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 2013/04/24 03:33:07 UTC
svn commit: r1471224 [7/8] - 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/optimizer/physical/ ql/sr...
Modified: hive/trunk/ql/src/test/results/clientpositive/auto_sortmerge_join_9.q.out
URL: http://svn.apache.org/viewvc/hive/trunk/ql/src/test/results/clientpositive/auto_sortmerge_join_9.q.out?rev=1471224&r1=1471223&r2=1471224&view=diff
==============================================================================
--- hive/trunk/ql/src/test/results/clientpositive/auto_sortmerge_join_9.q.out (original)
+++ hive/trunk/ql/src/test/results/clientpositive/auto_sortmerge_join_9.q.out Wed Apr 24 01:33:05 2013
@@ -2067,3 +2067,4410 @@ POSTHOOK: Lineage: tbl1.value SIMPLE [(s
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), ]
20
+PREHOOK: query: -- The join is being performed as part of sub-query. It should be converted to a sort-merge join
+explain
+select count(*) from (
+ select a.key as key, a.value as val1, b.value as val2 from tbl1 a join tbl2 b on a.key = b.key
+) subq1
+PREHOOK: type: QUERY
+POSTHOOK: query: -- The join is being performed as part of sub-query. It should be converted to a sort-merge join
+explain
+select count(*) from (
+ select a.key as key, a.value as val1, b.value as val2 from tbl1 a join tbl2 b on a.key = b.key
+) subq1
+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), ]
+ABSTRACT SYNTAX TREE:
+ (TOK_QUERY (TOK_FROM (TOK_SUBQUERY (TOK_QUERY (TOK_FROM (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_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (. (TOK_TABLE_OR_COL a) key) key) (TOK_SELEXPR (. (TOK_TABLE_OR_COL a) value) val1) (TOK_SELEXPR (. (TOK_TABLE_OR_COL b) value) val2)))) subq1)) (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:
+ subq1:b
+ Fetch Operator
+ limit: -1
+ Alias -> Map Local Operator Tree:
+ subq1:b
+ TableScan
+ alias: b
+ 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:
+ subq1:a
+ TableScan
+ alias: a
+ 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
+ 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-7
+ Map Reduce Local Work
+ Alias -> Map Local Tables:
+ subq1:a
+ Fetch Operator
+ limit: -1
+ Alias -> Map Local Operator Tree:
+ subq1:a
+ TableScan
+ alias: a
+ 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:
+ subq1:b
+ TableScan
+ alias: b
+ 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
+ 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:
+ subq1:a
+ TableScan
+ alias: a
+ 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
+ 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 (
+ select a.key as key, a.value as val1, b.value as val2 from tbl1 a join tbl2 b on a.key = b.key
+) subq1
+PREHOOK: type: QUERY
+PREHOOK: Input: default@tbl1
+PREHOOK: Input: default@tbl2
+#### A masked pattern was here ####
+POSTHOOK: query: select count(*) from (
+ select a.key as key, a.value as val1, b.value as val2 from tbl1 a join tbl2 b on a.key = b.key
+) subq1
+POSTHOOK: type: QUERY
+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), ]
+22
+PREHOOK: query: -- The join is being performed as part of sub-query. It should be converted to a sort-merge join
+-- Add a order by at the end to make the results deterministic.
+explain
+select key, count(*) from
+(
+ select a.key as key, a.value as val1, b.value as val2 from tbl1 a join tbl2 b on a.key = b.key
+) subq1
+group by key
+order by key
+PREHOOK: type: QUERY
+POSTHOOK: query: -- The join is being performed as part of sub-query. It should be converted to a sort-merge join
+-- Add a order by at the end to make the results deterministic.
+explain
+select key, count(*) from
+(
+ select a.key as key, a.value as val1, b.value as val2 from tbl1 a join tbl2 b on a.key = b.key
+) subq1
+group by key
+order by 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), ]
+ABSTRACT SYNTAX TREE:
+ (TOK_QUERY (TOK_FROM (TOK_SUBQUERY (TOK_QUERY (TOK_FROM (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_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (. (TOK_TABLE_OR_COL a) key) key) (TOK_SELEXPR (. (TOK_TABLE_OR_COL a) value) val1) (TOK_SELEXPR (. (TOK_TABLE_OR_COL b) value) val2)))) subq1)) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_TABLE_OR_COL key)) (TOK_SELEXPR (TOK_FUNCTIONSTAR count))) (TOK_GROUPBY (TOK_TABLE_OR_COL key)) (TOK_ORDERBY (TOK_TABSORTCOLNAMEASC (TOK_TABLE_OR_COL key)))))
+
+STAGE DEPENDENCIES:
+ Stage-6 is a root stage , consists of Stage-7, Stage-8, Stage-1
+ Stage-7 has a backup stage: Stage-1
+ Stage-4 depends on stages: Stage-7
+ Stage-2 depends on stages: Stage-1, Stage-4, Stage-5
+ Stage-8 has a backup stage: Stage-1
+ Stage-5 depends on stages: Stage-8
+ Stage-1
+ Stage-0 is a root stage
+
+STAGE PLANS:
+ Stage: Stage-6
+ Conditional Operator
+
+ Stage: Stage-7
+ Map Reduce Local Work
+ Alias -> Map Local Tables:
+ subq1:b
+ Fetch Operator
+ limit: -1
+ Alias -> Map Local Operator Tree:
+ subq1:b
+ TableScan
+ alias: b
+ HashTable Sink Operator
+ condition expressions:
+ 0 {key}
+ 1
+ handleSkewJoin: false
+ keys:
+ 0 [Column[key]]
+ 1 [Column[key]]
+ Position of Big Table: 0
+
+ Stage: Stage-4
+ Map Reduce
+ Alias -> Map Operator Tree:
+ subq1:a
+ TableScan
+ alias: a
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0 {key}
+ 1
+ handleSkewJoin: false
+ keys:
+ 0 [Column[key]]
+ 1 [Column[key]]
+ outputColumnNames: _col0
+ Position of Big Table: 0
+ Select Operator
+ expressions:
+ expr: _col0
+ type: int
