/tags/release-0.2.0-rc0/hive/external/ql/src/test/results/clientpositive/bucketmapjoin4.q.out
text | 1013 lines | 989 code | 24 blank | 0 comment | 0 complexity | 570d96aceb6cb4a11e968199a42b5df6 MD5 | raw file
Possible License(s): Apache-2.0, BSD-3-Clause, JSON, CPL-1.0
- PREHOOK: query: CREATE TABLE srcbucket_mapjoin(key int, value string) CLUSTERED BY (key) INTO 2 BUCKETS STORED AS TEXTFILE
- PREHOOK: type: CREATETABLE
- POSTHOOK: query: CREATE TABLE srcbucket_mapjoin(key int, value string) CLUSTERED BY (key) INTO 2 BUCKETS STORED AS TEXTFILE
- POSTHOOK: type: CREATETABLE
- POSTHOOK: Output: default@srcbucket_mapjoin
- PREHOOK: query: load data local inpath '../data/files/srcbucket20.txt' INTO TABLE srcbucket_mapjoin
- PREHOOK: type: LOAD
- PREHOOK: Output: default@srcbucket_mapjoin
- POSTHOOK: query: load data local inpath '../data/files/srcbucket20.txt' INTO TABLE srcbucket_mapjoin
- POSTHOOK: type: LOAD
- POSTHOOK: Output: default@srcbucket_mapjoin
- PREHOOK: query: load data local inpath '../data/files/srcbucket21.txt' INTO TABLE srcbucket_mapjoin
- PREHOOK: type: LOAD
- PREHOOK: Output: default@srcbucket_mapjoin
- POSTHOOK: query: load data local inpath '../data/files/srcbucket21.txt' INTO TABLE srcbucket_mapjoin
- POSTHOOK: type: LOAD
- POSTHOOK: Output: default@srcbucket_mapjoin
- PREHOOK: query: CREATE TABLE srcbucket_mapjoin_part (key int, value string) partitioned by (ds string) CLUSTERED BY (key) INTO 4 BUCKETS STORED AS TEXTFILE
- PREHOOK: type: CREATETABLE
- POSTHOOK: query: CREATE TABLE srcbucket_mapjoin_part (key int, value string) partitioned by (ds string) CLUSTERED BY (key) INTO 4 BUCKETS STORED AS TEXTFILE
- POSTHOOK: type: CREATETABLE
- POSTHOOK: Output: default@srcbucket_mapjoin_part
- PREHOOK: query: load data local inpath '../data/files/srcbucket20.txt' INTO TABLE srcbucket_mapjoin_part partition(ds='2008-04-08')
- PREHOOK: type: LOAD
- PREHOOK: Output: default@srcbucket_mapjoin_part
- POSTHOOK: query: load data local inpath '../data/files/srcbucket20.txt' INTO TABLE srcbucket_mapjoin_part partition(ds='2008-04-08')
- POSTHOOK: type: LOAD
- POSTHOOK: Output: default@srcbucket_mapjoin_part
- POSTHOOK: Output: default@srcbucket_mapjoin_part@ds=2008-04-08
- PREHOOK: query: load data local inpath '../data/files/srcbucket21.txt' INTO TABLE srcbucket_mapjoin_part partition(ds='2008-04-08')
- PREHOOK: type: LOAD
- PREHOOK: Output: default@srcbucket_mapjoin_part@ds=2008-04-08
- POSTHOOK: query: load data local inpath '../data/files/srcbucket21.txt' INTO TABLE srcbucket_mapjoin_part partition(ds='2008-04-08')
- POSTHOOK: type: LOAD
- POSTHOOK: Output: default@srcbucket_mapjoin_part@ds=2008-04-08
- PREHOOK: query: load data local inpath '../data/files/srcbucket22.txt' INTO TABLE srcbucket_mapjoin_part partition(ds='2008-04-08')
- PREHOOK: type: LOAD
- PREHOOK: Output: default@srcbucket_mapjoin_part@ds=2008-04-08
- POSTHOOK: query: load data local inpath '../data/files/srcbucket22.txt' INTO TABLE srcbucket_mapjoin_part partition(ds='2008-04-08')
- POSTHOOK: type: LOAD
- POSTHOOK: Output: default@srcbucket_mapjoin_part@ds=2008-04-08
