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 2013/04/26 21:16:13 UTC
svn commit: r1476348 [15/29] - in /hive/branches/vectorization: ./ beeline/
beeline/src/java/org/apache/hive/beeline/ beeline/src/test/org/
beeline/src/test/org/apache/ beeline/src/test/org/apache/hive/
beeline/src/test/org/apache/hive/beeline/ beeline...
Modified: hive/branches/vectorization/ql/src/test/results/clientpositive/auto_sortmerge_join_6.q.out
URL: http://svn.apache.org/viewvc/hive/branches/vectorization/ql/src/test/results/clientpositive/auto_sortmerge_join_6.q.out?rev=1476348&r1=1476347&r2=1476348&view=diff
==============================================================================
--- hive/branches/vectorization/ql/src/test/results/clientpositive/auto_sortmerge_join_6.q.out (original)
+++ hive/branches/vectorization/ql/src/test/results/clientpositive/auto_sortmerge_join_6.q.out Fri Apr 26 19:14:49 2013
@@ -824,3 +824,1046 @@ POSTHOOK: Lineage: tbl3.value SIMPLE [(s
POSTHOOK: Lineage: tbl4.key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
POSTHOOK: Lineage: tbl4.value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
2654
+PREHOOK: query: -- A SMB join is being followed by a regular join on a non-bucketed table on a different key
+explain select count(*) FROM tbl1 a JOIN tbl2 b ON a.key = b.key join src c on c.value = a.value
+PREHOOK: type: QUERY
+POSTHOOK: query: -- A SMB join is being followed by a regular join on a non-bucketed table on a different key
+explain select count(*) FROM tbl1 a JOIN tbl2 b ON a.key = b.key join src c on c.value = a.value
+POSTHOOK: type: QUERY
+POSTHOOK: Lineage: tbl1.key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: tbl1.value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: tbl2.key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: tbl2.value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: tbl3.key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: tbl3.value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: tbl4.key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: tbl4.value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+ABSTRACT SYNTAX TREE:
+ (TOK_QUERY (TOK_FROM (TOK_JOIN (TOK_JOIN (TOK_TABREF (TOK_TABNAME tbl1) a) (TOK_TABREF (TOK_TABNAME tbl2) b) (= (. (TOK_TABLE_OR_COL a) key) (. (TOK_TABLE_OR_COL b) key))) (TOK_TABREF (TOK_TABNAME src) c) (= (. (TOK_TABLE_OR_COL c) value) (. (TOK_TABLE_OR_COL a) value)))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_FUNCTIONSTAR count)))))
+
+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:
+ a
+ TableScan
+ alias: a
+ Sorted Merge Bucket Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0 {value}
+ 1
+ handleSkewJoin: false
+ keys:
+ 0 [Column[key]]
+ 1 [Column[key]]
+ outputColumnNames: _col1
+ Position of Big Table: 0
+ Reduce Output Operator
+ key expressions:
+ expr: _col1
+ type: string
+ sort order: +
+ Map-reduce partition columns:
+ expr: _col1
+ type: string
+ tag: 0
+ c
+ TableScan
+ alias: c
+ Reduce Output Operator
+ key expressions:
+ expr: value
+ type: string
+ sort order: +
+ Map-reduce partition columns:
+ expr: value
+ type: string
+ tag: 1
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0
+ 1
+ handleSkewJoin: false
+ Select Operator
+ Group By Operator
+ aggregations:
+ expr: count()
+ bucketGroup: false
+ mode: hash
+ 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 ####
+ Reduce Output Operator
+ sort order:
+ tag: -1
+ value expressions:
+ expr: _col0
+ type: bigint
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations:
+ expr: count(VALUE._col0)
+ bucketGroup: false
+ mode: mergepartial
+ outputColumnNames: _col0
+ Select Operator
+ expressions:
+ expr: _col0
+ type: bigint
+ outputColumnNames: _col0
+ 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 count(*) FROM tbl1 a JOIN tbl2 b ON a.key = b.key join src c on c.value = a.value
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+PREHOOK: Input: default@tbl1
+PREHOOK: Input: default@tbl2
+#### A masked pattern was here ####
+POSTHOOK: query: select count(*) FROM tbl1 a JOIN tbl2 b ON a.key = b.key join src c on c.value = a.value
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+POSTHOOK: Input: default@tbl1
+POSTHOOK: Input: default@tbl2
+#### A masked pattern was here ####
+POSTHOOK: Lineage: tbl1.key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: tbl1.value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: tbl2.key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: tbl2.value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: tbl3.key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: tbl3.value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: tbl4.key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: tbl4.value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+2654
+PREHOOK: query: -- A SMB join is being followed by a regular join on a non-bucketed table on the same key
+explain select count(*) FROM tbl1 a JOIN tbl2 b ON a.key = b.key join src c on c.key = a.key
+PREHOOK: type: QUERY
+POSTHOOK: query: -- A SMB join is being followed by a regular join on a non-bucketed table on the same key
+explain select count(*) FROM tbl1 a JOIN tbl2 b ON a.key = b.key join src c on c.key = a.key
+POSTHOOK: type: QUERY