+ outputColumnNames: _col0
+ Group By Operator
+ aggregations:
+ expr: count()
+ bucketGroup: false
+ keys:
+ expr: _col0
+ type: int
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Reduce Output Operator
+ key expressions:
+ expr: _col0
+ type: int
+ sort order: +
+ Map-reduce partition columns:
+ expr: _col0
+ type: int
+ tag: -1
+ value expressions:
+ expr: _col1
+ type: bigint
+ Local Work:
+ Map Reduce Local Work
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations:
+ expr: count(VALUE._col0)
+ bucketGroup: false
+ keys:
+ expr: KEY._col0
+ type: int
+ mode: mergepartial
+ outputColumnNames: _col0, _col1
+ Select Operator
+ expressions:
+ expr: _col0
+ type: int
+ expr: _col1
+ type: bigint
+ outputColumnNames: _col0, _col1
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+
+ Stage: Stage-2
+ Map Reduce
+ Alias -> Map Operator Tree:
+#### A masked pattern was here ####
+ Reduce Output Operator
+ key expressions:
+ expr: _col0
+ type: int
+ sort order: +
+ tag: -1
+ value expressions:
+ expr: _col0
+ type: int
+ expr: _col1
+ type: bigint
+ Reduce Operator Tree:
+ Extract
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+
+ Stage: Stage-8
+ Map Reduce Local Work
+ Alias -> Map Local Tables:
+ subq1:a
+ Fetch Operator
+ limit: -1
+ Alias -> Map Local Operator Tree:
+ subq1:a
+ TableScan
+ alias: a
+ HashTable Sink Operator
+ condition expressions:
+ 0 {key}
+ 1
+ handleSkewJoin: false
+ keys:
+ 0 [Column[key]]
+ 1 [Column[key]]
+ Position of Big Table: 1
+
+ Stage: Stage-5
+ Map Reduce
+ Alias -> Map Operator Tree:
+ subq1:b
+ TableScan
+ alias: b
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0 {key}
+ 1
+ handleSkewJoin: false
+ keys:
+ 0 [Column[key]]
+ 1 [Column[key]]
+ outputColumnNames: _col0
+ Position of Big Table: 1
+ Select Operator
+ expressions:
+ expr: _col0
+ type: int
+ outputColumnNames: _col0
+ Group By Operator
+ aggregations:
+ expr: count()
+ bucketGroup: false
+ keys:
+ expr: _col0
+ type: int
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Reduce Output Operator
+ key expressions:
+ expr: _col0
+ type: int
+ sort order: +
+ Map-reduce partition columns:
+ expr: _col0
+ type: int
+ tag: -1
+ value expressions:
+ expr: _col1
+ type: bigint
+ Local Work:
+ Map Reduce Local Work
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations:
+ expr: count(VALUE._col0)
+ bucketGroup: false
+ keys:
+ expr: KEY._col0
+ type: int
+ mode: mergepartial
+ outputColumnNames: _col0, _col1
+ Select Operator
+ expressions:
+ expr: _col0
+ type: int
+ expr: _col1
+ type: bigint
+ outputColumnNames: _col0, _col1
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+
+ Stage: Stage-1
+ Map Reduce
+ Alias -> Map Operator Tree:
+ subq1:a
+ TableScan
+ alias: a
+ Sorted Merge Bucket Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0 {key}
+ 1
+ handleSkewJoin: false
+ keys:
+ 0 [Column[key]]
+ 1 [Column[key]]
+ outputColumnNames: _col0
+ Position of Big Table: 0
+ Select Operator
+ expressions:
+ expr: _col0
+ type: int
+ outputColumnNames: _col0
+ Group By Operator
+ aggregations:
+ expr: count()
+ bucketGroup: false
+ keys:
+ expr: _col0
+ type: int
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Reduce Output Operator
+ key expressions:
+ expr: _col0
+ type: int
+ sort order: +
+ Map-reduce partition columns:
+ expr: _col0
+ type: int
+ 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: int
+ mode: mergepartial
+ outputColumnNames: _col0, _col1
+ Select Operator
+ expressions:
+ expr: _col0
+ type: int
+ expr: _col1
+ type: bigint
+ outputColumnNames: _col0, _col1
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+
+
+PREHOOK: query: select key, count(*) from
+(
+ select a.key as key, a.value as val1, b.value as val2 from tbl1 a join tbl2 b on a.key = b.key
+) subq1
+group by key
+order by key
+PREHOOK: type: QUERY
+PREHOOK: Input: default@tbl1
+PREHOOK: Input: default@tbl2
+#### A masked pattern was here ####
+POSTHOOK: query: select key, count(*) from
+(
+ select a.key as key, a.value as val1, b.value as val2 from tbl1 a join tbl2 b on a.key = b.key
+) subq1
+group by key
+order by key
+POSTHOOK: type: QUERY
+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), ]
+0 9
+2 1
+4 1
+5 9
+8 1
+9 1
+PREHOOK: query: -- The join is being performed as part of more than one sub-query. It should be converted to a sort-merge join
+explain
+select count(*) from
+(
+ select key, count(*) from
+ (
+ select a.key as key, a.value as val1, b.value as val2 from tbl1 a join tbl2 b on a.key = b.key
+ ) subq1
+ group by key
+) subq2
+PREHOOK: type: QUERY
+POSTHOOK: query: -- The join is being performed as part of more than one sub-query. It should be converted to a sort-merge join
+explain
+select count(*) from
+(
+ select key, count(*) from
+ (
+ select a.key as key, a.value as val1, b.value as val2 from tbl1 a join tbl2 b on a.key = b.key
+ ) subq1
+ group by key
+) subq2
+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), ]
+ABSTRACT SYNTAX TREE:
+ (TOK_QUERY (TOK_FROM (TOK_SUBQUERY (TOK_QUERY (TOK_FROM (TOK_SUBQUERY (TOK_QUERY (TOK_FROM (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_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (. (TOK_TABLE_OR_COL a) key) key) (TOK_SELEXPR (. (TOK_TABLE_OR_COL a) value) val1) (TOK_SELEXPR (. (TOK_TABLE_OR_COL b) value) val2)))) subq1)) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_TABLE_OR_COL key)) (TOK_SELEXPR (TOK_FUNCTIONSTAR count))) (TOK_GROUPBY (TOK_TABLE_OR_COL key)))) subq2)) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_FUNCTIONSTAR count)))))
