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 21:13:12 UTC
[5/7] 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/llap/auto_sortmerge_join_2.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/auto_sortmerge_join_2.q.out b/ql/src/test/results/clientpositive/llap/auto_sortmerge_join_2.q.out
index d4472cf..054b0d0 100644
--- a/ql/src/test/results/clientpositive/llap/auto_sortmerge_join_2.q.out
+++ b/ql/src/test/results/clientpositive/llap/auto_sortmerge_join_2.q.out
@@ -1,8 +1,8 @@
-PREHOOK: query: CREATE TABLE bucket_small (key string, value string) partitioned by (ds string) CLUSTERED BY (key) SORTED BY (key) INTO 2 BUCKETS STORED AS TEXTFILE
+PREHOOK: query: CREATE TABLE bucket_small (key string, value string) partitioned by (ds 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) partitioned by (ds string) CLUSTERED BY (key) SORTED BY (key) INTO 2 BUCKETS STORED AS TEXTFILE
+POSTHOOK: query: CREATE TABLE bucket_small (key string, value string) partitioned by (ds 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
@@ -23,11 +23,27 @@ 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@ds=2008-04-08
-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: load data local inpath '../../data/files/auto_sortmerge_join/small/000002_0' INTO TABLE bucket_small partition(ds='2008-04-08')
+PREHOOK: type: LOAD
+#### A masked pattern was here ####
+PREHOOK: Output: default@bucket_small@ds=2008-04-08
+POSTHOOK: query: load data local inpath '../../data/files/auto_sortmerge_join/small/000002_0' INTO TABLE bucket_small partition(ds='2008-04-08')
+POSTHOOK: type: LOAD
+#### A masked pattern was here ####
+POSTHOOK: Output: default@bucket_small@ds=2008-04-08
+PREHOOK: query: load data local inpath '../../data/files/auto_sortmerge_join/small/000003_0' INTO TABLE bucket_small partition(ds='2008-04-08')
+PREHOOK: type: LOAD
+#### A masked pattern was here ####
+PREHOOK: Output: default@bucket_small@ds=2008-04-08
+POSTHOOK: query: load data local inpath '../../data/files/auto_sortmerge_join/small/000003_0' INTO TABLE bucket_small partition(ds='2008-04-08')
+POSTHOOK: type: LOAD
+#### A masked pattern was here ####
+POSTHOOK: Output: default@bucket_small@ds=2008-04-08
+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
@@ -48,22 +64,6 @@ 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 ####
@@ -81,22 +81,6 @@ 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_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
@@ -117,16 +101,16 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: b
- Statistics: Num rows: 2 Data size: 1508 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4 Data size: 2996 Basic stats: COMPLETE Column stats: NONE
GatherStats: false
Filter Operator
isSamplingPred: false
predicate: key is not null (type: boolean)
- Statistics: Num rows: 2 Data size: 1508 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4 Data size: 2996 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: key (type: string)
outputColumnNames: _col0
- Statistics: Num rows: 2 Data size: 1508 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4 Data size: 2996 Basic stats: COMPLETE Column stats: NONE
Path -> Alias:
#### A masked pattern was here ####
Path -> Partition:
@@ -137,7 +121,7 @@ STAGE PLANS:
partition values:
ds 2008-04-08
properties:
- bucket_count 2
+ bucket_count 4
bucket_field_name key
column.name.delimiter ,
columns key,value
@@ -145,7 +129,7 @@ STAGE PLANS:
columns.types string:string
#### A masked pattern was here ####
name default.bucket_small
- numFiles 2
+ numFiles 4
numRows 0
partition_columns ds
partition_columns.types string
@@ -153,7 +137,7 @@ STAGE PLANS:
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
@@ -161,7 +145,7 @@ 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
@@ -183,16 +167,16 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: a
- Statistics: Num rows: 240 Data size: 158376 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 112 Data size: 74872 Basic stats: COMPLETE Column stats: NONE
GatherStats: false
Filter Operator
isSamplingPred: false
predicate: key is not null (type: boolean)
- Statistics: Num rows: 228 Data size: 150457 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 107 Data size: 71529 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: key (type: string)
outputColumnNames: _col0
- Statistics: Num rows: 228 Data size: 150457 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 107 Data size: 71529 Basic stats: COMPLETE Column stats: NONE
Merge Join Operator
condition map:
Inner Join 0 to 1
@@ -200,7 +184,7 @@ STAGE PLANS:
0 _col0 (type: string)
1 _col0 (type: string)
Position of Big Table: 0
- Statistics: Num rows: 250 Data size: 165502 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 117 Data size: 78681 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: count()
mode: hash
@@ -224,7 +208,7 @@ 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
@@ -232,7 +216,7 @@ 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
@@ -240,7 +224,7 @@ 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
@@ -248,7 +232,7 @@ 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
@@ -272,7 +256,7 @@ 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
@@ -280,7 +264,7 @@ 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
