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 [13/15] - 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/correlationoptimizer7.q.out
URL: http://svn.apache.org/viewvc/hive/trunk/ql/src/test/results/clientpositive/correlationoptimizer7.q.out?rev=1504395&view=auto
==============================================================================
--- hive/trunk/ql/src/test/results/clientpositive/correlationoptimizer7.q.out (added)
+++ hive/trunk/ql/src/test/results/clientpositive/correlationoptimizer7.q.out Thu Jul 18 09:16:52 2013
@@ -0,0 +1,1048 @@
+PREHOOK: query: EXPLAIN
+SELECT xx.key, xx.cnt, yy.key, yy.value
+FROM (SELECT x.key AS key, count(1) AS cnt
+ FROM src x JOIN src1 y ON (x.key = y.key)
+ GROUP BY x.key) xx
+JOIN src1 yy
+ON xx.key=yy.key ORDER BY xx.key, xx.cnt, yy.key, yy.value
+PREHOOK: type: QUERY
+POSTHOOK: query: EXPLAIN
+SELECT xx.key, xx.cnt, yy.key, yy.value
+FROM (SELECT x.key AS key, count(1) AS cnt
+ FROM src x JOIN src1 y ON (x.key = y.key)
+ GROUP BY x.key) xx
+JOIN src1 yy
+ON xx.key=yy.key ORDER BY xx.key, xx.cnt, yy.key, yy.value
+POSTHOOK: type: QUERY
+ABSTRACT SYNTAX TREE:
+ (TOK_QUERY (TOK_FROM (TOK_JOIN (TOK_SUBQUERY (TOK_QUERY (TOK_FROM (TOK_JOIN (TOK_TABREF (TOK_TABNAME src) 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 src1) 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_SELEXPR (. (TOK_TABLE_OR_COL yy) value))) (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) value)))))
+
+STAGE DEPENDENCIES:
+ Stage-9 is a root stage
+ Stage-7 depends on stages: Stage-9
+ Stage-4 depends on stages: Stage-7
+ Stage-8 depends on stages: Stage-4
+ Stage-6 depends on stages: Stage-8
+ Stage-2 depends on stages: Stage-6
+ Stage-0 is a root stage
+
+STAGE PLANS:
+ Stage: Stage-9
+ 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-7
+ 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-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-8
+ Map Reduce Local Work
+ Alias -> Map Local Tables:
+ yy
+ Fetch Operator
+ limit: -1
+ Alias -> Map Local Operator Tree:
+ yy
+ TableScan
+ alias: yy
+ HashTable Sink Operator
+ condition expressions:
+ 0 {_col0} {_col1}
+ 1 {key} {value}
+ handleSkewJoin: false
+ keys:
+ 0 [Column[_col0]]
+ 1 [Column[key]]
+ Position of Big Table: 0
+
+ Stage: Stage-6
+ Map Reduce
+ Alias -> Map Operator Tree:
+ $INTNAME
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0 {_col0} {_col1}
+ 1 {key} {value}
+ handleSkewJoin: false
+ keys:
+ 0 [Column[_col0]]
+ 1 [Column[key]]
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Position of Big Table: 0
+ Select Operator
+ expressions:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: bigint
+ expr: _col2
+ type: string
+ expr: _col3
+ type: string
+ 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
+ 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
+ expr: _col1
+ type: bigint
+ expr: _col2
+ type: string
+ expr: _col3
+ type: string
+ sort order: ++++
+ tag: -1
+ value expressions:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: bigint
+ expr: _col2
+ type: string
+ expr: _col3
+ 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, yy.value
+FROM (SELECT x.key AS key, count(1) AS cnt
+ FROM src x JOIN src1 y ON (x.key = y.key)
+ GROUP BY x.key) xx
+JOIN src1 yy
+ON xx.key=yy.key ORDER BY xx.key, xx.cnt, yy.key, yy.value
+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.value
+FROM (SELECT x.key AS key, count(1) AS cnt
+ FROM src x JOIN src1 y ON (x.key = y.key)
+ GROUP BY x.key) xx
+JOIN src1 yy
+ON xx.key=yy.key ORDER BY xx.key, xx.cnt, yy.key, yy.value
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+POSTHOOK: Input: default@src1
