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 2018/04/16 18:09:15 UTC
[06/11] hive git commit: HIVE-19195,
HIVE-17055 : Fix flaky tests and cleanup testconfiguration to run
llap specific tests in llap only.
http://git-wip-us.apache.org/repos/asf/hive/blob/77da6997/ql/src/test/results/clientpositive/auto_sortmerge_join_2.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/auto_sortmerge_join_2.q.out b/ql/src/test/results/clientpositive/auto_sortmerge_join_2.q.out
deleted file mode 100644
index 5cfc35a..0000000
--- a/ql/src/test/results/clientpositive/auto_sortmerge_join_2.q.out
+++ /dev/null
@@ -1,1109 +0,0 @@
-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 4 BUCKETS STORED AS TEXTFILE
-POSTHOOK: type: CREATETABLE
-POSTHOOK: Output: database:default
-POSTHOOK: Output: default@bucket_small
-PREHOOK: query: load data local inpath '../../data/files/auto_sortmerge_join/small/000000_0' INTO TABLE bucket_small partition(ds='2008-04-08')
-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/000000_0' INTO TABLE bucket_small partition(ds='2008-04-08')
-POSTHOOK: type: LOAD
-#### A masked pattern was here ####
-POSTHOOK: Output: default@bucket_small
-POSTHOOK: Output: default@bucket_small@ds=2008-04-08
-PREHOOK: query: load data local inpath '../../data/files/auto_sortmerge_join/small/000001_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/000001_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/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 2 BUCKETS STORED AS TEXTFILE
-POSTHOOK: type: CREATETABLE
-POSTHOOK: Output: database:default
-POSTHOOK: Output: default@bucket_big
-PREHOOK: query: load data local inpath '../../data/files/auto_sortmerge_join/big/000000_0' INTO TABLE bucket_big partition(ds='2008-04-08')
-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/000000_0' INTO TABLE bucket_big partition(ds='2008-04-08')
-POSTHOOK: type: LOAD
-#### A masked pattern was here ####
-POSTHOOK: Output: default@bucket_big
-POSTHOOK: Output: default@bucket_big@ds=2008-04-08
-PREHOOK: query: load data local inpath '../../data/files/auto_sortmerge_join/big/000001_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/000001_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 ####
-PREHOOK: Output: default@bucket_big
-POSTHOOK: query: load data local inpath '../../data/files/auto_sortmerge_join/big/000000_0' INTO TABLE bucket_big partition(ds='2008-04-09')
-POSTHOOK: type: LOAD
-#### A masked pattern was here ####
-POSTHOOK: Output: default@bucket_big
-POSTHOOK: Output: default@bucket_big@ds=2008-04-09
-PREHOOK: query: load data local inpath '../../data/files/auto_sortmerge_join/big/000001_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/000001_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
-POSTHOOK: type: QUERY
-STAGE DEPENDENCIES:
- Stage-1 is a root stage
- Stage-0 depends on stages: Stage-1
-
-STAGE PLANS:
- Stage: Stage-1
- Map Reduce
- Map Operator Tree:
- TableScan
- alias: a
- Statistics: Num rows: 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: 112 Data size: 55000 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: key (type: string)
- outputColumnNames: _col0
- 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
- keys:
- 0 _col0 (type: string)
- 1 _col0 (type: string)
- Position of Big Table: 0
- BucketMapJoin: true
- Group By Operator
- aggregations: count()
- mode: hash
- outputColumnNames: _col0
- Reduce Output Operator
- null sort order:
- sort order:
- tag: -1
- value expressions: _col0 (type: bigint)
- auto parallelism: false
- Path -> Alias:
-#### A masked pattern was here ####
- Path -> Partition:
-#### A masked pattern was here ####
- Partition
- base file name: ds=2008-04-08
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- partition values:
- ds 2008-04-08
- properties:
- bucket_count 2
- bucket_field_name key
- column.name.delimiter ,
- columns key,value
- columns.comments
- columns.types string:string
-#### A masked pattern was here ####
- name default.bucket_big
- numFiles 2
- numRows 0
- partition_columns ds
- partition_columns.types string
- rawDataSize 0
- serialization.ddl struct bucket_big { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 2750
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- SORTBUCKETCOLSPREFIX TRUE