@@ -288,7 +272,7 @@ 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
@@ -296,7 +280,7 @@ 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
@@ -391,16 +375,16 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: b
- Statistics: Num rows: 2 Data size: 1508 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4 Data size: 2996 Basic stats: COMPLETE Column stats: NONE
GatherStats: false
Filter Operator
isSamplingPred: false
predicate: key is not null (type: boolean)
- Statistics: Num rows: 2 Data size: 1508 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4 Data size: 2996 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: key (type: string)
outputColumnNames: _col0
- Statistics: Num rows: 2 Data size: 1508 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4 Data size: 2996 Basic stats: COMPLETE Column stats: NONE
Path -> Alias:
#### A masked pattern was here ####
Path -> Partition:
@@ -411,7 +395,7 @@ STAGE PLANS:
partition values:
ds 2008-04-08
properties:
- bucket_count 2
+ bucket_count 4
bucket_field_name key
column.name.delimiter ,
columns key,value
@@ -419,7 +403,7 @@ STAGE PLANS:
columns.types string:string
#### A masked pattern was here ####
name default.bucket_small
- numFiles 2
+ numFiles 4
numRows 0
partition_columns ds
partition_columns.types string
@@ -427,7 +411,7 @@ STAGE PLANS:
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
@@ -435,7 +419,7 @@ 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
@@ -457,16 +441,16 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: a
- Statistics: Num rows: 240 Data size: 158376 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 112 Data size: 74872 Basic stats: COMPLETE Column stats: NONE
GatherStats: false
Filter Operator
isSamplingPred: false
predicate: key is not null (type: boolean)
- Statistics: Num rows: 228 Data size: 150457 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 107 Data size: 71529 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: key (type: string)
outputColumnNames: _col0
- Statistics: Num rows: 228 Data size: 150457 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 107 Data size: 71529 Basic stats: COMPLETE Column stats: NONE
Merge Join Operator
condition map:
Inner Join 0 to 1
@@ -474,7 +458,7 @@ STAGE PLANS:
0 _col0 (type: string)
1 _col0 (type: string)
Position of Big Table: 0
- Statistics: Num rows: 250 Data size: 165502 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 117 Data size: 78681 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: count()
mode: hash
@@ -498,7 +482,7 @@ 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
@@ -506,7 +490,7 @@ 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
@@ -514,7 +498,7 @@ 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
@@ -522,7 +506,7 @@ 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
@@ -546,7 +530,7 @@ 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
@@ -554,7 +538,7 @@ 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
@@ -562,7 +546,7 @@ 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
@@ -570,7 +554,7 @@ 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
http://git-wip-us.apache.org/repos/asf/hive/blob/3464df45/ql/src/test/results/clientpositive/llap/auto_sortmerge_join_4.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/auto_sortmerge_join_4.q.out b/ql/src/test/results/clientpositive/llap/auto_sortmerge_join_4.q.out
index 5cd5d79..95d3298 100644
--- a/ql/src/test/results/clientpositive/llap/auto_sortmerge_join_4.q.out
+++ b/ql/src/test/results/clientpositive/llap/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
@@ -248,16 +232,16 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: b
- Statistics: Num rows: 120 Data size: 79280 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 56 Data size: 37620 Basic stats: COMPLETE Column stats: NONE
GatherStats: false
Filter Operator
isSamplingPred: false
predicate: key is not null (type: boolean)
- Statistics: Num rows: 114 Data size: 75316 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 54 Data size: 36276 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: key (type: string)
outputColumnNames: _col0
- Statistics: Num rows: 114 Data size: 75316 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 54 Data size: 36276 Basic stats: COMPLETE Column stats: NONE
Merge Join Operator
condition map:
Inner Join 0 to 1
@@ -265,7 +249,7 @@ STAGE PLANS:
0 _col0 (type: string)
1 _col0 (type: string)
Position of Big Table: 1
- Statistics: Num rows: 125 Data size: 82847 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 59 Data size: 39903 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: count()
mode: hash
@@ -289,7 +273,7 @@ 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
@@ -297,7 +281,7 @@ 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
@@ -305,7 +289,7 @@ 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
@@ -313,7 +297,7 @@ 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
@@ -386,7 +370,7 @@ 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
@@ -522,16 +506,16 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: a
- Statistics: Num rows: 120 Data size: 79280 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 56 Data size: 37620 Basic stats: COMPLETE Column stats: NONE
