You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@hive.apache.org by ha...@apache.org on 2013/07/18 11:16:53 UTC
svn commit: r1504395 [5/15] - in /hive/trunk:
common/src/java/org/apache/hadoop/hive/conf/ conf/ ql/if/
ql/src/gen/thrift/gen-javabean/org/apache/hadoop/hive/ql/plan/api/
ql/src/java/org/apache/hadoop/hive/ql/exec/
ql/src/java/org/apache/hadoop/hive/ql...
Added: hive/trunk/ql/src/test/results/clientpositive/correlationoptimizer1.q.out
URL: http://svn.apache.org/viewvc/hive/trunk/ql/src/test/results/clientpositive/correlationoptimizer1.q.out?rev=1504395&view=auto
==============================================================================
--- hive/trunk/ql/src/test/results/clientpositive/correlationoptimizer1.q.out (added)
+++ hive/trunk/ql/src/test/results/clientpositive/correlationoptimizer1.q.out Thu Jul 18 09:16:52 2013
@@ -0,0 +1,3710 @@
+PREHOOK: query: -- This query has a GroupByOperator folling JoinOperator and they share the same keys.
+-- When Correlation Optimizer is turned off, three MR jobs will be generated.
+-- When Correlation Optimizer is turned on, two MR jobs will be generated
+-- and JoinOperator (on the column of key) and GroupByOperator (also on the column
+-- of key) will be executed in the first MR job.
+EXPLAIN
+SELECT SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt))
+FROM (SELECT x.key AS key, count(1) AS cnt
+ FROM src1 x JOIN src y ON (x.key = y.key)
+ GROUP BY x.key) tmp
+PREHOOK: type: QUERY
+POSTHOOK: query: -- This query has a GroupByOperator folling JoinOperator and they share the same keys.
+-- When Correlation Optimizer is turned off, three MR jobs will be generated.
+-- When Correlation Optimizer is turned on, two MR jobs will be generated
+-- and JoinOperator (on the column of key) and GroupByOperator (also on the column
+-- of key) will be executed in the first MR job.
+EXPLAIN
+SELECT SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt))
+FROM (SELECT x.key AS key, count(1) AS cnt
+ FROM src1 x JOIN src y ON (x.key = y.key)
+ GROUP BY x.key) tmp
+POSTHOOK: type: QUERY
+ABSTRACT SYNTAX TREE:
+ (TOK_QUERY (TOK_FROM (TOK_SUBQUERY (TOK_QUERY (TOK_FROM (TOK_JOIN (TOK_TABREF (TOK_TABNAME src1) x) (TOK_TABREF (TOK_TABNAME src) y) (= (. (TOK_TABLE_OR_COL x) key) (. (TOK_TABLE_OR_COL y) key)))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (. (TOK_TABLE_OR_COL x) key) key) (TOK_SELEXPR (TOK_FUNCTION count 1) cnt)) (TOK_GROUPBY (. (TOK_TABLE_OR_COL x) key)))) tmp)) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_FUNCTION SUM (TOK_FUNCTION HASH (. (TOK_TABLE_OR_COL tmp) key)))) (TOK_SELEXPR (TOK_FUNCTION SUM (TOK_FUNCTION HASH (. (TOK_TABLE_OR_COL tmp) cnt)))))))
+
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-2 depends on stages: Stage-1
+ Stage-3 depends on stages: Stage-2
+ Stage-0 is a root stage
+
+STAGE PLANS:
+ Stage: Stage-1
+ Map Reduce
+ Alias -> Map Operator Tree:
+ tmp:x
+ TableScan
+ alias: x
+ Reduce Output Operator
+ key expressions:
+ expr: key
+ type: string
+ sort order: +
+ Map-reduce partition columns:
+ expr: key
+ type: string
+ tag: 0
+ value expressions:
+ expr: key
+ type: string
+ tmp:y
+ TableScan
+ alias: y
+ Reduce Output Operator
+ key expressions:
+ expr: key
+ type: string
+ sort order: +
+ Map-reduce partition columns:
+ expr: key
+ type: string
+ tag: 1
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0 {VALUE._col0}
+ 1
+ handleSkewJoin: false
+ outputColumnNames: _col0
+ Select Operator
+ expressions:
+ expr: _col0
+ type: string
+ outputColumnNames: _col0
+ Group By Operator
+ aggregations:
+ expr: count(1)
+ bucketGroup: false
+ keys:
+ expr: _col0
+ type: string
+ mode: hash
+ outputColumnNames: _col0, _col1
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+
+ Stage: Stage-2
+ Map Reduce
+ Alias -> Map Operator Tree:
+#### A masked pattern was here ####
+ Reduce Output Operator
+ key expressions:
+ expr: _col0
+ type: string
+ sort order: +
+ Map-reduce partition columns:
+ expr: _col0
+ type: string
+ tag: -1
+ value expressions:
+ expr: _col1
+ type: bigint
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations:
+ expr: count(VALUE._col0)
+ bucketGroup: false
+ keys:
+ expr: KEY._col0
+ type: string
+ mode: mergepartial
+ outputColumnNames: _col0, _col1
+ Select Operator
+ expressions:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: bigint
+ outputColumnNames: _col0, _col1
+ Group By Operator
+ aggregations:
+ expr: sum(hash(_col0))
+ expr: sum(hash(_col1))
+ bucketGroup: false
+ mode: hash
+ outputColumnNames: _col0, _col1
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+
+ Stage: Stage-3
+ Map Reduce
+ Alias -> Map Operator Tree:
+#### A masked pattern was here ####
+ Reduce Output Operator
+ sort order:
+ tag: -1
+ value expressions:
+ expr: _col0
+ type: bigint
+ expr: _col1
+ type: bigint
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations:
+ expr: sum(VALUE._col0)
+ expr: sum(VALUE._col1)
+ bucketGroup: false
+ mode: mergepartial
+ outputColumnNames: _col0, _col1
+ Select Operator
+ expressions:
+ expr: _col0
+ type: bigint
+ expr: _col1
+ type: bigint
+ outputColumnNames: _col0, _col1
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+
+
+PREHOOK: query: SELECT SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt))
+FROM (SELECT x.key AS key, count(1) AS cnt
+ FROM src1 x JOIN src y ON (x.key = y.key)
+ GROUP BY x.key) tmp
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+PREHOOK: Input: default@src1
+#### A masked pattern was here ####
+POSTHOOK: query: SELECT SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt))
+FROM (SELECT x.key AS key, count(1) AS cnt
+ FROM src1 x JOIN src y ON (x.key = y.key)
+ GROUP BY x.key) tmp
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+POSTHOOK: Input: default@src1
+#### A masked pattern was here ####
+652447 37
+PREHOOK: query: EXPLAIN
+SELECT SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt))
+FROM (SELECT x.key AS key, count(1) AS cnt
+ FROM src1 x JOIN src y ON (x.key = y.key)
+ GROUP BY x.key) tmp
+PREHOOK: type: QUERY
+POSTHOOK: query: EXPLAIN
+SELECT SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt))
+FROM (SELECT x.key AS key, count(1) AS cnt
+ FROM src1 x JOIN src y ON (x.key = y.key)
+ GROUP BY x.key) tmp
+POSTHOOK: type: QUERY
+ABSTRACT SYNTAX TREE:
+ (TOK_QUERY (TOK_FROM (TOK_SUBQUERY (TOK_QUERY (TOK_FROM (TOK_JOIN (TOK_TABREF (TOK_TABNAME src1) x) (TOK_TABREF (TOK_TABNAME src) y) (= (. (TOK_TABLE_OR_COL x) key) (. (TOK_TABLE_OR_COL y) key)))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (. (TOK_TABLE_OR_COL x) key) key) (TOK_SELEXPR (TOK_FUNCTION count 1) cnt)) (TOK_GROUPBY (. (TOK_TABLE_OR_COL x) key)))) tmp)) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_FUNCTION SUM (TOK_FUNCTION HASH (. (TOK_TABLE_OR_COL tmp) key)))) (TOK_SELEXPR (TOK_FUNCTION SUM (TOK_FUNCTION HASH (. (TOK_TABLE_OR_COL tmp) cnt)))))))
+
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-2 depends on stages: Stage-1
+ Stage-0 is a root stage
+
+STAGE PLANS:
+ Stage: Stage-1
+ Map Reduce
+ Alias -> Map Operator Tree:
+ tmp:x
+ TableScan
+ alias: x
+ Reduce Output Operator
+ key expressions:
+ expr: key
+ type: string
+ sort order: +
+ Map-reduce partition columns:
+ expr: key
+ type: string
+ tag: 0
+ value expressions:
+ expr: key
+ type: string
+ tmp:y
+ TableScan
+ alias: y
+ Reduce Output Operator
+ key expressions:
+ expr: key
+ type: string
+ sort order: +
+ Map-reduce partition columns:
+ expr: key
+ type: string
+ tag: 1
+ Reduce Operator Tree:
+ Demux Operator
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0 {VALUE._col0}
+ 1
+ handleSkewJoin: false
+ outputColumnNames: _col0
+ Select Operator
+ expressions:
+ expr: _col0
+ type: string
+ outputColumnNames: _col0
+ Mux Operator
+ Group By Operator
+ aggregations:
+ expr: count(1)
+ bucketGroup: false
+ keys:
+ expr: _col0
+ type: string
+ mode: complete
+ outputColumnNames: _col0, _col1
+ Select Operator
+ expressions:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: bigint
+ outputColumnNames: _col0, _col1
+ Group By Operator
+ aggregations:
+ expr: sum(hash(_col0))
+ expr: sum(hash(_col1))
+ bucketGroup: false
+ mode: hash
+ outputColumnNames: _col0, _col1
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+
+ Stage: Stage-2
+ Map Reduce
+ Alias -> Map Operator Tree:
+#### A masked pattern was here ####
+ Reduce Output Operator
+ sort order:
+ tag: -1
+ value expressions:
+ expr: _col0
+ type: bigint
+ expr: _col1
+ type: bigint
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations:
+ expr: sum(VALUE._col0)
+ expr: sum(VALUE._col1)
+ bucketGroup: false
+ mode: mergepartial
+ outputColumnNames: _col0, _col1
+ Select Operator
+ expressions:
+ expr: _col0
+ type: bigint
+ expr: _col1
+ type: bigint
+ outputColumnNames: _col0, _col1
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+
+
+PREHOOK: query: SELECT SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt))
+FROM (SELECT x.key AS key, count(1) AS cnt
+ FROM src1 x JOIN src y ON (x.key = y.key)
+ GROUP BY x.key) tmp
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+PREHOOK: Input: default@src1
+#### A masked pattern was here ####
+POSTHOOK: query: SELECT SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt))
+FROM (SELECT x.key AS key, count(1) AS cnt
+ FROM src1 x JOIN src y ON (x.key = y.key)
+ GROUP BY x.key) tmp
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+POSTHOOK: Input: default@src1
+#### A masked pattern was here ####
+652447 37
+PREHOOK: query: -- Enable hive.auto.convert.join.
