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 [9/15] - in /hive/trunk:
common/src/java/org/apache/hadoop/hive/conf/ conf/ ql/if/
ql/src/gen/thrift/gen-javabean/org/apache/hadoop/hive/ql/plan/api/
ql/src/java/org/apache/hadoop/hive/ql/exec/
ql/src/java/org/apache/hadoop/hive/ql...
Added: hive/trunk/ql/src/test/results/clientpositive/correlationoptimizer3.q.out
URL: http://svn.apache.org/viewvc/hive/trunk/ql/src/test/results/clientpositive/correlationoptimizer3.q.out?rev=1504395&view=auto
==============================================================================
--- hive/trunk/ql/src/test/results/clientpositive/correlationoptimizer3.q.out (added)
+++ hive/trunk/ql/src/test/results/clientpositive/correlationoptimizer3.q.out Thu Jul 18 09:16:52 2013
@@ -0,0 +1,1782 @@
+PREHOOK: query: -- When Correlation Optimizer is turned off, 5 MR jobs will be generated.
+-- When Correlation Optimizer is turned on, the subquery tmp will be evalauted
+-- in a single MR job (including the subquery b, the subquery d, and b join d).
+-- At the reduce side of the MR job evaluating tmp, two operation paths
+-- (for subquery b and d) have different depths. The path starting from subquery b
+-- is JOIN->GBY->JOIN, which has a depth of 3. While, the path starting from subquery d
+-- is JOIN->JOIN. We should be able to handle this case.
+EXPLAIN
+SELECT SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt)), SUM(HASH(tmp.value))
+FROM (SELECT b.key AS key, b.cnt AS cnt, d.value AS value
+ FROM (SELECT x.key, count(1) AS cnt FROM src1 x JOIN src y ON (x.key = y.key) group by x.key) b
+ JOIN (SELECT x.key, x.value FROM src1 x JOIN src y ON (x.key = y.key)) d
+ ON b.key = d.key) tmp
+PREHOOK: type: QUERY
+POSTHOOK: query: -- When Correlation Optimizer is turned off, 5 MR jobs will be generated.
+-- When Correlation Optimizer is turned on, the subquery tmp will be evalauted
+-- in a single MR job (including the subquery b, the subquery d, and b join d).
+-- At the reduce side of the MR job evaluating tmp, two operation paths
+-- (for subquery b and d) have different depths. The path starting from subquery b
+-- is JOIN->GBY->JOIN, which has a depth of 3. While, the path starting from subquery d
+-- is JOIN->JOIN. We should be able to handle this case.
+EXPLAIN
+SELECT SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt)), SUM(HASH(tmp.value))
+FROM (SELECT b.key AS key, b.cnt AS cnt, d.value AS value
+ FROM (SELECT x.key, count(1) AS cnt FROM src1 x JOIN src y ON (x.key = y.key) group by x.key) b
+ JOIN (SELECT x.key, x.value FROM src1 x JOIN src y ON (x.key = y.key)) d
+ ON b.key = d.key) tmp
+POSTHOOK: type: QUERY
+ABSTRACT SYNTAX TREE:
+ (TOK_QUERY (TOK_FROM (TOK_SUBQUERY (TOK_QUERY (TOK_FROM (TOK_JOIN (TOK_SUBQUERY (TOK_QUERY (TOK_FROM (TOK_JOIN (TOK_TABREF (TOK_TABNAME src1) x) (TOK_TABREF (TOK_TABNAME src) y) (= (. (TOK_TABLE_OR_COL x) key) (. (TOK_TABLE_OR_COL y) key)))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (. (TOK_TABLE_OR_COL x) key)) (TOK_SELEXPR (TOK_FUNCTION count 1) cnt)) (TOK_GROUPBY (. (TOK_TABLE_OR_COL x) key)))) b) (TOK_SUBQUERY (TOK_QUERY (TOK_FROM (TOK_JOIN (TOK_TABREF (TOK_TABNAME src1) x) (TOK_TABREF (TOK_TABNAME src) y) (= (. (TOK_TABLE_OR_COL x) key) (. (TOK_TABLE_OR_COL y) key)))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (. (TOK_TABLE_OR_COL x) key)) (TOK_SELEXPR (. (TOK_TABLE_OR_COL x) value))))) d) (= (. (TOK_TABLE_OR_COL b) key) (. (TOK_TABLE_OR_COL d) key)))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (. (TOK_TABLE_OR_COL b) key) key) (TOK_SELEXPR (. (TOK_TABLE_OR_COL b) cnt) cn
t) (TOK_SELEXPR (. (TOK_TABLE_OR_COL d) value) value)))) tmp)) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_FUNCTION SUM (TOK_FUNCTION HASH (. (TOK_TABLE_OR_COL tmp) key)))) (TOK_SELEXPR (TOK_FUNCTION SUM (TOK_FUNCTION HASH (. (TOK_TABLE_OR_COL tmp) cnt)))) (TOK_SELEXPR (TOK_FUNCTION SUM (TOK_FUNCTION HASH (. (TOK_TABLE_OR_COL tmp) value)))))))
+
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-2 depends on stages: Stage-1
+ Stage-3 depends on stages: Stage-2, Stage-6
+ Stage-4 depends on stages: Stage-3
+ Stage-6 is a root stage
+ Stage-0 is a root stage
+
+STAGE PLANS:
+ Stage: Stage-1
+ Map Reduce
+ Alias -> Map Operator Tree:
+ tmp:b:x
+ TableScan
+ alias: x
+ Reduce Output Operator
+ key expressions:
+ expr: key
+ type: string
