You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@hive.apache.org by ke...@apache.org on 2012/09/18 07:53:37 UTC
svn commit: r1386996 [4/5] - in /hive/trunk:
common/src/java/org/apache/hadoop/hive/conf/ conf/
ql/src/java/org/apache/hadoop/hive/ql/exec/
ql/src/java/org/apache/hadoop/hive/ql/optimizer/
ql/src/java/org/apache/hadoop/hive/ql/parse/ ql/src/java/org/ap...
Added: hive/trunk/ql/src/test/results/clientpositive/skewjoinopt2.q.out
URL: http://svn.apache.org/viewvc/hive/trunk/ql/src/test/results/clientpositive/skewjoinopt2.q.out?rev=1386996&view=auto
==============================================================================
--- hive/trunk/ql/src/test/results/clientpositive/skewjoinopt2.q.out (added)
+++ hive/trunk/ql/src/test/results/clientpositive/skewjoinopt2.q.out Tue Sep 18 05:53:35 2012
@@ -0,0 +1,981 @@
+PREHOOK: query: CREATE TABLE T1(key STRING, val STRING)
+SKEWED BY (key) ON ((2), (7)) STORED AS TEXTFILE
+PREHOOK: type: CREATETABLE
+POSTHOOK: query: CREATE TABLE T1(key STRING, val STRING)
+SKEWED BY (key) ON ((2), (7)) STORED AS TEXTFILE
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: default@T1
+PREHOOK: query: LOAD DATA LOCAL INPATH '../data/files/T1.txt' INTO TABLE T1
+PREHOOK: type: LOAD
+PREHOOK: Output: default@t1
+POSTHOOK: query: LOAD DATA LOCAL INPATH '../data/files/T1.txt' INTO TABLE T1
+POSTHOOK: type: LOAD
+POSTHOOK: Output: default@t1
+PREHOOK: query: CREATE TABLE T2(key STRING, val STRING)
+SKEWED BY (key) ON ((3), (8)) STORED AS TEXTFILE
+PREHOOK: type: CREATETABLE
+POSTHOOK: query: CREATE TABLE T2(key STRING, val STRING)
+SKEWED BY (key) ON ((3), (8)) STORED AS TEXTFILE
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: default@T2
+PREHOOK: query: LOAD DATA LOCAL INPATH '../data/files/T2.txt' INTO TABLE T2
+PREHOOK: type: LOAD
+PREHOOK: Output: default@t2
+POSTHOOK: query: LOAD DATA LOCAL INPATH '../data/files/T2.txt' INTO TABLE T2
+POSTHOOK: type: LOAD
+POSTHOOK: Output: default@t2
+PREHOOK: query: -- a simple query with skew on both the tables on the join key
+-- multiple skew values are present for the skewed keys
+-- but the skewed values do not overlap.
+-- The join values are a superset of the skewed keys.
+
+EXPLAIN
+SELECT a.*, b.* FROM T1 a JOIN T2 b ON a.key = b.key and a.val = b.val
+PREHOOK: type: QUERY
+POSTHOOK: query: -- a simple query with skew on both the tables on the join key
+-- multiple skew values are present for the skewed keys
+-- but the skewed values do not overlap.
+-- The join values are a superset of the skewed keys.
+
+EXPLAIN
+SELECT a.*, b.* FROM T1 a JOIN T2 b ON a.key = b.key and a.val = b.val
+POSTHOOK: type: QUERY
+ABSTRACT SYNTAX TREE:
+ (TOK_QUERY (TOK_FROM (TOK_JOIN (TOK_TABREF (TOK_TABNAME T1) a) (TOK_TABREF (TOK_TABNAME T2) b) (and (= (. (TOK_TABLE_OR_COL a) key) (. (TOK_TABLE_OR_COL b) key)) (= (. (TOK_TABLE_OR_COL a) val) (. (TOK_TABLE_OR_COL b) val))))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_ALLCOLREF (TOK_TABNAME a))) (TOK_SELEXPR (TOK_ALLCOLREF (TOK_TABNAME b))))))
+
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-2 depends on stages: Stage-1, Stage-4
+ Stage-4 is a root stage
+ Stage-0 is a root stage
+
+STAGE PLANS:
+ Stage: Stage-1
+ Map Reduce
+ Alias -> Map Operator Tree:
+ subquery1:a
+ TableScan
+ alias: a
+ Filter Operator
+ predicate:
+ expr: (not ((((key = '2') or (key = '7')) or (key = '3')) or (key = '8')))
+ type: boolean
+ Reduce Output Operator
+ key expressions:
+ expr: key
+ type: string
+ expr: val
+ type: string
+ sort order: ++
+ Map-reduce partition columns:
+ expr: key
+ type: string
+ expr: val
+ type: string
+ tag: 0
+ value expressions:
+ expr: key
+ type: string
+ expr: val
+ type: string
+ subquery1:b
+ TableScan
+ alias: b
+ Filter Operator
+ predicate:
+ expr: (not ((((key = '2') or (key = '7')) or (key = '3')) or (key = '8')))
+ type: boolean
+ Reduce Output Operator
+ key expressions:
+ expr: key
+ type: string
+ expr: val
+ type: string
+ sort order: ++
+ Map-reduce partition columns:
+ expr: key
+ type: string
+ expr: val
+ type: string
+ tag: 1
+ value expressions:
+ expr: key
+ type: string
+ expr: val
+ type: string
+ 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, _col4, _col5
+ Select Operator
+ expressions:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: string
+ expr: _col4
+ type: string
+ expr: _col5
+ 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 ####
+ TableScan
+ Union
+ Select Operator
+ SELECT * : (no compute)
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+#### A masked pattern was here ####
+ TableScan
+ Union
+ Select Operator
+ SELECT * : (no compute)
+ 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:
+ a
+ TableScan
+ alias: a
+ Filter Operator
+ predicate:
+ expr: ((((key = '2') or (key = '7')) or (key = '3')) or (key = '8'))
+ type: boolean
+ Reduce Output Operator
+ key expressions:
+ expr: key
+ type: string
+ expr: val
+ type: string
+ sort order: ++
+ Map-reduce partition columns:
+ expr: key
+ type: string
+ expr: val
+ type: string
+ tag: 0
+ value expressions:
+ expr: key
+ type: string
+ expr: val
+ type: string
+ b
+ TableScan
+ alias: b
+ Filter Operator
+ predicate:
+ expr: ((((key = '2') or (key = '7')) or (key = '3')) or (key = '8'))
+ type: boolean
+ Reduce Output Operator
+ key expressions:
+ expr: key
