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 [14/15] - in /hive/trunk:
common/src/java/org/apache/hadoop/hive/conf/ conf/ ql/if/
ql/src/gen/thrift/gen-javabean/org/apache/hadoop/hive/ql/plan/api/
ql/src/java/org/apache/hadoop/hive/ql/exec/
ql/src/java/org/apache/hadoop/hive/q...
Added: hive/trunk/ql/src/test/results/clientpositive/correlationoptimizer8.q.out
URL: http://svn.apache.org/viewvc/hive/trunk/ql/src/test/results/clientpositive/correlationoptimizer8.q.out?rev=1504395&view=auto
==============================================================================
--- hive/trunk/ql/src/test/results/clientpositive/correlationoptimizer8.q.out (added)
+++ hive/trunk/ql/src/test/results/clientpositive/correlationoptimizer8.q.out Thu Jul 18 09:16:52 2013
@@ -0,0 +1,1806 @@
+PREHOOK: query: -- When the Correlation Optimizer is turned off, this query will be evaluated by
+-- 4 MR jobs.
+-- When the Correlation Optimizer is turned on, because both inputs of the
+-- UnionOperator are correlated, we can use 2 MR jobs to evaluate this query.
+-- The first MR job will evaluate subquery subq1 and subq1 join x. The second
+-- MR is for ordering.
+EXPLAIN
+SELECT x.key, x.value, subq1.cnt
+FROM
+( SELECT x.key as key, count(1) as cnt from src x where x.key < 20 group by x.key
+ UNION ALL
+ SELECT x1.key as key, count(1) as cnt from src x1 where x1.key > 100 group by x1.key
+) subq1
+JOIN src1 x ON (x.key = subq1.key) ORDER BY x.key, x.value, subq1.cnt
+PREHOOK: type: QUERY
+POSTHOOK: query: -- When the Correlation Optimizer is turned off, this query will be evaluated by
+-- 4 MR jobs.
+-- When the Correlation Optimizer is turned on, because both inputs of the
+-- UnionOperator are correlated, we can use 2 MR jobs to evaluate this query.
+-- The first MR job will evaluate subquery subq1 and subq1 join x. The second
+-- MR is for ordering.
+EXPLAIN
+SELECT x.key, x.value, subq1.cnt
+FROM
+( SELECT x.key as key, count(1) as cnt from src x where x.key < 20 group by x.key
+ UNION ALL
+ SELECT x1.key as key, count(1) as cnt from src x1 where x1.key > 100 group by x1.key
+) subq1
+JOIN src1 x ON (x.key = subq1.key) ORDER BY x.key, x.value, subq1.cnt
+POSTHOOK: type: QUERY
+ABSTRACT SYNTAX TREE:
+ (TOK_QUERY (TOK_FROM (TOK_JOIN (TOK_SUBQUERY (TOK_UNION (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME src) x)) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (. (TOK_TABLE_OR_COL x) key) key) (TOK_SELEXPR (TOK_FUNCTION count 1) cnt)) (TOK_WHERE (< (. (TOK_TABLE_OR_COL x) key) 20)) (TOK_GROUPBY (. (TOK_TABLE_OR_COL x) key)))) (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME src) x1)) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (. (TOK_TABLE_OR_COL x1) key) key) (TOK_SELEXPR (TOK_FUNCTION count 1) cnt)) (TOK_WHERE (> (. (TOK_TABLE_OR_COL x1) key) 100)) (TOK_GROUPBY (. (TOK_TABLE_OR_COL x1) key))))) subq1) (TOK_TABREF (TOK_TABNAME src1) x) (= (. (TOK_TABLE_OR_COL x) key) (. (TOK_TABLE_OR_COL subq1) 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)) (TOK_SELEXPR (. (TOK_TABLE_OR_COL subq1) cnt))) (TOK_ORDERBY (TOK_T
ABSORTCOLNAMEASC (. (TOK_TABLE_OR_COL x) key)) (TOK_TABSORTCOLNAMEASC (. (TOK_TABLE_OR_COL x) value)) (TOK_TABSORTCOLNAMEASC (. (TOK_TABLE_OR_COL subq1) cnt)))))
+
+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:
+ null-subquery1:subq1-subquery1:x
+ TableScan
+ alias: x
+ Filter Operator
+ predicate:
+ expr: (key < 20.0)
+ type: boolean
+ Select Operator
+ expressions:
+ expr: key
+ type: string
+ outputColumnNames: key
+ Group By Operator
+ aggregations:
+ expr: count(1)
+ bucketGroup: false
+ keys:
+ expr: key
+ type: string
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Reduce Output Operator
+ key expressions:
+ expr: _col0
+ type: string
+ sort order: +
+ Map-reduce partition columns:
+ expr: _col0
+ type: string
+ tag: -1
+ value expressions:
+ expr: _col1
+ type: bigint
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations:
+ expr: count(VALUE._col0)
+ bucketGroup: false
+ keys:
+ expr: KEY._col0
+ type: string
+ mode: mergepartial
+ outputColumnNames: _col0, _col1
+ Select Operator
+ expressions:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: bigint
+ outputColumnNames: _col0, _col1
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+
+ Stage: Stage-2
+ Map Reduce
+ Alias -> Map Operator Tree:
+#### A masked pattern was here ####
+ TableScan
+ Union
+ 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 ####
+ TableScan
+ Union
+ 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
+ x
+ TableScan
+ alias: x
+ Reduce Output Operator
+ key expressions:
+ expr: key
+ type: string
+ sort order: +
+ Map-reduce partition columns:
+ expr: key
+ type: string
+ tag: 1
+ value expressions:
+ expr: key
