You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@hive.apache.org by dj...@apache.org on 2018/02/08 21:13:13 UTC
[6/7] hive git commit: Revert "HIVE-18350 : load data should rename
files consistent with insert statements. (Deepak Jaiswal,
reviewed by Sergey Shelukhin and Ashutosh Chauhan)"
http://git-wip-us.apache.org/repos/asf/hive/blob/3464df45/ql/src/test/results/clientpositive/auto_sortmerge_join_4.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/auto_sortmerge_join_4.q.out b/ql/src/test/results/clientpositive/auto_sortmerge_join_4.q.out
index b54c574..0d586fd 100644
--- a/ql/src/test/results/clientpositive/auto_sortmerge_join_4.q.out
+++ b/ql/src/test/results/clientpositive/auto_sortmerge_join_4.q.out
@@ -72,11 +72,11 @@ POSTHOOK: query: load data local inpath '../../data/files/auto_sortmerge_join/sm
POSTHOOK: type: LOAD
#### A masked pattern was here ####
POSTHOOK: Output: default@bucket_small@ds=2008-04-09
-PREHOOK: query: CREATE TABLE bucket_big (key string, value string) partitioned by (ds string) CLUSTERED BY (key) SORTED BY (key) INTO 4 BUCKETS STORED AS TEXTFILE
+PREHOOK: query: CREATE TABLE bucket_big (key string, value string) partitioned by (ds string) CLUSTERED BY (key) SORTED BY (key) INTO 2 BUCKETS STORED AS TEXTFILE
PREHOOK: type: CREATETABLE
PREHOOK: Output: database:default
PREHOOK: Output: default@bucket_big
-POSTHOOK: query: CREATE TABLE bucket_big (key string, value string) partitioned by (ds string) CLUSTERED BY (key) SORTED BY (key) INTO 4 BUCKETS STORED AS TEXTFILE
+POSTHOOK: query: CREATE TABLE bucket_big (key string, value string) partitioned by (ds string) CLUSTERED BY (key) SORTED BY (key) INTO 2 BUCKETS STORED AS TEXTFILE
POSTHOOK: type: CREATETABLE
POSTHOOK: Output: database:default
POSTHOOK: Output: default@bucket_big
@@ -97,22 +97,6 @@ POSTHOOK: query: load data local inpath '../../data/files/auto_sortmerge_join/bi
POSTHOOK: type: LOAD
#### A masked pattern was here ####
POSTHOOK: Output: default@bucket_big@ds=2008-04-08
-PREHOOK: query: load data local inpath '../../data/files/auto_sortmerge_join/big/000002_0' INTO TABLE bucket_big partition(ds='2008-04-08')
-PREHOOK: type: LOAD
-#### A masked pattern was here ####
-PREHOOK: Output: default@bucket_big@ds=2008-04-08
-POSTHOOK: query: load data local inpath '../../data/files/auto_sortmerge_join/big/000002_0' INTO TABLE bucket_big partition(ds='2008-04-08')
-POSTHOOK: type: LOAD
-#### A masked pattern was here ####
-POSTHOOK: Output: default@bucket_big@ds=2008-04-08
-PREHOOK: query: load data local inpath '../../data/files/auto_sortmerge_join/big/000003_0' INTO TABLE bucket_big partition(ds='2008-04-08')
-PREHOOK: type: LOAD
-#### A masked pattern was here ####
-PREHOOK: Output: default@bucket_big@ds=2008-04-08
-POSTHOOK: query: load data local inpath '../../data/files/auto_sortmerge_join/big/000003_0' INTO TABLE bucket_big partition(ds='2008-04-08')
-POSTHOOK: type: LOAD
-#### A masked pattern was here ####
-POSTHOOK: Output: default@bucket_big@ds=2008-04-08
PREHOOK: query: explain extended select count(*) FROM bucket_small a JOIN bucket_big b ON a.key = b.key
PREHOOK: type: QUERY
POSTHOOK: query: explain extended select count(*) FROM bucket_small a JOIN bucket_big b ON a.key = b.key
@@ -127,16 +111,16 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: b
- Statistics: Num rows: 120 Data size: 58120 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 56 Data size: 27500 Basic stats: COMPLETE Column stats: NONE
GatherStats: false
Filter Operator
isSamplingPred: false
predicate: key is not null (type: boolean)
- Statistics: Num rows: 120 Data size: 58120 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 56 Data size: 27500 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: key (type: string)
outputColumnNames: _col0
- Statistics: Num rows: 120 Data size: 58120 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 56 Data size: 27500 Basic stats: COMPLETE Column stats: NONE
Sorted Merge Bucket Map Join Operator
condition map:
Inner Join 0 to 1
@@ -166,7 +150,7 @@ STAGE PLANS:
partition values:
ds 2008-04-08
properties:
- bucket_count 4
+ bucket_count 2
bucket_field_name key
column.name.delimiter ,
columns key,value
@@ -174,7 +158,7 @@ STAGE PLANS:
columns.types string:string
#### A masked pattern was here ####
name default.bucket_big
- numFiles 4
+ numFiles 2
numRows 0
partition_columns ds
partition_columns.types string
@@ -182,7 +166,7 @@ STAGE PLANS:
serialization.ddl struct bucket_big { string key, string value}
serialization.format 1
serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 5812
+ totalSize 2750
#### A masked pattern was here ####
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
@@ -190,7 +174,7 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
SORTBUCKETCOLSPREFIX TRUE
- bucket_count 4
+ bucket_count 2
bucket_field_name key
column.name.delimiter ,
columns key,value
@@ -259,7 +243,7 @@ POSTHOOK: Input: default@bucket_small
POSTHOOK: Input: default@bucket_small@ds=2008-04-08
POSTHOOK: Input: default@bucket_small@ds=2008-04-09
#### A masked pattern was here ####
-78
+38
PREHOOK: query: explain extended select count(*) FROM bucket_big a JOIN bucket_small b ON a.key = b.key
PREHOOK: type: QUERY
POSTHOOK: query: explain extended select count(*) FROM bucket_big a JOIN bucket_small b ON a.key = b.key
@@ -274,16 +258,16 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: a
- Statistics: Num rows: 120 Data size: 58120 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 56 Data size: 27500 Basic stats: COMPLETE Column stats: NONE
GatherStats: false
Filter Operator
isSamplingPred: false
predicate: key is not null (type: boolean)
- Statistics: Num rows: 120 Data size: 58120 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 56 Data size: 27500 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: key (type: string)
outputColumnNames: _col0
- Statistics: Num rows: 120 Data size: 58120 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 56 Data size: 27500 Basic stats: COMPLETE Column stats: NONE