+POSTHOOK: Lineage: tbl1.key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: tbl1.value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: tbl2.key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: tbl2.value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: tbl3.key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: tbl3.value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: tbl4.key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: tbl4.value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+ABSTRACT SYNTAX TREE:
+ (TOK_QUERY (TOK_FROM (TOK_JOIN (TOK_JOIN (TOK_TABREF (TOK_TABNAME tbl1) a) (TOK_TABREF (TOK_TABNAME tbl2) b) (= (. (TOK_TABLE_OR_COL a) key) (. (TOK_TABLE_OR_COL b) key))) (TOK_TABREF (TOK_TABNAME src) c) (= (. (TOK_TABLE_OR_COL c) key) (. (TOK_TABLE_OR_COL a) key)))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_FUNCTIONSTAR count)))))
+
+STAGE DEPENDENCIES:
+ Stage-8 is a root stage , consists of Stage-9, Stage-10, Stage-11, Stage-1
+ Stage-9 has a backup stage: Stage-1
+ Stage-5 depends on stages: Stage-9
+ Stage-2 depends on stages: Stage-1, Stage-5, Stage-6, Stage-7
+ Stage-10 has a backup stage: Stage-1
+ Stage-6 depends on stages: Stage-10
+ Stage-11 has a backup stage: Stage-1
+ Stage-7 depends on stages: Stage-11
+ Stage-1
+ Stage-0 is a root stage
+
+STAGE PLANS:
+ Stage: Stage-8
+ Conditional Operator
+
+ Stage: Stage-9
+ Map Reduce Local Work
+ Alias -> Map Local Tables:
+ b
+ Fetch Operator
+ limit: -1
+ c
+ Fetch Operator
+ limit: -1
+ Alias -> Map Local Operator Tree:
+ b
+ TableScan
+ alias: b
+ HashTable Sink Operator
+ condition expressions:
+ 0
+ 1
+ 2
+ handleSkewJoin: false
+ keys:
+ 0 [class org.apache.hadoop.hive.ql.udf.generic.GenericUDFBridge(Column[key]()]
+ 1 [class org.apache.hadoop.hive.ql.udf.generic.GenericUDFBridge(Column[key]()]
+ 2 [class org.apache.hadoop.hive.ql.udf.generic.GenericUDFBridge(Column[key]()]
+ Position of Big Table: 0
+ c
+ TableScan
+ alias: c
+ HashTable Sink Operator
+ condition expressions:
+ 0
+ 1
+ 2
+ handleSkewJoin: false
+ keys:
+ 0 [class org.apache.hadoop.hive.ql.udf.generic.GenericUDFBridge(Column[key]()]
+ 1 [class org.apache.hadoop.hive.ql.udf.generic.GenericUDFBridge(Column[key]()]
+ 2 [class org.apache.hadoop.hive.ql.udf.generic.GenericUDFBridge(Column[key]()]
+ Position of Big Table: 0
+
+ Stage: Stage-5
+ Map Reduce
+ Alias -> Map Operator Tree:
+ a
+ TableScan
+ alias: a
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ Inner Join 0 to 2
+ condition expressions:
+ 0
+ 1
+ 2
+ handleSkewJoin: false
+ keys:
+ 0 [class org.apache.hadoop.hive.ql.udf.generic.GenericUDFBridge(Column[key]()]
+ 1 [class org.apache.hadoop.hive.ql.udf.generic.GenericUDFBridge(Column[key]()]
+ 2 [class org.apache.hadoop.hive.ql.udf.generic.GenericUDFBridge(Column[key]()]
+ Position of Big Table: 0
+ Select Operator
+ Group By Operator
+ aggregations:
+ expr: count()
+ bucketGroup: false
+ mode: hash
+ 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
+ Local Work:
+ Map Reduce Local Work
+
+ Stage: Stage-2
+ Map Reduce
+ Alias -> Map Operator Tree:
+#### A masked pattern was here ####
+ Reduce Output Operator
+ sort order:
+ tag: -1
+ value expressions:
+ expr: _col0
+ type: bigint
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations:
+ expr: count(VALUE._col0)
+ bucketGroup: false
+ mode: mergepartial
+ outputColumnNames: _col0
+ Select Operator
+ expressions:
+ expr: _col0
+ type: bigint
+ outputColumnNames: _col0
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+
+ Stage: Stage-10
+ Map Reduce Local Work
+ Alias -> Map Local Tables:
+ a
+ Fetch Operator
+ limit: -1
+ c
+ Fetch Operator
+ limit: -1
+ Alias -> Map Local Operator Tree:
+ a
+ TableScan
+ alias: a
+ HashTable Sink Operator
+ condition expressions:
+ 0
+ 1
+ 2
+ handleSkewJoin: false
+ keys:
+ 0 [class org.apache.hadoop.hive.ql.udf.generic.GenericUDFBridge(Column[key]()]
+ 1 [class org.apache.hadoop.hive.ql.udf.generic.GenericUDFBridge(Column[key]()]
+ 2 [class org.apache.hadoop.hive.ql.udf.generic.GenericUDFBridge(Column[key]()]
+ Position of Big Table: 1
+ c
+ TableScan
+ alias: c
+ HashTable Sink Operator
+ condition expressions:
+ 0
+ 1
+ 2
+ handleSkewJoin: false
+ keys:
+ 0 [class org.apache.hadoop.hive.ql.udf.generic.GenericUDFBridge(Column[key]()]
+ 1 [class org.apache.hadoop.hive.ql.udf.generic.GenericUDFBridge(Column[key]()]
+ 2 [class org.apache.hadoop.hive.ql.udf.generic.GenericUDFBridge(Column[key]()]
+ Position of Big Table: 1
+
+ Stage: Stage-6
+ Map Reduce
+ Alias -> Map Operator Tree:
+ b
+ TableScan
+ alias: b
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ Inner Join 0 to 2
+ condition expressions:
+ 0
+ 1
+ 2
+ handleSkewJoin: false
+ keys:
+ 0 [class org.apache.hadoop.hive.ql.udf.generic.GenericUDFBridge(Column[key]()]
+ 1 [class org.apache.hadoop.hive.ql.udf.generic.GenericUDFBridge(Column[key]()]
+ 2 [class org.apache.hadoop.hive.ql.udf.generic.GenericUDFBridge(Column[key]()]
+ Position of Big Table: 1
+ Select Operator
+ Group By Operator
+ aggregations:
+ expr: count()
+ bucketGroup: false
+ mode: hash
+ 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
+ Local Work:
+ Map Reduce Local Work
+
+ Stage: Stage-11
+ Map Reduce Local Work
+ Alias -> Map Local Tables:
+ a
+ Fetch Operator
+ limit: -1
+ b
+ Fetch Operator
+ limit: -1
+ Alias -> Map Local Operator Tree:
+ a
+ TableScan
