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 [12/15] - 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/q...
Added: hive/trunk/ql/src/test/results/clientpositive/correlationoptimizer6.q.out
URL: http://svn.apache.org/viewvc/hive/trunk/ql/src/test/results/clientpositive/correlationoptimizer6.q.out?rev=1504395&view=auto
==============================================================================
--- hive/trunk/ql/src/test/results/clientpositive/correlationoptimizer6.q.out (added)
+++ hive/trunk/ql/src/test/results/clientpositive/correlationoptimizer6.q.out Thu Jul 18 09:16:52 2013
@@ -0,0 +1,5482 @@
+PREHOOK: query: -- When Correlation Optimizer is turned off, 6 MR jobs are needed.
+-- When Correlation Optimizer is turned on, 2 MR jobs are needed.
+-- The first job will evaluate subquery xx, subquery yy, and xx join yy.
+EXPLAIN
+SELECT xx.key, xx.cnt, yy.key, yy.cnt
+FROM
+(SELECT x.key as key, count(1) as cnt FROM src1 x JOIN src1 y ON (x.key = y.key) group by x.key) xx
+JOIN
+(SELECT x.key as key, count(1) as cnt FROM src x JOIN src y ON (x.key = y.key) group by x.key) yy
+ON xx.key=yy.key ORDER BY xx.key, xx.cnt, yy.key, yy.cnt
+PREHOOK: type: QUERY
+POSTHOOK: query: -- When Correlation Optimizer is turned off, 6 MR jobs are needed.
+-- When Correlation Optimizer is turned on, 2 MR jobs are needed.
+-- The first job will evaluate subquery xx, subquery yy, and xx join yy.
+EXPLAIN
+SELECT xx.key, xx.cnt, yy.key, yy.cnt
+FROM
+(SELECT x.key as key, count(1) as cnt FROM src1 x JOIN src1 y ON (x.key = y.key) group by x.key) xx
+JOIN
+(SELECT x.key as key, count(1) as cnt FROM src x JOIN src y ON (x.key = y.key) group by x.key) yy
+ON xx.key=yy.key ORDER BY xx.key, xx.cnt, yy.key, yy.cnt
+POSTHOOK: type: QUERY
+ABSTRACT SYNTAX TREE:
+ (TOK_QUERY (TOK_FROM (TOK_JOIN (TOK_SUBQUERY (TOK_QUERY (TOK_FROM (TOK_JOIN (TOK_TABREF (TOK_TABNAME src1) x) (TOK_TABREF (TOK_TABNAME src1) 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)))) xx) (TOK_SUBQUERY (TOK_QUERY (TOK_FROM (TOK_JOIN (TOK_TABREF (TOK_TABNAME src) 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)))) yy) (= (. (TOK_TABLE_OR_COL xx) key) (. (TOK_TABLE_OR_COL yy) key)))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (. (TOK_TABLE_OR_COL xx) key)) (TOK_SELEXPR (. (TOK_TABLE_OR_C
OL xx) cnt)) (TOK_SELEXPR (. (TOK_TABLE_OR_COL yy) key)) (TOK_SELEXPR (. (TOK_TABLE_OR_COL yy) cnt))) (TOK_ORDERBY (TOK_TABSORTCOLNAMEASC (. (TOK_TABLE_OR_COL xx) key)) (TOK_TABSORTCOLNAMEASC (. (TOK_TABLE_OR_COL xx) cnt)) (TOK_TABSORTCOLNAMEASC (. (TOK_TABLE_OR_COL yy) key)) (TOK_TABSORTCOLNAMEASC (. (TOK_TABLE_OR_COL yy) cnt)))))
+
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-2 depends on stages: Stage-1
+ Stage-3 depends on stages: Stage-2, Stage-7
+ Stage-4 depends on stages: Stage-3
+ Stage-6 is a root stage
+ Stage-7 depends on stages: Stage-6
+ Stage-0 is a root stage
+
+STAGE PLANS:
+ Stage: Stage-1
+ Map Reduce
+ Alias -> Map Operator Tree:
+ yy: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
+ yy: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
+ 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:
+ $INTNAME
+ 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: bigint
+ $INTNAME1
+ Reduce Output Operator
+ key expressions:
+ expr: _col0
+ type: string
+ sort order: +
+ Map-reduce partition columns:
+ expr: _col0
+ type: string
+ tag: 0
+ value expressions:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: bigint
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0 {VALUE._col0} {VALUE._col1}
+ 1 {VALUE._col0} {VALUE._col1}
+ handleSkewJoin: false
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Select Operator
+ expressions:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: bigint
+ expr: _col2
+ type: string
+ expr: _col3
+ type: bigint
+ outputColumnNames: _col0, _col1, _col2, _col3
+ 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:
+#### A masked pattern was here ####
+ Reduce Output Operator
+ key expressions:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: bigint
+ expr: _col2
+ type: string
+ expr: _col3
+ type: bigint
+ sort order: ++++
+ tag: -1
+ value expressions:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: bigint
+ expr: _col2
+ type: string
+ expr: _col3
+ type: bigint
+ Reduce Operator Tree:
+ Extract
+ 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-6
+ Map Reduce
+ Alias -> Map Operator Tree:
+ xx: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
+ xx: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-7
+ 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
+ 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: SELECT xx.key, xx.cnt, yy.key, yy.cnt
+FROM
+(SELECT x.key as key, count(1) as cnt FROM src1 x JOIN src1 y ON (x.key = y.key) group by x.key) xx
+JOIN
+(SELECT x.key as key, count(1) as cnt FROM src x JOIN src y ON (x.key = y.key) group by x.key) yy
+ON xx.key=yy.key ORDER BY xx.key, xx.cnt, yy.key, yy.cnt
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+PREHOOK: Input: default@src1
+#### A masked pattern was here ####
+POSTHOOK: query: SELECT xx.key, xx.cnt, yy.key, yy.cnt
+FROM