- bucket_count 2
- bucket_field_name key
- column.name.delimiter ,
- columns key,value
- columns.comments
- columns.types string:string
-#### A masked pattern was here ####
- name default.bucket_big
- partition_columns ds
- partition_columns.types string
- serialization.ddl struct bucket_big { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.bucket_big
- name: default.bucket_big
-#### A masked pattern was here ####
- Partition
- base file name: ds=2008-04-09
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- partition values:
- ds 2008-04-09
- properties:
- bucket_count 2
- bucket_field_name key
- column.name.delimiter ,
- columns key,value
- columns.comments
- columns.types string:string
-#### A masked pattern was here ####
- name default.bucket_big
- numFiles 2
- numRows 0
- partition_columns ds
- partition_columns.types string
- rawDataSize 0
- serialization.ddl struct bucket_big { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 2750
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- SORTBUCKETCOLSPREFIX TRUE
- bucket_count 2
- bucket_field_name key
- column.name.delimiter ,
- columns key,value
- columns.comments
- columns.types string:string
-#### A masked pattern was here ####
- name default.bucket_big
- partition_columns ds
- partition_columns.types string
- serialization.ddl struct bucket_big { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.bucket_big
- name: default.bucket_big
- Truncated Path -> Alias:
- /bucket_big/ds=2008-04-08 [$hdt$_0:a]
- /bucket_big/ds=2008-04-09 [$hdt$_0:a]
- Needs Tagging: false
- Reduce Operator Tree:
- Group By Operator
- aggregations: count(VALUE._col0)
- mode: mergepartial
- outputColumnNames: _col0
- File Output Operator
- compressed: false
- GlobalTableId: 0
-#### A masked pattern was here ####
- NumFilesPerFileSink: 1
-#### A masked pattern was here ####
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- properties:
- columns _col0
- columns.types bigint
- escape.delim \
- hive.serialization.extend.additional.nesting.levels true
- serialization.escape.crlf true
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- TotalFiles: 1
- GatherStats: false
- MultiFileSpray: false
-
- Stage: Stage-0
- Fetch Operator
- limit: -1
- Processor Tree:
- ListSink
-
-PREHOOK: query: select count(*) FROM bucket_big a JOIN bucket_small b ON a.key = b.key
-PREHOOK: type: QUERY
-PREHOOK: Input: default@bucket_big
-PREHOOK: Input: default@bucket_big@ds=2008-04-08
-PREHOOK: Input: default@bucket_big@ds=2008-04-09
-PREHOOK: Input: default@bucket_small
-PREHOOK: Input: default@bucket_small@ds=2008-04-08
-#### A masked pattern was here ####
-POSTHOOK: query: select count(*) FROM bucket_big a JOIN bucket_small b ON a.key = b.key
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@bucket_big
-POSTHOOK: Input: default@bucket_big@ds=2008-04-08
-POSTHOOK: Input: default@bucket_big@ds=2008-04-09
-POSTHOOK: Input: default@bucket_small
-POSTHOOK: Input: default@bucket_small@ds=2008-04-08
-#### A masked pattern was here ####
-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
-POSTHOOK: type: QUERY
-STAGE DEPENDENCIES:
- Stage-5 is a root stage , consists of Stage-6, Stage-7, Stage-1
- Stage-6 has a backup stage: Stage-1
- Stage-3 depends on stages: Stage-6
- Stage-7 has a backup stage: Stage-1
- Stage-4 depends on stages: Stage-7
- Stage-1
- Stage-0 depends on stages: Stage-3, Stage-4, Stage-1
-
-STAGE PLANS:
- Stage: Stage-5
- Conditional Operator
-
- Stage: Stage-6
- Map Reduce Local Work
- Alias -> Map Local Tables:
- $hdt$_1:b
- Fetch Operator
- limit: -1
- Partition Description:
- Partition
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- partition values:
- ds 2008-04-08
- properties:
- bucket_count 4
- bucket_field_name key
- column.name.delimiter ,
- columns key,value
- columns.comments
- columns.types string:string
-#### A masked pattern was here ####
- name default.bucket_small
- numFiles 4
- numRows 0
- partition_columns ds
- partition_columns.types string
- rawDataSize 0
- serialization.ddl struct bucket_small { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 226
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- SORTBUCKETCOLSPREFIX TRUE
- bucket_count 4
- bucket_field_name key
- column.name.delimiter ,
- columns key,value