Sorted Merge Bucket Map Join Operator
condition map:
Inner Join 0 to 1
@@ -313,7 +297,7 @@ STAGE PLANS:
partition values:
ds 2008-04-08
properties:
- bucket_count 4
+ bucket_count 2
bucket_field_name key
column.name.delimiter ,
columns key,value
@@ -321,7 +305,7 @@ STAGE PLANS:
columns.types string:string
#### A masked pattern was here ####
name default.bucket_big
- numFiles 4
+ numFiles 2
numRows 0
partition_columns ds
partition_columns.types string
@@ -329,7 +313,7 @@ STAGE PLANS:
serialization.ddl struct bucket_big { string key, string value}
serialization.format 1
serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 5812
+ totalSize 2750
#### A masked pattern was here ####
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
@@ -337,7 +321,7 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
SORTBUCKETCOLSPREFIX TRUE
- bucket_count 4
+ bucket_count 2
bucket_field_name key
column.name.delimiter ,
columns key,value
@@ -406,7 +390,7 @@ POSTHOOK: Input: default@bucket_small
POSTHOOK: Input: default@bucket_small@ds=2008-04-08
POSTHOOK: Input: default@bucket_small@ds=2008-04-09
#### A masked pattern was here ####
-78
+38
PREHOOK: query: explain extended select count(*) FROM bucket_big a JOIN bucket_small b ON a.key = b.key
PREHOOK: type: QUERY
POSTHOOK: query: explain extended select count(*) FROM bucket_big a JOIN bucket_small b ON a.key = b.key
@@ -550,16 +534,16 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: a
- Statistics: Num rows: 120 Data size: 58120 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 56 Data size: 27500 Basic stats: COMPLETE Column stats: NONE
GatherStats: false
Filter Operator
isSamplingPred: false
predicate: key is not null (type: boolean)
- Statistics: Num rows: 120 Data size: 58120 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 56 Data size: 27500 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: key (type: string)
outputColumnNames: _col0
- Statistics: Num rows: 120 Data size: 58120 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 56 Data size: 27500 Basic stats: COMPLETE Column stats: NONE
Map Join Operator
condition map:
Inner Join 0 to 1
@@ -590,7 +574,7 @@ STAGE PLANS:
partition values:
ds 2008-04-08
properties:
- bucket_count 4
+ bucket_count 2
bucket_field_name key
column.name.delimiter ,
columns key,value
@@ -598,7 +582,7 @@ STAGE PLANS:
columns.types string:string
#### A masked pattern was here ####
name default.bucket_big
- numFiles 4
+ numFiles 2
numRows 0
partition_columns ds
partition_columns.types string
@@ -606,7 +590,7 @@ STAGE PLANS:
serialization.ddl struct bucket_big { string key, string value}
serialization.format 1
serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 5812
+ totalSize 2750
#### A masked pattern was here ####
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
@@ -614,7 +598,7 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
SORTBUCKETCOLSPREFIX TRUE
- bucket_count 4
+ bucket_count 2
bucket_field_name key
column.name.delimiter ,
columns key,value
@@ -771,7 +755,7 @@ STAGE PLANS:
partition values:
ds 2008-04-08
properties:
- bucket_count 4
+ bucket_count 2
bucket_field_name key
column.name.delimiter ,
columns key,value
@@ -779,7 +763,7 @@ STAGE PLANS:
columns.types string:string
#### A masked pattern was here ####
name default.bucket_big
- numFiles 4
+ numFiles 2
numRows 0
partition_columns ds
partition_columns.types string
@@ -787,7 +771,7 @@ STAGE PLANS:
serialization.ddl struct bucket_big { string key, string value}
serialization.format 1
serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 5812
+ totalSize 2750
#### A masked pattern was here ####
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
@@ -795,7 +779,7 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
SORTBUCKETCOLSPREFIX TRUE
- bucket_count 4
+ bucket_count 2
bucket_field_name key
column.name.delimiter ,
columns key,value
@@ -816,16 +800,16 @@ STAGE PLANS:
$hdt$_0:a
TableScan
alias: a
- Statistics: Num rows: 120 Data size: 58120 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 56 Data size: 27500 Basic stats: COMPLETE Column stats: NONE
GatherStats: false
Filter Operator
isSamplingPred: false
predicate: key is not null (type: boolean)
- Statistics: Num rows: 120 Data size: 58120 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 56 Data size: 27500 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: key (type: string)
outputColumnNames: _col0
- Statistics: Num rows: 120 Data size: 58120 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 56 Data size: 27500 Basic stats: COMPLETE Column stats: NONE
HashTable Sink Operator
keys:
0 _col0 (type: string)
@@ -877,7 +861,7 @@ STAGE PLANS:
partition values:
ds 2008-04-08
properties:
- bucket_count 4
+ bucket_count 2
bucket_field_name key
column.name.delimiter ,
columns key,value
@@ -885,7 +869,7 @@ STAGE PLANS:
columns.types string:string
#### A masked pattern was here ####
name default.bucket_big
- numFiles 4
+ numFiles 2
numRows 0
partition_columns ds
partition_columns.types string
@@ -893,7 +877,7 @@ STAGE PLANS:
serialization.ddl struct bucket_big { string key, string value}
serialization.format 1
serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 5812
+ totalSize 2750
#### A masked pattern was here ####
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
@@ -901,7 +885,7 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
SORTBUCKETCOLSPREFIX TRUE
- bucket_count 4
+ bucket_count 2
bucket_field_name key
column.name.delimiter ,
columns key,value
@@ -1050,16 +1034,16 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: a
- Statistics: Num rows: 120 Data size: 58120 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 56 Data size: 27500 Basic stats: COMPLETE Column stats: NONE
GatherStats: false
Filter Operator
isSamplingPred: false
predicate: key is not null (type: boolean)
- Statistics: Num rows: 120 Data size: 58120 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 56 Data size: 27500 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: key (type: string)