+(SELECT x.key as key, count(1) as cnt FROM src1 x JOIN src1 y ON (x.key = y.key) group by x.key) xx
+JOIN
+(SELECT x.key as key, count(1) as cnt FROM src x JOIN src y ON (x.key = y.key) group by x.key) yy
+ON xx.key=yy.key ORDER BY xx.key, xx.cnt, yy.key, yy.cnt
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+POSTHOOK: Input: default@src1
+#### A masked pattern was here ####
+128 1 128 9
+146 1 146 4
+150 1 150 1
+213 1 213 4
+224 1 224 4
+238 1 238 4
+255 1 255 4
+273 1 273 9
+278 1 278 4
+311 1 311 9
+369 1 369 9
+401 1 401 25
+406 1 406 16
+66 1 66 1
+98 1 98 4
+PREHOOK: query: EXPLAIN
+SELECT xx.key, xx.cnt, yy.key, yy.cnt
+FROM
+(SELECT x.key as key, count(1) as cnt FROM src1 x JOIN src1 y ON (x.key = y.key) group by x.key) xx
+JOIN
+(SELECT x.key as key, count(1) as cnt FROM src x JOIN src y ON (x.key = y.key) group by x.key) yy
+ON xx.key=yy.key ORDER BY xx.key, xx.cnt, yy.key, yy.cnt
+PREHOOK: type: QUERY
+POSTHOOK: query: EXPLAIN
+SELECT xx.key, xx.cnt, yy.key, yy.cnt
+FROM
+(SELECT x.key as key, count(1) as cnt FROM src1 x JOIN src1 y ON (x.key = y.key) group by x.key) xx
+JOIN
+(SELECT x.key as key, count(1) as cnt FROM src x JOIN src y ON (x.key = y.key) group by x.key) yy
+ON xx.key=yy.key ORDER BY xx.key, xx.cnt, yy.key, yy.cnt
+POSTHOOK: type: QUERY
+ABSTRACT SYNTAX TREE:
+ (TOK_QUERY (TOK_FROM (TOK_JOIN (TOK_SUBQUERY (TOK_QUERY (TOK_FROM (TOK_JOIN (TOK_TABREF (TOK_TABNAME src1) x) (TOK_TABREF (TOK_TABNAME src1) 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)))) xx) (TOK_SUBQUERY (TOK_QUERY (TOK_FROM (TOK_JOIN (TOK_TABREF (TOK_TABNAME src) 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)))) yy) (= (. (TOK_TABLE_OR_COL xx) key) (. (TOK_TABLE_OR_COL yy) key)))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (. (TOK_TABLE_OR_COL xx) key)) (TOK_SELEXPR (. (TOK_TABLE_OR_C
OL xx) cnt)) (TOK_SELEXPR (. (TOK_TABLE_OR_COL yy) key)) (TOK_SELEXPR (. (TOK_TABLE_OR_COL yy) cnt))) (TOK_ORDERBY (TOK_TABSORTCOLNAMEASC (. (TOK_TABLE_OR_COL xx) key)) (TOK_TABSORTCOLNAMEASC (. (TOK_TABLE_OR_COL xx) cnt)) (TOK_TABSORTCOLNAMEASC (. (TOK_TABLE_OR_COL yy) key)) (TOK_TABSORTCOLNAMEASC (. (TOK_TABLE_OR_COL yy) 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:
+ xx: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
+ xx: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
+ yy:x
+ TableScan
+ alias: x
+ Reduce Output Operator
+ key expressions:
+ expr: key
+ type: string
+ sort order: +
+ Map-reduce partition columns:
+ expr: key
+ type: string
+ tag: 2
+ value expressions:
+ expr: key
+ type: string
+ yy:y
+ TableScan
+ alias: y
+ Reduce Output Operator
+ key expressions:
+ expr: key
+ type: string
+ sort order: +
+ Map-reduce partition columns:
+ expr: key
+ type: string
+ tag: 3
+ 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
+ Mux Operator
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0 {VALUE._col0} {VALUE._col1}
+ 1 {VALUE._col0} {VALUE._col1}
+ handleSkewJoin: false
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Select Operator
+ expressions:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: bigint
+ expr: _col2
+ type: string
+ expr: _col3
+ type: bigint
+ outputColumnNames: _col0, _col1, _col2, _col3
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ 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
+ Mux Operator
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0 {VALUE._col0} {VALUE._col1}
+ 1 {VALUE._col0} {VALUE._col1}
+ handleSkewJoin: false
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Select Operator
+ expressions:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: bigint
+ expr: _col2
+ type: string
+ expr: _col3
+ type: bigint
+ outputColumnNames: _col0, _col1, _col2, _col3
+ 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
+ expr: _col1
+ type: bigint
+ expr: _col2
+ type: string
+ expr: _col3
+ type: bigint
+ sort order: ++++
+ tag: -1
+ value expressions:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: bigint
+ expr: _col2
+ type: string
+ expr: _col3
+ type: bigint
+ Reduce Operator Tree:
+ Extract
+ 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 xx.key, xx.cnt, yy.key, yy.cnt
+FROM
+(SELECT x.key as key, count(1) as cnt FROM src1 x JOIN src1 y ON (x.key = y.key) group by x.key) xx
+JOIN
+(SELECT x.key as key, count(1) as cnt FROM src x JOIN src y ON (x.key = y.key) group by x.key) yy
+ON xx.key=yy.key ORDER BY xx.key, xx.cnt, yy.key, yy.cnt
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+PREHOOK: Input: default@src1
+#### A masked pattern was here ####
+POSTHOOK: query: SELECT xx.key, xx.cnt, yy.key, yy.cnt
+FROM
+(SELECT x.key as key, count(1) as cnt FROM src1 x JOIN src1 y ON (x.key = y.key) group by x.key) xx
+JOIN
+(SELECT x.key as key, count(1) as cnt FROM src x JOIN src y ON (x.key = y.key) group by x.key) yy
+ON xx.key=yy.key ORDER BY xx.key, xx.cnt, yy.key, yy.cnt
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+POSTHOOK: Input: default@src1
+#### A masked pattern was here ####
+128 1 128 9
+146 1 146 4
+150 1 150 1
+213 1 213 4
+224 1 224 4
+238 1 238 4
+255 1 255 4
+273 1 273 9
+278 1 278 4
+311 1 311 9
+369 1 369 9
+401 1 401 25
+406 1 406 16
+66 1 66 1
+98 1 98 4
+PREHOOK: query: -- Enable hive.auto.convert.join.