- columns.comments
- columns.types string:string
-#### A masked pattern was here ####
- name default.bucket_small
- partition_columns ds
- partition_columns.types string
- serialization.ddl struct bucket_small { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.bucket_small
- name: default.bucket_small
- Alias -> Map Local Operator Tree:
- $hdt$_1:b
- TableScan
- alias: b
- Statistics: Num rows: 4 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: 4 Data size: 2260 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: key (type: string)
- outputColumnNames: _col0
- Statistics: Num rows: 4 Data size: 2260 Basic stats: COMPLETE Column stats: NONE
- HashTable Sink Operator
- keys:
- 0 _col0 (type: string)
- 1 _col0 (type: string)
- Position of Big Table: 0
-
- Stage: Stage-3
- Map Reduce
- Map Operator Tree:
- TableScan
- alias: a
- 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: 112 Data size: 55000 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: key (type: string)
- outputColumnNames: _col0
- Statistics: Num rows: 112 Data size: 55000 Basic stats: COMPLETE Column stats: NONE
- Map Join Operator
- condition map:
- Inner Join 0 to 1
- keys:
- 0 _col0 (type: string)
- 1 _col0 (type: string)
- Position of Big Table: 0
- Group By Operator
- aggregations: count()
- mode: hash
- outputColumnNames: _col0
- Reduce Output Operator
- null sort order:
- sort order:
- tag: -1
- value expressions: _col0 (type: bigint)
- auto parallelism: false
- Local Work:
- Map Reduce Local Work
- Path -> Alias:
-#### A masked pattern was here ####
- Path -> Partition:
-#### A masked pattern was here ####
- Partition
- base file name: ds=2008-04-08
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- partition values:
- ds 2008-04-08
- properties:
- bucket_count 2
- bucket_field_name key
- column.name.delimiter ,
- columns key,value
- columns.comments
- columns.types string:string
-#### A masked pattern was here ####
- name default.bucket_big
- numFiles 2
- numRows 0
- partition_columns ds
- partition_columns.types string
- rawDataSize 0
- serialization.ddl struct bucket_big { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 2750
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- SORTBUCKETCOLSPREFIX TRUE
- bucket_count 2
- bucket_field_name key
- column.name.delimiter ,
- columns key,value
- columns.comments
- columns.types string:string
-#### A masked pattern was here ####
- name default.bucket_big
- partition_columns ds
- partition_columns.types string
- serialization.ddl struct bucket_big { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.bucket_big
- name: default.bucket_big
-#### A masked pattern was here ####
- Partition
- base file name: ds=2008-04-09
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- partition values:
- ds 2008-04-09
- properties:
- bucket_count 2
- bucket_field_name key
- column.name.delimiter ,
- columns key,value
- columns.comments
- columns.types string:string
-#### A masked pattern was here ####
- name default.bucket_big
- numFiles 2
- numRows 0
- partition_columns ds
- partition_columns.types string
- rawDataSize 0
- serialization.ddl struct bucket_big { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 2750
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- SORTBUCKETCOLSPREFIX TRUE
- bucket_count 2
- bucket_field_name key
- column.name.delimiter ,
- columns key,value
- columns.comments
- columns.types string:string
-#### A masked pattern was here ####
- name default.bucket_big
- partition_columns ds
- partition_columns.types string
- serialization.ddl struct bucket_big { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.bucket_big
- name: default.bucket_big
-#### A masked pattern was here ####
- Partition
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- partition values:
- ds 2008-04-08
- properties:
- bucket_count 4
- bucket_field_name key
- column.name.delimiter ,
- columns key,value
- columns.comments
- columns.types string:string
-#### A masked pattern was here ####
- name default.bucket_small
- numFiles 4
- numRows 0
- partition_columns ds
- partition_columns.types string
- rawDataSize 0
- serialization.ddl struct bucket_small { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 226
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- SORTBUCKETCOLSPREFIX TRUE