+-- Correlation Optimizer will detect that the join will be converted to a Map-join,
+-- so it will not try to optimize this query.
+EXPLAIN
+SELECT SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt))
+FROM (SELECT x.key AS key, count(1) AS cnt
+ FROM src1 x JOIN src y ON (x.key = y.key)
+ GROUP BY x.key) tmp
+PREHOOK: type: QUERY
+POSTHOOK: query: -- Enable hive.auto.convert.join.
+-- Correlation Optimizer will detect that the join will be converted to a Map-join,
+-- so it will not try to optimize this query.
+EXPLAIN
+SELECT SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt))
+FROM (SELECT x.key AS key, count(1) AS cnt
+ FROM src1 x JOIN src y ON (x.key = y.key)
+ GROUP BY x.key) tmp
+POSTHOOK: type: QUERY
+ABSTRACT SYNTAX TREE:
+ (TOK_QUERY (TOK_FROM (TOK_SUBQUERY (TOK_QUERY (TOK_FROM (TOK_JOIN (TOK_TABREF (TOK_TABNAME src1) x) (TOK_TABREF (TOK_TABNAME src) y) (= (. (TOK_TABLE_OR_COL x) key) (. (TOK_TABLE_OR_COL y) key)))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (. (TOK_TABLE_OR_COL x) key) key) (TOK_SELEXPR (TOK_FUNCTION count 1) cnt)) (TOK_GROUPBY (. (TOK_TABLE_OR_COL x) key)))) tmp)) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_FUNCTION SUM (TOK_FUNCTION HASH (. (TOK_TABLE_OR_COL tmp) key)))) (TOK_SELEXPR (TOK_FUNCTION SUM (TOK_FUNCTION HASH (. (TOK_TABLE_OR_COL tmp) cnt)))))))
+
+STAGE DEPENDENCIES:
+ Stage-6 is a root stage
+ Stage-5 depends on stages: Stage-6
+ Stage-2 depends on stages: Stage-5
+ Stage-3 depends on stages: Stage-2
+ Stage-0 is a root stage
+
+STAGE PLANS:
+ Stage: Stage-6
+ Map Reduce Local Work
+ Alias -> Map Local Tables:
+ tmp:x
+ Fetch Operator
+ limit: -1
+ Alias -> Map Local Operator Tree:
+ tmp:x
+ TableScan
+ alias: x
+ HashTable Sink Operator
+ condition expressions:
+ 0 {key}
+ 1
+ handleSkewJoin: false
+ keys:
+ 0 [Column[key]]
+ 1 [Column[key]]
+ Position of Big Table: 1
+
+ Stage: Stage-5
+ Map Reduce
+ Alias -> Map Operator Tree:
+ tmp:y
+ TableScan
+ alias: y
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0 {key}
+ 1
+ handleSkewJoin: false
+ keys:
+ 0 [Column[key]]
+ 1 [Column[key]]
+ outputColumnNames: _col0
+ Position of Big Table: 1
+ Select Operator
+ expressions:
+ expr: _col0
+ type: string
+ outputColumnNames: _col0
+ Group By Operator
+ aggregations:
+ expr: count(1)
+ bucketGroup: false
+ keys:
+ expr: _col0
+ type: string
+ mode: hash
+ outputColumnNames: _col0, _col1
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ Local Work:
+ Map Reduce Local Work
+
+ Stage: Stage-2
+ Map Reduce
+ Alias -> Map Operator Tree:
+#### A masked pattern was here ####
+ Reduce Output Operator
+ key expressions:
+ expr: _col0
+ type: string
+ sort order: +
+ Map-reduce partition columns:
+ expr: _col0
+ type: string
+ tag: -1
+ value expressions:
+ expr: _col1
+ type: bigint
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations:
+ expr: count(VALUE._col0)
+ bucketGroup: false
+ keys:
+ expr: KEY._col0
+ type: string
+ mode: mergepartial
+ outputColumnNames: _col0, _col1
+ Select Operator
+ expressions:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: bigint
+ outputColumnNames: _col0, _col1
+ Group By Operator
+ aggregations:
+ expr: sum(hash(_col0))
+ expr: sum(hash(_col1))
+ bucketGroup: false
+ mode: hash
+ outputColumnNames: _col0, _col1
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+
+ Stage: Stage-3
+ Map Reduce
+ Alias -> Map Operator Tree:
+#### A masked pattern was here ####
+ Reduce Output Operator
+ sort order:
+ tag: -1
+ value expressions:
+ expr: _col0
+ type: bigint
+ expr: _col1
+ type: bigint
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations:
+ expr: sum(VALUE._col0)
+ expr: sum(VALUE._col1)
+ bucketGroup: false
+ mode: mergepartial
+ outputColumnNames: _col0, _col1
+ Select Operator
+ expressions:
+ expr: _col0
+ type: bigint
+ expr: _col1
+ type: bigint
+ outputColumnNames: _col0, _col1
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+
+
+PREHOOK: query: SELECT SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt))
+FROM (SELECT x.key AS key, count(1) AS cnt
+ FROM src1 x JOIN src y ON (x.key = y.key)
+ GROUP BY x.key) tmp
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+PREHOOK: Input: default@src1
+#### A masked pattern was here ####
+POSTHOOK: query: SELECT SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt))
+FROM (SELECT x.key AS key, count(1) AS cnt
+ FROM src1 x JOIN src y ON (x.key = y.key)
+ GROUP BY x.key) tmp
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+POSTHOOK: Input: default@src1
+#### A masked pattern was here ####
+652447 37
+PREHOOK: query: -- Enable hive.auto.convert.join.
+-- Correlation Optimizer will detect that the join will be converted to a Map-join,
+-- so it will not try to optimize this query.
+-- We should generate 1 MR job for subquery tmp.
+EXPLAIN
+SELECT SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt))
+FROM (SELECT x.key AS key, count(1) AS cnt
+ FROM src1 x JOIN src y ON (x.key = y.key)
+ GROUP BY x.key) tmp
+PREHOOK: type: QUERY
+POSTHOOK: query: -- Enable hive.auto.convert.join.
+-- Correlation Optimizer will detect that the join will be converted to a Map-join,
+-- so it will not try to optimize this query.
+-- We should generate 1 MR job for subquery tmp.
