You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@hive.apache.org by na...@apache.org on 2011/04/09 00:00:18 UTC
svn commit: r1090463 [4/5] - in /hive/trunk/ql/src:
java/org/apache/hadoop/hive/ql/exec/
java/org/apache/hadoop/hive/ql/optimizer/
java/org/apache/hadoop/hive/ql/optimizer/physical/
java/org/apache/hadoop/hive/ql/plan/ test/queries/clientpositive/ test...
Added: hive/trunk/ql/src/test/results/clientpositive/auto_join30.q.out
URL: http://svn.apache.org/viewvc/hive/trunk/ql/src/test/results/clientpositive/auto_join30.q.out?rev=1090463&view=auto
==============================================================================
--- hive/trunk/ql/src/test/results/clientpositive/auto_join30.q.out (added)
+++ hive/trunk/ql/src/test/results/clientpositive/auto_join30.q.out Fri Apr 8 22:00:18 2011
@@ -0,0 +1,2802 @@
+PREHOOK: query: explain
+FROM
+(SELECT src.* FROM src sort by key) x
+JOIN
+(SELECT src.* FROM src sort by value) Y
+ON (x.key = Y.key)
+select sum(hash(Y.key,Y.value))
+PREHOOK: type: QUERY
+POSTHOOK: query: explain
+FROM
+(SELECT src.* FROM src sort by key) x
+JOIN
+(SELECT src.* FROM src sort by value) Y
+ON (x.key = Y.key)
+select sum(hash(Y.key,Y.value))
+POSTHOOK: type: QUERY
+ABSTRACT SYNTAX TREE:
+ (TOK_QUERY (TOK_FROM (TOK_JOIN (TOK_SUBQUERY (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME src))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_ALLCOLREF (TOK_TABNAME src)))) (TOK_SORTBY (TOK_TABSORTCOLNAMEASC (TOK_TABLE_OR_COL key))))) x) (TOK_SUBQUERY (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME src))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_ALLCOLREF (TOK_TABNAME src)))) (TOK_SORTBY (TOK_TABSORTCOLNAMEASC (TOK_TABLE_OR_COL value))))) 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_FUNCTION sum (TOK_FUNCTION hash (. (TOK_TABLE_OR_COL Y) key) (. (TOK_TABLE_OR_COL Y) value)))))))
+
+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 is a root stage
+
+STAGE PLANS:
+ Stage: Stage-1
+ Map Reduce
+ Alias -> Map Operator Tree:
+ x:src
+ TableScan
+ alias: src
+ Select Operator
+ expressions:
+ expr: key
+ type: string
+ expr: value
+ type: string
+ outputColumnNames: _col0, _col1
+ Reduce Output Operator
+ key expressions:
+ expr: _col0
+ type: string
+ sort order: +
+ tag: -1
+ value expressions:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: string
+ Reduce Operator Tree:
+ Extract
+ 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-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
+ HashTable Sink Operator
+ condition expressions:
+ 0
+ 1 {_col0} {_col1}
+ handleSkewJoin: false
+ keys:
+ 0 [Column[_col0]]
+ 1 [Column[_col0]]
+ Position of Big Table: 0
+
+ Stage: Stage-5
+ Map Reduce
+ Alias -> Map Operator Tree:
+ $INTNAME
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0
+ 1 {_col0} {_col1}
+ handleSkewJoin: false
+ keys:
+ 0 [Column[_col0]]
+ 1 [Column[_col0]]
+ outputColumnNames: _col2, _col3
+ Position of Big Table: 0
+ Select Operator
+ expressions:
+ expr: _col2
+ type: string
+ expr: _col3
+ type: string
+ outputColumnNames: _col2, _col3
+ Group By Operator
+ aggregations:
+ expr: sum(hash(_col2,_col3))
+ bucketGroup: false
+ mode: hash
+ outputColumnNames: _col0
+ 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-3
+ Map Reduce
+ Alias -> Map Operator Tree:
+ file:/var/folders/6g/6grtCwPMEf4sqHUPpy6xQG9ByHg/-Tmp-/heyongqiang/hive_2011-04-07_01-29-33_521_1049482282230510027/-mr-10003
+ Reduce Output Operator
+ sort order:
+ tag: -1
+ value expressions:
+ expr: _col0
+ type: bigint
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations:
+ expr: sum(VALUE._col0)
+ bucketGroup: false
+ mode: mergepartial
+ outputColumnNames: _col0
+ Select Operator
+ expressions:
+ expr: _col0
+ type: bigint
+ outputColumnNames: _col0
+ 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-9
+ Map Reduce Local Work
+ Alias -> Map Local Tables:
+ $INTNAME
+ Fetch Operator
+ limit: -1
+ Alias -> Map Local Operator Tree:
+ $INTNAME
+ HashTable Sink Operator
+ condition expressions:
+ 0
+ 1 {_col0} {_col1}
+ handleSkewJoin: false
+ keys:
+ 0 [Column[_col0]]
+ 1 [Column[_col0]]
+ Position of Big Table: 1
+
+ Stage: Stage-6
+ Map Reduce
+ Alias -> Map Operator Tree:
+ $INTNAME1
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0
+ 1 {_col0} {_col1}
+ handleSkewJoin: false
+ keys:
+ 0 [Column[_col0]]
+ 1 [Column[_col0]]
+ outputColumnNames: _col2, _col3
+ Position of Big Table: 1
+ Select Operator
+ expressions:
+ expr: _col2
+ type: string
+ expr: _col3
+ type: string
+ outputColumnNames: _col2, _col3
+ Group By Operator
+ aggregations:
+ expr: sum(hash(_col2,_col3))
+ bucketGroup: false
+ mode: hash
+ outputColumnNames: _col0
+ 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:
+ $INTNAME
+ Reduce Output Operator
+ key expressions:
+ expr: _col0
+ type: string
+ sort order: +
+ Map-reduce partition columns:
+ expr: _col0
+ type: string
+ tag: 0
+ $INTNAME1
+ Reduce Output Operator
+ key expressions:
+ expr: _col0
+ type: string
+ sort order: +
+ Map-reduce partition columns:
+ expr: _col0
+ type: string
+ tag: 1
+ value expressions:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: string
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0
+ 1 {VALUE._col0} {VALUE._col1}
+ handleSkewJoin: false
+ outputColumnNames: _col2, _col3
+ Select Operator
+ expressions:
+ expr: _col2
+ type: string
+ expr: _col3
+ type: string
+ outputColumnNames: _col2, _col3
+ Group By Operator
+ aggregations:
+ expr: sum(hash(_col2,_col3))
+ bucketGroup: false
+ mode: hash
+ outputColumnNames: _col0
+ 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-4
+ Map Reduce
+ Alias -> Map Operator Tree:
+ y:src
+ TableScan
+ alias: src
+ Select Operator
+ expressions:
+ expr: key
+ type: string
+ expr: value
+ type: string
+ outputColumnNames: _col0, _col1
+ Reduce Output Operator
+ key expressions:
+ expr: _col1
+ type: string
+ sort order: +
+ tag: -1
+ value expressions:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: string
+ Reduce Operator Tree:
+ Extract
+ 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-0
+ Fetch Operator
+ limit: -1
+
+
+PREHOOK: query: FROM
+(SELECT src.* FROM src sort by key) x
+JOIN
+(SELECT src.* FROM src sort by value) Y
+ON (x.key = Y.key)
+select sum(hash(Y.key,Y.value))
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+PREHOOK: Output: file:/var/folders/6g/6grtCwPMEf4sqHUPpy6xQG9ByHg/-Tmp-/heyongqiang/hive_2011-04-07_01-29-35_206_4517835727241747847/-mr-10000
