http://git-wip-us.apache.org/repos/asf/hive/blob/38405c14/ql/src/test/results/clientpositive/auto_sortmerge_join_12.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/auto_sortmerge_join_12.q.out
b/ql/src/test/results/clientpositive/auto_sortmerge_join_12.q.out
index 3d0559a..1ed3dd0 100644
--- a/ql/src/test/results/clientpositive/auto_sortmerge_join_12.q.out
+++ b/ql/src/test/results/clientpositive/auto_sortmerge_join_12.q.out
@@ -134,21 +134,39 @@ POSTHOOK: query: load data local inpath
'../../data/files/smallsrcsortbucket3out
POSTHOOK: type: LOAD
#### A masked pattern was here ####
POSTHOOK: Output: default@bucket_medium@ds=2008-04-08
-Warning: Map Join MAPJOIN[31][bigTable=?] in task 'Stage-3:MAPRED' is a cross
product
+Warning: Map Join MAPJOIN[32][bigTable=?] in task 'Stage-8:MAPRED' is a cross
product
+Warning: Map Join MAPJOIN[31][bigTable=?] in task 'Stage-7:MAPRED' is a cross
product
+Warning: Shuffle Join JOIN[17][tables = [$hdt$_1, $hdt$_2, $hdt$_0, $hdt$_3]]
in Stage 'Stage-2:MAPRED' is a cross product
PREHOOK: query: explain extended select count(*) FROM bucket_small a JOIN
bucket_medium b ON a.key = b.key JOIN bucket_big c ON c.key = b.key JOIN
bucket_medium d ON c.key = b.key
PREHOOK: type: QUERY
POSTHOOK: query: explain extended select count(*) FROM bucket_small a JOIN
bucket_medium b ON a.key = b.key JOIN bucket_big c ON c.key = b.key JOIN
bucket_medium d ON c.key = b.key
POSTHOOK: type: QUERY
STAGE DEPENDENCIES:
- Stage-9 is a root stage
- Stage-3 depends on stages: Stage-9
+ Stage-13 is a root stage , consists of Stage-16, Stage-17, Stage-18, Stage-1
+ Stage-16 has a backup stage: Stage-1
+ Stage-10 depends on stages: Stage-16
+ Stage-9 depends on stages: Stage-1, Stage-10, Stage-11, Stage-12 , consists
of Stage-14, Stage-15, Stage-2
+ Stage-14 has a backup stage: Stage-2
+ Stage-7 depends on stages: Stage-14
+ Stage-3 depends on stages: Stage-2, Stage-7, Stage-8
+ Stage-15 has a backup stage: Stage-2
+ Stage-8 depends on stages: Stage-15
+ Stage-2
+ Stage-17 has a backup stage: Stage-1
+ Stage-11 depends on stages: Stage-17
+ Stage-18 has a backup stage: Stage-1
+ Stage-12 depends on stages: Stage-18
+ Stage-1
Stage-0 depends on stages: Stage-3
STAGE PLANS:
- Stage: Stage-9
+ Stage: Stage-13
+ Conditional Operator
+
+ Stage: Stage-16
Map Reduce Local Work
Alias -> Map Local Tables:
- $hdt$_1:a
+ $hdt$_0:c
Fetch Operator
limit: -1
Partition Description:
@@ -159,23 +177,23 @@ STAGE PLANS:
partition values:
ds 2008-04-08
properties:
- bucket_count 2
+ bucket_count 4
bucket_field_name key
column.name.delimiter ,
columns key,value
columns.comments
columns.types string:string
#### A masked pattern was here ####
- name default.bucket_small
- numFiles 2
+ name default.bucket_big
+ numFiles 4
numRows 0
partition_columns ds
partition_columns.types string
rawDataSize 0
- serialization.ddl struct bucket_small { string key, string
value}
+ serialization.ddl struct bucket_big { string key, string
value}
serialization.format 1
serialization.lib
org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 114
+ totalSize 5812
#### A masked pattern was here ####
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
@@ -183,51 +201,47 @@ STAGE PLANS:
output format:
org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
SORTBUCKETCOLSPREFIX TRUE
- bucket_count 2
+ bucket_count 4
bucket_field_name key
column.name.delimiter ,
columns key,value
columns.comments
columns.types string:string
#### A masked pattern was here ####
- name default.bucket_small
+ name default.bucket_big
partition_columns ds
partition_columns.types string
- serialization.ddl struct bucket_small { string key,
string value}
+ serialization.ddl struct bucket_big { string key, string
value}
serialization.format 1
serialization.lib
org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
#### A masked pattern was here ####
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.bucket_small
- name: default.bucket_small
- $hdt$_2:b
- Fetch Operator
- limit: -1
- Partition Description:
+ name: default.bucket_big
+ name: default.bucket_big
Partition
- base file name: ds=2008-04-08
+ base file name: ds=2008-04-09
input format: org.apache.hadoop.mapred.TextInputFormat
output format:
org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
partition values:
- ds 2008-04-08
+ ds 2008-04-09
properties:
- bucket_count 3
+ bucket_count 4
bucket_field_name key
column.name.delimiter ,
columns key,value
columns.comments
columns.types string:string
#### A masked pattern was here ####
- name default.bucket_medium
- numFiles 3
+ name default.bucket_big
+ numFiles 4
numRows 0
partition_columns ds
partition_columns.types string
rawDataSize 0
- serialization.ddl struct bucket_medium { string key,
string value}
+ serialization.ddl struct bucket_big { string key, string
value}
serialization.format 1
serialization.lib
org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 170
+ totalSize 5812
#### A masked pattern was here ####
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
@@ -235,24 +249,24 @@ STAGE PLANS:
output format:
org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
SORTBUCKETCOLSPREFIX TRUE
- bucket_count 3
+ bucket_count 4
bucket_field_name key
column.name.delimiter ,
columns key,value
columns.comments
columns.types string:string
#### A masked pattern was here ####
- name default.bucket_medium
+ name default.bucket_big
partition_columns ds
partition_columns.types string
- serialization.ddl struct bucket_medium { string key,
string value}
+ serialization.ddl struct bucket_big { string key, string
value}
serialization.format 1
serialization.lib
org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
#### A masked pattern was here ####
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.bucket_medium
- name: default.bucket_medium
- $hdt$_3:d
+ name: default.bucket_big
+ name: default.bucket_big
+ $hdt$_2:b
Fetch Operator
limit: -1
Partition Description:
@@ -305,25 +319,25 @@ STAGE PLANS:
name: default.bucket_medium
name: default.bucket_medium
Alias -> Map Local Operator Tree:
- $hdt$_1:a
+ $hdt$_0:c
TableScan
- alias: a
- Statistics: Num rows: 1 Data size: 114 Basic stats: COMPLETE
Column stats: NONE
+ alias: c
+ Statistics: Num rows: 116 Data size: 11624 Basic stats: COMPLETE
Column stats: NONE
GatherStats: false
Filter Operator
isSamplingPred: false
predicate: key is not null (type: boolean)
- Statistics: Num rows: 1 Data size: 114 Basic stats: COMPLETE
Column stats: NONE
+ Statistics: Num rows: 116 Data size: 11624 Basic stats: COMPLETE
Column stats: NONE
Select Operator
expressions: key (type: string)
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 114 Basic stats: COMPLETE
Column stats: NONE
+ Statistics: Num rows: 116 Data size: 11624 Basic stats:
COMPLETE Column stats: NONE
HashTable Sink Operator
keys:
0 _col0 (type: string)