+EXPLAIN
+SELECT xx.key, xx.cnt, yy.key, yy.cnt
+FROM
+(SELECT x.key as key, count(1) as cnt FROM src1 x JOIN src1 y ON (x.key = y.key) group by x.key) xx
+JOIN
+(SELECT x.key as key, count(1) as cnt FROM src x JOIN src y ON (x.key = y.key) group by x.key) yy
+ON xx.key=yy.key ORDER BY xx.key, xx.cnt, yy.key, yy.cnt
+PREHOOK: type: QUERY
+POSTHOOK: query: -- Enable hive.auto.convert.join.
+EXPLAIN
+SELECT xx.key, xx.cnt, yy.key, yy.cnt
+FROM
+(SELECT x.key as key, count(1) as cnt FROM src1 x JOIN src1 y ON (x.key = y.key) group by x.key) xx
+JOIN
+(SELECT x.key as key, count(1) as cnt FROM src x JOIN src y ON (x.key = y.key) group by x.key) yy
+ON xx.key=yy.key ORDER BY xx.key, xx.cnt, yy.key, yy.cnt
+POSTHOOK: type: QUERY
+ABSTRACT SYNTAX TREE:
+ (TOK_QUERY (TOK_FROM (TOK_JOIN (TOK_SUBQUERY (TOK_QUERY (TOK_FROM (TOK_JOIN (TOK_TABREF (TOK_TABNAME src1) x) (TOK_TABREF (TOK_TABNAME src1) 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)))) xx) (TOK_SUBQUERY (TOK_QUERY (TOK_FROM (TOK_JOIN (TOK_TABREF (TOK_TABNAME src) 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)))) yy) (= (. (TOK_TABLE_OR_COL xx) key) (. (TOK_TABLE_OR_COL yy) key)))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (. (TOK_TABLE_OR_COL xx) key)) (TOK_SELEXPR (. (TOK_TABLE_OR_C
OL xx) cnt)) (TOK_SELEXPR (. (TOK_TABLE_OR_COL yy) key)) (TOK_SELEXPR (. (TOK_TABLE_OR_COL yy) cnt))) (TOK_ORDERBY (TOK_TABSORTCOLNAMEASC (. (TOK_TABLE_OR_COL xx) key)) (TOK_TABSORTCOLNAMEASC (. (TOK_TABLE_OR_COL xx) cnt)) (TOK_TABSORTCOLNAMEASC (. (TOK_TABLE_OR_COL yy) key)) (TOK_TABSORTCOLNAMEASC (. (TOK_TABLE_OR_COL yy) cnt)))))
+
+STAGE DEPENDENCIES:
+ Stage-9 is a root stage
+ Stage-7 depends on stages: Stage-9
+ Stage-2 depends on stages: Stage-7, Stage-8
+ Stage-3 depends on stages: Stage-2
+ Stage-10 is a root stage
+ Stage-8 depends on stages: Stage-10
+ Stage-0 is a root stage
+
+STAGE PLANS:
+ Stage: Stage-9
+ Map Reduce Local Work
+ Alias -> Map Local Tables:
+ yy:y
+ Fetch Operator
+ limit: -1
+ Alias -> Map Local Operator Tree:
+ yy:y
+ TableScan
+ alias: y
+ HashTable Sink Operator
+ condition expressions:
+ 0 {key}
+ 1
+ handleSkewJoin: false
+ keys:
+ 0 [Column[key]]
+ 1 [Column[key]]
+ Position of Big Table: 0
+
+ Stage: Stage-7
+ Map Reduce
+ Alias -> Map Operator Tree:
+ yy:x
+ TableScan
+ alias: x
+ 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: 0
+ 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
+#### 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: 0
+ value expressions:
+ expr: _col1
+ type: bigint
+ Reduce Operator Tree:
+ Demux Operator
+ 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
+ Mux Operator
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0 {VALUE._col0} {VALUE._col1}
+ 1 {VALUE._col0} {VALUE._col1}
+ handleSkewJoin: false
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Select Operator
+ expressions:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: bigint
+ expr: _col2
+ type: string
+ expr: _col3
+ type: bigint
+ outputColumnNames: _col0, _col1, _col2, _col3
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ 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
+ Mux Operator
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0 {VALUE._col0} {VALUE._col1}
+ 1 {VALUE._col0} {VALUE._col1}
+ handleSkewJoin: false
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Select Operator
+ expressions:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: bigint
+ expr: _col2
+ type: string
+ expr: _col3
+ type: bigint
+ outputColumnNames: _col0, _col1, _col2, _col3
+ 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
+ key expressions:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: bigint
+ expr: _col2
+ type: string
+ expr: _col3
+ type: bigint
+ sort order: ++++
+ tag: -1
+ value expressions:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: bigint
+ expr: _col2
+ type: string
+ expr: _col3
+ type: bigint
+ Reduce Operator Tree:
+ Extract
+ 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:
+ xx:y
+ Fetch Operator
+ limit: -1
+ Alias -> Map Local Operator Tree:
+ xx:y
+ TableScan
+ alias: y
+ HashTable Sink Operator
+ condition expressions:
+ 0 {key}
+ 1
+ handleSkewJoin: false
+ keys:
+ 0 [Column[key]]
+ 1 [Column[key]]
+ Position of Big Table: 0
+
+ Stage: Stage-8
+ Map Reduce
+ Alias -> Map Operator Tree:
+ xx:x
+ TableScan
+ alias: x
+ 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: 0
+ 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-0
+ Fetch Operator
+ limit: -1
+
+
+PREHOOK: query: SELECT xx.key, xx.cnt, yy.key, yy.cnt
+FROM
+(SELECT x.key as key, count(1) as cnt FROM src1 x JOIN src1 y ON (x.key = y.key) group by x.key) xx
+JOIN
+(SELECT x.key as key, count(1) as cnt FROM src x JOIN src y ON (x.key = y.key) group by x.key) yy
+ON xx.key=yy.key ORDER BY xx.key, xx.cnt, yy.key, yy.cnt
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+PREHOOK: Input: default@src1
+#### A masked pattern was here ####
+POSTHOOK: query: SELECT xx.key, xx.cnt, yy.key, yy.cnt
+FROM
+(SELECT x.key as key, count(1) as cnt FROM src1 x JOIN src1 y ON (x.key = y.key) group by x.key) xx
+JOIN
+(SELECT x.key as key, count(1) as cnt FROM src x JOIN src y ON (x.key = y.key) group by x.key) yy
+ON xx.key=yy.key ORDER BY xx.key, xx.cnt, yy.key, yy.cnt
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+POSTHOOK: Input: default@src1
+#### A masked pattern was here ####
+128 1 128 9
+146 1 146 4
+150 1 150 1
+213 1 213 4
+224 1 224 4
+238 1 238 4
+255 1 255 4
+273 1 273 9
+278 1 278 4
+311 1 311 9
+369 1 369 9
+401 1 401 25
+406 1 406 16
+66 1 66 1
+98 1 98 4
+PREHOOK: query: -- When Correlation Optimizer is turned off, 3 MR jobs are needed.