+ alias: a
+ HashTable Sink Operator
+ condition expressions:
+ 0
+ 1
+ 2
+ handleSkewJoin: false
+ keys:
+ 0 [class org.apache.hadoop.hive.ql.udf.generic.GenericUDFBridge(Column[key]()]
+ 1 [class org.apache.hadoop.hive.ql.udf.generic.GenericUDFBridge(Column[key]()]
+ 2 [class org.apache.hadoop.hive.ql.udf.generic.GenericUDFBridge(Column[key]()]
+ Position of Big Table: 2
+ b
+ TableScan
+ alias: b
+ HashTable Sink Operator
+ condition expressions:
+ 0
+ 1
+ 2
+ handleSkewJoin: false
+ keys:
+ 0 [class org.apache.hadoop.hive.ql.udf.generic.GenericUDFBridge(Column[key]()]
+ 1 [class org.apache.hadoop.hive.ql.udf.generic.GenericUDFBridge(Column[key]()]
+ 2 [class org.apache.hadoop.hive.ql.udf.generic.GenericUDFBridge(Column[key]()]
+ Position of Big Table: 2
+
+ Stage: Stage-7
+ Map Reduce
+ Alias -> Map Operator Tree:
+ c
+ TableScan
+ alias: c
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ Inner Join 0 to 2
+ condition expressions:
+ 0
+ 1
+ 2
+ handleSkewJoin: false
+ keys:
+ 0 [class org.apache.hadoop.hive.ql.udf.generic.GenericUDFBridge(Column[key]()]
+ 1 [class org.apache.hadoop.hive.ql.udf.generic.GenericUDFBridge(Column[key]()]
+ 2 [class org.apache.hadoop.hive.ql.udf.generic.GenericUDFBridge(Column[key]()]
+ Position of Big Table: 2
+ Select Operator
+ Group By Operator
+ aggregations:
+ expr: count()
+ bucketGroup: false
+ mode: hash
+ 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
+ Local Work:
+ Map Reduce Local Work
+
+ Stage: Stage-1
+ Map Reduce
+ Alias -> Map Operator Tree:
+ a
+ TableScan
+ alias: a
+ Reduce Output Operator
+ key expressions:
+ expr: UDFToDouble(key)
+ type: double
+ sort order: +
+ Map-reduce partition columns:
+ expr: UDFToDouble(key)
+ type: double
+ tag: 0
+ b
+ TableScan
+ alias: b
+ Reduce Output Operator
+ key expressions:
+ expr: UDFToDouble(key)
+ type: double
+ sort order: +
+ Map-reduce partition columns:
+ expr: UDFToDouble(key)
+ type: double
+ tag: 1
+ c
+ TableScan
+ alias: c
+ Reduce Output Operator
+ key expressions:
+ expr: UDFToDouble(key)
+ type: double
+ sort order: +
+ Map-reduce partition columns:
+ expr: UDFToDouble(key)
+ type: double
+ tag: 2
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ Inner Join 0 to 2
+ condition expressions:
+ 0
+ 1
+ 2
+ handleSkewJoin: false
+ Select Operator
+ Group By Operator
+ aggregations:
+ expr: count()
+ bucketGroup: false
+ mode: hash
+ 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 count(*) FROM tbl1 a JOIN tbl2 b ON a.key = b.key join src c on c.key = a.key
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+PREHOOK: Input: default@tbl1
+PREHOOK: Input: default@tbl2
+#### A masked pattern was here ####
+POSTHOOK: query: select count(*) FROM tbl1 a JOIN tbl2 b ON a.key = b.key join src c on c.key = a.key
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+POSTHOOK: Input: default@tbl1
+POSTHOOK: Input: default@tbl2
+#### A masked pattern was here ####
+POSTHOOK: Lineage: tbl1.key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: tbl1.value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: tbl2.key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: tbl2.value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: tbl3.key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: tbl3.value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: tbl4.key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: tbl4.value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+2654
+PREHOOK: query: -- A SMB join is being followed by a regular join on a bucketed table on the same key
+explain select count(*) FROM tbl1 a JOIN tbl2 b ON a.key = b.key join tbl3 c on c.key = a.key
+PREHOOK: type: QUERY
+POSTHOOK: query: -- A SMB join is being followed by a regular join on a bucketed table on the same key
+explain select count(*) FROM tbl1 a JOIN tbl2 b ON a.key = b.key join tbl3 c on c.key = a.key
+POSTHOOK: type: QUERY
+POSTHOOK: Lineage: tbl1.key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: tbl1.value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: tbl2.key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: tbl2.value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: tbl3.key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: tbl3.value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: tbl4.key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: tbl4.value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+ABSTRACT SYNTAX TREE:
+ (TOK_QUERY (TOK_FROM (TOK_JOIN (TOK_JOIN (TOK_TABREF (TOK_TABNAME tbl1) a) (TOK_TABREF (TOK_TABNAME tbl2) b) (= (. (TOK_TABLE_OR_COL a) key) (. (TOK_TABLE_OR_COL b) key))) (TOK_TABREF (TOK_TABNAME tbl3) c) (= (. (TOK_TABLE_OR_COL c) key) (. (TOK_TABLE_OR_COL a) key)))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_FUNCTIONSTAR count)))))
+
+STAGE DEPENDENCIES:
+ Stage-7 is a root stage , consists of Stage-8, Stage-9, Stage-10, Stage-1
+ Stage-8 has a backup stage: Stage-1
+ Stage-4 depends on stages: Stage-8
+ Stage-9 has a backup stage: Stage-1
+ Stage-5 depends on stages: Stage-9
+ Stage-10 has a backup stage: Stage-1
+ Stage-6 depends on stages: Stage-10
+ Stage-1
+ Stage-0 is a root stage
+
+STAGE PLANS:
+ Stage: Stage-7
+ Conditional Operator
+
+ Stage: Stage-8
+ Map Reduce Local Work
+ Alias -> Map Local Tables:
+ b
+ Fetch Operator
+ limit: -1
+ c