1 _col0 (type: string)
2 _col0 (type: string)
- Position of Big Table: 2
+ Position of Big Table: 0
$hdt$_2:b
TableScan
alias: b
@@ -342,35 +356,23 @@ STAGE PLANS:
0 _col0 (type: string)
1 _col0 (type: string)
2 _col0 (type: string)
- Position of Big Table: 2
- $hdt$_3:d
- TableScan
- alias: d
- Statistics: Num rows: 1 Data size: 170 Basic stats: PARTIAL Column
stats: NONE
- GatherStats: false
- Select Operator
- Statistics: Num rows: 1 Data size: 170 Basic stats: PARTIAL
Column stats: NONE
- HashTable Sink Operator
- keys:
- 0
- 1
- Position of Big Table: 0
+ Position of Big Table: 0
- Stage: Stage-3
+ Stage: Stage-10
Map Reduce
Map Operator Tree:
TableScan
- alias: c
- Statistics: Num rows: 116 Data size: 11624 Basic stats: COMPLETE
Column stats: NONE
+ alias: a
+ Statistics: Num rows: 1 Data size: 114 Basic stats: COMPLETE
Column stats: NONE
GatherStats: false
Filter Operator
isSamplingPred: false
predicate: key is not null (type: boolean)
- Statistics: Num rows: 116 Data size: 11624 Basic stats: COMPLETE
Column stats: NONE
+ Statistics: Num rows: 1 Data size: 114 Basic stats: COMPLETE
Column stats: NONE
Select Operator
expressions: key (type: string)
outputColumnNames: _col0
- Statistics: Num rows: 116 Data size: 11624 Basic stats:
COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 114 Basic stats: COMPLETE
Column stats: NONE
Map Join Operator
condition map:
Inner Join 0 to 1
@@ -379,28 +381,26 @@ STAGE PLANS:
0 _col0 (type: string)
1 _col0 (type: string)
2 _col0 (type: string)
- Position of Big Table: 2
+ Position of Big Table: 0
Statistics: Num rows: 255 Data size: 25572 Basic stats:
COMPLETE Column stats: NONE
- Map Join Operator
- condition map:
- Inner Join 0 to 1
- keys:
- 0
- 1
- Position of Big Table: 0
- Statistics: Num rows: 255 Data size: 69177 Basic stats:
PARTIAL Column stats: NONE
- Group By Operator
- aggregations: count()
- mode: hash
- outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats:
PARTIAL Column stats: NONE
- Reduce Output Operator
- null sort order:
- sort order:
- Statistics: Num rows: 1 Data size: 8 Basic stats:
PARTIAL Column stats: NONE
- tag: -1
- value expressions: _col0 (type: bigint)
- auto parallelism: false
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+#### A masked pattern was here ####
+ NumFilesPerFileSink: 1
+ table:
+ input format:
org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format:
org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ properties:
+ column.name.delimiter ,
+ columns
+ columns.types
+ escape.delim \
+ serialization.lib
org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+ serde:
org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+ TotalFiles: 1
+ GatherStats: false
+ MultiFileSpray: false
Local Work:
Map Reduce Local Work
Path -> Alias:
@@ -603,8 +603,234 @@ STAGE PLANS:
name: default.bucket_small
name: default.bucket_small
Truncated Path -> Alias:
- /bucket_big/ds=2008-04-08 [$hdt$_0:c]
- /bucket_big/ds=2008-04-09 [$hdt$_0:c]
+ /bucket_small/ds=2008-04-08 [$hdt$_1:a]
+
+ Stage: Stage-9
+ Conditional Operator
+
+ Stage: Stage-14
+ Map Reduce Local Work
+ Alias -> Map Local Tables:
+ $hdt$_3:d
+ Fetch Operator
+ limit: -1
+ Partition Description:
+ Partition
+ base file name: ds=2008-04-08
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format:
org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ partition values:
+ ds 2008-04-08
+ properties:
+ bucket_count 3
+ bucket_field_name key
+ column.name.delimiter ,
+ columns key,value
+ columns.comments
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.bucket_medium
+ numFiles 3
+ numRows 0
+ partition_columns ds
+ partition_columns.types string
+ rawDataSize 0
+ serialization.ddl struct bucket_medium { string key,
string value}
+ serialization.format 1
+ serialization.lib
org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ totalSize 170
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format:
org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ properties:
+ SORTBUCKETCOLSPREFIX TRUE
+ bucket_count 3
+ bucket_field_name key
+ column.name.delimiter ,
+ columns key,value
+ columns.comments
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.bucket_medium
+ partition_columns ds
+ partition_columns.types string
+ serialization.ddl struct bucket_medium { string key,
string value}
+ serialization.format 1
+ serialization.lib
org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.bucket_medium
+ name: default.bucket_medium
+ Alias -> Map Local Operator Tree:
+ $hdt$_3:d
+ TableScan
+ alias: d
+ Statistics: Num rows: 1 Data size: 170 Basic stats: PARTIAL Column
stats: NONE
+ GatherStats: false
+ Select Operator
+ Statistics: Num rows: 1 Data size: 170 Basic stats: PARTIAL
Column stats: NONE
+ HashTable Sink Operator
+ keys:
+ 0
+ 1
+ Position of Big Table: 0
+
+ Stage: Stage-7
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ GatherStats: false
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0
+ 1
+ Position of Big Table: 0
+ Statistics: Num rows: 255 Data size: 69177 Basic stats: PARTIAL
Column stats: NONE
+ Group By Operator
+ aggregations: count()
+ mode: hash
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 8 Basic stats: PARTIAL
Column stats: NONE
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+#### A masked pattern was here ####
+ NumFilesPerFileSink: 1
+ table:
+ input format:
org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format:
org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ properties:
+ column.name.delimiter ,
+ columns _col0
+ columns.types bigint
+ escape.delim \
+ serialization.lib
org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+ serde:
org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+ TotalFiles: 1
+ GatherStats: false
+ MultiFileSpray: false
+ Local Work:
+ Map Reduce Local Work
+ Path -> Alias:
+#### A masked pattern was here ####
+ Path -> Partition:
+#### A masked pattern was here ####
+ Partition
+ base file name: -mr-10004
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format:
org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ properties:
+ column.name.delimiter ,
+ columns
+ columns.types
+ escape.delim \
+ serialization.lib
org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+ serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format:
org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ properties:
+ column.name.delimiter ,
+ columns
+ columns.types
+ escape.delim \
+ serialization.lib
org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+ serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+#### A masked pattern was here ####
+ Partition
+ base file name: ds=2008-04-08
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format:
org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ partition values:
+ ds 2008-04-08
+ properties:
+ bucket_count 3