outputColumnNames: _col0
- Statistics: Num rows: 120 Data size: 58120 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 56 Data size: 27500 Basic stats: COMPLETE Column stats: NONE
Sorted Merge Bucket Map Join Operator
condition map:
Inner Join 0 to 1
@@ -1089,7 +1073,7 @@ STAGE PLANS:
partition values:
ds 2008-04-08
properties:
- bucket_count 4
+ bucket_count 2
bucket_field_name key
column.name.delimiter ,
columns key,value
@@ -1097,7 +1081,7 @@ STAGE PLANS:
columns.types string:string
#### A masked pattern was here ####
name default.bucket_big
- numFiles 4
+ numFiles 2
numRows 0
partition_columns ds
partition_columns.types string
@@ -1105,7 +1089,7 @@ STAGE PLANS:
serialization.ddl struct bucket_big { string key, string value}
serialization.format 1
serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 5812
+ totalSize 2750
#### A masked pattern was here ####
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
@@ -1113,7 +1097,7 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
SORTBUCKETCOLSPREFIX TRUE
- bucket_count 4
+ bucket_count 2
bucket_field_name key
column.name.delimiter ,
columns key,value
@@ -1182,4 +1166,4 @@ POSTHOOK: Input: default@bucket_small
POSTHOOK: Input: default@bucket_small@ds=2008-04-08
POSTHOOK: Input: default@bucket_small@ds=2008-04-09
#### A masked pattern was here ####
-78
+38
http://git-wip-us.apache.org/repos/asf/hive/blob/3464df45/ql/src/test/results/clientpositive/auto_sortmerge_join_5.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/auto_sortmerge_join_5.q.out b/ql/src/test/results/clientpositive/auto_sortmerge_join_5.q.out
index 451c3b3..45704d1 100644
--- a/ql/src/test/results/clientpositive/auto_sortmerge_join_5.q.out
+++ b/ql/src/test/results/clientpositive/auto_sortmerge_join_5.q.out
@@ -1,8 +1,8 @@
-PREHOOK: query: CREATE TABLE bucket_small (key string, value string) CLUSTERED BY (key) SORTED BY (key) INTO 2 BUCKETS STORED AS TEXTFILE
+PREHOOK: query: CREATE TABLE bucket_small (key string, value string) CLUSTERED BY (key) SORTED BY (key) INTO 4 BUCKETS STORED AS TEXTFILE
PREHOOK: type: CREATETABLE
PREHOOK: Output: database:default
PREHOOK: Output: default@bucket_small
-POSTHOOK: query: CREATE TABLE bucket_small (key string, value string) CLUSTERED BY (key) SORTED BY (key) INTO 2 BUCKETS STORED AS TEXTFILE
+POSTHOOK: query: CREATE TABLE bucket_small (key string, value string) CLUSTERED BY (key) SORTED BY (key) INTO 4 BUCKETS STORED AS TEXTFILE
POSTHOOK: type: CREATETABLE
POSTHOOK: Output: database:default
POSTHOOK: Output: default@bucket_small
@@ -22,11 +22,27 @@ POSTHOOK: query: load data local inpath '../../data/files/auto_sortmerge_join/sm
POSTHOOK: type: LOAD
#### A masked pattern was here ####
POSTHOOK: Output: default@bucket_small
-PREHOOK: query: CREATE TABLE bucket_big (key string, value string) CLUSTERED BY (key) SORTED BY (key) INTO 4 BUCKETS STORED AS TEXTFILE
+PREHOOK: query: load data local inpath '../../data/files/auto_sortmerge_join/small/000002_0' INTO TABLE bucket_small
+PREHOOK: type: LOAD
+#### A masked pattern was here ####
+PREHOOK: Output: default@bucket_small
+POSTHOOK: query: load data local inpath '../../data/files/auto_sortmerge_join/small/000002_0' INTO TABLE bucket_small
+POSTHOOK: type: LOAD
+#### A masked pattern was here ####
+POSTHOOK: Output: default@bucket_small
+PREHOOK: query: load data local inpath '../../data/files/auto_sortmerge_join/small/000003_0' INTO TABLE bucket_small
+PREHOOK: type: LOAD
+#### A masked pattern was here ####
+PREHOOK: Output: default@bucket_small
+POSTHOOK: query: load data local inpath '../../data/files/auto_sortmerge_join/small/000003_0' INTO TABLE bucket_small
+POSTHOOK: type: LOAD
+#### A masked pattern was here ####
+POSTHOOK: Output: default@bucket_small
+PREHOOK: query: CREATE TABLE bucket_big (key string, value string) CLUSTERED BY (key) SORTED BY (key) INTO 2 BUCKETS STORED AS TEXTFILE
PREHOOK: type: CREATETABLE
PREHOOK: Output: database:default
PREHOOK: Output: default@bucket_big
-POSTHOOK: query: CREATE TABLE bucket_big (key string, value string) CLUSTERED BY (key) SORTED BY (key) INTO 4 BUCKETS STORED AS TEXTFILE
+POSTHOOK: query: CREATE TABLE bucket_big (key string, value string) CLUSTERED BY (key) SORTED BY (key) INTO 2 BUCKETS STORED AS TEXTFILE
POSTHOOK: type: CREATETABLE
POSTHOOK: Output: database:default
POSTHOOK: Output: default@bucket_big
@@ -46,22 +62,6 @@ POSTHOOK: query: load data local inpath '../../data/files/auto_sortmerge_join/bi
POSTHOOK: type: LOAD
#### A masked pattern was here ####
POSTHOOK: Output: default@bucket_big
-PREHOOK: query: load data local inpath '../../data/files/auto_sortmerge_join/big/000002_0' INTO TABLE bucket_big
-PREHOOK: type: LOAD
-#### A masked pattern was here ####
-PREHOOK: Output: default@bucket_big
-POSTHOOK: query: load data local inpath '../../data/files/auto_sortmerge_join/big/000002_0' INTO TABLE bucket_big
-POSTHOOK: type: LOAD
-#### A masked pattern was here ####
-POSTHOOK: Output: default@bucket_big
-PREHOOK: query: load data local inpath '../../data/files/auto_sortmerge_join/big/000003_0' INTO TABLE bucket_big
-PREHOOK: type: LOAD
-#### A masked pattern was here ####
-PREHOOK: Output: default@bucket_big
-POSTHOOK: query: load data local inpath '../../data/files/auto_sortmerge_join/big/000003_0' INTO TABLE bucket_big
-POSTHOOK: type: LOAD
-#### A masked pattern was here ####
-POSTHOOK: Output: default@bucket_big
PREHOOK: query: explain extended select count(*) FROM bucket_small a JOIN bucket_big b ON a.key = b.key
PREHOOK: type: QUERY
POSTHOOK: query: explain extended select count(*) FROM bucket_small a JOIN bucket_big b ON a.key = b.key
@@ -76,16 +76,16 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: b
- Statistics: Num rows: 1 Data size: 58120 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 27500 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: 58120 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 27500 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: key (type: string)