+ type: string
+ expr: val
+ type: string
+ sort order: ++
+ Map-reduce partition columns:
+ expr: key
+ type: string
+ expr: val
+ type: string
+ tag: 1
+ value expressions:
+ expr: key
+ type: string
+ expr: val
+ type: string
+ 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, _col4, _col5
+ Select Operator
+ expressions:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: string
+ expr: _col4
+ type: string
+ expr: _col5
+ 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-0
+ Fetch Operator
+ limit: -1
+
+PREHOOK: query: SELECT a.*, b.* FROM T1 a JOIN T2 b ON a.key = b.key and a.val = b.val
+PREHOOK: type: QUERY
+PREHOOK: Input: default@t1
+PREHOOK: Input: default@t2
+#### A masked pattern was here ####
+POSTHOOK: query: SELECT a.*, b.* FROM T1 a JOIN T2 b ON a.key = b.key and a.val = b.val
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@t1
+POSTHOOK: Input: default@t2
+#### A masked pattern was here ####
+3 13 3 13
+8 18 8 18
+8 18 8 18
+PREHOOK: query: -- test outer joins also
+
+EXPLAIN
+SELECT a.*, b.* FROM T1 a LEFT OUTER JOIN T2 b ON a.key = b.key and a.val = b.val
+PREHOOK: type: QUERY
+POSTHOOK: query: -- test outer joins also
+
+EXPLAIN
+SELECT a.*, b.* FROM T1 a LEFT OUTER JOIN T2 b ON a.key = b.key and a.val = b.val
+POSTHOOK: type: QUERY
+ABSTRACT SYNTAX TREE:
+ (TOK_QUERY (TOK_FROM (TOK_LEFTOUTERJOIN (TOK_TABREF (TOK_TABNAME T1) a) (TOK_TABREF (TOK_TABNAME T2) b) (and (= (. (TOK_TABLE_OR_COL a) key) (. (TOK_TABLE_OR_COL b) key)) (= (. (TOK_TABLE_OR_COL a) val) (. (TOK_TABLE_OR_COL b) val))))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_ALLCOLREF (TOK_TABNAME a))) (TOK_SELEXPR (TOK_ALLCOLREF (TOK_TABNAME b))))))
+
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-2 depends on stages: Stage-1, Stage-4
+ Stage-4 is a root stage
+ Stage-0 is a root stage
+
+STAGE PLANS:
+ Stage: Stage-1
+ Map Reduce
+ Alias -> Map Operator Tree:
+ subquery1:a
+ TableScan
+ alias: a
+ Filter Operator
+ predicate:
+ expr: (not ((((key = '2') or (key = '7')) or (key = '3')) or (key = '8')))
+ type: boolean
+ Reduce Output Operator
+ key expressions:
+ expr: key
+ type: string
+ expr: val
+ type: string
+ sort order: ++
+ Map-reduce partition columns:
+ expr: key
+ type: string
+ expr: val
+ type: string
+ tag: 0
+ value expressions:
+ expr: key
+ type: string
+ expr: val
+ type: string
+ subquery1:b
+ TableScan
+ alias: b
+ Filter Operator
+ predicate:
+ expr: (not ((((key = '2') or (key = '7')) or (key = '3')) or (key = '8')))
+ type: boolean
+ Reduce Output Operator
+ key expressions:
+ expr: key
+ type: string
+ expr: val
+ type: string
+ sort order: ++
+ Map-reduce partition columns:
+ expr: key
+ type: string
+ expr: val
+ type: string
+ tag: 1
+ value expressions:
+ expr: key
+ type: string
+ expr: val
+ 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, _col4, _col5
+ Select Operator
+ expressions:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: string
+ expr: _col4
+ type: string
+ expr: _col5
+ 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 ####
+ TableScan
+ Union
+ Select Operator
+ SELECT * : (no compute)
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+#### A masked pattern was here ####
+ TableScan
+ Union
+ Select Operator
+ SELECT * : (no compute)
+ 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:
+ a
+ TableScan
+ alias: a
+ Filter Operator
+ predicate:
+ expr: ((((key = '2') or (key = '7')) or (key = '3')) or (key = '8'))
+ type: boolean
+ Reduce Output Operator
+ key expressions:
+ expr: key
+ type: string
+ expr: val
+ type: string
+ sort order: ++
+ Map-reduce partition columns:
+ expr: key
+ type: string
+ expr: val
+ type: string
+ tag: 0
+ value expressions:
+ expr: key
+ type: string
+ expr: val
+ type: string
+ b
+ TableScan
+ alias: b
+ Filter Operator
+ predicate:
+ expr: ((((key = '2') or (key = '7')) or (key = '3')) or (key = '8'))
+ type: boolean
+ Reduce Output Operator
+ key expressions:
+ expr: key
+ type: string
+ expr: val
+ type: string
+ sort order: ++
+ Map-reduce partition columns:
+ expr: key
+ type: string
+ expr: val
+ type: string
+ tag: 1
+ value expressions:
+ expr: key
+ type: string
+ expr: val
+ 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, _col4, _col5
+ Select Operator
+ expressions:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: string
+ expr: _col4
+ type: string
+ expr: _col5
+ 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-0
+ Fetch Operator
+ limit: -1
+
+PREHOOK: query: SELECT a.*, b.* FROM T1 a LEFT OUTER JOIN T2 b ON a.key = b.key and a.val = b.val
+PREHOOK: type: QUERY
+PREHOOK: Input: default@t1
+PREHOOK: Input: default@t2
+#### A masked pattern was here ####
+POSTHOOK: query: SELECT a.*, b.* FROM T1 a LEFT OUTER JOIN T2 b ON a.key = b.key and a.val = b.val
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@t1
+POSTHOOK: Input: default@t2
+#### A masked pattern was here ####
+1 11 NULL NULL
+2 12 NULL NULL
+3 13 3 13
+7 17 NULL NULL
+8 18 8 18
+8 18 8 18
+8 28 NULL NULL
+PREHOOK: query: -- a group by at the end should not change anything
+
+EXPLAIN
+SELECT a.key, count(1) FROM T1 a JOIN T2 b ON a.key = b.key and a.val = b.val group by a.key
+PREHOOK: type: QUERY
+POSTHOOK: query: -- a group by at the end should not change anything
+
+EXPLAIN