GatherStats: false
Filter Operator
isSamplingPred: false
predicate: key is not null (type: boolean)
- Statistics: Num rows: 114 Data size: 75316 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 54 Data size: 36276 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: key (type: string)
outputColumnNames: _col0
- Statistics: Num rows: 114 Data size: 75316 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 54 Data size: 36276 Basic stats: COMPLETE Column stats: NONE
Merge Join Operator
condition map:
Inner Join 0 to 1
@@ -539,7 +523,7 @@ STAGE PLANS:
0 _col0 (type: string)
1 _col0 (type: string)
Position of Big Table: 0
- Statistics: Num rows: 125 Data size: 82847 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 59 Data size: 39903 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: count()
mode: hash
@@ -563,7 +547,7 @@ 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
@@ -571,7 +555,7 @@ 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
@@ -579,7 +563,7 @@ 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
@@ -587,7 +571,7 @@ 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
@@ -660,7 +644,7 @@ 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
@@ -796,16 +780,16 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: a
- Statistics: Num rows: 120 Data size: 79280 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 56 Data size: 37620 Basic stats: COMPLETE Column stats: NONE
GatherStats: false
Filter Operator
isSamplingPred: false
predicate: key is not null (type: boolean)
- Statistics: Num rows: 114 Data size: 75316 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 54 Data size: 36276 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: key (type: string)
outputColumnNames: _col0
- Statistics: Num rows: 114 Data size: 75316 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 54 Data size: 36276 Basic stats: COMPLETE Column stats: NONE
Merge Join Operator
condition map:
Inner Join 0 to 1
@@ -813,7 +797,7 @@ STAGE PLANS:
0 _col0 (type: string)
1 _col0 (type: string)
Position of Big Table: 0
- Statistics: Num rows: 125 Data size: 82847 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 59 Data size: 39903 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: count()
mode: hash
@@ -837,7 +821,7 @@ 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
@@ -845,7 +829,7 @@ 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
@@ -853,7 +837,7 @@ 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
@@ -861,7 +845,7 @@ 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
@@ -934,4 +918,4 @@ 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/llap/auto_sortmerge_join_5.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/auto_sortmerge_join_5.q.out b/ql/src/test/results/clientpositive/llap/auto_sortmerge_join_5.q.out
index a18f4b2..e711715 100644
--- a/ql/src/test/results/clientpositive/llap/auto_sortmerge_join_5.q.out
+++ b/ql/src/test/results/clientpositive/llap/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
@@ -101,7 +101,7 @@ 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
@@ -109,13 +109,13 @@ 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
@@ -123,7 +123,7 @@ 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
@@ -131,13 +131,13 @@ 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
@@ -187,7 +187,7 @@ 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
@@ -195,13 +195,13 @@ 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
@@ -209,7 +209,7 @@ 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
@@ -217,13 +217,13 @@ 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
@@ -318,7 +318,7 @@ 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
@@ -326,13 +326,13 @@ 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
@@ -340,7 +340,7 @@ 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
@@ -348,13 +348,13 @@ 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
@@ -404,7 +404,7 @@ 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
@@ -412,13 +412,13 @@ 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
@@ -426,7 +426,7 @@ 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
@@ -434,13 +434,13 @@ 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
@@ -562,7 +562,7 @@ 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
@@ -570,13 +570,13 @@ 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
@@ -584,7 +584,7 @@ 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
@@ -592,13 +592,13 @@ 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
@@ -639,7 +639,7 @@ 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
@@ -647,13 +647,13 @@ 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
@@ -661,7 +661,7 @@ 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
@@ -669,13 +669,13 @@ 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
http://git-wip-us.apache.org/repos/asf/hive/blob/3464df45/ql/src/test/results/clientpositive/llap/auto_sortmerge_join_7.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/auto_sortmerge_join_7.q.out b/ql/src/test/results/clientpositive/llap/auto_sortmerge_join_7.q.out
index fdea211..53c685c 100644
--- a/ql/src/test/results/clientpositive/llap/auto_sortmerge_join_7.q.out
+++ b/ql/src/test/results/clientpositive/llap/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
