You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@hive.apache.org by yc...@apache.org on 2018/12/06 14:36:06 UTC
[5/9] hive git commit: HIVE-20915: Make dynamic sort partition
optimization available to HoS and MR (Yongzhi Chen, reviewed by Naveen Gangam)
http://git-wip-us.apache.org/repos/asf/hive/blob/9f2e8e61/ql/src/test/results/clientpositive/load_dyn_part8.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/load_dyn_part8.q.out b/ql/src/test/results/clientpositive/load_dyn_part8.q.out
index 97b8886..1037a33 100644
--- a/ql/src/test/results/clientpositive/load_dyn_part8.q.out
+++ b/ql/src/test/results/clientpositive/load_dyn_part8.q.out
@@ -59,9 +59,9 @@ STAGE DEPENDENCIES:
Stage-2 is a root stage
Stage-0 depends on stages: Stage-2
Stage-3 depends on stages: Stage-0
- Stage-1 depends on stages: Stage-2
- Stage-4 depends on stages: Stage-1, Stage-5
- Stage-5 depends on stages: Stage-2
+ Stage-4 depends on stages: Stage-2
+ Stage-1 depends on stages: Stage-4
+ Stage-5 depends on stages: Stage-1
STAGE PLANS:
Stage: Stage-2
@@ -79,54 +79,14 @@ STAGE PLANS:
expressions: key (type: string), value (type: string), ds (type: string), hr (type: string)
outputColumnNames: _col0, _col1, _col2, _col3
Statistics: Num rows: 666 Data size: 7075 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- GlobalTableId: 1
-#### A masked pattern was here ####
- NumFilesPerFileSink: 1
- Statistics: Num rows: 666 Data size: 7075 Basic stats: COMPLETE Column stats: NONE
-#### A masked pattern was here ####
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- bucket_count -1
- column.name.delimiter ,
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.nzhang_part8_n0
- partition_columns ds/hr
- partition_columns.types string:string
- serialization.ddl struct nzhang_part8_n0 { 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.nzhang_part8_n0
- TotalFiles: 1
- GatherStats: true
- MultiFileSpray: false
- Select Operator
- expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string)
- outputColumnNames: key, value, ds, hr
- Statistics: Num rows: 666 Data size: 7075 Basic stats: COMPLETE Column stats: NONE
- Group By Operator
- aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll')
- keys: ds (type: string), hr (type: string)
- mode: hash
- outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 666 Data size: 7075 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: string), _col1 (type: string)
- null sort order: aa
- sort order: ++
- Map-reduce partition columns: _col0 (type: string), _col1 (type: string)
- Statistics: Num rows: 666 Data size: 7075 Basic stats: COMPLETE Column stats: NONE
- tag: -1
- value expressions: _col2 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col3 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>)
- auto parallelism: false
+ Reduce Output Operator
+ key expressions: _col2 (type: string), _col3 (type: string)
+ null sort order: aa
+ sort order: ++
+ Map-reduce partition columns: _col2 (type: string), _col3 (type: string)
+ tag: -1
+ value expressions: _col0 (type: string), _col1 (type: string)
+ auto parallelism: false
Filter Operator
isSamplingPred: false
predicate: (ds > '2008-04-08') (type: boolean)
@@ -137,62 +97,23 @@ STAGE PLANS:
Statistics: Num rows: 666 Data size: 7075 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
- GlobalTableId: 2
+ GlobalTableId: 0
#### A masked pattern was here ####
NumFilesPerFileSink: 1
- Static Partition Specification: ds=2008-12-31/
- Statistics: Num rows: 666 Data size: 7075 Basic stats: COMPLETE Column stats: NONE
-#### A masked pattern was here ####
table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
properties:
- bucket_count -1
column.name.delimiter ,
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.nzhang_part8_n0
- partition_columns ds/hr
- partition_columns.types string:string
- serialization.ddl struct nzhang_part8_n0 { 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.nzhang_part8_n0
+ columns _col0,_col1,_col2
+ columns.types string,string,string
+ escape.delim \
+ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+ serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
TotalFiles: 1
- GatherStats: true
+ GatherStats: false
MultiFileSpray: false
- Select Operator
- expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string)
- outputColumnNames: key, value, hr
- Statistics: Num rows: 666 Data size: 7075 Basic stats: COMPLETE Column stats: NONE
- Group By Operator
- aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll')
- keys: '2008-12-31' (type: string), hr (type: string)
- mode: hash
- outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 666 Data size: 7075 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 _col0,_col1,_col2,_col3
- columns.types string,string,struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>,struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>
- 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
+ Execution mode: vectorized
Path -> Alias:
#### A masked pattern was here ####
Path -> Partition:
@@ -399,38 +320,39 @@ STAGE PLANS:
/srcpart/ds=2008-04-09/hr=12 [srcpart]
Needs Tagging: false
Reduce Operator Tree:
- Group By Operator
- aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1)
- keys: KEY._col0 (type: string), KEY._col1 (type: string)
- mode: mergepartial
+ Select Operator
+ expressions: VALUE._col0 (type: string), VALUE._col1 (type: string), KEY._col2 (type: string), KEY._col3 (type: string)
outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col2 (type: struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col3 (type: struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col0 (type: string), _col1 (type: string)
- outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- GlobalTableId: 0
+ File Output Operator
