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 [8/15] - 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/correlationoptimizer2.q.out
URL: http://svn.apache.org/viewvc/hive/trunk/ql/src/test/results/clientpositive/correlationoptimizer2.q.out?rev=1504395&view=auto
==============================================================================
--- hive/trunk/ql/src/test/results/clientpositive/correlationoptimizer2.q.out (added)
+++ hive/trunk/ql/src/test/results/clientpositive/correlationoptimizer2.q.out Thu Jul 18 09:16:52 2013
@@ -0,0 +1,3311 @@
+PREHOOK: query: -- In this query, subquery a and b both have a GroupByOperator and the a and b will be
+-- joined. The key of JoinOperator is the same with both keys of GroupByOperators in subquery
+-- a and b. When Correlation Optimizer is turned off, we have four MR jobs.
+-- When Correlation Optimizer is turned on, 2 MR jobs will be generated.
+-- The first job will evaluate subquery tmp (including subquery a, b, and the JoinOperator on a
+-- and b).
+EXPLAIN
+SELECT SUM(HASH(key1)), SUM(HASH(cnt1)), SUM(HASH(key2)), SUM(HASH(cnt2))
+FROM (SELECT a.key AS key1, a.cnt AS cnt1, b.key AS key2, b.cnt AS cnt2
+ FROM (SELECT x.key as key, count(x.value) AS cnt FROM src x group by x.key) a
+ JOIN (SELECT y.key as key, count(y.value) AS cnt FROM src1 y group by y.key) b
+ ON (a.key = b.key)) tmp
+PREHOOK: type: QUERY
+POSTHOOK: query: -- In this query, subquery a and b both have a GroupByOperator and the a and b will be
+-- joined. The key of JoinOperator is the same with both keys of GroupByOperators in subquery
+-- a and b. When Correlation Optimizer is turned off, we have four MR jobs.
+-- When Correlation Optimizer is turned on, 2 MR jobs will be generated.
+-- The first job will evaluate subquery tmp (including subquery a, b, and the JoinOperator on a
+-- and b).
+EXPLAIN
+SELECT SUM(HASH(key1)), SUM(HASH(cnt1)), SUM(HASH(key2)), SUM(HASH(cnt2))
+FROM (SELECT a.key AS key1, a.cnt AS cnt1, b.key AS key2, b.cnt AS cnt2
+ FROM (SELECT x.key as key, count(x.value) AS cnt FROM src x group by x.key) a
+ JOIN (SELECT y.key as key, count(y.value) AS cnt FROM src1 y group by y.key) b
+ ON (a.key = b.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_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 (. (TOK_TABLE_OR_COL x) value)) cnt)) (TOK_GROUPBY (. (TOK_TABLE_OR_COL x) key)))) a) (TOK_SUBQUERY (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME src1) y)) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (. (TOK_TABLE_OR_COL y) key) key) (TOK_SELEXPR (TOK_FUNCTION count (. (TOK_TABLE_OR_COL y) value)) cnt)) (TOK_GROUPBY (. (TOK_TABLE_OR_COL y) key)))) b) (= (. (TOK_TABLE_OR_COL a) key) (. (TOK_TABLE_OR_COL b) key)))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (. (TOK_TABLE_OR_COL a) key) key1) (TOK_SELEXPR (. (TOK_TABLE_OR_COL a) cnt) cnt1) (TOK_SELEXPR (. (TOK_TABLE_OR_COL b) key) key2) (TOK_SELEXPR (. (TOK_TABLE_OR_COL b) cnt) cnt2)))) tmp)
) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_FUNCTION SUM (TOK_FUNCTION HASH (TOK_TABLE_OR_COL key1)))) (TOK_SELEXPR (TOK_FUNCTION SUM (TOK_FUNCTION HASH (TOK_TABLE_OR_COL cnt1)))) (TOK_SELEXPR (TOK_FUNCTION SUM (TOK_FUNCTION HASH (TOK_TABLE_OR_COL key2)))) (TOK_SELEXPR (TOK_FUNCTION SUM (TOK_FUNCTION HASH (TOK_TABLE_OR_COL cnt2)))))))
+
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-2 depends on stages: Stage-1, Stage-4
+ Stage-3 depends on stages: Stage-2
+ Stage-4 is a root stage
+ Stage-0 is a root stage
+
+STAGE PLANS:
+ Stage: Stage-1
+ Map Reduce
+ Alias -> Map Operator Tree:
+ tmp:b:y
+ TableScan
+ alias: y
+ Select Operator
+ expressions:
+ expr: key
+ type: string
+ expr: value
+ type: string
+ outputColumnNames: key, value
+ Group By Operator
+ aggregations:
+ expr: count(value)
+ 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
+ $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
+ Group By Operator
+ aggregations:
+ expr: sum(hash(_col0))
+ expr: sum(hash(_col1))
+ expr: sum(hash(_col2))
+ expr: sum(hash(_col3))
+ bucketGroup: false
+ mode: hash
+ 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
+ sort order:
+ tag: -1
+ value expressions:
+ expr: _col0
+ type: bigint
+ expr: _col1
+ type: bigint
+ expr: _col2
+ type: bigint
+ expr: _col3
+ type: bigint
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations:
+ expr: sum(VALUE._col0)
+ expr: sum(VALUE._col1)
+ expr: sum(VALUE._col2)
+ expr: sum(VALUE._col3)
+ bucketGroup: false
+ mode: mergepartial
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Select Operator
+ expressions:
+ expr: _col0
+ type: bigint
+ expr: _col1
+ type: bigint
+ expr: _col2
+ type: bigint
+ expr: _col3
+ type: bigint
+ outputColumnNames: _col0, _col1, _col2, _col3
+ 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-4
+ Map Reduce
+ Alias -> Map Operator Tree:
+ tmp:a:x
+ TableScan
+ alias: x
+ Select Operator
+ expressions:
+ expr: key
+ type: string
+ expr: value
+ type: string
+ outputColumnNames: key, value
+ Group By Operator
+ aggregations:
+ expr: count(value)
+ 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-0
+ Fetch Operator
+ limit: -1
+
+
+PREHOOK: query: SELECT SUM(HASH(key1)), SUM(HASH(cnt1)), SUM(HASH(key2)), SUM(HASH(cnt2))
+FROM (SELECT a.key AS key1, a.cnt AS cnt1, b.key AS key2, b.cnt AS cnt2
+ FROM (SELECT x.key as key, count(x.value) AS cnt FROM src x group by x.key) a