+
+STAGE DEPENDENCIES:
+ Stage-6 is a root stage , consists of Stage-7, Stage-8, Stage-1
+ Stage-7 has a backup stage: Stage-1
+ Stage-4 depends on stages: Stage-7
+ Stage-2 depends on stages: Stage-1, Stage-4, Stage-5
+ Stage-8 has a backup stage: Stage-1
+ Stage-5 depends on stages: Stage-8
+ Stage-1
+ Stage-0 is a root stage
+
+STAGE PLANS:
+ Stage: Stage-6
+ Conditional Operator
+
+ Stage: Stage-7
+ Map Reduce Local Work
+ Alias -> Map Local Tables:
+ subq2:subq1:b
+ Fetch Operator
+ limit: -1
+ Alias -> Map Local Operator Tree:
+ subq2:subq1:b
+ TableScan
+ alias: b
+ HashTable Sink Operator
+ condition expressions:
+ 0 {key}
+ 1
+ handleSkewJoin: false
+ keys:
+ 0 [Column[key]]
+ 1 [Column[key]]
+ Position of Big Table: 0
+
+ Stage: Stage-4
+ Map Reduce
+ Alias -> Map Operator Tree:
+ subq2:subq1:a
+ TableScan
+ alias: a
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0 {key}
+ 1
+ handleSkewJoin: false
+ keys:
+ 0 [Column[key]]
+ 1 [Column[key]]
+ outputColumnNames: _col0
+ Position of Big Table: 0
+ Select Operator
+ expressions:
+ expr: _col0
+ type: int
+ outputColumnNames: _col0
+ Group By Operator
+ aggregations:
+ expr: count()
+ bucketGroup: false
+ keys:
+ expr: _col0
+ type: int
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Reduce Output Operator
+ key expressions:
+ expr: _col0
+ type: int
+ sort order: +
+ Map-reduce partition columns:
+ expr: _col0
+ type: int
+ tag: -1
+ value expressions:
+ expr: _col1
+ type: bigint
+ Local Work:
+ Map Reduce Local Work
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations:
+ expr: count(VALUE._col0)
+ bucketGroup: false
+ keys:
+ expr: KEY._col0
+ type: int
+ mode: mergepartial
+ outputColumnNames: _col0, _col1
+ 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-8
+ Map Reduce Local Work
+ Alias -> Map Local Tables:
+ subq2:subq1:a
+ Fetch Operator
+ limit: -1
+ Alias -> Map Local Operator Tree:
+ subq2:subq1:a
+ TableScan
+ alias: a
+ HashTable Sink Operator
+ condition expressions:
+ 0 {key}
+ 1
+ handleSkewJoin: false
+ keys:
+ 0 [Column[key]]
+ 1 [Column[key]]
+ Position of Big Table: 1
+
+ Stage: Stage-5
+ Map Reduce
+ Alias -> Map Operator Tree:
+ subq2:subq1:b
+ TableScan
+ alias: b
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0 {key}
+ 1
+ handleSkewJoin: false
+ keys:
+ 0 [Column[key]]
+ 1 [Column[key]]
+ outputColumnNames: _col0
+ Position of Big Table: 1
+ Select Operator
+ expressions:
+ expr: _col0
+ type: int
+ outputColumnNames: _col0
+ Group By Operator
+ aggregations:
+ expr: count()
+ bucketGroup: false
+ keys:
+ expr: _col0
+ type: int
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Reduce Output Operator
+ key expressions:
+ expr: _col0
+ type: int
+ sort order: +
+ Map-reduce partition columns:
+ expr: _col0
+ type: int
+ tag: -1
+ value expressions:
+ expr: _col1
+ type: bigint
+ Local Work:
+ Map Reduce Local Work
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations:
+ expr: count(VALUE._col0)
+ bucketGroup: false
+ keys:
+ expr: KEY._col0
+ type: int
+ mode: mergepartial
+ outputColumnNames: _col0, _col1
+ 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-1
+ Map Reduce
+ Alias -> Map Operator Tree:
+ subq2:subq1:a
+ TableScan
+ alias: a
+ Sorted Merge Bucket Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0 {key}
+ 1
+ handleSkewJoin: false
+ keys:
+ 0 [Column[key]]
+ 1 [Column[key]]
+ outputColumnNames: _col0
+ Position of Big Table: 0
+ Select Operator
+ expressions:
+ expr: _col0
+ type: int
+ outputColumnNames: _col0
+ Group By Operator
+ aggregations:
+ expr: count()
+ bucketGroup: false
+ keys:
+ expr: _col0
+ type: int
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Reduce Output Operator
+ key expressions:
+ expr: _col0
+ type: int
+ sort order: +
+ Map-reduce partition columns:
+ expr: _col0
+ type: int
+ 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: int
+ mode: mergepartial
+ outputColumnNames: _col0, _col1
+ 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
+(
+ select key, count(*) from
+ (
+ select a.key as key, a.value as val1, b.value as val2 from tbl1 a join tbl2 b on a.key = b.key
+ ) subq1
+ group by key
+) subq2
+PREHOOK: type: QUERY
+PREHOOK: Input: default@tbl1
+PREHOOK: Input: default@tbl2
+#### A masked pattern was here ####
+POSTHOOK: query: select count(*) from
+(
+ select key, count(*) from
+ (
+ select a.key as key, a.value as val1, b.value as val2 from tbl1 a join tbl2 b on a.key = b.key
+ ) subq1
+ group by key
+) subq2
+POSTHOOK: type: QUERY
+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), ]
+6
+PREHOOK: query: -- A join is being performed across different sub-queries, where a join is being performed in each of them.
+-- Each sub-query should be converted to a sort-merge join.
+explain
+select src1.key, src1.cnt1, src2.cnt1 from
+(
+ select key, count(*) as cnt1 from
+ (
+ select a.key as key, a.value as val1, b.value as val2 from tbl1 a join tbl2 b on a.key = b.key
+ ) subq1 group by key
+) src1
+join
+(
+ select key, count(*) as cnt1 from
+ (
+ select a.key as key, a.value as val1, b.value as val2 from tbl1 a join tbl2 b on a.key = b.key
+ ) subq2 group by key
+) src2
+on src1.key = src2.key
+order by src1.key, src1.cnt1, src2.cnt1
+PREHOOK: type: QUERY
+POSTHOOK: query: -- A join is being performed across different sub-queries, where a join is being performed in each of them.
+-- Each sub-query should be converted to a sort-merge join.