+ type: string
+ expr: value
+ type: string
+ 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: string
+ expr: _col1
+ type: bigint
+ outputColumnNames: _col0, _col1, _col2
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+
+ Stage: Stage-3
+ Map Reduce
+ Alias -> Map Operator Tree:
+#### A masked pattern was here ####
+ Reduce Output Operator
+ key expressions:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: string
+ expr: _col2
+ type: bigint
+ sort order: +++
+ tag: -1
+ value expressions:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: string
+ expr: _col2
+ type: bigint
+ Reduce Operator Tree:
+ Extract
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+
+ Stage: Stage-4
+ Map Reduce
+ Alias -> Map Operator Tree:
+ null-subquery2:subq1-subquery2:x1
+ TableScan
+ alias: x1
+ Filter Operator
+ predicate:
+ expr: (key > 100.0)
+ type: boolean
+ Select Operator
+ expressions:
+ expr: key
+ type: string
+ outputColumnNames: key
+ Group By Operator
+ aggregations:
+ expr: count(1)
+ bucketGroup: false
+ keys:
+ expr: key
+ type: string
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Reduce Output Operator
+ key expressions:
+ expr: _col0
+ type: string
+ sort order: +
+ Map-reduce partition columns:
+ expr: _col0
+ type: string
+ tag: -1
+ value expressions:
+ expr: _col1
+ type: bigint
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations:
+ expr: count(VALUE._col0)
+ bucketGroup: false
+ keys:
+ expr: KEY._col0
+ type: string
+ mode: mergepartial
+ outputColumnNames: _col0, _col1
+ Select Operator
+ expressions:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: bigint
+ outputColumnNames: _col0, _col1
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+
+
+PREHOOK: query: SELECT x.key, x.value, subq1.cnt
+FROM
+( SELECT x.key as key, count(1) as cnt from src x where x.key < 20 group by x.key
+ UNION ALL
+ SELECT x1.key as key, count(1) as cnt from src x1 where x1.key > 100 group by x1.key
+) subq1
+JOIN src1 x ON (x.key = subq1.key) ORDER BY x.key, x.value, subq1.cnt
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+PREHOOK: Input: default@src1
+#### A masked pattern was here ####
+POSTHOOK: query: SELECT x.key, x.value, subq1.cnt
+FROM
+( SELECT x.key as key, count(1) as cnt from src x where x.key < 20 group by x.key
+ UNION ALL
+ SELECT x1.key as key, count(1) as cnt from src x1 where x1.key > 100 group by x1.key
+) subq1
+JOIN src1 x ON (x.key = subq1.key) ORDER BY x.key, x.value, subq1.cnt
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+POSTHOOK: Input: default@src1
+#### A masked pattern was here ####
+128 3
+146 val_146 2
+150 val_150 1
+213 val_213 2
+224 2
+238 val_238 2
+255 val_255 2
+273 val_273 3
+278 val_278 2
+311 val_311 3
+369 3
+401 val_401 5
+406 val_406 4
+PREHOOK: query: EXPLAIN
+SELECT x.key, x.value, subq1.cnt
+FROM
+( SELECT x.key as key, count(1) as cnt from src x where x.key < 20 group by x.key
+ UNION ALL
+ SELECT x1.key as key, count(1) as cnt from src x1 where x1.key > 100 group by x1.key
+) subq1
+JOIN src1 x ON (x.key = subq1.key) ORDER BY x.key, x.value, subq1.cnt
+PREHOOK: type: QUERY
+POSTHOOK: query: EXPLAIN
+SELECT x.key, x.value, subq1.cnt
+FROM
+( SELECT x.key as key, count(1) as cnt from src x where x.key < 20 group by x.key
+ UNION ALL
+ SELECT x1.key as key, count(1) as cnt from src x1 where x1.key > 100 group by x1.key
+) subq1
+JOIN src1 x ON (x.key = subq1.key) ORDER BY x.key, x.value, subq1.cnt
+POSTHOOK: type: QUERY
+ABSTRACT SYNTAX TREE:
+ (TOK_QUERY (TOK_FROM (TOK_JOIN (TOK_SUBQUERY (TOK_UNION (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME src) x)) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (. (TOK_TABLE_OR_COL x) key) key) (TOK_SELEXPR (TOK_FUNCTION count 1) cnt)) (TOK_WHERE (< (. (TOK_TABLE_OR_COL x) key) 20)) (TOK_GROUPBY (. (TOK_TABLE_OR_COL x) key)))) (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME src) x1)) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (. (TOK_TABLE_OR_COL x1) key) key) (TOK_SELEXPR (TOK_FUNCTION count 1) cnt)) (TOK_WHERE (> (. (TOK_TABLE_OR_COL x1) key) 100)) (TOK_GROUPBY (. (TOK_TABLE_OR_COL x1) key))))) subq1) (TOK_TABREF (TOK_TABNAME src1) x) (= (. (TOK_TABLE_OR_COL x) key) (. (TOK_TABLE_OR_COL subq1) 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)) (TOK_SELEXPR (. (TOK_TABLE_OR_COL subq1) cnt))) (TOK_ORDERBY (TOK_T
ABSORTCOLNAMEASC (. (TOK_TABLE_OR_COL x) key)) (TOK_TABSORTCOLNAMEASC (. (TOK_TABLE_OR_COL x) value)) (TOK_TABSORTCOLNAMEASC (. (TOK_TABLE_OR_COL subq1) cnt)))))
+
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-2 depends on stages: Stage-1
+ Stage-0 is a root stage
+
+STAGE PLANS:
+ Stage: Stage-1
+ Map Reduce
+ Alias -> Map Operator Tree:
+ null-subquery1:subq1-subquery1:x