+SELECT a.key, count(1) FROM T1 a JOIN T2 b ON a.key = b.key and a.val = b.val group by a.key
+POSTHOOK: type: QUERY
+ABSTRACT SYNTAX TREE:
+ (TOK_QUERY (TOK_FROM (TOK_JOIN (TOK_TABREF (TOK_TABNAME T1) a) (TOK_TABREF (TOK_TABNAME T2) b) (and (= (. (TOK_TABLE_OR_COL a) key) (. (TOK_TABLE_OR_COL b) key)) (= (. (TOK_TABLE_OR_COL a) val) (. (TOK_TABLE_OR_COL b) val))))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (. (TOK_TABLE_OR_COL a) key)) (TOK_SELEXPR (TOK_FUNCTION count 1))) (TOK_GROUPBY (. (TOK_TABLE_OR_COL a) key))))
+
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-2 depends on stages: Stage-1, Stage-4
+ Stage-4 is a root stage
+ Stage-0 is a root stage
+
+STAGE PLANS:
+ Stage: Stage-1
+ Map Reduce
+ Alias -> Map Operator Tree:
+ subquery1:a
+ TableScan
+ alias: a
+ Filter Operator
+ predicate:
+ expr: (not ((((key = '2') or (key = '7')) or (key = '3')) or (key = '8')))
+ type: boolean
+ Reduce Output Operator
+ key expressions:
+ expr: key
+ type: string
+ expr: val
+ type: string
+ sort order: ++
+ Map-reduce partition columns:
+ expr: key
+ type: string
+ expr: val
+ type: string
+ tag: 0
+ value expressions:
+ expr: key
+ type: string
+ subquery1:b
+ TableScan
+ alias: b
+ Filter Operator
+ predicate:
+ expr: (not ((((key = '2') or (key = '7')) or (key = '3')) or (key = '8')))
+ type: boolean
+ Reduce Output Operator
+ key expressions:
+ expr: key
+ type: string
+ expr: val
+ type: string
+ sort order: ++
+ Map-reduce partition columns:
+ expr: key
+ type: string
+ expr: val
+ type: string
+ tag: 1
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0 {VALUE._col0}
+ 1
+ handleSkewJoin: false
+ outputColumnNames: _col0
+ Select Operator
+ expressions:
+ expr: _col0
+ type: string
+ outputColumnNames: _col0
+ 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
+ Select Operator
+ SELECT * : (no compute)
+ Group By Operator
+ aggregations:
+ expr: count(1)
+ bucketGroup: false
+ keys:
+ expr: _col0
+ type: string
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Reduce Output Operator
+ key expressions:
+ expr: _col0
+ type: string
+ sort order: +
+ Map-reduce partition columns:
+ expr: _col0
+ type: string
+ tag: -1
+ value expressions:
+ expr: _col1
+ type: bigint
+#### A masked pattern was here ####
+ TableScan
+ Union
+ Select Operator
+ SELECT * : (no compute)
+ Group By Operator
+ aggregations:
+ expr: count(1)
+ bucketGroup: false
+ keys:
+ expr: _col0
+ type: string
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Reduce Output Operator
+ key expressions:
+ expr: _col0
+ type: string
+ sort order: +
+ Map-reduce partition columns:
+ expr: _col0
+ type: string
+ tag: -1
+ value expressions:
+ expr: _col1
+ type: bigint
+ 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.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+
+ Stage: Stage-4
+ Map Reduce
+ Alias -> Map Operator Tree:
+ a
+ TableScan
+ alias: a
+ Filter Operator
+ predicate:
+ expr: ((((key = '2') or (key = '7')) or (key = '3')) or (key = '8'))
+ type: boolean
+ Reduce Output Operator
+ key expressions:
+ expr: key
+ type: string
+ expr: val
+ type: string
+ sort order: ++
+ Map-reduce partition columns:
+ expr: key
+ type: string
+ expr: val
+ type: string
+ tag: 0
+ value expressions:
+ expr: key
+ type: string
+ b
+ TableScan
+ alias: b
+ Filter Operator
+ predicate:
+ expr: ((((key = '2') or (key = '7')) or (key = '3')) or (key = '8'))
+ type: boolean
+ Reduce Output Operator
+ key expressions:
+ expr: key
+ type: string
+ expr: val
+ type: string
+ sort order: ++
+ Map-reduce partition columns:
+ expr: key
+ type: string
+ expr: val
+ type: string
+ tag: 1
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0 {VALUE._col0}
+ 1
+ handleSkewJoin: false
+ outputColumnNames: _col0
+ Select Operator
+ expressions:
+ expr: _col0
+ type: string
+ outputColumnNames: _col0
+ 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 a.key, count(1) FROM T1 a JOIN T2 b ON a.key = b.key and a.val = b.val group by a.key
+PREHOOK: type: QUERY
+PREHOOK: Input: default@t1
+PREHOOK: Input: default@t2
+#### A masked pattern was here ####
+POSTHOOK: query: SELECT a.key, count(1) FROM T1 a JOIN T2 b ON a.key = b.key and a.val = b.val group by a.key
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@t1
+POSTHOOK: Input: default@t2
+#### A masked pattern was here ####
+3 1
+8 2
+PREHOOK: query: EXPLAIN
+SELECT a.key, count(1) FROM T1 a LEFT OUTER JOIN T2 b ON a.key = b.key and a.val = b.val group by a.key
+PREHOOK: type: QUERY
+POSTHOOK: query: EXPLAIN
+SELECT a.key, count(1) FROM T1 a LEFT OUTER JOIN T2 b ON a.key = b.key and a.val = b.val group by a.key
+POSTHOOK: type: QUERY
+ABSTRACT SYNTAX TREE:
+ (TOK_QUERY (TOK_FROM (TOK_LEFTOUTERJOIN (TOK_TABREF (TOK_TABNAME T1) a) (TOK_TABREF (TOK_TABNAME T2) b) (and (= (. (TOK_TABLE_OR_COL a) key) (. (TOK_TABLE_OR_COL b) key)) (= (. (TOK_TABLE_OR_COL a) val) (. (TOK_TABLE_OR_COL b) val))))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (. (TOK_TABLE_OR_COL a) key)) (TOK_SELEXPR (TOK_FUNCTION count 1))) (TOK_GROUPBY (. (TOK_TABLE_OR_COL a) key))))
+
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-2 depends on stages: Stage-1, Stage-4
+ Stage-4 is a root stage
+ Stage-0 is a root stage
+
+STAGE PLANS:
+ Stage: Stage-1
+ Map Reduce
+ Alias -> Map Operator Tree:
+ subquery1:a
+ TableScan
+ alias: a
+ Filter Operator