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 58120 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 27500 Basic stats: COMPLETE Column stats: NONE
Sorted Merge Bucket Map Join Operator
condition map:
Inner Join 0 to 1
@@ -114,7 +114,7 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
SORTBUCKETCOLSPREFIX TRUE
- bucket_count 4
+ bucket_count 2
bucket_field_name key
column.name.delimiter ,
columns key,value
@@ -122,13 +122,13 @@ STAGE PLANS:
columns.types string:string
#### A masked pattern was here ####
name default.bucket_big
- numFiles 4
+ numFiles 2
numRows 0
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
+ totalSize 2750
#### A masked pattern was here ####
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
@@ -136,7 +136,7 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
SORTBUCKETCOLSPREFIX TRUE
- bucket_count 4
+ bucket_count 2
bucket_field_name key
column.name.delimiter ,
columns key,value
@@ -144,13 +144,13 @@ STAGE PLANS:
columns.types string:string
#### A masked pattern was here ####
name default.bucket_big
- numFiles 4
+ numFiles 2
numRows 0
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
+ totalSize 2750
#### A masked pattern was here ####
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.bucket_big
@@ -216,16 +216,16 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: a
- Statistics: Num rows: 1 Data size: 58120 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 27500 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: 58120 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 27500 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: key (type: string)
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 58120 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 27500 Basic stats: COMPLETE Column stats: NONE
Sorted Merge Bucket Map Join Operator
condition map:
Inner Join 0 to 1
@@ -254,7 +254,7 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
SORTBUCKETCOLSPREFIX TRUE
- bucket_count 4
+ bucket_count 2
bucket_field_name key
column.name.delimiter ,
columns key,value
@@ -262,13 +262,13 @@ STAGE PLANS:
columns.types string:string
#### A masked pattern was here ####
name default.bucket_big
- numFiles 4
+ numFiles 2
numRows 0
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
+ totalSize 2750
#### A masked pattern was here ####
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
@@ -276,7 +276,7 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
SORTBUCKETCOLSPREFIX TRUE
- bucket_count 4
+ bucket_count 2
bucket_field_name key
column.name.delimiter ,
columns key,value
@@ -284,13 +284,13 @@ STAGE PLANS:
columns.types string:string
#### A masked pattern was here ####
name default.bucket_big
- numFiles 4
+ numFiles 2
numRows 0
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
+ totalSize 2750
#### A masked pattern was here ####
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.bucket_big
@@ -369,16 +369,16 @@ STAGE PLANS:
$hdt$_1:b
TableScan
alias: b
- Statistics: Num rows: 1 Data size: 1140 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 2260 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: 1140 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 2260 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: key (type: string)
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 1140 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 2260 Basic stats: COMPLETE Column stats: NONE
HashTable Sink Operator
keys:
0 _col0 (type: string)
@@ -390,16 +390,16 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: a
- Statistics: Num rows: 1 Data size: 58120 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 27500 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: 58120 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 27500 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: key (type: string)
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 58120 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 27500 Basic stats: COMPLETE Column stats: NONE
Map Join Operator
condition map:
Inner Join 0 to 1
@@ -429,7 +429,7 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
SORTBUCKETCOLSPREFIX TRUE
- bucket_count 4
+ bucket_count 2
bucket_field_name key
column.name.delimiter ,
columns key,value
@@ -437,13 +437,13 @@ STAGE PLANS:
columns.types string:string
#### A masked pattern was here ####
name default.bucket_big
- numFiles 4
+ numFiles 2
numRows 0
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
+ totalSize 2750
#### A masked pattern was here ####
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
@@ -451,7 +451,7 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
SORTBUCKETCOLSPREFIX TRUE
- bucket_count 4
+ bucket_count 2
bucket_field_name key
column.name.delimiter ,
columns key,value
@@ -459,13 +459,13 @@ STAGE PLANS:
columns.types string:string
#### A masked pattern was here ####
name default.bucket_big
- numFiles 4
+ numFiles 2
numRows 0
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
+ totalSize 2750
#### A masked pattern was here ####
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.bucket_big
@@ -475,7 +475,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- bucket_count 2
+ bucket_count 4
bucket_field_name key
column.name.delimiter ,
columns key,value
@@ -492,7 +492,7 @@ 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
@@ -500,13 +500,13 @@ STAGE PLANS:
columns.types string:string
#### A masked pattern was here ####
name default.bucket_small
- numFiles 2
+ numFiles 4
numRows 0
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
+ totalSize 226
#### A masked pattern was here ####
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.bucket_small
@@ -551,16 +551,16 @@ STAGE PLANS:
$hdt$_0:a
TableScan
alias: a
- Statistics: Num rows: 1 Data size: 58120 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 27500 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: 58120 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 27500 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: key (type: string)