+ JOIN (SELECT y.key as key, count(y.value) AS cnt FROM src1 y group by y.key) b
+ ON (a.key = b.key)) tmp
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+PREHOOK: Input: default@src1
+#### A masked pattern was here ####
+POSTHOOK: query: SELECT SUM(HASH(key1)), SUM(HASH(cnt1)), SUM(HASH(key2)), SUM(HASH(cnt2))
+FROM (SELECT a.key AS key1, a.cnt AS cnt1, b.key AS key2, b.cnt AS cnt2
+ FROM (SELECT x.key as key, count(x.value) AS cnt FROM src x group by x.key) a
+ JOIN (SELECT y.key as key, count(y.value) AS cnt FROM src1 y group by y.key) b
+ ON (a.key = b.key)) tmp
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+POSTHOOK: Input: default@src1
+#### A masked pattern was here ####
+652447 37 652447 15
+PREHOOK: query: EXPLAIN
+SELECT SUM(HASH(key1)), SUM(HASH(cnt1)), SUM(HASH(key2)), SUM(HASH(cnt2))
+FROM (SELECT a.key AS key1, a.cnt AS cnt1, b.key AS key2, b.cnt AS cnt2
+ FROM (SELECT x.key as key, count(x.value) AS cnt FROM src x group by x.key) a
+ JOIN (SELECT y.key as key, count(y.value) AS cnt FROM src1 y group by y.key) b
+ ON (a.key = b.key)) tmp
+PREHOOK: type: QUERY
+POSTHOOK: query: EXPLAIN
+SELECT SUM(HASH(key1)), SUM(HASH(cnt1)), SUM(HASH(key2)), SUM(HASH(cnt2))
+FROM (SELECT a.key AS key1, a.cnt AS cnt1, b.key AS key2, b.cnt AS cnt2
+ FROM (SELECT x.key as key, count(x.value) AS cnt FROM src x group by x.key) a
+ JOIN (SELECT y.key as key, count(y.value) AS cnt FROM src1 y group by y.key) b
+ ON (a.key = b.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_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 (. (TOK_TABLE_OR_COL x) value)) cnt)) (TOK_GROUPBY (. (TOK_TABLE_OR_COL x) key)))) a) (TOK_SUBQUERY (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME src1) y)) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (. (TOK_TABLE_OR_COL y) key) key) (TOK_SELEXPR (TOK_FUNCTION count (. (TOK_TABLE_OR_COL y) value)) cnt)) (TOK_GROUPBY (. (TOK_TABLE_OR_COL y) key)))) b) (= (. (TOK_TABLE_OR_COL a) key) (. (TOK_TABLE_OR_COL b) key)))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (. (TOK_TABLE_OR_COL a) key) key1) (TOK_SELEXPR (. (TOK_TABLE_OR_COL a) cnt) cnt1) (TOK_SELEXPR (. (TOK_TABLE_OR_COL b) key) key2) (TOK_SELEXPR (. (TOK_TABLE_OR_COL b) cnt) cnt2)))) tmp)
) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_FUNCTION SUM (TOK_FUNCTION HASH (TOK_TABLE_OR_COL key1)))) (TOK_SELEXPR (TOK_FUNCTION SUM (TOK_FUNCTION HASH (TOK_TABLE_OR_COL cnt1)))) (TOK_SELEXPR (TOK_FUNCTION SUM (TOK_FUNCTION HASH (TOK_TABLE_OR_COL key2)))) (TOK_SELEXPR (TOK_FUNCTION SUM (TOK_FUNCTION HASH (TOK_TABLE_OR_COL cnt2)))))))
+
+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:a:x
+ TableScan
+ alias: x
+ Select Operator
+ expressions:
+ expr: key
+ type: string
+ expr: value
+ type: string
+ outputColumnNames: key, value
+ Group By Operator
+ aggregations:
+ expr: count(value)
+ 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: 0
+ value expressions:
+ expr: _col1
+ type: bigint
+ tmp:b:y
+ TableScan
+ alias: y
+ Select Operator
+ expressions:
+ expr: key
+ type: string
+ expr: value
+ type: string
+ outputColumnNames: key, value
+ Group By Operator
+ aggregations:
+ expr: count(value)
+ 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
+ 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
+ Group By Operator
+ aggregations:
+ expr: sum(hash(_col0))
+ expr: sum(hash(_col1))
+ expr: sum(hash(_col2))
+ expr: sum(hash(_col3))
+ bucketGroup: false
+ mode: hash
+ 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
+ Group By Operator
+ aggregations:
+ expr: sum(hash(_col0))
+ expr: sum(hash(_col1))
+ expr: sum(hash(_col2))
+ expr: sum(hash(_col3))
+ bucketGroup: false
+ mode: hash
+ 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
+ sort order:
+ tag: -1
+ value expressions:
+ expr: _col0
+ type: bigint
+ expr: _col1
+ type: bigint
+ expr: _col2
+ type: bigint
+ expr: _col3
+ type: bigint
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations:
+ expr: sum(VALUE._col0)
+ expr: sum(VALUE._col1)
+ expr: sum(VALUE._col2)
+ expr: sum(VALUE._col3)
+ bucketGroup: false
+ mode: mergepartial
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Select Operator
+ expressions:
+ expr: _col0
+ type: bigint
+ expr: _col1
+ type: bigint
+ expr: _col2
+ type: bigint
+ expr: _col3
+ type: bigint
+ outputColumnNames: _col0, _col1, _col2, _col3
+ 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(key1)), SUM(HASH(cnt1)), SUM(HASH(key2)), SUM(HASH(cnt2))
+FROM (SELECT a.key AS key1, a.cnt AS cnt1, b.key AS key2, b.cnt AS cnt2
+ FROM (SELECT x.key as key, count(x.value) AS cnt FROM src x group by x.key) a
+ JOIN (SELECT y.key as key, count(y.value) AS cnt FROM src1 y group by y.key) b
+ ON (a.key = b.key)) tmp
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+PREHOOK: Input: default@src1
+#### A masked pattern was here ####
+POSTHOOK: query: SELECT SUM(HASH(key1)), SUM(HASH(cnt1)), SUM(HASH(key2)), SUM(HASH(cnt2))
+FROM (SELECT a.key AS key1, a.cnt AS cnt1, b.key AS key2, b.cnt AS cnt2
+ FROM (SELECT x.key as key, count(x.value) AS cnt FROM src x group by x.key) a
+ JOIN (SELECT y.key as key, count(y.value) AS cnt FROM src1 y group by y.key) b
+ ON (a.key = b.key)) tmp
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+POSTHOOK: Input: default@src1
+#### A masked pattern was here ####
+652447 37 652447 15
+PREHOOK: query: -- Left Outer Join should be handled.