+#### A masked pattern was here ####
+128 3 128
+146 2 146 val_146
+150 1 150 val_150
+213 2 213 val_213
+224 2 224
+238 2 238 val_238
+255 2 255 val_255
+273 3 273 val_273
+278 2 278 val_278
+311 3 311 val_311
+369 3 369
+401 5 401 val_401
+406 4 406 val_406
+66 1 66 val_66
+98 2 98 val_98
+PREHOOK: query: EXPLAIN
+SELECT xx.key, xx.cnt, yy.key, yy.value
+FROM (SELECT x.key AS key, count(1) AS cnt
+ FROM src x JOIN src1 y ON (x.key = y.key)
+ GROUP BY x.key) xx
+JOIN src1 yy
+ON xx.key=yy.key ORDER BY xx.key, xx.cnt, yy.key, yy.value
+PREHOOK: type: QUERY
+POSTHOOK: query: EXPLAIN
+SELECT xx.key, xx.cnt, yy.key, yy.value
+FROM (SELECT x.key AS key, count(1) AS cnt
+ FROM src x JOIN src1 y ON (x.key = y.key)
+ GROUP BY x.key) xx
+JOIN src1 yy
+ON xx.key=yy.key ORDER BY xx.key, xx.cnt, yy.key, yy.value
+POSTHOOK: type: QUERY
+ABSTRACT SYNTAX TREE:
+ (TOK_QUERY (TOK_FROM (TOK_JOIN (TOK_SUBQUERY (TOK_QUERY (TOK_FROM (TOK_JOIN (TOK_TABREF (TOK_TABNAME src) 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 src1) 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_SELEXPR (. (TOK_TABLE_OR_COL yy) value))) (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) value)))))
+
+STAGE DEPENDENCIES:
+ Stage-6 is a root stage
+ Stage-5 depends on stages: Stage-6
+ Stage-1 depends on stages: Stage-5
+ Stage-2 depends on stages: Stage-1
+ Stage-0 is a root stage
+
+STAGE PLANS:
+ Stage: Stage-6
+ 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-5
+ 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-1
+ 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: 0
+ value expressions:
+ 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
+ expr: value
+ type: string
+ 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: string
+ 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
+ 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: string
+ 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: string
+ sort order: ++++
+ tag: -1
+ value expressions:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: bigint
+ expr: _col2
+ type: string
+ expr: _col3
+ 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, yy.value
+FROM (SELECT x.key AS key, count(1) AS cnt
+ FROM src x JOIN src1 y ON (x.key = y.key)
+ GROUP BY x.key) xx
+JOIN src1 yy
+ON xx.key=yy.key ORDER BY xx.key, xx.cnt, yy.key, yy.value
+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.value
+FROM (SELECT x.key AS key, count(1) AS cnt
+ FROM src x JOIN src1 y ON (x.key = y.key)
+ GROUP BY x.key) xx
+JOIN src1 yy
+ON xx.key=yy.key ORDER BY xx.key, xx.cnt, yy.key, yy.value
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+POSTHOOK: Input: default@src1
+#### A masked pattern was here ####
+128 3 128
+146 2 146 val_146
+150 1 150 val_150
+213 2 213 val_213
+224 2 224
+238 2 238 val_238
+255 2 255 val_255
+273 3 273 val_273
+278 2 278 val_278
+311 3 311 val_311
+369 3 369
+401 5 401 val_401
+406 4 406 val_406
+66 1 66 val_66
+98 2 98 val_98
+PREHOOK: query: -- Without correlation optimizer, we will have 3 MR jobs.
+-- The first one is a MapJoin and Aggregation (in the Reduce Phase).
+-- The second one is another MapJoin. The third one is for ordering.
+-- With the correlation optimizer, right now, we still have
+-- 3 MR jobs. The first one is a MapJoin and the map-side aggregation (a map-only job).
+-- The second one have the reduce-side aggregation and the second join.
+-- The third one is for ordering.
+-- Although we have turned on hive.optimize.mapjoin.mapreduce, that optimizer
+-- can not handle the case that the MR job (the one which a map-only job will be merged in)
+-- has multiple inputs. We should improve that optimizer.
