http://git-wip-us.apache.org/repos/asf/hive/blob/6f5c1135/ql/src/test/results/clientpositive/auto_sortmerge_join_6.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/auto_sortmerge_join_6.q.out
b/ql/src/test/results/clientpositive/auto_sortmerge_join_6.q.out
deleted file mode 100644
index 7cf01e5..0000000
--- a/ql/src/test/results/clientpositive/auto_sortmerge_join_6.q.out
+++ /dev/null
@@ -1,1353 +0,0 @@
-PREHOOK: query: CREATE TABLE tbl1(key int, value string) CLUSTERED BY (key)
SORTED BY (key) INTO 2 BUCKETS
-PREHOOK: type: CREATETABLE
-PREHOOK: Output: database:default
-PREHOOK: Output: default@tbl1
-POSTHOOK: query: CREATE TABLE tbl1(key int, value string) CLUSTERED BY (key)
SORTED BY (key) INTO 2 BUCKETS
-POSTHOOK: type: CREATETABLE
-POSTHOOK: Output: database:default
-POSTHOOK: Output: default@tbl1
-PREHOOK: query: CREATE TABLE tbl2(key int, value string) CLUSTERED BY (key)
SORTED BY (key) INTO 2 BUCKETS
-PREHOOK: type: CREATETABLE
-PREHOOK: Output: database:default
-PREHOOK: Output: default@tbl2
-POSTHOOK: query: CREATE TABLE tbl2(key int, value string) CLUSTERED BY (key)
SORTED BY (key) INTO 2 BUCKETS
-POSTHOOK: type: CREATETABLE
-POSTHOOK: Output: database:default
-POSTHOOK: Output: default@tbl2
-PREHOOK: query: CREATE TABLE tbl3(key int, value string) CLUSTERED BY (key)
SORTED BY (key) INTO 2 BUCKETS
-PREHOOK: type: CREATETABLE
-PREHOOK: Output: database:default
-PREHOOK: Output: default@tbl3
-POSTHOOK: query: CREATE TABLE tbl3(key int, value string) CLUSTERED BY (key)
SORTED BY (key) INTO 2 BUCKETS
-POSTHOOK: type: CREATETABLE
-POSTHOOK: Output: database:default
-POSTHOOK: Output: default@tbl3
-PREHOOK: query: CREATE TABLE tbl4(key int, value string) CLUSTERED BY (value)
SORTED BY (value) INTO 2 BUCKETS
-PREHOOK: type: CREATETABLE
-PREHOOK: Output: database:default
-PREHOOK: Output: default@tbl4
-POSTHOOK: query: CREATE TABLE tbl4(key int, value string) CLUSTERED BY (value)
SORTED BY (value) INTO 2 BUCKETS
-POSTHOOK: type: CREATETABLE
-POSTHOOK: Output: database:default
-POSTHOOK: Output: default@tbl4
-PREHOOK: query: insert overwrite table tbl1 select * from src
-PREHOOK: type: QUERY
-PREHOOK: Input: default@src
-PREHOOK: Output: default@tbl1
-POSTHOOK: query: insert overwrite table tbl1 select * from src
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@src
-POSTHOOK: Output: default@tbl1
-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), ]
-PREHOOK: query: insert overwrite table tbl2 select * from src
-PREHOOK: type: QUERY
-PREHOOK: Input: default@src
-PREHOOK: Output: default@tbl2
-POSTHOOK: query: insert overwrite table tbl2 select * from src
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@src
-POSTHOOK: Output: default@tbl2
-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), ]
-PREHOOK: query: insert overwrite table tbl3 select * from src
-PREHOOK: type: QUERY
-PREHOOK: Input: default@src
-PREHOOK: Output: default@tbl3
-POSTHOOK: query: insert overwrite table tbl3 select * from src
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@src
-POSTHOOK: Output: default@tbl3
-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), ]
-PREHOOK: query: insert overwrite table tbl4 select * from src
-PREHOOK: type: QUERY
-PREHOOK: Input: default@src
-PREHOOK: Output: default@tbl4
-POSTHOOK: query: insert overwrite table tbl4 select * from src
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@src
-POSTHOOK: Output: default@tbl4
-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), ]
-PREHOOK: query: -- A SMB join is being followed by a regular join on a
non-bucketed table on a different key
-
--- Three tests below are all the same query with different alias, which
changes dispatch order of GenMapRedWalker
--- This is dependent to iteration order of HashMap, so can be meaningless in
non-sun jdk
--- b = TS[0]-OP[13]-MAPJOIN[11]-RS[6]-JOIN[8]-SEL[9]-FS[10]
--- c = TS[1]-RS[7]-JOIN[8]
--- a = TS[2]-MAPJOIN[11]
-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
-
--- Three tests below are all the same query with different alias, which
changes dispatch order of GenMapRedWalker
--- This is dependent to iteration order of HashMap, so can be meaningless in
non-sun jdk
--- b = TS[0]-OP[13]-MAPJOIN[11]-RS[6]-JOIN[8]-SEL[9]-FS[10]
--- c = TS[1]-RS[7]-JOIN[8]
--- a = TS[2]-MAPJOIN[11]
-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
-STAGE DEPENDENCIES:
- Stage-1 is a root stage
- Stage-2 depends on stages: Stage-1
- Stage-0 depends on stages: Stage-2
-
-STAGE PLANS:
- Stage: Stage-1
- Map Reduce