+explain
+select src1.key, src1.cnt1, src2.cnt1 from
+(
+ select key, count(*) as cnt1 from
+ (
+ select a.key as key, a.value as val1, b.value as val2 from tbl1 a join tbl2 b on a.key = b.key
+ ) subq1 group by key
+) src1
+join
+(
+ select key, count(*) as cnt1 from
+ (
+ select a.key as key, a.value as val1, b.value as val2 from tbl1 a join tbl2 b on a.key = b.key
+ ) subq2 group by key
+) src2
+on src1.key = src2.key
+order by src1.key, src1.cnt1, src2.cnt1
+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), ]
+ABSTRACT SYNTAX TREE:
+ (TOK_QUERY (TOK_FROM (TOK_JOIN (TOK_SUBQUERY (TOK_QUERY (TOK_FROM (TOK_SUBQUERY (TOK_QUERY (TOK_FROM (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_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (. (TOK_TABLE_OR_COL a) key) key) (TOK_SELEXPR (. (TOK_TABLE_OR_COL a) value) val1) (TOK_SELEXPR (. (TOK_TABLE_OR_COL b) value) val2)))) subq1)) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_TABLE_OR_COL key)) (TOK_SELEXPR (TOK_FUNCTIONSTAR count) cnt1)) (TOK_GROUPBY (TOK_TABLE_OR_COL key)))) src1) (TOK_SUBQUERY (TOK_QUERY (TOK_FROM (TOK_SUBQUERY (TOK_QUERY (TOK_FROM (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_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (. (TOK_TABLE_OR_COL a) key) key) (TOK_
SELEXPR (. (TOK_TABLE_OR_COL a) value) val1) (TOK_SELEXPR (. (TOK_TABLE_OR_COL b) value) val2)))) subq2)) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_TABLE_OR_COL key)) (TOK_SELEXPR (TOK_FUNCTIONSTAR count) cnt1)) (TOK_GROUPBY (TOK_TABLE_OR_COL key)))) src2) (= (. (TOK_TABLE_OR_COL src1) key) (. (TOK_TABLE_OR_COL src2) key)))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (. (TOK_TABLE_OR_COL src1) key)) (TOK_SELEXPR (. (TOK_TABLE_OR_COL src1) cnt1)) (TOK_SELEXPR (. (TOK_TABLE_OR_COL src2) cnt1))) (TOK_ORDERBY (TOK_TABSORTCOLNAMEASC (. (TOK_TABLE_OR_COL src1) key)) (TOK_TABSORTCOLNAMEASC (. (TOK_TABLE_OR_COL src1) cnt1)) (TOK_TABSORTCOLNAMEASC (. (TOK_TABLE_OR_COL src2) cnt1)))))
+
+STAGE DEPENDENCIES:
+ Stage-12 is a root stage , consists of Stage-18, Stage-19, Stage-1
+ Stage-18 has a backup stage: Stage-1
+ Stage-10 depends on stages: Stage-18
+ Stage-9 depends on stages: Stage-1, Stage-5, Stage-10, Stage-11, Stage-13, Stage-14 , consists of Stage-16, Stage-17, Stage-2
+ Stage-16 has a backup stage: Stage-2
+ Stage-7 depends on stages: Stage-16
+ Stage-3 depends on stages: Stage-2, Stage-7, Stage-8
+ Stage-17 has a backup stage: Stage-2
+ Stage-8 depends on stages: Stage-17
+ Stage-2
+ Stage-19 has a backup stage: Stage-1
+ Stage-11 depends on stages: Stage-19
+ Stage-1
+ Stage-15 is a root stage , consists of Stage-20, Stage-21, Stage-5
+ Stage-20 has a backup stage: Stage-5
+ Stage-13 depends on stages: Stage-20
+ Stage-21 has a backup stage: Stage-5
+ Stage-14 depends on stages: Stage-21
+ Stage-5
+ Stage-0 is a root stage
+
+STAGE PLANS:
+ Stage: Stage-12
+ Conditional Operator
+
+ Stage: Stage-18
+ Map Reduce Local Work
+ Alias -> Map Local Tables:
+ src1:subq1:b
+ Fetch Operator
+ limit: -1
+ Alias -> Map Local Operator Tree:
+ src1:subq1:b
+ TableScan
+ alias: b
+ HashTable Sink Operator
+ condition expressions:
+ 0 {key}
+ 1
+ handleSkewJoin: false
+ keys:
+ 0 [Column[key]]
+ 1 [Column[key]]
+ Position of Big Table: 0
+
+ Stage: Stage-10
+ Map Reduce
+ Alias -> Map Operator Tree:
+ src1:subq1:a
+ TableScan
+ alias: a
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0 {key}
+ 1
+ handleSkewJoin: false
+ keys:
+ 0 [Column[key]]
+ 1 [Column[key]]
+ outputColumnNames: _col0
+ Position of Big Table: 0
+ Select Operator
+ expressions:
+ expr: _col0
+ type: int
+ outputColumnNames: _col0
+ Group By Operator
+ aggregations:
+ expr: count()
+ bucketGroup: false
+ keys:
+ expr: _col0
+ type: int
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Reduce Output Operator
+ key expressions:
+ expr: _col0
+ type: int
+ sort order: +
+ Map-reduce partition columns:
+ expr: _col0
+ type: int
+ tag: -1
+ value expressions:
+ expr: _col1
+ type: bigint
+ Local Work:
+ Map Reduce Local Work
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations:
+ expr: count(VALUE._col0)
+ bucketGroup: false
+ keys:
+ expr: KEY._col0
+ type: int
+ mode: mergepartial
+ outputColumnNames: _col0, _col1
+ Select Operator
+ expressions:
+ expr: _col0
+ type: int
+ expr: _col1
+ type: bigint
+ outputColumnNames: _col0, _col1
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+
+ Stage: Stage-9
+ Conditional Operator
+
+ Stage: Stage-16
+ Map Reduce Local Work
+ Alias -> Map Local Tables:
+ $INTNAME1
+ Fetch Operator
+ limit: -1
+ Alias -> Map Local Operator Tree:
+ $INTNAME1
+ HashTable Sink Operator
+ condition expressions:
+ 0 {_col0} {_col1}
+ 1 {_col1}
+ handleSkewJoin: false
+ keys:
+ 0 [Column[_col0]]
+ 1 [Column[_col0]]
+ Position of Big Table: 0
+
+ Stage: Stage-7
+ Map Reduce
+ Alias -> Map Operator Tree:
+ $INTNAME
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0 {_col0} {_col1}
+ 1 {_col1}
+ handleSkewJoin: false
+ keys:
+ 0 [Column[_col0]]
+ 1 [Column[_col0]]
+ outputColumnNames: _col0, _col1, _col3
+ Position of Big Table: 0
+ Select Operator
+ expressions:
+ expr: _col0
+ type: int