+EXPLAIN
+SELECT xx.key, xx.cnt, yy.key, yy.value
+FROM (SELECT x.key AS key, count(1) AS cnt
+ FROM src x JOIN src1 y ON (x.key = y.key)
+ GROUP BY x.key) xx
+JOIN src1 yy
+ON xx.key=yy.key ORDER BY xx.key, xx.cnt, yy.key, yy.value
+PREHOOK: type: QUERY
+POSTHOOK: query: -- Without correlation optimizer, we will have 3 MR jobs.
+-- The first one is a MapJoin and Aggregation (in the Reduce Phase).
+-- The second one is another MapJoin. The third one is for ordering.
+-- With the correlation optimizer, right now, we still have
+-- 3 MR jobs. The first one is a MapJoin and the map-side aggregation (a map-only job).
+-- The second one have the reduce-side aggregation and the second join.
+-- The third one is for ordering.
+-- Although we have turned on hive.optimize.mapjoin.mapreduce, that optimizer
+-- can not handle the case that the MR job (the one which a map-only job will be merged in)
+-- has multiple inputs. We should improve that optimizer.
+EXPLAIN
+SELECT xx.key, xx.cnt, yy.key, yy.value
+FROM (SELECT x.key AS key, count(1) AS cnt
+ FROM src x JOIN src1 y ON (x.key = y.key)
+ GROUP BY x.key) xx
+JOIN src1 yy
+ON xx.key=yy.key ORDER BY xx.key, xx.cnt, yy.key, yy.value
+POSTHOOK: type: QUERY
+ABSTRACT SYNTAX TREE:
+ (TOK_QUERY (TOK_FROM (TOK_JOIN (TOK_SUBQUERY (TOK_QUERY (TOK_FROM (TOK_JOIN (TOK_TABREF (TOK_TABNAME src) 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 src1) 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_SELEXPR (. (TOK_TABLE_OR_COL yy) value))) (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) value)))))
+
+STAGE DEPENDENCIES:
+ Stage-9 is a root stage
+ Stage-7 depends on stages: Stage-9
+ Stage-8 depends on stages: Stage-7
+ Stage-6 depends on stages: Stage-8
+ Stage-0 is a root stage
+
+STAGE PLANS:
+ Stage: Stage-9
+ 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-7
+ 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
+ Reduce Output Operator
+ key expressions:
+ expr: _col0
+ type: string
+ sort order: +
+ Map-reduce partition columns:
+ expr: _col0
+ type: string
+ tag: -1
+ value expressions:
+ expr: _col1
+ type: bigint
+ Local Work:
+ Map Reduce Local Work
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations:
+ expr: count(VALUE._col0)
+ bucketGroup: false
+ keys:
+ expr: KEY._col0
+ type: string
+ mode: mergepartial
+ outputColumnNames: _col0, _col1
+ Select Operator
+ expressions:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: bigint
+ outputColumnNames: _col0, _col1
+ 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
+ Map Reduce Local Work
+ Alias -> Map Local Tables:
+ yy
+ Fetch Operator
+ limit: -1
+ Alias -> Map Local Operator Tree:
+ yy
+ TableScan
+ alias: yy
+ HashTable Sink Operator
+ condition expressions:
+ 0 {_col0} {_col1}
+ 1 {key} {value}
+ handleSkewJoin: false
+ keys:
+ 0 [Column[_col0]]
+ 1 [Column[key]]
+ Position of Big Table: 0
+
+ Stage: Stage-6
+ Map Reduce
+ Alias -> Map Operator Tree:
+ $INTNAME
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0 {_col0} {_col1}
+ 1 {key} {value}
+ handleSkewJoin: false
+ keys:
+ 0 [Column[_col0]]
+ 1 [Column[key]]
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Position of Big Table: 0
+ Select Operator
+ expressions:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: bigint
+ expr: _col2
+ type: string
+ expr: _col3
+ type: string
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Reduce Output Operator
+ key expressions:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: bigint
+ expr: _col2
+ type: string
+ expr: _col3
+ type: string
+ sort order: ++++
+ tag: -1
+ value expressions:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: bigint