+EXPLAIN
+SELECT SUM(HASH(key1)), SUM(HASH(cnt1)), SUM(HASH(key2)), SUM(HASH(cnt2))
+FROM (SELECT a.key AS key1, a.cnt AS cnt1, b.key AS key2, b.cnt AS cnt2
+ FROM (SELECT x.key as key, count(x.value) AS cnt FROM src x group by x.key) a
+ LEFT OUTER JOIN (SELECT y.key as key, count(y.value) AS cnt FROM src1 y group by y.key) b
+ ON (a.key = b.key)) tmp
+PREHOOK: type: QUERY
+POSTHOOK: query: -- Left Outer Join should be handled.
+EXPLAIN
+SELECT SUM(HASH(key1)), SUM(HASH(cnt1)), SUM(HASH(key2)), SUM(HASH(cnt2))
+FROM (SELECT a.key AS key1, a.cnt AS cnt1, b.key AS key2, b.cnt AS cnt2
+ FROM (SELECT x.key as key, count(x.value) AS cnt FROM src x group by x.key) a
+ LEFT OUTER JOIN (SELECT y.key as key, count(y.value) AS cnt FROM src1 y group by y.key) b
+ ON (a.key = b.key)) tmp
+POSTHOOK: type: QUERY
+ABSTRACT SYNTAX TREE:
+ (TOK_QUERY (TOK_FROM (TOK_SUBQUERY (TOK_QUERY (TOK_FROM (TOK_LEFTOUTERJOIN (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 (. (TOK_TABLE_OR_COL x) value)) cnt)) (TOK_GROUPBY (. (TOK_TABLE_OR_COL x) key)))) a) (TOK_SUBQUERY (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME src1) y)) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (. (TOK_TABLE_OR_COL y) key) key) (TOK_SELEXPR (TOK_FUNCTION count (. (TOK_TABLE_OR_COL y) value)) cnt)) (TOK_GROUPBY (. (TOK_TABLE_OR_COL y) key)))) b) (= (. (TOK_TABLE_OR_COL a) key) (. (TOK_TABLE_OR_COL b) key)))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (. (TOK_TABLE_OR_COL a) key) key1) (TOK_SELEXPR (. (TOK_TABLE_OR_COL a) cnt) cnt1) (TOK_SELEXPR (. (TOK_TABLE_OR_COL b) key) key2) (TOK_SELEXPR (. (TOK_TABLE_OR_COL b) cnt) cnt2
)))) tmp)) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_FUNCTION SUM (TOK_FUNCTION HASH (TOK_TABLE_OR_COL key1)))) (TOK_SELEXPR (TOK_FUNCTION SUM (TOK_FUNCTION HASH (TOK_TABLE_OR_COL cnt1)))) (TOK_SELEXPR (TOK_FUNCTION SUM (TOK_FUNCTION HASH (TOK_TABLE_OR_COL key2)))) (TOK_SELEXPR (TOK_FUNCTION SUM (TOK_FUNCTION HASH (TOK_TABLE_OR_COL cnt2)))))))
+
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-2 depends on stages: Stage-1, Stage-4
+ Stage-3 depends on stages: Stage-2
+ Stage-4 is a root stage
+ Stage-0 is a root stage
+
+STAGE PLANS:
+ Stage: Stage-1
+ Map Reduce
+ Alias -> Map Operator Tree:
+ tmp:b:y
+ TableScan
+ alias: y
+ Select Operator
+ expressions:
+ expr: key
+ type: string
+ expr: value
+ type: string
+ outputColumnNames: key, value
+ Group By Operator
+ aggregations:
+ expr: count(value)
+ 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
+ $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:
+ Left Outer Join0 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
+ Group By Operator
+ aggregations:
+ expr: sum(hash(_col0))
+ expr: sum(hash(_col1))
+ expr: sum(hash(_col2))
+ expr: sum(hash(_col3))
+ bucketGroup: false
+ mode: hash
+ 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
+ sort order:
+ tag: -1
+ value expressions:
+ expr: _col0
+ type: bigint
+ expr: _col1
+ type: bigint
+ expr: _col2
+ type: bigint
+ expr: _col3
+ type: bigint
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations:
+ expr: sum(VALUE._col0)
+ expr: sum(VALUE._col1)
+ expr: sum(VALUE._col2)
+ expr: sum(VALUE._col3)
+ bucketGroup: false
+ mode: mergepartial
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Select Operator
+ expressions:
+ expr: _col0
+ type: bigint
+ expr: _col1
+ type: bigint
+ expr: _col2
+ type: bigint
+ expr: _col3
+ type: bigint
+ outputColumnNames: _col0, _col1, _col2, _col3
+ 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-4
+ Map Reduce
+ Alias -> Map Operator Tree:
+ tmp:a:x
+ TableScan
+ alias: x
+ Select Operator
+ expressions:
+ expr: key
+ type: string
+ expr: value
+ type: string
+ outputColumnNames: key, value
+ Group By Operator
+ aggregations:
+ expr: count(value)
+ 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-0
+ Fetch Operator
+ limit: -1
+
+
+PREHOOK: query: SELECT SUM(HASH(key1)), SUM(HASH(cnt1)), SUM(HASH(key2)), SUM(HASH(cnt2))
+FROM (SELECT a.key AS key1, a.cnt AS cnt1, b.key AS key2, b.cnt AS cnt2
+ FROM (SELECT x.key as key, count(x.value) AS cnt FROM src x group by x.key) a
+ LEFT OUTER JOIN (SELECT y.key as key, count(y.value) AS cnt FROM src1 y group by y.key) b
+ ON (a.key = b.key)) tmp
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+PREHOOK: Input: default@src1
+#### A masked pattern was here ####
+POSTHOOK: query: SELECT SUM(HASH(key1)), SUM(HASH(cnt1)), SUM(HASH(key2)), SUM(HASH(cnt2))
+FROM (SELECT a.key AS key1, a.cnt AS cnt1, b.key AS key2, b.cnt AS cnt2
+ FROM (SELECT x.key as key, count(x.value) AS cnt FROM src x group by x.key) a
+ LEFT OUTER JOIN (SELECT y.key as key, count(y.value) AS cnt FROM src1 y group by y.key) b
+ ON (a.key = b.key)) tmp
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+POSTHOOK: Input: default@src1
+#### A masked pattern was here ####
+12744278 500 652447 15
+PREHOOK: query: EXPLAIN