+ sort order: +
+ Map-reduce partition columns:
+ expr: key
+ type: string
+ tag: 0
+ value expressions:
+ expr: key
+ type: string
+ tmp:b: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: 0
+ 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: 1
+ value expressions:
+ expr: _col1
+ type: string
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0 {VALUE._col0} {VALUE._col1}
+ 1 {VALUE._col1}
+ handleSkewJoin: false
+ outputColumnNames: _col0, _col1, _col3
+ Select Operator
+ expressions:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: bigint
+ expr: _col3
+ type: string
+ outputColumnNames: _col0, _col1, _col2
+ Group By Operator
+ aggregations:
+ expr: sum(hash(_col0))
+ expr: sum(hash(_col1))
+ expr: sum(hash(_col2))
+ bucketGroup: false
+ mode: hash
+ 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
+ sort order:
+ tag: -1
+ value expressions:
+ expr: _col0
+ type: bigint
+ expr: _col1
+ type: bigint
+ expr: _col2
+ type: bigint
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations:
+ expr: sum(VALUE._col0)
+ expr: sum(VALUE._col1)
+ expr: sum(VALUE._col2)
+ bucketGroup: false
+ mode: mergepartial
+ outputColumnNames: _col0, _col1, _col2
+ Select Operator
+ expressions:
+ expr: _col0
+ type: bigint
+ expr: _col1
+ type: bigint
+ expr: _col2
+ type: bigint
+ outputColumnNames: _col0, _col1, _col2
+ 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:
+ tmp:d: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
+ expr: value
+ type: string
+ tmp:d: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} {VALUE._col1}
+ 1
+ handleSkewJoin: false
+ outputColumnNames: _col0, _col1
+ Select Operator
+ expressions:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: string
+ 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 SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt)), SUM(HASH(tmp.value))
+FROM (SELECT b.key AS key, b.cnt AS cnt, d.value AS value
+ FROM (SELECT x.key, count(1) AS cnt FROM src1 x JOIN src y ON (x.key = y.key) group by x.key) b
+ JOIN (SELECT x.key, x.value FROM src1 x JOIN src y ON (x.key = y.key)) d
+ ON b.key = d.key) tmp
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+PREHOOK: Input: default@src1
+#### A masked pattern was here ####
+POSTHOOK: query: SELECT SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt)), SUM(HASH(tmp.value))
+FROM (SELECT b.key AS key, b.cnt AS cnt, d.value AS value
+ FROM (SELECT x.key, count(1) AS cnt FROM src1 x JOIN src y ON (x.key = y.key) group by x.key) b
+ JOIN (SELECT x.key, x.value FROM src1 x JOIN src y ON (x.key = y.key)) d
+ ON b.key = d.key) tmp
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+POSTHOOK: Input: default@src1
+#### A masked pattern was here ####
+1711763 107 3531902962
+PREHOOK: query: EXPLAIN
+SELECT SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt)), SUM(HASH(tmp.value))
+FROM (SELECT b.key AS key, b.cnt AS cnt, d.value AS value
+ FROM (SELECT x.key, count(1) AS cnt FROM src1 x JOIN src y ON (x.key = y.key) group by x.key) b
+ JOIN (SELECT x.key, x.value FROM src1 x JOIN src y ON (x.key = y.key)) d
+ ON b.key = d.key) tmp
+PREHOOK: type: QUERY
+POSTHOOK: query: EXPLAIN
+SELECT SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt)), SUM(HASH(tmp.value))
+FROM (SELECT b.key AS key, b.cnt AS cnt, d.value AS value
+ FROM (SELECT x.key, count(1) AS cnt FROM src1 x JOIN src y ON (x.key = y.key) group by x.key) b
+ JOIN (SELECT x.key, x.value FROM src1 x JOIN src y ON (x.key = y.key)) d
+ ON b.key = d.key) tmp
+POSTHOOK: type: QUERY
+ABSTRACT SYNTAX TREE:
+ (TOK_QUERY (TOK_FROM (TOK_SUBQUERY (TOK_QUERY (TOK_FROM (TOK_JOIN (TOK_SUBQUERY (TOK_QUERY (TOK_FROM (TOK_JOIN (TOK_TABREF (TOK_TABNAME src1) x) (TOK_TABREF (TOK_TABNAME src) y) (= (. (TOK_TABLE_OR_COL x) key) (. (TOK_TABLE_OR_COL y) key)))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (. (TOK_TABLE_OR_COL x) key)) (TOK_SELEXPR (TOK_FUNCTION count 1) cnt)) (TOK_GROUPBY (. (TOK_TABLE_OR_COL x) key)))) b) (TOK_SUBQUERY (TOK_QUERY (TOK_FROM (TOK_JOIN (TOK_TABREF (TOK_TABNAME src1) x) (TOK_TABREF (TOK_TABNAME src) y) (= (. (TOK_TABLE_OR_COL x) key) (. (TOK_TABLE_OR_COL y) key)))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (. (TOK_TABLE_OR_COL x) key)) (TOK_SELEXPR (. (TOK_TABLE_OR_COL x) value))))) d) (= (. (TOK_TABLE_OR_COL b) key) (. (TOK_TABLE_OR_COL d) key)))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (. (TOK_TABLE_OR_COL b) key) key) (TOK_SELEXPR (. (TOK_TABLE_OR_COL b) cnt) cn
