator
+ limit: -1
+ Alias -> Map Local Operator Tree:
+ $INTNAME1
+ TableScan
+ HashTable Sink Operator
+ keys:
+ 0 _col0 (type: string)
+ 1 _col0 (type: string)
+
+ Stage: Stage-5
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ Map Join Operator
+ condition map:
+ Left Outer Join0 to 1
+ keys:
+ 0 _col0 (type: string)
+ 1 _col0 (type: string)
+ outputColumnNames: _col2, _col3
+ Group By Operator
+ aggregations: sum(hash(_col2,_col3))
+ mode: hash
+ outputColumnNames: _col0
+ File Output Operator
+ compressed: false
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+ Local Work:
+ Map Reduce Local Work
+
+ Stage: Stage-3
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: bigint)
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: sum(VALUE._col0)
+ mode: mergepartial
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ Stage: Stage-2
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE
+ TableScan
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col1 (type: string)
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Left Outer Join0 to 1
+ keys:
+ 0 _col0 (type: string)
+ 1 _col0 (type: string)
+ outputColumnNames: _col2, _col3
+ Statistics: Num rows: 550 Data size: 96800 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: sum(hash(_col2,_col3))
+ mode: hash
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+
+ Stage: Stage-4
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ alias: orcsrc
+ Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: key (type: string), value (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col1 (type: string)
+ sort order: +
+ Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: string)
+ Execution mode: vectorized
+ Reduce Operator Tree:
+ Select Operator
+ expressions: VALUE._col0 (type: string), KEY.reducesinkkey0 (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ ListSink
+
+PREHOOK: query: FROM
+(SELECT orcsrc.* FROM orcsrc sort by key) x
+LEFT OUTER JOIN
+(SELECT orcsrc.* FROM orcsrc sort by value) Y
+ON (x.key = Y.key)
+select sum(hash(Y.key,Y.value))
+PREHOOK: type: QUERY
+PREHOOK: Input: default@orcsrc
+#### A masked pattern was here ####
+POSTHOOK: query: FROM
+(SELECT orcsrc.* FROM orcsrc sort by key) x
+LEFT OUTER JOIN
+(SELECT orcsrc.* FROM orcsrc sort by value) Y
+ON (x.key = Y.key)
+select sum(hash(Y.key,Y.value))
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@orcsrc
+#### A masked pattern was here ####
+103231310608
+PREHOOK: query: explain
+FROM
+(SELECT orcsrc.* FROM orcsrc sort by key) x
+RIGHT OUTER JOIN
+(SELECT orcsrc.* FROM orcsrc sort by value) Y
+ON (x.key = Y.key)
+select sum(hash(Y.key,Y.value))
+PREHOOK: type: QUERY
+POSTHOOK: query: explain
+FROM
+(SELECT orcsrc.* FROM orcsrc sort by key) x
+RIGHT OUTER JOIN
+(SELECT orcsrc.* FROM orcsrc sort by value) Y
+ON (x.key = Y.key)
+select sum(hash(Y.key,Y.value))
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-6 depends on stages: Stage-1, Stage-4 , consists of Stage-7, Stage-2
+ Stage-7 has a backup stage: Stage-2
+ Stage-5 depends on stages: Stage-7
+ Stage-3 depends on stages: Stage-2, Stage-5
+ Stage-2
+ Stage-4 is a root stage
+ Stage-0 depends on stages: Stage-3
+
+STAGE PLANS:
+ Stage: Stage-1
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ alias: orcsrc
+ Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: key (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ sort order: +
+ Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE
+ Execution mode: vectorized
+ Reduce Operator Tree:
+ Select Operator
+ expressions: KEY.reducesinkkey0 (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+
+ Stage: Stage-6
+ Conditional Operator
+
+ Stage: Stage-7
+ Map Reduce Local Work
+ Alias -> Map Local Tables:
+ $INTNAME
+ Fetch Operator
+ limit: -1
+ Alias -> Map Local Operator Tree:
+ $INTNAME
+ TableScan
+ HashTable Sink Operator
+ keys:
+ 0 _col0 (type: string)
+ 1 _col0 (type: string)
+
+ Stage: Stage-5
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ Map Join Operator
+ condition map:
+ Right Outer Join0 to 1
+ keys:
+ 0 _col0 (type: string)
+ 1 _col0 (type: string)
+ outputColumnNames: _col2, _col3
+ Group By Operator
+ aggregations: sum(hash(_col2,_col3))
+ mode: hash
+ outputColumnNames: _col0
+ File Output Operator
+ compressed: false