+POSTHOOK: query: FROM
+(SELECT src.* FROM src sort by key) x
+JOIN
+(SELECT src.* FROM src sort by value) Y
+ON (x.key = Y.key)
+select sum(hash(Y.key,Y.value))
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+POSTHOOK: Output: file:/var/folders/6g/6grtCwPMEf4sqHUPpy6xQG9ByHg/-Tmp-/heyongqiang/hive_2011-04-07_01-29-35_206_4517835727241747847/-mr-10000
+103231310608
+PREHOOK: query: explain
+FROM
+(SELECT src.* FROM src sort by key) x
+LEFT OUTER JOIN
+(SELECT src.* FROM src sort by value) Y
+ON (x.key = Y.key)
+select sum(hash(Y.key,Y.value))
+PREHOOK: type: QUERY
+POSTHOOK: query: explain
+FROM
+(SELECT src.* FROM src sort by key) x
+LEFT OUTER JOIN
+(SELECT src.* FROM src sort by value) Y
+ON (x.key = Y.key)
+select sum(hash(Y.key,Y.value))
+POSTHOOK: type: QUERY
+ABSTRACT SYNTAX TREE:
+ (TOK_QUERY (TOK_FROM (TOK_LEFTOUTERJOIN (TOK_SUBQUERY (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME src))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_ALLCOLREF (TOK_TABNAME src)))) (TOK_SORTBY (TOK_TABSORTCOLNAMEASC (TOK_TABLE_OR_COL key))))) x) (TOK_SUBQUERY (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME src))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_ALLCOLREF (TOK_TABNAME src)))) (TOK_SORTBY (TOK_TABSORTCOLNAMEASC (TOK_TABLE_OR_COL value))))) 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_FUNCTION sum (TOK_FUNCTION hash (. (TOK_TABLE_OR_COL Y) key) (. (TOK_TABLE_OR_COL Y) value)))))))
+
+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 is a root stage
+
+STAGE PLANS:
+ Stage: Stage-1
+ Map Reduce
+ Alias -> Map Operator Tree:
+ x:src
+ TableScan
+ alias: src
+ Select Operator
+ expressions:
+ expr: key
+ type: string
+ expr: value
+ type: string
+ outputColumnNames: _col0, _col1
+ Reduce Output Operator
+ key expressions:
+ expr: _col0
+ type: string
+ sort order: +
+ tag: -1
+ value expressions:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: string
+ Reduce Operator Tree:
+ Extract
+ 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-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
+ HashTable Sink Operator
+ condition expressions:
+ 0
+ 1 {_col0} {_col1}
+ handleSkewJoin: false
+ keys:
+ 0 [Column[_col0]]
+ 1 [Column[_col0]]
+ Position of Big Table: 0
+
+ Stage: Stage-5
+ Map Reduce
+ Alias -> Map Operator Tree:
+ $INTNAME
+ Map Join Operator
+ condition map:
+ Left Outer Join0 to 1
+ condition expressions:
+ 0
+ 1 {_col0} {_col1}
+ handleSkewJoin: false
+ keys:
+ 0 [Column[_col0]]
+ 1 [Column[_col0]]
+ outputColumnNames: _col2, _col3
+ Position of Big Table: 0
+ Select Operator
+ expressions:
+ expr: _col2
+ type: string
+ expr: _col3
+ type: string
+ outputColumnNames: _col2, _col3
+ Group By Operator
+ aggregations:
+ expr: sum(hash(_col2,_col3))
+ bucketGroup: false
+ mode: hash
+ outputColumnNames: _col0
+ 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-3
+ Map Reduce
+ Alias -> Map Operator Tree:
+ file:/var/folders/6g/6grtCwPMEf4sqHUPpy6xQG9ByHg/-Tmp-/heyongqiang/hive_2011-04-07_01-30-12_697_8776019509777494227/-mr-10003
+ Reduce Output Operator
+ sort order:
+ tag: -1
+ value expressions:
+ expr: _col0
+ type: bigint
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations:
+ expr: sum(VALUE._col0)
+ bucketGroup: false
+ mode: mergepartial
+ outputColumnNames: _col0
+ Select Operator
+ expressions:
+ expr: _col0
+ type: bigint
+ outputColumnNames: _col0
+ 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-2
+ Map Reduce
+ Alias -> Map Operator Tree:
+ $INTNAME
+ Reduce Output Operator
+ key expressions:
+ expr: _col0
+ type: string
+ sort order: +
+ Map-reduce partition columns:
+ expr: _col0
+ type: string
+ tag: 0
+ $INTNAME1
+ Reduce Output Operator
+ key expressions:
+ expr: _col0
+ type: string
+ sort order: +
+ Map-reduce partition columns:
+ expr: _col0
+ type: string
+ tag: 1
+ value expressions:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: string
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Left Outer Join0 to 1
+ condition expressions:
+ 0
+ 1 {VALUE._col0} {VALUE._col1}
+ handleSkewJoin: false
+ outputColumnNames: _col2, _col3
+ Select Operator
+ expressions:
+ expr: _col2
+ type: string
+ expr: _col3
+ type: string
+ outputColumnNames: _col2, _col3
+ Group By Operator
+ aggregations:
+ expr: sum(hash(_col2,_col3))
+ bucketGroup: false
+ mode: hash
+ outputColumnNames: _col0
+ 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-4
+ Map Reduce
+ Alias -> Map Operator Tree:
+ y:src
+ TableScan
+ alias: src
+ Select Operator
+ expressions:
+ expr: key
+ type: string
+ expr: value
+ type: string
+ outputColumnNames: _col0, _col1
+ Reduce Output Operator
+ key expressions:
+ expr: _col1
+ type: string
+ sort order: +
+ tag: -1
+ value expressions:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: string
+ Reduce Operator Tree:
+ Extract
+ 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-0
+ Fetch Operator
+ limit: -1
+
+
+PREHOOK: query: FROM
+(SELECT src.* FROM src sort by key) x
+LEFT OUTER JOIN
+(SELECT src.* FROM src sort by value) Y
+ON (x.key = Y.key)
+select sum(hash(Y.key,Y.value))
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+PREHOOK: Output: file:/var/folders/6g/6grtCwPMEf4sqHUPpy6xQG9ByHg/-Tmp-/heyongqiang/hive_2011-04-07_01-30-13_659_8930056926219050163/-mr-10000
+POSTHOOK: query: FROM
+(SELECT src.* FROM src sort by key) x
+LEFT OUTER JOIN
+(SELECT src.* FROM src sort by value) Y
+ON (x.key = Y.key)
+select sum(hash(Y.key,Y.value))
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+POSTHOOK: Output: file:/var/folders/6g/6grtCwPMEf4sqHUPpy6xQG9ByHg/-Tmp-/heyongqiang/hive_2011-04-07_01-30-13_659_8930056926219050163/-mr-10000
+103231310608
+PREHOOK: query: explain
+FROM
+(SELECT src.* FROM src sort by key) x
+RIGHT OUTER JOIN
+(SELECT src.* FROM src sort by value) Y
+ON (x.key = Y.key)
+select sum(hash(Y.key,Y.value))
+PREHOOK: type: QUERY
+POSTHOOK: query: explain
+FROM
+(SELECT src.* FROM src sort by key) x
+RIGHT OUTER JOIN
+(SELECT src.* FROM src sort by value) Y
+ON (x.key = Y.key)
+select sum(hash(Y.key,Y.value))
+POSTHOOK: type: QUERY
+ABSTRACT SYNTAX TREE:
+ (TOK_QUERY (TOK_FROM (TOK_RIGHTOUTERJOIN (TOK_SUBQUERY (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME src))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_ALLCOLREF (TOK_TABNAME src)))) (TOK_SORTBY (TOK_TABSORTCOLNAMEASC (TOK_TABLE_OR_COL key))))) x) (TOK_SUBQUERY (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME src))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_ALLCOLREF (TOK_TABNAME src)))) (TOK_SORTBY (TOK_TABSORTCOLNAMEASC (TOK_TABLE_OR_COL value))))) 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_FUNCTION sum (TOK_FUNCTION hash (. (TOK_TABLE_OR_COL Y) key) (. (TOK_TABLE_OR_COL Y) value)))))))
+
+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 is a root stage
+
+STAGE PLANS:
+ Stage: Stage-1
+ Map Reduce
+ Alias -> Map Operator Tree:
+ x:src
+ TableScan
+ alias: src
+ Select Operator
+ expressions:
+ expr: key
+ type: string
+ expr: value
+ type: string
+ outputColumnNames: _col0, _col1
+ Reduce Output Operator
+ key expressions:
+ expr: _col0
+ type: string
+ sort order: +
+ tag: -1
+ value expressions:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: string
+ Reduce Operator Tree:
+ Extract
+ 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-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
+ HashTable Sink Operator
+ condition expressions:
+ 0
+ 1 {_col0} {_col1}
+ handleSkewJoin: false
+ keys:
+ 0 [Column[_col0]]
+ 1 [Column[_col0]]
+ Position of Big Table: 1
+
+ Stage: Stage-5
+ Map Reduce
+ Alias -> Map Operator Tree:
+ $INTNAME1
+ Map Join Operator
+ condition map:
+ Right Outer Join0 to 1
+ condition expressions:
+ 0
+ 1 {_col0} {_col1}
+ handleSkewJoin: false
+ keys:
+ 0 [Column[_col0]]
+ 1 [Column[_col0]]
+ outputColumnNames: _col2, _col3
+ Position of Big Table: 1
+ Select Operator
+ expressions:
+ expr: _col2
+ type: string
+ expr: _col3
+ type: string
+ outputColumnNames: _col2, _col3
+ Group By Operator
+ aggregations:
+ expr: sum(hash(_col2,_col3))
+ bucketGroup: false
+ mode: hash
+ outputColumnNames: _col0
+ 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-3
+ Map Reduce
+ Alias -> Map Operator Tree:
+ file:/var/folders/6g/6grtCwPMEf4sqHUPpy6xQG9ByHg/-Tmp-/heyongqiang/hive_2011-04-07_01-30-45_367_2576785772484562232/-mr-10003
+ Reduce Output Operator
+ sort order:
+ tag: -1
+ value expressions:
+ expr: _col0
+ type: bigint
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations:
+ expr: sum(VALUE._col0)
+ bucketGroup: false
+ mode: mergepartial
+ outputColumnNames: _col0
+ Select Operator
+ expressions:
+ expr: _col0
+ type: bigint
+ outputColumnNames: _col0
+ 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-2
+ Map Reduce
+ Alias -> Map Operator Tree:
+ $INTNAME
+ Reduce Output Operator
+ key expressions:
+ expr: _col0
+ type: string
+ sort order: +
+ Map-reduce partition columns:
+ expr: _col0
+ type: string
+ tag: 0
+ $INTNAME1
+ Reduce Output Operator
+ key expressions:
+ expr: _col0
+ type: string
+ sort order: +
+ Map-reduce partition columns:
+ expr: _col0
+ type: string
+ tag: 1
+ value expressions:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: string
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Right Outer Join0 to 1
+ condition expressions:
+ 0
+ 1 {VALUE._col0} {VALUE._col1}
+ handleSkewJoin: false
+ outputColumnNames: _col2, _col3
+ Select Operator
+ expressions:
+ expr: _col2
+ type: string
+ expr: _col3
+ type: string
+ outputColumnNames: _col2, _col3
+ Group By Operator
+ aggregations:
+ expr: sum(hash(_col2,_col3))
+ bucketGroup: false
+ mode: hash
+ outputColumnNames: _col0
+ 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-4
+ Map Reduce
+ Alias -> Map Operator Tree:
+ y:src
+ TableScan
+ alias: src
+ Select Operator
+ expressions:
+ expr: key
+ type: string
+ expr: value
+ type: string
+ outputColumnNames: _col0, _col1
+ Reduce Output Operator
+ key expressions:
+ expr: _col1
+ type: string
+ sort order: +
+ tag: -1
+ value expressions:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: string
+ Reduce Operator Tree:
+ Extract
+ 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-0
+ Fetch Operator
+ limit: -1
+
+
+PREHOOK: query: FROM
+(SELECT src.* FROM src sort by key) x
+RIGHT OUTER JOIN
+(SELECT src.* FROM src sort by value) Y
+ON (x.key = Y.key)
+select sum(hash(Y.key,Y.value))
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+PREHOOK: Output: file:/var/folders/6g/6grtCwPMEf4sqHUPpy6xQG9ByHg/-Tmp-/heyongqiang/hive_2011-04-07_01-30-45_713_4388632692386585223/-mr-10000
+POSTHOOK: query: FROM
+(SELECT src.* FROM src sort by key) x
+RIGHT OUTER JOIN
+(SELECT src.* FROM src sort by value) Y
+ON (x.key = Y.key)
+select sum(hash(Y.key,Y.value))
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+POSTHOOK: Output: file:/var/folders/6g/6grtCwPMEf4sqHUPpy6xQG9ByHg/-Tmp-/heyongqiang/hive_2011-04-07_01-30-45_713_4388632692386585223/-mr-10000
+103231310608
+PREHOOK: query: explain
+FROM
+(SELECT src.* FROM src sort by key) x
+JOIN
+(SELECT src.* FROM src sort by value) Y
+ON (x.key = Y.key)
+JOIN
+(SELECT src.* FROM src sort by value) Z
+ON (x.key = Z.key)
+select sum(hash(Y.key,Y.value))
+PREHOOK: type: QUERY
+POSTHOOK: query: explain
+FROM
+(SELECT src.* FROM src sort by key) x
+JOIN
+(SELECT src.* FROM src sort by value) Y
+ON (x.key = Y.key)
+JOIN
+(SELECT src.* FROM src sort by value) Z
+ON (x.key = Z.key)
+select sum(hash(Y.key,Y.value))
+POSTHOOK: type: QUERY
+ABSTRACT SYNTAX TREE:
+ (TOK_QUERY (TOK_FROM (TOK_JOIN (TOK_JOIN (TOK_SUBQUERY (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME src))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_ALLCOLREF (TOK_TABNAME src)))) (TOK_SORTBY (TOK_TABSORTCOLNAMEASC (TOK_TABLE_OR_COL key))))) x) (TOK_SUBQUERY (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME src))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_ALLCOLREF (TOK_TABNAME src)))) (TOK_SORTBY (TOK_TABSORTCOLNAMEASC (TOK_TABLE_OR_COL value))))) Y) (= (. (TOK_TABLE_OR_COL x) key) (. (TOK_TABLE_OR_COL Y) key))) (TOK_SUBQUERY (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME src))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_ALLCOLREF (TOK_TABNAME src)))) (TOK_SORTBY (TOK_TABSORTCOLNAMEASC (TOK_TABLE_OR_COL value))))) Z) (= (. (TOK_TABLE_OR_COL x) key) (. (TOK_TABLE_OR_COL Z) key)))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR
(TOK_FUNCTION sum (TOK_FUNCTION hash (. (TOK_TABLE_OR_COL Y) key) (. (TOK_TABLE_OR_COL Y) value)))))))
+
+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 is a root stage
+
+STAGE PLANS:
+ Stage: Stage-1
+ Map Reduce
+ Alias -> Map Operator Tree:
+ z:src
+ TableScan
+ alias: src
+ Select Operator
+ expressions:
+ expr: key
+ type: string
+ expr: value
+ type: string