+ TableScan
+ alias: x
+ Filter Operator
+ predicate:
+ expr: (key < 20.0)
+ type: boolean
+ Select Operator
+ expressions:
+ expr: key
+ type: string
+ outputColumnNames: key
+ Group By Operator
+ aggregations:
+ expr: count(1)
+ bucketGroup: false
+ keys:
+ expr: key
+ type: string
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Reduce Output Operator
+ key expressions:
+ expr: _col0
+ type: string
+ sort order: +
+ Map-reduce partition columns:
+ expr: _col0
+ type: string
+ tag: 0
+ value expressions:
+ expr: _col1
+ type: bigint
+ null-subquery2:subq1-subquery2:x1
+ TableScan
+ alias: x1
+ Filter Operator
+ predicate:
+ expr: (key > 100.0)
+ type: boolean
+ Select Operator
+ expressions:
+ expr: key
+ type: string
+ outputColumnNames: key
+ Group By Operator
+ aggregations:
+ expr: count(1)
+ bucketGroup: false
+ keys:
+ expr: key
+ type: string
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Reduce Output Operator
+ key expressions:
+ expr: _col0
+ type: string
+ sort order: +
+ Map-reduce partition columns:
+ expr: _col0
+ type: string
+ tag: 1
+ value expressions:
+ expr: _col1
+ type: bigint
+ 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
+ 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
+ Union
+ 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: string
+ expr: _col1
+ type: bigint
+ outputColumnNames: _col0, _col1, _col2
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ Group By Operator
+ aggregations:
+ expr: count(VALUE._col0)
+ bucketGroup: false
+ keys:
+ expr: KEY._col0
+ type: string
+ mode: mergepartial
+ outputColumnNames: _col0, _col1
+ Select Operator
+ expressions:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: bigint
+ outputColumnNames: _col0, _col1
+ Union
+ 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: string
+ expr: _col1
+ type: bigint
+ outputColumnNames: _col0, _col1, _col2
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ 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: string
+ expr: _col1
+ type: bigint
+ outputColumnNames: _col0, _col1, _col2
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+
+ Stage: Stage-2
+ Map Reduce
+ Alias -> Map Operator Tree:
+#### A masked pattern was here ####
+ Reduce Output Operator
+ key expressions:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: string
+ expr: _col2
+ type: bigint
+ sort order: +++
+ tag: -1
+ value expressions:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: string
+ expr: _col2
+ type: bigint
+ Reduce Operator Tree:
+ Extract
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+
+
+PREHOOK: query: SELECT x.key, x.value, subq1.cnt
+FROM
+( SELECT x.key as key, count(1) as cnt from src x where x.key < 20 group by x.key
+ UNION ALL
+ SELECT x1.key as key, count(1) as cnt from src x1 where x1.key > 100 group by x1.key
+) subq1
+JOIN src1 x ON (x.key = subq1.key) ORDER BY x.key, x.value, subq1.cnt
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+PREHOOK: Input: default@src1
+#### A masked pattern was here ####
+POSTHOOK: query: SELECT x.key, x.value, subq1.cnt
+FROM
+( SELECT x.key as key, count(1) as cnt from src x where x.key < 20 group by x.key
+ UNION ALL
+ SELECT x1.key as key, count(1) as cnt from src x1 where x1.key > 100 group by x1.key
+) subq1
+JOIN src1 x ON (x.key = subq1.key) ORDER BY x.key, x.value, subq1.cnt
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+POSTHOOK: Input: default@src1
+#### A masked pattern was here ####
+128 3
+146 val_146 2
+150 val_150 1
+213 val_213 2
+224 2
+238 val_238 2
+255 val_255 2
+273 val_273 3
+278 val_278 2
+311 val_311 3
+369 3
+401 val_401 5
+406 val_406 4
+PREHOOK: query: -- When the Correlation Optimizer is turned off, this query will be evaluated by
+-- 4 MR jobs.
+-- When the Correlation Optimizer is turned on, because both inputs of the
+-- UnionOperator are correlated, we can use 2 MR jobs to evaluate this query.
+-- The first MR job will evaluate subquery subq1 and subq1 join x. The second
+-- MR is for ordering.
+EXPLAIN
+SELECT subq1.key, subq1.cnt, x.key, x.value
+FROM
+( SELECT x.key as key, count(1) as cnt from src x where x.key < 20 group by x.key
+ UNION ALL
+ SELECT x1.value as key, count(1) as cnt from src1 x1 where x1.key > 100 group by x1.value
+) subq1
+LEFT OUTER JOIN src1 x ON (x.key = subq1.key) ORDER BY subq1.key, subq1.cnt, x.key, x.value
+PREHOOK: type: QUERY
+POSTHOOK: query: -- When the Correlation Optimizer is turned off, this query will be evaluated by
+-- 4 MR jobs.
+-- When the Correlation Optimizer is turned on, because both inputs of the
+-- UnionOperator are correlated, we can use 2 MR jobs to evaluate this query.
+-- The first MR job will evaluate subquery subq1 and subq1 join x. The second
+-- MR is for ordering.