+ expr: _col1
+ type: bigint
+ expr: _col3
+ type: bigint
+ outputColumnNames: _col0, _col1, _col2
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ Local Work:
+ Map Reduce Local Work
+
+ Stage: Stage-3
+ Map Reduce
+ Alias -> Map Operator Tree:
+#### A masked pattern was here ####
+ Reduce Output Operator
+ key expressions:
+ expr: _col0
+ type: int
+ expr: _col1
+ type: bigint
+ expr: _col2
+ type: bigint
+ sort order: +++
+ tag: -1
+ value expressions:
+ expr: _col0
+ type: int
+ expr: _col1
+ type: bigint
+ expr: _col2
+ type: bigint
+ Reduce Operator Tree:
+ Extract
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+
+ Stage: Stage-17
+ Map Reduce Local Work
+ Alias -> Map Local Tables:
+ $INTNAME
+ Fetch Operator
+ limit: -1
+ Alias -> Map Local Operator Tree:
+ $INTNAME
+ HashTable Sink Operator
+ condition expressions:
+ 0 {_col0} {_col1}
+ 1 {_col1}
+ handleSkewJoin: false
+ keys:
+ 0 [Column[_col0]]
+ 1 [Column[_col0]]
+ Position of Big Table: 1
+
+ Stage: Stage-8
+ Map Reduce
+ Alias -> Map Operator Tree:
+ $INTNAME1
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0 {_col0} {_col1}
+ 1 {_col1}
+ handleSkewJoin: false
+ keys:
+ 0 [Column[_col0]]
+ 1 [Column[_col0]]
+ outputColumnNames: _col0, _col1, _col3
+ Position of Big Table: 1
+ Select Operator
+ expressions:
+ expr: _col0
+ type: int
+ expr: _col1
+ type: bigint
+ expr: _col3
+ type: bigint
+ outputColumnNames: _col0, _col1, _col2
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ Local Work:
+ Map Reduce Local Work
+
+ Stage: Stage-2
+ Map Reduce
+ Alias -> Map Operator Tree:
+ $INTNAME
+ Reduce Output Operator
+ key expressions:
+ expr: _col0
+ type: int
+ sort order: +
+ Map-reduce partition columns:
+ expr: _col0
+ type: int
+ tag: 0
+ value expressions:
+ expr: _col0
+ type: int
+ expr: _col1
+ type: bigint
+ $INTNAME1
+ Reduce Output Operator
+ key expressions:
+ expr: _col0
+ type: int
+ sort order: +
+ Map-reduce partition columns:
+ expr: _col0
+ type: int
+ tag: 1
+ value expressions:
+ expr: _col1
+ type: bigint
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0 {VALUE._col0} {VALUE._col1}
+ 1 {VALUE._col1}
+ handleSkewJoin: false
+ outputColumnNames: _col0, _col1, _col3
+ Select Operator
+ expressions:
+ expr: _col0
+ type: int
+ expr: _col1
+ type: bigint
+ expr: _col3
+ type: bigint
+ outputColumnNames: _col0, _col1, _col2
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+
+ Stage: Stage-19
+ Map Reduce Local Work
+ Alias -> Map Local Tables:
+ src1:subq1:a
+ Fetch Operator
+ limit: -1
+ Alias -> Map Local Operator Tree:
+ src1:subq1:a
+ TableScan
+ alias: a
+ HashTable Sink Operator
+ condition expressions:
+ 0 {key}
+ 1
+ handleSkewJoin: false
+ keys:
+ 0 [Column[key]]
+ 1 [Column[key]]
+ Position of Big Table: 1
+
+ Stage: Stage-11
+ Map Reduce
+ Alias -> Map Operator Tree:
+ src1:subq1:b
+ TableScan
+ alias: b
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0 {key}
+ 1
+ handleSkewJoin: false
+ keys:
+ 0 [Column[key]]
+ 1 [Column[key]]
+ outputColumnNames: _col0
+ Position of Big Table: 1
+ Select Operator
+ expressions:
+ expr: _col0
+ type: int
+ outputColumnNames: _col0
+ Group By Operator
+ aggregations:
+ expr: count()
+ bucketGroup: false
+ keys:
+ expr: _col0
+ type: int
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Reduce Output Operator
+ key expressions:
+ expr: _col0
+ type: int
+ sort order: +
+ Map-reduce partition columns:
+ expr: _col0
+ type: int
+ tag: -1
+ value expressions:
+ expr: _col1
+ type: bigint
+ Local Work:
+ Map Reduce Local Work
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations:
+ expr: count(VALUE._col0)
+ bucketGroup: false
+ keys:
+ expr: KEY._col0
+ type: int
+ mode: mergepartial
+ outputColumnNames: _col0, _col1
+ Select Operator
+ expressions:
+ expr: _col0
+ type: int
+ expr: _col1
+ type: bigint
+ outputColumnNames: _col0, _col1
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+
+ Stage: Stage-1
+ Map Reduce
+ Alias -> Map Operator Tree:
+ src1:subq1:a
+ TableScan
+ alias: a
+ Sorted Merge Bucket Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0 {key}
+ 1
+ handleSkewJoin: false
+ keys:
+ 0 [Column[key]]
+ 1 [Column[key]]
+ outputColumnNames: _col0
+ Position of Big Table: 0
+ Select Operator
+ expressions:
+ expr: _col0
+ type: int
+ outputColumnNames: _col0
+ Group By Operator
+ aggregations:
+ expr: count()
+ bucketGroup: false
+ keys:
+ expr: _col0
+ type: int
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Reduce Output Operator
+ key expressions:
+ expr: _col0
+ type: int
+ sort order: +
+ Map-reduce partition columns:
+ expr: _col0
+ type: int
+ 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: int
+ mode: mergepartial
+ outputColumnNames: _col0, _col1
+ Select Operator
+ expressions:
+ expr: _col0
+ type: int
+ expr: _col1
+ type: bigint
+ outputColumnNames: _col0, _col1
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+
+ Stage: Stage-15
+ Conditional Operator
+
+ Stage: Stage-20
+ Map Reduce Local Work
+ Alias -> Map Local Tables:
+ src2:subq2:b
+ Fetch Operator
+ limit: -1
+ Alias -> Map Local Operator Tree:
+ src2:subq2:b
+ TableScan
+ alias: b