+EXPLAIN
+SELECT SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt))
+FROM (SELECT x.key AS key, count(1) AS cnt
+ FROM src1 x JOIN src y ON (x.key = y.key)
+ GROUP BY x.key) tmp
+POSTHOOK: type: QUERY
+ABSTRACT SYNTAX TREE:
+ (TOK_QUERY (TOK_FROM (TOK_SUBQUERY (TOK_QUERY (TOK_FROM (TOK_JOIN (TOK_TABREF (TOK_TABNAME src1) x) (TOK_TABREF (TOK_TABNAME src) y) (= (. (TOK_TABLE_OR_COL x) key) (. (TOK_TABLE_OR_COL y) key)))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (. (TOK_TABLE_OR_COL x) key) key) (TOK_SELEXPR (TOK_FUNCTION count 1) cnt)) (TOK_GROUPBY (. (TOK_TABLE_OR_COL x) key)))) tmp)) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_FUNCTION SUM (TOK_FUNCTION HASH (. (TOK_TABLE_OR_COL tmp) key)))) (TOK_SELEXPR (TOK_FUNCTION SUM (TOK_FUNCTION HASH (. (TOK_TABLE_OR_COL tmp) cnt)))))))
+
+STAGE DEPENDENCIES:
+ Stage-6 is a root stage
+ Stage-5 depends on stages: Stage-6
+ Stage-3 depends on stages: Stage-5
+ Stage-0 is a root stage
+
+STAGE PLANS:
+ Stage: Stage-6
+ Map Reduce Local Work
+ Alias -> Map Local Tables:
+ tmp:x
+ Fetch Operator
+ limit: -1
+ Alias -> Map Local Operator Tree:
+ tmp:x
+ TableScan
+ alias: x
+ HashTable Sink Operator
+ condition expressions:
+ 0 {key}
+ 1
+ handleSkewJoin: false
+ keys:
+ 0 [Column[key]]
+ 1 [Column[key]]
+ Position of Big Table: 1
+
+ Stage: Stage-5
+ Map Reduce
+ Alias -> Map Operator Tree:
+ tmp:y
+ TableScan
+ alias: y
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0 {key}
+ 1
+ handleSkewJoin: false
+ keys:
+ 0 [Column[key]]
+ 1 [Column[key]]
+ outputColumnNames: _col0
+ Position of Big Table: 1
+ Select Operator
+ expressions:
+ expr: _col0
+ type: string
+ outputColumnNames: _col0
+ Group By Operator
+ aggregations:
+ expr: count(1)
+ bucketGroup: false
+ keys:
+ expr: _col0
+ type: string
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Reduce Output Operator
+ key expressions:
+ expr: _col0
+ type: string
+ sort order: +
+ Map-reduce partition columns:
+ expr: _col0
+ type: string
+ tag: -1
+ value expressions:
+ expr: _col1
+ type: bigint
+ Local Work:
+ Map Reduce Local Work
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations:
+ expr: count(VALUE._col0)
+ bucketGroup: false
+ keys:
+ expr: KEY._col0
+ type: string
+ mode: mergepartial
+ outputColumnNames: _col0, _col1
+ Select Operator
+ expressions:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: bigint
+ outputColumnNames: _col0, _col1
+ Group By Operator
+ aggregations:
+ expr: sum(hash(_col0))
+ expr: sum(hash(_col1))
+ bucketGroup: false
+ mode: hash
+ outputColumnNames: _col0, _col1
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+
+ Stage: Stage-3
+ Map Reduce
+ Alias -> Map Operator Tree:
+#### A masked pattern was here ####
+ Reduce Output Operator
+ sort order:
+ tag: -1
+ value expressions:
+ expr: _col0
+ type: bigint
+ expr: _col1
+ type: bigint
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations:
+ expr: sum(VALUE._col0)
+ expr: sum(VALUE._col1)
+ bucketGroup: false
+ mode: mergepartial
+ outputColumnNames: _col0, _col1
+ Select Operator
+ expressions:
+ expr: _col0
+ type: bigint
+ expr: _col1
+ type: bigint
+ outputColumnNames: _col0, _col1
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+
+
+PREHOOK: query: SELECT SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt))
+FROM (SELECT x.key AS key, count(1) AS cnt
+ FROM src1 x JOIN src y ON (x.key = y.key)
+ GROUP BY x.key) tmp
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+PREHOOK: Input: default@src1
+#### A masked pattern was here ####
+POSTHOOK: query: SELECT SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt))
+FROM (SELECT x.key AS key, count(1) AS cnt
+ FROM src1 x JOIN src y ON (x.key = y.key)
+ GROUP BY x.key) tmp
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+POSTHOOK: Input: default@src1
+#### A masked pattern was here ####
+652447 37
+PREHOOK: query: -- If the key of a GroupByOperator is the left table's key in
+-- a Left Semi Join, these two operators will be executed in
+-- the same MR job when Correlation Optimizer is enabled.
+EXPLAIN
+SELECT SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt))
+FROM (SELECT x.key AS key, count(1) AS cnt
+ FROM src1 x LEFT SEMI JOIN src y ON (x.key = y.key)
+ GROUP BY x.key) tmp
+PREHOOK: type: QUERY
+POSTHOOK: query: -- If the key of a GroupByOperator is the left table's key in
+-- a Left Semi Join, these two operators will be executed in
+-- the same MR job when Correlation Optimizer is enabled.
+EXPLAIN
+SELECT SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt))
+FROM (SELECT x.key AS key, count(1) AS cnt
+ FROM src1 x LEFT SEMI JOIN src y ON (x.key = y.key)
+ GROUP BY x.key) tmp
+POSTHOOK: type: QUERY
+ABSTRACT SYNTAX TREE:
+ (TOK_QUERY (TOK_FROM (TOK_SUBQUERY (TOK_QUERY (TOK_FROM (TOK_LEFTSEMIJOIN (TOK_TABREF (TOK_TABNAME src1) x) (TOK_TABREF (TOK_TABNAME src) y) (= (. (TOK_TABLE_OR_COL x) key) (. (TOK_TABLE_OR_COL y) key)))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (. (TOK_TABLE_OR_COL x) key) key) (TOK_SELEXPR (TOK_FUNCTION count 1) cnt)) (TOK_GROUPBY (. (TOK_TABLE_OR_COL x) key)))) tmp)) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_FUNCTION SUM (TOK_FUNCTION HASH (. (TOK_TABLE_OR_COL tmp) key)))) (TOK_SELEXPR (TOK_FUNCTION SUM (TOK_FUNCTION HASH (. (TOK_TABLE_OR_COL tmp) cnt)))))))
+
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-2 depends on stages: Stage-1
+ Stage-3 depends on stages: Stage-2
+ Stage-0 is a root stage
+
+STAGE PLANS:
+ Stage: Stage-1
+ Map Reduce
+ Alias -> Map Operator Tree:
+ tmp:x
+ TableScan
+ alias: x
+ Reduce Output Operator
+ key expressions:
+ expr: key
+ type: string
+ sort order: +
+ Map-reduce partition columns:
+ expr: key
+ type: string
+ tag: 0
+ value expressions:
+ expr: key
+ type: string
+ tmp:y
+ TableScan
+ alias: y
+ Select Operator
+ expressions:
+ expr: key
+ type: string
+ outputColumnNames: key
+ Group By Operator
+ bucketGroup: false
+ keys:
+ expr: key
+ type: string
+ mode: hash
+ outputColumnNames: _col0
+ Reduce Output Operator
+ key expressions:
+ expr: _col0
+ type: string
+ sort order: +
+ Map-reduce partition columns:
+ expr: _col0
+ type: string
+ tag: 1
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Left Semi Join 0 to 1
+ condition expressions:
+ 0 {VALUE._col0}
+ 1
+ handleSkewJoin: false
+ outputColumnNames: _col0
+ Select Operator
+ expressions:
+ expr: _col0
+ type: string
+ outputColumnNames: _col0
+ Group By Operator
+ aggregations:
+ expr: count(1)
+ bucketGroup: false
+ keys:
+ expr: _col0
+ type: string
+ mode: hash
+ outputColumnNames: _col0, _col1
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+
+ Stage: Stage-2