+EXPLAIN
+SELECT subq1.key, subq1.cnt, x.key, x.value
+FROM
+( SELECT x.key as key, count(1) as cnt from src x where x.key < 20 group by x.key
+ UNION ALL
+ SELECT x1.value as key, count(1) as cnt from src1 x1 where x1.key > 100 group by x1.value
+) subq1
+LEFT OUTER JOIN src1 x ON (x.key = subq1.key) ORDER BY subq1.key, subq1.cnt, x.key, x.value
+POSTHOOK: type: QUERY
+ABSTRACT SYNTAX TREE:
+ (TOK_QUERY (TOK_FROM (TOK_LEFTOUTERJOIN (TOK_SUBQUERY (TOK_UNION (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME src) x)) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (. (TOK_TABLE_OR_COL x) key) key) (TOK_SELEXPR (TOK_FUNCTION count 1) cnt)) (TOK_WHERE (< (. (TOK_TABLE_OR_COL x) key) 20)) (TOK_GROUPBY (. (TOK_TABLE_OR_COL x) key)))) (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME src1) x1)) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (. (TOK_TABLE_OR_COL x1) value) key) (TOK_SELEXPR (TOK_FUNCTION count 1) cnt)) (TOK_WHERE (> (. (TOK_TABLE_OR_COL x1) key) 100)) (TOK_GROUPBY (. (TOK_TABLE_OR_COL x1) value))))) subq1) (TOK_TABREF (TOK_TABNAME src1) x) (= (. (TOK_TABLE_OR_COL x) key) (. (TOK_TABLE_OR_COL subq1) key)))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (. (TOK_TABLE_OR_COL subq1) key)) (TOK_SELEXPR (. (TOK_TABLE_OR_COL subq1) cnt)) (TOK_SELEXPR (. (TOK_TABLE_OR_COL x) key)) (TOK
_SELEXPR (. (TOK_TABLE_OR_COL x) value))) (TOK_ORDERBY (TOK_TABSORTCOLNAMEASC (. (TOK_TABLE_OR_COL subq1) key)) (TOK_TABSORTCOLNAMEASC (. (TOK_TABLE_OR_COL subq1) cnt)) (TOK_TABSORTCOLNAMEASC (. (TOK_TABLE_OR_COL x) key)) (TOK_TABSORTCOLNAMEASC (. (TOK_TABLE_OR_COL x) value)))))
+
+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:
+ null-subquery1:subq1-subquery1:x
+ TableScan
+ alias: x
+ Filter Operator
+ predicate:
+ expr: (key < 20.0)
+ type: boolean
+ Select Operator
+ expressions:
+ expr: key
+ type: string
+ outputColumnNames: key
+ Group By Operator
+ aggregations:
+ expr: count(1)
+ bucketGroup: false
+ keys:
+ expr: key
+ type: string
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Reduce Output Operator
+ key expressions:
+ expr: _col0
+ type: string
+ sort order: +
+ Map-reduce partition columns:
+ expr: _col0
+ type: string
+ tag: -1
+ value expressions:
+ expr: _col1
+ type: bigint
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations:
+ expr: count(VALUE._col0)
+ bucketGroup: false
+ keys:
+ expr: KEY._col0
+ type: string
+ mode: mergepartial
+ outputColumnNames: _col0, _col1
+ Select Operator
+ expressions:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: bigint
+ outputColumnNames: _col0, _col1
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+
+ Stage: Stage-2
+ Map Reduce
+ Alias -> Map Operator Tree:
+#### A masked pattern was here ####
+ TableScan
+ Union
+ 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
+#### A masked pattern was here ####
+ TableScan
+ Union
+ 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
+ x
+ TableScan
+ alias: x
+ Reduce Output Operator
+ key expressions:
+ expr: key
+ type: string
+ sort order: +
+ Map-reduce partition columns:
+ expr: key
+ type: string
+ tag: 1
+ value expressions:
+ expr: key
+ type: string
+ expr: value
+ type: string
+ 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: string
+ outputColumnNames: _col0, _col1, _col2, _col3
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+
+ Stage: Stage-3
+ Map Reduce
+ Alias -> Map Operator Tree:
+#### A masked pattern was here ####
+ Reduce Output Operator
+ key expressions:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: bigint
+ expr: _col2
+ type: string
+ expr: _col3
+ type: string
+ sort order: ++++
+ tag: -1
+ value expressions:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: bigint
+ expr: _col2
+ type: string
+ expr: _col3
+ type: string
+ Reduce Operator Tree:
+ Extract
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+
+ Stage: Stage-4
+ Map Reduce
+ Alias -> Map Operator Tree:
+ null-subquery2:subq1-subquery2:x1
+ TableScan
+ alias: x1
+ Filter Operator
+ predicate:
+ expr: (key > 100.0)
+ type: boolean
+ Select Operator
+ expressions:
+ expr: value
+ type: string
+ outputColumnNames: value
+ Group By Operator
+ aggregations:
+ expr: count(1)
+ bucketGroup: false
+ keys:
+ expr: value
+ 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 subq1.key, subq1.cnt, x.key, x.value
+FROM
+( SELECT x.key as key, count(1) as cnt from src x where x.key < 20 group by x.key
+ UNION ALL