+-- When Correlation Optimizer is turned on, 2 MR jobs are needed.
+-- The first job will evaluate subquery yy and xx join yy.
+EXPLAIN
+SELECT xx.key, yy.key, yy.cnt
+FROM src1 xx
+JOIN
+(SELECT x.key as key, count(1) as cnt FROM src x GROUP BY x.key) yy
+ON xx.key=yy.key ORDER BY xx.key, yy.key, yy.cnt
+PREHOOK: type: QUERY
+POSTHOOK: query: -- When Correlation Optimizer is turned off, 3 MR jobs are needed.
+-- When Correlation Optimizer is turned on, 2 MR jobs are needed.
+-- The first job will evaluate subquery yy and xx join yy.
+EXPLAIN
+SELECT xx.key, yy.key, yy.cnt
+FROM src1 xx
+JOIN
+(SELECT x.key as key, count(1) as cnt FROM src x GROUP BY x.key) yy
+ON xx.key=yy.key ORDER BY xx.key, yy.key, yy.cnt
+POSTHOOK: type: QUERY
+ABSTRACT SYNTAX TREE:
+ (TOK_QUERY (TOK_FROM (TOK_JOIN (TOK_TABREF (TOK_TABNAME src1) xx) (TOK_SUBQUERY (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME src) x)) (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)))) yy) (= (. (TOK_TABLE_OR_COL xx) key) (. (TOK_TABLE_OR_COL yy) key)))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (. (TOK_TABLE_OR_COL xx) key)) (TOK_SELEXPR (. (TOK_TABLE_OR_COL yy) key)) (TOK_SELEXPR (. (TOK_TABLE_OR_COL yy) cnt))) (TOK_ORDERBY (TOK_TABSORTCOLNAMEASC (. (TOK_TABLE_OR_COL xx) key)) (TOK_TABSORTCOLNAMEASC (. (TOK_TABLE_OR_COL yy) key)) (TOK_TABSORTCOLNAMEASC (. (TOK_TABLE_OR_COL yy) 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:
+ yy:x
+ TableScan
+ alias: x
+ Select Operator
+ expressions:
+ expr: key
+ type: string
+ outputColumnNames: key
+ Group By Operator
+ aggregations:
+ expr: count(1)
+ bucketGroup: false
+ keys:
+ expr: key
+ 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
+ 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
+ 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:
+ $INTNAME
+ 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: bigint
+ xx
+ TableScan
+ alias: xx
+ 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:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0 {VALUE._col0}
+ 1 {VALUE._col0} {VALUE._col1}
+ handleSkewJoin: false
+ outputColumnNames: _col0, _col4, _col5
+ Select Operator
+ expressions:
+ expr: _col0
+ type: string
+ expr: _col4
+ type: string
+ expr: _col5
+ type: bigint
+ outputColumnNames: _col0, _col1, _col2
+ 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
+ key expressions:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: string
+ expr: _col2
+ type: bigint
+ sort order: +++
+ tag: -1
+ value expressions:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: string
+ expr: _col2
+ type: bigint
+ Reduce Operator Tree:
+ Extract
+ 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 xx.key, yy.key, yy.cnt
+FROM src1 xx
+JOIN
+(SELECT x.key as key, count(1) as cnt FROM src x GROUP BY x.key) yy
+ON xx.key=yy.key ORDER BY xx.key, yy.key, yy.cnt
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+PREHOOK: Input: default@src1
+#### A masked pattern was here ####
+POSTHOOK: query: SELECT xx.key, yy.key, yy.cnt
+FROM src1 xx
+JOIN
+(SELECT x.key as key, count(1) as cnt FROM src x GROUP BY x.key) yy
+ON xx.key=yy.key ORDER BY xx.key, yy.key, yy.cnt
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+POSTHOOK: Input: default@src1
+#### A masked pattern was here ####
+128 128 3
+146 146 2
+150 150 1
+213 213 2
+224 224 2
+238 238 2
+255 255 2
+273 273 3
+278 278 2
+311 311 3
+369 369 3
+401 401 5
+406 406 4
+66 66 1
+98 98 2
+PREHOOK: query: EXPLAIN
+SELECT xx.key, yy.key, yy.cnt
+FROM src1 xx
+JOIN
+(SELECT x.key as key, count(1) as cnt FROM src x GROUP BY x.key) yy
+ON xx.key=yy.key ORDER BY xx.key, yy.key, yy.cnt
+PREHOOK: type: QUERY
+POSTHOOK: query: EXPLAIN
+SELECT xx.key, yy.key, yy.cnt
+FROM src1 xx
+JOIN
+(SELECT x.key as key, count(1) as cnt FROM src x GROUP BY x.key) yy
+ON xx.key=yy.key ORDER BY xx.key, yy.key, yy.cnt
+POSTHOOK: type: QUERY
+ABSTRACT SYNTAX TREE:
+ (TOK_QUERY (TOK_FROM (TOK_JOIN (TOK_TABREF (TOK_TABNAME src1) xx) (TOK_SUBQUERY (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME src) x)) (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)))) yy) (= (. (TOK_TABLE_OR_COL xx) key) (. (TOK_TABLE_OR_COL yy) key)))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (. (TOK_TABLE_OR_COL xx) key)) (TOK_SELEXPR (. (TOK_TABLE_OR_COL yy) key)) (TOK_SELEXPR (. (TOK_TABLE_OR_COL yy) cnt))) (TOK_ORDERBY (TOK_TABSORTCOLNAMEASC (. (TOK_TABLE_OR_COL xx) key)) (TOK_TABSORTCOLNAMEASC (. (TOK_TABLE_OR_COL yy) key)) (TOK_TABSORTCOLNAMEASC (. (TOK_TABLE_OR_COL yy) 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:
+ xx
+ TableScan
+ alias: xx
+ 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
+ yy:x
+ TableScan
+ alias: x
+ Select Operator
+ expressions:
+ expr: key
+ type: string
+ outputColumnNames: key