+ Map Reduce
+ Alias -> Map Operator Tree:
+#### A masked pattern was here ####
+ Reduce Output Operator
+ key expressions:
+ expr: _col0
+ type: string
+ sort order: +
+ Map-reduce partition columns:
+ expr: _col0
+ type: string
+ tag: -1
+ value expressions:
+ expr: _col1
+ type: bigint
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations:
+ expr: count(VALUE._col0)
+ bucketGroup: false
+ keys:
+ expr: KEY._col0
+ type: string
+ mode: mergepartial
+ outputColumnNames: _col0, _col1
+ Select Operator
+ expressions:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: bigint
+ outputColumnNames: _col0, _col1
+ Group By Operator
+ aggregations:
+ expr: sum(hash(_col0))
+ expr: sum(hash(_col1))
+ bucketGroup: false
+ mode: hash
+ outputColumnNames: _col0, _col1
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+
+ Stage: Stage-3
+ Map Reduce
+ Alias -> Map Operator Tree:
+#### A masked pattern was here ####
+ Reduce Output Operator
+ sort order:
+ tag: -1
+ value expressions:
+ expr: _col0
+ type: bigint
+ expr: _col1
+ type: bigint
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations:
+ expr: sum(VALUE._col0)
+ expr: sum(VALUE._col1)
+ bucketGroup: false
+ mode: mergepartial
+ outputColumnNames: _col0, _col1
+ Select Operator
+ expressions:
+ expr: _col0
+ type: bigint
+ expr: _col1
+ type: bigint
+ outputColumnNames: _col0, _col1
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+
+
+PREHOOK: query: SELECT SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt))
+FROM (SELECT x.key AS key, count(1) AS cnt
+ FROM src1 x LEFT SEMI JOIN src y ON (x.key = y.key)
+ GROUP BY x.key) tmp
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+PREHOOK: Input: default@src1
+#### A masked pattern was here ####
+POSTHOOK: query: SELECT SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt))
+FROM (SELECT x.key AS key, count(1) AS cnt
+ FROM src1 x LEFT SEMI JOIN src y ON (x.key = y.key)
+ GROUP BY x.key) tmp
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+POSTHOOK: Input: default@src1
+#### A masked pattern was here ####
+652447 15
+PREHOOK: query: EXPLAIN
+SELECT SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt))
+FROM (SELECT x.key AS key, count(1) AS cnt
+ FROM src1 x LEFT SEMI JOIN src y ON (x.key = y.key)
+ GROUP BY x.key) tmp
+PREHOOK: type: QUERY
+POSTHOOK: query: EXPLAIN
+SELECT SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt))
+FROM (SELECT x.key AS key, count(1) AS cnt
+ FROM src1 x LEFT SEMI JOIN src y ON (x.key = y.key)
+ GROUP BY x.key) tmp
+POSTHOOK: type: QUERY
+ABSTRACT SYNTAX TREE:
+ (TOK_QUERY (TOK_FROM (TOK_SUBQUERY (TOK_QUERY (TOK_FROM (TOK_LEFTSEMIJOIN (TOK_TABREF (TOK_TABNAME src1) x) (TOK_TABREF (TOK_TABNAME src) y) (= (. (TOK_TABLE_OR_COL x) key) (. (TOK_TABLE_OR_COL y) key)))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (. (TOK_TABLE_OR_COL x) key) key) (TOK_SELEXPR (TOK_FUNCTION count 1) cnt)) (TOK_GROUPBY (. (TOK_TABLE_OR_COL x) key)))) tmp)) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_FUNCTION SUM (TOK_FUNCTION HASH (. (TOK_TABLE_OR_COL tmp) key)))) (TOK_SELEXPR (TOK_FUNCTION SUM (TOK_FUNCTION HASH (. (TOK_TABLE_OR_COL tmp) cnt)))))))
+
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-2 depends on stages: Stage-1
+ Stage-0 is a root stage
+
+STAGE PLANS:
+ Stage: Stage-1
+ Map Reduce
+ Alias -> Map Operator Tree:
+ tmp:x
+ TableScan
+ alias: x
+ Reduce Output Operator
+ key expressions:
+ expr: key
+ type: string
+ sort order: +
+ Map-reduce partition columns:
+ expr: key
+ type: string
+ tag: 0
+ value expressions:
+ expr: key
+ type: string
+ tmp:y
+ TableScan
+ alias: y
+ Select Operator
+ expressions:
+ expr: key
+ type: string
+ outputColumnNames: key
+ Group By Operator
+ bucketGroup: false
+ keys:
+ expr: key
+ type: string
+ mode: hash
+ outputColumnNames: _col0
+ Reduce Output Operator
+ key expressions:
+ expr: _col0
+ type: string
+ sort order: +
+ Map-reduce partition columns:
+ expr: _col0
+ type: string
+ tag: 1
+ Reduce Operator Tree:
+ Demux Operator
+ Join Operator
+ condition map:
+ Left Semi Join 0 to 1
+ condition expressions:
+ 0 {VALUE._col0}
+ 1
+ handleSkewJoin: false
+ outputColumnNames: _col0
+ Select Operator
+ expressions:
+ expr: _col0
+ type: string
+ outputColumnNames: _col0
+ Mux Operator
+ Group By Operator
+ aggregations:
+ expr: count(1)
+ bucketGroup: false
+ keys:
+ expr: _col0
+ type: string
+ mode: complete
+ outputColumnNames: _col0, _col1
+ Select Operator
+ expressions:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: bigint
+ outputColumnNames: _col0, _col1
+ Group By Operator
+ aggregations:
+ expr: sum(hash(_col0))
+ expr: sum(hash(_col1))
+ bucketGroup: false
+ mode: hash
+ outputColumnNames: _col0, _col1
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+
+ Stage: Stage-2
+ Map Reduce
+ Alias -> Map Operator Tree:
+#### A masked pattern was here ####
+ Reduce Output Operator
+ sort order:
+ tag: -1
+ value expressions:
+ expr: _col0
+ type: bigint
+ expr: _col1
+ type: bigint
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations:
+ expr: sum(VALUE._col0)
+ expr: sum(VALUE._col1)
+ bucketGroup: false
+ mode: mergepartial
+ outputColumnNames: _col0, _col1
+ Select Operator
+ expressions:
+ expr: _col0
+ type: bigint
+ expr: _col1
+ type: bigint
+ outputColumnNames: _col0, _col1
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+
+
+PREHOOK: query: SELECT SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt))
+FROM (SELECT x.key AS key, count(1) AS cnt
+ FROM src1 x LEFT SEMI JOIN src y ON (x.key = y.key)
+ GROUP BY x.key) tmp
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+PREHOOK: Input: default@src1
+#### A masked pattern was here ####
+POSTHOOK: query: SELECT SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt))
+FROM (SELECT x.key AS key, count(1) AS cnt
+ FROM src1 x LEFT SEMI JOIN src y ON (x.key = y.key)
+ GROUP BY x.key) tmp
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+POSTHOOK: Input: default@src1
+#### A masked pattern was here ####
+652447 15
+PREHOOK: query: -- If the key of a GroupByOperator is the left table's key in
+-- a Left Outer Join, these two operators will be executed in
+-- the same MR job when Correlation Optimizer is enabled.
+EXPLAIN
+SELECT SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt))
+FROM (SELECT x.key AS key, count(1) AS cnt
+ FROM src1 x LEFT OUTER JOIN src y ON (x.key = y.key)
+ GROUP BY x.key) tmp
+PREHOOK: type: QUERY
+POSTHOOK: query: -- If the key of a GroupByOperator is the left table's key in
+-- a Left Outer Join, these two operators will be executed in
+-- the same MR job when Correlation Optimizer is enabled.