t) (TOK_SELEXPR (. (TOK_TABLE_OR_COL d) value) value)))) tmp)) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_FUNCTION SUM (TOK_FUNCTION HASH (. (TOK_TABLE_OR_COL tmp) key)))) (TOK_SELEXPR (TOK_FUNCTION SUM (TOK_FUNCTION HASH (. (TOK_TABLE_OR_COL tmp) cnt)))) (TOK_SELEXPR (TOK_FUNCTION SUM (TOK_FUNCTION HASH (. (TOK_TABLE_OR_COL tmp) value)))))))
+
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-2 depends on stages: Stage-1
+ Stage-0 is a root stage
+
+STAGE PLANS:
+ Stage: Stage-1
+ Map Reduce
+ Alias -> Map Operator Tree:
+ tmp:b:x
+ TableScan
+ alias: x
+ Reduce Output Operator
+ key expressions:
+ expr: key
+ type: string
+ sort order: +
+ Map-reduce partition columns:
+ expr: key
+ type: string
+ tag: 0
+ value expressions:
+ expr: key
+ type: string
+ tmp:b: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
+ tmp:d: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
+ expr: value
+ type: string
+ tmp:d: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._col1}
+ handleSkewJoin: false
+ outputColumnNames: _col0, _col1, _col3
+ Select Operator
+ expressions:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: bigint
+ expr: _col3
+ type: string
+ outputColumnNames: _col0, _col1, _col2
+ Group By Operator
+ aggregations:
+ expr: sum(hash(_col0))
+ expr: sum(hash(_col1))
+ expr: sum(hash(_col2))
+ bucketGroup: false
+ mode: hash
+ 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} {VALUE._col1}
+ 1
+ handleSkewJoin: false
+ outputColumnNames: _col0, _col1
+ Select Operator
+ expressions:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: string
+ outputColumnNames: _col0, _col1
+ Mux Operator
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0 {VALUE._col0} {VALUE._col1}
+ 1 {VALUE._col1}
+ handleSkewJoin: false
+ outputColumnNames: _col0, _col1, _col3
+ Select Operator
+ expressions:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: bigint
+ expr: _col3
+ type: string
+ outputColumnNames: _col0, _col1, _col2
+ Group By Operator
+ aggregations:
+ expr: sum(hash(_col0))
+ expr: sum(hash(_col1))
+ expr: sum(hash(_col2))
+ bucketGroup: false
+ mode: hash
+ 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
+ sort order:
+ tag: -1
+ value expressions:
+ expr: _col0
+ type: bigint
+ expr: _col1
+ type: bigint
+ expr: _col2
+ type: bigint
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations:
+ expr: sum(VALUE._col0)
+ expr: sum(VALUE._col1)
+ expr: sum(VALUE._col2)
+ bucketGroup: false
+ mode: mergepartial
+ outputColumnNames: _col0, _col1, _col2
+ Select Operator
+ expressions:
+ expr: _col0
+ type: bigint
+ expr: _col1
+ type: bigint
+ expr: _col2
+ type: bigint
+ outputColumnNames: _col0, _col1, _col2
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+
+
+PREHOOK: query: SELECT SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt)), SUM(HASH(tmp.value))
+FROM (SELECT b.key AS key, b.cnt AS cnt, d.value AS value
+ FROM (SELECT x.key, count(1) AS cnt FROM src1 x JOIN src y ON (x.key = y.key) group by x.key) b
+ JOIN (SELECT x.key, x.value FROM src1 x JOIN src y ON (x.key = y.key)) d
+ ON b.key = d.key) tmp
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+PREHOOK: Input: default@src1
+#### A masked pattern was here ####
+POSTHOOK: query: SELECT SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt)), SUM(HASH(tmp.value))
+FROM (SELECT b.key AS key, b.cnt AS cnt, d.value AS value
+ FROM (SELECT x.key, count(1) AS cnt FROM src1 x JOIN src y ON (x.key = y.key) group by x.key) b
+ JOIN (SELECT x.key, x.value FROM src1 x JOIN src y ON (x.key = y.key)) d
+ ON b.key = d.key) tmp
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+POSTHOOK: Input: default@src1
+#### A masked pattern was here ####
+1711763 107 3531902962
+PREHOOK: query: -- Enable hive.auto.convert.join.
+EXPLAIN
+SELECT SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt)), SUM(HASH(tmp.value))
+FROM (SELECT b.key AS key, b.cnt AS cnt, d.value AS value
+ FROM (SELECT x.key, count(1) AS cnt FROM src1 x JOIN src y ON (x.key = y.key) group by x.key) b
+ JOIN (SELECT x.key, x.value FROM src1 x JOIN src y ON (x.key = y.key)) d
+ ON b.key = d.key) tmp
+PREHOOK: type: QUERY
+POSTHOOK: query: -- Enable hive.auto.convert.join.