+ Fetch Operator
+ limit: -1
+ Alias -> Map Local Operator Tree:
+ b
+ TableScan
+ alias: b
+ HashTable Sink Operator
+ condition expressions:
+ 0
+ 1
+ 2
+ handleSkewJoin: false
+ keys:
+ 0 [Column[key]]
+ 1 [Column[key]]
+ 2 [Column[key]]
+ Position of Big Table: 0
+ c
+ TableScan
+ alias: c
+ HashTable Sink Operator
+ condition expressions:
+ 0
+ 1
+ 2
+ handleSkewJoin: false
+ keys:
+ 0 [Column[key]]
+ 1 [Column[key]]
+ 2 [Column[key]]
+ Position of Big Table: 0
+
+ Stage: Stage-4
+ Map Reduce
+ Alias -> Map Operator Tree:
+ a
+ TableScan
+ alias: a
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ Inner Join 0 to 2
+ condition expressions:
+ 0
+ 1
+ 2
+ handleSkewJoin: false
+ keys:
+ 0 [Column[key]]
+ 1 [Column[key]]
+ 2 [Column[key]]
+ Position of Big Table: 0
+ Select Operator
+ Group By Operator
+ aggregations:
+ expr: count()
+ bucketGroup: false
+ mode: hash
+ outputColumnNames: _col0
+ Reduce Output Operator
+ sort order:
+ tag: -1
+ value expressions:
+ expr: _col0
+ type: bigint
+ Local Work:
+ Map Reduce Local Work
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations:
+ expr: count(VALUE._col0)
+ bucketGroup: false
+ mode: mergepartial
+ outputColumnNames: _col0
+ Select Operator
+ expressions:
+ expr: _col0
+ type: bigint
+ outputColumnNames: _col0
+ 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-9
+ Map Reduce Local Work
+ Alias -> Map Local Tables:
+ a
+ Fetch Operator
+ limit: -1
+ c
+ Fetch Operator
+ limit: -1
+ Alias -> Map Local Operator Tree:
+ a
+ TableScan
+ alias: a
+ HashTable Sink Operator
+ condition expressions:
+ 0
+ 1
+ 2
+ handleSkewJoin: false
+ keys:
+ 0 [Column[key]]
+ 1 [Column[key]]
+ 2 [Column[key]]
+ Position of Big Table: 1
+ c
+ TableScan
+ alias: c
+ HashTable Sink Operator
+ condition expressions:
+ 0
+ 1
+ 2
+ handleSkewJoin: false
+ keys:
+ 0 [Column[key]]
+ 1 [Column[key]]
+ 2 [Column[key]]
+ Position of Big Table: 1
+
+ Stage: Stage-5
+ Map Reduce
+ Alias -> Map Operator Tree:
+ b
+ TableScan
+ alias: b
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ Inner Join 0 to 2
+ condition expressions:
+ 0
+ 1
+ 2
+ handleSkewJoin: false
+ keys:
+ 0 [Column[key]]
+ 1 [Column[key]]
+ 2 [Column[key]]
+ Position of Big Table: 1
+ Select Operator
+ Group By Operator
+ aggregations:
+ expr: count()
+ bucketGroup: false
+ mode: hash
+ outputColumnNames: _col0
+ Reduce Output Operator
+ sort order:
+ tag: -1
+ value expressions:
+ expr: _col0
+ type: bigint
+ Local Work:
+ Map Reduce Local Work
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations:
+ expr: count(VALUE._col0)
+ bucketGroup: false
+ mode: mergepartial
+ outputColumnNames: _col0
+ Select Operator
+ expressions:
+ expr: _col0
+ type: bigint
+ outputColumnNames: _col0
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+
+ Stage: Stage-10
+ Map Reduce Local Work
+ Alias -> Map Local Tables:
+ a
+ Fetch Operator
+ limit: -1
+ b
+ Fetch Operator
+ limit: -1
+ Alias -> Map Local Operator Tree:
+ a
+ TableScan
+ alias: a
+ HashTable Sink Operator
+ condition expressions:
+ 0
+ 1
+ 2
+ handleSkewJoin: false
+ keys:
+ 0 [Column[key]]
+ 1 [Column[key]]
+ 2 [Column[key]]
+ Position of Big Table: 2
+ b
+ TableScan
+ alias: b
+ HashTable Sink Operator
+ condition expressions:
+ 0
+ 1
+ 2
+ handleSkewJoin: false
+ keys:
+ 0 [Column[key]]
+ 1 [Column[key]]
+ 2 [Column[key]]
+ Position of Big Table: 2
+
+ Stage: Stage-6
+ Map Reduce
+ Alias -> Map Operator Tree:
+ c
+ TableScan
+ alias: c
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ Inner Join 0 to 2
+ condition expressions:
+ 0
+ 1
+ 2
+ handleSkewJoin: false
+ keys:
+ 0 [Column[key]]
+ 1 [Column[key]]
+ 2 [Column[key]]
+ Position of Big Table: 2
+ Select Operator
+ Group By Operator
+ aggregations:
+ expr: count()
+ bucketGroup: false
+ mode: hash
+ outputColumnNames: _col0
+ Reduce Output Operator
+ sort order:
+ tag: -1
+ value expressions:
+ expr: _col0
+ type: bigint
+ Local Work:
+ Map Reduce Local Work
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations:
+ expr: count(VALUE._col0)
+ bucketGroup: false
+ mode: mergepartial
+ outputColumnNames: _col0
+ Select Operator
+ expressions:
+ expr: _col0
+ type: bigint
+ outputColumnNames: _col0
+ 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-1
+ Map Reduce
+ Alias -> Map Operator Tree:
+ a
+ TableScan
+ alias: a
+ Sorted Merge Bucket Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ Inner Join 0 to 2
+ condition expressions:
+ 0
+ 1
+ 2
+ handleSkewJoin: false
+ keys:
+ 0 [Column[key]]
+ 1 [Column[key]]
+ 2 [Column[key]]
+ Position of Big Table: 0
+ Select Operator
+ Group By Operator
+ aggregations:
+ expr: count()
+ bucketGroup: false
+ mode: hash
+ outputColumnNames: _col0
+ Reduce Output Operator
+ sort order:
+ tag: -1
+ value expressions:
+ expr: _col0
+ type: bigint
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations:
+ expr: count(VALUE._col0)
+ bucketGroup: false
+ mode: mergepartial
+ outputColumnNames: _col0
+ Select Operator
+ expressions:
+ expr: _col0
+ type: bigint
+ outputColumnNames: _col0
+ 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 count(*) FROM tbl1 a JOIN tbl2 b ON a.key = b.key join tbl3 c on c.key = a.key
+PREHOOK: type: QUERY
+PREHOOK: Input: default@tbl1
+PREHOOK: Input: default@tbl2
+PREHOOK: Input: default@tbl3
+#### A masked pattern was here ####