+EXPLAIN
+SELECT SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt))
+FROM (SELECT x.key AS key, count(1) AS cnt
+ FROM src1 x LEFT OUTER JOIN src y ON (x.key = y.key)
+ GROUP BY x.key) tmp
+POSTHOOK: type: QUERY
+ABSTRACT SYNTAX TREE:
+ (TOK_QUERY (TOK_FROM (TOK_SUBQUERY (TOK_QUERY (TOK_FROM (TOK_LEFTOUTERJOIN (TOK_TABREF (TOK_TABNAME src1) x) (TOK_TABREF (TOK_TABNAME src) y) (= (. (TOK_TABLE_OR_COL x) key) (. (TOK_TABLE_OR_COL y) key)))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (. (TOK_TABLE_OR_COL x) key) key) (TOK_SELEXPR (TOK_FUNCTION count 1) cnt)) (TOK_GROUPBY (. (TOK_TABLE_OR_COL x) key)))) tmp)) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_FUNCTION SUM (TOK_FUNCTION HASH (. (TOK_TABLE_OR_COL tmp) key)))) (TOK_SELEXPR (TOK_FUNCTION SUM (TOK_FUNCTION HASH (. (TOK_TABLE_OR_COL tmp) cnt)))))))
+
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-2 depends on stages: Stage-1
+ Stage-3 depends on stages: Stage-2
+ Stage-0 is a root stage
+
+STAGE PLANS:
+ Stage: Stage-1
+ Map Reduce
+ Alias -> Map Operator Tree:
+ tmp:x
+ TableScan
+ alias: x
+ Reduce Output Operator
+ key expressions:
+ expr: key
+ type: string
+ sort order: +
+ Map-reduce partition columns:
+ expr: key
+ type: string
+ tag: 0
+ value expressions:
+ expr: key
+ type: string
+ tmp:y
+ TableScan
+ alias: y
+ Reduce Output Operator
+ key expressions:
+ expr: key
+ type: string
+ sort order: +
+ Map-reduce partition columns:
+ expr: key
+ type: string
+ tag: 1
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Left Outer Join0 to 1
+ condition expressions:
+ 0 {VALUE._col0}
+ 1
+ handleSkewJoin: false
+ outputColumnNames: _col0
+ Select Operator
+ expressions:
+ expr: _col0
+ type: string
+ outputColumnNames: _col0
+ Group By Operator
+ aggregations:
+ expr: count(1)
+ bucketGroup: false
+ keys:
+ expr: _col0
+ type: string
+ mode: hash
+ outputColumnNames: _col0, _col1
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+
+ Stage: Stage-2
+ Map Reduce
+ Alias -> Map Operator Tree:
+#### A masked pattern was here ####
+ Reduce Output Operator
+ key expressions:
+ expr: _col0
+ type: string
+ sort order: +
+ Map-reduce partition columns:
+ expr: _col0
+ type: string
+ tag: -1
+ value expressions:
+ expr: _col1
+ type: bigint
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations:
+ expr: count(VALUE._col0)
+ bucketGroup: false
+ keys:
+ expr: KEY._col0
+ type: string
+ mode: mergepartial
+ outputColumnNames: _col0, _col1
+ Select Operator
+ expressions:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: bigint
+ outputColumnNames: _col0, _col1
+ Group By Operator
+ aggregations:
+ expr: sum(hash(_col0))
+ expr: sum(hash(_col1))
+ bucketGroup: false
+ mode: hash
+ outputColumnNames: _col0, _col1
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+
+ Stage: Stage-3
+ Map Reduce
+ Alias -> Map Operator Tree:
+#### A masked pattern was here ####
+ Reduce Output Operator
+ sort order:
+ tag: -1
+ value expressions:
+ expr: _col0
+ type: bigint
+ expr: _col1
+ type: bigint
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations:
+ expr: sum(VALUE._col0)
+ expr: sum(VALUE._col1)
+ bucketGroup: false
+ mode: mergepartial
+ outputColumnNames: _col0, _col1
+ Select Operator
+ expressions:
+ expr: _col0
+ type: bigint
+ expr: _col1
+ type: bigint
+ outputColumnNames: _col0, _col1
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+
+
+PREHOOK: query: SELECT SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt))
+FROM (SELECT x.key AS key, count(1) AS cnt
+ FROM src1 x LEFT OUTER JOIN src y ON (x.key = y.key)
+ GROUP BY x.key) tmp
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+PREHOOK: Input: default@src1
+#### A masked pattern was here ####
+POSTHOOK: query: SELECT SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt))
+FROM (SELECT x.key AS key, count(1) AS cnt
+ FROM src1 x LEFT OUTER JOIN src y ON (x.key = y.key)
+ GROUP BY x.key) tmp
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+POSTHOOK: Input: default@src1
+#### A masked pattern was here ####
+652447 47
+PREHOOK: query: EXPLAIN
+SELECT SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt))
+FROM (SELECT x.key AS key, count(1) AS cnt
+ FROM src1 x LEFT OUTER JOIN src y ON (x.key = y.key)
+ GROUP BY x.key) tmp
+PREHOOK: type: QUERY
+POSTHOOK: query: EXPLAIN
+SELECT SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt))
+FROM (SELECT x.key AS key, count(1) AS cnt
+ FROM src1 x LEFT OUTER JOIN src y ON (x.key = y.key)
+ GROUP BY x.key) tmp
+POSTHOOK: type: QUERY
+ABSTRACT SYNTAX TREE:
+ (TOK_QUERY (TOK_FROM (TOK_SUBQUERY (TOK_QUERY (TOK_FROM (TOK_LEFTOUTERJOIN (TOK_TABREF (TOK_TABNAME src1) x) (TOK_TABREF (TOK_TABNAME src) y) (= (. (TOK_TABLE_OR_COL x) key) (. (TOK_TABLE_OR_COL y) key)))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (. (TOK_TABLE_OR_COL x) key) key) (TOK_SELEXPR (TOK_FUNCTION count 1) cnt)) (TOK_GROUPBY (. (TOK_TABLE_OR_COL x) key)))) tmp)) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_FUNCTION SUM (TOK_FUNCTION HASH (. (TOK_TABLE_OR_COL tmp) key)))) (TOK_SELEXPR (TOK_FUNCTION SUM (TOK_FUNCTION HASH (. (TOK_TABLE_OR_COL tmp) cnt)))))))
+
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-2 depends on stages: Stage-1
+ Stage-0 is a root stage
+
+STAGE PLANS:
+ Stage: Stage-1
+ Map Reduce
+ Alias -> Map Operator Tree:
+ tmp:x
+ TableScan
+ alias: x
+ Reduce Output Operator
+ key expressions:
+ expr: key
+ type: string
+ sort order: +
+ Map-reduce partition columns:
+ expr: key
+ type: string
+ tag: 0
+ value expressions:
+ expr: key
+ type: string
+ tmp:y
+ TableScan
+ alias: y
+ Reduce Output Operator
+ key expressions:
+ expr: key
+ type: string
+ sort order: +
+ Map-reduce partition columns:
+ expr: key
+ type: string
+ tag: 1
+ Reduce Operator Tree:
+ Demux Operator
+ Join Operator
+ condition map:
+ Left Outer Join0 to 1
+ condition expressions:
+ 0 {VALUE._col0}
+ 1
+ handleSkewJoin: false
+ outputColumnNames: _col0
+ Select Operator
+ expressions:
+ expr: _col0
+ type: string
+ outputColumnNames: _col0
+ Mux Operator
+ Group By Operator
+ aggregations:
+ expr: count(1)
+ bucketGroup: false
+ keys:
+ expr: _col0
+ type: string
+ mode: complete
+ outputColumnNames: _col0, _col1
+ Select Operator
+ expressions:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: bigint
+ outputColumnNames: _col0, _col1
+ Group By Operator
+ aggregations:
+ expr: sum(hash(_col0))
+ expr: sum(hash(_col1))
+ bucketGroup: false
+ mode: hash
+ outputColumnNames: _col0, _col1
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+
+ Stage: Stage-2
+ Map Reduce
+ Alias -> Map Operator Tree:
+#### A masked pattern was here ####
+ Reduce Output Operator
+ sort order:
+ tag: -1
+ value expressions:
+ expr: _col0
+ type: bigint
+ expr: _col1
+ type: bigint
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations:
+ expr: sum(VALUE._col0)
+ expr: sum(VALUE._col1)
+ bucketGroup: false
+ mode: mergepartial
+ outputColumnNames: _col0, _col1
+ Select Operator
+ expressions:
+ expr: _col0
+ type: bigint
+ expr: _col1
+ type: bigint
+ outputColumnNames: _col0, _col1
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+
+
+PREHOOK: query: SELECT SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt))
+FROM (SELECT x.key AS key, count(1) AS cnt
+ FROM src1 x LEFT OUTER JOIN src y ON (x.key = y.key)
+ GROUP BY x.key) tmp
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+PREHOOK: Input: default@src1
+#### A masked pattern was here ####
+POSTHOOK: query: SELECT SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt))
+FROM (SELECT x.key AS key, count(1) AS cnt
+ FROM src1 x LEFT OUTER JOIN src y ON (x.key = y.key)
+ GROUP BY x.key) tmp
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+POSTHOOK: Input: default@src1
+#### A masked pattern was here ####
+652447 47
+PREHOOK: query: -- If the key of a GroupByOperator is the right table's key in
+-- a Left Outer Join, we cannot use a single MR to execute these two
+-- operators because those keys with a null value are not grouped.
+EXPLAIN
+SELECT SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt))
+FROM (SELECT y.key AS key, count(1) AS cnt
+ FROM src1 x LEFT OUTER JOIN src y ON (x.key = y.key)
+ GROUP BY y.key) tmp
+PREHOOK: type: QUERY
+POSTHOOK: query: -- If the key of a GroupByOperator is the right table's key in
+-- a Left Outer Join, we cannot use a single MR to execute these two
+-- operators because those keys with a null value are not grouped.