+EXPLAIN
+SELECT SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt)), SUM(HASH(tmp.value))
+FROM (SELECT b.key AS key, b.cnt AS cnt, d.value AS value
+ FROM (SELECT x.key, count(1) AS cnt FROM src1 x JOIN src y ON (x.key = y.key) group by x.key) b
+ JOIN (SELECT x.key, x.value FROM src1 x JOIN src y ON (x.key = y.key)) d
+ ON b.key = d.key) tmp
+POSTHOOK: type: QUERY
+ABSTRACT SYNTAX TREE:
+ (TOK_QUERY (TOK_FROM (TOK_SUBQUERY (TOK_QUERY (TOK_FROM (TOK_JOIN (TOK_SUBQUERY (TOK_QUERY (TOK_FROM (TOK_JOIN (TOK_TABREF (TOK_TABNAME src1) x) (TOK_TABREF (TOK_TABNAME src) y) (= (. (TOK_TABLE_OR_COL x) key) (. (TOK_TABLE_OR_COL y) key)))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (. (TOK_TABLE_OR_COL x) key)) (TOK_SELEXPR (TOK_FUNCTION count 1) cnt)) (TOK_GROUPBY (. (TOK_TABLE_OR_COL x) key)))) b) (TOK_SUBQUERY (TOK_QUERY (TOK_FROM (TOK_JOIN (TOK_TABREF (TOK_TABNAME src1) x) (TOK_TABREF (TOK_TABNAME src) y) (= (. (TOK_TABLE_OR_COL x) key) (. (TOK_TABLE_OR_COL y) key)))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (. (TOK_TABLE_OR_COL x) key)) (TOK_SELEXPR (. (TOK_TABLE_OR_COL x) value))))) d) (= (. (TOK_TABLE_OR_COL b) key) (. (TOK_TABLE_OR_COL d) key)))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (. (TOK_TABLE_OR_COL b) key) key) (TOK_SELEXPR (. (TOK_TABLE_OR_COL b) cnt) cn
t) (TOK_SELEXPR (. (TOK_TABLE_OR_COL d) value) value)))) tmp)) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_FUNCTION SUM (TOK_FUNCTION HASH (. (TOK_TABLE_OR_COL tmp) key)))) (TOK_SELEXPR (TOK_FUNCTION SUM (TOK_FUNCTION HASH (. (TOK_TABLE_OR_COL tmp) cnt)))) (TOK_SELEXPR (TOK_FUNCTION SUM (TOK_FUNCTION HASH (. (TOK_TABLE_OR_COL tmp) value)))))))
+
+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:
+ tmp:b:x
+ Fetch Operator
+ limit: -1
+ Alias -> Map Local Operator Tree:
+ tmp:b:x
+ TableScan
+ alias: x
+ HashTable Sink Operator
+ condition expressions:
+ 0 {key}
+ 1
+ handleSkewJoin: false
+ keys:
+ 0 [Column[key]]
+ 1 [Column[key]]
+ Position of Big Table: 1
+
+ Stage: Stage-7
+ Map Reduce
+ Alias -> Map Operator Tree:
+ tmp:b:y
+ TableScan
+ alias: y
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0 {key}
+ 1
+ handleSkewJoin: false
+ keys:
+ 0 [Column[key]]
+ 1 [Column[key]]
+ outputColumnNames: _col0
+ Position of Big Table: 1
+ Select Operator
+ expressions:
+ expr: _col0
+ type: string
+ outputColumnNames: _col0
+ Group By Operator
+ aggregations:
+ expr: count(1)
+ bucketGroup: false
+ keys:
+ expr: _col0
+ type: string
+ mode: hash
+ outputColumnNames: _col0, _col1
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ Local Work:
+ Map Reduce Local Work
+
+ Stage: Stage-2
+ Map Reduce
+ Alias -> Map Operator Tree:
+#### A masked pattern was here ####
+ Reduce Output Operator
+ key expressions:
+ expr: _col0
+ type: string
+ sort order: +
+ Map-reduce partition columns:
+ expr: _col0
+ type: string
+ tag: 0
+ 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: 1
+ value expressions:
+ expr: _col1
+ 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._col1}
+ handleSkewJoin: false
+ outputColumnNames: _col0, _col1, _col3
+ Select Operator
+ expressions:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: bigint
+ expr: _col3
+ type: string
+ outputColumnNames: _col0, _col1, _col2
+ Group By Operator
+ aggregations:
+ expr: sum(hash(_col0))
+ expr: sum(hash(_col1))
+ expr: sum(hash(_col2))
+ bucketGroup: false
+ mode: hash
+ 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._col1}
+ handleSkewJoin: false
+ outputColumnNames: _col0, _col1, _col3
+ Select Operator
+ expressions:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: bigint
+ expr: _col3
+ type: string
+ outputColumnNames: _col0, _col1, _col2
+ Group By Operator
+ aggregations:
+ expr: sum(hash(_col0))
+ expr: sum(hash(_col1))
+ expr: sum(hash(_col2))
+ bucketGroup: false
+ mode: hash
+ 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
+ sort order:
+ tag: -1
+ value expressions:
+ expr: _col0
+ type: bigint
+ expr: _col1
+ type: bigint
+ expr: _col2
+ type: bigint
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations:
+ expr: sum(VALUE._col0)
+ expr: sum(VALUE._col1)
+ expr: sum(VALUE._col2)
+ bucketGroup: false
+ mode: mergepartial
+ outputColumnNames: _col0, _col1, _col2
+ Select Operator
+ expressions:
+ expr: _col0
+ type: bigint
+ expr: _col1
+ type: bigint
+ expr: _col2
+ type: bigint
+ outputColumnNames: _col0, _col1, _col2
+ 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:
+ tmp:d:x
+ Fetch Operator
+ limit: -1
+ Alias -> Map Local Operator Tree:
+ tmp:d:x
+ TableScan
+ alias: x
+ HashTable Sink Operator
+ condition expressions:
+ 0 {key} {value}
+ 1
+ handleSkewJoin: false
+ keys:
+ 0 [Column[key]]