+ bucket_field_name key
+ column.name.delimiter ,
+ columns key,value
+ columns.comments
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.bucket_medium
+ numFiles 3
+ numRows 0
+ partition_columns ds
+ partition_columns.types string
+ rawDataSize 0
+ serialization.ddl struct bucket_medium { string key, string
value}
+ serialization.format 1
+ serialization.lib
org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ totalSize 170
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format:
org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ properties:
+ SORTBUCKETCOLSPREFIX TRUE
+ bucket_count 3
+ bucket_field_name key
+ column.name.delimiter ,
+ columns key,value
+ columns.comments
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.bucket_medium
+ partition_columns ds
+ partition_columns.types string
+ serialization.ddl struct bucket_medium { string key, string
value}
+ serialization.format 1
+ serialization.lib
org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.bucket_medium
+ name: default.bucket_medium
+ Truncated Path -> Alias:
+#### A masked pattern was here ####
+
+ Stage: Stage-3
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ GatherStats: false
+ Reduce Output Operator
+ null sort order:
+ sort order:
+ Statistics: Num rows: 1 Data size: 8 Basic stats: PARTIAL Column
stats: NONE
+ tag: -1
+ value expressions: _col0 (type: bigint)
+ auto parallelism: false
+ Path -> Alias:
+#### A masked pattern was here ####
+ Path -> Partition:
+#### A masked pattern was here ####
+ Partition
+ base file name: -mr-10005
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format:
org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ properties:
+ column.name.delimiter ,
+ columns _col0
+ columns.types bigint
+ escape.delim \
+ serialization.lib
org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+ serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format:
org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ properties:
+ column.name.delimiter ,
+ columns _col0
+ columns.types bigint
+ escape.delim \
+ serialization.lib
org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+ serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+ Truncated Path -> Alias:
+#### A masked pattern was here ####
Needs Tagging: false
Reduce Operator Tree:
Group By Operator
@@ -635,13 +861,1417 @@ STAGE PLANS:
GatherStats: false
MultiFileSpray: false
+ Stage: Stage-15
+ Map Reduce Local Work
+ Alias -> Map Local Tables:
+ $INTNAME
+ Fetch Operator
+ limit: -1
+ Alias -> Map Local Operator Tree:
+ $INTNAME
+ TableScan
+ GatherStats: false
+ HashTable Sink Operator
+ keys:
+ 0
+ 1
+ Position of Big Table: 1
+
+ Stage: Stage-8
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ alias: d
+ Statistics: Num rows: 1 Data size: 170 Basic stats: PARTIAL Column
stats: NONE
+ GatherStats: false
+ Select Operator
+ Statistics: Num rows: 1 Data size: 170 Basic stats: PARTIAL
Column stats: NONE
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0
+ 1
+ Position of Big Table: 1
+ Statistics: Num rows: 255 Data size: 69177 Basic stats:
PARTIAL Column stats: NONE
+ Group By Operator
+ aggregations: count()
+ mode: hash
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 8 Basic stats: PARTIAL
Column stats: NONE
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+#### A masked pattern was here ####
+ NumFilesPerFileSink: 1
+ table:
+ input format:
org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format:
org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ properties:
+ column.name.delimiter ,
+ columns _col0
+ columns.types bigint
+ escape.delim \
+ serialization.lib
org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+ serde:
org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+ TotalFiles: 1
+ GatherStats: false
+ MultiFileSpray: false
+ Local Work:
+ Map Reduce Local Work
+ Path -> Alias:
+#### A masked pattern was here ####
+ Path -> Partition:
+#### A masked pattern was here ####
+ Partition
+ base file name: -mr-10004
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format:
org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ properties:
+ column.name.delimiter ,
+ columns
+ columns.types
+ escape.delim \
+ serialization.lib
org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+ serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format:
org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ properties:
+ column.name.delimiter ,
+ columns
+ columns.types
+ escape.delim \
+ serialization.lib
org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+ serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+#### A masked pattern was here ####
+ Partition
+ base file name: ds=2008-04-08
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format:
org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ partition values:
+ ds 2008-04-08
+ properties:
+ bucket_count 3
+ bucket_field_name key
+ column.name.delimiter ,
+ columns key,value
+ columns.comments
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.bucket_medium
+ numFiles 3
+ numRows 0
+ partition_columns ds
+ partition_columns.types string
+ rawDataSize 0
+ serialization.ddl struct bucket_medium { string key, string
value}
+ serialization.format 1
+ serialization.lib
org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ totalSize 170
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format:
org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ properties:
+ SORTBUCKETCOLSPREFIX TRUE
+ bucket_count 3
+ bucket_field_name key
+ column.name.delimiter ,
+ columns key,value
+ columns.comments
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.bucket_medium
+ partition_columns ds
+ partition_columns.types string
+ serialization.ddl struct bucket_medium { string key, string
value}
+ serialization.format 1
+ serialization.lib
org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.bucket_medium
+ name: default.bucket_medium
+ Truncated Path -> Alias:
+ /bucket_medium/ds=2008-04-08 [$hdt$_3:d]
+
+ Stage: Stage-2
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ GatherStats: false
+ Reduce Output Operator
+ null sort order:
+ sort order:
+ Statistics: Num rows: 255 Data size: 25572 Basic stats: COMPLETE
Column stats: NONE
+ tag: 0
+ auto parallelism: false
+ TableScan
+ alias: d
+ Statistics: Num rows: 1 Data size: 170 Basic stats: PARTIAL Column
stats: NONE
+ GatherStats: false
+ Select Operator
+ Statistics: Num rows: 1 Data size: 170 Basic stats: PARTIAL
Column stats: NONE
+ Reduce Output Operator
+ null sort order:
+ sort order:
+ Statistics: Num rows: 1 Data size: 170 Basic stats: PARTIAL
Column stats: NONE
+ tag: 1
+ auto parallelism: false
+ Path -> Alias:
+#### A masked pattern was here ####
+ Path -> Partition:
+#### A masked pattern was here ####
+ Partition
+ base file name: -mr-10004