+ compressed: false
+ GlobalTableId: 1
+#### A masked pattern was here ####
+ Dp Sort State: PARTITION_SORTED
+ NumFilesPerFileSink: 1
+ Statistics: Num rows: 666 Data size: 7075 Basic stats: COMPLETE Column stats: NONE
+#### A masked pattern was here ####
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ properties:
+ bucket_count -1
+ column.name.delimiter ,
+ columns key,value
+ columns.comments 'default','default'
+ columns.types string:string
#### A masked pattern was here ####
- NumFilesPerFileSink: 1
- Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE
+ name default.nzhang_part8_n0
+ partition_columns ds/hr
+ partition_columns.types string:string
+ serialization.ddl struct nzhang_part8_n0 { string key, string value}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
#### A masked pattern was here ####
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- properties:
- columns _col0,_col1,_col2,_col3
- columns.types struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>:struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>:string:string
- escape.delim \
- hive.serialization.extend.additional.nesting.levels true
- serialization.escape.crlf true
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- TotalFiles: 1
- GatherStats: false
- MultiFileSpray: false
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.nzhang_part8_n0
+ TotalFiles: 1
+ GatherStats: true
+ MultiFileSpray: false
Stage: Stage-0
Move Operator
@@ -465,57 +387,18 @@ STAGE PLANS:
Basic Stats Work:
#### A masked pattern was here ####
- Stage: Stage-1
- Move Operator
- tables:
- partition:
- ds 2008-12-31
- hr
- replace: true
-#### A masked pattern was here ####
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- bucket_count -1
- column.name.delimiter ,
- columns key,value
- columns.comments 'default','default'
- columns.types string:string
-#### A masked pattern was here ####
- name default.nzhang_part8_n0
- partition_columns ds/hr
- partition_columns.types string:string
- serialization.ddl struct nzhang_part8_n0 { 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.nzhang_part8_n0
-
Stage: Stage-4
- Stats Work
- Basic Stats Work:
-#### A masked pattern was here ####
- Column Stats Desc:
- Columns: key, value
- Column Types: string, string
- Table: default.nzhang_part8_n0
- Is Table Level Stats: false
-
- Stage: Stage-5
Map Reduce
Map Operator Tree:
TableScan
GatherStats: false
Reduce Output Operator
- key expressions: '2008-12-31' (type: string), _col1 (type: string)
- null sort order: aa
- sort order: ++
- Map-reduce partition columns: '2008-12-31' (type: string), _col1 (type: string)
- Statistics: Num rows: 666 Data size: 7075 Basic stats: COMPLETE Column stats: NONE
+ key expressions: _col2 (type: string)
+ null sort order: a
+ sort order: +
+ Map-reduce partition columns: _col2 (type: string)
tag: -1
- value expressions: _col2 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col3 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>)
+ value expressions: _col0 (type: string), _col1 (type: string)
auto parallelism: false
Execution mode: vectorized
Path -> Alias:
@@ -528,8 +411,8 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
properties:
column.name.delimiter ,
- columns _col0,_col1,_col2,_col3
- columns.types string,string,struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>,struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>
+ columns _col0,_col1,_col2
+ columns.types string,string,string
escape.delim \
serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
@@ -538,8 +421,8 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
properties:
column.name.delimiter ,
- columns _col0,_col1,_col2,_col3
- columns.types string,string,struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>,struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>
+ columns _col0,_col1,_col2
+ columns.types string,string,string
escape.delim \
serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
@@ -547,38 +430,78 @@ STAGE PLANS:
#### A masked pattern was here ####
Needs Tagging: false
Reduce Operator Tree:
- Group By Operator
- aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1)
- keys: '2008-12-31' (type: string), KEY._col1 (type: string)
- mode: mergepartial
- outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col2 (type: struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col3 (type: struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), '2008-12-31' (type: string), _col1 (type: string)
- outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- GlobalTableId: 0
+ Select Operator
+ expressions: VALUE._col0 (type: string), VALUE._col1 (type: string), KEY._col2 (type: string)
+ outputColumnNames: _col0, _col1, _col2
+ File Output Operator
+ compressed: false
+ GlobalTableId: 2
+#### A masked pattern was here ####
+ Dp Sort State: PARTITION_SORTED
+ NumFilesPerFileSink: 1
+ Static Partition Specification: ds=2008-12-31/
+ Statistics: Num rows: 666 Data size: 7075 Basic stats: COMPLETE Column stats: NONE
#### A masked pattern was here ####
- NumFilesPerFileSink: 1
- Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ properties:
+ bucket_count -1
+ column.name.delimiter ,
+ columns key,value
+ columns.comments 'default','default'
+ columns.types string:string
#### A masked pattern was here ####
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- properties:
- columns _col0,_col1,_col2,_col3
- columns.types struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>:struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>:string:string
- escape.delim \
- hive.serialization.extend.additional.nesting.levels true
- serialization.escape.crlf true
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- TotalFiles: 1
- GatherStats: false
- MultiFileSpray: false
+ name default.nzhang_part8_n0