+ 1 [Column[key]]
+ Position of Big Table: 1
+
+ Stage: Stage-8
+ Map Reduce
+ Alias -> Map Operator Tree:
+ tmp:d:y
+ TableScan
+ alias: y
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0 {key} {value}
+ 1
+ handleSkewJoin: false
+ keys:
+ 0 [Column[key]]
+ 1 [Column[key]]
+ outputColumnNames: _col0, _col1
+ Position of Big Table: 1
+ Select Operator
+ expressions:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: string
+ 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 SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt)), SUM(HASH(tmp.value))
+FROM (SELECT b.key AS key, b.cnt AS cnt, d.value AS value
+ FROM (SELECT x.key, count(1) AS cnt FROM src1 x JOIN src y ON (x.key = y.key) group by x.key) b
+ JOIN (SELECT x.key, x.value FROM src1 x JOIN src y ON (x.key = y.key)) d
+ ON b.key = d.key) tmp
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+PREHOOK: Input: default@src1
+#### A masked pattern was here ####
+POSTHOOK: query: SELECT SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt)), SUM(HASH(tmp.value))
+FROM (SELECT b.key AS key, b.cnt AS cnt, d.value AS value
+ FROM (SELECT x.key, count(1) AS cnt FROM src1 x JOIN src y ON (x.key = y.key) group by x.key) b
+ JOIN (SELECT x.key, x.value FROM src1 x JOIN src y ON (x.key = y.key)) d
+ ON b.key = d.key) tmp
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+POSTHOOK: Input: default@src1
+#### A masked pattern was here ####
+1711763 107 3531902962
+PREHOOK: query: EXPLAIN
+SELECT SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt)), SUM(HASH(tmp.value))
+FROM (SELECT d.key AS key, d.cnt AS cnt, b.value as value
+ FROM (SELECT x.key, x.value FROM src1 x JOIN src y ON (x.key = y.key)) b
+ JOIN (SELECT x.key, count(1) AS cnt FROM src1 x JOIN src y ON (x.key = y.key) group by x.key) d
+ ON b.key = d.key) tmp
+PREHOOK: type: QUERY
+POSTHOOK: query: EXPLAIN
+SELECT SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt)), SUM(HASH(tmp.value))
+FROM (SELECT d.key AS key, d.cnt AS cnt, b.value as value
+ FROM (SELECT x.key, x.value FROM src1 x JOIN src y ON (x.key = y.key)) b
+ JOIN (SELECT x.key, count(1) AS cnt FROM src1 x JOIN src y ON (x.key = y.key) group by x.key) d
+ ON b.key = d.key) tmp
+POSTHOOK: type: QUERY
+ABSTRACT SYNTAX TREE:
+ (TOK_QUERY (TOK_FROM (TOK_SUBQUERY (TOK_QUERY (TOK_FROM (TOK_JOIN (TOK_SUBQUERY (TOK_QUERY (TOK_FROM (TOK_JOIN (TOK_TABREF (TOK_TABNAME src1) x) (TOK_TABREF (TOK_TABNAME src) y) (= (. (TOK_TABLE_OR_COL x) key) (. (TOK_TABLE_OR_COL y) key)))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (. (TOK_TABLE_OR_COL x) key)) (TOK_SELEXPR (. (TOK_TABLE_OR_COL x) value))))) b) (TOK_SUBQUERY (TOK_QUERY (TOK_FROM (TOK_JOIN (TOK_TABREF (TOK_TABNAME src1) x) (TOK_TABREF (TOK_TABNAME src) y) (= (. (TOK_TABLE_OR_COL x) key) (. (TOK_TABLE_OR_COL y) key)))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (. (TOK_TABLE_OR_COL x) key)) (TOK_SELEXPR (TOK_FUNCTION count 1) cnt)) (TOK_GROUPBY (. (TOK_TABLE_OR_COL x) key)))) d) (= (. (TOK_TABLE_OR_COL b) key) (. (TOK_TABLE_OR_COL d) key)))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (. (TOK_TABLE_OR_COL d) key) key) (TOK_SELEXPR (. (TOK_TABLE_OR_COL d) cnt) cn
t) (TOK_SELEXPR (. (TOK_TABLE_OR_COL b) value) value)))) tmp)) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_FUNCTION SUM (TOK_FUNCTION HASH (. (TOK_TABLE_OR_COL tmp) key)))) (TOK_SELEXPR (TOK_FUNCTION SUM (TOK_FUNCTION HASH (. (TOK_TABLE_OR_COL tmp) cnt)))) (TOK_SELEXPR (TOK_FUNCTION SUM (TOK_FUNCTION HASH (. (TOK_TABLE_OR_COL tmp) value)))))))
+
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-2 depends on stages: Stage-1, Stage-6
+ Stage-3 depends on stages: Stage-2
+ Stage-5 is a root stage
+ Stage-6 depends on stages: Stage-5
+ Stage-0 is a root stage
+
+STAGE PLANS:
+ Stage: Stage-1
+ Map Reduce
+ Alias -> Map Operator Tree:
+ tmp:b: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
+ expr: value
+ type: string
+ tmp:b: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} {VALUE._col1}
+ 1
+ handleSkewJoin: false
+ outputColumnNames: _col0, _col1
+ Select Operator
+ expressions:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: string
+ 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: 0
+ value expressions:
+ expr: _col1
+ type: string
+ $INTNAME1
+ Reduce Output Operator
+ key expressions:
+ expr: _col0
+ type: string
+ sort order: +
+ Map-reduce partition columns:
+ expr: _col0
+ type: string
+ tag: 1
+ value expressions:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: bigint
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0 {VALUE._col1}
+ 1 {VALUE._col0} {VALUE._col1}
+ handleSkewJoin: false
+ outputColumnNames: _col1, _col2, _col3
+ Select Operator
+ expressions:
+ expr: _col2
+ type: string
+ expr: _col3
+ type: bigint
+ expr: _col1
+ type: string
+ outputColumnNames: _col0, _col1, _col2
+ Group By Operator
+ aggregations:
+ expr: sum(hash(_col0))
+ expr: sum(hash(_col1))
+ expr: sum(hash(_col2))
+ bucketGroup: false
+ mode: hash
+ 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
+ sort order:
+ tag: -1
+ value expressions:
+ expr: _col0
+ type: bigint
+ expr: _col1
+ type: bigint
+ expr: _col2
+ type: bigint
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations:
+ expr: sum(VALUE._col0)
+ expr: sum(VALUE._col1)
+ expr: sum(VALUE._col2)
+ bucketGroup: false
+ mode: mergepartial
+ outputColumnNames: _col0, _col1, _col2
+ Select Operator
+ expressions:
+ expr: _col0
+ type: bigint
+ expr: _col1
+ type: bigint
+ expr: _col2
+ type: bigint
+ outputColumnNames: _col0, _col1, _col2
+ 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-5
+ Map Reduce
+ Alias -> Map Operator Tree:
+ tmp:d:x
+ TableScan
+ alias: x
+ Reduce Output Operator
+ key expressions:
+ expr: key
+ type: string
+ sort order: +
+ Map-reduce partition columns:
+ expr: key
+ type: string
+ tag: 0
+ value expressions:
+ expr: key
+ type: string
+ tmp:d: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-6
+ 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 SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt)), SUM(HASH(tmp.value))
+FROM (SELECT d.key AS key, d.cnt AS cnt, b.value as value
+ FROM (SELECT x.key, x.value FROM src1 x JOIN src y ON (x.key = y.key)) b
+ JOIN (SELECT x.key, count(1) AS cnt FROM src1 x JOIN src y ON (x.key = y.key) group by x.key) d
+ ON b.key = d.key) tmp
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+PREHOOK: Input: default@src1
+#### A masked pattern was here ####
+POSTHOOK: query: SELECT SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt)), SUM(HASH(tmp.value))
+FROM (SELECT d.key AS key, d.cnt AS cnt, b.value as value
+ FROM (SELECT x.key, x.value FROM src1 x JOIN src y ON (x.key = y.key)) b
+ JOIN (SELECT x.key, count(1) AS cnt FROM src1 x JOIN src y ON (x.key = y.key) group by x.key) d
+ ON b.key = d.key) tmp
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+POSTHOOK: Input: default@src1
+#### A masked pattern was here ####
+1711763 107 3531902962
+PREHOOK: query: EXPLAIN
+SELECT SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt)), SUM(HASH(tmp.value))
+FROM (SELECT d.key AS key, d.cnt AS cnt, b.value as value
+ FROM (SELECT x.key, x.value FROM src1 x JOIN src y ON (x.key = y.key)) b
+ JOIN (SELECT x.key, count(1) AS cnt FROM src1 x JOIN src y ON (x.key = y.key) group by x.key) d
+ ON b.key = d.key) tmp
+PREHOOK: type: QUERY
+POSTHOOK: query: EXPLAIN
+SELECT SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt)), SUM(HASH(tmp.value))
+FROM (SELECT d.key AS key, d.cnt AS cnt, b.value as value
+ FROM (SELECT x.key, x.value FROM src1 x JOIN src y ON (x.key = y.key)) b
+ JOIN (SELECT x.key, count(1) AS cnt FROM src1 x JOIN src y ON (x.key = y.key) group by x.key) d
+ ON b.key = d.key) tmp
+POSTHOOK: type: QUERY
+ABSTRACT SYNTAX TREE:
+ (TOK_QUERY (TOK_FROM (TOK_SUBQUERY (TOK_QUERY (TOK_FROM (TOK_JOIN (TOK_SUBQUERY (TOK_QUERY (TOK_FROM (TOK_JOIN (TOK_TABREF (TOK_TABNAME src1) x) (TOK_TABREF (TOK_TABNAME src) y) (= (. (TOK_TABLE_OR_COL x) key) (. (TOK_TABLE_OR_COL y) key)))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (. (TOK_TABLE_OR_COL x) key)) (TOK_SELEXPR (. (TOK_TABLE_OR_COL x) value))))) b) (TOK_SUBQUERY (TOK_QUERY (TOK_FROM (TOK_JOIN (TOK_TABREF (TOK_TABNAME src1) x) (TOK_TABREF (TOK_TABNAME src) y) (= (. (TOK_TABLE_OR_COL x) key) (. (TOK_TABLE_OR_COL y) key)))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (. (TOK_TABLE_OR_COL x) key)) (TOK_SELEXPR (TOK_FUNCTION count 1) cnt)) (TOK_GROUPBY (. (TOK_TABLE_OR_COL x) key)))) d) (= (. (TOK_TABLE_OR_COL b) key) (. (TOK_TABLE_OR_COL d) key)))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (. (TOK_TABLE_OR_COL d) key) key) (TOK_SELEXPR (. (TOK_TABLE_OR_COL d) cnt) cn
t) (TOK_SELEXPR (. (TOK_TABLE_OR_COL b) value) value)))) tmp)) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_FUNCTION SUM (TOK_FUNCTION HASH (. (TOK_TABLE_OR_COL tmp) key)))) (TOK_SELEXPR (TOK_FUNCTION SUM (TOK_FUNCTION HASH (. (TOK_TABLE_OR_COL tmp) cnt)))) (TOK_SELEXPR (TOK_FUNCTION SUM (TOK_FUNCTION HASH (. (TOK_TABLE_OR_COL tmp) value)))))))
+
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-2 depends on stages: Stage-1
+ Stage-0 is a root stage
+
+STAGE PLANS:
+ Stage: Stage-1
+ Map Reduce
+ Alias -> Map Operator Tree:
+ tmp:b: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
+ expr: value
+ type: string
+ tmp:b: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