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format:
org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ properties:
+ column.name.delimiter ,
+ columns
+ columns.types
+ escape.delim \
+ serialization.lib
org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+ serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format:
org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ properties:
+ column.name.delimiter ,
+ columns
+ columns.types
+ escape.delim \
+ serialization.lib
org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+ serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+#### A masked pattern was here ####
+ Partition
+ base file name: ds=2008-04-08
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format:
org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ partition values:
+ ds 2008-04-08
+ properties:
+ bucket_count 3
+ bucket_field_name key
+ column.name.delimiter ,
+ columns key,value
+ columns.comments
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.bucket_medium
+ numFiles 3
+ numRows 0
+ partition_columns ds
+ partition_columns.types string
+ rawDataSize 0
+ serialization.ddl struct bucket_medium { string key, string
value}
+ serialization.format 1
+ serialization.lib
org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ totalSize 170
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format:
org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ properties:
+ SORTBUCKETCOLSPREFIX TRUE
+ bucket_count 3
+ bucket_field_name key
+ column.name.delimiter ,
+ columns key,value
+ columns.comments
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.bucket_medium
+ partition_columns ds
+ partition_columns.types string
+ serialization.ddl struct bucket_medium { string key, string
value}
+ serialization.format 1
+ serialization.lib
org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.bucket_medium
+ name: default.bucket_medium
+ Truncated Path -> Alias:
+ /bucket_medium/ds=2008-04-08 [$hdt$_3:d]
+#### A masked pattern was here ####
+ Needs Tagging: true
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0
+ 1
+ Statistics: Num rows: 255 Data size: 69177 Basic stats: PARTIAL
Column stats: NONE
+ Group By Operator
+ aggregations: count()
+ mode: hash
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 8 Basic stats: PARTIAL Column
stats: NONE
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+#### A masked pattern was here ####
+ NumFilesPerFileSink: 1
+ table:
+ input format:
org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format:
org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ properties:
+ column.name.delimiter ,
+ columns _col0
+ columns.types bigint
+ escape.delim \
+ serialization.lib
org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+ serde:
org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+ TotalFiles: 1
+ GatherStats: false
+ MultiFileSpray: false
+
+ Stage: Stage-17
+ Map Reduce Local Work
+ Alias -> Map Local Tables:
+ $hdt$_0:c
+ Fetch Operator
+ limit: -1
+ Partition Description:
+ Partition
+ base file name: ds=2008-04-08
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format:
org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ partition values:
+ ds 2008-04-08
+ properties:
+ bucket_count 4
+ bucket_field_name key
+ column.name.delimiter ,
+ columns key,value
+ columns.comments
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.bucket_big
+ numFiles 4
+ numRows 0
+ partition_columns ds
+ partition_columns.types string
+ rawDataSize 0
+ serialization.ddl struct bucket_big { string key, string
value}
+ serialization.format 1
+ serialization.lib
org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ totalSize 5812
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format:
org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ properties:
+ SORTBUCKETCOLSPREFIX TRUE
+ bucket_count 4
+ bucket_field_name key
+ column.name.delimiter ,
+ columns key,value
+ columns.comments
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.bucket_big
+ partition_columns ds
+ partition_columns.types string
+ serialization.ddl struct bucket_big { string key, string
value}
+ serialization.format 1
+ serialization.lib
org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.bucket_big
+ name: default.bucket_big
+ Partition
+ base file name: ds=2008-04-09
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format:
org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ partition values:
+ ds 2008-04-09
+ properties:
+ bucket_count 4
+ bucket_field_name key
+ column.name.delimiter ,
+ columns key,value
+ columns.comments
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.bucket_big
+ numFiles 4
+ numRows 0
+ partition_columns ds
+ partition_columns.types string
+ rawDataSize 0
+ serialization.ddl struct bucket_big { string key, string
value}
+ serialization.format 1
+ serialization.lib
org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ totalSize 5812
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format:
org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ properties:
+ SORTBUCKETCOLSPREFIX TRUE
+ bucket_count 4
+ bucket_field_name key
+ column.name.delimiter ,
+ columns key,value
+ columns.comments
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.bucket_big
+ partition_columns ds
+ partition_columns.types string
+ serialization.ddl struct bucket_big { string key, string
value}
+ serialization.format 1
+ serialization.lib
org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.bucket_big
+ name: default.bucket_big
+ $hdt$_1:a
+ Fetch Operator
+ limit: -1
+ Partition Description:
+ Partition
+ base file name: ds=2008-04-08
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format:
org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ partition values:
+ ds 2008-04-08
+ properties:
+ bucket_count 2
+ bucket_field_name key
+ column.name.delimiter ,
+ columns key,value
+ columns.comments
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.bucket_small
+ numFiles 2
+ numRows 0
+ partition_columns ds
+ partition_columns.types string
+ rawDataSize 0
+ serialization.ddl struct bucket_small { string key, string
value}
+ serialization.format 1
+ serialization.lib
org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ totalSize 114
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format:
org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ properties:
+ SORTBUCKETCOLSPREFIX TRUE
+ bucket_count 2
+ bucket_field_name key
+ column.name.delimiter ,
+ columns key,value
+ columns.comments
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.bucket_small
+ partition_columns ds
+ partition_columns.types string
+ serialization.ddl struct bucket_small { string key,
string value}
+ serialization.format 1
+ serialization.lib
org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.bucket_small
+ name: default.bucket_small