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+ Local Work:
+ Map Reduce Local Work
+
+ Stage: Stage-3
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: bigint)
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: sum(VALUE._col0)
+ mode: mergepartial
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ Stage: Stage-2
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE
+ TableScan
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col1 (type: string)
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Right Outer Join0 to 1
+ keys:
+ 0 _col0 (type: string)
+ 1 _col0 (type: string)
+ outputColumnNames: _col2, _col3
+ Statistics: Num rows: 550 Data size: 96800 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: sum(hash(_col2,_col3))
+ mode: hash
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+
+ Stage: Stage-4
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ alias: orcsrc
+ Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: key (type: string), value (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col1 (type: string)
+ sort order: +
+ Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: string)
+ Execution mode: vectorized
+ Reduce Operator Tree:
+ Select Operator
+ expressions: VALUE._col0 (type: string), KEY.reducesinkkey0 (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ ListSink
+
+PREHOOK: query: FROM
+(SELECT orcsrc.* FROM orcsrc sort by key) x
+RIGHT OUTER JOIN
+(SELECT orcsrc.* FROM orcsrc sort by value) Y
+ON (x.key = Y.key)
+select sum(hash(Y.key,Y.value))
+PREHOOK: type: QUERY
+PREHOOK: Input: default@orcsrc
+#### A masked pattern was here ####
+POSTHOOK: query: FROM
+(SELECT orcsrc.* FROM orcsrc sort by key) x
+RIGHT OUTER JOIN
+(SELECT orcsrc.* FROM orcsrc sort by value) Y
+ON (x.key = Y.key)
+select sum(hash(Y.key,Y.value))
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@orcsrc
+#### A masked pattern was here ####
+103231310608
+PREHOOK: query: explain
+FROM
+(SELECT orcsrc.* FROM orcsrc sort by key) x
+JOIN
+(SELECT orcsrc.* FROM orcsrc sort by value) Y
+ON (x.key = Y.key)
+JOIN
+(SELECT orcsrc.* FROM orcsrc sort by value) Z
+ON (x.key = Z.key)
+select sum(hash(Y.key,Y.value))
+PREHOOK: type: QUERY
+POSTHOOK: query: explain
+FROM
+(SELECT orcsrc.* FROM orcsrc sort by key) x
+JOIN
+(SELECT orcsrc.* FROM orcsrc sort by value) Y
+ON (x.key = Y.key)
+JOIN
+(SELECT orcsrc.* FROM orcsrc sort by value) Z
+ON (x.key = Z.key)
+select sum(hash(Y.key,Y.value))
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-9 depends on stages: Stage-1, Stage-4, Stage-5 , consists of Stage-10, Stage-11, Stage-12, Stage-2
+ Stage-10 has a backup stage: Stage-2
+ Stage-6 depends on stages: Stage-10
+ Stage-3 depends on stages: Stage-2, Stage-6, Stage-7, Stage-8
+ Stage-11 has a backup stage: Stage-2
+ Stage-7 depends on stages: Stage-11
+ Stage-12 has a backup stage: Stage-2
+ Stage-8 depends on stages: Stage-12
+ Stage-2
+ Stage-4 is a root stage
+ Stage-5 is a root stage
+ Stage-0 depends on stages: Stage-3
+
+STAGE PLANS:
+ Stage: Stage-1
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ alias: orcsrc
+ Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: key is not null (type: boolean)
+ Statistics: Num rows: 250 Data size: 44000 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: key (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 250 Data size: 44000 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ sort order: +
+ Statistics: Num rows: 250 Data size: 44000 Basic stats: COMPLETE Column stats: NONE
+ Execution mode: vectorized
+ Reduce Operator Tree:
+ Select Operator
+ expressions: KEY.reducesinkkey0 (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 250 Data size: 44000 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+
+ Stage: Stage-9
+ Conditional Operator
+
+ Stage: Stage-10
+ Map Reduce Local Work
+ Alias -> Map Local Tables:
+ $INTNAME1
+ Fetch Operator
+ limit: -1
+ $INTNAME2
+ Fetch Operator
+ limit: -1
+ Alias -> Map Local Operator Tree:
+ $INTNAME1
+ TableScan
+ HashTable Sink Operator
+ keys:
+ 0 _col0 (type: string)
+ 1 _col0 (type: string)
+ 2 _col0 (type: string)
+ $INTNAME2
+ TableScan
+ HashTable Sink Operator
+ keys:
+ 0 _col0 (type: string)
+ 1 _col0 (type: string)
+ 2 _col0 (type: string)
+
+ Stage: Stage-6