@@ -281,16 +249,16 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: b
- Statistics: Num rows: 240 Data size: 158376 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 112 Data size: 74872 Basic stats: COMPLETE Column stats: NONE
GatherStats: false
Filter Operator
isSamplingPred: false
predicate: key is not null (type: boolean)
- Statistics: Num rows: 228 Data size: 150457 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 107 Data size: 71529 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: key (type: string)
outputColumnNames: _col0
- Statistics: Num rows: 228 Data size: 150457 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 107 Data size: 71529 Basic stats: COMPLETE Column stats: NONE
Merge Join Operator
condition map:
Inner Join 0 to 1
@@ -298,7 +266,7 @@ STAGE PLANS:
0 _col0 (type: string)
1 _col0 (type: string)
Position of Big Table: 1
- Statistics: Num rows: 250 Data size: 165502 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 117 Data size: 78681 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: count()
mode: hash
@@ -322,7 +290,7 @@ 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
@@ -330,7 +298,7 @@ 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
@@ -338,7 +306,7 @@ 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
@@ -346,7 +314,7 @@ 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
@@ -370,7 +338,7 @@ 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
@@ -378,7 +346,7 @@ 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
@@ -386,7 +354,7 @@ 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
@@ -394,7 +362,7 @@ 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
@@ -470,7 +438,7 @@ 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
@@ -606,16 +574,16 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: a
- Statistics: Num rows: 240 Data size: 158376 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 112 Data size: 74872 Basic stats: COMPLETE Column stats: NONE
GatherStats: false
Filter Operator
isSamplingPred: false
predicate: key is not null (type: boolean)
- Statistics: Num rows: 228 Data size: 150457 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 107 Data size: 71529 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: key (type: string)
outputColumnNames: _col0
- Statistics: Num rows: 228 Data size: 150457 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 107 Data size: 71529 Basic stats: COMPLETE Column stats: NONE
Merge Join Operator
condition map:
Inner Join 0 to 1
@@ -623,7 +591,7 @@ STAGE PLANS:
0 _col0 (type: string)
1 _col0 (type: string)
Position of Big Table: 0
- Statistics: Num rows: 250 Data size: 165502 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 117 Data size: 78681 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: count()
mode: hash
@@ -647,7 +615,7 @@ 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
@@ -655,7 +623,7 @@ 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
@@ -663,7 +631,7 @@ 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
@@ -671,7 +639,7 @@ 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
@@ -695,7 +663,7 @@ 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
@@ -703,7 +671,7 @@ 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
@@ -711,7 +679,7 @@ 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
@@ -719,7 +687,7 @@ 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
@@ -795,7 +763,7 @@ 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
@@ -931,16 +899,16 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: a
- Statistics: Num rows: 240 Data size: 158376 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 112 Data size: 74872 Basic stats: COMPLETE Column stats: NONE
GatherStats: false
Filter Operator
isSamplingPred: false
predicate: key is not null (type: boolean)
- Statistics: Num rows: 228 Data size: 150457 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 107 Data size: 71529 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: key (type: string)
outputColumnNames: _col0
- Statistics: Num rows: 228 Data size: 150457 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 107 Data size: 71529 Basic stats: COMPLETE Column stats: NONE
Merge Join Operator
condition map:
Inner Join 0 to 1
@@ -948,7 +916,7 @@ STAGE PLANS:
0 _col0 (type: string)
1 _col0 (type: string)
Position of Big Table: 0
- Statistics: Num rows: 250 Data size: 165502 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 117 Data size: 78681 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: count()
mode: hash
@@ -972,7 +940,7 @@ 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
@@ -980,7 +948,7 @@ 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
@@ -988,7 +956,7 @@ 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
@@ -996,7 +964,7 @@ 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
@@ -1020,7 +988,7 @@ 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
@@ -1028,7 +996,7 @@ 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
@@ -1036,7 +1004,7 @@ 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
@@ -1044,7 +1012,7 @@ 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
@@ -1120,4 +1088,4 @@ 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