+SELECT SUM(HASH(key1)), SUM(HASH(cnt1)), SUM(HASH(key2)), SUM(HASH(cnt2))
+FROM (SELECT a.key AS key1, a.cnt AS cnt1, b.key AS key2, b.cnt AS cnt2
+ FROM (SELECT x.key as key, count(x.value) AS cnt FROM src x group by x.key) a
+ LEFT OUTER JOIN (SELECT y.key as key, count(y.value) AS cnt FROM src1 y group by y.key) b
+ ON (a.key = b.key)) tmp
+PREHOOK: type: QUERY
+POSTHOOK: query: EXPLAIN
+SELECT SUM(HASH(key1)), SUM(HASH(cnt1)), SUM(HASH(key2)), SUM(HASH(cnt2))
+FROM (SELECT a.key AS key1, a.cnt AS cnt1, b.key AS key2, b.cnt AS cnt2
+ FROM (SELECT x.key as key, count(x.value) AS cnt FROM src x group by x.key) a
+ LEFT OUTER JOIN (SELECT y.key as key, count(y.value) AS cnt FROM src1 y group by y.key) b
+ ON (a.key = b.key)) tmp
+POSTHOOK: type: QUERY
+ABSTRACT SYNTAX TREE:
+ (TOK_QUERY (TOK_FROM (TOK_SUBQUERY (TOK_QUERY (TOK_FROM (TOK_LEFTOUTERJOIN (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 (. (TOK_TABLE_OR_COL x) value)) cnt)) (TOK_GROUPBY (. (TOK_TABLE_OR_COL x) key)))) a) (TOK_SUBQUERY (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME src1) y)) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (. (TOK_TABLE_OR_COL y) key) key) (TOK_SELEXPR (TOK_FUNCTION count (. (TOK_TABLE_OR_COL y) value)) cnt)) (TOK_GROUPBY (. (TOK_TABLE_OR_COL y) key)))) b) (= (. (TOK_TABLE_OR_COL a) key) (. (TOK_TABLE_OR_COL b) key)))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (. (TOK_TABLE_OR_COL a) key) key1) (TOK_SELEXPR (. (TOK_TABLE_OR_COL a) cnt) cnt1) (TOK_SELEXPR (. (TOK_TABLE_OR_COL b) key) key2) (TOK_SELEXPR (. (TOK_TABLE_OR_COL b) cnt) cnt2
)))) tmp)) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_FUNCTION SUM (TOK_FUNCTION HASH (TOK_TABLE_OR_COL key1)))) (TOK_SELEXPR (TOK_FUNCTION SUM (TOK_FUNCTION HASH (TOK_TABLE_OR_COL cnt1)))) (TOK_SELEXPR (TOK_FUNCTION SUM (TOK_FUNCTION HASH (TOK_TABLE_OR_COL key2)))) (TOK_SELEXPR (TOK_FUNCTION SUM (TOK_FUNCTION HASH (TOK_TABLE_OR_COL cnt2)))))))
+
+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:a:x
+ TableScan
+ alias: x
+ Select Operator
+ expressions:
+ expr: key
+ type: string
+ expr: value
+ type: string
+ outputColumnNames: key, value
+ Group By Operator
+ aggregations:
+ expr: count(value)
+ 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: 0
+ value expressions:
+ expr: _col1
+ type: bigint
+ tmp:b:y
+ TableScan
+ alias: y
+ Select Operator
+ expressions:
+ expr: key
+ type: string
+ expr: value
+ type: string
+ outputColumnNames: key, value
+ Group By Operator
+ aggregations:
+ expr: count(value)
+ 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
+ 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:
+ Left Outer Join0 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
+ Group By Operator
+ aggregations:
+ expr: sum(hash(_col0))
+ expr: sum(hash(_col1))
+ expr: sum(hash(_col2))
+ expr: sum(hash(_col3))
+ bucketGroup: false
+ mode: hash
+ 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:
+ Left Outer Join0 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
+ Group By Operator
+ aggregations:
+ expr: sum(hash(_col0))
+ expr: sum(hash(_col1))
+ expr: sum(hash(_col2))
+ expr: sum(hash(_col3))
+ bucketGroup: false
+ mode: hash
+ 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
+ sort order:
+ tag: -1
+ value expressions:
+ expr: _col0
+ type: bigint
+ expr: _col1
+ type: bigint
+ expr: _col2
+ type: bigint
+ expr: _col3
+ type: bigint
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations:
+ expr: sum(VALUE._col0)
+ expr: sum(VALUE._col1)
+ expr: sum(VALUE._col2)
+ expr: sum(VALUE._col3)
+ bucketGroup: false
+ mode: mergepartial
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Select Operator
+ expressions:
+ expr: _col0
+ type: bigint
+ expr: _col1
+ type: bigint
+ expr: _col2
+ type: bigint
+ expr: _col3
+ type: bigint
+ outputColumnNames: _col0, _col1, _col2, _col3
+ 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(key1)), SUM(HASH(cnt1)), SUM(HASH(key2)), SUM(HASH(cnt2))
+FROM (SELECT a.key AS key1, a.cnt AS cnt1, b.key AS key2, b.cnt AS cnt2
+ FROM (SELECT x.key as key, count(x.value) AS cnt FROM src x group by x.key) a
+ LEFT OUTER JOIN (SELECT y.key as key, count(y.value) AS cnt FROM src1 y group by y.key) b
+ ON (a.key = b.key)) tmp
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+PREHOOK: Input: default@src1
+#### A masked pattern was here ####
+POSTHOOK: query: SELECT SUM(HASH(key1)), SUM(HASH(cnt1)), SUM(HASH(key2)), SUM(HASH(cnt2))
+FROM (SELECT a.key AS key1, a.cnt AS cnt1, b.key AS key2, b.cnt AS cnt2
+ FROM (SELECT x.key as key, count(x.value) AS cnt FROM src x group by x.key) a
+ LEFT OUTER JOIN (SELECT y.key as key, count(y.value) AS cnt FROM src1 y group by y.key) b
+ ON (a.key = b.key)) tmp
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+POSTHOOK: Input: default@src1
+#### A masked pattern was here ####
+12744278 500 652447 15
+PREHOOK: query: -- Right Outer Join should be handled.