+POSTHOOK: query: select count(*) FROM tbl1 a JOIN tbl2 b ON a.key = b.key join tbl3 c on c.key = a.key
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@tbl1
+POSTHOOK: Input: default@tbl2
+POSTHOOK: Input: default@tbl3
+#### A masked pattern was here ####
+POSTHOOK: Lineage: tbl1.key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: tbl1.value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: tbl2.key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: tbl2.value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: tbl3.key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: tbl3.value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: tbl4.key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: tbl4.value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+2654
+PREHOOK: query: -- A SMB join is being followed by a regular join on a bucketed table on a different key
+explain select count(*) FROM tbl1 a JOIN tbl2 b ON a.key = b.key join tbl4 c on c.value = a.value
+PREHOOK: type: QUERY
+POSTHOOK: query: -- A SMB join is being followed by a regular join on a bucketed table on a different key
+explain select count(*) FROM tbl1 a JOIN tbl2 b ON a.key = b.key join tbl4 c on c.value = a.value
+POSTHOOK: type: QUERY
+POSTHOOK: Lineage: tbl1.key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: tbl1.value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: tbl2.key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: tbl2.value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: tbl3.key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: tbl3.value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: tbl4.key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: tbl4.value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+ABSTRACT SYNTAX TREE:
+ (TOK_QUERY (TOK_FROM (TOK_JOIN (TOK_JOIN (TOK_TABREF (TOK_TABNAME tbl1) a) (TOK_TABREF (TOK_TABNAME tbl2) b) (= (. (TOK_TABLE_OR_COL a) key) (. (TOK_TABLE_OR_COL b) key))) (TOK_TABREF (TOK_TABNAME tbl4) c) (= (. (TOK_TABLE_OR_COL c) value) (. (TOK_TABLE_OR_COL a) value)))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_FUNCTIONSTAR count)))))
+
+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:
+ a
+ TableScan
+ alias: a
+ Sorted Merge Bucket Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0 {value}
+ 1
+ handleSkewJoin: false
+ keys:
+ 0 [Column[key]]
+ 1 [Column[key]]
+ outputColumnNames: _col1
+ Position of Big Table: 0
+ Reduce Output Operator
+ key expressions:
+ expr: _col1
+ type: string
+ sort order: +
+ Map-reduce partition columns:
+ expr: _col1
+ type: string
+ tag: 0
+ c
+ TableScan
+ alias: c
+ Reduce Output Operator
+ key expressions:
+ expr: value
+ type: string
+ sort order: +
+ Map-reduce partition columns:
+ expr: value
+ type: string
+ tag: 1
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0
+ 1
+ handleSkewJoin: false
+ Select Operator
+ Group By Operator
+ aggregations:
+ expr: count()
+ bucketGroup: false
+ mode: hash
+ 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 ####
+ Reduce Output Operator
+ sort order:
+ tag: -1
+ value expressions:
+ expr: _col0
+ type: bigint
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations:
+ expr: count(VALUE._col0)
+ bucketGroup: false
+ mode: mergepartial
+ outputColumnNames: _col0
+ Select Operator
+ expressions:
+ expr: _col0
+ type: bigint
+ outputColumnNames: _col0
+ 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 count(*) FROM tbl1 a JOIN tbl2 b ON a.key = b.key join tbl4 c on c.value = a.value
+PREHOOK: type: QUERY
+PREHOOK: Input: default@tbl1
+PREHOOK: Input: default@tbl2
+PREHOOK: Input: default@tbl4
+#### A masked pattern was here ####
+POSTHOOK: query: select count(*) FROM tbl1 a JOIN tbl2 b ON a.key = b.key join tbl4 c on c.value = a.value
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@tbl1
+POSTHOOK: Input: default@tbl2
+POSTHOOK: Input: default@tbl4
+#### A masked pattern was here ####
+POSTHOOK: Lineage: tbl1.key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: tbl1.value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: tbl2.key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: tbl2.value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: tbl3.key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: tbl3.value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: tbl4.key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: tbl4.value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+2654
Modified: hive/branches/vectorization/ql/src/test/results/clientpositive/auto_sortmerge_join_7.q.out
URL: http://svn.apache.org/viewvc/hive/branches/vectorization/ql/src/test/results/clientpositive/auto_sortmerge_join_7.q.out?rev=1476348&r1=1476347&r2=1476348&view=diff
==============================================================================
--- hive/branches/vectorization/ql/src/test/results/clientpositive/auto_sortmerge_join_7.q.out (original)
+++ hive/branches/vectorization/ql/src/test/results/clientpositive/auto_sortmerge_join_7.q.out Fri Apr 26 19:14:49 2013
@@ -488,3 +488,773 @@ POSTHOOK: Input: default@bucket_small@ds
POSTHOOK: Input: default@bucket_small@ds=2008-04-09
#### A masked pattern was here ####
76
+PREHOOK: query: explain extended select count(*) FROM bucket_big a JOIN bucket_small b ON a.key = b.key
+PREHOOK: type: QUERY