- Map Operator Tree:
- TableScan
- alias: a
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE
Column stats: NONE
- Filter Operator
- predicate: (key is not null and value is not null) (type:
boolean)
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE
Column stats: NONE
- Select Operator
- expressions: key (type: int), value (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 500 Data size: 5312 Basic stats:
COMPLETE Column stats: NONE
- Sorted Merge Bucket Map Join Operator
- condition map:
- Inner Join 0 to 1
- keys:
- 0 _col0 (type: int)
- 1 _col0 (type: int)
- outputColumnNames: _col1
- Reduce Output Operator
- key expressions: _col1 (type: string)
- sort order: +
- Map-reduce partition columns: _col1 (type: string)
- TableScan
- alias: c
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE
Column stats: NONE
- Filter Operator
- predicate: value is not null (type: boolean)
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE
Column stats: NONE
- Select Operator
- expressions: value (type: string)
- outputColumnNames: _col0
- Statistics: Num rows: 500 Data size: 5312 Basic stats:
COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: string)
- sort order: +
- Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 500 Data size: 5312 Basic stats:
COMPLETE Column stats: NONE
- Reduce Operator Tree:
- Join Operator
- condition map:
- Inner Join 0 to 1
- keys:
- 0 _col1 (type: string)
- 1 _col0 (type: string)
- Group By Operator
- aggregations: count()
- mode: hash
- outputColumnNames: _col0
- File Output Operator
- compressed: false
- table:
- input format:
org.apache.hadoop.mapred.SequenceFileInputFormat
- output format:
org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde:
org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
-
- Stage: Stage-2
- Map Reduce
- Map Operator Tree:
- TableScan
- Reduce Output Operator
- sort order:
- value expressions: _col0 (type: bigint)
- Reduce Operator Tree:
- Group By Operator
- aggregations: count(VALUE._col0)
- mode: mergepartial
- outputColumnNames: _col0
- File Output Operator
- compressed: false
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format:
org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
- Stage: Stage-0
- Fetch Operator
- limit: -1
- Processor Tree:
- ListSink
-
-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 ####
-2654
-PREHOOK: query: -- d = TS[0]-RS[7]-JOIN[8]-SEL[9]-FS[10]
--- b = TS[1]-OP[13]-MAPJOIN[11]-RS[6]-JOIN[8]
--- a = TS[2]-MAPJOIN[11]
-explain select count(*) FROM tbl1 a JOIN tbl2 b ON a.key = b.key join src d on
d.value = a.value
-PREHOOK: type: QUERY
-POSTHOOK: query: -- d = TS[0]-RS[7]-JOIN[8]-SEL[9]-FS[10]
--- b = TS[1]-OP[13]-MAPJOIN[11]-RS[6]-JOIN[8]
--- a = TS[2]-MAPJOIN[11]
-explain select count(*) FROM tbl1 a JOIN tbl2 b ON a.key = b.key join src d on
d.value = a.value
-POSTHOOK: type: QUERY
-STAGE DEPENDENCIES:
- Stage-1 is a root stage
- Stage-2 depends on stages: Stage-1
- Stage-0 depends on stages: Stage-2
-
-STAGE PLANS:
- Stage: Stage-1
- Map Reduce
- Map Operator Tree:
- TableScan
- alias: a
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE
Column stats: NONE
- Filter Operator
- predicate: (key is not null and value is not null) (type:
boolean)
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE
Column stats: NONE
- Select Operator
- expressions: key (type: int), value (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 500 Data size: 5312 Basic stats:
COMPLETE Column stats: NONE
- Sorted Merge Bucket Map Join Operator
- condition map:
- Inner Join 0 to 1
- keys:
- 0 _col0 (type: int)
- 1 _col0 (type: int)
- outputColumnNames: _col1
- Reduce Output Operator
- key expressions: _col1 (type: string)
- sort order: +
- Map-reduce partition columns: _col1 (type: string)
- TableScan
- alias: d
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE
Column stats: NONE
- Filter Operator
- predicate: value is not null (type: boolean)
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE
Column stats: NONE
- Select Operator
- expressions: value (type: string)
- outputColumnNames: _col0
- Statistics: Num rows: 500 Data size: 5312 Basic stats:
COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: string)
- sort order: +
- Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 500 Data size: 5312 Basic stats:
COMPLETE Column stats: NONE
- Reduce Operator Tree:
- Join Operator
- condition map:
- Inner Join 0 to 1
- keys:
- 0 _col1 (type: string)
- 1 _col0 (type: string)
- Group By Operator
- aggregations: count()