+EXPLAIN
+SELECT SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt))
+FROM (SELECT y.key AS key, count(1) AS cnt
+ FROM src1 x LEFT OUTER JOIN src y ON (x.key = y.key)
+ GROUP BY y.key) tmp
+POSTHOOK: type: QUERY
+ABSTRACT SYNTAX TREE:
+ (TOK_QUERY (TOK_FROM (TOK_SUBQUERY (TOK_QUERY (TOK_FROM (TOK_LEFTOUTERJOIN (TOK_TABREF (TOK_TABNAME src1) x) (TOK_TABREF (TOK_TABNAME src) y) (= (. (TOK_TABLE_OR_COL x) key) (. (TOK_TABLE_OR_COL y) key)))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (. (TOK_TABLE_OR_COL y) key) key) (TOK_SELEXPR (TOK_FUNCTION count 1) cnt)) (TOK_GROUPBY (. (TOK_TABLE_OR_COL y) key)))) tmp)) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_FUNCTION SUM (TOK_FUNCTION HASH (. (TOK_TABLE_OR_COL tmp) key)))) (TOK_SELEXPR (TOK_FUNCTION SUM (TOK_FUNCTION HASH (. (TOK_TABLE_OR_COL tmp) cnt)))))))
+
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-2 depends on stages: Stage-1
+ Stage-3 depends on stages: Stage-2
+ Stage-0 is a root stage
+
+STAGE PLANS:
+ Stage: Stage-1
+ Map Reduce
+ Alias -> Map Operator Tree:
+ tmp:x
+ TableScan
+ alias: x
+ Reduce Output Operator
+ key expressions:
+ expr: key
+ type: string
+ sort order: +
+ Map-reduce partition columns:
+ expr: key
+ type: string
+ tag: 0
+ tmp:y
+ TableScan
+ alias: y
+ Reduce Output Operator
+ key expressions:
+ expr: key
+ type: string
+ sort order: +
+ Map-reduce partition columns:
+ expr: key
+ type: string
+ tag: 1
+ value expressions:
+ expr: key
+ type: string
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Left Outer Join0 to 1
+ condition expressions:
+ 0
+ 1 {VALUE._col0}
+ handleSkewJoin: false
+ outputColumnNames: _col4
+ Select Operator
+ expressions:
+ expr: _col4
+ type: string
+ outputColumnNames: _col4
+ Group By Operator
+ aggregations:
+ expr: count(1)
+ bucketGroup: false
+ keys:
+ expr: _col4
+ type: string
+ mode: hash
+ outputColumnNames: _col0, _col1
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+
+ Stage: Stage-2
+ Map Reduce
+ Alias -> Map Operator Tree:
+#### A masked pattern was here ####
+ Reduce Output Operator
+ key expressions:
+ expr: _col0
+ type: string
+ sort order: +
+ Map-reduce partition columns:
+ expr: _col0
+ type: string
+ tag: -1
+ value expressions:
+ expr: _col1
+ type: bigint
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations:
+ expr: count(VALUE._col0)
+ bucketGroup: false
+ keys:
+ expr: KEY._col0
+ type: string
+ mode: mergepartial
+ outputColumnNames: _col0, _col1
+ Select Operator
+ expressions:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: bigint
+ outputColumnNames: _col0, _col1
+ Group By Operator
+ aggregations:
+ expr: sum(hash(_col0))
+ expr: sum(hash(_col1))
+ bucketGroup: false
+ mode: hash
+ outputColumnNames: _col0, _col1
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+
+ Stage: Stage-3
+ Map Reduce
+ Alias -> Map Operator Tree:
+#### A masked pattern was here ####
+ Reduce Output Operator
+ sort order:
+ tag: -1
+ value expressions:
+ expr: _col0
+ type: bigint
+ expr: _col1
+ type: bigint
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations:
+ expr: sum(VALUE._col0)
+ expr: sum(VALUE._col1)
+ bucketGroup: false
+ mode: mergepartial
+ outputColumnNames: _col0, _col1
+ Select Operator
+ expressions:
+ expr: _col0
+ type: bigint
+ expr: _col1
+ type: bigint
+ outputColumnNames: _col0, _col1
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+
+
+PREHOOK: query: SELECT SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt))
+FROM (SELECT y.key AS key, count(1) AS cnt
+ FROM src1 x LEFT OUTER JOIN src y ON (x.key = y.key)
+ GROUP BY y.key) tmp
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+PREHOOK: Input: default@src1
+#### A masked pattern was here ####
+POSTHOOK: query: SELECT SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt))
+FROM (SELECT y.key AS key, count(1) AS cnt
+ FROM src1 x LEFT OUTER JOIN src y ON (x.key = y.key)
+ GROUP BY y.key) tmp
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+POSTHOOK: Input: default@src1
+#### A masked pattern was here ####
+652447 47
+PREHOOK: query: EXPLAIN
+SELECT SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt))
+FROM (SELECT y.key AS key, count(1) AS cnt
+ FROM src1 x LEFT OUTER JOIN src y ON (x.key = y.key)
+ GROUP BY y.key) tmp
+PREHOOK: type: QUERY
+POSTHOOK: query: EXPLAIN
+SELECT SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt))
+FROM (SELECT y.key AS key, count(1) AS cnt
+ FROM src1 x LEFT OUTER JOIN src y ON (x.key = y.key)
+ GROUP BY y.key) tmp
+POSTHOOK: type: QUERY
+ABSTRACT SYNTAX TREE:
+ (TOK_QUERY (TOK_FROM (TOK_SUBQUERY (TOK_QUERY (TOK_FROM (TOK_LEFTOUTERJOIN (TOK_TABREF (TOK_TABNAME src1) x) (TOK_TABREF (TOK_TABNAME src) y) (= (. (TOK_TABLE_OR_COL x) key) (. (TOK_TABLE_OR_COL y) key)))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (. (TOK_TABLE_OR_COL y) key) key) (TOK_SELEXPR (TOK_FUNCTION count 1) cnt)) (TOK_GROUPBY (. (TOK_TABLE_OR_COL y) key)))) tmp)) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_FUNCTION SUM (TOK_FUNCTION HASH (. (TOK_TABLE_OR_COL tmp) key)))) (TOK_SELEXPR (TOK_FUNCTION SUM (TOK_FUNCTION HASH (. (TOK_TABLE_OR_COL tmp) cnt)))))))
+
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-2 depends on stages: Stage-1
+ Stage-3 depends on stages: Stage-2
+ Stage-0 is a root stage
+
+STAGE PLANS:
+ Stage: Stage-1
+ Map Reduce
+ Alias -> Map Operator Tree:
+ tmp:x
+ TableScan
+ alias: x
+ Reduce Output Operator
+ key expressions:
+ expr: key
+ type: string
+ sort order: +
+ Map-reduce partition columns:
+ expr: key
+ type: string
+ tag: 0
+ tmp:y
+ TableScan
+ alias: y
+ Reduce Output Operator
+ key expressions:
+ expr: key
+ type: string
+ sort order: +
+ Map-reduce partition columns:
+ expr: key
+ type: string
+ tag: 1
+ value expressions:
+ expr: key
+ type: string
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Left Outer Join0 to 1
+ condition expressions:
+ 0
+ 1 {VALUE._col0}
+ handleSkewJoin: false
+ outputColumnNames: _col4
+ Select Operator
+ expressions:
+ expr: _col4
+ type: string
+ outputColumnNames: _col4
+ Group By Operator
+ aggregations:
+ expr: count(1)
+ bucketGroup: false
+ keys:
+ expr: _col4
+ type: string
+ mode: hash
+ outputColumnNames: _col0, _col1
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+
+ Stage: Stage-2
+ Map Reduce
+ Alias -> Map Operator Tree:
+#### A masked pattern was here ####
+ Reduce Output Operator
+ key expressions:
+ expr: _col0
+ type: string
+ sort order: +
+ Map-reduce partition columns:
+ expr: _col0
+ type: string
+ tag: -1
+ value expressions:
+ expr: _col1
+ type: bigint
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations:
+ expr: count(VALUE._col0)
+ bucketGroup: false
+ keys:
+ expr: KEY._col0
+ type: string
+ mode: mergepartial
+ outputColumnNames: _col0, _col1
+ Select Operator
+ expressions:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: bigint
+ outputColumnNames: _col0, _col1
+ Group By Operator
+ aggregations:
+ expr: sum(hash(_col0))
+ expr: sum(hash(_col1))
+ bucketGroup: false
+ mode: hash
+ outputColumnNames: _col0, _col1
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+
+ Stage: Stage-3
+ Map Reduce
+ Alias -> Map Operator Tree:
+#### A masked pattern was here ####
+ Reduce Output Operator
+ sort order:
+ tag: -1
+ value expressions:
+ expr: _col0
+ type: bigint
+ expr: _col1
+ type: bigint
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations:
+ expr: sum(VALUE._col0)
+ expr: sum(VALUE._col1)
+ bucketGroup: false
+ mode: mergepartial
+ outputColumnNames: _col0, _col1
+ Select Operator
+ expressions:
+ expr: _col0
+ type: bigint
+ expr: _col1
+ type: bigint
+ outputColumnNames: _col0, _col1
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+
+
+PREHOOK: query: SELECT SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt))
+FROM (SELECT y.key AS key, count(1) AS cnt
+ FROM src1 x LEFT OUTER JOIN src y ON (x.key = y.key)
+ GROUP BY y.key) tmp
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+PREHOOK: Input: default@src1
+#### A masked pattern was here ####
+POSTHOOK: query: SELECT SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt))
+FROM (SELECT y.key AS key, count(1) AS cnt
+ FROM src1 x LEFT OUTER JOIN src y ON (x.key = y.key)
+ GROUP BY y.key) tmp
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+POSTHOOK: Input: default@src1
+#### A masked pattern was here ####
+652447 47
+PREHOOK: query: -- If the key of a GroupByOperator is the right table's key in
+-- a Right Outer Join, these two operators will be executed in
+-- the same MR job when Correlation Optimizer is enabled.
+EXPLAIN
+SELECT SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt))
+FROM (SELECT y.key AS key, count(1) AS cnt
+ FROM src1 x RIGHT OUTER JOIN src y ON (x.key = y.key)
+ GROUP BY y.key) tmp
+PREHOOK: type: QUERY
+POSTHOOK: query: -- If the key of a GroupByOperator is the right table's key in
+-- a Right Outer Join, these two operators will be executed in
+-- the same MR job when Correlation Optimizer is enabled.