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 58120 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 27500 Basic stats: COMPLETE Column stats: NONE
HashTable Sink Operator
keys:
0 _col0 (type: string)
@@ -572,16 +572,16 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: b
- Statistics: Num rows: 1 Data size: 1140 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 2260 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: 1140 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 2260 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: key (type: string)
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 1140 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 2260 Basic stats: COMPLETE Column stats: NONE
Map Join Operator
condition map:
Inner Join 0 to 1
@@ -611,7 +611,7 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
SORTBUCKETCOLSPREFIX TRUE
- bucket_count 4
+ bucket_count 2
bucket_field_name key
column.name.delimiter ,
columns key,value
@@ -619,13 +619,13 @@ STAGE PLANS:
columns.types string:string
#### A masked pattern was here ####
name default.bucket_big
- numFiles 4
+ numFiles 2
numRows 0
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
+ totalSize 2750
#### A masked pattern was here ####
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
@@ -633,7 +633,7 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
SORTBUCKETCOLSPREFIX TRUE
- bucket_count 4
+ bucket_count 2
bucket_field_name key
column.name.delimiter ,
columns key,value
@@ -641,13 +641,13 @@ STAGE PLANS:
columns.types string:string
#### A masked pattern was here ####
name default.bucket_big
- numFiles 4
+ numFiles 2
numRows 0
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
+ totalSize 2750
#### A masked pattern was here ####
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.bucket_big
@@ -657,7 +657,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- bucket_count 2
+ bucket_count 4
bucket_field_name key
column.name.delimiter ,
columns key,value
@@ -674,7 +674,7 @@ 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
@@ -682,13 +682,13 @@ STAGE PLANS:
columns.types string:string
#### A masked pattern was here ####
name default.bucket_small
- numFiles 2
+ numFiles 4
numRows 0
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
+ totalSize 226
#### A masked pattern was here ####
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.bucket_small
@@ -728,16 +728,16 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: a
- Statistics: Num rows: 1 Data size: 58120 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 27500 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: 58120 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 27500 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: key (type: string)
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 58120 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 27500 Basic stats: COMPLETE Column stats: NONE
Sorted Merge Bucket Map Join Operator
condition map:
Inner Join 0 to 1
@@ -766,7 +766,7 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
SORTBUCKETCOLSPREFIX TRUE
- bucket_count 4
+ bucket_count 2
bucket_field_name key
column.name.delimiter ,
columns key,value
@@ -774,13 +774,13 @@ STAGE PLANS:
columns.types string:string
#### A masked pattern was here ####
name default.bucket_big
- numFiles 4
+ numFiles 2
numRows 0
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
+ totalSize 2750
#### A masked pattern was here ####
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
@@ -788,7 +788,7 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
SORTBUCKETCOLSPREFIX TRUE
- bucket_count 4
+ bucket_count 2
bucket_field_name key
column.name.delimiter ,
columns key,value
@@ -796,13 +796,13 @@ STAGE PLANS:
columns.types string:string
#### A masked pattern was here ####
name default.bucket_big
- numFiles 4
+ numFiles 2
numRows 0
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
+ totalSize 2750
#### A masked pattern was here ####
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.bucket_big
http://git-wip-us.apache.org/repos/asf/hive/blob/3464df45/ql/src/test/results/clientpositive/auto_sortmerge_join_7.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/auto_sortmerge_join_7.q.out b/ql/src/test/results/clientpositive/auto_sortmerge_join_7.q.out
index f335142..1959075 100644
--- a/ql/src/test/results/clientpositive/auto_sortmerge_join_7.q.out
+++ b/ql/src/test/results/clientpositive/auto_sortmerge_join_7.q.out
@@ -72,11 +72,11 @@ POSTHOOK: query: load data local inpath '../../data/files/auto_sortmerge_join/sm
POSTHOOK: type: LOAD
#### A masked pattern was here ####
POSTHOOK: Output: default@bucket_small@ds=2008-04-09
-PREHOOK: query: CREATE TABLE bucket_big (key string, value string) partitioned by (ds string) CLUSTERED BY (key) SORTED BY (key) INTO 4 BUCKETS STORED AS TEXTFILE
+PREHOOK: query: CREATE TABLE bucket_big (key string, value string) partitioned by (ds string) CLUSTERED BY (key) SORTED BY (key) INTO 2 BUCKETS STORED AS TEXTFILE
PREHOOK: type: CREATETABLE
PREHOOK: Output: database:default
PREHOOK: Output: default@bucket_big
-POSTHOOK: query: CREATE TABLE bucket_big (key string, value string) partitioned by (ds string) CLUSTERED BY (key) SORTED BY (key) INTO 4 BUCKETS STORED AS TEXTFILE
+POSTHOOK: query: CREATE TABLE bucket_big (key string, value string) partitioned by (ds string) CLUSTERED BY (key) SORTED BY (key) INTO 2 BUCKETS STORED AS TEXTFILE
POSTHOOK: type: CREATETABLE
POSTHOOK: Output: database:default
POSTHOOK: Output: default@bucket_big
@@ -97,22 +97,6 @@ POSTHOOK: query: load data local inpath '../../data/files/auto_sortmerge_join/bi
POSTHOOK: type: LOAD
#### A masked pattern was here ####
POSTHOOK: Output: default@bucket_big@ds=2008-04-08
-PREHOOK: query: load data local inpath '../../data/files/auto_sortmerge_join/big/000002_0' INTO TABLE bucket_big partition(ds='2008-04-08')