- mode: hash
- outputColumnNames: _col0
- File Output Operator
- compressed: false
- table:
- input format:
org.apache.hadoop.mapred.SequenceFileInputFormat
- output format:
org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde:
org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
-
- Stage: Stage-2
- Map Reduce
- Map Operator Tree:
- TableScan
- Reduce Output Operator
- sort order:
- value expressions: _col0 (type: bigint)
- Reduce Operator Tree:
- Group By Operator
- aggregations: count(VALUE._col0)
- mode: mergepartial
- outputColumnNames: _col0
- File Output Operator
- compressed: false
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format:
org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
- Stage: Stage-0
- Fetch Operator
- limit: -1
- Processor Tree:
- ListSink
-
-PREHOOK: query: select count(*) FROM tbl1 a JOIN tbl2 b ON a.key = b.key join
src d on d.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 d on d.value = a.value
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@src
-POSTHOOK: Input: default@tbl1
-POSTHOOK: Input: default@tbl2
-#### A masked pattern was here ####
-2654
-PREHOOK: query: -- b = TS[0]-OP[13]-MAPJOIN[11]-RS[6]-JOIN[8]-SEL[9]-FS[10]
--- a = TS[1]-MAPJOIN[11]
--- h = TS[2]-RS[7]-JOIN[8]
-explain select count(*) FROM tbl1 a JOIN tbl2 b ON a.key = b.key join src h on
h.value = a.value
-PREHOOK: type: QUERY
-POSTHOOK: query: -- b = TS[0]-OP[13]-MAPJOIN[11]-RS[6]-JOIN[8]-SEL[9]-FS[10]
--- a = TS[1]-MAPJOIN[11]
--- h = TS[2]-RS[7]-JOIN[8]
-explain select count(*) FROM tbl1 a JOIN tbl2 b ON a.key = b.key join src h on
h.value = a.value
-POSTHOOK: type: QUERY
-STAGE DEPENDENCIES:
- Stage-1 is a root stage
- Stage-2 depends on stages: Stage-1
- Stage-0 depends on stages: Stage-2
-
-STAGE PLANS:
- Stage: Stage-1
- Map Reduce
- Map Operator Tree:
- TableScan
- alias: a
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE
Column stats: NONE
- Filter Operator
- predicate: (key is not null and value is not null) (type:
boolean)
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE
Column stats: NONE
- Select Operator
- expressions: key (type: int), value (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 500 Data size: 5312 Basic stats:
COMPLETE Column stats: NONE
- Sorted Merge Bucket Map Join Operator
- condition map:
- Inner Join 0 to 1
- keys:
- 0 _col0 (type: int)
- 1 _col0 (type: int)
- outputColumnNames: _col1
- Reduce Output Operator
- key expressions: _col1 (type: string)
- sort order: +
- Map-reduce partition columns: _col1 (type: string)
- TableScan
- alias: h
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE
Column stats: NONE
- Filter Operator
- predicate: value is not null (type: boolean)
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE
Column stats: NONE
- Select Operator
- expressions: value (type: string)
- outputColumnNames: _col0
- Statistics: Num rows: 500 Data size: 5312 Basic stats:
COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: string)
- sort order: +
- Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 500 Data size: 5312 Basic stats:
COMPLETE Column stats: NONE
- Reduce Operator Tree:
- Join Operator
- condition map:
- Inner Join 0 to 1
- keys:
- 0 _col1 (type: string)
- 1 _col0 (type: string)
- Group By Operator
- aggregations: count()
- mode: hash
- outputColumnNames: _col0
- File Output Operator
- compressed: false
- table:
- input format:
org.apache.hadoop.mapred.SequenceFileInputFormat
- output format:
org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde:
org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
-
- Stage: Stage-2
- Map Reduce
- Map Operator Tree:
- TableScan
- Reduce Output Operator
- sort order:
- value expressions: _col0 (type: bigint)
- Reduce Operator Tree:
- Group By Operator
- aggregations: count(VALUE._col0)
- mode: mergepartial
- outputColumnNames: _col0
- File Output Operator
- compressed: false
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format:
org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
- Stage: Stage-0
- Fetch Operator
- limit: -1
- Processor Tree:
- ListSink
-
-PREHOOK: query: select count(*) FROM tbl1 a JOIN tbl2 b ON a.key = b.key join
src h on h.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 h on h.value = a.value
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@src
-POSTHOOK: Input: default@tbl1
-POSTHOOK: Input: default@tbl2
-#### A masked pattern was here ####
-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
-STAGE DEPENDENCIES:
- Stage-1 is a root stage