+EXPLAIN
+SELECT SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt))
+FROM (SELECT y.key AS key, count(1) AS cnt
+ FROM src1 x RIGHT OUTER JOIN src y ON (x.key = y.key)
+ GROUP BY y.key) tmp
+POSTHOOK: type: QUERY
+ABSTRACT SYNTAX TREE:
+ (TOK_QUERY (TOK_FROM (TOK_SUBQUERY (TOK_QUERY (TOK_FROM (TOK_RIGHTOUTERJOIN (TOK_TABREF (TOK_TABNAME src1) x) (TOK_TABREF (TOK_TABNAME src) y) (= (. (TOK_TABLE_OR_COL x) key) (. (TOK_TABLE_OR_COL y) key)))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (. (TOK_TABLE_OR_COL y) key) key) (TOK_SELEXPR (TOK_FUNCTION count 1) cnt)) (TOK_GROUPBY (. (TOK_TABLE_OR_COL y) key)))) tmp)) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_FUNCTION SUM (TOK_FUNCTION HASH (. (TOK_TABLE_OR_COL tmp) key)))) (TOK_SELEXPR (TOK_FUNCTION SUM (TOK_FUNCTION HASH (. (TOK_TABLE_OR_COL tmp) cnt)))))))
+
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-2 depends on stages: Stage-1
+ Stage-3 depends on stages: Stage-2
+ Stage-0 is a root stage
+
+STAGE PLANS:
+ Stage: Stage-1
+ Map Reduce
+ Alias -> Map Operator Tree:
+ tmp:x
+ TableScan
+ alias: x
+ Reduce Output Operator
+ key expressions:
+ expr: key
+ type: string
+ sort order: +
+ Map-reduce partition columns:
+ expr: key
+ type: string
+ tag: 0
+ tmp:y
+ TableScan
+ alias: y
+ Reduce Output Operator
+ key expressions:
+ expr: key
+ type: string
+ sort order: +
+ Map-reduce partition columns:
+ expr: key
+ type: string
+ tag: 1
+ value expressions:
+ expr: key
+ type: string
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Right Outer Join0 to 1
+ condition expressions:
+ 0
+ 1 {VALUE._col0}
+ handleSkewJoin: false
+ outputColumnNames: _col4
+ Select Operator
+ expressions:
+ expr: _col4
+ type: string
+ outputColumnNames: _col4
+ Group By Operator
+ aggregations:
+ expr: count(1)
+ bucketGroup: false
+ keys:
+ expr: _col4
+ type: string
+ mode: hash
+ outputColumnNames: _col0, _col1
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+
+ Stage: Stage-2
+ Map Reduce
+ Alias -> Map Operator Tree:
+#### A masked pattern was here ####
+ Reduce Output Operator
+ key expressions:
+ expr: _col0
+ type: string
+ sort order: +
+ Map-reduce partition columns:
+ expr: _col0
+ type: string
+ tag: -1
+ value expressions:
+ expr: _col1
+ type: bigint
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations:
+ expr: count(VALUE._col0)
+ bucketGroup: false
+ keys:
+ expr: KEY._col0
+ type: string
+ mode: mergepartial
+ outputColumnNames: _col0, _col1
+ Select Operator
+ expressions:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: bigint
+ outputColumnNames: _col0, _col1
+ Group By Operator
+ aggregations:
+ expr: sum(hash(_col0))
+ expr: sum(hash(_col1))
+ bucketGroup: false
+ mode: hash
+ outputColumnNames: _col0, _col1
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+
+ Stage: Stage-3
+ Map Reduce
+ Alias -> Map Operator Tree:
+#### A masked pattern was here ####
+ Reduce Output Operator
+ sort order:
+ tag: -1
+ value expressions:
+ expr: _col0
+ type: bigint
+ expr: _col1
+ type: bigint
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations:
+ expr: sum(VALUE._col0)
+ expr: sum(VALUE._col1)
+ bucketGroup: false
+ mode: mergepartial
+ outputColumnNames: _col0, _col1
+ Select Operator
+ expressions:
+ expr: _col0
+ type: bigint
+ expr: _col1
+ type: bigint
+ outputColumnNames: _col0, _col1
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+
+
+PREHOOK: query: SELECT SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt))
+FROM (SELECT y.key AS key, count(1) AS cnt
+ FROM src1 x RIGHT OUTER JOIN src y ON (x.key = y.key)
+ GROUP BY y.key) tmp
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+PREHOOK: Input: default@src1
+#### A masked pattern was here ####
+POSTHOOK: query: SELECT SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt))
+FROM (SELECT y.key AS key, count(1) AS cnt
+ FROM src1 x RIGHT OUTER JOIN src y ON (x.key = y.key)
+ GROUP BY y.key) tmp
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+POSTHOOK: Input: default@src1
+#### A masked pattern was here ####
+12744278 500
+PREHOOK: query: EXPLAIN
+SELECT SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt))
+FROM (SELECT y.key AS key, count(1) AS cnt
+ FROM src1 x RIGHT OUTER JOIN src y ON (x.key = y.key)
+ GROUP BY y.key) tmp
+PREHOOK: type: QUERY
+POSTHOOK: query: EXPLAIN
+SELECT SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt))
+FROM (SELECT y.key AS key, count(1) AS cnt
+ FROM src1 x RIGHT OUTER JOIN src y ON (x.key = y.key)
+ GROUP BY y.key) tmp
+POSTHOOK: type: QUERY
+ABSTRACT SYNTAX TREE:
+ (TOK_QUERY (TOK_FROM (TOK_SUBQUERY (TOK_QUERY (TOK_FROM (TOK_RIGHTOUTERJOIN (TOK_TABREF (TOK_TABNAME src1) x) (TOK_TABREF (TOK_TABNAME src) y) (= (. (TOK_TABLE_OR_COL x) key) (. (TOK_TABLE_OR_COL y) key)))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (. (TOK_TABLE_OR_COL y) key) key) (TOK_SELEXPR (TOK_FUNCTION count 1) cnt)) (TOK_GROUPBY (. (TOK_TABLE_OR_COL y) key)))) tmp)) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_FUNCTION SUM (TOK_FUNCTION HASH (. (TOK_TABLE_OR_COL tmp) key)))) (TOK_SELEXPR (TOK_FUNCTION SUM (TOK_FUNCTION HASH (. (TOK_TABLE_OR_COL tmp) cnt)))))))
+
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-2 depends on stages: Stage-1
+ Stage-0 is a root stage
+
+STAGE PLANS:
+ Stage: Stage-1
+ Map Reduce
+ Alias -> Map Operator Tree:
+ tmp:x
+ TableScan
+ alias: x
+ Reduce Output Operator
+ key expressions:
+ expr: key
+ type: string
+ sort order: +
+ Map-reduce partition columns:
+ expr: key
+ type: string
+ tag: 1
+ tmp:y
+ TableScan
+ alias: y
+ Reduce Output Operator
+ key expressions:
+ expr: key
+ type: string
+ sort order: +
+ Map-reduce partition columns:
+ expr: key
+ type: string
+ tag: 0
+ value expressions:
+ expr: key
+ type: string
+ Reduce Operator Tree:
+ Demux Operator
+ Join Operator
+ condition map:
+ Right Outer Join0 to 1
+ condition expressions:
+ 0
+ 1 {VALUE._col0}
+ handleSkewJoin: false
+ outputColumnNames: _col4
+ Select Operator
+ expressions:
+ expr: _col4
+ type: string
+ outputColumnNames: _col4
+ Mux Operator
+ Group By Operator
+ aggregations:
+ expr: count(1)
+ bucketGroup: false
+ keys:
+ expr: _col4
+ type: string
+ mode: complete
+ outputColumnNames: _col0, _col1
+ Select Operator
+ expressions:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: bigint
+ outputColumnNames: _col0, _col1
+ Group By Operator
+ aggregations:
+ expr: sum(hash(_col0))
+ expr: sum(hash(_col1))
+ bucketGroup: false
+ mode: hash
+ outputColumnNames: _col0, _col1
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+
+ Stage: Stage-2
+ Map Reduce
+ Alias -> Map Operator Tree:
+#### A masked pattern was here ####
+ Reduce Output Operator
+ sort order:
+ tag: -1
+ value expressions:
+ expr: _col0
+ type: bigint
+ expr: _col1
+ type: bigint
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations:
+ expr: sum(VALUE._col0)
+ expr: sum(VALUE._col1)
+ bucketGroup: false
+ mode: mergepartial
+ outputColumnNames: _col0, _col1
+ Select Operator
+ expressions:
+ expr: _col0
+ type: bigint
+ expr: _col1
+ type: bigint
+ outputColumnNames: _col0, _col1
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+
+
+PREHOOK: query: SELECT SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt))
+FROM (SELECT y.key AS key, count(1) AS cnt
+ FROM src1 x RIGHT OUTER JOIN src y ON (x.key = y.key)
+ GROUP BY y.key) tmp
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+PREHOOK: Input: default@src1
+#### A masked pattern was here ####
+POSTHOOK: query: SELECT SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt))
+FROM (SELECT y.key AS key, count(1) AS cnt
+ FROM src1 x RIGHT OUTER JOIN src y ON (x.key = y.key)
+ GROUP BY y.key) tmp
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+POSTHOOK: Input: default@src1
+#### A masked pattern was here ####
+12744278 500
+PREHOOK: query: -- If the key of a GroupByOperator is the left table's key in
+-- a Right Outer Join, we cannot use a single MR to execute these two
+-- operators because those keys with a null value are not grouped.