+ partition_columns ds/hr
+ partition_columns.types string:string
+ serialization.ddl struct nzhang_part8_n0 { 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.nzhang_part8_n0
+ TotalFiles: 1
+ GatherStats: true
+ MultiFileSpray: false
+
+ Stage: Stage-1
+ Move Operator
+ tables:
+ partition:
+ ds 2008-12-31
+ hr
+ replace: true
+#### A masked pattern was here ####
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ properties:
+ bucket_count -1
+ column.name.delimiter ,
+ columns key,value
+ columns.comments 'default','default'
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.nzhang_part8_n0
+ partition_columns ds/hr
+ partition_columns.types string:string
+ serialization.ddl struct nzhang_part8_n0 { 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.nzhang_part8_n0
+
+ Stage: Stage-5
+ Stats Work
+ Basic Stats Work:
+#### A masked pattern was here ####
+ Column Stats Desc:
+ Columns: key, value
+ Column Types: string, string
+ Table: default.nzhang_part8_n0
+ Is Table Level Stats: false
PREHOOK: query: from srcpart
insert overwrite table nzhang_part8_n0 partition (ds, hr) select key, value, ds, hr where ds <= '2008-04-08'
http://git-wip-us.apache.org/repos/asf/hive/blob/9f2e8e61/ql/src/test/results/clientpositive/load_dyn_part9.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/load_dyn_part9.q.out b/ql/src/test/results/clientpositive/load_dyn_part9.q.out
index 34b1f26..4e272bb 100644
--- a/ql/src/test/results/clientpositive/load_dyn_part9.q.out
+++ b/ql/src/test/results/clientpositive/load_dyn_part9.q.out
@@ -65,48 +65,25 @@ STAGE PLANS:
expressions: key (type: string), value (type: string), ds (type: string), hr (type: string)
outputColumnNames: _col0, _col1, _col2, _col3
Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.nzhang_part9
- Select Operator
- expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string)
- outputColumnNames: key, value, ds, hr
- Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
- Group By Operator
- aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll')
- keys: ds (type: string), hr (type: string)
- mode: hash
- outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: string), _col1 (type: string)
- sort order: ++
- Map-reduce partition columns: _col0 (type: string), _col1 (type: string)
- Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col2 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col3 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>)
+ Reduce Output Operator
+ key expressions: _col2 (type: string), _col3 (type: string)
+ sort order: ++
+ Map-reduce partition columns: _col2 (type: string), _col3 (type: string)
+ value expressions: _col0 (type: string), _col1 (type: string)
+ Execution mode: vectorized
Reduce Operator Tree:
- Group By Operator
- aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1)
- keys: KEY._col0 (type: string), KEY._col1 (type: string)
- mode: mergepartial
+ Select Operator
+ expressions: VALUE._col0 (type: string), VALUE._col1 (type: string), KEY._col2 (type: string), KEY._col3 (type: string)
outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col2 (type: struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col3 (type: struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col0 (type: string), _col1 (type: string)
- outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- 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
+ File Output Operator
+ compressed: false
+ Dp Sort State: PARTITION_SORTED
+ Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.nzhang_part9
Stage: Stage-0
Move Operator
http://git-wip-us.apache.org/repos/asf/hive/blob/9f2e8e61/ql/src/test/results/clientpositive/merge3.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/merge3.q.out b/ql/src/test/results/clientpositive/merge3.q.out
index 5a4747a..0b4da94 100644
--- a/ql/src/test/results/clientpositive/merge3.q.out
+++ b/ql/src/test/results/clientpositive/merge3.q.out
@@ -2415,54 +2415,15 @@ STAGE PLANS:
expressions: key (type: string), value (type: string), ds (type: string)
outputColumnNames: _col0, _col1, _col2
Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- GlobalTableId: 1
-#### A masked pattern was here ####
- NumFilesPerFileSink: 1
- Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE
-#### A masked pattern was here ####
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- bucket_count -1
- column.name.delimiter ,
- columns key,value
- columns.comments
- columns.types string:string
-#### A masked pattern was here ####
- name default.merge_src_part2
- partition_columns ds
- partition_columns.types string
- serialization.ddl struct merge_src_part2 { 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.merge_src_part2
- TotalFiles: 1
- GatherStats: true
- MultiFileSpray: false
- Select Operator
- expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string)
- outputColumnNames: key, value, ds
- Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE
- Group By Operator
- aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll')
- keys: ds (type: string)
- mode: hash
- outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 2000 Data size: 21248 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: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE
- tag: -1
- value expressions: _col1 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col2 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>)
- auto parallelism: false
+ Reduce Output Operator
+ key expressions: _col2 (type: string)
+ null sort order: a
+ sort order: +
+ Map-reduce partition columns: _col2 (type: string)
+ tag: -1
+ value expressions: _col0 (type: string), _col1 (type: string)
+ auto parallelism: false
+ Execution mode: vectorized
Path -> Alias:
#### A masked pattern was here ####
Path -> Partition:
@@ -2482,7 +2443,7 @@ STAGE PLANS:
columns.types string:string
#### A masked pattern was here ####
name default.merge_src_part
- numFiles 2
+ numFiles 1
numRows 1000
partition_columns ds
partition_columns.types string
@@ -2530,7 +2491,7 @@ STAGE PLANS:
columns.types string:string
#### A masked pattern was here ####
name default.merge_src_part
- numFiles 2
+ numFiles 1
numRows 1000
partition_columns ds
partition_columns.types string
@@ -2567,38 +2528,39 @@ STAGE PLANS:
/merge_src_part/ds=2008-04-09 [merge_src_part]
Needs Tagging: false
Reduce Operator Tree:
- Group By Operator
- aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1)
- keys: KEY._col0 (type: string)
- mode: mergepartial
+ Select Operator
+ expressions: VALUE._col0 (type: string), VALUE._col1 (type: string), KEY._col2 (type: string)
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col1 (type: struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col2 (type: struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col0 (type: string)
- outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- GlobalTableId: 0
+ File Output Operator
+ compressed: false
+ GlobalTableId: 1
#### A masked pattern was here ####
- NumFilesPerFileSink: 1
- Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
+ Dp Sort State: PARTITION_SORTED
+ NumFilesPerFileSink: 1
+ Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE
#### A masked pattern was here ####
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- properties:
- columns _col0,_col1,_col2
- columns.types struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>:struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>:string
- escape.delim \
- hive.serialization.extend.additional.nesting.levels true
- serialization.escape.crlf true
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- TotalFiles: 1
- GatherStats: false
- MultiFileSpray: false
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ properties:
+ bucket_count -1
+ column.name.delimiter ,
+ columns key,value
+ columns.comments
+ columns.types string:string
+#### A masked pattern was here ####
+ name default.merge_src_part2
+ partition_columns ds
+ partition_columns.types string
+ serialization.ddl struct merge_src_part2 { 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.merge_src_part2
+ TotalFiles: 1
+ GatherStats: true
+ MultiFileSpray: false
Stage: Stage-7
Conditional Operator
@@ -4907,12 +4869,11 @@ STAGE PLANS:
Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col2 (type: string)
- null sort order: a
- sort order: +
+ null sort order: aa
+ sort order: ++
Map-reduce partition columns: _col2 (type: string)
- Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE
tag: -1
- value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string)
+ value expressions: _col0 (type: string), _col1 (type: string)
auto parallelism: false
Execution mode: vectorized
Path -> Alias:
@@ -4934,7 +4895,7 @@ STAGE PLANS:
columns.types string:string
#### A masked pattern was here ####
name default.merge_src_part
- numFiles 2
+ numFiles 1
numRows 1000
partition_columns ds
partition_columns.types string
@@ -4982,7 +4943,7 @@ STAGE PLANS:
columns.types string:string
#### A masked pattern was here ####
name default.merge_src_part
- numFiles 2
+ numFiles 1
numRows 1000
partition_columns ds
partition_columns.types string
@@ -5020,13 +4981,13 @@ STAGE PLANS:
Needs Tagging: false
Reduce Operator Tree:
Select Operator
- expressions: VALUE._col0 (type: string), VALUE._col1 (type: string), VALUE._col2 (type: string)
+ expressions: VALUE._col0 (type: string), VALUE._col1 (type: string), KEY._col2 (type: string)
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
GlobalTableId: 1
#### A masked pattern was here ####
+ Dp Sort State: PARTITION_SORTED
NumFilesPerFileSink: 1
Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE
#### A masked pattern was here ####
@@ -5052,42 +5013,6 @@ STAGE PLANS:
TotalFiles: 1
GatherStats: true
MultiFileSpray: false
- Select Operator
- expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string)
- outputColumnNames: key, value, ds
- Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE
- Group By Operator
- aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll')
- keys: ds (type: string)
- mode: complete
- outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col1 (type: struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col2 (type: struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col0 (type: string)
- outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- GlobalTableId: 0
-#### A masked pattern was here ####
- NumFilesPerFileSink: 1
- Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
-#### A masked pattern was here ####
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- properties:
- columns _col0,_col1,_col2
- columns.types struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>:struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>:string
- escape.delim \
- hive.serialization.extend.additional.nesting.levels true
- serialization.escape.crlf true
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- TotalFiles: 1
- GatherStats: false
- MultiFileSpray: false
Stage: Stage-7
Conditional Operator
http://git-wip-us.apache.org/repos/asf/hive/blob/9f2e8e61/ql/src/test/results/clientpositive/merge4.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/merge4.q.out b/ql/src/test/results/clientpositive/merge4.q.out
index 78561ce..fcc557a 100644
--- a/ql/src/test/results/clientpositive/merge4.q.out
+++ b/ql/src/test/results/clientpositive/merge4.q.out
@@ -41,48 +41,25 @@ STAGE PLANS:
expressions: key (type: string), value (type: string), hr (type: string)
outputColumnNames: _col0, _col1, _col2
Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.nzhang_part
- Select Operator