+ Group By Operator
+ aggregations:
+ expr: count(1)
+ bucketGroup: false
+ keys:
+ expr: key
+ 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
+ Reduce Operator Tree:
+ Demux Operator
+ Mux Operator
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0 {VALUE._col0}
+ 1 {VALUE._col0} {VALUE._col1}
+ handleSkewJoin: false
+ outputColumnNames: _col0, _col4, _col5
+ Select Operator
+ expressions:
+ expr: _col0
+ type: string
+ expr: _col4
+ type: string
+ expr: _col5
+ type: bigint
+ outputColumnNames: _col0, _col1, _col2
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ 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
+ Mux Operator
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0 {VALUE._col0}
+ 1 {VALUE._col0} {VALUE._col1}
+ handleSkewJoin: false
+ outputColumnNames: _col0, _col4, _col5
+ Select Operator
+ expressions:
+ expr: _col0
+ type: string
+ expr: _col4
+ type: string
+ expr: _col5
+ type: bigint
+ outputColumnNames: _col0, _col1, _col2
+ 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
+ expr: _col1
+ type: string
+ expr: _col2
+ type: bigint
+ sort order: +++
+ tag: -1
+ value expressions:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: string
+ expr: _col2
+ type: bigint
+ Reduce Operator Tree:
+ Extract
+ 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 xx.key, yy.key, yy.cnt
+FROM src1 xx
+JOIN
+(SELECT x.key as key, count(1) as cnt FROM src x GROUP BY x.key) yy
+ON xx.key=yy.key ORDER BY xx.key, yy.key, yy.cnt
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+PREHOOK: Input: default@src1
+#### A masked pattern was here ####
+POSTHOOK: query: SELECT xx.key, yy.key, yy.cnt
+FROM src1 xx
+JOIN
+(SELECT x.key as key, count(1) as cnt FROM src x GROUP BY x.key) yy
+ON xx.key=yy.key ORDER BY xx.key, yy.key, yy.cnt
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+POSTHOOK: Input: default@src1
+#### A masked pattern was here ####
+128 128 3
+146 146 2
+150 150 1
+213 213 2
+224 224 2
+238 238 2
+255 255 2
+273 273 3
+278 278 2
+311 311 3
+369 369 3
+401 401 5
+406 406 4
+66 66 1
+98 98 2
+PREHOOK: query: -- When Correlation Optimizer is turned off, 4 MR jobs are needed.
+-- When Correlation Optimizer is turned on, 2 MR jobs are needed.
+-- The first job will evaluate subquery yy and xx join yy.
+EXPLAIN
+SELECT xx.key, yy.key, yy.cnt
+FROM src1 xx
+JOIN
+(SELECT x.key as key, count(1) as cnt FROM src x JOIN src y ON (x.key = y.key) group by x.key) yy
+ON xx.key=yy.key ORDER BY xx.key, yy.key, yy.cnt
+PREHOOK: type: QUERY
+POSTHOOK: query: -- When Correlation Optimizer is turned off, 4 MR jobs are needed.
+-- When Correlation Optimizer is turned on, 2 MR jobs are needed.
+-- The first job will evaluate subquery yy and xx join yy.
+EXPLAIN
+SELECT xx.key, yy.key, yy.cnt
+FROM src1 xx
+JOIN
+(SELECT x.key as key, count(1) as cnt FROM src x JOIN src y ON (x.key = y.key) group by x.key) yy
+ON xx.key=yy.key ORDER BY xx.key, yy.key, yy.cnt
+POSTHOOK: type: QUERY
+ABSTRACT SYNTAX TREE:
+ (TOK_QUERY (TOK_FROM (TOK_JOIN (TOK_TABREF (TOK_TABNAME src1) xx) (TOK_SUBQUERY (TOK_QUERY (TOK_FROM (TOK_JOIN (TOK_TABREF (TOK_TABNAME src) 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)))) yy) (= (. (TOK_TABLE_OR_COL xx) key) (. (TOK_TABLE_OR_COL yy) key)))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (. (TOK_TABLE_OR_COL xx) key)) (TOK_SELEXPR (. (TOK_TABLE_OR_COL yy) key)) (TOK_SELEXPR (. (TOK_TABLE_OR_COL yy) cnt))) (TOK_ORDERBY (TOK_TABSORTCOLNAMEASC (. (TOK_TABLE_OR_COL xx) key)) (TOK_TABSORTCOLNAMEASC (. (TOK_TABLE_OR_COL yy) key)) (TOK_TABSORTCOLNAMEASC (. (TOK_TABLE_OR_COL yy) cnt)))))
+
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-2 depends on stages: Stage-1
+ Stage-3 depends on stages: Stage-2
+ Stage-4 depends on stages: Stage-3
+ Stage-0 is a root stage
+
+STAGE PLANS:
+ Stage: Stage-1
+ Map Reduce
+ Alias -> Map Operator Tree:
+ yy: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
+ yy: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
+ 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:
+ $INTNAME
+ 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: bigint
+ xx
+ TableScan
+ alias: xx
+ 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:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0 {VALUE._col0}
+ 1 {VALUE._col0} {VALUE._col1}
+ handleSkewJoin: false
+ outputColumnNames: _col0, _col4, _col5
+ Select Operator
+ expressions:
+ expr: _col0
+ type: string
+ expr: _col4
+ type: string
+ expr: _col5
+ type: bigint
+ outputColumnNames: _col0, _col1, _col2
+ 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:
+#### A masked pattern was here ####
+ Reduce Output Operator
+ key expressions:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: string
+ expr: _col2
+ type: bigint
+ sort order: +++
+ tag: -1