+ HashTable Sink Operator
+ condition expressions:
+ 0 {key}
+ 1
+ handleSkewJoin: false
+ keys:
+ 0 [Column[key]]
+ 1 [Column[key]]
+ Position of Big Table: 0
+
+ Stage: Stage-13
+ Map Reduce
+ Alias -> Map Operator Tree:
+ src2:subq2:a
+ TableScan
+ alias: a
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0 {key}
+ 1
+ handleSkewJoin: false
+ keys:
+ 0 [Column[key]]
+ 1 [Column[key]]
+ outputColumnNames: _col0
+ Position of Big Table: 0
+ Select Operator
+ expressions:
+ expr: _col0
+ type: int
+ outputColumnNames: _col0
+ Group By Operator
+ aggregations:
+ expr: count()
+ bucketGroup: false
+ keys:
+ expr: _col0
+ type: int
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Reduce Output Operator
+ key expressions:
+ expr: _col0
+ type: int
+ sort order: +
+ Map-reduce partition columns:
+ expr: _col0
+ type: int
+ tag: -1
+ value expressions:
+ expr: _col1
+ type: bigint
+ Local Work:
+ Map Reduce Local Work
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations:
+ expr: count(VALUE._col0)
+ bucketGroup: false
+ keys:
+ expr: KEY._col0
+ type: int
+ mode: mergepartial
+ outputColumnNames: _col0, _col1
+ Select Operator
+ expressions:
+ expr: _col0
+ type: int
+ expr: _col1
+ type: bigint
+ outputColumnNames: _col0, _col1
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+
+ Stage: Stage-21
+ Map Reduce Local Work
+ Alias -> Map Local Tables:
+ src2:subq2:a
+ Fetch Operator
+ limit: -1
+ Alias -> Map Local Operator Tree:
+ src2:subq2:a
+ TableScan
+ alias: a
+ HashTable Sink Operator
+ condition expressions:
+ 0 {key}
+ 1
+ handleSkewJoin: false
+ keys:
+ 0 [Column[key]]
+ 1 [Column[key]]
+ Position of Big Table: 1
+
+ Stage: Stage-14
+ Map Reduce
+ Alias -> Map Operator Tree:
+ src2:subq2:b
+ TableScan
+ alias: b
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0 {key}
+ 1
+ handleSkewJoin: false
+ keys:
+ 0 [Column[key]]
+ 1 [Column[key]]
+ outputColumnNames: _col0
+ Position of Big Table: 1
+ Select Operator
+ expressions:
+ expr: _col0
+ type: int
+ outputColumnNames: _col0
+ Group By Operator
+ aggregations:
+ expr: count()
+ bucketGroup: false
+ keys:
+ expr: _col0
+ type: int
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Reduce Output Operator
+ key expressions:
+ expr: _col0
+ type: int
+ sort order: +
+ Map-reduce partition columns:
+ expr: _col0
+ type: int
+ tag: -1
+ value expressions:
+ expr: _col1
+ type: bigint
+ Local Work:
+ Map Reduce Local Work
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations:
+ expr: count(VALUE._col0)
+ bucketGroup: false
+ keys:
+ expr: KEY._col0
+ type: int
+ mode: mergepartial
+ outputColumnNames: _col0, _col1
+ Select Operator
+ expressions:
+ expr: _col0
+ type: int
+ expr: _col1
+ type: bigint
+ outputColumnNames: _col0, _col1
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+
+ Stage: Stage-5
+ Map Reduce
+ Alias -> Map Operator Tree:
+ src2:subq2:a
+ TableScan
+ alias: a
+ Sorted Merge Bucket Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0 {key}
+ 1
+ handleSkewJoin: false
+ keys:
+ 0 [Column[key]]
+ 1 [Column[key]]
+ outputColumnNames: _col0
+ Position of Big Table: 0
+ Select Operator
+ expressions:
+ expr: _col0
+ type: int
+ outputColumnNames: _col0
+ Group By Operator
+ aggregations:
+ expr: count()
+ bucketGroup: false
+ keys:
+ expr: _col0
+ type: int
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Reduce Output Operator
+ key expressions:
+ expr: _col0
+ type: int
+ sort order: +
+ Map-reduce partition columns:
+ expr: _col0
+ type: int
+ 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: int
+ mode: mergepartial
+ outputColumnNames: _col0, _col1
+ Select Operator
+ expressions:
+ expr: _col0
+ type: int
+ expr: _col1
+ type: bigint
+ outputColumnNames: _col0, _col1
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+
+
+PREHOOK: query: select src1.key, src1.cnt1, src2.cnt1 from
+(
+ select key, count(*) as cnt1 from
+ (
+ select a.key as key, a.value as val1, b.value as val2 from tbl1 a join tbl2 b on a.key = b.key
+ ) subq1 group by key
+) src1
+join
+(
+ select key, count(*) as cnt1 from
+ (
+ select a.key as key, a.value as val1, b.value as val2 from tbl1 a join tbl2 b on a.key = b.key
+ ) subq2 group by key
+) src2
+on src1.key = src2.key
+order by src1.key, src1.cnt1, src2.cnt1
+PREHOOK: type: QUERY
+PREHOOK: Input: default@tbl1
+PREHOOK: Input: default@tbl2
+#### A masked pattern was here ####
+POSTHOOK: query: select src1.key, src1.cnt1, src2.cnt1 from
+(
+ select key, count(*) as cnt1 from
+ (
+ select a.key as key, a.value as val1, b.value as val2 from tbl1 a join tbl2 b on a.key = b.key
+ ) subq1 group by key
+) src1
+join
+(
+ select key, count(*) as cnt1 from
+ (
+ select a.key as key, a.value as val1, b.value as val2 from tbl1 a join tbl2 b on a.key = b.key
+ ) subq2 group by key
+) src2
+on src1.key = src2.key
+order by src1.key, src1.cnt1, src2.cnt1
+POSTHOOK: type: QUERY
+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), ]
+0 9 9
+2 1 1
+4 1 1
+5 9 9
+8 1 1
+9 1 1
+PREHOOK: query: -- The subquery itself is being joined. Since the sub-query only contains selects and filters, it should
+-- be converted to a sort-merge join.