- expressions: _col0 (type: string), _col1 (type: string), '2010-08-15' (type: string), _col2 (type: string)
- outputColumnNames: key, value, ds, hr
- Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
- Group By Operator
- aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll')
- keys: ds (type: string), hr (type: string)
- mode: hash
- outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: string), _col1 (type: string)
- sort order: ++
- Map-reduce partition columns: _col0 (type: string), _col1 (type: string)
- Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col2 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col3 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>)
+ Reduce Output Operator
+ key expressions: _col2 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col2 (type: string)
+ value expressions: _col0 (type: string), _col1 (type: string)
+ Execution mode: vectorized
Reduce Operator Tree:
- Group By Operator
- aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1)
- keys: KEY._col0 (type: string), KEY._col1 (type: string)
- mode: mergepartial
- outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col2 (type: struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col3 (type: struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col0 (type: string), _col1 (type: string)
- outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- 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
+ Select Operator
+ expressions: VALUE._col0 (type: string), VALUE._col1 (type: string), KEY._col2 (type: string)
+ outputColumnNames: _col0, _col1, _col2
+ File Output Operator
+ compressed: false
+ Dp Sort State: PARTITION_SORTED
+ Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.nzhang_part
Stage: Stage-7
Conditional Operator
http://git-wip-us.apache.org/repos/asf/hive/blob/9f2e8e61/ql/src/test/results/clientpositive/merge_dynamic_partition.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/merge_dynamic_partition.q.out b/ql/src/test/results/clientpositive/merge_dynamic_partition.q.out
index 7d12b58..6e75c6e 100644
--- a/ql/src/test/results/clientpositive/merge_dynamic_partition.q.out
+++ b/ql/src/test/results/clientpositive/merge_dynamic_partition.q.out
@@ -75,48 +75,24 @@ STAGE PLANS:
expressions: key (type: string), value (type: string), hr (type: string)
outputColumnNames: _col0, _col1, _col2
Statistics: Num rows: 99 Data size: 58120 Basic stats: PARTIAL Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 99 Data size: 58120 Basic stats: PARTIAL Column stats: NONE
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.merge_dynamic_part_n1
- Select Operator
- expressions: _col0 (type: string), _col1 (type: string), '2008-04-08' (type: string), _col2 (type: string)
- outputColumnNames: key, value, ds, hr
- Statistics: Num rows: 99 Data size: 58120 Basic stats: PARTIAL Column stats: NONE
- Group By Operator
- aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll')
- keys: ds (type: string), hr (type: string)
- mode: hash
- outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 99 Data size: 58120 Basic stats: PARTIAL Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: string), _col1 (type: string)
- sort order: ++
- Map-reduce partition columns: _col0 (type: string), _col1 (type: string)
- Statistics: Num rows: 99 Data size: 58120 Basic stats: PARTIAL Column stats: NONE
- value expressions: _col2 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col3 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>)
+ Reduce Output Operator
+ key expressions: _col2 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col2 (type: string)
+ value expressions: _col0 (type: string), _col1 (type: string)
Reduce Operator Tree:
- Group By Operator
- aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1)
- keys: KEY._col0 (type: string), KEY._col1 (type: string)
- mode: mergepartial
- outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 49 Data size: 28766 Basic stats: PARTIAL Column stats: NONE
- Select Operator
- expressions: _col2 (type: struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col3 (type: struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col0 (type: string), _col1 (type: string)
- outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 49 Data size: 28766 Basic stats: PARTIAL Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 49 Data size: 28766 Basic stats: PARTIAL Column stats: NONE
- 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
+ Select Operator
+ expressions: VALUE._col0 (type: string), VALUE._col1 (type: string), KEY._col2 (type: string)
+ outputColumnNames: _col0, _col1, _col2
+ File Output Operator
+ compressed: false
+ Dp Sort State: PARTITION_SORTED
+ Statistics: Num rows: 99 Data size: 58120 Basic stats: PARTIAL Column stats: NONE
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.merge_dynamic_part_n1
Stage: Stage-0
Move Operator
@@ -672,10 +648,10 @@ outputformat:org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
columns:struct columns { string key, string value}
partitioned:true
partitionColumns:struct partition_columns { string ds, string hr}
-totalNumberFiles:4
+totalNumberFiles:1
totalFileSize:5812
-maxFileSize:1612
-minFileSize:1358
+maxFileSize:5812
+minFileSize:5812
#### A masked pattern was here ####
PREHOOK: query: explain
@@ -1387,48 +1363,24 @@ STAGE PLANS:
expressions: key (type: string), value (type: string), '2008-04-08' (type: string), hr (type: string)
outputColumnNames: _col0, _col1, _col2, _col3
Statistics: Num rows: 99 Data size: 58120 Basic stats: PARTIAL Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 99 Data size: 58120 Basic stats: PARTIAL Column stats: NONE
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.merge_dynamic_part_n1
- Select Operator
- expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string)