+EXPLAIN
+SELECT SUM(HASH(key1)), SUM(HASH(cnt1)), SUM(HASH(key2)), SUM(HASH(cnt2))
+FROM (SELECT a.key AS key1, a.cnt AS cnt1, b.key AS key2, b.cnt AS cnt2
+ FROM (SELECT x.key as key, count(x.value) AS cnt FROM src x group by x.key) a
+ RIGHT OUTER JOIN (SELECT y.key as key, count(y.value) AS cnt FROM src1 y group by y.key) b
+ ON (a.key = b.key)) tmp
+PREHOOK: type: QUERY
+POSTHOOK: query: -- Right Outer Join should be handled.
+EXPLAIN
+SELECT SUM(HASH(key1)), SUM(HASH(cnt1)), SUM(HASH(key2)), SUM(HASH(cnt2))
+FROM (SELECT a.key AS key1, a.cnt AS cnt1, b.key AS key2, b.cnt AS cnt2
+ FROM (SELECT x.key as key, count(x.value) AS cnt FROM src x group by x.key) a
+ RIGHT OUTER JOIN (SELECT y.key as key, count(y.value) AS cnt FROM src1 y group by y.key) b
+ ON (a.key = b.key)) tmp
+POSTHOOK: type: QUERY
+ABSTRACT SYNTAX TREE:
+ (TOK_QUERY (TOK_FROM (TOK_SUBQUERY (TOK_QUERY (TOK_FROM (TOK_RIGHTOUTERJOIN (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 (. (TOK_TABLE_OR_COL x) value)) cnt)) (TOK_GROUPBY (. (TOK_TABLE_OR_COL x) key)))) a) (TOK_SUBQUERY (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME src1) y)) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (. (TOK_TABLE_OR_COL y) key) key) (TOK_SELEXPR (TOK_FUNCTION count (. (TOK_TABLE_OR_COL y) value)) cnt)) (TOK_GROUPBY (. (TOK_TABLE_OR_COL y) key)))) b) (= (. (TOK_TABLE_OR_COL a) key) (. (TOK_TABLE_OR_COL b) key)))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (. (TOK_TABLE_OR_COL a) key) key1) (TOK_SELEXPR (. (TOK_TABLE_OR_COL a) cnt) cnt1) (TOK_SELEXPR (. (TOK_TABLE_OR_COL b) key) key2) (TOK_SELEXPR (. (TOK_TABLE_OR_COL b) cnt) cnt
2)))) tmp)) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_FUNCTION SUM (TOK_FUNCTION HASH (TOK_TABLE_OR_COL key1)))) (TOK_SELEXPR (TOK_FUNCTION SUM (TOK_FUNCTION HASH (TOK_TABLE_OR_COL cnt1)))) (TOK_SELEXPR (TOK_FUNCTION SUM (TOK_FUNCTION HASH (TOK_TABLE_OR_COL key2)))) (TOK_SELEXPR (TOK_FUNCTION SUM (TOK_FUNCTION HASH (TOK_TABLE_OR_COL cnt2)))))))
+
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-2 depends on stages: Stage-1, Stage-4
+ Stage-3 depends on stages: Stage-2
+ Stage-4 is a root stage
+ Stage-0 is a root stage
+
+STAGE PLANS:
+ Stage: Stage-1
+ Map Reduce
+ Alias -> Map Operator Tree:
+ tmp:b:y
+ TableScan
+ alias: y
+ Select Operator
+ expressions:
+ expr: key
+ type: string
+ expr: value
+ type: string
+ outputColumnNames: key, value
+ Group By Operator
+ aggregations:
+ expr: count(value)
+ 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
+ $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:
+ Right Outer Join0 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
+ Group By Operator
+ aggregations:
+ expr: sum(hash(_col0))
+ expr: sum(hash(_col1))
+ expr: sum(hash(_col2))
+ expr: sum(hash(_col3))
+ bucketGroup: false
+ mode: hash
+ 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
+ sort order:
+ tag: -1
+ value expressions:
+ expr: _col0
+ type: bigint
+ expr: _col1
+ type: bigint
+ expr: _col2
+ type: bigint
+ expr: _col3
+ type: bigint
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations:
+ expr: sum(VALUE._col0)
+ expr: sum(VALUE._col1)
+ expr: sum(VALUE._col2)
+ expr: sum(VALUE._col3)
+ bucketGroup: false
+ mode: mergepartial
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Select Operator
+ expressions:
+ expr: _col0
+ type: bigint
+ expr: _col1
+ type: bigint
+ expr: _col2
+ type: bigint
+ expr: _col3
+ type: bigint
+ outputColumnNames: _col0, _col1, _col2, _col3
+ 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-4
+ Map Reduce
+ Alias -> Map Operator Tree:
+ tmp:a:x
+ TableScan
+ alias: x
+ Select Operator
+ expressions:
+ expr: key
+ type: string
+ expr: value
+ type: string
+ outputColumnNames: key, value
+ Group By Operator
+ aggregations:
+ expr: count(value)
+ 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-0
+ Fetch Operator
+ limit: -1
+
+
+PREHOOK: query: SELECT SUM(HASH(key1)), SUM(HASH(cnt1)), SUM(HASH(key2)), SUM(HASH(cnt2))
+FROM (SELECT a.key AS key1, a.cnt AS cnt1, b.key AS key2, b.cnt AS cnt2
+ FROM (SELECT x.key as key, count(x.value) AS cnt FROM src x group by x.key) a
+ RIGHT OUTER JOIN (SELECT y.key as key, count(y.value) AS cnt FROM src1 y group by y.key) b
+ ON (a.key = b.key)) tmp
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+PREHOOK: Input: default@src1
+#### A masked pattern was here ####
+POSTHOOK: query: SELECT SUM(HASH(key1)), SUM(HASH(cnt1)), SUM(HASH(key2)), SUM(HASH(cnt2))
+FROM (SELECT a.key AS key1, a.cnt AS cnt1, b.key AS key2, b.cnt AS cnt2
+ FROM (SELECT x.key as key, count(x.value) AS cnt FROM src x group by x.key) a
+ RIGHT OUTER JOIN (SELECT y.key as key, count(y.value) AS cnt FROM src1 y group by y.key) b
+ ON (a.key = b.key)) tmp
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+POSTHOOK: Input: default@src1
+#### A masked pattern was here ####
+652447 37 652447 25
+PREHOOK: query: EXPLAIN