+explain
+select count(*) from
+ (select a.key as key, a.value as value from tbl1 a where key < 6) subq1
+ join
+ (select a.key as key, a.value as value from tbl2 a where key < 6) subq2
+ on subq1.key = subq2.key
+PREHOOK: type: QUERY
+POSTHOOK: query: -- The subquery itself is being joined. Since the sub-query only contains selects and filters, it should
+-- be converted to a sort-merge join.
+explain
+select count(*) from
+ (select a.key as key, a.value as value from tbl1 a where key < 6) subq1
+ join
+ (select a.key as key, a.value as value from tbl2 a where key < 6) subq2
+ on subq1.key = subq2.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), ]
+ABSTRACT SYNTAX TREE:
+ (TOK_QUERY (TOK_FROM (TOK_JOIN (TOK_SUBQUERY (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME tbl1) a)) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (. (TOK_TABLE_OR_COL a) key) key) (TOK_SELEXPR (. (TOK_TABLE_OR_COL a) value) value)) (TOK_WHERE (< (TOK_TABLE_OR_COL key) 6)))) subq1) (TOK_SUBQUERY (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME tbl2) a)) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (. (TOK_TABLE_OR_COL a) key) key) (TOK_SELEXPR (. (TOK_TABLE_OR_COL a) value) value)) (TOK_WHERE (< (TOK_TABLE_OR_COL key) 6)))) subq2) (= (. (TOK_TABLE_OR_COL subq1) key) (. (TOK_TABLE_OR_COL subq2) 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:
+ subq2:a
+ Fetch Operator
+ limit: -1
+ Alias -> Map Local Operator Tree:
+ subq2:a
+ TableScan
+ alias: a
+ Filter Operator
+ predicate:
+ expr: (key < 6)
+ type: boolean
+ Select Operator
+ expressions:
+ expr: key
+ type: int
+ outputColumnNames: _col0
+ HashTable Sink Operator
+ condition expressions:
+ 0
+ 1
+ handleSkewJoin: false
+ keys:
+ 0 [Column[_col0]]
+ 1 [Column[_col0]]
+ Position of Big Table: 0
+
+ Stage: Stage-3
+ Map Reduce
+ Alias -> Map Operator Tree:
+ subq1:a
+ TableScan
+ alias: a
+ Filter Operator
+ predicate:
+ expr: (key < 6)
+ type: boolean
+ Select Operator
+ expressions:
+ expr: key
+ type: int
+ outputColumnNames: _col0
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0
+ 1
+ handleSkewJoin: false
+ keys:
+ 0 [Column[_col0]]
+ 1 [Column[_col0]]
+ 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-7
+ Map Reduce Local Work
+ Alias -> Map Local Tables:
+ subq1:a
+ Fetch Operator
+ limit: -1
+ Alias -> Map Local Operator Tree:
+ subq1:a
+ TableScan
+ alias: a
+ Filter Operator
+ predicate:
+ expr: (key < 6)
+ type: boolean
+ Select Operator
+ expressions:
+ expr: key
+ type: int
+ outputColumnNames: _col0
+ HashTable Sink Operator
+ condition expressions:
+ 0
+ 1
+ handleSkewJoin: false
+ keys:
+ 0 [Column[_col0]]
+ 1 [Column[_col0]]
+ Position of Big Table: 1
+
+ Stage: Stage-4
+ Map Reduce
+ Alias -> Map Operator Tree:
+ subq2:a
+ TableScan
+ alias: a
+ Filter Operator
+ predicate:
+ expr: (key < 6)
+ type: boolean
+ Select Operator
+ expressions:
+ expr: key
+ type: int
+ outputColumnNames: _col0
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0
+ 1
+ handleSkewJoin: false
+ keys:
+ 0 [Column[_col0]]
+ 1 [Column[_col0]]
+ 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-1
+ Map Reduce
+ Alias -> Map Operator Tree:
+ subq1:a
+ TableScan
+ alias: a
+ Filter Operator
+ predicate:
+ expr: (key < 6)
+ type: boolean
+ Select Operator
+ expressions:
+ expr: key
+ type: int
+ outputColumnNames: _col0
+ Sorted Merge Bucket Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0
+ 1
+ handleSkewJoin: false
+ keys:
+ 0 [Column[_col0]]
+ 1 [Column[_col0]]
+ 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
+ (select a.key as key, a.value as value from tbl1 a where key < 6) subq1
+ join
+ (select a.key as key, a.value as value from tbl2 a where key < 6) subq2
+ on subq1.key = subq2.key
+PREHOOK: type: QUERY
+PREHOOK: Input: default@tbl1
+PREHOOK: Input: default@tbl2
+#### A masked pattern was here ####
+POSTHOOK: query: select count(*) from
+ (select a.key as key, a.value as value from tbl1 a where key < 6) subq1
+ join
+ (select a.key as key, a.value as value from tbl2 a where key < 6) subq2
+ on subq1.key = subq2.key
+POSTHOOK: type: QUERY
+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), ]
+20
+PREHOOK: query: -- The subquery itself is being joined. Since the sub-query only contains selects and filters, it should
+-- be converted to a sort-merge join, although there is more than one level of sub-query
+explain
+select count(*) from
+ (
+ select * from
+ (
+ select a.key as key, a.value as value from tbl1 a where key < 8
+ ) subq1
+ where key < 6
+ ) subq2
+ join tbl2 b
+ on subq2.key = b.key
+PREHOOK: type: QUERY
+POSTHOOK: query: -- The subquery itself is being joined. Since the sub-query only contains selects and filters, it should
+-- be converted to a sort-merge join, although there is more than one level of sub-query
+explain
+select count(*) from
+ (
+ select * from
+ (
+ select a.key as key, a.value as value from tbl1 a where key < 8
+ ) subq1
+ where key < 6
+ ) subq2
+ join tbl2 b
+ on subq2.key = b.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), ]
+ABSTRACT SYNTAX TREE:
+ (TOK_QUERY (TOK_FROM (TOK_JOIN (TOK_SUBQUERY (TOK_QUERY (TOK_FROM (TOK_SUBQUERY (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME tbl1) a)) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (. (TOK_TABLE_OR_COL a) key) key) (TOK_SELEXPR (. (TOK_TABLE_OR_COL a) value) value)) (TOK_WHERE (< (TOK_TABLE_OR_COL key) 8)))) subq1)) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR TOK_ALLCOLREF)) (TOK_WHERE (< (TOK_TABLE_OR_COL key) 6)))) subq2) (TOK_TABREF (TOK_TABNAME tbl2) b) (= (. (TOK_TABLE_OR_COL subq2) 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