+ Alias -> Map Local Operator Tree:
+ $hdt$_0:c
+ TableScan
+ alias: c
+ Statistics: Num rows: 116 Data size: 11624 Basic stats: COMPLETE
Column stats: NONE
+ GatherStats: false
+ Filter Operator
+ isSamplingPred: false
+ predicate: key is not null (type: boolean)
+ Statistics: Num rows: 116 Data size: 11624 Basic stats: COMPLETE
Column stats: NONE
+ Select Operator
+ expressions: key (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 116 Data size: 11624 Basic stats:
COMPLETE Column stats: NONE
+ HashTable Sink Operator
+ keys:
+ 0 _col0 (type: string)
+ 1 _col0 (type: string)
+ 2 _col0 (type: string)
+ Position of Big Table: 1
+ $hdt$_1:a
+ TableScan
+ alias: a
+ Statistics: Num rows: 1 Data size: 114 Basic stats: COMPLETE
Column stats: NONE
+ GatherStats: false
+ Filter Operator
+ isSamplingPred: false
+ predicate: key is not null (type: boolean)
+ Statistics: Num rows: 1 Data size: 114 Basic stats: COMPLETE
Column stats: NONE
+ Select Operator
+ expressions: key (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 114 Basic stats: COMPLETE
Column stats: NONE
+ HashTable Sink Operator
+ keys:
+ 0 _col0 (type: string)
+ 1 _col0 (type: string)
+ 2 _col0 (type: string)
+ Position of Big Table: 1
+
+ Stage: Stage-11
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ alias: b
+ Statistics: Num rows: 1 Data size: 170 Basic stats: COMPLETE
Column stats: NONE
+ GatherStats: false
+ Filter Operator
+ isSamplingPred: false
+ predicate: key is not null (type: boolean)
+ Statistics: Num rows: 1 Data size: 170 Basic stats: COMPLETE
Column stats: NONE
+ Select Operator
+ expressions: key (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 170 Basic stats: COMPLETE
Column stats: NONE
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ Inner Join 1 to 2
+ keys:
+ 0 _col0 (type: string)
+ 1 _col0 (type: string)
+ 2 _col0 (type: string)
+ Position of Big Table: 1
+ Statistics: Num rows: 255 Data size: 25572 Basic stats:
COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+#### A masked pattern was here ####
+ NumFilesPerFileSink: 1
+ table:
+ input format:
org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format:
org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ properties:
+ column.name.delimiter ,
+ columns
+ columns.types
+ escape.delim \
+ serialization.lib
org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+ serde:
org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+ TotalFiles: 1
+ GatherStats: false
+ MultiFileSpray: false
+ Local Work:
+ Map Reduce Local Work
+ Path -> Alias:
+#### A masked pattern was here ####
+ Path -> Partition:
+#### A masked pattern was here ####
+ Partition
+ base file name: ds=2008-04-08
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format:
org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ partition values:
+ ds 2008-04-08
+ properties:
+ bucket_count 4
+ bucket_field_name key
+ column.name.delimiter ,
+ columns key,value
+ columns.comments
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.bucket_big
+ numFiles 4
+ numRows 0
+ partition_columns ds
+ partition_columns.types string
+ rawDataSize 0
+ serialization.ddl struct bucket_big { string key, string value}
+ serialization.format 1
+ serialization.lib
org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ totalSize 5812
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format:
org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ properties:
+ SORTBUCKETCOLSPREFIX TRUE
+ bucket_count 4
+ bucket_field_name key
+ column.name.delimiter ,
+ columns key,value
+ columns.comments
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.bucket_big
+ partition_columns ds
+ partition_columns.types string
+ serialization.ddl struct bucket_big { string key, string value}
+ serialization.format 1
+ serialization.lib
org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.bucket_big
+ name: default.bucket_big
+#### A masked pattern was here ####
+ Partition
+ base file name: ds=2008-04-09
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format:
org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ partition values:
+ ds 2008-04-09
+ properties:
+ bucket_count 4
+ bucket_field_name key
+ column.name.delimiter ,
+ columns key,value
+ columns.comments
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.bucket_big
+ numFiles 4
+ numRows 0
+ partition_columns ds
+ partition_columns.types string
+ rawDataSize 0
+ serialization.ddl struct bucket_big { string key, string value}
+ serialization.format 1
+ serialization.lib
org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ totalSize 5812
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format:
org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ properties:
+ SORTBUCKETCOLSPREFIX TRUE
+ bucket_count 4
+ bucket_field_name key
+ column.name.delimiter ,
+ columns key,value
+ columns.comments
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.bucket_big
+ partition_columns ds
+ partition_columns.types string
+ serialization.ddl struct bucket_big { string key, string value}
+ serialization.format 1
+ serialization.lib
org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.bucket_big
+ name: default.bucket_big
+#### A masked pattern was here ####
+ Partition
+ base file name: ds=2008-04-08
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format:
org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ partition values:
+ ds 2008-04-08
+ properties:
+ bucket_count 3
+ bucket_field_name key
+ column.name.delimiter ,
+ columns key,value
+ columns.comments
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.bucket_medium
+ numFiles 3
+ numRows 0
+ partition_columns ds
+ partition_columns.types string
+ rawDataSize 0
+ serialization.ddl struct bucket_medium { string key, string
value}
+ serialization.format 1
+ serialization.lib
org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ totalSize 170
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format:
org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ properties:
+ SORTBUCKETCOLSPREFIX TRUE
+ bucket_count 3
+ bucket_field_name key
+ column.name.delimiter ,
+ columns key,value
+ columns.comments
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.bucket_medium
+ partition_columns ds
+ partition_columns.types string
+ serialization.ddl struct bucket_medium { string key, string
value}
+ serialization.format 1
+ serialization.lib
org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.bucket_medium
+ name: default.bucket_medium
+#### A masked pattern was here ####
+ Partition
+ base file name: ds=2008-04-08
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format:
org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ partition values:
+ ds 2008-04-08
+ properties:
+ bucket_count 2
+ bucket_field_name key
+ column.name.delimiter ,
+ columns key,value