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ Map 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: _col2, _col3
+ Group By Operator
+ aggregations: sum(hash(_col2,_col3))
+ mode: hash
+ outputColumnNames: _col0
+ File Output Operator
+ compressed: false
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+ Local Work:
+ Map Reduce Local Work
+
+ Stage: Stage-3
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: bigint)
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: sum(VALUE._col0)
+ mode: mergepartial
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ Stage: Stage-11
+ Map Reduce Local Work
+ Alias -> Map Local Tables:
+ $INTNAME
+ Fetch Operator
+ limit: -1
+ $INTNAME2
+ Fetch Operator
+ limit: -1
+ Alias -> Map Local Operator Tree:
+ $INTNAME
+ TableScan
+ HashTable Sink Operator
+ keys:
+ 0 _col0 (type: string)
+ 1 _col0 (type: string)
+ 2 _col0 (type: string)
+ $INTNAME2
+ TableScan
+ HashTable Sink Operator
+ keys:
+ 0 _col0 (type: string)
+ 1 _col0 (type: string)
+ 2 _col0 (type: string)
+
+ Stage: Stage-7
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ Map 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: _col2, _col3
+ Group By Operator
+ aggregations: sum(hash(_col2,_col3))
+ mode: hash
+ outputColumnNames: _col0
+ File Output Operator
+ compressed: false
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+ Local Work:
+ Map Reduce Local Work
+
+ Stage: Stage-12
+ Map Reduce Local Work
+ Alias -> Map Local Tables:
+ $INTNAME
+ Fetch Operator
+ limit: -1
+ $INTNAME1
+ Fetch Operator
+ limit: -1
+ Alias -> Map Local Operator Tree:
+ $INTNAME
+ TableScan
+ HashTable Sink Operator
+ keys:
+ 0 _col0 (type: string)
+ 1 _col0 (type: string)
+ 2 _col0 (type: string)
+ $INTNAME1
+ TableScan
+ HashTable Sink Operator
+ keys:
+ 0 _col0 (type: string)
+ 1 _col0 (type: string)
+ 2 _col0 (type: string)
+
+ Stage: Stage-8
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ Map 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: _col2, _col3
+ Group By Operator
+ aggregations: sum(hash(_col2,_col3))
+ mode: hash
+ outputColumnNames: _col0
+ File Output Operator
+ compressed: false
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+ Local Work:
+ Map Reduce Local Work
+
+ Stage: Stage-2
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 250 Data size: 44000 Basic stats: COMPLETE Column stats: NONE
+ TableScan
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 250 Data size: 44000 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col1 (type: string)
+ TableScan
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 250 Data size: 44000 Basic stats: COMPLETE Column stats: NONE
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ Inner Join 0 to 2
+ keys:
+ 0 _col0 (type: string)
+ 1 _col0 (type: string)
+ 2 _col0 (type: string)
+ outputColumnNames: _col2, _col3
+ Statistics: Num rows: 550 Data size: 96800 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: sum(hash(_col2,_col3))
+ mode: hash
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+
+ Stage: Stage-4
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ alias: orcsrc
+ Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: key is not null (type: boolean)
+ Statistics: Num rows: 250 Data size: 44000 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: key (type: string), value (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 250 Data size: 44000 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col1 (type: string)
+ sort order: +
+ Statistics: Num rows: 250 Data size: 44000 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: string)
+ Execution mode: vectorized
+ Reduce Operator Tree:
+ Select Operator
+ expressions: VALUE._col0 (type: string), KEY.reducesinkkey0 (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 250 Data size: 44000 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+
+ Stage: Stage-5
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ alias: orcsrc
+ Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: key is not null (type: boolean)
+ Statistics: Num rows: 250 Data size: 44000 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: key (type: string), value (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 250 Data size: 44000 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col1 (type: string)
+ sort order: +