+ predicate:
+ expr: (not ((((key = '2') or (key = '7')) or (key = '3')) or (key = '8')))
+ type: boolean
+ Reduce Output Operator
+ key expressions:
+ expr: key
+ type: string
+ expr: val
+ type: string
+ sort order: ++
+ Map-reduce partition columns:
+ expr: key
+ type: string
+ expr: val
+ type: string
+ tag: 0
+ value expressions:
+ expr: key
+ type: string
+ subquery1:b
+ TableScan
+ alias: b
+ Filter Operator
+ predicate:
+ expr: (not ((((key = '2') or (key = '7')) or (key = '3')) or (key = '8')))
+ type: boolean
+ Reduce Output Operator
+ key expressions:
+ expr: key
+ type: string
+ expr: val
+ type: string
+ sort order: ++
+ Map-reduce partition columns:
+ expr: key
+ type: string
+ expr: val
+ type: string
+ tag: 1
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Left Outer Join0 to 1
+ condition expressions:
+ 0 {VALUE._col0}
+ 1
+ handleSkewJoin: false
+ outputColumnNames: _col0
+ Select Operator
+ expressions:
+ expr: _col0
+ type: string
+ outputColumnNames: _col0
+ 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
+ Select Operator
+ SELECT * : (no compute)
+ Group By Operator
+ aggregations:
+ expr: count(1)
+ bucketGroup: false
+ keys:
+ expr: _col0
+ type: string
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Reduce Output Operator
+ key expressions:
+ expr: _col0
+ type: string
+ sort order: +
+ Map-reduce partition columns:
+ expr: _col0
+ type: string
+ tag: -1
+ value expressions:
+ expr: _col1
+ type: bigint
+#### A masked pattern was here ####
+ TableScan
+ Union
+ Select Operator
+ SELECT * : (no compute)
+ Group By Operator
+ aggregations:
+ expr: count(1)
+ bucketGroup: false
+ keys:
+ expr: _col0
+ type: string
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Reduce Output Operator
+ key expressions:
+ expr: _col0
+ type: string
+ sort order: +
+ Map-reduce partition columns:
+ expr: _col0
+ type: string
+ tag: -1
+ value expressions:
+ expr: _col1
+ type: bigint
+ 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.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+
+ Stage: Stage-4
+ Map Reduce
+ Alias -> Map Operator Tree:
+ a
+ TableScan
+ alias: a
+ Filter Operator
+ predicate:
+ expr: ((((key = '2') or (key = '7')) or (key = '3')) or (key = '8'))
+ type: boolean
+ Reduce Output Operator
+ key expressions:
+ expr: key
+ type: string
+ expr: val
+ type: string
+ sort order: ++
+ Map-reduce partition columns:
+ expr: key
+ type: string
+ expr: val
+ type: string
+ tag: 0
+ value expressions:
+ expr: key
+ type: string
+ b
+ TableScan
+ alias: b
+ Filter Operator
+ predicate:
+ expr: ((((key = '2') or (key = '7')) or (key = '3')) or (key = '8'))
+ type: boolean
+ Reduce Output Operator
+ key expressions:
+ expr: key
+ type: string
+ expr: val
+ type: string
+ sort order: ++
+ Map-reduce partition columns:
+ expr: key
+ type: string
+ expr: val
+ type: string
+ tag: 1
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Left Outer Join0 to 1
+ condition expressions:
+ 0 {VALUE._col0}
+ 1
+ handleSkewJoin: false
+ outputColumnNames: _col0
+ Select Operator
+ expressions:
+ expr: _col0
+ type: string
+ outputColumnNames: _col0
+ 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 a.key, count(1) FROM T1 a LEFT OUTER JOIN T2 b ON a.key = b.key and a.val = b.val group by a.key
+PREHOOK: type: QUERY
+PREHOOK: Input: default@t1
+PREHOOK: Input: default@t2
+#### A masked pattern was here ####
+POSTHOOK: query: SELECT a.key, count(1) FROM T1 a LEFT OUTER JOIN T2 b ON a.key = b.key and a.val = b.val group by a.key
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@t1
+POSTHOOK: Input: default@t2
+#### A masked pattern was here ####
+1 1
+2 1
+3 1
+7 1
+8 3
Added: hive/trunk/ql/src/test/results/clientpositive/skewjoinopt20.q.out
URL: http://svn.apache.org/viewvc/hive/trunk/ql/src/test/results/clientpositive/skewjoinopt20.q.out?rev=1386996&view=auto
==============================================================================
--- hive/trunk/ql/src/test/results/clientpositive/skewjoinopt20.q.out (added)
+++ hive/trunk/ql/src/test/results/clientpositive/skewjoinopt20.q.out Tue Sep 18 05:53:35 2012
@@ -0,0 +1,239 @@
+PREHOOK: query: CREATE TABLE T1(key STRING, val STRING)
+CLUSTERED BY (key) SORTED BY (key) INTO 4 BUCKETS
+SKEWED BY (key) ON ((2)) STORED AS TEXTFILE
+PREHOOK: type: CREATETABLE
+POSTHOOK: query: CREATE TABLE T1(key STRING, val STRING)
+CLUSTERED BY (key) SORTED BY (key) INTO 4 BUCKETS
+SKEWED BY (key) ON ((2)) STORED AS TEXTFILE
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: default@T1
+PREHOOK: query: LOAD DATA LOCAL INPATH '../data/files/T1.txt' INTO TABLE T1
+PREHOOK: type: LOAD
+PREHOOK: Output: default@t1
+POSTHOOK: query: LOAD DATA LOCAL INPATH '../data/files/T1.txt' INTO TABLE T1
+POSTHOOK: type: LOAD
+POSTHOOK: Output: default@t1
+PREHOOK: query: CREATE TABLE T2(key STRING, val STRING) STORED AS TEXTFILE
+PREHOOK: type: CREATETABLE
+POSTHOOK: query: CREATE TABLE T2(key STRING, val STRING) STORED AS TEXTFILE
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: default@T2
+PREHOOK: query: LOAD DATA LOCAL INPATH '../data/files/T2.txt' INTO TABLE T2
+PREHOOK: type: LOAD
+PREHOOK: Output: default@t2
+POSTHOOK: query: LOAD DATA LOCAL INPATH '../data/files/T2.txt' INTO TABLE T2
+POSTHOOK: type: LOAD
+POSTHOOK: Output: default@t2