+EXPLAIN
+SELECT SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt))
+FROM (SELECT x.key AS key, count(1) AS cnt
+ FROM src1 x RIGHT OUTER JOIN src y ON (x.key = y.key)
+ GROUP BY x.key) tmp
+PREHOOK: type: QUERY
+POSTHOOK: query: -- If the key of a GroupByOperator is the left table's key in
+-- a Right Outer Join, we cannot use a single MR to execute these two
+-- operators because those keys with a null value are not grouped.
+EXPLAIN
+SELECT SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt))
+FROM (SELECT x.key AS key, count(1) AS cnt
+ FROM src1 x RIGHT OUTER JOIN src y ON (x.key = y.key)
+ GROUP BY x.key) tmp
+POSTHOOK: type: QUERY
+ABSTRACT SYNTAX TREE:
+ (TOK_QUERY (TOK_FROM (TOK_SUBQUERY (TOK_QUERY (TOK_FROM (TOK_RIGHTOUTERJOIN (TOK_TABREF (TOK_TABNAME src1) x) (TOK_TABREF (TOK_TABNAME src) y) (= (. (TOK_TABLE_OR_COL x) key) (. (TOK_TABLE_OR_COL y) key)))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (. (TOK_TABLE_OR_COL x) key) key) (TOK_SELEXPR (TOK_FUNCTION count 1) cnt)) (TOK_GROUPBY (. (TOK_TABLE_OR_COL x) key)))) tmp)) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_FUNCTION SUM (TOK_FUNCTION HASH (. (TOK_TABLE_OR_COL tmp) key)))) (TOK_SELEXPR (TOK_FUNCTION SUM (TOK_FUNCTION HASH (. (TOK_TABLE_OR_COL tmp) cnt)))))))
+
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-2 depends on stages: Stage-1
+ Stage-3 depends on stages: Stage-2
+ Stage-0 is a root stage
+
+STAGE PLANS:
+ Stage: Stage-1
+ Map Reduce
+ Alias -> Map Operator Tree:
+ tmp:x
+ TableScan
+ alias: x
+ Reduce Output Operator
+ key expressions:
+ expr: key
+ type: string
+ sort order: +
+ Map-reduce partition columns:
+ expr: key
+ type: string
+ tag: 0
+ value expressions:
+ expr: key
+ type: string
+ tmp:y
+ TableScan
+ alias: y
+ Reduce Output Operator
+ key expressions:
+ expr: key
+ type: string
+ sort order: +
+ Map-reduce partition columns:
+ expr: key
+ type: string
+ tag: 1
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Right Outer Join0 to 1
+ condition expressions:
+ 0 {VALUE._col0}
+ 1
+ handleSkewJoin: false
+ outputColumnNames: _col0
+ Select Operator
+ expressions:
+ expr: _col0
+ type: string
+ outputColumnNames: _col0
+ Group By Operator
+ aggregations:
+ expr: count(1)
+ bucketGroup: false
+ keys:
+ expr: _col0
+ type: string
+ mode: hash
+ outputColumnNames: _col0, _col1
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+
+ Stage: Stage-2
+ Map Reduce
+ Alias -> Map Operator Tree:
+#### A masked pattern was here ####
+ Reduce Output Operator
+ key expressions:
+ expr: _col0
+ type: string
+ sort order: +
+ Map-reduce partition columns:
+ expr: _col0
+ type: string
+ tag: -1
+ value expressions:
+ expr: _col1
+ type: bigint
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations:
+ expr: count(VALUE._col0)
+ bucketGroup: false
+ keys:
+ expr: KEY._col0
+ type: string
+ mode: mergepartial
+ outputColumnNames: _col0, _col1
+ Select Operator
+ expressions:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: bigint
+ outputColumnNames: _col0, _col1
+ Group By Operator
+ aggregations:
+ expr: sum(hash(_col0))
+ expr: sum(hash(_col1))
+ bucketGroup: false
+ mode: hash
+ outputColumnNames: _col0, _col1
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+
+ Stage: Stage-3
+ Map Reduce
+ Alias -> Map Operator Tree:
+#### A masked pattern was here ####
+ Reduce Output Operator
+ sort order:
+ tag: -1
+ value expressions:
+ expr: _col0
+ type: bigint
+ expr: _col1
+ type: bigint
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations:
+ expr: sum(VALUE._col0)
+ expr: sum(VALUE._col1)
+ bucketGroup: false
+ mode: mergepartial
+ outputColumnNames: _col0, _col1
+ Select Operator
+ expressions:
+ expr: _col0
+ type: bigint
+ expr: _col1
+ type: bigint
+ outputColumnNames: _col0, _col1
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+
+
+PREHOOK: query: SELECT SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt))
+FROM (SELECT x.key AS key, count(1) AS cnt
+ FROM src1 x RIGHT OUTER JOIN src y ON (x.key = y.key)
+ GROUP BY x.key) tmp
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+PREHOOK: Input: default@src1
+#### A masked pattern was here ####
+POSTHOOK: query: SELECT SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt))
+FROM (SELECT x.key AS key, count(1) AS cnt
+ FROM src1 x RIGHT OUTER JOIN src y ON (x.key = y.key)
+ GROUP BY x.key) tmp
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+POSTHOOK: Input: default@src1
+#### A masked pattern was here ####
+652447 500
+PREHOOK: query: EXPLAIN
+SELECT SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt))
+FROM (SELECT x.key AS key, count(1) AS cnt
+ FROM src1 x RIGHT OUTER JOIN src y ON (x.key = y.key)
+ GROUP BY x.key) tmp
+PREHOOK: type: QUERY
+POSTHOOK: query: EXPLAIN
+SELECT SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt))
+FROM (SELECT x.key AS key, count(1) AS cnt
+ FROM src1 x RIGHT OUTER JOIN src y ON (x.key = y.key)
+ GROUP BY x.key) tmp
+POSTHOOK: type: QUERY
+ABSTRACT SYNTAX TREE:
+ (TOK_QUERY (TOK_FROM (TOK_SUBQUERY (TOK_QUERY (TOK_FROM (TOK_RIGHTOUTERJOIN (TOK_TABREF (TOK_TABNAME src1) x) (TOK_TABREF (TOK_TABNAME src) y) (= (. (TOK_TABLE_OR_COL x) key) (. (TOK_TABLE_OR_COL y) key)))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (. (TOK_TABLE_OR_COL x) key) key) (TOK_SELEXPR (TOK_FUNCTION count 1) cnt)) (TOK_GROUPBY (. (TOK_TABLE_OR_COL x) key)))) tmp)) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_FUNCTION SUM (TOK_FUNCTION HASH (. (TOK_TABLE_OR_COL tmp) key)))) (TOK_SELEXPR (TOK_FUNCTION SUM (TOK_FUNCTION HASH (. (TOK_TABLE_OR_COL tmp) cnt)))))))
+
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-2 depends on stages: Stage-1
+ Stage-3 depends on stages: Stage-2
+ Stage-0 is a root stage
+
+STAGE PLANS:
+ Stage: Stage-1
+ Map Reduce
+ Alias -> Map Operator Tree:
+ tmp:x
+ TableScan
+ alias: x
+ Reduce Output Operator
+ key expressions:
+ expr: key
+ type: string
+ sort order: +
+ Map-reduce partition columns:
+ expr: key
+ type: string
+ tag: 0
+ value expressions:
+ expr: key
+ type: string
+ tmp:y
+ TableScan
+ alias: y
+ Reduce Output Operator
+ key expressions:
+ expr: key
+ type: string
+ sort order: +
+ Map-reduce partition columns:
+ expr: key
+ type: string
+ tag: 1
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Right Outer Join0 to 1
+ condition expressions:
+ 0 {VALUE._col0}
+ 1
+ handleSkewJoin: false
+ outputColumnNames: _col0
+ Select Operator
+ expressions:
+ expr: _col0
+ type: string
+ outputColumnNames: _col0
+ Group By Operator
+ aggregations:
+ expr: count(1)
+ bucketGroup: false
+ keys:
+ expr: _col0
+ type: string
+ mode: hash
+ outputColumnNames: _col0, _col1
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+ table:
[... 1285 lines stripped ...]