+POSTHOOK: query: explain extended select count(*) FROM bucket_big a JOIN bucket_small b ON a.key = b.key
+POSTHOOK: type: QUERY
+ABSTRACT SYNTAX TREE:
+ (TOK_QUERY (TOK_FROM (TOK_JOIN (TOK_TABREF (TOK_TABNAME bucket_big) a) (TOK_TABREF (TOK_TABNAME bucket_small) 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_FUNCTIONSTAR count)))))
+
+STAGE DEPENDENCIES:
+ Stage-5 is a root stage , consists of Stage-6, Stage-7, Stage-1
+ Stage-6 has a backup stage: Stage-1
+ Stage-3 depends on stages: Stage-6
+ Stage-7 has a backup stage: Stage-1
+ Stage-4 depends on stages: Stage-7
+ Stage-1
+ Stage-0 is a root stage
+
+STAGE PLANS:
+ Stage: Stage-5
+ Conditional Operator
+
+ Stage: Stage-6
+ Map Reduce Local Work
+ Alias -> Map Local Tables:
+ b
+ Fetch Operator
+ limit: -1
+ Alias -> Map Local Operator Tree:
+ b
+ TableScan
+ alias: b
+ GatherStats: false
+ HashTable Sink Operator
+ condition expressions:
+ 0
+ 1
+ handleSkewJoin: false
+ keys:
+ 0 [Column[key]]
+ 1 [Column[key]]
+ Position of Big Table: 0
+
+ Stage: Stage-3
+ Map Reduce
+ Alias -> Map Operator Tree:
+ a
+ TableScan
+ alias: a
+ GatherStats: false
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0
+ 1
+ handleSkewJoin: false
+ keys:
+ 0 [Column[key]]
+ 1 [Column[key]]
+ Position of Big Table: 0
+ Select Operator
+ Group By Operator
+ aggregations:
+ expr: count()
+ bucketGroup: false
+ mode: hash
+ outputColumnNames: _col0
+ Reduce Output Operator
+ sort order:
+ tag: -1
+ value expressions:
+ expr: _col0
+ type: bigint
+ Local Work:
+ Map Reduce Local Work
+ Needs Tagging: false
+ Path -> Alias:
+#### A masked pattern was here ####
+ Path -> Partition:
+#### A masked pattern was here ####
+ Partition
+ base file name: ds=2008-04-08
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ partition values:
+ ds 2008-04-08
+ properties:
+ bucket_count 2
+ bucket_field_name key
+ columns key,value
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.bucket_big
+ numFiles 2
+ numRows 0
+ partition_columns ds
+ rawDataSize 0
+ serialization.ddl struct bucket_big { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ totalSize 2750
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ properties:
+ SORTBUCKETCOLSPREFIX TRUE
+ bucket_count 2
+ bucket_field_name key
+ columns key,value
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.bucket_big
+ numFiles 4
+ numPartitions 2
+ numRows 0
+ partition_columns ds
+ rawDataSize 0
+ serialization.ddl struct bucket_big { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ totalSize 5500
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.bucket_big
+ name: default.bucket_big
+#### A masked pattern was here ####
+ Partition
+ base file name: ds=2008-04-09
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ partition values:
+ ds 2008-04-09
+ properties:
+ bucket_count 2
+ bucket_field_name key
+ columns key,value
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.bucket_big
+ numFiles 2
+ numRows 0
+ partition_columns ds
+ rawDataSize 0
+ serialization.ddl struct bucket_big { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ totalSize 2750
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ properties:
+ SORTBUCKETCOLSPREFIX TRUE
+ bucket_count 2
+ bucket_field_name key
+ columns key,value
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.bucket_big
+ numFiles 4
+ numPartitions 2
+ numRows 0
+ partition_columns ds
+ rawDataSize 0
+ serialization.ddl struct bucket_big { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ totalSize 5500
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.bucket_big
+ name: default.bucket_big
+#### A masked pattern was here ####
+ Partition
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ partition values:
+ ds 2008-04-08
+ properties:
+ bucket_count 4
+ bucket_field_name key
+ columns key,value
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.bucket_small
+ numFiles 4
+ numRows 0
+ partition_columns ds
+ rawDataSize 0
+ serialization.ddl struct bucket_small { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ totalSize 226
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ properties:
+ SORTBUCKETCOLSPREFIX TRUE
+ bucket_count 4
+ bucket_field_name key
+ columns key,value
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.bucket_small
+ numFiles 8
+ numPartitions 2
+ numRows 0
+ partition_columns ds
+ rawDataSize 0
+ serialization.ddl struct bucket_small { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ totalSize 452
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.bucket_small
+ name: default.bucket_small
+#### A masked pattern was here ####
+ Partition
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ partition values:
+ ds 2008-04-08
+ properties:
+ bucket_count 4
+ bucket_field_name key
+ columns key,value
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.bucket_small
+ numFiles 4
+ numRows 0
+ partition_columns ds
+ rawDataSize 0
+ serialization.ddl struct bucket_small { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ totalSize 226
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ properties:
+ SORTBUCKETCOLSPREFIX TRUE
+ bucket_count 4
+ bucket_field_name key
+ columns key,value
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.bucket_small
+ numFiles 8
+ numPartitions 2
+ numRows 0
+ partition_columns ds
+ rawDataSize 0