- outputColumnNames: key, value, ds, hr
- Statistics: Num rows: 99 Data size: 58120 Basic stats: PARTIAL Column stats: NONE
- Group By Operator
- aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll')
- keys: ds (type: string), hr (type: string)
- mode: hash
- outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 99 Data size: 58120 Basic stats: PARTIAL Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: string), _col1 (type: string)
- sort order: ++
- Map-reduce partition columns: _col0 (type: string), _col1 (type: string)
- Statistics: Num rows: 99 Data size: 58120 Basic stats: PARTIAL Column stats: NONE
- value expressions: _col2 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col3 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>)
+ Reduce Output Operator
+ key expressions: _col2 (type: string), _col3 (type: string)
+ sort order: ++
+ Map-reduce partition columns: _col2 (type: string), _col3 (type: string)
+ value expressions: _col0 (type: string), _col1 (type: string)
Reduce Operator Tree:
- Group By Operator
- aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1)
- keys: KEY._col0 (type: string), KEY._col1 (type: string)
- mode: mergepartial
+ Select Operator
+ expressions: VALUE._col0 (type: string), VALUE._col1 (type: string), KEY._col2 (type: string), KEY._col3 (type: string)
outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 49 Data size: 28766 Basic stats: PARTIAL Column stats: NONE
- Select Operator
- expressions: _col2 (type: struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col3 (type: struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col0 (type: string), _col1 (type: string)
- outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 49 Data size: 28766 Basic stats: PARTIAL Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 49 Data size: 28766 Basic stats: PARTIAL Column stats: NONE
- 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
+ File Output Operator
+ compressed: false
+ Dp Sort State: PARTITION_SORTED
+ Statistics: Num rows: 99 Data size: 58120 Basic stats: PARTIAL Column stats: NONE
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.merge_dynamic_part_n1
Stage: Stage-7
Conditional Operator
http://git-wip-us.apache.org/repos/asf/hive/blob/9f2e8e61/ql/src/test/results/clientpositive/merge_dynamic_partition2.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/merge_dynamic_partition2.q.out b/ql/src/test/results/clientpositive/merge_dynamic_partition2.q.out
index 2450284..a98bfbf 100644
--- a/ql/src/test/results/clientpositive/merge_dynamic_partition2.q.out
+++ b/ql/src/test/results/clientpositive/merge_dynamic_partition2.q.out
@@ -99,48 +99,24 @@ STAGE PLANS:
expressions: key (type: string), value (type: string), hr (type: string)
outputColumnNames: _col0, _col1, _col2
Statistics: Num rows: 297 Data size: 174150 Basic stats: PARTIAL Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 297 Data size: 174150 Basic stats: PARTIAL Column stats: NONE
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.merge_dynamic_part_n0
- Select Operator
- expressions: _col0 (type: string), _col1 (type: string), '2008-04-08' (type: string), _col2 (type: string)
- outputColumnNames: key, value, ds, hr
- Statistics: Num rows: 297 Data size: 174150 Basic stats: PARTIAL Column stats: NONE
- Group By Operator
- aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll')
- keys: ds (type: string), hr (type: string)
- mode: hash
- outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 297 Data size: 174150 Basic stats: PARTIAL Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: string), _col1 (type: string)
- sort order: ++
- Map-reduce partition columns: _col0 (type: string), _col1 (type: string)
- Statistics: Num rows: 297 Data size: 174150 Basic stats: PARTIAL Column stats: NONE
- value expressions: _col2 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col3 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>)
+ Reduce Output Operator
+ key expressions: _col2 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col2 (type: string)
+ value expressions: _col0 (type: string), _col1 (type: string)
Reduce Operator Tree:
- Group By Operator
- aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1)
- keys: KEY._col0 (type: string), KEY._col1 (type: string)
- mode: mergepartial
- outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 148 Data size: 86781 Basic stats: PARTIAL Column stats: NONE
- Select Operator
- expressions: _col2 (type: struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col3 (type: struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col0 (type: string), _col1 (type: string)
- outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 148 Data size: 86781 Basic stats: PARTIAL Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 148 Data size: 86781 Basic stats: PARTIAL Column stats: NONE
- 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
+ Select Operator
+ expressions: VALUE._col0 (type: string), VALUE._col1 (type: string), KEY._col2 (type: string)
+ outputColumnNames: _col0, _col1, _col2
+ File Output Operator
+ compressed: false
+ Dp Sort State: PARTITION_SORTED
+ Statistics: Num rows: 297 Data size: 174150 Basic stats: PARTIAL Column stats: NONE
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.merge_dynamic_part_n0
Stage: Stage-7
Conditional Operator
@@ -230,9 +206,9 @@ outputformat:org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
columns:struct columns { string key, string value}
partitioned:true
partitionColumns:struct partition_columns { string ds, string hr}
-totalNumberFiles:3
+totalNumberFiles:2
totalFileSize:17415
-maxFileSize:5901
-minFileSize:5702
+maxFileSize:11603
+minFileSize:5812