+PREHOOK: query: -- add a test where the skewed key is also the bucketized/sorted key
+-- it should not matter, and the compile time skewed join
+-- optimization is performed
+EXPLAIN
+SELECT a.*, b.* FROM T1 a JOIN T2 b ON a.key = b.key
+PREHOOK: type: QUERY
+POSTHOOK: query: -- add a test where the skewed key is also the bucketized/sorted key
+-- it should not matter, and the compile time skewed join
+-- optimization is performed
+EXPLAIN
+SELECT a.*, b.* FROM T1 a JOIN T2 b ON a.key = b.key
+POSTHOOK: type: QUERY
+ABSTRACT SYNTAX TREE:
+ (TOK_QUERY (TOK_FROM (TOK_JOIN (TOK_TABREF (TOK_TABNAME T1) a) (TOK_TABREF (TOK_TABNAME T2) 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_ALLCOLREF (TOK_TABNAME a))) (TOK_SELEXPR (TOK_ALLCOLREF (TOK_TABNAME b))))))
+
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-2 depends on stages: Stage-1, Stage-4
+ Stage-4 is a root stage
+ Stage-0 is a root stage
+
+STAGE PLANS:
+ Stage: Stage-1
+ Map Reduce
+ Alias -> Map Operator Tree:
+ subquery1:a
+ TableScan
+ alias: a
+ Filter Operator
+ predicate:
+ expr: (not (key = '2'))
+ type: boolean
+ Reduce Output Operator
+ key expressions:
+ expr: key
+ type: string
+ sort order: +
+ Map-reduce partition columns:
+ expr: key
+ type: string
+ tag: 0
+ value expressions:
+ expr: key
+ type: string
+ expr: val
+ type: string
+ subquery1:b
+ TableScan
+ alias: b
+ Filter Operator
+ predicate:
+ expr: (not (key = '2'))
+ type: boolean
+ 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: val
+ type: string
+ 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, _col4, _col5
+ Select Operator
+ expressions:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: string
+ expr: _col4
+ type: string
+ expr: _col5
+ 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 ####
+ TableScan
+ Union
+ Select Operator
+ SELECT * : (no compute)
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+#### A masked pattern was here ####
+ TableScan
+ Union
+ Select Operator
+ SELECT * : (no compute)
+ 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:
+ a
+ TableScan
+ alias: a
+ Filter Operator
+ predicate:
+ expr: (key = '2')
+ type: boolean
+ Reduce Output Operator
+ key expressions:
+ expr: key
+ type: string
+ sort order: +
+ Map-reduce partition columns:
+ expr: key
+ type: string
+ tag: 0
+ value expressions:
+ expr: key
+ type: string
+ expr: val
+ type: string
+ b
+ TableScan
+ alias: b
+ Filter Operator
+ predicate:
+ expr: (key = '2')
+ type: boolean
+ 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: val
+ type: string
+ 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, _col4, _col5
+ Select Operator
+ expressions:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: string
+ expr: _col4
+ type: string
+ expr: _col5
+ 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-0
+ Fetch Operator
+ limit: -1
+
+
+PREHOOK: query: SELECT a.*, b.* FROM T1 a JOIN T2 b ON a.key = b.key
+PREHOOK: type: QUERY
+PREHOOK: Input: default@t1
+PREHOOK: Input: default@t2
+#### A masked pattern was here ####
+POSTHOOK: query: SELECT a.*, b.* FROM T1 a JOIN T2 b ON a.key = b.key
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@t1
+POSTHOOK: Input: default@t2
+#### A masked pattern was here ####
+3 13 3 13
+8 18 8 18
+8 18 8 18
+8 28 8 18
+8 28 8 18
+2 12 2 22
Added: hive/trunk/ql/src/test/results/clientpositive/skewjoinopt3.q.out
URL: http://svn.apache.org/viewvc/hive/trunk/ql/src/test/results/clientpositive/skewjoinopt3.q.out?rev=1386996&view=auto
==============================================================================
--- hive/trunk/ql/src/test/results/clientpositive/skewjoinopt3.q.out (added)
+++ hive/trunk/ql/src/test/results/clientpositive/skewjoinopt3.q.out Tue Sep 18 05:53:35 2012
@@ -0,0 +1,456 @@
+PREHOOK: query: CREATE TABLE T1(key STRING, val STRING)
+SKEWED BY (key) ON ((2), (8)) STORED AS TEXTFILE
+PREHOOK: type: CREATETABLE
+POSTHOOK: query: CREATE TABLE T1(key STRING, val STRING)
+SKEWED BY (key) ON ((2), (8)) STORED AS TEXTFILE
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: default@T1
+PREHOOK: query: LOAD DATA LOCAL INPATH '../data/files/T1.txt' INTO TABLE T1
+PREHOOK: type: LOAD
+PREHOOK: Output: default@t1
+POSTHOOK: query: LOAD DATA LOCAL INPATH '../data/files/T1.txt' INTO TABLE T1
+POSTHOOK: type: LOAD
+POSTHOOK: Output: default@t1
+PREHOOK: query: CREATE TABLE T2(key STRING, val STRING)
+SKEWED BY (key) ON ((3), (8)) STORED AS TEXTFILE
+PREHOOK: type: CREATETABLE
+POSTHOOK: query: CREATE TABLE T2(key STRING, val STRING)
+SKEWED BY (key) ON ((3), (8)) STORED AS TEXTFILE
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: default@T2
+PREHOOK: query: LOAD DATA LOCAL INPATH '../data/files/T2.txt' INTO TABLE T2
+PREHOOK: type: LOAD
+PREHOOK: Output: default@t2
+POSTHOOK: query: LOAD DATA LOCAL INPATH '../data/files/T2.txt' INTO TABLE T2
+POSTHOOK: type: LOAD
+POSTHOOK: Output: default@t2
+PREHOOK: query: -- a simple query with skew on both the tables. One of the skewed
+-- value is common to both the tables. The skewed value should not be
+-- repeated in the filter.
+
+EXPLAIN
+SELECT a.*, b.* FROM T1 a JOIN T2 b ON a.key = b.key
+PREHOOK: type: QUERY
+POSTHOOK: query: -- a simple query with skew on both the tables. One of the skewed
+-- value is common to both the tables. The skewed value should not be
+-- repeated in the filter.