+ tmp:d: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
+ tmp:d: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} {VALUE._col1}
+ 1
+ handleSkewJoin: false
+ outputColumnNames: _col0, _col1
+ Select Operator
+ expressions:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: string
+ outputColumnNames: _col0, _col1
+ Mux Operator
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0 {VALUE._col1}
+ 1 {VALUE._col0} {VALUE._col1}
+ handleSkewJoin: false
+ outputColumnNames: _col1, _col2, _col3
+ Select Operator
+ expressions:
+ expr: _col2
+ type: string
+ expr: _col3
+ type: bigint
+ expr: _col1
+ type: string
+ outputColumnNames: _col0, _col1, _col2
+ Group By Operator
+ aggregations:
+ expr: sum(hash(_col0))
+ expr: sum(hash(_col1))
+ expr: sum(hash(_col2))
+ bucketGroup: false
+ mode: hash
+ 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._col1}
+ 1 {VALUE._col0} {VALUE._col1}
+ handleSkewJoin: false
+ outputColumnNames: _col1, _col2, _col3
+ Select Operator
+ expressions:
+ expr: _col2
+ type: string
+ expr: _col3
+ type: bigint
+ expr: _col1
+ type: string
+ outputColumnNames: _col0, _col1, _col2
+ Group By Operator
+ aggregations:
+ expr: sum(hash(_col0))
+ expr: sum(hash(_col1))
+ expr: sum(hash(_col2))
+ bucketGroup: false
+ mode: hash
+ 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
+ sort order:
+ tag: -1
+ value expressions:
+ expr: _col0
+ type: bigint
+ expr: _col1
+ type: bigint
+ expr: _col2
+ type: bigint
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations:
+ expr: sum(VALUE._col0)
+ expr: sum(VALUE._col1)
+ expr: sum(VALUE._col2)
+ bucketGroup: false
+ mode: mergepartial
+ outputColumnNames: _col0, _col1, _col2
+ Select Operator
+ expressions:
+ expr: _col0
+ type: bigint
+ expr: _col1
+ type: bigint
+ expr: _col2
+ type: bigint
+ outputColumnNames: _col0, _col1, _col2
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+
+
+PREHOOK: query: SELECT SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt)), SUM(HASH(tmp.value))
+FROM (SELECT d.key AS key, d.cnt AS cnt, b.value as value
+ FROM (SELECT x.key, x.value FROM src1 x JOIN src y ON (x.key = y.key)) b
+ JOIN (SELECT x.key, count(1) AS cnt FROM src1 x JOIN src y ON (x.key = y.key) group by x.key) d
+ ON b.key = d.key) tmp
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+PREHOOK: Input: default@src1
+#### A masked pattern was here ####
+POSTHOOK: query: SELECT SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt)), SUM(HASH(tmp.value))
+FROM (SELECT d.key AS key, d.cnt AS cnt, b.value as value
+ FROM (SELECT x.key, x.value FROM src1 x JOIN src y ON (x.key = y.key)) b
+ JOIN (SELECT x.key, count(1) AS cnt FROM src1 x JOIN src y ON (x.key = y.key) group by x.key) d
+ ON b.key = d.key) tmp
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+POSTHOOK: Input: default@src1
+#### A masked pattern was here ####
+1711763 107 3531902962
+PREHOOK: query: -- Enable hive.auto.convert.join.
+EXPLAIN
+SELECT SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt)), SUM(HASH(tmp.value))
+FROM (SELECT d.key AS key, d.cnt AS cnt, b.value as value
+ FROM (SELECT x.key, x.value FROM src1 x JOIN src y ON (x.key = y.key)) b
+ JOIN (SELECT x.key, count(1) AS cnt FROM src1 x JOIN src y ON (x.key = y.key) group by x.key) d
+ ON b.key = d.key) tmp
+PREHOOK: type: QUERY
+POSTHOOK: query: -- Enable hive.auto.convert.join.
+EXPLAIN
+SELECT SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt)), SUM(HASH(tmp.value))
+FROM (SELECT d.key AS key, d.cnt AS cnt, b.value as value
+ FROM (SELECT x.key, x.value FROM src1 x JOIN src y ON (x.key = y.key)) b
+ JOIN (SELECT x.key, count(1) AS cnt FROM src1 x JOIN src y ON (x.key = y.key) group by x.key) d
+ ON b.key = d.key) tmp
+POSTHOOK: type: QUERY
+ABSTRACT SYNTAX TREE:
+ (TOK_QUERY (TOK_FROM (TOK_SUBQUERY (TOK_QUERY (TOK_FROM (TOK_JOIN (TOK_SUBQUERY (TOK_QUERY (TOK_FROM (TOK_JOIN (TOK_TABREF (TOK_TABNAME src1) x) (TOK_TABREF (TOK_TABNAME src) y) (= (. (TOK_TABLE_OR_COL x) key) (. (TOK_TABLE_OR_COL y) key)))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (. (TOK_TABLE_OR_COL x) key)) (TOK_SELEXPR (. (TOK_TABLE_OR_COL x) value))))) b) (TOK_SUBQUERY (TOK_QUERY (TOK_FROM (TOK_JOIN (TOK_TABREF (TOK_TABNAME src1) x) (TOK_TABREF (TOK_TABNAME src) y) (= (. (TOK_TABLE_OR_COL x) key) (. (TOK_TABLE_OR_COL y) key)))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (. (TOK_TABLE_OR_COL x) key)) (TOK_SELEXPR (TOK_FUNCTION count 1) cnt)) (TOK_GROUPBY (. (TOK_TABLE_OR_COL x) key)))) d) (= (. (TOK_TABLE_OR_COL b) key) (. (TOK_TABLE_OR_COL d) key)))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (. (TOK_TABLE_OR_COL d) key) key) (TOK_SELEXPR (. (TOK_TABLE_OR_COL d) cnt) cn