+ columns.comments
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.bucket_small
+ numFiles 2
+ numRows 0
+ partition_columns ds
+ partition_columns.types string
+ rawDataSize 0
+ serialization.ddl struct bucket_small { string key, string value}
+ serialization.format 1
+ serialization.lib
org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ totalSize 114
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format:
org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ properties:
+ SORTBUCKETCOLSPREFIX TRUE
+ bucket_count 2
+ bucket_field_name key
+ column.name.delimiter ,
+ columns key,value
+ columns.comments
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.bucket_small
+ partition_columns ds
+ partition_columns.types string
+ serialization.ddl struct bucket_small { string key, string
value}
+ serialization.format 1
+ serialization.lib
org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.bucket_small
+ name: default.bucket_small
+ Truncated Path -> Alias:
+ /bucket_medium/ds=2008-04-08 [$hdt$_2:b]
+
+ Stage: Stage-18
+ Map Reduce Local Work
+ Alias -> Map Local Tables:
+ $hdt$_1:a
+ Fetch Operator
+ limit: -1
+ Partition Description:
+ Partition
+ base file name: ds=2008-04-08
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format:
org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ partition values:
+ ds 2008-04-08
+ properties:
+ bucket_count 2
+ bucket_field_name key
+ column.name.delimiter ,
+ columns key,value
+ columns.comments
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.bucket_small
+ numFiles 2
+ numRows 0
+ partition_columns ds
+ partition_columns.types string
+ rawDataSize 0
+ serialization.ddl struct bucket_small { string key, string
value}
+ serialization.format 1
+ serialization.lib
org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ totalSize 114
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format:
org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ properties:
+ SORTBUCKETCOLSPREFIX TRUE
+ bucket_count 2
+ bucket_field_name key
+ column.name.delimiter ,
+ columns key,value
+ columns.comments
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.bucket_small
+ partition_columns ds
+ partition_columns.types string
+ serialization.ddl struct bucket_small { string key,
string value}
+ serialization.format 1
+ serialization.lib
org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.bucket_small
+ name: default.bucket_small
+ $hdt$_2:b
+ Fetch Operator
+ limit: -1
+ Partition Description:
+ Partition
+ base file name: ds=2008-04-08
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format:
org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ partition values:
+ ds 2008-04-08
+ properties:
+ bucket_count 3
+ bucket_field_name key
+ column.name.delimiter ,
+ columns key,value
+ columns.comments
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.bucket_medium
+ numFiles 3
+ numRows 0
+ partition_columns ds
+ partition_columns.types string
+ rawDataSize 0
+ serialization.ddl struct bucket_medium { string key,
string value}
+ serialization.format 1
+ serialization.lib
org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ totalSize 170
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format:
org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ properties:
+ SORTBUCKETCOLSPREFIX TRUE
+ bucket_count 3
+ bucket_field_name key
+ column.name.delimiter ,
+ columns key,value
+ columns.comments
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.bucket_medium
+ partition_columns ds
+ partition_columns.types string
+ serialization.ddl struct bucket_medium { string key,
string value}
+ serialization.format 1
+ serialization.lib
org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.bucket_medium
+ name: default.bucket_medium
+ Alias -> Map Local Operator Tree:
+ $hdt$_1:a
+ TableScan
+ alias: a
+ Statistics: Num rows: 1 Data size: 114 Basic stats: COMPLETE
Column stats: NONE
+ GatherStats: false
+ Filter Operator
+ isSamplingPred: false
+ predicate: key is not null (type: boolean)
+ Statistics: Num rows: 1 Data size: 114 Basic stats: COMPLETE
Column stats: NONE
+ Select Operator
+ expressions: key (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 114 Basic stats: COMPLETE
Column stats: NONE
+ HashTable Sink Operator
+ keys:
+ 0 _col0 (type: string)
+ 1 _col0 (type: string)
+ 2 _col0 (type: string)
+ Position of Big Table: 2
+ $hdt$_2:b
+ TableScan
+ alias: b
+ Statistics: Num rows: 1 Data size: 170 Basic stats: COMPLETE
Column stats: NONE
+ GatherStats: false
+ Filter Operator
+ isSamplingPred: false
+ predicate: key is not null (type: boolean)
+ Statistics: Num rows: 1 Data size: 170 Basic stats: COMPLETE
Column stats: NONE
+ Select Operator
+ expressions: key (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 170 Basic stats: COMPLETE
Column stats: NONE
+ HashTable Sink Operator
+ keys:
+ 0 _col0 (type: string)
+ 1 _col0 (type: string)
+ 2 _col0 (type: string)
+ Position of Big Table: 2
+
+ Stage: Stage-12
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ alias: c
+ Statistics: Num rows: 116 Data size: 11624 Basic stats: COMPLETE
Column stats: NONE
+ GatherStats: false
+ Filter Operator
+ isSamplingPred: false
+ predicate: key is not null (type: boolean)
+ Statistics: Num rows: 116 Data size: 11624 Basic stats: COMPLETE
Column stats: NONE
+ Select Operator
+ expressions: key (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 116 Data size: 11624 Basic stats:
COMPLETE Column stats: NONE
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ Inner Join 1 to 2
+ keys:
+ 0 _col0 (type: string)
+ 1 _col0 (type: string)
+ 2 _col0 (type: string)
+ Position of Big Table: 2
+ Statistics: Num rows: 255 Data size: 25572 Basic stats:
COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+#### A masked pattern was here ####
+ NumFilesPerFileSink: 1
+ table:
+ input format:
org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format:
org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ properties:
+ column.name.delimiter ,
+ columns
+ columns.types
+ escape.delim \
+ serialization.lib
org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+ serde:
org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+ TotalFiles: 1
+ GatherStats: false
+ MultiFileSpray: false
+ Local Work:
+ Map Reduce Local Work
+ Path -> Alias:
+#### A masked pattern was here ####
+ Path -> Partition:
+#### A masked pattern was here ####
+ Partition
+ base file name: ds=2008-04-08
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format:
org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ partition values:
+ ds 2008-04-08
+ properties:
+ bucket_count 4
+ bucket_field_name key
+ column.name.delimiter ,
+ columns key,value
+ columns.comments
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.bucket_big
+ numFiles 4
+ numRows 0
+ partition_columns ds