+
+EXPLAIN
+SELECT a.*, b.* FROM T1 a JOIN T2 b ON a.key = b.key
+POSTHOOK: type: QUERY
+ABSTRACT SYNTAX TREE:
+ (TOK_QUERY (TOK_FROM (TOK_JOIN (TOK_TABREF (TOK_TABNAME T1) a) (TOK_TABREF (TOK_TABNAME T2) 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_ALLCOLREF (TOK_TABNAME a))) (TOK_SELEXPR (TOK_ALLCOLREF (TOK_TABNAME b))))))
+
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-2 depends on stages: Stage-1, Stage-4
+ Stage-4 is a root stage
+ Stage-0 is a root stage
+
+STAGE PLANS:
+ Stage: Stage-1
+ Map Reduce
+ Alias -> Map Operator Tree:
+ subquery1:a
+ TableScan
+ alias: a
+ Filter Operator
+ predicate:
+ expr: (not (((key = '2') or (key = '8')) or (key = '3')))
+ type: boolean
+ Reduce Output Operator
+ key expressions:
+ expr: key
+ type: string
+ sort order: +
+ Map-reduce partition columns:
+ expr: key
+ type: string
+ tag: 0
+ value expressions:
+ expr: key
+ type: string
+ expr: val
+ type: string
+ subquery1:b
+ TableScan
+ alias: b
+ Filter Operator
+ predicate:
+ expr: (not (((key = '2') or (key = '8')) or (key = '3')))
+ type: boolean
+ 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: val
+ type: string
+ 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, _col4, _col5
+ Select Operator
+ expressions:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: string
+ expr: _col4
+ type: string
+ expr: _col5
+ 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 ####
+ TableScan
+ Union
+ Select Operator
+ SELECT * : (no compute)
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+#### A masked pattern was here ####
+ TableScan
+ Union
+ Select Operator
+ SELECT * : (no compute)
+ 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:
+ a
+ TableScan
+ alias: a
+ Filter Operator
+ predicate:
+ expr: (((key = '2') or (key = '8')) or (key = '3'))
+ type: boolean
+ Reduce Output Operator
+ key expressions:
+ expr: key
+ type: string
+ sort order: +
+ Map-reduce partition columns:
+ expr: key
+ type: string
+ tag: 0
+ value expressions:
+ expr: key
+ type: string
+ expr: val
+ type: string
+ b
+ TableScan
+ alias: b
+ Filter Operator
+ predicate:
+ expr: (((key = '2') or (key = '8')) or (key = '3'))
+ type: boolean
+ 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: val
+ type: string
+ 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, _col4, _col5
+ Select Operator
+ expressions:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: string
+ expr: _col4
+ type: string
+ expr: _col5
+ 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-0
+ Fetch Operator
+ limit: -1
+
+
+PREHOOK: query: SELECT a.*, b.* FROM T1 a JOIN T2 b ON a.key = b.key
+PREHOOK: type: QUERY
+PREHOOK: Input: default@t1
+PREHOOK: Input: default@t2
+#### A masked pattern was here ####
+POSTHOOK: query: SELECT a.*, b.* FROM T1 a JOIN T2 b ON a.key = b.key
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@t1
+POSTHOOK: Input: default@t2
+#### A masked pattern was here ####
+2 12 2 22
+3 13 3 13
+8 18 8 18
+8 18 8 18
+8 28 8 18
+8 28 8 18
+PREHOOK: query: -- test outer joins also
+
+EXPLAIN
+SELECT a.*, b.* FROM T1 a FULL OUTER JOIN T2 b ON a.key = b.key
+PREHOOK: type: QUERY
+POSTHOOK: query: -- test outer joins also
+
+EXPLAIN
+SELECT a.*, b.* FROM T1 a FULL OUTER JOIN T2 b ON a.key = b.key
+POSTHOOK: type: QUERY
+ABSTRACT SYNTAX TREE:
+ (TOK_QUERY (TOK_FROM (TOK_FULLOUTERJOIN (TOK_TABREF (TOK_TABNAME T1) a) (TOK_TABREF (TOK_TABNAME T2) 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_ALLCOLREF (TOK_TABNAME a))) (TOK_SELEXPR (TOK_ALLCOLREF (TOK_TABNAME b))))))
+
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-2 depends on stages: Stage-1, Stage-4
+ Stage-4 is a root stage
+ Stage-0 is a root stage
+
+STAGE PLANS:
+ Stage: Stage-1
+ Map Reduce
+ Alias -> Map Operator Tree:
+ subquery1:a
+ TableScan
+ alias: a
+ Filter Operator
+ predicate:
+ expr: (not (((key = '2') or (key = '8')) or (key = '3')))
+ type: boolean
+ Reduce Output Operator
+ key expressions:
+ expr: key
+ type: string
+ sort order: +
+ Map-reduce partition columns:
+ expr: key
+ type: string
+ tag: 0
+ value expressions:
+ expr: key
+ type: string
+ expr: val
+ type: string
+ subquery1:b
+ TableScan
+ alias: b
+ Filter Operator
+ predicate:
+ expr: (not (((key = '2') or (key = '8')) or (key = '3')))
+ type: boolean
+ 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: val
+ 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, _col4, _col5
+ Select Operator
+ expressions:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: string
+ expr: _col4
+ type: string
+ expr: _col5
+ 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 ####
+ TableScan
+ Union
+ Select Operator
+ SELECT * : (no compute)
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+#### A masked pattern was here ####
+ TableScan
+ Union
+ Select Operator
+ SELECT * : (no compute)
+ 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:
+ a
+ TableScan
+ alias: a
+ Filter Operator
+ predicate:
+ expr: (((key = '2') or (key = '8')) or (key = '3'))
+ type: boolean
+ Reduce Output Operator
+ key expressions:
+ expr: key
+ type: string
+ sort order: +
+ Map-reduce partition columns:
+ expr: key
+ type: string
+ tag: 0
+ value expressions:
+ expr: key
+ type: string
+ expr: val
+ type: string
+ b
+ TableScan
+ alias: b
+ Filter Operator
+ predicate:
+ expr: (((key = '2') or (key = '8')) or (key = '3'))
+ type: boolean
+ 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: val
+ 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, _col4, _col5
+ Select Operator
+ expressions:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: string
+ expr: _col4
+ type: string
+ expr: _col5
+ 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-0
+ Fetch Operator
+ limit: -1
+
+
+PREHOOK: query: SELECT a.*, b.* FROM T1 a FULL OUTER JOIN T2 b ON a.key = b.key
+PREHOOK: type: QUERY
+PREHOOK: Input: default@t1
+PREHOOK: Input: default@t2
+#### A masked pattern was here ####
+POSTHOOK: query: SELECT a.*, b.* FROM T1 a FULL OUTER JOIN T2 b ON a.key = b.key
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@t1
+POSTHOOK: Input: default@t2
+#### A masked pattern was here ####
+1 11 NULL NULL
+NULL NULL 4 14
+NULL NULL 5 15
+7 17 NULL NULL
+2 12 2 22
+3 13 3 13
+8 18 8 18
+8 18 8 18
+8 28 8 18
+8 28 8 18
Added: hive/trunk/ql/src/test/results/clientpositive/skewjoinopt4.q.out