+ Statistics: Num rows: 250 Data size: 44000 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: string)
+ Execution mode: vectorized
+ Reduce Operator Tree:
+ Select Operator
+ expressions: VALUE._col0 (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 250 Data size: 44000 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ ListSink
+
+PREHOOK: query: FROM
+(SELECT orcsrc.* FROM orcsrc sort by key) x
+JOIN
+(SELECT orcsrc.* FROM orcsrc sort by value) Y
+ON (x.key = Y.key)
+JOIN
+(SELECT orcsrc.* FROM orcsrc sort by value) Z
+ON (x.key = Z.key)
+select sum(hash(Y.key,Y.value))
+PREHOOK: type: QUERY
+PREHOOK: Input: default@orcsrc
+#### A masked pattern was here ####
+POSTHOOK: query: FROM
+(SELECT orcsrc.* FROM orcsrc sort by key) x
+JOIN
+(SELECT orcsrc.* FROM orcsrc sort by value) Y
+ON (x.key = Y.key)
+JOIN
+(SELECT orcsrc.* FROM orcsrc sort by value) Z
+ON (x.key = Z.key)
+select sum(hash(Y.key,Y.value))
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@orcsrc
+#### A masked pattern was here ####
+348019368476
+PREHOOK: query: explain
+FROM
+(SELECT orcsrc.* FROM orcsrc sort by key) x
+JOIN
+(SELECT orcsrc.* FROM orcsrc sort by value) Y
+ON (x.key = Y.key)
+LEFT OUTER JOIN
+(SELECT orcsrc.* FROM orcsrc sort by value) Z
+ON (x.key = Z.key)
+select sum(hash(Y.key,Y.value))
+PREHOOK: type: QUERY
+POSTHOOK: query: explain
+FROM
+(SELECT orcsrc.* FROM orcsrc sort by key) x
+JOIN
+(SELECT orcsrc.* FROM orcsrc sort by value) Y
+ON (x.key = Y.key)
+LEFT OUTER JOIN
+(SELECT orcsrc.* FROM orcsrc sort by value) Z
+ON (x.key = Z.key)
+select sum(hash(Y.key,Y.value))
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-8 depends on stages: Stage-1, Stage-4, Stage-5 , consists of Stage-9, Stage-10, Stage-2
+ Stage-9 has a backup stage: Stage-2
+ Stage-6 depends on stages: Stage-9
+ Stage-3 depends on stages: Stage-2, Stage-6, Stage-7
+ Stage-10 has a backup stage: Stage-2
+ Stage-7 depends on stages: Stage-10
+ Stage-2
+ Stage-4 is a root stage
+ Stage-5 is a root stage
+ Stage-0 depends on stages: Stage-3
+
+STAGE PLANS:
+ Stage: Stage-1
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ alias: orcsrc
+ Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: key (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ sort order: +
+ Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE
+ Execution mode: vectorized
+ Reduce Operator Tree:
+ Select Operator
+ expressions: KEY.reducesinkkey0 (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+
+ Stage: Stage-8
+ Conditional Operator
+
+ Stage: Stage-9
+ Map Reduce Local Work
+ Alias -> Map Local Tables:
+ $INTNAME1
+ Fetch Operator
+ limit: -1
+ $INTNAME2
+ Fetch Operator
+ limit: -1
+ Alias -> Map Local Operator Tree:
+ $INTNAME1
+ TableScan
+ HashTable Sink Operator
+ keys:
+ 0 _col0 (type: string)
+ 1 _col0 (type: string)
+ 2 _col0 (type: string)
+ $INTNAME2
+ TableScan
+ HashTable Sink Operator
+ keys:
+ 0 _col0 (type: string)
+ 1 _col0 (type: string)
+ 2 _col0 (type: string)
+
+ Stage: Stage-6
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ Left Outer Join0 to 2
+ keys:
+ 0 _col0 (type: string)
+ 1 _col0 (type: string)
+ 2 _col0 (type: string)
+ outputColumnNames: _col2, _col3
+ Group By Operator
+ aggregations: sum(hash(_col2,_col3))
+ mode: hash
+ outputColumnNames: _col0
+ File Output Operator
+ compressed: false
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+ Local Work:
+ Map Reduce Local Work
+
+ Stage: Stage-3
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: bigint)
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: sum(VALUE._col0)
+ mode: mergepartial
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ Stage: Stage-10
+ Map Reduce Local Work
+ Alias -> Map Local Tables:
+ $INTNAME
+ Fetch Operator
+ limit: -1
+ $INTNAME2
+ Fetch Operator
+ limit: -1
+ Alias -> Map Local Operator Tree:
+ $INTNAME
+ TableScan
+ HashTable Sink Operator
+ keys:
+ 0 _col0 (type: string)
+ 1 _col0 (type: string)
+ 2 _col0 (type: string)
+ $INTNAME2
+ TableScan
+ HashTable Sink Operator
+ keys:
+ 0 _col0 (type: string)
+ 1 _col0 (type: string)
+ 2 _col0 (type: string)
+
+ Stage: Stage-7
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ Left Outer Join0 to 2
+ keys:
+ 0 _col0 (type: string)
+ 1 _col0 (type: string)
+ 2 _col0 (type: string)
+ outputColumnNames: _col2, _col3