t) (TOK_SELEXPR (. (TOK_TABLE_OR_COL b) value) value)))) tmp)) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_FUNCTION SUM (TOK_FUNCTION HASH (. (TOK_TABLE_OR_COL tmp) key)))) (TOK_SELEXPR (TOK_FUNCTION SUM (TOK_FUNCTION HASH (. (TOK_TABLE_OR_COL tmp) cnt)))) (TOK_SELEXPR (TOK_FUNCTION SUM (TOK_FUNCTION HASH (. (TOK_TABLE_OR_COL tmp) value)))))))
+
+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:
+ tmp:b:x
+ Fetch Operator
+ limit: -1
+ Alias -> Map Local Operator Tree:
+ tmp:b:x
+ TableScan
+ alias: x
+ HashTable Sink Operator
+ condition expressions:
+ 0 {key} {value}
+ 1
+ handleSkewJoin: false
+ keys:
+ 0 [Column[key]]
+ 1 [Column[key]]
+ Position of Big Table: 1
+
+ Stage: Stage-7
+ Map Reduce
+ Alias -> Map Operator Tree:
+ tmp:b:y
+ TableScan
+ alias: y
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0 {key} {value}
+ 1
+ handleSkewJoin: false
+ keys:
+ 0 [Column[key]]
+ 1 [Column[key]]
+ outputColumnNames: _col0, _col1
+ Position of Big Table: 1
+ Select Operator
+ expressions:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: string
+ 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: 0
+ value expressions:
+ expr: _col1
+ type: string
+#### 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:
+ Demux Operator
+ Mux Operator
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0 {VALUE._col1}
+ 1 {VALUE._col0} {VALUE._col1}
+ handleSkewJoin: false
+ outputColumnNames: _col1, _col2, _col3
+ Select Operator
+ expressions:
+ expr: _col2
+ type: string
+ expr: _col3
+ type: bigint
+ expr: _col1
+ type: string
+ outputColumnNames: _col0, _col1, _col2
+ Group By Operator
+ aggregations:
+ expr: sum(hash(_col0))
+ expr: sum(hash(_col1))
+ expr: sum(hash(_col2))
+ bucketGroup: false
+ mode: hash
+ 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._col1}
+ 1 {VALUE._col0} {VALUE._col1}
+ handleSkewJoin: false
+ outputColumnNames: _col1, _col2, _col3
+ Select Operator
+ expressions:
+ expr: _col2
+ type: string
+ expr: _col3
+ type: bigint
+ expr: _col1
+ type: string
+ outputColumnNames: _col0, _col1, _col2
+ Group By Operator
+ aggregations:
+ expr: sum(hash(_col0))
+ expr: sum(hash(_col1))
+ expr: sum(hash(_col2))
+ bucketGroup: false
+ mode: hash
+ 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
+ sort order:
+ tag: -1
+ value expressions:
+ expr: _col0
+ type: bigint
+ expr: _col1
+ type: bigint
+ expr: _col2
+ type: bigint
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations:
+ expr: sum(VALUE._col0)
+ expr: sum(VALUE._col1)
+ expr: sum(VALUE._col2)
+ bucketGroup: false
+ mode: mergepartial
+ outputColumnNames: _col0, _col1, _col2
+ Select Operator
+ expressions:
+ expr: _col0
+ type: bigint
+ expr: _col1
+ type: bigint
+ expr: _col2
+ type: bigint
+ outputColumnNames: _col0, _col1, _col2
+ 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:
+ tmp:d:x
+ Fetch Operator
+ limit: -1
+ Alias -> Map Local Operator Tree:
+ tmp:d:x
+ TableScan
+ alias: x
+ HashTable Sink Operator
+ condition expressions:
+ 0 {key}
+ 1
+ handleSkewJoin: false
+ keys:
+ 0 [Column[key]]
+ 1 [Column[key]]
+ Position of Big Table: 1
+
+ Stage: Stage-8
+ Map Reduce
+ Alias -> Map Operator Tree:
+ tmp:d:y
+ TableScan
+ alias: y
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0 {key}
+ 1
+ handleSkewJoin: false
+ keys:
+ 0 [Column[key]]
+ 1 [Column[key]]
+ outputColumnNames: _col0
+ Position of Big Table: 1
+ Select Operator
+ expressions:
+ expr: _col0
+ type: string
+ outputColumnNames: _col0
+ Group By Operator
+ aggregations:
+ expr: count(1)
+ bucketGroup: false
+ keys:
+ expr: _col0
+ type: string
+ mode: hash
+ outputColumnNames: _col0, _col1
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ Local Work:
+ Map Reduce Local Work
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+
+
+PREHOOK: query: SELECT SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt)), SUM(HASH(tmp.value))
+FROM (SELECT d.key AS key, d.cnt AS cnt, b.value as value
+ FROM (SELECT x.key, x.value FROM src1 x JOIN src y ON (x.key = y.key)) b
+ JOIN (SELECT x.key, count(1) AS cnt FROM src1 x JOIN src y ON (x.key = y.key) group by x.key) d
+ ON b.key = d.key) tmp
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+PREHOOK: Input: default@src1
+#### A masked pattern was here ####
+POSTHOOK: query: SELECT SUM(HASH(tmp.key)), SUM(HASH(tmp.cnt)), SUM(HASH(tmp.value))
+FROM (SELECT d.key AS key, d.cnt AS cnt, b.value as value
+ FROM (SELECT x.key, x.value FROM src1 x JOIN src y ON (x.key = y.key)) b
+ JOIN (SELECT x.key, count(1) AS cnt FROM src1 x JOIN src y ON (x.key = y.key) group by x.key) d
+ ON b.key = d.key) tmp
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+POSTHOOK: Input: default@src1
+#### A masked pattern was here ####
+1711763 107 3531902962