+ value expressions:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: string
+ expr: _col2
+ type: bigint
+ Reduce Operator Tree:
+ Extract
+ 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 xx.key, yy.key, yy.cnt
+FROM src1 xx
+JOIN
+(SELECT x.key as key, count(1) as cnt FROM src x JOIN src y ON (x.key = y.key) group by x.key) yy
+ON xx.key=yy.key ORDER BY xx.key, yy.key, yy.cnt
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+PREHOOK: Input: default@src1
+#### A masked pattern was here ####
+POSTHOOK: query: SELECT xx.key, yy.key, yy.cnt
+FROM src1 xx
+JOIN
+(SELECT x.key as key, count(1) as cnt FROM src x JOIN src y ON (x.key = y.key) group by x.key) yy
+ON xx.key=yy.key ORDER BY xx.key, yy.key, yy.cnt
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+POSTHOOK: Input: default@src1
+#### A masked pattern was here ####
+128 128 9
+146 146 4
+150 150 1
+213 213 4
+224 224 4
+238 238 4
+255 255 4
+273 273 9
+278 278 4
+311 311 9
+369 369 9
+401 401 25
+406 406 16
+66 66 1
+98 98 4
+PREHOOK: query: EXPLAIN
+SELECT xx.key, yy.key, yy.cnt
+FROM src1 xx
+JOIN
+(SELECT x.key as key, count(1) as cnt FROM src x JOIN src y ON (x.key = y.key) group by x.key) yy
+ON xx.key=yy.key ORDER BY xx.key, yy.key, yy.cnt
+PREHOOK: type: QUERY
+POSTHOOK: query: EXPLAIN
+SELECT xx.key, yy.key, yy.cnt
+FROM src1 xx
+JOIN
+(SELECT x.key as key, count(1) as cnt FROM src x JOIN src y ON (x.key = y.key) group by x.key) yy
+ON xx.key=yy.key ORDER BY xx.key, yy.key, yy.cnt
+POSTHOOK: type: QUERY
+ABSTRACT SYNTAX TREE:
+ (TOK_QUERY (TOK_FROM (TOK_JOIN (TOK_TABREF (TOK_TABNAME src1) xx) (TOK_SUBQUERY (TOK_QUERY (TOK_FROM (TOK_JOIN (TOK_TABREF (TOK_TABNAME src) 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)))) yy) (= (. (TOK_TABLE_OR_COL xx) key) (. (TOK_TABLE_OR_COL yy) key)))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (. (TOK_TABLE_OR_COL xx) key)) (TOK_SELEXPR (. (TOK_TABLE_OR_COL yy) key)) (TOK_SELEXPR (. (TOK_TABLE_OR_COL yy) cnt))) (TOK_ORDERBY (TOK_TABSORTCOLNAMEASC (. (TOK_TABLE_OR_COL xx) key)) (TOK_TABSORTCOLNAMEASC (. (TOK_TABLE_OR_COL yy) key)) (TOK_TABSORTCOLNAMEASC (. (TOK_TABLE_OR_COL yy) 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:
+ xx
+ TableScan
+ alias: xx
+ 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
+ yy: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
+ value expressions:
+ expr: key
+ type: string
+ yy:y
+ TableScan
+ alias: y
+ Reduce Output Operator
+ key expressions:
+ expr: key
+ type: string
+ sort order: +
+ Map-reduce partition columns:
+ expr: key
+ type: string
+ tag: 2
+ Reduce Operator Tree:
+ Demux Operator
+ Mux Operator
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0 {VALUE._col0}
+ 1 {VALUE._col0} {VALUE._col1}
+ handleSkewJoin: false
+ outputColumnNames: _col0, _col4, _col5
+ Select Operator
+ expressions:
+ expr: _col0
+ type: string
+ expr: _col4
+ type: string
+ expr: _col5
+ type: bigint
+ outputColumnNames: _col0, _col1, _col2
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ 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
+ Mux Operator
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0 {VALUE._col0}
+ 1 {VALUE._col0} {VALUE._col1}
+ handleSkewJoin: false
+ outputColumnNames: _col0, _col4, _col5
+ Select Operator
+ expressions:
+ expr: _col0
+ type: string
+ expr: _col4
+ type: string
+ expr: _col5
+ type: bigint
+ outputColumnNames: _col0, _col1, _col2
+ 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
+ expr: _col1
+ type: string
+ expr: _col2
+ type: bigint
+ sort order: +++
+ tag: -1
+ value expressions:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: string
+ expr: _col2
+ type: bigint
+ Reduce Operator Tree:
+ Extract
+ 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 xx.key, yy.key, yy.cnt
+FROM src1 xx
+JOIN
+(SELECT x.key as key, count(1) as cnt FROM src x JOIN src y ON (x.key = y.key) group by x.key) yy
+ON xx.key=yy.key ORDER BY xx.key, yy.key, yy.cnt
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+PREHOOK: Input: default@src1
+#### A masked pattern was here ####
+POSTHOOK: query: SELECT xx.key, yy.key, yy.cnt
+FROM src1 xx
+JOIN
+(SELECT x.key as key, count(1) as cnt FROM src x JOIN src y ON (x.key = y.key) group by x.key) yy
+ON xx.key=yy.key ORDER BY xx.key, yy.key, yy.cnt
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+POSTHOOK: Input: default@src1
+#### A masked pattern was here ####
+128 128 9
+146 146 4
+150 150 1
+213 213 4
+224 224 4
+238 238 4
+255 255 4
+273 273 9
+278 278 4
+311 311 9
+369 369 9
+401 401 25
+406 406 16
+66 66 1
+98 98 4
+PREHOOK: query: -- When Correlation Optimizer is turned off, 4 MR jobs are needed.
+-- When Correlation Optimizer is turned on, 2 MR jobs are needed.
+-- The first job will evaluate subquery xx and xx join yy.