- Stage-2 depends on stages: Stage-1
- Stage-0 depends on stages: Stage-2
-
-STAGE PLANS:
- Stage: Stage-1
- Map Reduce
- Map Operator Tree:
- TableScan
- alias: a
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE
Column stats: NONE
- Filter Operator
- predicate: key is not null (type: boolean)
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE
Column stats: NONE
- Select Operator
- expressions: key (type: int)
- outputColumnNames: _col0
- Statistics: Num rows: 500 Data size: 5312 Basic stats:
COMPLETE Column stats: NONE
- Sorted Merge Bucket Map Join Operator
- condition map:
- Inner Join 0 to 1
- keys:
- 0 _col0 (type: int)
- 1 _col0 (type: int)
- outputColumnNames: _col0
- Reduce Output Operator
- key expressions: UDFToDouble(_col0) (type: double)
- sort order: +
- Map-reduce partition columns: UDFToDouble(_col0) (type:
double)
- TableScan
- alias: c
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE
Column stats: NONE
- Filter Operator
- predicate: key is not null (type: boolean)
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE
Column stats: NONE
- Select Operator
- expressions: key (type: string)
- outputColumnNames: _col0
- Statistics: Num rows: 500 Data size: 5312 Basic stats:
COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: UDFToDouble(_col0) (type: double)
- sort order: +
- Map-reduce partition columns: UDFToDouble(_col0) (type:
double)
- Statistics: Num rows: 500 Data size: 5312 Basic stats:
COMPLETE Column stats: NONE
- Reduce Operator Tree:
- Join Operator
- condition map:
- Inner Join 0 to 1
- keys:
- 0 UDFToDouble(_col0) (type: double)
- 1 UDFToDouble(_col0) (type: double)
- Group By Operator
- aggregations: count()
- mode: hash
- outputColumnNames: _col0
- File Output Operator
- compressed: false
- table:
- input format:
org.apache.hadoop.mapred.SequenceFileInputFormat
- output format:
org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde:
org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
-
- Stage: Stage-2
- Map Reduce
- Map Operator Tree:
- TableScan
- Reduce Output Operator
- sort order:
- value expressions: _col0 (type: bigint)
- Reduce Operator Tree:
- Group By Operator
- aggregations: count(VALUE._col0)
- mode: mergepartial
- outputColumnNames: _col0
- File Output Operator
- compressed: false
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format:
org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
- Stage: Stage-0
- Fetch Operator
- limit: -1
- Processor Tree:
- ListSink
-
-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 ####
-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
-STAGE DEPENDENCIES:
- Stage-1 is a root stage
- Stage-0 depends on stages: Stage-1
-
-STAGE PLANS:
- Stage: Stage-1
- Map Reduce
- Map Operator Tree:
- TableScan
- alias: a
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE
Column stats: NONE
- Filter Operator
- predicate: key is not null (type: boolean)
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE
Column stats: NONE
- Select Operator
- expressions: key (type: int)
- outputColumnNames: _col0
- Statistics: Num rows: 500 Data size: 5312 Basic stats:
COMPLETE Column stats: NONE
- Sorted Merge Bucket Map Join Operator
- condition map:
- Inner Join 0 to 1
- Inner Join 0 to 2
- keys:
- 0 _col0 (type: int)
- 1 _col0 (type: int)
- 2 _col0 (type: int)
- Group By Operator
- aggregations: count()
- mode: hash
- outputColumnNames: _col0
- Reduce Output Operator
- sort order:
- value expressions: _col0 (type: bigint)
- Reduce Operator Tree:
- Group By Operator
- aggregations: count(VALUE._col0)
- mode: mergepartial
- outputColumnNames: _col0
- File Output Operator
- compressed: false
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format:
org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
- Stage: Stage-0
- Fetch Operator
- limit: -1
- Processor Tree:
- ListSink
-
-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 ####
-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
-STAGE DEPENDENCIES:
- Stage-1 is a root stage
- Stage-2 depends on stages: Stage-1
- Stage-0 depends on stages: Stage-2
-
-STAGE PLANS:
- Stage: Stage-1
- Map Reduce
- Map Operator Tree:
- TableScan
- alias: a
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE
Column stats: NONE
- Filter Operator
- predicate: (key is not null and value is not null) (type:
boolean)
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE
Column stats: NONE
- Select Operator
- expressions: key (type: int), value (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 500 Data size: 5312 Basic stats:
COMPLETE Column stats: NONE
- Sorted Merge Bucket Map Join Operator
- condition map:
- Inner Join 0 to 1
- keys:
- 0 _col0 (type: int)
- 1 _col0 (type: int)
- outputColumnNames: _col1
- Reduce Output Operator
- key expressions: _col1 (type: string)
- sort order: +
- Map-reduce partition columns: _col1 (type: string)
- TableScan
- alias: c
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE
Column stats: NONE
- Filter Operator
- predicate: value is not null (type: boolean)
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE
Column stats: NONE
- Select Operator
- expressions: value (type: string)
- outputColumnNames: _col0
- Statistics: Num rows: 500 Data size: 5312 Basic stats:
COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: string)
- sort order: +
- Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 500 Data size: 5312 Basic stats:
COMPLETE Column stats: NONE
- Reduce Operator Tree:
- Join Operator
- condition map:
- Inner Join 0 to 1
- keys:
- 0 _col1 (type: string)
- 1 _col0 (type: string)
- Group By Operator
- aggregations: count()
- mode: hash
- outputColumnNames: _col0
- File Output Operator
- compressed: false
- table:
- input format:
org.apache.hadoop.mapred.SequenceFileInputFormat
- output format:
org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde:
org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
-
- Stage: Stage-2
- Map Reduce
- Map Operator Tree:
- TableScan
- Reduce Output Operator
- sort order:
- value expressions: _col0 (type: bigint)
- Reduce Operator Tree:
- Group By Operator
- aggregations: count(VALUE._col0)
- mode: mergepartial
- outputColumnNames: _col0
- File Output Operator
- compressed: false
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format:
org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
- Stage: Stage-0
- Fetch Operator
- limit: -1
- Processor Tree:
- ListSink
-
-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 ####
-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
-STAGE DEPENDENCIES:
- Stage-1 is a root stage
- Stage-2 depends on stages: Stage-1
- Stage-0 depends on stages: Stage-2
-
-STAGE PLANS:
- Stage: Stage-1
- Map Reduce
- Map Operator Tree:
- TableScan
- alias: a
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE
Column stats: NONE
- Filter Operator
- predicate: (key is not null and value is not null) (type:
boolean)
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE
Column stats: NONE
- Select Operator
- expressions: key (type: int), value (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 500 Data size: 5312 Basic stats:
COMPLETE Column stats: NONE
- Sorted Merge Bucket Map Join Operator
- condition map:
- Inner Join 0 to 1
- keys:
- 0 _col0 (type: int)
- 1 _col0 (type: int)
- outputColumnNames: _col1
- Reduce Output Operator
- key expressions: _col1 (type: string)
- sort order: +
- Map-reduce partition columns: _col1 (type: string)
- TableScan
- alias: c
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE
Column stats: NONE
- Filter Operator
- predicate: value is not null (type: boolean)
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE
Column stats: NONE
- Select Operator
- expressions: value (type: string)
- outputColumnNames: _col0
- Statistics: Num rows: 500 Data size: 5312 Basic stats:
COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: string)
- sort order: +
- Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 500 Data size: 5312 Basic stats:
COMPLETE Column stats: NONE
- Reduce Operator Tree:
- Join Operator
- condition map:
- Inner Join 0 to 1
- keys:
- 0 _col1 (type: string)
- 1 _col0 (type: string)
- Group By Operator
- aggregations: count()
- mode: hash
- outputColumnNames: _col0
- File Output Operator
- compressed: false
- table:
- input format:
org.apache.hadoop.mapred.SequenceFileInputFormat
- output format:
org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde:
org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
-
- Stage: Stage-2
- Map Reduce
- Map Operator Tree:
- TableScan
- Reduce Output Operator
- sort order:
- value expressions: _col0 (type: bigint)
- Reduce Operator Tree:
- Group By Operator
- aggregations: count(VALUE._col0)
- mode: mergepartial
- outputColumnNames: _col0
- File Output Operator
- compressed: false
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format:
org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
- Stage: Stage-0
- Fetch Operator
- limit: -1
- Processor Tree:
- ListSink
-
-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 ####