- bucket_count 4
- bucket_field_name key
- column.name.delimiter ,
- columns key,value
- columns.comments
- columns.types string:string
-#### A masked pattern was here ####
- name default.bucket_small
- partition_columns ds
- partition_columns.types string
- serialization.ddl struct bucket_small { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.bucket_small
- name: default.bucket_small
- Truncated Path -> Alias:
- /bucket_big/ds=2008-04-08 [$hdt$_0:a]
- /bucket_big/ds=2008-04-09 [$hdt$_0:a]
- Needs Tagging: false
- Reduce Operator Tree:
- Group By Operator
- aggregations: count(VALUE._col0)
- mode: mergepartial
- outputColumnNames: _col0
- File Output Operator
- compressed: false
- GlobalTableId: 0
-#### A masked pattern was here ####
- NumFilesPerFileSink: 1
-#### A masked pattern was here ####
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- properties:
- columns _col0
- columns.types bigint
- escape.delim \
- hive.serialization.extend.additional.nesting.levels true
- serialization.escape.crlf true
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- TotalFiles: 1
- GatherStats: false
- MultiFileSpray: false
-
- Stage: Stage-7
- Map Reduce Local Work
- Alias -> Map Local Tables:
- $hdt$_0:a
- Fetch Operator
- limit: -1
- Partition Description:
- Partition
- base file name: ds=2008-04-08
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- partition values:
- ds 2008-04-08
- properties:
- bucket_count 2
- bucket_field_name key
- column.name.delimiter ,
- columns key,value
- columns.comments
- columns.types string:string
-#### A masked pattern was here ####
- name default.bucket_big
- numFiles 2
- numRows 0
- partition_columns ds
- partition_columns.types string
- rawDataSize 0
- serialization.ddl struct bucket_big { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 2750
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- SORTBUCKETCOLSPREFIX TRUE
- bucket_count 2
- bucket_field_name key
- column.name.delimiter ,
- columns key,value
- columns.comments
- columns.types string:string
-#### A masked pattern was here ####
- name default.bucket_big
- partition_columns ds
- partition_columns.types string
- serialization.ddl struct bucket_big { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.bucket_big
- name: default.bucket_big
- Partition
- base file name: ds=2008-04-09
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- partition values:
- ds 2008-04-09
- properties:
- bucket_count 2
- bucket_field_name key
- column.name.delimiter ,
- columns key,value
- columns.comments
- columns.types string:string
-#### A masked pattern was here ####
- name default.bucket_big
- numFiles 2
- numRows 0
- partition_columns ds
- partition_columns.types string
- rawDataSize 0
- serialization.ddl struct bucket_big { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 2750
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- SORTBUCKETCOLSPREFIX TRUE
- bucket_count 2
- bucket_field_name key
- column.name.delimiter ,
- columns key,value
- columns.comments
- columns.types string:string
-#### A masked pattern was here ####
- name default.bucket_big
- partition_columns ds
- partition_columns.types string
- serialization.ddl struct bucket_big { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.bucket_big
- name: default.bucket_big
- Alias -> Map Local Operator Tree:
- $hdt$_0:a
- TableScan
- alias: a
- 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: 112 Data size: 55000 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: key (type: string)
- outputColumnNames: _col0
- Statistics: Num rows: 112 Data size: 55000 Basic stats: COMPLETE Column stats: NONE
- HashTable Sink Operator
- keys:
- 0 _col0 (type: string)
- 1 _col0 (type: string)
- Position of Big Table: 1
-
- Stage: Stage-4
- Map Reduce
- Map Operator Tree:
- TableScan
- alias: b
- Statistics: Num rows: 4 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: 4 Data size: 2260 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: key (type: string)
- outputColumnNames: _col0
- Statistics: Num rows: 4 Data size: 2260 Basic stats: COMPLETE Column stats: NONE
- Map Join Operator
- condition map:
- Inner Join 0 to 1
- keys:
- 0 _col0 (type: string)
- 1 _col0 (type: string)
- Position of Big Table: 1