+SELECT SUM(HASH(key1)), SUM(HASH(cnt1)), SUM(HASH(key2)), SUM(HASH(cnt2))
+FROM (SELECT a.key AS key1, a.cnt AS cnt1, b.key AS key2, b.cnt AS cnt2
+ FROM (SELECT x.key as key, count(x.value) AS cnt FROM src x group by x.key) a
+ RIGHT OUTER JOIN (SELECT y.key as key, count(y.value) AS cnt FROM src1 y group by y.key) b
+ ON (a.key = b.key)) tmp
+PREHOOK: type: QUERY
+POSTHOOK: query: EXPLAIN
+SELECT SUM(HASH(key1)), SUM(HASH(cnt1)), SUM(HASH(key2)), SUM(HASH(cnt2))
+FROM (SELECT a.key AS key1, a.cnt AS cnt1, b.key AS key2, b.cnt AS cnt2
+ FROM (SELECT x.key as key, count(x.value) AS cnt FROM src x group by x.key) a
+ RIGHT OUTER JOIN (SELECT y.key as key, count(y.value) AS cnt FROM src1 y group by y.key) b
+ ON (a.key = b.key)) tmp
+POSTHOOK: type: QUERY
+ABSTRACT SYNTAX TREE:
+ (TOK_QUERY (TOK_FROM (TOK_SUBQUERY (TOK_QUERY (TOK_FROM (TOK_RIGHTOUTERJOIN (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 (. (TOK_TABLE_OR_COL x) value)) cnt)) (TOK_GROUPBY (. (TOK_TABLE_OR_COL x) key)))) a) (TOK_SUBQUERY (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME src1) y)) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (. (TOK_TABLE_OR_COL y) key) key) (TOK_SELEXPR (TOK_FUNCTION count (. (TOK_TABLE_OR_COL y) value)) cnt)) (TOK_GROUPBY (. (TOK_TABLE_OR_COL y) key)))) b) (= (. (TOK_TABLE_OR_COL a) key) (. (TOK_TABLE_OR_COL b) key)))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (. (TOK_TABLE_OR_COL a) key) key1) (TOK_SELEXPR (. (TOK_TABLE_OR_COL a) cnt) cnt1) (TOK_SELEXPR (. (TOK_TABLE_OR_COL b) key) key2) (TOK_SELEXPR (. (TOK_TABLE_OR_COL b) cnt) cnt
2)))) tmp)) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_FUNCTION SUM (TOK_FUNCTION HASH (TOK_TABLE_OR_COL key1)))) (TOK_SELEXPR (TOK_FUNCTION SUM (TOK_FUNCTION HASH (TOK_TABLE_OR_COL cnt1)))) (TOK_SELEXPR (TOK_FUNCTION SUM (TOK_FUNCTION HASH (TOK_TABLE_OR_COL key2)))) (TOK_SELEXPR (TOK_FUNCTION SUM (TOK_FUNCTION HASH (TOK_TABLE_OR_COL cnt2)))))))
+
+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:a:x
+ TableScan
+ alias: x
+ Select Operator
+ expressions:
+ expr: key
+ type: string
+ expr: value
+ type: string
+ outputColumnNames: key, value
+ Group By Operator
+ aggregations:
+ expr: count(value)
+ 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: 0
+ value expressions:
+ expr: _col1
+ type: bigint
+ tmp:b:y
+ TableScan
+ alias: y
+ Select Operator
+ expressions:
+ expr: key
+ type: string
+ expr: value
+ type: string
+ outputColumnNames: key, value
+ Group By Operator
+ aggregations:
+ expr: count(value)
+ 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
+ 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:
+ Right Outer Join0 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
+ Group By Operator
+ aggregations:
+ expr: sum(hash(_col0))
+ expr: sum(hash(_col1))
+ expr: sum(hash(_col2))
+ expr: sum(hash(_col3))
+ bucketGroup: false
+ mode: hash
+ 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:
+ Right Outer Join0 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
+ Group By Operator
+ aggregations:
+ expr: sum(hash(_col0))
+ expr: sum(hash(_col1))
+ expr: sum(hash(_col2))
+ expr: sum(hash(_col3))
+ bucketGroup: false
+ mode: hash
+ 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
+ sort order:
+ tag: -1
+ value expressions:
+ expr: _col0
+ type: bigint
+ expr: _col1
+ type: bigint
+ expr: _col2
+ type: bigint
+ expr: _col3
+ type: bigint
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations:
+ expr: sum(VALUE._col0)
+ expr: sum(VALUE._col1)
+ expr: sum(VALUE._col2)
+ expr: sum(VALUE._col3)
+ bucketGroup: false
+ mode: mergepartial
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Select Operator
+ expressions:
+ expr: _col0
+ type: bigint
+ expr: _col1
+ type: bigint
+ expr: _col2
+ type: bigint
+ expr: _col3
+ type: bigint
+ outputColumnNames: _col0, _col1, _col2, _col3
+ 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(key1)), SUM(HASH(cnt1)), SUM(HASH(key2)), SUM(HASH(cnt2))
+FROM (SELECT a.key AS key1, a.cnt AS cnt1, b.key AS key2, b.cnt AS cnt2
+ FROM (SELECT x.key as key, count(x.value) AS cnt FROM src x group by x.key) a
+ RIGHT OUTER JOIN (SELECT y.key as key, count(y.value) AS cnt FROM src1 y group by y.key) b
+ ON (a.key = b.key)) tmp
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+PREHOOK: Input: default@src1
+#### A masked pattern was here ####
+POSTHOOK: query: SELECT SUM(HASH(key1)), SUM(HASH(cnt1)), SUM(HASH(key2)), SUM(HASH(cnt2))
+FROM (SELECT a.key AS key1, a.cnt AS cnt1, b.key AS key2, b.cnt AS cnt2
+ FROM (SELECT x.key as key, count(x.value) AS cnt FROM src x group by x.key) a
+ RIGHT OUTER JOIN (SELECT y.key as key, count(y.value) AS cnt FROM src1 y group by y.key) b
+ ON (a.key = b.key)) tmp
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+POSTHOOK: Input: default@src1
+#### A masked pattern was here ####
+652447 37 652447 25
+PREHOOK: query: -- Full Outer Join should be handled.