+ outputColumnNames: _col0, _col1
+ Reduce Output Operator
+ key expressions:
+ expr: _col1
+ type: string
+ sort order: +
+ tag: -1
+ value expressions:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: string
+ Reduce Operator Tree:
+ Extract
+ 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-9
+ Conditional Operator
+
+ 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
+ HashTable Sink Operator
+ condition expressions:
+ 0
+ 1 {_col0} {_col1}
+ 2
+ handleSkewJoin: false
+ keys:
+ 0 [Column[_col0]]
+ 1 [Column[_col0]]
+ 2 [Column[_col0]]
+ Position of Big Table: 0
+ $INTNAME2
+ HashTable Sink Operator
+ condition expressions:
+ 0
+ 1 {_col0} {_col1}
+ 2
+ handleSkewJoin: false
+ keys:
+ 0 [Column[_col0]]
+ 1 [Column[_col0]]
+ 2 [Column[_col0]]
+ Position of Big Table: 0
+
+ Stage: Stage-6
+ Map Reduce
+ Alias -> Map Operator Tree:
+ $INTNAME1
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ Inner Join 0 to 2
+ condition expressions:
+ 0
+ 1 {_col0} {_col1}
+ 2
+ handleSkewJoin: false
+ keys:
+ 0 [Column[_col0]]
+ 1 [Column[_col0]]
+ 2 [Column[_col0]]
+ outputColumnNames: _col2, _col3
+ Position of Big Table: 0
+ Select Operator
+ expressions:
+ expr: _col2
+ type: string
+ expr: _col3
+ type: string
+ outputColumnNames: _col2, _col3
+ Group By Operator
+ aggregations:
+ expr: sum(hash(_col2,_col3))
+ bucketGroup: false
+ mode: hash
+ outputColumnNames: _col0
+ 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-3
+ Map Reduce
+ Alias -> Map Operator Tree:
+ file:/var/folders/6g/6grtCwPMEf4sqHUPpy6xQG9ByHg/-Tmp-/heyongqiang/hive_2011-04-07_01-31-13_566_5103248435836603181/-mr-10003
+ Reduce Output Operator
+ sort order:
+ tag: -1
+ value expressions:
+ expr: _col0
+ type: bigint
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations:
+ expr: sum(VALUE._col0)
+ bucketGroup: false
+ mode: mergepartial
+ outputColumnNames: _col0
+ Select Operator
+ expressions:
+ expr: _col0
+ type: bigint
+ outputColumnNames: _col0
+ 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-11
+ Map Reduce Local Work
+ Alias -> Map Local Tables:
+ $INTNAME
+ Fetch Operator
+ limit: -1
+ $INTNAME1
+ Fetch Operator
+ limit: -1
+ Alias -> Map Local Operator Tree:
+ $INTNAME
+ HashTable Sink Operator
+ condition expressions:
+ 0
+ 1 {_col0} {_col1}
+ 2
+ handleSkewJoin: false
+ keys:
+ 0 [Column[_col0]]
+ 1 [Column[_col0]]
+ 2 [Column[_col0]]
+ Position of Big Table: 1
+ $INTNAME1
+ HashTable Sink Operator
+ condition expressions:
+ 0
+ 1 {_col0} {_col1}
+ 2
+ handleSkewJoin: false
+ keys:
+ 0 [Column[_col0]]
+ 1 [Column[_col0]]
+ 2 [Column[_col0]]
+ Position of Big Table: 1
+
+ Stage: Stage-7
+ Map Reduce
+ Alias -> Map Operator Tree:
+ $INTNAME2
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ Inner Join 0 to 2
+ condition expressions:
+ 0
+ 1 {_col0} {_col1}
+ 2
+ handleSkewJoin: false
+ keys:
+ 0 [Column[_col0]]
+ 1 [Column[_col0]]
+ 2 [Column[_col0]]
+ outputColumnNames: _col2, _col3
+ Position of Big Table: 1
+ Select Operator
+ expressions:
+ expr: _col2
+ type: string
+ expr: _col3
+ type: string
+ outputColumnNames: _col2, _col3
+ Group By Operator
+ aggregations:
+ expr: sum(hash(_col2,_col3))
+ bucketGroup: false
+ mode: hash
+ outputColumnNames: _col0
+ 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-12
+ Map Reduce Local Work
+ Alias -> Map Local Tables:
+ $INTNAME1
+ Fetch Operator
+ limit: -1
+ $INTNAME2
+ Fetch Operator
+ limit: -1
+ Alias -> Map Local Operator Tree:
+ $INTNAME1
+ HashTable Sink Operator
+ condition expressions:
+ 0
+ 1 {_col0} {_col1}
+ 2
+ handleSkewJoin: false
+ keys:
+ 0 [Column[_col0]]
+ 1 [Column[_col0]]
+ 2 [Column[_col0]]
+ Position of Big Table: 2
+ $INTNAME2
+ HashTable Sink Operator
+ condition expressions:
+ 0
+ 1 {_col0} {_col1}
+ 2
+ handleSkewJoin: false
+ keys:
+ 0 [Column[_col0]]
+ 1 [Column[_col0]]
+ 2 [Column[_col0]]
+ Position of Big Table: 2
+
+ Stage: Stage-8
+ Map Reduce
+ Alias -> Map Operator Tree:
+ $INTNAME
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ Inner Join 0 to 2
+ condition expressions:
+ 0
+ 1 {_col0} {_col1}
+ 2
+ handleSkewJoin: false
+ keys:
+ 0 [Column[_col0]]
+ 1 [Column[_col0]]
+ 2 [Column[_col0]]
+ outputColumnNames: _col2, _col3
+ Position of Big Table: 2
+ Select Operator
+ expressions:
+ expr: _col2
+ type: string
+ expr: _col3
+ type: string
+ outputColumnNames: _col2, _col3
+ Group By Operator
+ aggregations:
+ expr: sum(hash(_col2,_col3))
+ bucketGroup: false
+ mode: hash
+ outputColumnNames: _col0
+ 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:
+ $INTNAME
+ Reduce Output Operator
+ key expressions:
+ expr: _col0
+ type: string
+ sort order: +
+ Map-reduce partition columns:
+ expr: _col0
+ type: string
+ tag: 2
+ $INTNAME1
+ Reduce Output Operator
+ key expressions:
+ expr: _col0
+ type: string
+ sort order: +
+ Map-reduce partition columns:
+ expr: _col0
+ type: string
+ tag: 0
+ $INTNAME2
+ Reduce Output Operator
+ key expressions:
+ expr: _col0
+ type: string
+ sort order: +
+ Map-reduce partition columns:
+ expr: _col0
+ type: string
+ tag: 1
+ value expressions:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: string
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ Inner Join 0 to 2
+ condition expressions:
+ 0
+ 1 {VALUE._col0} {VALUE._col1}
+ 2
+ handleSkewJoin: false
+ outputColumnNames: _col2, _col3
+ Select Operator
+ expressions:
+ expr: _col2
+ type: string
+ expr: _col3
+ type: string
+ outputColumnNames: _col2, _col3
+ Group By Operator
+ aggregations:
+ expr: sum(hash(_col2,_col3))
+ bucketGroup: false
+ mode: hash
+ outputColumnNames: _col0
+ 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-4
+ Map Reduce
+ Alias -> Map Operator Tree:
+ x:src
+ TableScan
+ alias: src
+ Select Operator
+ expressions:
+ expr: key
+ type: string
+ expr: value
+ type: string
+ outputColumnNames: _col0, _col1
+ Reduce Output Operator
+ key expressions:
+ expr: _col0
+ type: string
+ sort order: +
+ tag: -1
+ value expressions:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: string
+ Reduce Operator Tree:
+ Extract
+ 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-5
+ Map Reduce
+ Alias -> Map Operator Tree:
+ y:src
+ TableScan
+ alias: src
+ Select Operator
+ expressions:
+ expr: key
+ type: string
+ expr: value
+ type: string
+ outputColumnNames: _col0, _col1
+ Reduce Output Operator
+ key expressions:
+ expr: _col1
+ type: string
+ sort order: +
+ tag: -1