+ partition_columns.types string
+ rawDataSize 0
+ serialization.ddl struct bucket_big { string key, string value}
+ serialization.format 1
+ serialization.lib
org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ totalSize 5812
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format:
org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ properties:
+ SORTBUCKETCOLSPREFIX TRUE
+ bucket_count 4
+ bucket_field_name key
+ column.name.delimiter ,
+ columns key,value
+ columns.comments
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.bucket_big
+ partition_columns ds
+ partition_columns.types string
+ serialization.ddl struct bucket_big { string key, string value}
+ serialization.format 1
+ serialization.lib
org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.bucket_big
+ name: default.bucket_big
+#### A masked pattern was here ####
+ Partition
+ base file name: ds=2008-04-09
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format:
org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ partition values:
+ ds 2008-04-09
+ properties:
+ bucket_count 4
+ bucket_field_name key
+ column.name.delimiter ,
+ columns key,value
+ columns.comments
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.bucket_big
+ numFiles 4
+ numRows 0
+ partition_columns ds
+ partition_columns.types string
+ rawDataSize 0
+ serialization.ddl struct bucket_big { string key, string value}
+ serialization.format 1
+ serialization.lib
org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ totalSize 5812
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format:
org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ properties:
+ SORTBUCKETCOLSPREFIX TRUE
+ bucket_count 4
+ bucket_field_name key
+ column.name.delimiter ,
+ columns key,value
+ columns.comments
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.bucket_big
+ partition_columns ds
+ partition_columns.types string
+ serialization.ddl struct bucket_big { string key, string value}
+ serialization.format 1
+ serialization.lib
org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.bucket_big
+ name: default.bucket_big
+#### A masked pattern was here ####
+ Partition
+ base file name: ds=2008-04-08
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format:
org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ partition values:
+ ds 2008-04-08
+ properties:
+ bucket_count 3
+ bucket_field_name key
+ column.name.delimiter ,
+ columns key,value
+ columns.comments
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.bucket_medium
+ numFiles 3
+ numRows 0
+ partition_columns ds
+ partition_columns.types string
+ rawDataSize 0
+ serialization.ddl struct bucket_medium { string key, string
value}
+ serialization.format 1
+ serialization.lib
org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ totalSize 170
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format:
org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ properties:
+ SORTBUCKETCOLSPREFIX TRUE
+ bucket_count 3
+ bucket_field_name key
+ column.name.delimiter ,
+ columns key,value
+ columns.comments
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.bucket_medium
+ partition_columns ds
+ partition_columns.types string
+ serialization.ddl struct bucket_medium { string key, string
value}
+ serialization.format 1
+ serialization.lib
org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.bucket_medium
+ name: default.bucket_medium
+#### A masked pattern was here ####
+ Partition
+ base file name: ds=2008-04-08
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format:
org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ partition values:
+ ds 2008-04-08
+ properties:
+ bucket_count 2
+ bucket_field_name key
+ column.name.delimiter ,
+ columns key,value
+ columns.comments
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.bucket_small
+ numFiles 2
+ numRows 0
+ partition_columns ds
+ partition_columns.types string
+ rawDataSize 0
+ serialization.ddl struct bucket_small { string key, string value}
+ serialization.format 1
+ serialization.lib
org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ totalSize 114
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format:
org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ properties:
+ SORTBUCKETCOLSPREFIX TRUE
+ bucket_count 2
+ bucket_field_name key
+ column.name.delimiter ,
+ columns key,value
+ columns.comments
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.bucket_small
+ partition_columns ds
+ partition_columns.types string
+ serialization.ddl struct bucket_small { string key, string
value}
+ serialization.format 1
+ serialization.lib
org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.bucket_small
+ name: default.bucket_small
+ Truncated Path -> Alias:
+ /bucket_big/ds=2008-04-08 [$hdt$_0:c]
+ /bucket_big/ds=2008-04-09 [$hdt$_0:c]
+
+ Stage: Stage-1
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ alias: a
+ Statistics: Num rows: 1 Data size: 114 Basic stats: COMPLETE
Column stats: NONE
+ GatherStats: false
+ Filter Operator
+ isSamplingPred: false
+ predicate: key is not null (type: boolean)
+ Statistics: Num rows: 1 Data size: 114 Basic stats: COMPLETE
Column stats: NONE
+ Select Operator
+ expressions: key (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 114 Basic stats: COMPLETE
Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ null sort order: a
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 1 Data size: 114 Basic stats: COMPLETE
Column stats: NONE
+ tag: 0
+ auto parallelism: false
+ TableScan
+ alias: b
+ Statistics: Num rows: 1 Data size: 170 Basic stats: COMPLETE
Column stats: NONE
+ GatherStats: false
+ Filter Operator
+ isSamplingPred: false
+ predicate: key is not null (type: boolean)
+ Statistics: Num rows: 1 Data size: 170 Basic stats: COMPLETE
Column stats: NONE
+ Select Operator
+ expressions: key (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 170 Basic stats: COMPLETE
Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ null sort order: a
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 1 Data size: 170 Basic stats: COMPLETE
Column stats: NONE
+ tag: 1
+ auto parallelism: false
+ TableScan
+ alias: c
+ Statistics: Num rows: 116 Data size: 11624 Basic stats: COMPLETE
Column stats: NONE
+ GatherStats: false
+ Filter Operator
+ isSamplingPred: false
+ predicate: key is not null (type: boolean)
+ Statistics: Num rows: 116 Data size: 11624 Basic stats: COMPLETE
Column stats: NONE
+ Select Operator
+ expressions: key (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 116 Data size: 11624 Basic stats:
COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ null sort order: a
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 116 Data size: 11624 Basic stats:
COMPLETE Column stats: NONE
+ tag: 2
+ auto parallelism: false
+ Path -> Alias:
+#### A masked pattern was here ####