+EXPLAIN
+SELECT SUM(HASH(key1)), SUM(HASH(cnt1)), SUM(HASH(key2)), SUM(HASH(cnt2))
+FROM (SELECT a.key AS key1, a.cnt AS cnt1, b.key AS key2, b.cnt AS cnt2
+ FROM (SELECT x.key as key, count(x.value) AS cnt FROM src x group by x.key) a
+ FULL OUTER JOIN (SELECT y.key as key, count(y.value) AS cnt FROM src1 y group by y.key) b
+ ON (a.key = b.key)) tmp
+PREHOOK: type: QUERY
+POSTHOOK: query: -- Full Outer Join should be handled.
+EXPLAIN
+SELECT SUM(HASH(key1)), SUM(HASH(cnt1)), SUM(HASH(key2)), SUM(HASH(cnt2))
+FROM (SELECT a.key AS key1, a.cnt AS cnt1, b.key AS key2, b.cnt AS cnt2
+ FROM (SELECT x.key as key, count(x.value) AS cnt FROM src x group by x.key) a
+ FULL OUTER JOIN (SELECT y.key as key, count(y.value) AS cnt FROM src1 y group by y.key) b
+ ON (a.key = b.key)) tmp
+POSTHOOK: type: QUERY
+ABSTRACT SYNTAX TREE:
+ (TOK_QUERY (TOK_FROM (TOK_SUBQUERY (TOK_QUERY (TOK_FROM (TOK_FULLOUTERJOIN (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 (. (TOK_TABLE_OR_COL x) value)) cnt)) (TOK_GROUPBY (. (TOK_TABLE_OR_COL x) key)))) a) (TOK_SUBQUERY (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME src1) y)) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (. (TOK_TABLE_OR_COL y) key) key) (TOK_SELEXPR (TOK_FUNCTION count (. (TOK_TABLE_OR_COL y) value)) cnt)) (TOK_GROUPBY (. (TOK_TABLE_OR_COL y) key)))) b) (= (. (TOK_TABLE_OR_COL a) key) (. (TOK_TABLE_OR_COL b) key)))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (. (TOK_TABLE_OR_COL a) key) key1) (TOK_SELEXPR (. (TOK_TABLE_OR_COL a) cnt) cnt1) (TOK_SELEXPR (. (TOK_TABLE_OR_COL b) key) key2) (TOK_SELEXPR (. (TOK_TABLE_OR_COL b) cnt) cnt2
)))) tmp)) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_FUNCTION SUM (TOK_FUNCTION HASH (TOK_TABLE_OR_COL key1)))) (TOK_SELEXPR (TOK_FUNCTION SUM (TOK_FUNCTION HASH (TOK_TABLE_OR_COL cnt1)))) (TOK_SELEXPR (TOK_FUNCTION SUM (TOK_FUNCTION HASH (TOK_TABLE_OR_COL key2)))) (TOK_SELEXPR (TOK_FUNCTION SUM (TOK_FUNCTION HASH (TOK_TABLE_OR_COL cnt2)))))))
+
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-2 depends on stages: Stage-1, Stage-4
+ Stage-3 depends on stages: Stage-2
+ Stage-4 is a root stage
+ Stage-0 is a root stage
+
+STAGE PLANS:
+ Stage: Stage-1
+ Map Reduce
+ Alias -> Map Operator Tree:
+ tmp:b:y
+ TableScan
+ alias: y
+ Select Operator
+ expressions:
+ expr: key
+ type: string
+ expr: value
+ type: string
+ outputColumnNames: key, value
+ Group By Operator
+ aggregations:
+ expr: count(value)
+ 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
+ $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:
+ Outer 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
+ Group By Operator
+ aggregations:
+ expr: sum(hash(_col0))
+ expr: sum(hash(_col1))
+ expr: sum(hash(_col2))
+ expr: sum(hash(_col3))
+ bucketGroup: false
+ mode: hash
+ 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
+ sort order:
+ tag: -1
+ value expressions:
+ expr: _col0
+ type: bigint
+ expr: _col1
+ type: bigint
+ expr: _col2
+ type: bigint
+ expr: _col3
+ type: bigint
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations:
+ expr: sum(VALUE._col0)
+ expr: sum(VALUE._col1)
+ expr: sum(VALUE._col2)
+ expr: sum(VALUE._col3)
+ bucketGroup: false
+ mode: mergepartial
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Select Operator
+ expressions:
+ expr: _col0
+ type: bigint
+ expr: _col1
+ type: bigint
+ expr: _col2
+ type: bigint
+ expr: _col3
+ type: bigint
+ outputColumnNames: _col0, _col1, _col2, _col3
+ 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-4
+ Map Reduce
+ Alias -> Map Operator Tree:
+ tmp:a:x
+ TableScan
+ alias: x
+ Select Operator
+ expressions:
+ expr: key
+ type: string
+ expr: value
+ type: string
+ outputColumnNames: key, value
+ Group By Operator
+ aggregations:
+ expr: count(value)
+ 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-0
+ Fetch Operator
+ limit: -1
+
+
+PREHOOK: query: SELECT SUM(HASH(key1)), SUM(HASH(cnt1)), SUM(HASH(key2)), SUM(HASH(cnt2))
+FROM (SELECT a.key AS key1, a.cnt AS cnt1, b.key AS key2, b.cnt AS cnt2
+ FROM (SELECT x.key as key, count(x.value) AS cnt FROM src x group by x.key) a