- Group By Operator
- aggregations: count()
- mode: hash
- outputColumnNames: _col0
- Reduce Output Operator
- null sort order:
- sort order:
- tag: -1
- value expressions: _col0 (type: bigint)
- auto parallelism: false
- Local Work:
- Map Reduce Local Work
- Path -> Alias:
-#### A masked pattern was here ####
- Path -> Partition:
-#### A masked pattern was here ####
- Partition
- base file name: ds=2008-04-08
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- partition values:
- ds 2008-04-08
- properties:
- bucket_count 2
- bucket_field_name key
- column.name.delimiter ,
- columns key,value
- columns.comments
- columns.types string:string
-#### A masked pattern was here ####
- name default.bucket_big
- numFiles 2
- numRows 0
- partition_columns ds
- partition_columns.types string
- rawDataSize 0
- serialization.ddl struct bucket_big { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 2750
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- SORTBUCKETCOLSPREFIX TRUE
- bucket_count 2
- bucket_field_name key
- column.name.delimiter ,
- columns key,value
- columns.comments
- columns.types string:string
-#### A masked pattern was here ####
- name default.bucket_big
- partition_columns ds
- partition_columns.types string
- serialization.ddl struct bucket_big { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.bucket_big
- name: default.bucket_big
-#### A masked pattern was here ####
- Partition
- base file name: ds=2008-04-09
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- partition values:
- ds 2008-04-09
- properties:
- bucket_count 2
- bucket_field_name key
- column.name.delimiter ,
- columns key,value
- columns.comments
- columns.types string:string
-#### A masked pattern was here ####
- name default.bucket_big
- numFiles 2
- numRows 0
- partition_columns ds
- partition_columns.types string
- rawDataSize 0
- serialization.ddl struct bucket_big { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 2750
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- SORTBUCKETCOLSPREFIX TRUE
- bucket_count 2
- bucket_field_name key
- column.name.delimiter ,
- columns key,value
- columns.comments
- columns.types string:string
-#### A masked pattern was here ####
- name default.bucket_big
- partition_columns ds
- partition_columns.types string
- serialization.ddl struct bucket_big { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.bucket_big
- name: default.bucket_big
-#### A masked pattern was here ####
- Partition
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- partition values:
- ds 2008-04-08
- properties:
- bucket_count 4
- bucket_field_name key
- column.name.delimiter ,
- columns key,value
- columns.comments
- columns.types string:string
-#### A masked pattern was here ####
- name default.bucket_small
- numFiles 4
- numRows 0
- partition_columns ds
- partition_columns.types string
- rawDataSize 0
- serialization.ddl struct bucket_small { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 226
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- SORTBUCKETCOLSPREFIX TRUE
- bucket_count 4
- bucket_field_name key
- column.name.delimiter ,
- columns key,value
- columns.comments
- columns.types string:string
-#### A masked pattern was here ####
- name default.bucket_small
- partition_columns ds
- partition_columns.types string
- serialization.ddl struct bucket_small { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.bucket_small
- name: default.bucket_small
- Truncated Path -> Alias:
- /bucket_small/ds=2008-04-08 [$hdt$_1:b]
- Needs Tagging: false
- Reduce Operator Tree:
- Group By Operator
- aggregations: count(VALUE._col0)
- mode: mergepartial
- outputColumnNames: _col0
- File Output Operator
- compressed: false
- GlobalTableId: 0
-#### A masked pattern was here ####
- NumFilesPerFileSink: 1
-#### A masked pattern was here ####
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- properties:
- columns _col0
- columns.types bigint
- escape.delim \
- hive.serialization.extend.additional.nesting.levels true
- serialization.escape.crlf true
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- TotalFiles: 1
- GatherStats: false
- MultiFileSpray: false
-
- Stage: Stage-1
- Map Reduce
- Map Operator Tree:
- TableScan
- alias: a