+ SELECT x1.value as key, count(1) as cnt from src1 x1 where x1.key > 100 group by x1.value
+) subq1
+LEFT OUTER JOIN src1 x ON (x.key = subq1.key) ORDER BY subq1.key, subq1.cnt, x.key, x.value
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+PREHOOK: Input: default@src1
+#### A masked pattern was here ####
+POSTHOOK: query: SELECT subq1.key, subq1.cnt, x.key, x.value
+FROM
+( SELECT x.key as key, count(1) as cnt from src x where x.key < 20 group by x.key
+ UNION ALL
+ SELECT x1.value as key, count(1) as cnt from src1 x1 where x1.key > 100 group by x1.value
+) subq1
+LEFT OUTER JOIN src1 x ON (x.key = subq1.key) ORDER BY subq1.key, subq1.cnt, x.key, x.value
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+POSTHOOK: Input: default@src1
+#### A masked pattern was here ####
+ 3
+ 3
+ 3
+ 3
+ 3 val_165
+ 3 val_193
+ 3 val_265
+ 3 val_27
+ 3 val_409
+ 3 val_484
+0 3 NULL NULL
+10 1 NULL NULL
+11 1 NULL NULL
+12 2 NULL NULL
+15 2 NULL NULL
+17 1 NULL NULL
+18 2 NULL NULL
+19 1 NULL NULL
+2 1 NULL NULL
+4 1 NULL NULL
+5 3 NULL NULL
+8 1 NULL NULL
+9 1 NULL NULL
+val_146 1 NULL NULL
+val_150 1 NULL NULL
+val_213 1 NULL NULL
+val_238 1 NULL NULL
+val_255 1 NULL NULL
+val_273 1 NULL NULL
+val_278 1 NULL NULL
+val_311 1 NULL NULL
+val_401 1 NULL NULL
+val_406 1 NULL NULL
+PREHOOK: query: EXPLAIN
+SELECT subq1.key, subq1.cnt, x.key, x.value
+FROM
+( SELECT x.key as key, count(1) as cnt from src x where x.key < 20 group by x.key
+ UNION ALL
+ SELECT x1.value as key, count(1) as cnt from src1 x1 where x1.key > 100 group by x1.value
+) subq1
+LEFT OUTER JOIN src1 x ON (x.key = subq1.key) ORDER BY subq1.key, subq1.cnt, x.key, x.value
+PREHOOK: type: QUERY
+POSTHOOK: query: EXPLAIN
+SELECT subq1.key, subq1.cnt, x.key, x.value
+FROM
+( SELECT x.key as key, count(1) as cnt from src x where x.key < 20 group by x.key
+ UNION ALL
+ SELECT x1.value as key, count(1) as cnt from src1 x1 where x1.key > 100 group by x1.value
+) subq1
+LEFT OUTER JOIN src1 x ON (x.key = subq1.key) ORDER BY subq1.key, subq1.cnt, x.key, x.value
+POSTHOOK: type: QUERY
+ABSTRACT SYNTAX TREE:
+ (TOK_QUERY (TOK_FROM (TOK_LEFTOUTERJOIN (TOK_SUBQUERY (TOK_UNION (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME src) x)) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (. (TOK_TABLE_OR_COL x) key) key) (TOK_SELEXPR (TOK_FUNCTION count 1) cnt)) (TOK_WHERE (< (. (TOK_TABLE_OR_COL x) key) 20)) (TOK_GROUPBY (. (TOK_TABLE_OR_COL x) key)))) (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME src1) x1)) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (. (TOK_TABLE_OR_COL x1) value) key) (TOK_SELEXPR (TOK_FUNCTION count 1) cnt)) (TOK_WHERE (> (. (TOK_TABLE_OR_COL x1) key) 100)) (TOK_GROUPBY (. (TOK_TABLE_OR_COL x1) value))))) subq1) (TOK_TABREF (TOK_TABNAME src1) x) (= (. (TOK_TABLE_OR_COL x) key) (. (TOK_TABLE_OR_COL subq1) key)))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (. (TOK_TABLE_OR_COL subq1) key)) (TOK_SELEXPR (. (TOK_TABLE_OR_COL subq1) cnt)) (TOK_SELEXPR (. (TOK_TABLE_OR_COL x) key)) (TOK
_SELEXPR (. (TOK_TABLE_OR_COL x) value))) (TOK_ORDERBY (TOK_TABSORTCOLNAMEASC (. (TOK_TABLE_OR_COL subq1) key)) (TOK_TABSORTCOLNAMEASC (. (TOK_TABLE_OR_COL subq1) cnt)) (TOK_TABSORTCOLNAMEASC (. (TOK_TABLE_OR_COL x) key)) (TOK_TABSORTCOLNAMEASC (. (TOK_TABLE_OR_COL x) 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:
+ null-subquery1:subq1-subquery1:x
+ TableScan
+ alias: x
+ Filter Operator
+ predicate:
+ expr: (key < 20.0)
+ type: boolean
+ Select Operator
+ expressions:
+ expr: key
+ type: string
+ outputColumnNames: key
+ Group By Operator
+ aggregations:
+ expr: count(1)
+ bucketGroup: false
+ keys:
+ expr: key
+ type: string
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Reduce Output Operator
+ key expressions:
+ expr: _col0
+ type: string
+ sort order: +
+ Map-reduce partition columns:
+ expr: _col0
+ type: string
+ tag: 0
+ value expressions:
+ expr: _col1
+ type: bigint
+ null-subquery2:subq1-subquery2:x1
+ TableScan
+ alias: x1
+ Filter Operator
+ predicate:
+ expr: (key > 100.0)
+ type: boolean
+ Select Operator
+ expressions:
+ expr: value
+ type: string
+ outputColumnNames: value
+ Group By Operator
+ aggregations:
+ expr: count(1)
+ bucketGroup: false
+ keys:
+ expr: value
+ 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
+ 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
+ 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
+ Union