-PREHOOK: type: LOAD
-#### A masked pattern was here ####
-PREHOOK: Output: default@bucket_big@ds=2008-04-08
-POSTHOOK: query: load data local inpath '../../data/files/auto_sortmerge_join/big/000002_0' INTO TABLE bucket_big partition(ds='2008-04-08')
-POSTHOOK: type: LOAD
-#### A masked pattern was here ####
-POSTHOOK: Output: default@bucket_big@ds=2008-04-08
-PREHOOK: query: load data local inpath '../../data/files/auto_sortmerge_join/big/000003_0' INTO TABLE bucket_big partition(ds='2008-04-08')
-PREHOOK: type: LOAD
-#### A masked pattern was here ####
-PREHOOK: Output: default@bucket_big@ds=2008-04-08
-POSTHOOK: query: load data local inpath '../../data/files/auto_sortmerge_join/big/000003_0' INTO TABLE bucket_big partition(ds='2008-04-08')
-POSTHOOK: type: LOAD
-#### A masked pattern was here ####
-POSTHOOK: Output: default@bucket_big@ds=2008-04-08
PREHOOK: query: load data local inpath '../../data/files/auto_sortmerge_join/big/000000_0' INTO TABLE bucket_big partition(ds='2008-04-09')
PREHOOK: type: LOAD
#### A masked pattern was here ####
@@ -130,22 +114,6 @@ POSTHOOK: query: load data local inpath '../../data/files/auto_sortmerge_join/bi
POSTHOOK: type: LOAD
#### A masked pattern was here ####
POSTHOOK: Output: default@bucket_big@ds=2008-04-09
-PREHOOK: query: load data local inpath '../../data/files/auto_sortmerge_join/big/000002_0' INTO TABLE bucket_big partition(ds='2008-04-09')
-PREHOOK: type: LOAD
-#### A masked pattern was here ####
-PREHOOK: Output: default@bucket_big@ds=2008-04-09
-POSTHOOK: query: load data local inpath '../../data/files/auto_sortmerge_join/big/000002_0' INTO TABLE bucket_big partition(ds='2008-04-09')
-POSTHOOK: type: LOAD
-#### A masked pattern was here ####
-POSTHOOK: Output: default@bucket_big@ds=2008-04-09
-PREHOOK: query: load data local inpath '../../data/files/auto_sortmerge_join/big/000003_0' INTO TABLE bucket_big partition(ds='2008-04-09')
-PREHOOK: type: LOAD
-#### A masked pattern was here ####
-PREHOOK: Output: default@bucket_big@ds=2008-04-09
-POSTHOOK: query: load data local inpath '../../data/files/auto_sortmerge_join/big/000003_0' INTO TABLE bucket_big partition(ds='2008-04-09')
-POSTHOOK: type: LOAD
-#### A masked pattern was here ####
-POSTHOOK: Output: default@bucket_big@ds=2008-04-09
PREHOOK: query: explain extended select count(*) FROM bucket_small a JOIN bucket_big b ON a.key = b.key
PREHOOK: type: QUERY
POSTHOOK: query: explain extended select count(*) FROM bucket_small a JOIN bucket_big b ON a.key = b.key
@@ -160,16 +128,16 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: b
- Statistics: Num rows: 240 Data size: 116240 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 112 Data size: 55000 Basic stats: COMPLETE Column stats: NONE
GatherStats: false
Filter Operator
isSamplingPred: false
predicate: key is not null (type: boolean)
- Statistics: Num rows: 240 Data size: 116240 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 112 Data size: 55000 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: key (type: string)
outputColumnNames: _col0
- Statistics: Num rows: 240 Data size: 116240 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 112 Data size: 55000 Basic stats: COMPLETE Column stats: NONE
Sorted Merge Bucket Map Join Operator
condition map:
Inner Join 0 to 1
@@ -199,7 +167,7 @@ STAGE PLANS:
partition values:
ds 2008-04-08
properties:
- bucket_count 4
+ bucket_count 2
bucket_field_name key
column.name.delimiter ,
columns key,value
@@ -207,7 +175,7 @@ STAGE PLANS:
columns.types string:string
#### A masked pattern was here ####
name default.bucket_big
- numFiles 4
+ numFiles 2
numRows 0
partition_columns ds
partition_columns.types string
@@ -215,7 +183,7 @@ STAGE PLANS:
serialization.ddl struct bucket_big { string key, string value}
serialization.format 1
serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 5812
+ totalSize 2750
#### A masked pattern was here ####
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
@@ -223,7 +191,7 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
SORTBUCKETCOLSPREFIX TRUE
- bucket_count 4
+ bucket_count 2
bucket_field_name key
column.name.delimiter ,
columns key,value
@@ -248,7 +216,7 @@ STAGE PLANS:
partition values:
ds 2008-04-09
properties:
- bucket_count 4
+ bucket_count 2
bucket_field_name key
column.name.delimiter ,
columns key,value
@@ -256,7 +224,7 @@ STAGE PLANS:
columns.types string:string
#### A masked pattern was here ####
name default.bucket_big
- numFiles 4
+ numFiles 2
numRows 0
partition_columns ds
partition_columns.types string
@@ -264,7 +232,7 @@ STAGE PLANS:
serialization.ddl struct bucket_big { string key, string value}
serialization.format 1
serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 5812
+ totalSize 2750
#### A masked pattern was here ####
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
@@ -272,7 +240,7 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
SORTBUCKETCOLSPREFIX TRUE
- bucket_count 4
+ bucket_count 2
bucket_field_name key
column.name.delimiter ,
columns key,value
@@ -344,7 +312,7 @@ POSTHOOK: Input: default@bucket_small
POSTHOOK: Input: default@bucket_small@ds=2008-04-08
POSTHOOK: Input: default@bucket_small@ds=2008-04-09
#### A masked pattern was here ####
-156
+76
PREHOOK: query: explain extended select count(*) FROM bucket_big a JOIN bucket_small b ON a.key = b.key
PREHOOK: type: QUERY
POSTHOOK: query: explain extended select count(*) FROM bucket_big a JOIN bucket_small b ON a.key = b.key
@@ -359,16 +327,16 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: a
- Statistics: Num rows: 240 Data size: 116240 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 112 Data size: 55000 Basic stats: COMPLETE Column stats: NONE
GatherStats: false
Filter Operator
isSamplingPred: false
predicate: key is not null (type: boolean)
- Statistics: Num rows: 240 Data size: 116240 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 112 Data size: 55000 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: key (type: string)