+ value expressions:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: string
+ Reduce Operator Tree:
+ Extract
+ 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-0
+ Fetch Operator
+ limit: -1
+
+
+PREHOOK: query: FROM
+(SELECT src.* FROM src sort by key) x
+JOIN
+(SELECT src.* FROM src sort by value) Y
+ON (x.key = Y.key)
+JOIN
+(SELECT src.* FROM src sort by value) Z
+ON (x.key = Z.key)
+select sum(hash(Y.key,Y.value))
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+PREHOOK: Output: file:/var/folders/6g/6grtCwPMEf4sqHUPpy6xQG9ByHg/-Tmp-/heyongqiang/hive_2011-04-07_01-31-14_078_677078805297192158/-mr-10000
+POSTHOOK: query: FROM
+(SELECT src.* FROM src sort by key) x
+JOIN
+(SELECT src.* FROM src sort by value) Y
+ON (x.key = Y.key)
+JOIN
+(SELECT src.* FROM src sort by value) Z
+ON (x.key = Z.key)
+select sum(hash(Y.key,Y.value))
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+POSTHOOK: Output: file:/var/folders/6g/6grtCwPMEf4sqHUPpy6xQG9ByHg/-Tmp-/heyongqiang/hive_2011-04-07_01-31-14_078_677078805297192158/-mr-10000
+348019368476
+PREHOOK: query: explain
+FROM
+(SELECT src.* FROM src sort by key) x
+JOIN
+(SELECT src.* FROM src sort by value) Y
+ON (x.key = Y.key)
+LEFT OUTER JOIN
+(SELECT src.* FROM src sort by value) Z
+ON (x.key = Z.key)
+select sum(hash(Y.key,Y.value))
+PREHOOK: type: QUERY
+POSTHOOK: query: explain
+FROM
+(SELECT src.* FROM src sort by key) x
+JOIN
+(SELECT src.* FROM src sort by value) Y
+ON (x.key = Y.key)
+LEFT OUTER JOIN
+(SELECT src.* FROM src sort by value) Z
+ON (x.key = Z.key)
+select sum(hash(Y.key,Y.value))
+POSTHOOK: type: QUERY
+ABSTRACT SYNTAX TREE:
+ (TOK_QUERY (TOK_FROM (TOK_LEFTOUTERJOIN (TOK_JOIN (TOK_SUBQUERY (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME src))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_ALLCOLREF (TOK_TABNAME src)))) (TOK_SORTBY (TOK_TABSORTCOLNAMEASC (TOK_TABLE_OR_COL key))))) x) (TOK_SUBQUERY (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME src))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_ALLCOLREF (TOK_TABNAME src)))) (TOK_SORTBY (TOK_TABSORTCOLNAMEASC (TOK_TABLE_OR_COL value))))) Y) (= (. (TOK_TABLE_OR_COL x) key) (. (TOK_TABLE_OR_COL Y) key))) (TOK_SUBQUERY (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME src))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_ALLCOLREF (TOK_TABNAME src)))) (TOK_SORTBY (TOK_TABSORTCOLNAMEASC (TOK_TABLE_OR_COL value))))) Z) (= (. (TOK_TABLE_OR_COL x) key) (. (TOK_TABLE_OR_COL Z) key)))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TO
K_SELEXPR (TOK_FUNCTION sum (TOK_FUNCTION hash (. (TOK_TABLE_OR_COL Y) key) (. (TOK_TABLE_OR_COL Y) value)))))))
+
+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 is a root stage
+
+STAGE PLANS:
+ Stage: Stage-1
+ Map Reduce
+ Alias -> Map Operator Tree:
+ z:src
+ TableScan
+ alias: src
+ Select Operator
+ expressions:
+ expr: key
+ type: string
+ expr: value
+ type: string
+ outputColumnNames: _col0, _col1
+ Reduce Output Operator
+ key expressions:
+ expr: _col1
+ type: string
+ sort order: +
+ tag: -1
+ value expressions:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: string
+ Reduce Operator Tree:
+ Extract
+ 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-8
+ Conditional Operator
+
+ Stage: Stage-9
+ Map Reduce Local Work
+ Alias -> Map Local Tables:
+ $INTNAME
+ Fetch Operator
+ limit: -1
+ $INTNAME2
+ Fetch Operator
+ limit: -1
+ Alias -> Map Local Operator Tree:
+ $INTNAME
+ HashTable Sink Operator
+ condition expressions:
+ 0
+ 1 {_col0} {_col1}
+ 2
+ handleSkewJoin: false
+ keys:
+ 0 [Column[_col0]]
+ 1 [Column[_col0]]
+ 2 [Column[_col0]]
+ Position of Big Table: 0
+ $INTNAME2
+ HashTable Sink Operator
+ condition expressions:
+ 0
+ 1 {_col0} {_col1}
+ 2
+ handleSkewJoin: false
+ keys:
+ 0 [Column[_col0]]
+ 1 [Column[_col0]]
+ 2 [Column[_col0]]
+ Position of Big Table: 0
+
+ Stage: Stage-6
+ Map Reduce
+ Alias -> Map Operator Tree:
+ $INTNAME1
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ Left Outer Join0 to 2
+ condition expressions:
+ 0
+ 1 {_col0} {_col1}
+ 2
+ handleSkewJoin: false
+ keys:
+ 0 [Column[_col0]]
+ 1 [Column[_col0]]
+ 2 [Column[_col0]]
+ outputColumnNames: _col2, _col3
+ Position of Big Table: 0
+ Select Operator
+ expressions:
+ expr: _col2
+ type: string
+ expr: _col3
+ type: string
+ outputColumnNames: _col2, _col3
+ Group By Operator
+ aggregations:
+ expr: sum(hash(_col2,_col3))
+ bucketGroup: false
+ mode: hash
+ outputColumnNames: _col0
+ 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-3
+ Map Reduce
+ Alias -> Map Operator Tree:
+ file:/var/folders/6g/6grtCwPMEf4sqHUPpy6xQG9ByHg/-Tmp-/heyongqiang/hive_2011-04-07_01-31-51_136_1396644593331730058/-mr-10003
+ Reduce Output Operator
+ sort order:
+ tag: -1
+ value expressions:
+ expr: _col0
+ type: bigint
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations:
+ expr: sum(VALUE._col0)
+ bucketGroup: false
+ mode: mergepartial
+ outputColumnNames: _col0
+ Select Operator
+ expressions:
+ expr: _col0
+ type: bigint
+ outputColumnNames: _col0
+ 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-10
+ Map Reduce Local Work
+ Alias -> Map Local Tables:
+ $INTNAME
+ Fetch Operator
+ limit: -1
+ $INTNAME1
+ Fetch Operator
+ limit: -1
+ Alias -> Map Local Operator Tree:
+ $INTNAME
+ HashTable Sink Operator
+ condition expressions:
+ 0
+ 1 {_col0} {_col1}
+ 2
+ handleSkewJoin: false
+ keys:
+ 0 [Column[_col0]]
+ 1 [Column[_col0]]
+ 2 [Column[_col0]]
+ Position of Big Table: 1
+ $INTNAME1
+ HashTable Sink Operator
+ condition expressions:
+ 0
+ 1 {_col0} {_col1}
+ 2
+ handleSkewJoin: false
+ keys:
+ 0 [Column[_col0]]
+ 1 [Column[_col0]]
+ 2 [Column[_col0]]
+ Position of Big Table: 1
+
+ Stage: Stage-7
+ Map Reduce
+ Alias -> Map Operator Tree:
+ $INTNAME2
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ Left Outer Join0 to 2
+ condition expressions:
+ 0
+ 1 {_col0} {_col1}
+ 2
+ handleSkewJoin: false
+ keys:
+ 0 [Column[_col0]]
+ 1 [Column[_col0]]
+ 2 [Column[_col0]]
+ outputColumnNames: _col2, _col3
+ Position of Big Table: 1
+ Select Operator
+ expressions:
+ expr: _col2
+ type: string
+ expr: _col3
+ type: string
+ outputColumnNames: _col2, _col3
+ Group By Operator
+ aggregations:
+ expr: sum(hash(_col2,_col3))
+ bucketGroup: false
+ mode: hash
+ outputColumnNames: _col0
+ 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:
+ $INTNAME
+ Reduce Output Operator
+ key expressions:
+ expr: _col0
+ type: string
+ sort order: +