#### A masked pattern was here ####
http://git-wip-us.apache.org/repos/asf/hive/blob/9f2e8e61/ql/src/test/results/clientpositive/merge_dynamic_partition3.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/merge_dynamic_partition3.q.out b/ql/src/test/results/clientpositive/merge_dynamic_partition3.q.out
index d07ad0a..cbc8afd 100644
--- a/ql/src/test/results/clientpositive/merge_dynamic_partition3.q.out
+++ b/ql/src/test/results/clientpositive/merge_dynamic_partition3.q.out
@@ -163,48 +163,24 @@ STAGE PLANS:
expressions: key (type: string), value (type: string), ds (type: string), hr (type: string)
outputColumnNames: _col0, _col1, _col2, _col3
Statistics: Num rows: 594 Data size: 348300 Basic stats: PARTIAL Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 594 Data size: 348300 Basic stats: PARTIAL Column stats: NONE
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.merge_dynamic_part_n2
- Select Operator
- expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string)
- outputColumnNames: key, value, ds, hr
- Statistics: Num rows: 594 Data size: 348300 Basic stats: PARTIAL Column stats: NONE
- Group By Operator
- aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll')
- keys: ds (type: string), hr (type: string)
- mode: hash
- outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 594 Data size: 348300 Basic stats: PARTIAL Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: string), _col1 (type: string)
- sort order: ++
- Map-reduce partition columns: _col0 (type: string), _col1 (type: string)
- Statistics: Num rows: 594 Data size: 348300 Basic stats: PARTIAL Column stats: NONE
- value expressions: _col2 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col3 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>)
+ Reduce Output Operator
+ key expressions: _col2 (type: string), _col3 (type: string)
+ sort order: ++
+ Map-reduce partition columns: _col2 (type: string), _col3 (type: string)
+ value expressions: _col0 (type: string), _col1 (type: string)
Reduce Operator Tree:
- Group By Operator
- aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1)
- keys: KEY._col0 (type: string), KEY._col1 (type: string)
- mode: mergepartial
+ Select Operator
+ expressions: VALUE._col0 (type: string), VALUE._col1 (type: string), KEY._col2 (type: string), KEY._col3 (type: string)
outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 297 Data size: 174150 Basic stats: PARTIAL Column stats: NONE
- Select Operator
- expressions: _col2 (type: struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col3 (type: struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col0 (type: string), _col1 (type: string)
- outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 297 Data size: 174150 Basic stats: PARTIAL Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 297 Data size: 174150 Basic stats: PARTIAL Column stats: NONE
- 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
+ File Output Operator
+ compressed: false
+ Dp Sort State: PARTITION_SORTED
+ Statistics: Num rows: 594 Data size: 348300 Basic stats: PARTIAL Column stats: NONE
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.merge_dynamic_part_n2
Stage: Stage-7
Conditional Operator
@@ -324,9 +300,9 @@ outputformat:org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
columns:struct columns { string key, string value}
partitioned:true
partitionColumns:struct partition_columns { string ds, string hr}
-totalNumberFiles:6
+totalNumberFiles:4
totalFileSize:34830
-maxFileSize:5812
-minFileSize:5791
+maxFileSize:11603
+minFileSize:5812
#### A masked pattern was here ####
http://git-wip-us.apache.org/repos/asf/hive/blob/9f2e8e61/ql/src/test/results/clientpositive/merge_dynamic_partition4.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/merge_dynamic_partition4.q.out b/ql/src/test/results/clientpositive/merge_dynamic_partition4.q.out
index 545ef90..8a4b96f 100644
--- a/ql/src/test/results/clientpositive/merge_dynamic_partition4.q.out
+++ b/ql/src/test/results/clientpositive/merge_dynamic_partition4.q.out
@@ -160,48 +160,24 @@ STAGE PLANS:
expressions: key (type: string), value (type: string), if(((UDFToDouble(key) % 2.0D) = 0.0D), 'a1', 'b1') (type: string)
outputColumnNames: _col0, _col1, _col2
Statistics: Num rows: 1000 Data size: 9624 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 1000 Data size: 9624 Basic stats: COMPLETE Column stats: NONE
- table:
- input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
- name: default.merge_dynamic_part_n3
- Select Operator
- expressions: _col0 (type: string), _col1 (type: string), '2008-04-08' (type: string), _col2 (type: string)
- outputColumnNames: key, value, ds, hr
- Statistics: Num rows: 1000 Data size: 9624 Basic stats: COMPLETE Column stats: NONE
- Group By Operator
- aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll')
- keys: ds (type: string), hr (type: string)
- mode: hash
- outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 1000 Data size: 9624 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: string), _col1 (type: string)
- sort order: ++
- Map-reduce partition columns: _col0 (type: string), _col1 (type: string)
- Statistics: Num rows: 1000 Data size: 9624 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col2 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col3 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>)
+ Reduce Output Operator
+ key expressions: _col2 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col2 (type: string)
+ value expressions: _col0 (type: string), _col1 (type: string)
Reduce Operator Tree:
- Group By Operator
- aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1)
- keys: KEY._col0 (type: string), KEY._col1 (type: string)
- mode: mergepartial
- outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 500 Data size: 4812 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col2 (type: struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col3 (type: struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col0 (type: string), _col1 (type: string)
- outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 500 Data size: 4812 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 500 Data size: 4812 Basic stats: COMPLETE Column stats: NONE
- 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
+ Select Operator
+ expressions: VALUE._col0 (type: string), VALUE._col1 (type: string), KEY._col2 (type: string)
+ outputColumnNames: _col0, _col1, _col2
+ File Output Operator
+ compressed: false
+ Dp Sort State: PARTITION_SORTED
+ Statistics: Num rows: 1000 Data size: 9624 Basic stats: COMPLETE Column stats: NONE
+ table:
+ input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
+ name: default.merge_dynamic_part_n3
Stage: Stage-7
Conditional Operator
http://git-wip-us.apache.org/repos/asf/hive/blob/9f2e8e61/ql/src/test/results/clientpositive/merge_dynamic_partition5.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/merge_dynamic_partition5.q.out b/ql/src/test/results/clientpositive/merge_dynamic_partition5.q.out
index 6d994d7..db782cb 100644
--- a/ql/src/test/results/clientpositive/merge_dynamic_partition5.q.out
+++ b/ql/src/test/results/clientpositive/merge_dynamic_partition5.q.out
@@ -136,48 +136,24 @@ STAGE PLANS:
expressions: key (type: string), value (type: string), if(((UDFToDouble(key) % 100.0D) = 0.0D), 'a1', 'b1') (type: string)
outputColumnNames: _col0, _col1, _col2
Statistics: Num rows: 618 Data size: 5934 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 618 Data size: 5934 Basic stats: COMPLETE Column stats: NONE
- table:
- input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
- name: default.merge_dynamic_part
- Select Operator
- expressions: _col0 (type: string), _col1 (type: string), '2008-04-08' (type: string), _col2 (type: string)
- outputColumnNames: key, value, ds, hr
- Statistics: Num rows: 618 Data size: 5934 Basic stats: COMPLETE Column stats: NONE
- Group By Operator
- aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll')
- keys: ds (type: string), hr (type: string)
- mode: hash
- outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 618 Data size: 5934 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: string), _col1 (type: string)
- sort order: ++
- Map-reduce partition columns: _col0 (type: string), _col1 (type: string)
- Statistics: Num rows: 618 Data size: 5934 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col2 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col3 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>)
+ Reduce Output Operator
+ key expressions: _col2 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col2 (type: string)
+ value expressions: _col0 (type: string), _col1 (type: string)
Reduce Operator Tree:
- Group By Operator
- aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1)
- keys: KEY._col0 (type: string), KEY._col1 (type: string)
- mode: mergepartial
- outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 309 Data size: 2967 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col2 (type: struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col3 (type: struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col0 (type: string), _col1 (type: string)
- outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 309 Data size: 2967 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 309 Data size: 2967 Basic stats: COMPLETE Column stats: NONE
- 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
+ Select Operator
+ expressions: VALUE._col0 (type: string), VALUE._col1 (type: string), KEY._col2 (type: string)
+ outputColumnNames: _col0, _col1, _col2
+ File Output Operator
+ compressed: false
+ Dp Sort State: PARTITION_SORTED
+ Statistics: Num rows: 618 Data size: 5934 Basic stats: COMPLETE Column stats: NONE
+ table:
+ input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe
+ name: default.merge_dynamic_part
Stage: Stage-7
Conditional Operator
http://git-wip-us.apache.org/repos/asf/hive/blob/9f2e8e61/ql/src/test/results/clientpositive/orc_int_type_promotion.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/orc_int_type_promotion.q.out b/ql/src/test/results/clientpositive/orc_int_type_promotion.q.out
index 7a1fb44..b6fb7e2 100644
--- a/ql/src/test/results/clientpositive/orc_int_type_promotion.q.out
+++ b/ql/src/test/results/clientpositive/orc_int_type_promotion.q.out
@@ -262,15 +262,15 @@ POSTHOOK: Input: default@src_part_orc@ds=2008-04-08
POSTHOOK: Input: default@src_part_orc@ds=2008-04-09
#### A masked pattern was here ####
238 val_238 2008-04-08
-86 val_86 2008-04-08
-311 val_311 2008-04-08
-27 val_27 2008-04-08
-165 val_165 2008-04-08
-409 val_409 2008-04-08
-255 val_255 2008-04-08
-278 val_278 2008-04-08
-98 val_98 2008-04-08
-484 val_484 2008-04-08
+97 val_97 2008-04-08
+200 val_200 2008-04-08
+400 val_400 2008-04-08
+403 val_403 2008-04-08
+169 val_169 2008-04-08
+90 val_90 2008-04-08
+126 val_126 2008-04-08
+222 val_222 2008-04-08
+477 val_477 2008-04-08
PREHOOK: query: alter table src_part_orc change key key bigint
PREHOOK: type: ALTERTABLE_RENAMECOL
PREHOOK: Input: default@src_part_orc
@@ -292,12 +292,12 @@ POSTHOOK: Input: default@src_part_orc@ds=2008-04-08
POSTHOOK: Input: default@src_part_orc@ds=2008-04-09
#### A masked pattern was here ####
238 val_238 2008-04-08
-86 val_86 2008-04-08
-311 val_311 2008-04-08
-27 val_27 2008-04-08
-165 val_165 2008-04-08
-409 val_409 2008-04-08
-255 val_255 2008-04-08
-278 val_278 2008-04-08
-98 val_98 2008-04-08
-484 val_484 2008-04-08
+97 val_97 2008-04-08
+200 val_200 2008-04-08
+400 val_400 2008-04-08
+403 val_403 2008-04-08
+169 val_169 2008-04-08
+90 val_90 2008-04-08
+126 val_126 2008-04-08
+222 val_222 2008-04-08
+477 val_477 2008-04-08