+ serialization.ddl struct bucket_small { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ totalSize 452
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.bucket_small
+ name: default.bucket_small
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations:
+ expr: count(VALUE._col0)
+ bucketGroup: false
+ mode: mergepartial
+ outputColumnNames: _col0
+ Select Operator
+ expressions:
+ expr: _col0
+ type: bigint
+ outputColumnNames: _col0
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+#### A masked pattern was here ####
+ NumFilesPerFileSink: 1
+#### A masked pattern was here ####
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ properties:
+ columns _col0
+ columns.types bigint
+ escape.delim \
+ serialization.format 1
+ TotalFiles: 1
+ GatherStats: false
+ MultiFileSpray: false
+ Truncated Path -> Alias:
+ /bucket_big/ds=2008-04-08 [a]
+ /bucket_big/ds=2008-04-09 [a]
+
+ Stage: Stage-7
+ Map Reduce Local Work
+ Alias -> Map Local Tables:
+ a
+ Fetch Operator
+ limit: -1
+ Alias -> Map Local Operator Tree:
+ a
+ TableScan
+ alias: a
+ GatherStats: false
+ HashTable Sink Operator
+ condition expressions:
+ 0
+ 1
+ handleSkewJoin: false
+ keys:
+ 0 [Column[key]]
+ 1 [Column[key]]
+ Position of Big Table: 1
+
+ Stage: Stage-4
+ Map Reduce
+ Alias -> Map Operator Tree:
+ b
+ TableScan
+ alias: b
+ GatherStats: false
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0
+ 1
+ handleSkewJoin: false
+ keys:
+ 0 [Column[key]]
+ 1 [Column[key]]
+ Position of Big Table: 1
+ Select Operator
+ Group By Operator
+ aggregations:
+ expr: count()
+ bucketGroup: false
+ mode: hash
+ outputColumnNames: _col0
+ Reduce Output Operator
+ sort order:
+ tag: -1
+ value expressions:
+ expr: _col0
+ type: bigint
+ Local Work:
+ Map Reduce Local Work
+ Needs Tagging: false
+ Path -> Alias:
+#### A masked pattern was here ####
+ Path -> Partition:
+#### A masked pattern was here ####
+ Partition
+ base file name: ds=2008-04-08
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ partition values:
+ ds 2008-04-08
+ properties:
+ bucket_count 2
+ bucket_field_name key
+ columns key,value
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.bucket_big
+ numFiles 2
+ numRows 0
+ partition_columns ds
+ rawDataSize 0
+ serialization.ddl struct bucket_big { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ totalSize 2750
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ properties:
+ SORTBUCKETCOLSPREFIX TRUE
+ bucket_count 2
+ bucket_field_name key
+ columns key,value
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.bucket_big
+ numFiles 4
+ numPartitions 2
+ numRows 0
+ partition_columns ds
+ rawDataSize 0
+ serialization.ddl struct bucket_big { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ totalSize 5500
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.bucket_big
+ name: default.bucket_big
+#### A masked pattern was here ####
+ Partition
+ base file name: ds=2008-04-09
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ partition values:
+ ds 2008-04-09
+ properties:
+ bucket_count 2
+ bucket_field_name key
+ columns key,value
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.bucket_big
+ numFiles 2
+ numRows 0
+ partition_columns ds
+ rawDataSize 0
+ serialization.ddl struct bucket_big { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ totalSize 2750
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ properties:
+ SORTBUCKETCOLSPREFIX TRUE
+ bucket_count 2
+ bucket_field_name key
+ columns key,value
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.bucket_big
+ numFiles 4
+ numPartitions 2
+ numRows 0
+ partition_columns ds
+ rawDataSize 0
+ serialization.ddl struct bucket_big { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ totalSize 5500
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.bucket_big
+ name: default.bucket_big
+#### A masked pattern was here ####
+ Partition
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ partition values:
+ ds 2008-04-08
+ properties:
+ bucket_count 4
+ bucket_field_name key
+ columns key,value
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.bucket_small
+ numFiles 4
+ numRows 0
+ partition_columns ds
+ rawDataSize 0
+ serialization.ddl struct bucket_small { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ totalSize 226
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ properties:
+ SORTBUCKETCOLSPREFIX TRUE
+ bucket_count 4
+ bucket_field_name key
+ columns key,value
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.bucket_small
+ numFiles 8
+ numPartitions 2
+ numRows 0
+ partition_columns ds
+ rawDataSize 0
+ serialization.ddl struct bucket_small { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ totalSize 452
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.bucket_small
+ name: default.bucket_small
+#### A masked pattern was here ####
+ Partition
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ partition values:
+ ds 2008-04-08
+ properties:
+ bucket_count 4
+ bucket_field_name key
+ columns key,value
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.bucket_small
+ numFiles 4
+ numRows 0
+ partition_columns ds
+ rawDataSize 0
+ serialization.ddl struct bucket_small { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ totalSize 226
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ properties:
+ SORTBUCKETCOLSPREFIX TRUE
+ bucket_count 4
+ bucket_field_name key
+ columns key,value
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.bucket_small
+ numFiles 8
+ numPartitions 2
+ numRows 0
+ partition_columns ds
+ rawDataSize 0
+ serialization.ddl struct bucket_small { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ totalSize 452
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.bucket_small
+ name: default.bucket_small
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations:
+ expr: count(VALUE._col0)
+ bucketGroup: false
+ mode: mergepartial
+ outputColumnNames: _col0
+ Select Operator
+ expressions:
+ expr: _col0
+ type: bigint
+ outputColumnNames: _col0
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+#### A masked pattern was here ####
+ NumFilesPerFileSink: 1
+#### A masked pattern was here ####
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ properties:
+ columns _col0
+ columns.types bigint
+ escape.delim \
+ serialization.format 1
+ TotalFiles: 1
+ GatherStats: false
+ MultiFileSpray: false
+ Truncated Path -> Alias:
+ /bucket_small/ds=2008-04-08 [b]
+ /bucket_small/ds=2008-04-09 [b]
+
+ Stage: Stage-1
+ Map Reduce
+ Alias -> Map Operator Tree:
+ a
+ TableScan
+ alias: a
+ GatherStats: false
+ Sorted Merge Bucket Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0
+ 1
+ handleSkewJoin: false
+ keys:
+ 0 [Column[key]]
+ 1 [Column[key]]
+ Position of Big Table: 0
+ Select Operator
+ Group By Operator
+ aggregations:
+ expr: count()
+ bucketGroup: false
+ mode: hash
+ outputColumnNames: _col0
+ Reduce Output Operator
+ sort order:
+ tag: -1
+ value expressions:
+ expr: _col0
+ type: bigint
+ Needs Tagging: false
+ Path -> Alias:
+#### A masked pattern was here ####
+ Path -> Partition:
+#### A masked pattern was here ####
+ Partition
+ base file name: ds=2008-04-08
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ partition values:
+ ds 2008-04-08
+ properties:
+ bucket_count 2
+ bucket_field_name key
+ columns key,value
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.bucket_big
+ numFiles 2
+ numRows 0
+ partition_columns ds
+ rawDataSize 0
+ serialization.ddl struct bucket_big { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ totalSize 2750
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ properties:
+ SORTBUCKETCOLSPREFIX TRUE
+ bucket_count 2
+ bucket_field_name key
+ columns key,value
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.bucket_big
+ numFiles 4
+ numPartitions 2
+ numRows 0
+ partition_columns ds
+ rawDataSize 0
+ serialization.ddl struct bucket_big { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ totalSize 5500
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.bucket_big
+ name: default.bucket_big
+#### A masked pattern was here ####
+ Partition
+ base file name: ds=2008-04-09
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ partition values:
+ ds 2008-04-09
+ properties:
+ bucket_count 2
+ bucket_field_name key
+ columns key,value
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.bucket_big
+ numFiles 2
+ numRows 0
+ partition_columns ds
+ rawDataSize 0
+ serialization.ddl struct bucket_big { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ totalSize 2750
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ properties:
+ SORTBUCKETCOLSPREFIX TRUE
+ bucket_count 2
+ bucket_field_name key
+ columns key,value
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.bucket_big
+ numFiles 4
+ numPartitions 2
+ numRows 0
+ partition_columns ds
+ rawDataSize 0
+ serialization.ddl struct bucket_big { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ totalSize 5500
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.bucket_big
+ name: default.bucket_big
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations:
+ expr: count(VALUE._col0)
+ bucketGroup: false
+ mode: mergepartial
+ outputColumnNames: _col0
+ Select Operator
+ expressions:
+ expr: _col0
+ type: bigint
+ outputColumnNames: _col0
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+#### A masked pattern was here ####
+ NumFilesPerFileSink: 1
+#### A masked pattern was here ####
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ properties:
+ columns _col0
+ columns.types bigint
+ escape.delim \
+ serialization.format 1
+ TotalFiles: 1
+ GatherStats: false
+ MultiFileSpray: false
+ Truncated Path -> Alias:
+ /bucket_big/ds=2008-04-08 [a]
+ /bucket_big/ds=2008-04-09 [a]
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+
+
+PREHOOK: query: select count(*) FROM bucket_big a JOIN bucket_small b ON a.key = b.key
+PREHOOK: type: QUERY
+PREHOOK: Input: default@bucket_big
+PREHOOK: Input: default@bucket_big@ds=2008-04-08
+PREHOOK: Input: default@bucket_big@ds=2008-04-09
+PREHOOK: Input: default@bucket_small
+PREHOOK: Input: default@bucket_small@ds=2008-04-08
+PREHOOK: Input: default@bucket_small@ds=2008-04-09
+#### A masked pattern was here ####
+POSTHOOK: query: select count(*) FROM bucket_big a JOIN bucket_small b ON a.key = b.key
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@bucket_big
+POSTHOOK: Input: default@bucket_big@ds=2008-04-08
+POSTHOOK: Input: default@bucket_big@ds=2008-04-09
+POSTHOOK: Input: default@bucket_small
+POSTHOOK: Input: default@bucket_small@ds=2008-04-08
+POSTHOOK: Input: default@bucket_small@ds=2008-04-09
+#### A masked pattern was here ####
+76