+ FULL OUTER JOIN (SELECT y.key as key, count(y.value) AS cnt FROM src1 y group by y.key) b
+ ON (a.key = b.key)) tmp
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+PREHOOK: Input: default@src1
+#### A masked pattern was here ####
+POSTHOOK: query: SELECT SUM(HASH(key1)), SUM(HASH(cnt1)), SUM(HASH(key2)), SUM(HASH(cnt2))
+FROM (SELECT a.key AS key1, a.cnt AS cnt1, b.key AS key2, b.cnt AS cnt2
+ FROM (SELECT x.key as key, count(x.value) AS cnt FROM src x group by x.key) a
+ FULL OUTER JOIN (SELECT y.key as key, count(y.value) AS cnt FROM src1 y group by y.key) b
+ ON (a.key = b.key)) tmp
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+POSTHOOK: Input: default@src1
+#### A masked pattern was here ####
+12744278 500 652447 25
+PREHOOK: query: EXPLAIN
+SELECT SUM(HASH(key1)), SUM(HASH(cnt1)), SUM(HASH(key2)), SUM(HASH(cnt2))
+FROM (SELECT a.key AS key1, a.cnt AS cnt1, b.key AS key2, b.cnt AS cnt2
+ FROM (SELECT x.key as key, count(x.value) AS cnt FROM src x group by x.key) a
+ FULL OUTER JOIN (SELECT y.key as key, count(y.value) AS cnt FROM src1 y group by y.key) b
+ ON (a.key = b.key)) tmp
+PREHOOK: type: QUERY
+POSTHOOK: query: EXPLAIN
+SELECT SUM(HASH(key1)), SUM(HASH(cnt1)), SUM(HASH(key2)), SUM(HASH(cnt2))
+FROM (SELECT a.key AS key1, a.cnt AS cnt1, b.key AS key2, b.cnt AS cnt2
+ FROM (SELECT x.key as key, count(x.value) AS cnt FROM src x group by x.key) a
+ FULL OUTER JOIN (SELECT y.key as key, count(y.value) AS cnt FROM src1 y group by y.key) b
+ ON (a.key = b.key)) tmp
+POSTHOOK: type: QUERY
+ABSTRACT SYNTAX TREE:
+ (TOK_QUERY (TOK_FROM (TOK_SUBQUERY (TOK_QUERY (TOK_FROM (TOK_FULLOUTERJOIN (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 (. (TOK_TABLE_OR_COL x) value)) cnt)) (TOK_GROUPBY (. (TOK_TABLE_OR_COL x) key)))) a) (TOK_SUBQUERY (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME src1) y)) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (. (TOK_TABLE_OR_COL y) key) key) (TOK_SELEXPR (TOK_FUNCTION count (. (TOK_TABLE_OR_COL y) value)) cnt)) (TOK_GROUPBY (. (TOK_TABLE_OR_COL y) key)))) b) (= (. (TOK_TABLE_OR_COL a) key) (. (TOK_TABLE_OR_COL b) key)))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (. (TOK_TABLE_OR_COL a) key) key1) (TOK_SELEXPR (. (TOK_TABLE_OR_COL a) cnt) cnt1) (TOK_SELEXPR (. (TOK_TABLE_OR_COL b) key) key2) (TOK_SELEXPR (. (TOK_TABLE_OR_COL b) cnt) cnt2
)))) tmp)) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_FUNCTION SUM (TOK_FUNCTION HASH (TOK_TABLE_OR_COL key1)))) (TOK_SELEXPR (TOK_FUNCTION SUM (TOK_FUNCTION HASH (TOK_TABLE_OR_COL cnt1)))) (TOK_SELEXPR (TOK_FUNCTION SUM (TOK_FUNCTION HASH (TOK_TABLE_OR_COL key2)))) (TOK_SELEXPR (TOK_FUNCTION SUM (TOK_FUNCTION HASH (TOK_TABLE_OR_COL cnt2)))))))
+
+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:a:x
+ TableScan
+ alias: x
+ Select Operator
+ expressions:
+ expr: key
+ type: string
+ expr: value
+ type: string
+ outputColumnNames: key, value
+ Group By Operator
+ aggregations:
+ expr: count(value)
+ 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: 0
+ value expressions:
+ expr: _col1
+ type: bigint
+ tmp:b:y
+ TableScan
+ alias: y
+ Select Operator
+ expressions:
+ expr: key
+ type: string
+ expr: value
+ type: string
+ outputColumnNames: key, value
+ Group By Operator
+ aggregations:
+ expr: count(value)
+ 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
+ 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:
+ Outer 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
+ Group By Operator
+ aggregations:
+ expr: sum(hash(_col0))
+ expr: sum(hash(_col1))
+ expr: sum(hash(_col2))
+ expr: sum(hash(_col3))
+ bucketGroup: false
+ mode: hash
+ 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:
+ Outer 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
+ Group By Operator
+ aggregations:
+ expr: sum(hash(_col0))
+ expr: sum(hash(_col1))
+ expr: sum(hash(_col2))
+ expr: sum(hash(_col3))
+ bucketGroup: false
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2, _col3
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
[... 1208 lines stripped ...]