+ 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: string
+ outputColumnNames: _col0, _col1, _col2, _col3
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ 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
+ Union
+ 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: string
+ outputColumnNames: _col0, _col1, _col2, _col3
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ Mux Operator
+ Join Operator
+ condition map:
+ 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: string
+ outputColumnNames: _col0, _col1, _col2, _col3
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+
+ Stage: Stage-2
+ Map Reduce
+ Alias -> Map Operator Tree:
+#### A masked pattern was here ####
+ Reduce Output Operator
+ key expressions:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: bigint
+ expr: _col2
+ type: string
+ expr: _col3
+ type: string
+ sort order: ++++
+ tag: -1
+ value expressions:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: bigint
+ expr: _col2
+ type: string
+ expr: _col3
+ type: string
+ Reduce Operator Tree:
+ Extract
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+
+
+PREHOOK: query: SELECT subq1.key, subq1.cnt, x.key, x.value
+FROM
+( SELECT x.key as key, count(1) as cnt from src x where x.key < 20 group by x.key
+ UNION ALL
+ SELECT x1.value as key, count(1) as cnt from src1 x1 where x1.key > 100 group by x1.value
+) subq1
+LEFT OUTER JOIN src1 x ON (x.key = subq1.key) ORDER BY subq1.key, subq1.cnt, x.key, x.value
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+PREHOOK: Input: default@src1
+#### A masked pattern was here ####
+POSTHOOK: query: SELECT subq1.key, subq1.cnt, x.key, x.value
+FROM
+( SELECT x.key as key, count(1) as cnt from src x where x.key < 20 group by x.key
+ UNION ALL
+ SELECT x1.value as key, count(1) as cnt from src1 x1 where x1.key > 100 group by x1.value
+) subq1
+LEFT OUTER JOIN src1 x ON (x.key = subq1.key) ORDER BY subq1.key, subq1.cnt, x.key, x.value
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+POSTHOOK: Input: default@src1
+#### A masked pattern was here ####
+ 3
+ 3
+ 3
+ 3
+ 3 val_165
+ 3 val_193
+ 3 val_265
+ 3 val_27
+ 3 val_409
+ 3 val_484
+0 3 NULL NULL
+10 1 NULL NULL
+11 1 NULL NULL
+12 2 NULL NULL
+15 2 NULL NULL
+17 1 NULL NULL
+18 2 NULL NULL
+19 1 NULL NULL
+2 1 NULL NULL
+4 1 NULL NULL
+5 3 NULL NULL
+8 1 NULL NULL
+9 1 NULL NULL
+val_146 1 NULL NULL
+val_150 1 NULL NULL
+val_213 1 NULL NULL
+val_238 1 NULL NULL
+val_255 1 NULL NULL
+val_273 1 NULL NULL
+val_278 1 NULL NULL
+val_311 1 NULL NULL
+val_401 1 NULL NULL
+val_406 1 NULL NULL
+PREHOOK: query: -- When the Correlation Optimizer is turned on, because a input of UnionOperator is
+-- not correlated, we cannot handle this case right now. So, this query will not be
+-- optimized.
+EXPLAIN
+SELECT x.key, x.value, subq1.cnt
+FROM
+( SELECT x.key as key, count(1) as cnt from src x where x.key < 20 group by x.key
+ UNION ALL
+ SELECT x1.key as key, count(1) as cnt from src x1 where x1.key > 100 group by x1.key, x1.value
+) subq1
+JOIN src1 x ON (x.key = subq1.key) ORDER BY x.key, x.value, subq1.cnt
+PREHOOK: type: QUERY
+POSTHOOK: query: -- When the Correlation Optimizer is turned on, because a input of UnionOperator is
+-- not correlated, we cannot handle this case right now. So, this query will not be
+-- optimized.
+EXPLAIN
+SELECT x.key, x.value, subq1.cnt
+FROM
+( SELECT x.key as key, count(1) as cnt from src x where x.key < 20 group by x.key
+ UNION ALL
+ SELECT x1.key as key, count(1) as cnt from src x1 where x1.key > 100 group by x1.key, x1.value
+) subq1
+JOIN src1 x ON (x.key = subq1.key) ORDER BY x.key, x.value, subq1.cnt
+POSTHOOK: type: QUERY
+ABSTRACT SYNTAX TREE:
+ (TOK_QUERY (TOK_FROM (TOK_JOIN (TOK_SUBQUERY (TOK_UNION (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME src) x)) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (. (TOK_TABLE_OR_COL x) key) key) (TOK_SELEXPR (TOK_FUNCTION count 1) cnt)) (TOK_WHERE (< (. (TOK_TABLE_OR_COL x) key) 20)) (TOK_GROUPBY (. (TOK_TABLE_OR_COL x) key)))) (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME src) x1)) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (. (TOK_TABLE_OR_COL x1) key) key) (TOK_SELEXPR (TOK_FUNCTION count 1) cnt)) (TOK_WHERE (> (. (TOK_TABLE_OR_COL x1) key) 100)) (TOK_GROUPBY (. (TOK_TABLE_OR_COL x1) key) (. (TOK_TABLE_OR_COL x1) value))))) subq1) (TOK_TABREF (TOK_TABNAME src1) x) (= (. (TOK_TABLE_OR_COL x) key) (. (TOK_TABLE_OR_COL subq1) 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)) (TOK_SELEXPR (. (TOK_TABLE_OR_COL s