-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
-STAGE DEPENDENCIES:
- Stage-1 is a root stage
- Stage-2 depends on stages: Stage-1
- Stage-0 depends on stages: Stage-2
-
-STAGE PLANS:
- Stage: Stage-1
- Map Reduce
- Map Operator Tree:
- TableScan
- alias: a
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE
Column stats: NONE
- Filter Operator
- predicate: key is not null (type: boolean)
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE
Column stats: NONE
- Select Operator
- expressions: key (type: int)
- outputColumnNames: _col0
- Statistics: Num rows: 500 Data size: 5312 Basic stats:
COMPLETE Column stats: NONE
- Sorted Merge Bucket Map Join Operator
- condition map:
- Inner Join 0 to 1
- keys:
- 0 _col0 (type: int)
- 1 _col0 (type: int)
- outputColumnNames: _col0
- Reduce Output Operator
- key expressions: UDFToDouble(_col0) (type: double)
- sort order: +
- Map-reduce partition columns: UDFToDouble(_col0) (type:
double)
- TableScan
- alias: c
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE
Column stats: NONE
- Filter Operator
- predicate: key is not null (type: boolean)
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE
Column stats: NONE
- Select Operator
- expressions: key (type: string)
- outputColumnNames: _col0
- Statistics: Num rows: 500 Data size: 5312 Basic stats:
COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: UDFToDouble(_col0) (type: double)
- sort order: +
- Map-reduce partition columns: UDFToDouble(_col0) (type:
double)
- Statistics: Num rows: 500 Data size: 5312 Basic stats:
COMPLETE Column stats: NONE
- Reduce Operator Tree:
- Join Operator
- condition map:
- Inner Join 0 to 1
- keys:
- 0 UDFToDouble(_col0) (type: double)
- 1 UDFToDouble(_col0) (type: double)
- Group By Operator
- aggregations: count()
- mode: hash
- outputColumnNames: _col0
- File Output Operator
- compressed: false
- table:
- input format:
org.apache.hadoop.mapred.SequenceFileInputFormat
- output format:
org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde:
org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
-
- Stage: Stage-2
- Map Reduce
- Map Operator Tree:
- TableScan
- Reduce Output Operator
- sort order:
- value expressions: _col0 (type: bigint)
- Reduce Operator Tree:
- Group By Operator
- aggregations: count(VALUE._col0)
- mode: mergepartial
- outputColumnNames: _col0
- File Output Operator
- compressed: false
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format:
org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
- Stage: Stage-0
- Fetch Operator
- limit: -1
- Processor Tree:
- ListSink
-
-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 ####
-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
-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 depends on stages: Stage-4, Stage-5, Stage-6, Stage-1
-
-STAGE PLANS:
- Stage: Stage-7
- Conditional Operator
-
- Stage: Stage-8
- Map Reduce Local Work
- Alias -> Map Local Tables:
- $hdt$_1:b
- Fetch Operator
- limit: -1
- $hdt$_2:c
- Fetch Operator
- limit: -1
- Alias -> Map Local Operator Tree:
- $hdt$_1:b
- TableScan
- alias: b
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE
Column stats: NONE
- Filter Operator
- predicate: key is not null (type: boolean)
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE
Column stats: NONE
- Select Operator
- expressions: key (type: int)
- outputColumnNames: _col0
- Statistics: Num rows: 500 Data size: 5312 Basic stats:
COMPLETE Column stats: NONE
- HashTable Sink Operator
- keys:
- 0 _col0 (type: int)
- 1 _col0 (type: int)
- 2 _col0 (type: int)
- $hdt$_2:c
- TableScan
- alias: c
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE
Column stats: NONE
- Filter Operator
- predicate: key is not null (type: boolean)
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE
Column stats: NONE
- Select Operator
- expressions: key (type: int)
- outputColumnNames: _col0
- Statistics: Num rows: 500 Data size: 5312 Basic stats:
COMPLETE Column stats: NONE
- HashTable Sink Operator
- keys:
- 0 _col0 (type: int)
- 1 _col0 (type: int)
- 2 _col0 (type: int)
-
- Stage: Stage-4
- Map Reduce
- Map Operator Tree:
- TableScan
- alias: a
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE
Column stats: NONE
- Filter Operator
- predicate: key is not null (type: boolean)
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE
Column stats: NONE
- Select Operator
- expressions: key (type: int)
- outputColumnNames: _col0
- Statistics: Num rows: 500 Data size: 5312 Basic stats:
COMPLETE Column stats: NONE
- Map Join Operator
- condition map:
- Inner Join 0 to 1
- Inner Join 0 to 2
- keys:
- 0 _col0 (type: int)
- 1 _col0 (type: int)
- 2 _col0 (type: int)
- Group By Operator
- aggregations: count()
- mode: hash
- outputColumnNames: _col0
- Reduce Output Operator
- sort order:
- value expressions: _col0 (type: bigint)
- Local Work:
- Map Reduce Local Work
- Reduce Operator Tree:
- Group By Operator
- aggregations: count(VALUE._col0)
- mode: mergepartial
- outputColumnNames: _col0
- File Output Operator
- compressed: false
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format:
org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
- Stage: Stage-9
- Map Reduce Local Work
- Alias -> Map Local Tables:
- $hdt$_0:a
- Fetch Operator
- limit: -1
- $hdt$_2:c
- Fetch Operator
- limit: -1
- Alias -> Map Local Operator Tree:
- $hdt$_0:a
- TableScan
- alias: a
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE
Column stats: NONE
- Filter Operator
- predicate: key is not null (type: boolean)
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE
Column stats: NONE
- Select Operator
- expressions: key (type: int)
- outputColumnNames: _col0
- Statistics: Num rows: 500 Data size: 5312 Basic stats:
COMPLETE Column stats: NONE
- HashTable Sink Operator
- keys:
- 0 _col0 (type: int)
- 1 _col0 (type: int)
- 2 _col0 (type: int)
- $hdt$_2:c
- TableScan
- alias: c
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE
Column stats: NONE
- Filter Operator
- predicate: key is not null (type: boolean)
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE
Column stats: NONE
- Select Operator
- expressions: key (type: int)
- outputColumnNames: _col0
- Statistics: Num rows: 500 Data size: 5312 Basic stats:
COMPLETE Column stats: NONE
- HashTable Sink Operator
- keys:
- 0 _col0 (type: int)
- 1 _col0 (type: int)
- 2 _col0 (type: int)
-
- Stage: Stage-5
- Map Reduce
- Map Operator Tree:
- TableScan
- alias: b
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE
Column stats: NONE
- Filter Operator
- predicate: key is not null (type: boolean)
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE
Column stats: NONE
- Select Operator
- expressions: key (type: int)
- outputColumnNames: _col0
- Statistics: Num rows: 500 Data size: 5312 Basic stats:
COMPLETE Column stats: NONE
- Map Join Operator
- condition map:
- Inner Join 0 to 1
- Inner Join 0 to 2
- keys:
- 0 _col0 (type: int)
- 1 _col0 (type: int)
- 2 _col0 (type: int)
- Group By Operator
- aggregations: count()
- mode: hash
- outputColumnNames: _col0
- Reduce Output Operator
- sort order:
- value expressions: _col0 (type: bigint)
- Local Work:
- Map Reduce Local Work
- Reduce Operator Tree:
- Group By Operator
- aggregations: count(VALUE._col0)
- mode: mergepartial
- outputColumnNames: _col0
- File Output Operator
- compressed: false
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format:
org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
- Stage: Stage-10
- Map Reduce Local Work
- Alias -> Map Local Tables:
- $hdt$_0:a
- Fetch Operator
- limit: -1
- $hdt$_1:b
- Fetch Operator
- limit: -1
- Alias -> Map Local Operator Tree:
- $hdt$_0:a
- TableScan
- alias: a
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE
Column stats: NONE
- Filter Operator
- predicate: key is not null (type: boolean)
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE
Column stats: NONE
- Select Operator
- expressions: key (type: int)
- outputColumnNames: _col0
- Statistics: Num rows: 500 Data size: 5312 Basic stats:
COMPLETE Column stats: NONE
- HashTable Sink Operator
- keys:
- 0 _col0 (type: int)
- 1 _col0 (type: int)
- 2 _col0 (type: int)
- $hdt$_1:b
- TableScan
- alias: b
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE
Column stats: NONE
- Filter Operator
- predicate: key is not null (type: boolean)
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE
Column stats: NONE
- Select Operator
- expressions: key (type: int)
- outputColumnNames: _col0
- Statistics: Num rows: 500 Data size: 5312 Basic stats:
COMPLETE Column stats: NONE
- HashTable Sink Operator
- keys:
- 0 _col0 (type: int)
- 1 _col0 (type: int)
- 2 _col0 (type: int)
-
- Stage: Stage-6
- Map Reduce
- Map Operator Tree:
- TableScan
- alias: c
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE
Column stats: NONE
- Filter Operator
- predicate: key is not null (type: boolean)
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE
Column stats: NONE
- Select Operator
- expressions: key (type: int)
- outputColumnNames: _col0