+EXPLAIN
+SELECT xx.key, xx.cnt, yy.key
+FROM
+(SELECT x.key as key, count(1) as cnt FROM src1 x JOIN src1 y ON (x.key = y.key) group by x.key) xx
+JOIN src yy
+ON xx.key=yy.key ORDER BY xx.key, xx.cnt, yy.key
+PREHOOK: type: QUERY
+POSTHOOK: query: -- When Correlation Optimizer is turned off, 4 MR jobs are needed.
+-- When Correlation Optimizer is turned on, 2 MR jobs are needed.
+-- The first job will evaluate subquery xx and xx join yy.
+EXPLAIN
+SELECT xx.key, xx.cnt, yy.key
+FROM
+(SELECT x.key as key, count(1) as cnt FROM src1 x JOIN src1 y ON (x.key = y.key) group by x.key) xx
+JOIN src yy
+ON xx.key=yy.key ORDER BY xx.key, xx.cnt, yy.key
+POSTHOOK: type: QUERY
+ABSTRACT SYNTAX TREE:
+ (TOK_QUERY (TOK_FROM (TOK_JOIN (TOK_SUBQUERY (TOK_QUERY (TOK_FROM (TOK_JOIN (TOK_TABREF (TOK_TABNAME src1) x) (TOK_TABREF (TOK_TABNAME src1) 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)))) xx) (TOK_TABREF (TOK_TABNAME src) yy) (= (. (TOK_TABLE_OR_COL xx) key) (. (TOK_TABLE_OR_COL yy) key)))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (. (TOK_TABLE_OR_COL xx) key)) (TOK_SELEXPR (. (TOK_TABLE_OR_COL xx) cnt)) (TOK_SELEXPR (. (TOK_TABLE_OR_COL yy) key))) (TOK_ORDERBY (TOK_TABSORTCOLNAMEASC (. (TOK_TABLE_OR_COL xx) key)) (TOK_TABSORTCOLNAMEASC (. (TOK_TABLE_OR_COL xx) cnt)) (TOK_TABSORTCOLNAMEASC (. (TOK_TABLE_OR_COL yy) key)))))
+
+STAGE DEPENDENCIES:
+ Stage-3 is a root stage
+ Stage-4 depends on stages: Stage-3
+ Stage-1 depends on stages: Stage-4
+ Stage-2 depends on stages: Stage-1
+ Stage-0 is a root stage
+
+STAGE PLANS:
+ Stage: Stage-3
+ Map Reduce
+ Alias -> Map Operator Tree:
+ xx: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
+ xx: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-4
+ 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
+ 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-1
+ 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
+ value expressions:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: bigint
+ yy
+ TableScan
+ alias: yy
+ 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:
+ Inner Join 0 to 1
+ condition expressions:
+ 0 {VALUE._col0} {VALUE._col1}
+ 1 {VALUE._col0}
+ handleSkewJoin: false
+ outputColumnNames: _col0, _col1, _col2
+ Select Operator
+ expressions:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: bigint
+ expr: _col2
+ type: string
+ outputColumnNames: _col0, _col1, _col2
+ 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
+ expr: _col1
+ type: bigint
+ expr: _col2
+ type: string
+ sort order: +++
+ tag: -1
+ value expressions:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: bigint
+ expr: _col2
+ type: string
+ Reduce Operator Tree:
+ Extract
+ 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 xx.key, xx.cnt, yy.key
+FROM
+(SELECT x.key as key, count(1) as cnt FROM src1 x JOIN src1 y ON (x.key = y.key) group by x.key) xx
+JOIN src yy
+ON xx.key=yy.key ORDER BY xx.key, xx.cnt, yy.key
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+PREHOOK: Input: default@src1
+#### A masked pattern was here ####
+POSTHOOK: query: SELECT xx.key, xx.cnt, yy.key
+FROM
+(SELECT x.key as key, count(1) as cnt FROM src1 x JOIN src1 y ON (x.key = y.key) group by x.key) xx
+JOIN src yy
+ON xx.key=yy.key ORDER BY xx.key, xx.cnt, yy.key
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+POSTHOOK: Input: default@src1
+#### A masked pattern was here ####
+128 1 128
+128 1 128
+128 1 128
+146 1 146
+146 1 146
+150 1 150
+213 1 213
+213 1 213
+224 1 224
+224 1 224
+238 1 238
+238 1 238
+255 1 255
+255 1 255
+273 1 273
+273 1 273
+273 1 273
+278 1 278
+278 1 278
+311 1 311
+311 1 311
+311 1 311
+369 1 369
+369 1 369
+369 1 369
+401 1 401
+401 1 401
+401 1 401
+401 1 401
+401 1 401
+406 1 406
+406 1 406
+406 1 406
+406 1 406
+66 1 66
+98 1 98
+98 1 98
+PREHOOK: query: EXPLAIN
+SELECT xx.key, xx.cnt, yy.key
+FROM
+(SELECT x.key as key, count(1) as cnt FROM src1 x JOIN src1 y ON (x.key = y.key) group by x.key) xx
+JOIN src yy
+ON xx.key=yy.key ORDER BY xx.key, xx.cnt, yy.key
+PREHOOK: type: QUERY
+POSTHOOK: query: EXPLAIN
+SELECT xx.key, xx.cnt, yy.key
+FROM
+(SELECT x.key as key, count(1) as cnt FROM src1 x JOIN src1 y ON (x.key = y.key) group by x.key) xx
+JOIN src yy
+ON xx.key=yy.key ORDER BY xx.key, xx.cnt, yy.key
+POSTHOOK: type: QUERY
+ABSTRACT SYNTAX TREE:
+ (TOK_QUERY (TOK_FROM (TOK_JOIN (TOK_SUBQUERY (TOK_QUERY (TOK_FROM (TOK_JOIN (TOK_TABREF (TOK_TABNAME src1) x) (TOK_TABREF (TOK_TABNAME src1) 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)))) xx) (TOK_TABREF (TOK_TABNAME src) yy) (= (. (TOK_TABLE_OR_COL xx) key) (. (TOK_TABLE_OR_COL yy) key)))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (. (TOK_TABLE_OR_COL xx) key)) (TOK_SELEXPR (. (TOK_TABLE_OR_COL xx) cnt)) (TOK_SELEXPR (. (TOK_TABLE_OR_COL yy) key))) (TOK_ORDERBY (TOK_TABSORTCOLNAMEASC (. (TOK_TABLE_OR_COL xx) key)) (TOK_TABSORTCOLNAMEASC (. (TOK_TABLE_OR_COL xx) cnt)) (TOK_TABSORTCOLNAMEASC (. (TOK_TABLE_OR_COL yy) key)))))