ubq1) cnt))) (TOK_ORDERBY (TOK_TABSORTCOLNAMEASC (. (TOK_TABLE_OR_COL x) key)) (TOK_TABSORTCOLNAMEASC (. (TOK_TABLE_OR_COL x) value)) (TOK_TABSORTCOLNAMEASC (. (TOK_TABLE_OR_COL subq1) cnt)))))
+
+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:
+ null-subquery1:subq1-subquery1:x
+ TableScan
+ alias: x
+ Filter Operator
+ predicate:
+ expr: (key < 20.0)
+ type: boolean
+ Select Operator
+ expressions:
+ expr: key
+ type: string
+ outputColumnNames: key
+ Group By Operator
+ aggregations:
+ expr: count(1)
+ bucketGroup: false
+ keys:
+ expr: key
+ type: string
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Reduce Output Operator
+ key expressions:
+ expr: _col0
+ type: string
+ sort order: +
+ Map-reduce partition columns:
+ expr: _col0
+ type: string
+ tag: -1
+ value expressions:
+ expr: _col1
+ type: bigint
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations:
+ expr: count(VALUE._col0)
+ bucketGroup: false
+ keys:
+ expr: KEY._col0
+ type: string
+ mode: mergepartial
+ outputColumnNames: _col0, _col1
+ Select Operator
+ expressions:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: bigint
+ outputColumnNames: _col0, _col1
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+
+ Stage: Stage-2
+ Map Reduce
+ Alias -> Map Operator Tree:
+#### A masked pattern was here ####
+ TableScan
+ Union
+ 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 ####
+ TableScan
+ Union
+ 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
+ x
+ TableScan
+ alias: x
+ Reduce Output Operator
+ key expressions:
+ expr: key
+ type: string
+ sort order: +
+ Map-reduce partition columns:
+ expr: key
+ type: string
+ tag: 1
+ value expressions:
+ expr: key
+ type: string
+ expr: value
+ type: string
+ 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: string
+ expr: _col1
+ type: bigint
+ outputColumnNames: _col0, _col1, _col2
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+
+ Stage: Stage-3
+ Map Reduce
+ Alias -> Map Operator Tree:
+#### A masked pattern was here ####
+ Reduce Output Operator
+ key expressions:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: string
+ expr: _col2
+ type: bigint
+ sort order: +++
+ tag: -1
+ value expressions:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: string
+ expr: _col2
+ type: bigint
+ Reduce Operator Tree:
+ Extract
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+
+ Stage: Stage-4
+ Map Reduce
+ Alias -> Map Operator Tree:
+ null-subquery2:subq1-subquery2:x1
+ TableScan
+ alias: x1
+ Filter Operator
+ predicate:
+ expr: (key > 100.0)
+ type: boolean
+ Select Operator
+ expressions:
+ expr: key
+ type: string
+ expr: value
+ type: string
+ outputColumnNames: key, value
+ Group By Operator
+ aggregations:
+ expr: count(1)
+ bucketGroup: false
+ keys:
+ expr: key
+ type: string
+ expr: value
+ type: string
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2
+ Reduce Output Operator
+ key expressions:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: string
+ sort order: ++
+ Map-reduce partition columns:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: string
+ tag: -1
+ value expressions:
+ expr: _col2
+ type: bigint
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations:
+ expr: count(VALUE._col0)
+ bucketGroup: false
+ keys:
+ expr: KEY._col0
+ type: string
+ expr: KEY._col1
+ type: string
+ mode: mergepartial
+ outputColumnNames: _col0, _col1, _col2
+ Select Operator
+ expressions:
+ expr: _col0
+ type: string
+ expr: _col2
+ 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: -- When the Correlation Optimizer is turned on, because a input of UnionOperator is
+-- not correlated, we cannot handle this case right now. So, this query will not be
+-- optimized.
+EXPLAIN
+SELECT subq1.key, subq1.value, x.key, x.value
+FROM
+( SELECT cast(x.key as INT) as key, count(1) as value from src x where x.key < 20 group by x.key
+ UNION ALL
+ SELECT count(1) as key, cast(x1.key as INT) as value from src x1 where x1.key > 100 group by x1.key
+) subq1
+FULL OUTER JOIN src1 x ON (x.key = subq1.key) ORDER BY subq1.key, subq1.value, x.key, x.value
+PREHOOK: type: QUERY
+POSTHOOK: query: -- When the Correlation Optimizer is turned on, because a input of UnionOperator is
+-- not correlated, we cannot handle this case right now. So, this query will not be
+-- optimized.