+ Map-reduce partition columns:
+ expr: _col0
+ type: string
+ tag: 2
+ $INTNAME1
+ Reduce Output Operator
+ key expressions:
+ expr: _col0
+ type: string
+ sort order: +
+ Map-reduce partition columns:
+ expr: _col0
+ type: string
+ tag: 0
+ $INTNAME2
+ Reduce Output Operator
+ key expressions:
+ expr: _col0
+ type: string
+ sort order: +
+ Map-reduce partition columns:
+ expr: _col0
+ type: string
+ tag: 1
+ value expressions:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: string
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ Left Outer Join0 to 2
+ condition expressions:
+ 0
+ 1 {VALUE._col0} {VALUE._col1}
+ 2
+ handleSkewJoin: false
+ outputColumnNames: _col2, _col3
+ Select Operator
+ expressions:
+ expr: _col2
+ type: string
+ expr: _col3
+ type: string
+ outputColumnNames: _col2, _col3
+ Group By Operator
+ aggregations:
+ expr: sum(hash(_col2,_col3))
+ bucketGroup: false
+ mode: hash
+ outputColumnNames: _col0
+ 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-4
+ Map Reduce
+ Alias -> Map Operator Tree:
+ x:src
+ TableScan
+ alias: src
+ Select Operator
+ expressions:
+ expr: key
+ type: string
+ expr: value
+ type: string
+ outputColumnNames: _col0, _col1
+ Reduce Output Operator
+ key expressions:
+ expr: _col0
+ type: string
+ sort order: +
+ tag: -1
+ value expressions:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: string
+ Reduce Operator Tree:
+ Extract
+ 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-5
+ Map Reduce
+ Alias -> Map Operator Tree:
+ y:src
+ TableScan
+ alias: src
+ Select Operator
+ expressions:
+ expr: key
+ type: string
+ expr: value
+ type: string
+ outputColumnNames: _col0, _col1
+ Reduce Output Operator
+ key expressions:
+ expr: _col1
+ type: string
+ sort order: +
+ tag: -1
+ value expressions:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: string
+ Reduce Operator Tree:
+ Extract
+ 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-0
+ Fetch Operator
+ limit: -1
+
+
+PREHOOK: query: FROM
+(SELECT src.* FROM src sort by key) x
+JOIN
+(SELECT src.* FROM src sort by value) Y
+ON (x.key = Y.key)
+LEFT OUTER JOIN
+(SELECT src.* FROM src sort by value) Z
+ON (x.key = Z.key)
+select sum(hash(Y.key,Y.value))
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+PREHOOK: Output: file:/var/folders/6g/6grtCwPMEf4sqHUPpy6xQG9ByHg/-Tmp-/heyongqiang/hive_2011-04-07_01-31-51_734_4658432184476577096/-mr-10000
+POSTHOOK: query: FROM
+(SELECT src.* FROM src sort by key) x
+JOIN
+(SELECT src.* FROM src sort by value) Y
+ON (x.key = Y.key)
+LEFT OUTER JOIN
+(SELECT src.* FROM src sort by value) Z
+ON (x.key = Z.key)
+select sum(hash(Y.key,Y.value))
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+POSTHOOK: Output: file:/var/folders/6g/6grtCwPMEf4sqHUPpy6xQG9ByHg/-Tmp-/heyongqiang/hive_2011-04-07_01-31-51_734_4658432184476577096/-mr-10000
+348019368476
+PREHOOK: query: explain
+FROM
+(SELECT src.* FROM src sort by key) x
+LEFT OUTER JOIN
+(SELECT src.* FROM src sort by value) Y
+ON (x.key = Y.key)
+LEFT OUTER JOIN
+(SELECT src.* FROM src sort by value) Z
+ON (x.key = Z.key)
+select sum(hash(Y.key,Y.value))
+PREHOOK: type: QUERY
+POSTHOOK: query: explain
+FROM
+(SELECT src.* FROM src sort by key) x
+LEFT OUTER JOIN
+(SELECT src.* FROM src sort by value) Y
+ON (x.key = Y.key)
+LEFT OUTER JOIN
+(SELECT src.* FROM src sort by value) Z
+ON (x.key = Z.key)
+select sum(hash(Y.key,Y.value))
+POSTHOOK: type: QUERY
+ABSTRACT SYNTAX TREE:
+ (TOK_QUERY (TOK_FROM (TOK_LEFTOUTERJOIN (TOK_LEFTOUTERJOIN (TOK_SUBQUERY (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME src))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_ALLCOLREF (TOK_TABNAME src)))) (TOK_SORTBY (TOK_TABSORTCOLNAMEASC (TOK_TABLE_OR_COL key))))) x) (TOK_SUBQUERY (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME src))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_ALLCOLREF (TOK_TABNAME src)))) (TOK_SORTBY (TOK_TABSORTCOLNAMEASC (TOK_TABLE_OR_COL value))))) Y) (= (. (TOK_TABLE_OR_COL x) key) (. (TOK_TABLE_OR_COL Y) key))) (TOK_SUBQUERY (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME src))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_ALLCOLREF (TOK_TABNAME src)))) (TOK_SORTBY (TOK_TABSORTCOLNAMEASC (TOK_TABLE_OR_COL value))))) Z) (= (. (TOK_TABLE_OR_COL x) key) (. (TOK_TABLE_OR_COL Z) key)))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_S
ELECT (TOK_SELEXPR (TOK_FUNCTION sum (TOK_FUNCTION hash (. (TOK_TABLE_OR_COL Y) key) (. (TOK_TABLE_OR_COL Y) value)))))))
+
+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 is a root stage
+
+STAGE PLANS:
+ Stage: Stage-1
+ Map Reduce
+ Alias -> Map Operator Tree:
+ z:src
+ TableScan
+ alias: src
+ Select Operator
+ expressions:
+ expr: key
+ type: string
+ expr: value
+ type: string
+ outputColumnNames: _col0, _col1
+ Reduce Output Operator
+ key expressions:
+ expr: _col1
+ type: string
+ sort order: +
+ tag: -1
+ value expressions:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: string
+ Reduce Operator Tree:
+ Extract
+ 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-7
+ Conditional Operator
+
+ Stage: Stage-8
+ Map Reduce Local Work
+ Alias -> Map Local Tables:
+ $INTNAME
+ Fetch Operator
+ limit: -1
+ $INTNAME2
+ Fetch Operator
+ limit: -1
+ Alias -> Map Local Operator Tree:
+ $INTNAME
+ HashTable Sink Operator
+ condition expressions:
+ 0
+ 1 {_col0} {_col1}
+ 2
+ handleSkewJoin: false
+ keys:
+ 0 [Column[_col0]]
+ 1 [Column[_col0]]
+ 2 [Column[_col0]]
+ Position of Big Table: 0
+ $INTNAME2
+ HashTable Sink Operator
+ condition expressions:
+ 0
+ 1 {_col0} {_col1}
+ 2
+ handleSkewJoin: false
+ keys:
+ 0 [Column[_col0]]
+ 1 [Column[_col0]]
+ 2 [Column[_col0]]
+ Position of Big Table: 0
+
+ Stage: Stage-6
+ Map Reduce
+ Alias -> Map Operator Tree:
+ $INTNAME1
+ Map Join Operator
+ condition map:
+ Left Outer Join0 to 1
+ Left Outer Join0 to 2
+ condition expressions:
+ 0
+ 1 {_col0} {_col1}
+ 2
+ handleSkewJoin: false
+ keys:
+ 0 [Column[_col0]]
+ 1 [Column[_col0]]
+ 2 [Column[_col0]]
+ outputColumnNames: _col2, _col3
+ Position of Big Table: 0
+ Select Operator
+ expressions:
+ expr: _col2
+ type: string
+ expr: _col3
+ type: string
+ outputColumnNames: _col2, _col3
+ Group By Operator
+ aggregations:
+ expr: sum(hash(_col2,_col3))
+ bucketGroup: false
+ mode: hash
+ outputColumnNames: _col0
+ 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-3
+ Map Reduce
+ Alias -> Map Operator Tree:
+ file:/var/folders/6g/6grtCwPMEf4sqHUPpy6xQG9ByHg/-Tmp-/heyongqiang/hive_2011-04-07_01-32-27_283_8537497135418357852/-mr-10003
+ Reduce Output Operator
+ sort order:
+ tag: -1
+ value expressions:
+ expr: _col0
+ type: bigint
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations:
+ expr: sum(VALUE._col0)
+ bucketGroup: false
+ mode: mergepartial
+ outputColumnNames: _col0
+ Select Operator
+ expressions:
+ expr: _col0
+ type: bigint
+ outputColumnNames: _col0
+ 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-2
+ Map Reduce
+ Alias -> Map Operator Tree:
+ $INTNAME
+ Reduce Output Operator
+ key expressions:
+ expr: _col0
+ type: string
+ sort order: +
+ Map-reduce partition columns:
+ expr: _col0
+ type: string
+ tag: 2
+ $INTNAME1
+ Reduce Output Operator
+ key expressions:
+ expr: _col0
+ type: string
+ sort order: +
+ Map-reduce partition columns:
+ expr: _col0
+ type: string
+ tag: 0
+ $INTNAME2
+ Reduce Output Operator
+ key expressions:
+ expr: _col0
+ type: string
+ sort order: +
+ Map-reduce partition columns:
+ expr: _col0
+ type: string
+ tag: 1
+ value expressions:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: string
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Left Outer Join0 to 1
+ Left Outer Join0 to 2
+ condition expressions:
+ 0
+ 1 {VALUE._col0} {VALUE._col1}
+ 2
+ handleSkewJoin: false
+ outputColumnNames: _col2, _col3
+ Select Operator
+ expressions:
+ expr: _col2
+ type: string
+ expr: _col3
+ type: string
+ outputColumnNames: _col2, _col3
+ Group By Operator
+ aggregations:
+ expr: sum(hash(_col2,_col3))
+ bucketGroup: false
+ mode: hash
+ outputColumnNames: _col0
+ 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-4
+ Map Reduce
+ Alias -> Map Operator Tree:
+ x:src
+ TableScan
+ alias: src
+ Select Operator
+ expressions:
+ expr: key
+ type: string
+ expr: value
+ type: string
+ outputColumnNames: _col0, _col1
+ Reduce Output Operator
+ key expressions:
+ expr: _col0
+ type: string
+ sort order: +
+ tag: -1
+ value expressions:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: string
+ Reduce Operator Tree:
+ Extract
+ 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-5
+ Map Reduce
+ Alias -> Map Operator Tree:
+ y:src
+ TableScan
+ alias: src
+ Select Operator
+ expressions:
+ expr: key
+ type: string
+ expr: value
+ type: string
+ outputColumnNames: _col0, _col1
+ Reduce Output Operator
+ key expressions:
+ expr: _col1
+ type: string
+ sort order: +
+ tag: -1
+ value expressions:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: string
+ Reduce Operator Tree:
+ Extract
+ 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-0
+ Fetch Operator
+ limit: -1
+
+
+PREHOOK: query: FROM
+(SELECT src.* FROM src sort by key) x
+LEFT OUTER JOIN
+(SELECT src.* FROM src sort by value) Y
+ON (x.key = Y.key)
+LEFT OUTER JOIN
+(SELECT src.* FROM src sort by value) Z
+ON (x.key = Z.key)
+select sum(hash(Y.key,Y.value))
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+PREHOOK: Output: file:/var/folders/6g/6grtCwPMEf4sqHUPpy6xQG9ByHg/-Tmp-/heyongqiang/hive_2011-04-07_01-32-27_678_1160688634274021101/-mr-10000
+POSTHOOK: query: FROM
+(SELECT src.* FROM src sort by key) x
+LEFT OUTER JOIN
+(SELECT src.* FROM src sort by value) Y
+ON (x.key = Y.key)
+LEFT OUTER JOIN
+(SELECT src.* FROM src sort by value) Z
+ON (x.key = Z.key)
+select sum(hash(Y.key,Y.value))
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+POSTHOOK: Output: file:/var/folders/6g/6grtCwPMEf4sqHUPpy6xQG9ByHg/-Tmp-/heyongqiang/hive_2011-04-07_01-32-27_678_1160688634274021101/-mr-10000
+348019368476
+PREHOOK: query: explain
+FROM
+(SELECT src.* FROM src sort by key) x
+LEFT OUTER JOIN
+(SELECT src.* FROM src sort by value) Y
+ON (x.key = Y.key)
+RIGHT OUTER JOIN
+(SELECT src.* FROM src sort by value) Z
+ON (x.key = Z.key)
+select sum(hash(Y.key,Y.value))
+PREHOOK: type: QUERY
+POSTHOOK: query: explain
+FROM
+(SELECT src.* FROM src sort by key) x
+LEFT OUTER JOIN
+(SELECT src.* FROM src sort by value) Y
+ON (x.key = Y.key)
+RIGHT OUTER JOIN
+(SELECT src.* FROM src sort by value) Z
+ON (x.key = Z.key)
+select sum(hash(Y.key,Y.value))
+POSTHOOK: type: QUERY
+ABSTRACT SYNTAX TREE:
+ (TOK_QUERY (TOK_FROM (TOK_RIGHTOUTERJOIN (TOK_LEFTOUTERJOIN (TOK_SUBQUERY (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME src))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_ALLCOLREF (TOK_TABNAME src)))) (TOK_SORTBY (TOK_TABSORTCOLNAMEASC (TOK_TABLE_OR_COL key))))) x) (TOK_SUBQUERY (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME src))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_ALLCOLREF (TOK_TABNAME src)))) (TOK_SORTBY (TOK_TABSORTCOLNAMEASC (TOK_TABLE_OR_COL value))))) Y) (= (. (TOK_TABLE_OR_COL x) key) (. (TOK_TABLE_OR_COL Y) key))) (TOK_SUBQUERY (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME src))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_ALLCOLREF (TOK_TABNAME src)))) (TOK_SORTBY (TOK_TABSORTCOLNAMEASC (TOK_TABLE_OR_COL value))))) Z) (= (. (TOK_TABLE_OR_COL x) key) (. (TOK_TABLE_OR_COL Z) key)))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_
SELECT (TOK_SELEXPR (TOK_FUNCTION sum (TOK_FUNCTION hash (. (TOK_TABLE_OR_COL Y) key) (. (TOK_TABLE_OR_COL Y) value)))))))
+
+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 is a root stage
+
+STAGE PLANS:
+ Stage: Stage-1
+ Map Reduce
+ Alias -> Map Operator Tree:
+ z:src
+ TableScan
+ alias: src
+ Select Operator
+ expressions:
+ expr: key
+ type: string
+ expr: value
+ type: string
+ outputColumnNames: _col0, _col1
+ Reduce Output Operator
+ key expressions:
+ expr: _col1
+ type: string
+ sort order: +
+ tag: -1
+ value expressions:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: string
+ Reduce Operator Tree:
+ Extract
+ 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-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
+ HashTable Sink Operator
+ condition expressions:
+ 0
+ 1 {_col0} {_col1}
+ 2
+ handleSkewJoin: false
+ keys:
+ 0 [Column[_col0]]
+ 1 [Column[_col0]]
+ 2 [Column[_col0]]
+ Position of Big Table: 2
+ $INTNAME2
+ HashTable Sink Operator
+ condition expressions:
+ 0
+ 1 {_col0} {_col1}
+ 2
+ handleSkewJoin: false
+ keys:
+ 0 [Column[_col0]]
+ 1 [Column[_col0]]
+ 2 [Column[_col0]]
+ Position of Big Table: 2
+
+ Stage: Stage-6
+ Map Reduce
+ Alias -> Map Operator Tree:
+ $INTNAME
+ Map Join Operator
+ condition map:
+ Left Outer Join0 to 1
+ Right Outer Join0 to 2
+ condition expressions:
+ 0