+ HashTable Sink Operator
+ condition expressions:
+ 0
+ 1
+ handleSkewJoin: false
+ keys:
+ 0 [Column[_col0]]
+ 1 [Column[key]]
+ Position of Big Table: 0
+
+ Stage: Stage-3
+ Map Reduce
+ Alias -> Map Operator Tree:
+ subq2:subq1:a
+ TableScan
+ alias: a
+ Filter Operator
+ predicate:
+ expr: ((key < 8) and (key < 6))
+ type: boolean
+ Select Operator
+ expressions:
+ expr: key
+ type: int
+ outputColumnNames: _col0
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0
+ 1
+ handleSkewJoin: false
+ keys:
+ 0 [Column[_col0]]
+ 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
+ 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-7
+ Map Reduce Local Work
+ Alias -> Map Local Tables:
+ subq2:subq1:a
+ Fetch Operator
+ limit: -1
+ Alias -> Map Local Operator Tree:
+ subq2:subq1:a
+ TableScan
+ alias: a
+ Filter Operator
+ predicate:
+ expr: ((key < 8) and (key < 6))
+ type: boolean
+ Select Operator
+ expressions:
+ expr: key
+ type: int
+ outputColumnNames: _col0
+ HashTable Sink Operator
+ condition expressions:
+ 0
+ 1
+ handleSkewJoin: false
+ keys:
+ 0 [Column[_col0]]
+ 1 [Column[key]]
+ Position of Big Table: 1
+
+ Stage: Stage-4
+ Map Reduce
+ Alias -> Map Operator Tree:
+ b
+ TableScan
+ alias: b
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0
+ 1
+ handleSkewJoin: false
+ keys:
+ 0 [Column[_col0]]
+ 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
+ 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:
+ subq2:subq1:a
+ TableScan
+ alias: a
+ Filter Operator
+ predicate:
+ expr: ((key < 8) and (key < 6))
+ type: boolean
+ Select Operator
+ expressions:
+ expr: key
+ type: int
+ outputColumnNames: _col0
+ Sorted Merge Bucket Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0
+ 1
+ handleSkewJoin: false
+ keys:
+ 0 [Column[_col0]]
+ 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
+ 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
+ (
+ select * from
+ (
+ select a.key as key, a.value as value from tbl1 a where key < 8
+ ) subq1
+ where key < 6
+ ) subq2
+ join tbl2 b
+ on subq2.key = b.key
+PREHOOK: type: QUERY
+PREHOOK: Input: default@tbl1
+PREHOOK: Input: default@tbl2
+#### A masked pattern was here ####
+POSTHOOK: query: select count(*) from
+ (
+ select * from
+ (
+ select a.key as key, a.value as value from tbl1 a where key < 8
+ ) subq1
+ where key < 6
+ ) subq2
+ join tbl2 b
+ on subq2.key = b.key
+POSTHOOK: type: QUERY
+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), ]
+20
+PREHOOK: query: -- Both the tables are nested sub-queries i.e more then 1 level of sub-query.
+-- The join should be converted to a sort-merge join
+explain
+select count(*) from
+ (
+ select * from
+ (
+ select a.key as key, a.value as value from tbl1 a where key < 8
+ ) subq1
+ where key < 6
+ ) subq2
+ join
+ (
+ select * from
+ (
+ select a.key as key, a.value as value from tbl1 a where key < 8
+ ) subq3
+ where key < 6
+ ) subq4
+ on subq2.key = subq4.key
+PREHOOK: type: QUERY
+POSTHOOK: query: -- Both the tables are nested sub-queries i.e more then 1 level of sub-query.
+-- The join should be converted to a sort-merge join
+explain
+select count(*) from
+ (
+ select * from
+ (
+ select a.key as key, a.value as value from tbl1 a where key < 8
+ ) subq1
+ where key < 6
+ ) subq2
+ join
+ (
+ select * from
+ (
+ select a.key as key, a.value as value from tbl1 a where key < 8
+ ) subq3
+ where key < 6
+ ) subq4
+ on subq2.key = subq4.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), ]
+ABSTRACT SYNTAX TREE:
+ (TOK_QUERY (TOK_FROM (TOK_JOIN (TOK_SUBQUERY (TOK_QUERY (TOK_FROM (TOK_SUBQUERY (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME tbl1) a)) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (. (TOK_TABLE_OR_COL a) key) key) (TOK_SELEXPR (. (TOK_TABLE_OR_COL a) value) value)) (TOK_WHERE (< (TOK_TABLE_OR_COL key) 8)))) subq1)) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR TOK_ALLCOLREF)) (TOK_WHERE (< (TOK_TABLE_OR_COL key) 6)))) subq2) (TOK_SUBQUERY (TOK_QUERY (TOK_FROM (TOK_SUBQUERY (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME tbl1) a)) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (. (TOK_TABLE_OR_COL a) key) key) (TOK_SELEXPR (. (TOK_TABLE_OR_COL a) value) value)) (TOK_WHERE (< (TOK_TABLE_OR_COL key) 8)))) subq3)) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR TOK_ALLCOLREF)) (TOK_WHERE (< (TOK_TABLE_OR_COL key) 6)))) subq4) (= (. (TOK_TABLE_OR_COL subq
2) key) (. (TOK_TABLE_OR_COL subq4) 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:
+ subq4:subq3:a
+ Fetch Operator
+ limit: -1
+ Alias -> Map Local Operator Tree:
+ subq4:subq3:a
+ TableScan
+ alias: a
+ Filter Operator
+ predicate:
+ expr: ((key < 8) and (key < 6))
+ type: boolean
+ Select Operator
+ expressions:
+ expr: key
+ type: int
+ outputColumnNames: _col0
+ HashTable Sink Operator
+ condition expressions:
+ 0
+ 1
+ handleSkewJoin: false
+ keys:
+ 0 [Column[_col0]]
+ 1 [Column[_col0]]
+ Position of Big Table: 0
+
+ Stage: Stage-3
+ Map Reduce
+ Alias -> Map Operator Tree:
+ subq2:subq1:a
+ TableScan
+ alias: a
+ Filter Operator
+ predicate:
+ expr: ((key < 8) and (key < 6))
+ type: boolean
+ Select Operator
+ expressions:
+ expr: key
+ type: int
+ outputColumnNames: _col0
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0
+ 1
[... 1921 lines stripped ...]