URL: http://svn.apache.org/viewvc/hive/trunk/ql/src/test/results/clientpositive/skewjoinopt4.q.out?rev=1386996&view=auto
==============================================================================
--- hive/trunk/ql/src/test/results/clientpositive/skewjoinopt4.q.out (added)
+++ hive/trunk/ql/src/test/results/clientpositive/skewjoinopt4.q.out Tue Sep 18 05:53:35 2012
@@ -0,0 +1,446 @@
+PREHOOK: query: CREATE TABLE T1(key STRING, val STRING)
+SKEWED BY (key) ON ((2)) STORED AS TEXTFILE
+PREHOOK: type: CREATETABLE
+POSTHOOK: query: CREATE TABLE T1(key STRING, val STRING)
+SKEWED BY (key) ON ((2)) STORED AS TEXTFILE
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: default@T1
+PREHOOK: query: LOAD DATA LOCAL INPATH '../data/files/T1.txt' INTO TABLE T1
+PREHOOK: type: LOAD
+PREHOOK: Output: default@t1
+POSTHOOK: query: LOAD DATA LOCAL INPATH '../data/files/T1.txt' INTO TABLE T1
+POSTHOOK: type: LOAD
+POSTHOOK: Output: default@t1
+PREHOOK: query: CREATE TABLE T2(key STRING, val STRING) STORED AS TEXTFILE
+PREHOOK: type: CREATETABLE
+POSTHOOK: query: CREATE TABLE T2(key STRING, val STRING) STORED AS TEXTFILE
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: default@T2
+PREHOOK: query: LOAD DATA LOCAL INPATH '../data/files/T2.txt' INTO TABLE T2
+PREHOOK: type: LOAD
+PREHOOK: Output: default@t2
+POSTHOOK: query: LOAD DATA LOCAL INPATH '../data/files/T2.txt' INTO TABLE T2
+POSTHOOK: type: LOAD
+POSTHOOK: Output: default@t2
+PREHOOK: query: -- only of the tables of the join (the left table of the join) is skewed
+-- the skewed filter would still be applied to both the tables
+
+EXPLAIN
+SELECT a.*, b.* FROM T1 a JOIN T2 b ON a.key = b.key
+PREHOOK: type: QUERY
+POSTHOOK: query: -- only of the tables of the join (the left table of the join) is skewed
+-- the skewed filter would still be applied to both the tables
+
+EXPLAIN
+SELECT a.*, b.* FROM T1 a JOIN T2 b ON a.key = b.key
+POSTHOOK: type: QUERY
+ABSTRACT SYNTAX TREE:
+ (TOK_QUERY (TOK_FROM (TOK_JOIN (TOK_TABREF (TOK_TABNAME T1) a) (TOK_TABREF (TOK_TABNAME T2) 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_ALLCOLREF (TOK_TABNAME a))) (TOK_SELEXPR (TOK_ALLCOLREF (TOK_TABNAME b))))))
+
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-2 depends on stages: Stage-1, Stage-4
+ Stage-4 is a root stage
+ Stage-0 is a root stage
+
+STAGE PLANS:
+ Stage: Stage-1
+ Map Reduce
+ Alias -> Map Operator Tree:
+ subquery1:a
+ TableScan
+ alias: a
+ Filter Operator
+ predicate:
+ expr: (not (key = '2'))
+ type: boolean
+ Reduce Output Operator
+ key expressions:
+ expr: key
+ type: string
+ sort order: +
+ Map-reduce partition columns:
+ expr: key
+ type: string
+ tag: 0
+ value expressions:
+ expr: key
+ type: string
+ expr: val
+ type: string
+ subquery1:b
+ TableScan
+ alias: b
+ Filter Operator
+ predicate:
+ expr: (not (key = '2'))
+ type: boolean
+ 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: val
+ type: string
+ 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, _col4, _col5
+ Select Operator
+ expressions:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: string
+ expr: _col4
+ type: string
+ expr: _col5
+ 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 ####
+ TableScan
+ Union
+ Select Operator
+ SELECT * : (no compute)
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+#### A masked pattern was here ####
+ TableScan
+ Union
+ Select Operator
+ SELECT * : (no compute)
+ 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:
+ a
+ TableScan
+ alias: a
+ Filter Operator
+ predicate:
+ expr: (key = '2')
+ type: boolean
+ Reduce Output Operator
+ key expressions:
+ expr: key
+ type: string
+ sort order: +
+ Map-reduce partition columns:
+ expr: key
+ type: string
+ tag: 0
+ value expressions:
+ expr: key
+ type: string
+ expr: val
+ type: string
+ b
+ TableScan
+ alias: b
+ Filter Operator
+ predicate:
+ expr: (key = '2')
+ type: boolean
+ 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: val
+ type: string
+ 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, _col4, _col5
+ Select Operator
+ expressions:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: string
+ expr: _col4
+ type: string
+ expr: _col5
+ 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-0
+ Fetch Operator
+ limit: -1
+
+
+PREHOOK: query: SELECT a.*, b.* FROM T1 a JOIN T2 b ON a.key = b.key
+PREHOOK: type: QUERY
+PREHOOK: Input: default@t1
+PREHOOK: Input: default@t2
+#### A masked pattern was here ####
+POSTHOOK: query: SELECT a.*, b.* FROM T1 a JOIN T2 b ON a.key = b.key
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@t1
+POSTHOOK: Input: default@t2
+#### A masked pattern was here ####
+3 13 3 13
+8 18 8 18
+8 18 8 18
+8 28 8 18
+8 28 8 18
+2 12 2 22
+PREHOOK: query: -- the order of the join should not matter, just confirming
+EXPLAIN
+SELECT a.*, b.* FROM T2 a JOIN T1 b ON a.key = b.key
+PREHOOK: type: QUERY
+POSTHOOK: query: -- the order of the join should not matter, just confirming
+EXPLAIN
+SELECT a.*, b.* FROM T2 a JOIN T1 b ON a.key = b.key
+POSTHOOK: type: QUERY
+ABSTRACT SYNTAX TREE:
+ (TOK_QUERY (TOK_FROM (TOK_JOIN (TOK_TABREF (TOK_TABNAME T2) a) (TOK_TABREF (TOK_TABNAME T1) 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_ALLCOLREF (TOK_TABNAME a))) (TOK_SELEXPR (TOK_ALLCOLREF (TOK_TABNAME b))))))
+
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-2 depends on stages: Stage-1, Stage-4
+ Stage-4 is a root stage
+ Stage-0 is a root stage
+
+STAGE PLANS:
+ Stage: Stage-1
+ Map Reduce
+ Alias -> Map Operator Tree:
+ subquery1:a
+ TableScan
+ alias: a
+ Filter Operator
+ predicate:
+ expr: (not (key = '2'))
+ type: boolean
+ Reduce Output Operator
+ key expressions:
+ expr: key
+ type: string
+ sort order: +
+ Map-reduce partition columns:
+ expr: key
+ type: string
+ tag: 0
+ value expressions:
+ expr: key
+ type: string
+ expr: val
+ type: string
+ subquery1:b
+ TableScan
+ alias: b
+ Filter Operator
+ predicate:
+ expr: (not (key = '2'))
+ type: boolean
+ 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: val
+ type: string
+ 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, _col4, _col5
+ Select Operator
+ expressions:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: string
+ expr: _col4
+ type: string
+ expr: _col5
+ 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 ####
+ TableScan
+ Union
+ Select Operator
+ SELECT * : (no compute)