+ Group By Operator
+ aggregations: sum(hash(_col2,_col3))
+ mode: hash
+ outputColumnNames: _col0
+ File Output Operator
+ compressed: false
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+ Local Work:
+ Map Reduce Local Work
+
+ Stage: Stage-2
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE
+ TableScan
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col1 (type: string)
+ TableScan
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ Left Outer Join0 to 2
+ keys:
+ 0 _col0 (type: string)
+ 1 _col0 (type: string)
+ 2 _col0 (type: string)
+ outputColumnNames: _col2, _col3
+ Statistics: Num rows: 1100 Data size: 193600 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: sum(hash(_col2,_col3))
+ mode: hash
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+
+ Stage: Stage-4
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ alias: orcsrc
+ Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: key (type: string), value (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col1 (type: string)
+ sort order: +
+ Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: string)
+ Execution mode: vectorized
+ Reduce Operator Tree:
+ Select Operator
+ expressions: VALUE._col0 (type: string), KEY.reducesinkkey0 (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+
+ Stage: Stage-5
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ alias: orcsrc
+ Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: key (type: string), value (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col1 (type: string)
+ sort order: +
+ Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: string)
+ Execution mode: vectorized
+ Reduce Operator Tree:
+ Select Operator
+ expressions: VALUE._col0 (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ ListSink
+
+PREHOOK: query: FROM
+(SELECT orcsrc.* FROM orcsrc sort by key) x
+JOIN
+(SELECT orcsrc.* FROM orcsrc sort by value) Y
+ON (x.key = Y.key)
+LEFT OUTER JOIN
+(SELECT orcsrc.* FROM orcsrc sort by value) Z
+ON (x.key = Z.key)
+select sum(hash(Y.key,Y.value))
+PREHOOK: type: QUERY
+PREHOOK: Input: default@orcsrc
+#### A masked pattern was here ####
+POSTHOOK: query: FROM
+(SELECT orcsrc.* FROM orcsrc sort by key) x
+JOIN
+(SELECT orcsrc.* FROM orcsrc sort by value) Y
+ON (x.key = Y.key)
+LEFT OUTER JOIN
+(SELECT orcsrc.* FROM orcsrc sort by value) Z
+ON (x.key = Z.key)
+select sum(hash(Y.key,Y.value))
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@orcsrc
+#### A masked pattern was here ####
+348019368476
+PREHOOK: query: explain
+FROM
+(SELECT orcsrc.* FROM orcsrc sort by key) x
+LEFT OUTER JOIN
+(SELECT orcsrc.* FROM orcsrc sort by value) Y
+ON (x.key = Y.key)
+LEFT OUTER JOIN
+(SELECT orcsrc.* FROM orcsrc sort by value) Z
+ON (x.key = Z.key)
+select sum(hash(Y.key,Y.value))
+PREHOOK: type: QUERY
+POSTHOOK: query: explain
+FROM
+(SELECT orcsrc.* FROM orcsrc sort by key) x
+LEFT OUTER JOIN
+(SELECT orcsrc.* FROM orcsrc sort by value) Y
+ON (x.key = Y.key)
+LEFT OUTER JOIN
+(SELECT orcsrc.* FROM orcsrc sort by value) Z
+ON (x.key = Z.key)
+select sum(hash(Y.key,Y.value))
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-7 depends on stages: Stage-1, Stage-4, Stage-5 , consists of Stage-8, Stage-2
+ Stage-8 has a backup stage: Stage-2
+ Stage-6 depends on stages: Stage-8
+ Stage-3 depends on stages: Stage-2, Stage-6
+ Stage-2
+ Stage-4 is a root stage
+ Stage-5 is a root stage
+ Stage-0 depends on stages: Stage-3
+
+STAGE PLANS:
+ Stage: Stage-1
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ alias: orcsrc
+ Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: key (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ sort order: +
+ Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE
+ Execution mode: vectorized
+ Reduce Operator Tree:
+ Select Operator
+ expressions: KEY.reducesinkkey0 (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+
+ Stage: Stage-7
+ Conditional Operator
+
+ Stage: Stage-8
+ Map Reduce Local Work
+ Alias -> Map Local Tables:
+ $INTNAME1
+ Fetch Operator
+ limit: -1
+ $INTNAME2
+ Fetch Operator
+ limit: -1
+ Alias -> Map Local Operator Tree:
+ $INTNAME1
+ TableScan
+ HashTable Sink Operator
+ keys:
+ 0 _col0 (type: string)
+ 1 _col0 (type: string)
+ 2 _col0 (type: string)
+ $INTNAME2
+ TableScan
+ HashTable Sink Operator
+ keys:
+ 0 _col0 (type: string)