+ 1 {_col0} {_col1}
+ 2
+ handleSkewJoin: false
+ keys:
+ 0 [Column[_col0]]
+ 1 [Column[_col0]]
+ 2 [Column[_col0]]
+ outputColumnNames: _col2, _col3
+ Position of Big Table: 2
+ Select Operator
+ expressions:
+ expr: _col2
+ type: string
+ expr: _col3
+ type: string
+ outputColumnNames: _col2, _col3
+ Group By Operator
+ aggregations:
+ expr: sum(hash(_col2,_col3))
+ bucketGroup: false
+ mode: hash
+ outputColumnNames: _col0
+ 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-3
+ Map Reduce
+ Alias -> Map Operator Tree:
+ file:/var/folders/6g/6grtCwPMEf4sqHUPpy6xQG9ByHg/-Tmp-/heyongqiang/hive_2011-04-07_01-33-03_110_2221229728249467440/-mr-10003
+ Reduce Output Operator
+ sort order:
+ tag: -1
+ value expressions:
+ expr: _col0
+ type: bigint
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations:
+ expr: sum(VALUE._col0)
+ bucketGroup: false
+ mode: mergepartial
+ outputColumnNames: _col0
+ Select Operator
+ expressions:
+ expr: _col0
+ type: bigint
+ outputColumnNames: _col0
+ 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-2
+ Map Reduce
+ Alias -> Map Operator Tree:
+ $INTNAME
+ Reduce Output Operator
+ key expressions:
+ expr: _col0
+ type: string
+ sort order: +
+ Map-reduce partition columns:
+ expr: _col0
+ type: string
+ tag: 2
+ $INTNAME1
+ Reduce Output Operator
+ key expressions:
+ expr: _col0
+ type: string
+ sort order: +
+ Map-reduce partition columns:
+ expr: _col0
+ type: string
+ tag: 0
+ $INTNAME2
+ Reduce Output Operator
+ key expressions:
+ expr: _col0
+ type: string
+ sort order: +
+ Map-reduce partition columns:
+ expr: _col0
+ type: string
+ tag: 1
+ value expressions:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: string
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Left Outer Join0 to 1
+ Right Outer Join0 to 2
+ condition expressions:
+ 0
+ 1 {VALUE._col0} {VALUE._col1}
+ 2
+ handleSkewJoin: false
+ outputColumnNames: _col2, _col3
+ Select Operator
+ expressions:
+ expr: _col2
+ type: string
+ expr: _col3
+ type: string
+ outputColumnNames: _col2, _col3
+ Group By Operator
+ aggregations:
+ expr: sum(hash(_col2,_col3))
+ bucketGroup: false
+ mode: hash
+ outputColumnNames: _col0
+ 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-4
+ Map Reduce
+ Alias -> Map Operator Tree:
+ x:src
+ TableScan
+ alias: src
+ Select Operator
+ expressions:
+ expr: key
+ type: string
+ expr: value
+ type: string
+ outputColumnNames: _col0, _col1
+ Reduce Output Operator
+ key expressions:
+ expr: _col0
+ type: string
+ sort order: +
+ tag: -1
+ value expressions:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: string
+ Reduce Operator Tree:
+ Extract
+ 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-5
+ Map Reduce
+ Alias -> Map Operator Tree:
+ y:src
+ TableScan
+ alias: src
+ Select Operator
+ expressions:
+ expr: key
+ type: string
+ expr: value
+ type: string
+ outputColumnNames: _col0, _col1
+ Reduce Output Operator
+ key expressions:
+ expr: _col1
+ type: string
+ sort order: +
+ tag: -1
+ value expressions:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: string
+ Reduce Operator Tree:
+ Extract
+ 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-0
+ Fetch Operator
+ limit: -1
+
+
+PREHOOK: query: FROM
+(SELECT src.* FROM src sort by key) x
+LEFT OUTER JOIN
+(SELECT src.* FROM src sort by value) Y
+ON (x.key = Y.key)
+RIGHT OUTER JOIN
+(SELECT src.* FROM src sort by value) Z
+ON (x.key = Z.key)
+select sum(hash(Y.key,Y.value))
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+PREHOOK: Output: file:/var/folders/6g/6grtCwPMEf4sqHUPpy6xQG9ByHg/-Tmp-/heyongqiang/hive_2011-04-07_01-33-03_471_7630997145926057936/-mr-10000
+POSTHOOK: query: FROM
+(SELECT src.* FROM src sort by key) x
+LEFT OUTER JOIN
+(SELECT src.* FROM src sort by value) Y
+ON (x.key = Y.key)
+RIGHT OUTER JOIN
+(SELECT src.* FROM src sort by value) Z
+ON (x.key = Z.key)
+select sum(hash(Y.key,Y.value))
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+POSTHOOK: Output: file:/var/folders/6g/6grtCwPMEf4sqHUPpy6xQG9ByHg/-Tmp-/heyongqiang/hive_2011-04-07_01-33-03_471_7630997145926057936/-mr-10000
+348019368476
+PREHOOK: query: explain
+FROM
+(SELECT src.* FROM src sort by key) x
+RIGHT OUTER JOIN
+(SELECT src.* FROM src sort by value) Y
+ON (x.key = Y.key)
+RIGHT OUTER JOIN
+(SELECT src.* FROM src sort by value) Z
+ON (x.key = Z.key)
+select sum(hash(Y.key,Y.value))
+PREHOOK: type: QUERY
+POSTHOOK: query: explain
+FROM
+(SELECT src.* FROM src sort by key) x
+RIGHT OUTER JOIN
+(SELECT src.* FROM src sort by value) Y
+ON (x.key = Y.key)
+RIGHT OUTER JOIN
+(SELECT src.* FROM src sort by value) Z
+ON (x.key = Z.key)
+select sum(hash(Y.key,Y.value))
+POSTHOOK: type: QUERY
+ABSTRACT SYNTAX TREE:
+ (TOK_QUERY (TOK_FROM (TOK_RIGHTOUTERJOIN (TOK_RIGHTOUTERJOIN (TOK_SUBQUERY (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME src))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_ALLCOLREF (TOK_TABNAME src)))) (TOK_SORTBY (TOK_TABSORTCOLNAMEASC (TOK_TABLE_OR_COL key))))) x) (TOK_SUBQUERY (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME src))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_ALLCOLREF (TOK_TABNAME src)))) (TOK_SORTBY (TOK_TABSORTCOLNAMEASC (TOK_TABLE_OR_COL value))))) Y) (= (. (TOK_TABLE_OR_COL x) key) (. (TOK_TABLE_OR_COL Y) key))) (TOK_SUBQUERY (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME src))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_ALLCOLREF (TOK_TABNAME src)))) (TOK_SORTBY (TOK_TABSORTCOLNAMEASC (TOK_TABLE_OR_COL value))))) Z) (= (. (TOK_TABLE_OR_COL x) key) (. (TOK_TABLE_OR_COL Z) key)))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK
_SELECT (TOK_SELEXPR (TOK_FUNCTION sum (TOK_FUNCTION hash (. (TOK_TABLE_OR_COL Y) key) (. (TOK_TABLE_OR_COL Y) value)))))))
+
+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 is a root stage
+
+STAGE PLANS:
+ Stage: Stage-1
+ Map Reduce
+ Alias -> Map Operator Tree:
+ z:src
+ TableScan
+ alias: src
+ Select Operator
+ expressions:
+ expr: key
+ type: string
+ expr: value
+ type: string
+ outputColumnNames: _col0, _col1
+ Reduce Output Operator
+ key expressions:
+ expr: _col1
+ type: string
+ sort order: +
+ tag: -1
+ value expressions:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: string
+ Reduce Operator Tree:
+ Extract
+ 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-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
+ HashTable Sink Operator
[... 259 lines stripped ...]