outputColumnNames: _col0
- Statistics: Num rows: 240 Data size: 116240 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 112 Data size: 55000 Basic stats: COMPLETE Column stats: NONE
Sorted Merge Bucket Map Join Operator
condition map:
Inner Join 0 to 1
@@ -398,7 +366,7 @@ STAGE PLANS:
partition values:
ds 2008-04-08
properties:
- bucket_count 4
+ bucket_count 2
bucket_field_name key
column.name.delimiter ,
columns key,value
@@ -406,7 +374,7 @@ STAGE PLANS:
columns.types string:string
#### A masked pattern was here ####
name default.bucket_big
- numFiles 4
+ numFiles 2
numRows 0
partition_columns ds
partition_columns.types string
@@ -414,7 +382,7 @@ STAGE PLANS:
serialization.ddl struct bucket_big { string key, string value}
serialization.format 1
serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 5812
+ totalSize 2750
#### A masked pattern was here ####
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
@@ -422,7 +390,7 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
SORTBUCKETCOLSPREFIX TRUE
- bucket_count 4
+ bucket_count 2
bucket_field_name key
column.name.delimiter ,
columns key,value
@@ -447,7 +415,7 @@ STAGE PLANS:
partition values:
ds 2008-04-09
properties:
- bucket_count 4
+ bucket_count 2
bucket_field_name key
column.name.delimiter ,
columns key,value
@@ -455,7 +423,7 @@ STAGE PLANS:
columns.types string:string
#### A masked pattern was here ####
name default.bucket_big
- numFiles 4
+ numFiles 2
numRows 0
partition_columns ds
partition_columns.types string
@@ -463,7 +431,7 @@ STAGE PLANS:
serialization.ddl struct bucket_big { string key, string value}
serialization.format 1
serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 5812
+ totalSize 2750
#### A masked pattern was here ####
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
@@ -471,7 +439,7 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
SORTBUCKETCOLSPREFIX TRUE
- bucket_count 4
+ bucket_count 2
bucket_field_name key
column.name.delimiter ,
columns key,value
@@ -543,7 +511,7 @@ POSTHOOK: Input: default@bucket_small
POSTHOOK: Input: default@bucket_small@ds=2008-04-08
POSTHOOK: Input: default@bucket_small@ds=2008-04-09
#### A masked pattern was here ####
-156
+76
PREHOOK: query: explain extended select count(*) FROM bucket_big a JOIN bucket_small b ON a.key = b.key
PREHOOK: type: QUERY
POSTHOOK: query: explain extended select count(*) FROM bucket_big a JOIN bucket_small b ON a.key = b.key
@@ -687,16 +655,16 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: a
- Statistics: Num rows: 240 Data size: 116240 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 112 Data size: 55000 Basic stats: COMPLETE Column stats: NONE
GatherStats: false
Filter Operator
isSamplingPred: false
predicate: key is not null (type: boolean)
- Statistics: Num rows: 240 Data size: 116240 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 112 Data size: 55000 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: key (type: string)
outputColumnNames: _col0
- Statistics: Num rows: 240 Data size: 116240 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 112 Data size: 55000 Basic stats: COMPLETE Column stats: NONE
Map Join Operator
condition map:
Inner Join 0 to 1
@@ -727,7 +695,7 @@ STAGE PLANS:
partition values:
ds 2008-04-08
properties:
- bucket_count 4
+ bucket_count 2
bucket_field_name key
column.name.delimiter ,
columns key,value
@@ -735,7 +703,7 @@ STAGE PLANS:
columns.types string:string
#### A masked pattern was here ####
name default.bucket_big
- numFiles 4
+ numFiles 2
numRows 0
partition_columns ds
partition_columns.types string
@@ -743,7 +711,7 @@ STAGE PLANS:
serialization.ddl struct bucket_big { string key, string value}
serialization.format 1
serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 5812
+ totalSize 2750
#### A masked pattern was here ####
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
@@ -751,7 +719,7 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
SORTBUCKETCOLSPREFIX TRUE
- bucket_count 4
+ bucket_count 2
bucket_field_name key
column.name.delimiter ,
columns key,value
@@ -776,7 +744,7 @@ STAGE PLANS:
partition values:
ds 2008-04-09
properties:
- bucket_count 4
+ bucket_count 2
bucket_field_name key
column.name.delimiter ,
columns key,value
@@ -784,7 +752,7 @@ STAGE PLANS:
columns.types string:string
#### A masked pattern was here ####
name default.bucket_big
- numFiles 4
+ numFiles 2
numRows 0
partition_columns ds
partition_columns.types string
@@ -792,7 +760,7 @@ STAGE PLANS:
serialization.ddl struct bucket_big { string key, string value}
serialization.format 1
serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 5812
+ totalSize 2750
#### A masked pattern was here ####
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
@@ -800,7 +768,7 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
SORTBUCKETCOLSPREFIX TRUE
- bucket_count 4
+ bucket_count 2
bucket_field_name key
column.name.delimiter ,
columns key,value
@@ -958,7 +926,7 @@ STAGE PLANS:
partition values:
ds 2008-04-08
properties:
- bucket_count 4
+ bucket_count 2
bucket_field_name key
column.name.delimiter ,
columns key,value
@@ -966,7 +934,7 @@ STAGE PLANS:
columns.types string:string
#### A masked pattern was here ####
name default.bucket_big
- numFiles 4
+ numFiles 2
numRows 0
partition_columns ds
partition_columns.types string
@@ -974,7 +942,7 @@ STAGE PLANS:
serialization.ddl struct bucket_big { string key, string value}
serialization.format 1
serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 5812
+ totalSize 2750
#### A masked pattern was here ####
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
@@ -982,7 +950,7 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
SORTBUCKETCOLSPREFIX TRUE
- bucket_count 4
+ bucket_count 2
bucket_field_name key
column.name.delimiter ,
columns key,value
@@ -1006,7 +974,7 @@ STAGE PLANS:
partition values:
ds 2008-04-09
properties:
- bucket_count 4
+ bucket_count 2
bucket_field_name key