+ 1 _col0 (type: string)
+ 2 _col0 (type: string)
+
+ Stage: Stage-6
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ Map Join Operator
+ condition map:
+ Left Outer Join0 to 1
+ Left Outer Join0 to 2
+ keys:
+ 0 _col0 (type: string)
+ 1 _col0 (type: string)
+ 2 _col0 (type: string)
+ outputColumnNames: _col2, _col3
+ Group By Operator
+ aggregations: sum(hash(_col2,_col3))
+ mode: hash
+ outputColumnNames: _col0
+ File Output Operator
+ compressed: false
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+ Local Work:
+ Map Reduce Local Work
+
+ Stage: Stage-3
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: bigint)
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: sum(VALUE._col0)
+ mode: mergepartial
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ Stage: Stage-2
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE
+ TableScan
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col1 (type: string)
+ TableScan
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Left Outer Join0 to 1
+ Left Outer Join0 to 2
+ keys:
+ 0 _col0 (type: string)
+ 1 _col0 (type: string)
+ 2 _col0 (type: string)
+ outputColumnNames: _col2, _col3
+ Statistics: Num rows: 1100 Data size: 193600 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: sum(hash(_col2,_col3))
+ mode: hash
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+
+ Stage: Stage-4
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ alias: orcsrc
+ Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: key (type: string), value (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col1 (type: string)
+ sort order: +
+ Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: string)
+ Execution mode: vectorized
+ Reduce Operator Tree:
+ Select Operator
+ expressions: VALUE._col0 (type: string), KEY.reducesinkkey0 (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+
+ Stage: Stage-5
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ alias: orcsrc
+ Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: key (type: string), value (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col1 (type: string)
+ sort order: +
+ Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: string)
+ Execution mode: vectorized
+ Reduce Operator Tree:
+ Select Operator
+ expressions: VALUE._col0 (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ ListSink
+
+PREHOOK: query: FROM
+(SELECT orcsrc.* FROM orcsrc sort by key) x
+LEFT OUTER JOIN
+(SELECT orcsrc.* FROM orcsrc sort by value) Y
+ON (x.key = Y.key)
+LEFT OUTER JOIN
+(SELECT orcsrc.* FROM orcsrc sort by value) Z
+ON (x.key = Z.key)
+select sum(hash(Y.key,Y.value))
+PREHOOK: type: QUERY
+PREHOOK: Input: default@orcsrc
+#### A masked pattern was here ####
+POSTHOOK: query: FROM
+(SELECT orcsrc.* FROM orcsrc sort by key) x
+LEFT OUTER JOIN
+(SELECT orcsrc.* FROM orcsrc sort by value) Y
+ON (x.key = Y.key)
+LEFT OUTER JOIN
+(SELECT orcsrc.* FROM orcsrc sort by value) Z
+ON (x.key = Z.key)
+select sum(hash(Y.key,Y.value))
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@orcsrc
+#### A masked pattern was here ####
+348019368476
+PREHOOK: query: explain
+FROM
+(SELECT orcsrc.* FROM orcsrc sort by key) x
+LEFT OUTER JOIN
+(SELECT orcsrc.* FROM orcsrc sort by value) Y
+ON (x.key = Y.key)
+RIGHT OUTER JOIN
+(SELECT orcsrc.* FROM orcsrc sort by value) Z
+ON (x.key = Z.key)
+select sum(hash(Y.key,Y.value))
+PREHOOK: type: QUERY
+POSTHOOK: query: explain
+FROM
+(SELECT orcsrc.* FROM orcsrc sort by key) x
+LEFT OUTER JOIN
+(SELECT orcsrc.* FROM orcsrc sort by value) Y
+ON (x.key = Y.key)
+RIGHT OUTER JOIN
+(SELECT orcsrc.* FROM orcsrc sort by value) Z
+ON (x.key = Z.key)
+select sum(hash(Y.key,Y.value))
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-7 depends on stages: Stage-1, Stage-4, Stage-5 , consists of Stage-8, Stage-2
+ Stage-8 has a backup stage: Stage-2
+ Stage-6 depends on stages: Stage-8
+ Stage-3 depends on stages: Stage-2, Stage-6
+ Stage-2
+ Stage-4 is a root stage
+ Stage-5 is a root stage
+ Stage-0 depends on stages: Stage-3
+
+STAGE PLANS:
+ Stage: Stage-1
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ alias: orcsrc
+ Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: key (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ sort order: +
+ Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE
+ Execution mode: vectorized
+ Reduce Operator Tree:
+ Select Operator
+ expressions: KEY.reducesinkkey0 (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+
+ Stage: Stage-7
+ Conditional Operator
+
+ Stage: Stage-8
+ Map Reduce Local Work
+ Alias -> Map Local Tables:
+ $INTNAME
+ Fetch Operator
+ limit: -1
+ $INTNAME1
+ Fetch Operator
+ limit: -1
+ Alias -> Map Local Operator Tree:
+ $INTNAME
+ TableScan
+ HashTable Sink Operator
+ keys:
+ 0 _col0 (type: string)
+ 1 _col0 (type: string)
+ 2 _col0 (type: string)
+ $INTNAME1
+ TableScan
+ HashTable Sink Operator
+ keys:
+ 0 _col0 (type: string)
+ 1 _col0 (type: string)
+ 2 _col0 (type: string)
+
+ Stage: Stage-6
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ Map Join Operator
+ condition map:
+ Left Outer Join0 to 1
+ Right Outer Join0 to 2
+ keys:
+ 0 _col0 (type: string)
+ 1 _col0 (type: string)
+ 2 _col0 (type: string)
+ outputColumnNames: _col2, _col3
+ Group By Operator
+ aggregations: sum(hash(_col2,_col3))
+ mode: hash
+ outputColumnNames: _col0
+ File Output Operator
+ compressed: false
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+ Local Work:
+ Map Reduce Local Work
+
+ Stage: Stage-3
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: bigint)
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: sum(VALUE._col0)
+ mode: mergepartial
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ Stage: Stage-2
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE
+ TableScan
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col1 (type: string)
+ TableScan
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Left Outer Join0 to 1
+ Right Outer Join0 to 2
+ keys:
+ 0 _col0 (type: string)
+ 1 _col0 (type: string)
+ 2 _col0 (type: string)
+ outputColumnNames: _col2, _col3
+ Statistics: Num rows: 1100 Data size: 193600 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: sum(hash(_col2,_col3))
+ mode: hash
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+
+ Stage: Stage-4
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ alias: orcsrc
+ Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: key (type: string), value (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col1 (type: string)
+ sort order: +
+ Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: string)
+ Execution mode: vectorized
+ Reduce Operator Tree:
+ Select Operator
+ expressions: VALUE._col0 (type: string), KEY.reducesinkkey0 (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+
+ Stage: Stage-5
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ alias: orcsrc
+ Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: key (type: string), value (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col1 (type: string)
+ sort order: +
+ Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: string)
+ Execution mode: vectorized
+ Reduce Operator Tree:
+ Select Operator
+ expressions: VALUE._col0 (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ ListSink
+
+PREHOOK: query: FROM
+(SELECT orcsrc.* FROM orcsrc sort by key) x
+LEFT OUTER JOIN
+(SELECT orcsrc.* FROM orcsrc sort by value) Y
+ON (x.key = Y.key)
+RIGHT OUTER JOIN
+(SELECT orcsrc.* FROM orcsrc sort by value) Z
+ON (x.key = Z.key)
+select sum(hash(Y.key,Y.value))
+PREHOOK: type: QUERY
+PREHOOK: Input: default@orcsrc
+#### A masked pattern was here ####
+POSTHOOK: query: FROM
+(SELECT orcsrc.* FROM orcsrc sort by key) x
+LEFT OUTER JOIN
+(SELECT orcsrc.* FROM orcsrc sort by value) Y
+ON (x.key = Y.key)
+RIGHT OUTER JOIN
+(SELECT orcsrc.* FROM orcsrc sort by value) Z
+ON (x.key = Z.key)
+select sum(hash(Y.key,Y.value))
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@orcsrc
+#### A masked pattern was here ####
+348019368476
+PREHOOK: query: explain
+FROM
+(SELECT orcsrc.* FROM orcsrc sort by key) x
+RIGHT OUTER JOIN
+(SELECT orcsrc.* FROM orcsrc sort by value) Y
+ON (x.key = Y.key)
+RIGHT OUTER JOIN
+(SELECT orcsrc.* FROM orcsrc sort by value) Z
+ON (x.key = Z.key)
+select sum(hash(Y.key,Y.value))
+PREHOOK: type: QUERY
+POSTHOOK: query: explain
+FROM
+(SELECT orcsrc.* FROM orcsrc sort by key) x
+RIGHT OUTER JOIN
+(SELECT orcsrc.* FROM orcsrc sort by value) Y
+ON (x.key = Y.key)
+RIGHT OUTER JOIN
+(SELECT orcsrc.* FROM orcsrc sort by value) Z
+ON (x.key = Z.key)
+select sum(hash(Y.key,Y.value))