+ Path -> Partition:
+#### A masked pattern was here ####
+ Partition
+ base file name: ds=2008-04-08
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format:
org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ partition values:
+ ds 2008-04-08
+ properties:
+ bucket_count 4
+ bucket_field_name key
+ column.name.delimiter ,
+ columns key,value
+ columns.comments
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.bucket_big
+ numFiles 4
+ numRows 0
+ partition_columns ds
+ partition_columns.types string
+ rawDataSize 0
+ serialization.ddl struct bucket_big { string key, string value}
+ serialization.format 1
+ serialization.lib
org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ totalSize 5812
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format:
org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ properties:
+ SORTBUCKETCOLSPREFIX TRUE
+ bucket_count 4
+ bucket_field_name key
+ column.name.delimiter ,
+ columns key,value
+ columns.comments
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.bucket_big
+ partition_columns ds
+ partition_columns.types string
+ serialization.ddl struct bucket_big { string key, string value}
+ serialization.format 1
+ serialization.lib
org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.bucket_big
+ name: default.bucket_big
+#### A masked pattern was here ####
+ Partition
+ base file name: ds=2008-04-09
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format:
org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ partition values:
+ ds 2008-04-09
+ properties:
+ bucket_count 4
+ bucket_field_name key
+ column.name.delimiter ,
+ columns key,value
+ columns.comments
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.bucket_big
+ numFiles 4
+ numRows 0
+ partition_columns ds
+ partition_columns.types string
+ rawDataSize 0
+ serialization.ddl struct bucket_big { string key, string value}
+ serialization.format 1
+ serialization.lib
org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ totalSize 5812
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format:
org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ properties:
+ SORTBUCKETCOLSPREFIX TRUE
+ bucket_count 4
+ bucket_field_name key
+ column.name.delimiter ,
+ columns key,value
+ columns.comments
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.bucket_big
+ partition_columns ds
+ partition_columns.types string
+ serialization.ddl struct bucket_big { string key, string value}
+ serialization.format 1
+ serialization.lib
org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.bucket_big
+ name: default.bucket_big
+#### A masked pattern was here ####
+ Partition
+ base file name: ds=2008-04-08
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format:
org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ partition values:
+ ds 2008-04-08
+ properties:
+ bucket_count 3
+ bucket_field_name key
+ column.name.delimiter ,
+ columns key,value
+ columns.comments
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.bucket_medium
+ numFiles 3
+ numRows 0
+ partition_columns ds
+ partition_columns.types string
+ rawDataSize 0
+ serialization.ddl struct bucket_medium { string key, string
value}
+ serialization.format 1
+ serialization.lib
org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ totalSize 170
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format:
org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ properties:
+ SORTBUCKETCOLSPREFIX TRUE
+ bucket_count 3
+ bucket_field_name key
+ column.name.delimiter ,
+ columns key,value
+ columns.comments
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.bucket_medium
+ partition_columns ds
+ partition_columns.types string
+ serialization.ddl struct bucket_medium { string key, string
value}
+ serialization.format 1
+ serialization.lib
org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.bucket_medium
+ name: default.bucket_medium
+#### A masked pattern was here ####
+ Partition
+ base file name: ds=2008-04-08
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format:
org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ partition values:
+ ds 2008-04-08
+ properties:
+ bucket_count 2
+ bucket_field_name key
+ column.name.delimiter ,
+ columns key,value
+ columns.comments
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.bucket_small
+ numFiles 2
+ numRows 0
+ partition_columns ds
+ partition_columns.types string
+ rawDataSize 0
+ serialization.ddl struct bucket_small { string key, string value}
+ serialization.format 1
+ serialization.lib
org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ totalSize 114
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format:
org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ properties:
+ SORTBUCKETCOLSPREFIX TRUE
+ bucket_count 2
+ bucket_field_name key
+ column.name.delimiter ,
+ columns key,value
+ columns.comments
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.bucket_small
+ partition_columns ds
+ partition_columns.types string
+ serialization.ddl struct bucket_small { string key, string
value}
+ serialization.format 1
+ serialization.lib
org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.bucket_small
+ name: default.bucket_small
+ Truncated Path -> Alias:
+ /bucket_big/ds=2008-04-08 [$hdt$_0:c]
+ /bucket_big/ds=2008-04-09 [$hdt$_0:c]
+ /bucket_medium/ds=2008-04-08 [$hdt$_2:b]
+ /bucket_small/ds=2008-04-08 [$hdt$_1:a]
+ Needs Tagging: true
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ Inner Join 1 to 2
+ keys:
+ 0 _col0 (type: string)
+ 1 _col0 (type: string)
+ 2 _col0 (type: string)
+ Statistics: Num rows: 255 Data size: 25572 Basic stats: COMPLETE
Column stats: NONE
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+#### A masked pattern was here ####
+ NumFilesPerFileSink: 1
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format:
org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ properties:
+ column.name.delimiter ,
+ columns
+ columns.types
+ escape.delim \
+ serialization.lib
org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+ serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+ TotalFiles: 1
+ GatherStats: false
+ MultiFileSpray: false
+
Stage: Stage-0
Fetch Operator
limit: -1
Processor Tree:
ListSink
-Warning: Map Join MAPJOIN[31][bigTable=?] in task 'Stage-3:MAPRED' is a cross
product
+Warning: Map Join MAPJOIN[32][bigTable=?] in task 'Stage-8:MAPRED' is a cross
product
+Warning: Map Join MAPJOIN[31][bigTable=?] in task 'Stage-7:MAPRED' is a cross
product
+Warning: Shuffle Join JOIN[17][tables = [$hdt$_1, $hdt$_2, $hdt$_0, $hdt$_3]]
in Stage 'Stage-2:MAPRED' is a cross product
PREHOOK: query: select count(*) FROM bucket_small a JOIN bucket_medium b ON
a.key = b.key JOIN bucket_big c ON c.key = b.key JOIN bucket_medium d ON c.key
= b.key
PREHOOK: type: QUERY
PREHOOK: Input: default@bucket_big