column.name.delimiter ,
columns key,value
@@ -1014,7 +982,7 @@ STAGE PLANS:
columns.types string:string
#### A masked pattern was here ####
name default.bucket_big
- numFiles 4
+ numFiles 2
numRows 0
partition_columns ds
partition_columns.types string
@@ -1022,7 +990,7 @@ STAGE PLANS:
serialization.ddl struct bucket_big { string key, string value}
serialization.format 1
serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 5812
+ totalSize 2750
#### A masked pattern was here ####
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
@@ -1030,7 +998,7 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
SORTBUCKETCOLSPREFIX TRUE
- bucket_count 4
+ bucket_count 2
bucket_field_name key
column.name.delimiter ,
columns key,value
@@ -1051,16 +1019,16 @@ STAGE PLANS:
$hdt$_0:a
TableScan
alias: a
- Statistics: Num rows: 240 Data size: 116240 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 112 Data size: 55000 Basic stats: COMPLETE Column stats: NONE
GatherStats: false
Filter Operator
isSamplingPred: false
predicate: key is not null (type: boolean)
- Statistics: Num rows: 240 Data size: 116240 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 112 Data size: 55000 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: key (type: string)
outputColumnNames: _col0
- Statistics: Num rows: 240 Data size: 116240 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 112 Data size: 55000 Basic stats: COMPLETE Column stats: NONE
HashTable Sink Operator
keys:
0 _col0 (type: string)
@@ -1112,7 +1080,7 @@ STAGE PLANS:
partition values:
ds 2008-04-08
properties:
- bucket_count 4
+ bucket_count 2
bucket_field_name key
column.name.delimiter ,
columns key,value
@@ -1120,7 +1088,7 @@ STAGE PLANS:
columns.types string:string
#### A masked pattern was here ####
name default.bucket_big
- numFiles 4
+ numFiles 2
numRows 0
partition_columns ds
partition_columns.types string
@@ -1128,7 +1096,7 @@ STAGE PLANS:
serialization.ddl struct bucket_big { string key, string value}
serialization.format 1
serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 5812
+ totalSize 2750
#### A masked pattern was here ####
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
@@ -1136,7 +1104,7 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
SORTBUCKETCOLSPREFIX TRUE
- bucket_count 4
+ bucket_count 2
bucket_field_name key
column.name.delimiter ,
columns key,value
@@ -1161,7 +1129,7 @@ STAGE PLANS:
partition values:
ds 2008-04-09
properties:
- bucket_count 4
+ bucket_count 2
bucket_field_name key
column.name.delimiter ,
columns key,value
@@ -1169,7 +1137,7 @@ STAGE PLANS:
columns.types string:string
#### A masked pattern was here ####
name default.bucket_big
- numFiles 4
+ numFiles 2
numRows 0
partition_columns ds
partition_columns.types string
@@ -1177,7 +1145,7 @@ STAGE PLANS:
serialization.ddl struct bucket_big { string key, string value}
serialization.format 1
serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 5812
+ totalSize 2750
#### A masked pattern was here ####
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
@@ -1185,7 +1153,7 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
SORTBUCKETCOLSPREFIX TRUE
- bucket_count 4
+ bucket_count 2
bucket_field_name key
column.name.delimiter ,
columns key,value
@@ -1334,16 +1302,16 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: a
- Statistics: Num rows: 240 Data size: 116240 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 112 Data size: 55000 Basic stats: COMPLETE Column stats: NONE
GatherStats: false
Filter Operator
isSamplingPred: false
predicate: key is not null (type: boolean)
- Statistics: Num rows: 240 Data size: 116240 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 112 Data size: 55000 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: key (type: string)
outputColumnNames: _col0
- Statistics: Num rows: 240 Data size: 116240 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 112 Data size: 55000 Basic stats: COMPLETE Column stats: NONE
Sorted Merge Bucket Map Join Operator
condition map:
Inner Join 0 to 1
@@ -1373,7 +1341,7 @@ STAGE PLANS:
partition values:
ds 2008-04-08
properties:
- bucket_count 4
+ bucket_count 2
bucket_field_name key
column.name.delimiter ,
columns key,value
@@ -1381,7 +1349,7 @@ STAGE PLANS:
columns.types string:string
#### A masked pattern was here ####
name default.bucket_big
- numFiles 4
+ numFiles 2
numRows 0
partition_columns ds
partition_columns.types string
@@ -1389,7 +1357,7 @@ STAGE PLANS:
serialization.ddl struct bucket_big { string key, string value}
serialization.format 1
serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 5812
+ totalSize 2750
#### A masked pattern was here ####
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
@@ -1397,7 +1365,7 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
SORTBUCKETCOLSPREFIX TRUE
- bucket_count 4
+ bucket_count 2
bucket_field_name key
column.name.delimiter ,
columns key,value
@@ -1422,7 +1390,7 @@ STAGE PLANS:
partition values:
ds 2008-04-09
properties:
- bucket_count 4
+ bucket_count 2
bucket_field_name key
column.name.delimiter ,
columns key,value
@@ -1430,7 +1398,7 @@ STAGE PLANS:
columns.types string:string
#### A masked pattern was here ####
name default.bucket_big
- numFiles 4
+ numFiles 2
numRows 0
partition_columns ds
partition_columns.types string
@@ -1438,7 +1406,7 @@ STAGE PLANS:
serialization.ddl struct bucket_big { string key, string value}
serialization.format 1
serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 5812
+ totalSize 2750
#### A masked pattern was here ####
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
@@ -1446,7 +1414,7 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
SORTBUCKETCOLSPREFIX TRUE
- bucket_count 4
+ bucket_count 2
bucket_field_name key
column.name.delimiter ,
columns key,value
@@ -1518,4 +1486,4 @@ POSTHOOK: Input: default@bucket_small
POSTHOOK: Input: default@bucket_small@ds=2008-04-08
POSTHOOK: Input: default@bucket_small@ds=2008-04-09
#### A masked pattern was here ####
-156
+76