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-7 depends on stages: Stage-1, Stage-4, Stage-5 , consists of Stage-8, Stage-2
+ Stage-8 has a backup stage: Stage-2
+ Stage-6 depends on stages: Stage-8
+ Stage-3 depends on stages: Stage-2, Stage-6
+ Stage-2
+ Stage-4 is a root stage
+ Stage-5 is a root stage
+ Stage-0 depends on stages: Stage-3
+
+STAGE PLANS:
+ Stage: Stage-1
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ alias: orcsrc
+ Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: key (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ sort order: +
+ Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE
+ Execution mode: vectorized
+ Reduce Operator Tree:
+ Select Operator
+ expressions: KEY.reducesinkkey0 (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+
+ Stage: Stage-7
+ Conditional Operator
+
+ Stage: Stage-8
+ Map Reduce Local Work
+ Alias -> Map Local Tables:
+ $INTNAME
+ Fetch Operator
+ limit: -1
+ $INTNAME1
+ Fetch Operator
+ limit: -1
+ Alias -> Map Local Operator Tree:
+ $INTNAME
+ TableScan
+ HashTable Sink Operator
+ keys:
+ 0 _col0 (type: string)
+ 1 _col0 (type: string)
+ 2 _col0 (type: string)
+ $INTNAME1
+ TableScan
+ HashTable Sink Operator
+ keys:
+ 0 _col0 (type: string)
+ 1 _col0 (type: string)
+ 2 _col0 (type: string)
+
+ Stage: Stage-6
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ Map Join Operator
+ condition map:
+ Right Outer Join0 to 1
+ Right Outer Join0 to 2
+ keys:
+ 0 _col0 (type: string)
+ 1 _col0 (type: string)
+ 2 _col0 (type: string)
+ outputColumnNames: _col2, _col3
+ Group By Operator
+ aggregations: sum(hash(_col2,_col3))
+ mode: hash
+ outputColumnNames: _col0
+ File Output Operator
+ compressed: false
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+ Local Work:
+ Map Reduce Local Work
+
+ Stage: Stage-3
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: bigint)
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: sum(VALUE._col0)
+ mode: mergepartial
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ Stage: Stage-2
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE
+ TableScan
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col1 (type: string)
+ TableScan
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Right Outer Join0 to 1
+ Right Outer Join0 to 2
+ keys:
+ 0 _col0 (type: string)
+ 1 _col0 (type: string)
+ 2 _col0 (type: string)
+ outputColumnNames: _col2, _col3
+ Statistics: Num rows: 1100 Data size: 193600 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: sum(hash(_col2,_col3))
+ mode: hash
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+
+ Stage: Stage-4
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ alias: orcsrc
+ Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: key (type: string), value (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col1 (type: string)
+ sort order: +
+ Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: string)
+ Execution mode: vectorized
+ Reduce Operator Tree:
+ Select Operator
+ expressions: VALUE._col0 (type: string), KEY.reducesinkkey0 (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+
+ Stage: Stage-5
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ alias: orcsrc
+ Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: key (type: string), value (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col1 (type: string)
+ sort order: +
+ Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: string)
+ Execution mode: vectorized
+ Reduce Operator Tree:
+ Select Operator
+ expressions: VALUE._col0 (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ ListSink
+
+PREHOOK: query: FROM
+(SELECT orcsrc.* FROM orcsrc sort by key) x
+RIGHT OUTER JOIN
+(SELECT orcsrc.* FROM orcsrc sort by value) Y
+ON (x.key = Y.key)
+RIGHT OUTER JOIN
+(SELECT orcsrc.* FROM orcsrc sort by value) Z
+ON (x.key = Z.key)
+select sum(hash(Y.key,Y.value))
+PREHOOK: type: QUERY
+PREHOOK: Input: default@orcsrc
+#### A masked pattern was here ####
+POSTHOOK: query: FROM
+(SELECT orcsrc.* FROM orcsrc sort by key) x
+RIGHT OUTER JOIN
+(SELECT orcsrc.* FROM orcsrc sort by value) Y
+ON (x.key = Y.key)
+RIGHT OUTER JOIN
+(SELECT orcsrc.* FROM orcsrc sort by value) Z
+ON (x.key = Z.key)
+select sum(hash(Y.key,Y.value))
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@orcsrc
+#### A masked pattern was here ####
+348019368476