+EXPLAIN
+SELECT subq1.key, subq1.value, x.key, x.value
+FROM
+( SELECT cast(x.key as INT) as key, count(1) as value from src x where x.key < 20 group by x.key
+ UNION ALL
+ SELECT count(1) as key, cast(x1.key as INT) as value from src x1 where x1.key > 100 group by x1.key
+) subq1
+FULL OUTER JOIN src1 x ON (x.key = subq1.key) ORDER BY subq1.key, subq1.value, x.key, x.value
+POSTHOOK: type: QUERY
+ABSTRACT SYNTAX TREE:
+ (TOK_QUERY (TOK_FROM (TOK_FULLOUTERJOIN (TOK_SUBQUERY (TOK_UNION (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME src) x)) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_FUNCTION TOK_INT (. (TOK_TABLE_OR_COL x) key)) key) (TOK_SELEXPR (TOK_FUNCTION count 1) value)) (TOK_WHERE (< (. (TOK_TABLE_OR_COL x) key) 20)) (TOK_GROUPBY (. (TOK_TABLE_OR_COL x) key)))) (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME src) x1)) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_FUNCTION count 1) key) (TOK_SELEXPR (TOK_FUNCTION TOK_INT (. (TOK_TABLE_OR_COL x1) key)) value)) (TOK_WHERE (> (. (TOK_TABLE_OR_COL x1) key) 100)) (TOK_GROUPBY (. (TOK_TABLE_OR_COL x1) key))))) subq1) (TOK_TABREF (TOK_TABNAME src1) x) (= (. (TOK_TABLE_OR_COL x) key) (. (TOK_TABLE_OR_COL subq1) key)))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (. (TOK_TABLE_OR_COL subq1) key)) (TOK_SELEXPR (. (TOK_TABLE_OR_COL subq1) value))
(TOK_SELEXPR (. (TOK_TABLE_OR_COL x) key)) (TOK_SELEXPR (. (TOK_TABLE_OR_COL x) value))) (TOK_ORDERBY (TOK_TABSORTCOLNAMEASC (. (TOK_TABLE_OR_COL subq1) key)) (TOK_TABSORTCOLNAMEASC (. (TOK_TABLE_OR_COL subq1) value)) (TOK_TABSORTCOLNAMEASC (. (TOK_TABLE_OR_COL x) key)) (TOK_TABSORTCOLNAMEASC (. (TOK_TABLE_OR_COL x) value)))))
+
+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:
+ null-subquery1:subq1-subquery1:x
+ TableScan
+ alias: x
+ Filter Operator
+ predicate:
+ expr: (key < 20.0)
+ type: boolean
+ Select Operator
+ expressions:
+ expr: key
+ type: string
+ outputColumnNames: key
+ Group By Operator
+ aggregations:
+ expr: count(1)
+ bucketGroup: false
+ keys:
+ expr: key
+ type: string
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Reduce Output Operator
+ key expressions:
+ expr: _col0
+ type: string
+ sort order: +
+ Map-reduce partition columns:
+ expr: _col0
+ type: string
+ tag: -1
+ value expressions:
+ expr: _col1
+ type: bigint
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations:
+ expr: count(VALUE._col0)
+ bucketGroup: false
+ keys:
+ expr: KEY._col0
+ type: string
+ mode: mergepartial
+ outputColumnNames: _col0, _col1
+ Select Operator
+ expressions:
+ expr: UDFToLong(UDFToInteger(_col0))
+ type: bigint
+ 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:
+#### A masked pattern was here ####
+ TableScan
+ Union
+ Reduce Output Operator
+ key expressions:
+ expr: UDFToDouble(_col0)
+ type: double
+ sort order: +
+ Map-reduce partition columns:
+ expr: UDFToDouble(_col0)
+ type: double
+ tag: 0
+ value expressions:
+ expr: _col0
+ type: bigint
+ expr: _col1
+ type: bigint
+#### A masked pattern was here ####
+ TableScan
+ Union
+ Reduce Output Operator
+ key expressions:
+ expr: UDFToDouble(_col0)
+ type: double
+ sort order: +
+ Map-reduce partition columns:
+ expr: UDFToDouble(_col0)
+ type: double
+ tag: 0
+ value expressions:
+ expr: _col0
+ type: bigint
+ expr: _col1
+ type: bigint
+ x
+ TableScan
+ alias: x
+ Reduce Output Operator
+ key expressions:
+ expr: UDFToDouble(key)
+ type: double
+ sort order: +
+ Map-reduce partition columns:
+ expr: UDFToDouble(key)
+ type: double
+ tag: 1
+ value expressions:
+ expr: key
+ type: string
+ expr: value
+ type: string
+ 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: bigint
+ expr: _col1
+ type: bigint
+ expr: _col2
+ type: string
+ expr: _col3
+ type: string
+ outputColumnNames: _col0, _col1, _col2, _col3
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+
+ Stage: Stage-3
+ Map Reduce
+ Alias -> Map Operator Tree:
+#### A masked pattern was here ####
+ Reduce Output Operator
+ key expressions:
+ expr: _col0
+ type: bigint
+ expr: _col1
+ type: bigint
+ expr: _col2
+ type: string
+ expr: _col3
+ type: string
+ sort order: ++++
+ tag: -1
+ value expressions:
+ expr: _col0
+ type: bigint
+ expr: _col1
+ type: bigint
+ expr: _col2
+ type: string
+ expr: _col3
+ type: string
+ Reduce Operator Tree:
+ Extract
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+
+ Stage: Stage-4
+ Map Reduce
+ Alias -> Map Operator Tree:
+ null-subquery2:subq1-subquery2:x1
+ TableScan
+ alias: x1
+ Filter Operator
+ predicate:
+ expr: (key > 100.0)
+ type: boolean
+ Select Operator
+ expressions:
+ expr: key
+ type: string
+ outputColumnNames: key
+ Group By Operator
+ aggregations:
+ expr: count(1)
+ bucketGroup: false
+ keys:
+ expr: key
+ type: string
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Reduce Output Operator
+ key expressions:
+ expr: _col0
+ type: string
+ sort order: +
+ Map-reduce partition columns:
+ expr: _col0
+ type: string
+ tag: -1
+ value expressions:
+ expr: _col1
+ type: bigint
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations:
+ expr: count(VALUE._col0)
+ bucketGroup: false
+ keys:
+ expr: KEY._col0
+ type: string
+ mode: mergepartial
+ outputColumnNames: _col0, _col1
+ Select Operator
+ expressions:
+ expr: _col1
+ type: bigint
+ expr: UDFToLong(UDFToInteger(_col0))
+ 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
+
+