+
+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:
+ xx: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
+ xx: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
+ yy
+ TableScan
+ alias: yy
+ Reduce Output Operator
+ key expressions:
+ expr: key
+ type: string
+ sort order: +
+ Map-reduce partition columns:
+ expr: key
+ type: string
+ tag: 2
+ value expressions:
+ expr: key
+ type: string
+ 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
+ Mux Operator
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0 {VALUE._col0} {VALUE._col1}
+ 1 {VALUE._col0}
+ handleSkewJoin: false
+ outputColumnNames: _col0, _col1, _col2
+ Select Operator
+ expressions:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: bigint
+ expr: _col2
+ type: string
+ outputColumnNames: _col0, _col1, _col2
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ Mux Operator
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0 {VALUE._col0} {VALUE._col1}
+ 1 {VALUE._col0}
+ handleSkewJoin: false
+ outputColumnNames: _col0, _col1, _col2
+ Select Operator
+ expressions:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: bigint
+ expr: _col2
+ type: string
+ outputColumnNames: _col0, _col1, _col2
+ 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
+ expr: _col1
+ type: bigint
+ expr: _col2
+ type: string
+ sort order: +++
+ tag: -1
+ value expressions:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: bigint
+ expr: _col2
+ type: string
+ Reduce Operator Tree:
+ Extract
+ 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 xx.key, xx.cnt, yy.key
+FROM
+(SELECT x.key as key, count(1) as cnt FROM src1 x JOIN src1 y ON (x.key = y.key) group by x.key) xx
+JOIN src yy
+ON xx.key=yy.key ORDER BY xx.key, xx.cnt, yy.key
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+PREHOOK: Input: default@src1
+#### A masked pattern was here ####
+POSTHOOK: query: SELECT xx.key, xx.cnt, yy.key
+FROM
+(SELECT x.key as key, count(1) as cnt FROM src1 x JOIN src1 y ON (x.key = y.key) group by x.key) xx
+JOIN src yy
+ON xx.key=yy.key ORDER BY xx.key, xx.cnt, yy.key
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+POSTHOOK: Input: default@src1
+#### A masked pattern was here ####
+128 1 128
+128 1 128
+128 1 128
+146 1 146
+146 1 146
+150 1 150
+213 1 213
+213 1 213
+224 1 224
+224 1 224
+238 1 238
+238 1 238
+255 1 255
+255 1 255
+273 1 273
+273 1 273
+273 1 273
+278 1 278
+278 1 278
+311 1 311
+311 1 311
+311 1 311
+369 1 369
+369 1 369
+369 1 369
+401 1 401
+401 1 401
+401 1 401
+401 1 401
+401 1 401
+406 1 406
+406 1 406
+406 1 406
+406 1 406
+66 1 66
+98 1 98
+98 1 98
+PREHOOK: query: -- When Correlation Optimizer is turned off, 4 MR jobs are needed.
+-- When Correlation Optimizer is turned on, 2 MR jobs are needed.
+-- The first job will evaluate subquery xx and xx join yy join zz.
+EXPLAIN
+SELECT xx.key, yy.key, yy.cnt
+FROM src1 xx
+JOIN src zz ON xx.key=zz.key
+JOIN
+(SELECT x.key as key, count(1) as cnt FROM src x JOIN src y ON (x.key = y.key) group by x.key) yy
+ON zz.key=yy.key
+ORDER BY xx.key, yy.key, yy.cnt
+PREHOOK: type: QUERY
+POSTHOOK: query: -- When Correlation Optimizer is turned off, 4 MR jobs are needed.
+-- When Correlation Optimizer is turned on, 2 MR jobs are needed.
+-- The first job will evaluate subquery xx and xx join yy join zz.
+EXPLAIN
+SELECT xx.key, yy.key, yy.cnt
+FROM src1 xx
+JOIN src zz ON xx.key=zz.key
+JOIN
+(SELECT x.key as key, count(1) as cnt FROM src x JOIN src y ON (x.key = y.key) group by x.key) yy
+ON zz.key=yy.key
+ORDER BY xx.key, yy.key, yy.cnt
+POSTHOOK: type: QUERY
+ABSTRACT SYNTAX TREE:
+ (TOK_QUERY (TOK_FROM (TOK_JOIN (TOK_JOIN (TOK_TABREF (TOK_TABNAME src1) xx) (TOK_TABREF (TOK_TABNAME src) zz) (= (. (TOK_TABLE_OR_COL xx) key) (. (TOK_TABLE_OR_COL zz) key))) (TOK_SUBQUERY (TOK_QUERY (TOK_FROM (TOK_JOIN (TOK_TABREF (TOK_TABNAME src) 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)))) yy) (= (. (TOK_TABLE_OR_COL zz) key) (. (TOK_TABLE_OR_COL yy) key)))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (. (TOK_TABLE_OR_COL xx) key)) (TOK_SELEXPR (. (TOK_TABLE_OR_COL yy) key)) (TOK_SELEXPR (. (TOK_TABLE_OR_COL yy) cnt))) (TOK_ORDERBY (TOK_TABSORTCOLNAMEASC (. (TOK_TABLE_OR_COL xx) key)) (TOK_TABSORTCOLNAMEASC (. (TOK_TABLE_OR_COL yy) key)) (TOK_TABSORTCOLNAMEASC (. (TOK_TABLE_OR_COL yy) cnt)))))
+
+STAGE DEPENDENCIES:
+ Stage-3 is a root stage
+ Stage-4 depends on stages: Stage-3
+ Stage-1 depends on stages: Stage-4
+ Stage-2 depends on stages: Stage-1
+ Stage-0 is a root stage
+
+STAGE PLANS:
+ Stage: Stage-3
+ Map Reduce
+ Alias -> Map Operator Tree:
+ yy: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
+ yy:y
+ TableScan
+ alias: y
[... 3035 lines stripped ...]