+ expr: _col2
+ type: string
+ expr: _col3
+ type: string
+ Local Work:
+ Map Reduce Local Work
+ 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.value
+FROM (SELECT x.key AS key, count(1) AS cnt
+ FROM src x JOIN src1 y ON (x.key = y.key)
+ GROUP BY x.key) xx
+JOIN src1 yy
+ON xx.key=yy.key ORDER BY xx.key, xx.cnt, yy.key, yy.value
+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.value
+FROM (SELECT x.key AS key, count(1) AS cnt
+ FROM src x JOIN src1 y ON (x.key = y.key)
+ GROUP BY x.key) xx
+JOIN src1 yy
+ON xx.key=yy.key ORDER BY xx.key, xx.cnt, yy.key, yy.value
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+POSTHOOK: Input: default@src1
+#### A masked pattern was here ####
+128 3 128
+146 2 146 val_146
+150 1 150 val_150
+213 2 213 val_213
+224 2 224
+238 2 238 val_238
+255 2 255 val_255
+273 3 273 val_273
+278 2 278 val_278
+311 3 311 val_311
+369 3 369
+401 5 401 val_401
+406 4 406 val_406
+66 1 66 val_66
+98 2 98 val_98
+PREHOOK: query: EXPLAIN
+SELECT xx.key, xx.cnt, yy.key, yy.value
+FROM (SELECT x.key AS key, count(1) AS cnt
+ FROM src x JOIN src1 y ON (x.key = y.key)
+ GROUP BY x.key) xx
+JOIN src1 yy
+ON xx.key=yy.key ORDER BY xx.key, xx.cnt, yy.key, yy.value
+PREHOOK: type: QUERY
+POSTHOOK: query: EXPLAIN
+SELECT xx.key, xx.cnt, yy.key, yy.value
+FROM (SELECT x.key AS key, count(1) AS cnt
+ FROM src x JOIN src1 y ON (x.key = y.key)
+ GROUP BY x.key) xx
+JOIN src1 yy
+ON xx.key=yy.key ORDER BY xx.key, xx.cnt, yy.key, yy.value
+POSTHOOK: type: QUERY
+ABSTRACT SYNTAX TREE:
+ (TOK_QUERY (TOK_FROM (TOK_JOIN (TOK_SUBQUERY (TOK_QUERY (TOK_FROM (TOK_JOIN (TOK_TABREF (TOK_TABNAME src) 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 src1) 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_SELEXPR (. (TOK_TABLE_OR_COL yy) value))) (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) value)))))
+
+STAGE DEPENDENCIES:
+ Stage-6 is a root stage
+ Stage-5 depends on stages: Stage-6
+ Stage-1 depends on stages: Stage-5
+ Stage-2 depends on stages: Stage-1
+ Stage-0 is a root stage
+
+STAGE PLANS:
+ Stage: Stage-6
+ 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-5
+ 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-1
+ 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: 0
+ value expressions:
+ 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
+ expr: value
+ type: string
+ 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: string
+ 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
+ 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: string
+ 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: string
+ sort order: ++++
+ tag: -1
+ value expressions:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: bigint
+ expr: _col2
+ type: string
+ expr: _col3
+ 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, yy.value
+FROM (SELECT x.key AS key, count(1) AS cnt
+ FROM src x JOIN src1 y ON (x.key = y.key)
+ GROUP BY x.key) xx
+JOIN src1 yy
+ON xx.key=yy.key ORDER BY xx.key, xx.cnt, yy.key, yy.value
+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.value
+FROM (SELECT x.key AS key, count(1) AS cnt
+ FROM src x JOIN src1 y ON (x.key = y.key)
+ GROUP BY x.key) xx
+JOIN src1 yy
+ON xx.key=yy.key ORDER BY xx.key, xx.cnt, yy.key, yy.value
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+POSTHOOK: Input: default@src1
+#### A masked pattern was here ####
+128 3 128
+146 2 146 val_146
+150 1 150 val_150
+213 2 213 val_213
+224 2 224
+238 2 238 val_238
+255 2 255 val_255
+273 3 273 val_273
+278 2 278 val_278
+311 3 311 val_311
+369 3 369
+401 5 401 val_401
+406 4 406 val_406
+66 1 66 val_66
+98 2 98 val_98