- 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: 112 Data size: 55000 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: key (type: string)
- outputColumnNames: _col0
- 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
- keys:
- 0 _col0 (type: string)
- 1 _col0 (type: string)
- Position of Big Table: 0
- BucketMapJoin: true
- Group By Operator
- aggregations: count()
- mode: hash
- outputColumnNames: _col0
- Reduce Output Operator
- null sort order:
- sort order:
- tag: -1
- value expressions: _col0 (type: bigint)
- auto parallelism: false
- Path -> Alias:
-#### A masked pattern was here ####
- Path -> Partition:
-#### A masked pattern was here ####
- Partition
- base file name: ds=2008-04-08
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- partition values:
- ds 2008-04-08
- properties:
- bucket_count 2
- bucket_field_name key
- column.name.delimiter ,
- columns key,value
- columns.comments
- columns.types string:string
-#### A masked pattern was here ####
- name default.bucket_big
- numFiles 2
- numRows 0
- partition_columns ds
- partition_columns.types string
- rawDataSize 0
- serialization.ddl struct bucket_big { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 2750
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- SORTBUCKETCOLSPREFIX TRUE
- bucket_count 2
- bucket_field_name key
- column.name.delimiter ,
- columns key,value
- columns.comments
- columns.types string:string
-#### A masked pattern was here ####
- name default.bucket_big
- partition_columns ds
- partition_columns.types string
- serialization.ddl struct bucket_big { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.bucket_big
- name: default.bucket_big
-#### A masked pattern was here ####
- Partition
- base file name: ds=2008-04-09
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- partition values:
- ds 2008-04-09
- properties:
- bucket_count 2
- bucket_field_name key
- column.name.delimiter ,
- columns key,value
- columns.comments
- columns.types string:string
-#### A masked pattern was here ####
- name default.bucket_big
- numFiles 2
- numRows 0
- partition_columns ds
- partition_columns.types string
- rawDataSize 0
- serialization.ddl struct bucket_big { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 2750
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- SORTBUCKETCOLSPREFIX TRUE
- bucket_count 2
- bucket_field_name key
- column.name.delimiter ,
- columns key,value
- columns.comments
- columns.types string:string
-#### A masked pattern was here ####
- name default.bucket_big
- partition_columns ds
- partition_columns.types string
- serialization.ddl struct bucket_big { string key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.bucket_big
- name: default.bucket_big
- Truncated Path -> Alias:
- /bucket_big/ds=2008-04-08 [$hdt$_0:a]
- /bucket_big/ds=2008-04-09 [$hdt$_0:a]
- Needs Tagging: false
- Reduce Operator Tree:
- Group By Operator
- aggregations: count(VALUE._col0)
- mode: mergepartial
- outputColumnNames: _col0
- File Output Operator
- compressed: false
- GlobalTableId: 0
-#### A masked pattern was here ####
- NumFilesPerFileSink: 1
-#### A masked pattern was here ####
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- properties:
- columns _col0
- columns.types bigint
- escape.delim \
- hive.serialization.extend.additional.nesting.levels true
- serialization.escape.crlf true
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- TotalFiles: 1
- GatherStats: false
- MultiFileSpray: false
-
- Stage: Stage-0
- Fetch Operator
- limit: -1
- Processor Tree:
- ListSink
-
-PREHOOK: query: select count(*) FROM bucket_big a JOIN bucket_small b ON a.key = b.key
-PREHOOK: type: QUERY
-PREHOOK: Input: default@bucket_big
-PREHOOK: Input: default@bucket_big@ds=2008-04-08
-PREHOOK: Input: default@bucket_big@ds=2008-04-09
-PREHOOK: Input: default@bucket_small
-PREHOOK: Input: default@bucket_small@ds=2008-04-08
-#### A masked pattern was here ####
-POSTHOOK: query: select count(*) FROM bucket_big a JOIN bucket_small b ON a.key = b.key
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@bucket_big
-POSTHOOK: Input: default@bucket_big@ds=2008-04-08
-POSTHOOK: Input: default@bucket_big@ds=2008-04-09
-POSTHOOK: Input: default@bucket_small
-POSTHOOK: Input: default@bucket_small@ds=2008-04-08
-#### A masked pattern was here ####
-38