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+#### A masked pattern was here ####
+ TableScan
+ Union
+ Select Operator
+ SELECT * : (no compute)
+ 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:
+ a
+ TableScan
+ alias: a
+ Filter Operator
+ predicate:
+ expr: (key = '2')
+ type: boolean
+ Reduce Output Operator
+ key expressions:
+ expr: key
+ type: string
+ sort order: +
+ Map-reduce partition columns:
+ expr: key
+ type: string
+ tag: 0
+ value expressions:
+ expr: key
+ type: string
+ expr: val
+ type: string
+ b
+ TableScan
+ alias: b
+ Filter Operator
+ predicate:
+ expr: (key = '2')
+ type: boolean
+ 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: val
+ type: string
+ 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, _col4, _col5
+ Select Operator
+ expressions:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: string
+ expr: _col4
+ type: string
+ expr: _col5
+ 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-0
+ Fetch Operator
+ limit: -1
+
+
+PREHOOK: query: SELECT a.*, b.* FROM T2 a JOIN T1 b ON a.key = b.key
+PREHOOK: type: QUERY
+PREHOOK: Input: default@t1
+PREHOOK: Input: default@t2
+#### A masked pattern was here ####
+POSTHOOK: query: SELECT a.*, b.* FROM T2 a JOIN T1 b ON a.key = b.key
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@t1
+POSTHOOK: Input: default@t2
+#### A masked pattern was here ####
+3 13 3 13
+8 18 8 18
+8 18 8 28
+8 18 8 18
+8 18 8 28
+2 22 2 12
Added: hive/trunk/ql/src/test/results/clientpositive/skewjoinopt5.q.out
URL: http://svn.apache.org/viewvc/hive/trunk/ql/src/test/results/clientpositive/skewjoinopt5.q.out?rev=1386996&view=auto
==============================================================================
--- hive/trunk/ql/src/test/results/clientpositive/skewjoinopt5.q.out (added)
+++ hive/trunk/ql/src/test/results/clientpositive/skewjoinopt5.q.out Tue Sep 18 05:53:35 2012
@@ -0,0 +1,239 @@
+PREHOOK: query: CREATE TABLE T1(key STRING, val STRING)
+SKEWED BY (key, val) ON ((2, 12)) STORED AS TEXTFILE
+PREHOOK: type: CREATETABLE
+POSTHOOK: query: CREATE TABLE T1(key STRING, val STRING)
+SKEWED BY (key, val) ON ((2, 12)) STORED AS TEXTFILE
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: default@T1
+PREHOOK: query: LOAD DATA LOCAL INPATH '../data/files/T1.txt' INTO TABLE T1
+PREHOOK: type: LOAD
+PREHOOK: Output: default@t1
+POSTHOOK: query: LOAD DATA LOCAL INPATH '../data/files/T1.txt' INTO TABLE T1
+POSTHOOK: type: LOAD
+POSTHOOK: Output: default@t1
+PREHOOK: query: CREATE TABLE T2(key STRING, val STRING)
+SKEWED BY (key) ON ((3)) STORED AS TEXTFILE
+PREHOOK: type: CREATETABLE
+POSTHOOK: query: CREATE TABLE T2(key STRING, val STRING)
+SKEWED BY (key) ON ((3)) STORED AS TEXTFILE
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: default@T2
+PREHOOK: query: LOAD DATA LOCAL INPATH '../data/files/T2.txt' INTO TABLE T2
+PREHOOK: type: LOAD
+PREHOOK: Output: default@t2
+POSTHOOK: query: LOAD DATA LOCAL INPATH '../data/files/T2.txt' INTO TABLE T2
+POSTHOOK: type: LOAD
+POSTHOOK: Output: default@t2
+PREHOOK: query: -- One of the tables is skewed by 2 columns, and the other table is
+-- skewed by one column. Ths join is performed on the first skewed column
+
+EXPLAIN
+SELECT a.*, b.* FROM T1 a JOIN T2 b ON a.key = b.key
+PREHOOK: type: QUERY
+POSTHOOK: query: -- One of the tables is skewed by 2 columns, and the other table is
+-- skewed by one column. Ths join is performed on the first skewed column
+
+EXPLAIN
+SELECT a.*, b.* FROM T1 a JOIN T2 b ON a.key = b.key
+POSTHOOK: type: QUERY
+ABSTRACT SYNTAX TREE:
+ (TOK_QUERY (TOK_FROM (TOK_JOIN (TOK_TABREF (TOK_TABNAME T1) a) (TOK_TABREF (TOK_TABNAME T2) 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_ALLCOLREF (TOK_TABNAME a))) (TOK_SELEXPR (TOK_ALLCOLREF (TOK_TABNAME b))))))
+
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-2 depends on stages: Stage-1, Stage-4
+ Stage-4 is a root stage
+ Stage-0 is a root stage
+
+STAGE PLANS:
+ Stage: Stage-1
+ Map Reduce
+ Alias -> Map Operator Tree:
+ subquery1:a
+ TableScan
+ alias: a
+ Filter Operator
+ predicate:
+ expr: (not ((key = '2') or (key = '3')))
+ type: boolean
+ Reduce Output Operator
+ key expressions:
+ expr: key
+ type: string
+ sort order: +
+ Map-reduce partition columns:
+ expr: key
+ type: string
+ tag: 0
+ value expressions:
+ expr: key
+ type: string
+ expr: val
+ type: string
+ subquery1:b
+ TableScan
+ alias: b
+ Filter Operator
+ predicate:
+ expr: (not ((key = '2') or (key = '3')))
+ type: boolean
+ 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: val
+ type: string
+ 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, _col4, _col5
+ Select Operator
+ expressions:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: string
+ expr: _col4
+ type: string
+ expr: _col5
+ 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 ####
+ TableScan
+ Union
+ Select Operator
+ SELECT * : (no compute)
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+#### A masked pattern was here ####
+ TableScan
+ Union
+ Select Operator
+ SELECT * : (no compute)
+ 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:
+ a
+ TableScan
+ alias: a
+ Filter Operator
+ predicate:
+ expr: ((key = '2') or (key = '3'))
+ type: boolean
+ Reduce Output Operator
+ key expressions:
+ expr: key
+ type: string
+ sort order: +
+ Map-reduce partition columns:
+ expr: key
+ type: string
+ tag: 0
+ value expressions:
+ expr: key
+ type: string
+ expr: val
+ type: string
+ b
+ TableScan
+ alias: b
+ Filter Operator
+ predicate:
+ expr: ((key = '2') or (key = '3'))
+ type: boolean
+ 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: val
+ type: string
+ 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, _col4, _col5
+ Select Operator
+ expressions:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: string
+ expr: _col4
+ type: string
+ expr: _col5
+ 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-0
+ Fetch Operator
+ limit: -1
+
+
+PREHOOK: query: SELECT a.*, b.* FROM T1 a JOIN T2 b ON a.key = b.key
+PREHOOK: type: QUERY
+PREHOOK: Input: default@t1
+PREHOOK: Input: default@t2
+#### A masked pattern was here ####
+POSTHOOK: query: SELECT a.*, b.* FROM T1 a JOIN T2 b ON a.key = b.key
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@t1
+POSTHOOK: Input: default@t2
+#### A masked pattern was here ####
+8 18 8 18
+8 18 8 18
+8 28 8 18
+8 28 8 18
+2 12 2 22
+3 13 3 13