- Statistics: Num rows: 500 Data size: 5312 Basic stats:
COMPLETE Column stats: NONE
- Map Join Operator
- condition map:
- Inner Join 0 to 1
- Inner Join 0 to 2
- keys:
- 0 _col0 (type: int)
- 1 _col0 (type: int)
- 2 _col0 (type: int)
- Group By Operator
- aggregations: count()
- mode: hash
- outputColumnNames: _col0
- Reduce Output Operator
- sort order:
- value expressions: _col0 (type: bigint)
- Local Work:
- Map Reduce Local Work
- Reduce Operator Tree:
- Group By Operator
- aggregations: count(VALUE._col0)
- mode: mergepartial
- outputColumnNames: _col0
- File Output Operator
- compressed: false
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format:
org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
- Stage: Stage-1
- Map Reduce
- Map Operator Tree:
- TableScan
- alias: a
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE
Column stats: NONE
- Filter Operator
- predicate: key is not null (type: boolean)
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE
Column stats: NONE
- Select Operator
- expressions: key (type: int)
- outputColumnNames: _col0
- Statistics: Num rows: 500 Data size: 5312 Basic stats:
COMPLETE Column stats: NONE
- Sorted Merge Bucket Map Join Operator
- condition map:
- Inner Join 0 to 1
- Inner Join 0 to 2
- keys:
- 0 _col0 (type: int)
- 1 _col0 (type: int)
- 2 _col0 (type: int)
- Group By Operator
- aggregations: count()
- mode: hash
- outputColumnNames: _col0
- Reduce Output Operator
- sort order:
- value expressions: _col0 (type: bigint)
- Reduce Operator Tree:
- Group By Operator
- aggregations: count(VALUE._col0)
- mode: mergepartial
- outputColumnNames: _col0
- File Output Operator
- compressed: false
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format:
org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
- Stage: Stage-0
- Fetch Operator
- limit: -1
- Processor Tree:
- ListSink
-
-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 ####
-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
-STAGE DEPENDENCIES:
- Stage-1 is a root stage
- Stage-2 depends on stages: Stage-1
- Stage-0 depends on stages: Stage-2
-
-STAGE PLANS:
- Stage: Stage-1
- Map Reduce
- Map Operator Tree:
- TableScan
- alias: a
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE
Column stats: NONE
- Filter Operator
- predicate: (key is not null and value is not null) (type:
boolean)
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE
Column stats: NONE
- Select Operator
- expressions: key (type: int), value (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 500 Data size: 5312 Basic stats:
COMPLETE Column stats: NONE
- Sorted Merge Bucket Map Join Operator
- condition map:
- Inner Join 0 to 1
- keys:
- 0 _col0 (type: int)
- 1 _col0 (type: int)
- outputColumnNames: _col1
- Reduce Output Operator
- key expressions: _col1 (type: string)
- sort order: +
- Map-reduce partition columns: _col1 (type: string)
- TableScan
- alias: c
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE
Column stats: NONE
- Filter Operator
- predicate: value is not null (type: boolean)
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE
Column stats: NONE
- Select Operator
- expressions: value (type: string)
- outputColumnNames: _col0
- Statistics: Num rows: 500 Data size: 5312 Basic stats:
COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: string)
- sort order: +
- Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 500 Data size: 5312 Basic stats:
COMPLETE Column stats: NONE
- Reduce Operator Tree:
- Join Operator
- condition map:
- Inner Join 0 to 1
- keys:
- 0 _col1 (type: string)
- 1 _col0 (type: string)
- Group By Operator
- aggregations: count()
- mode: hash
- outputColumnNames: _col0
- File Output Operator
- compressed: false
- table:
- input format:
org.apache.hadoop.mapred.SequenceFileInputFormat
- output format:
org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde:
org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
-
- Stage: Stage-2
- Map Reduce
- Map Operator Tree:
- TableScan
- Reduce Output Operator
- sort order:
- value expressions: _col0 (type: bigint)
- Reduce Operator Tree:
- Group By Operator
- aggregations: count(VALUE._col0)
- mode: mergepartial
- outputColumnNames: _col0
- File Output Operator
- compressed: false
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format:
org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
- Stage: Stage-0
- Fetch Operator
- limit: -1
- Processor Tree:
- ListSink
-
-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 ####
-2654