- PREHOOK: query: load data local inpath '../data/files/srcbucket23.txt' INTO TABLE srcbucket_mapjoin_part partition(ds='2008-04-08')
- PREHOOK: type: LOAD
- PREHOOK: Output: default@srcbucket_mapjoin_part@ds=2008-04-08
- POSTHOOK: query: load data local inpath '../data/files/srcbucket23.txt' INTO TABLE srcbucket_mapjoin_part partition(ds='2008-04-08')
- POSTHOOK: type: LOAD
- POSTHOOK: Output: default@srcbucket_mapjoin_part@ds=2008-04-08
- PREHOOK: query: CREATE TABLE srcbucket_mapjoin_part_2 (key int, value string) partitioned by (ds string) CLUSTERED BY (key) INTO 2 BUCKETS STORED AS TEXTFILE
- PREHOOK: type: CREATETABLE
- POSTHOOK: query: CREATE TABLE srcbucket_mapjoin_part_2 (key int, value string) partitioned by (ds string) CLUSTERED BY (key) INTO 2 BUCKETS STORED AS TEXTFILE
- POSTHOOK: type: CREATETABLE
- POSTHOOK: Output: default@srcbucket_mapjoin_part_2
- PREHOOK: query: load data local inpath '../data/files/srcbucket22.txt' INTO TABLE srcbucket_mapjoin_part_2 partition(ds='2008-04-08')
- PREHOOK: type: LOAD
- PREHOOK: Output: default@srcbucket_mapjoin_part_2
- POSTHOOK: query: load data local inpath '../data/files/srcbucket22.txt' INTO TABLE srcbucket_mapjoin_part_2 partition(ds='2008-04-08')
- POSTHOOK: type: LOAD
- POSTHOOK: Output: default@srcbucket_mapjoin_part_2
- POSTHOOK: Output: default@srcbucket_mapjoin_part_2@ds=2008-04-08
- PREHOOK: query: load data local inpath '../data/files/srcbucket23.txt' INTO TABLE srcbucket_mapjoin_part_2 partition(ds='2008-04-08')
- PREHOOK: type: LOAD
- PREHOOK: Output: default@srcbucket_mapjoin_part_2@ds=2008-04-08
- POSTHOOK: query: load data local inpath '../data/files/srcbucket23.txt' INTO TABLE srcbucket_mapjoin_part_2 partition(ds='2008-04-08')
- POSTHOOK: type: LOAD
- POSTHOOK: Output: default@srcbucket_mapjoin_part_2@ds=2008-04-08
- PREHOOK: query: create table bucketmapjoin_hash_result_1 (key bigint , value1 bigint, value2 bigint)
- PREHOOK: type: CREATETABLE
- POSTHOOK: query: create table bucketmapjoin_hash_result_1 (key bigint , value1 bigint, value2 bigint)
- POSTHOOK: type: CREATETABLE
- POSTHOOK: Output: default@bucketmapjoin_hash_result_1
- PREHOOK: query: create table bucketmapjoin_hash_result_2 (key bigint , value1 bigint, value2 bigint)
- PREHOOK: type: CREATETABLE
- POSTHOOK: query: create table bucketmapjoin_hash_result_2 (key bigint , value1 bigint, value2 bigint)
- POSTHOOK: type: CREATETABLE
- POSTHOOK: Output: default@bucketmapjoin_hash_result_2
- PREHOOK: query: create table bucketmapjoin_tmp_result (key string , value1 string, value2 string)
- PREHOOK: type: CREATETABLE
- POSTHOOK: query: create table bucketmapjoin_tmp_result (key string , value1 string, value2 string)
- POSTHOOK: type: CREATETABLE
- POSTHOOK: Output: default@bucketmapjoin_tmp_result
- PREHOOK: query: explain extended
- insert overwrite table bucketmapjoin_tmp_result
- select /*+mapjoin(b)*/ a.key, a.value, b.value
- from srcbucket_mapjoin a join srcbucket_mapjoin b
- on a.key=b.key
- PREHOOK: type: QUERY
- POSTHOOK: query: explain extended
- insert overwrite table bucketmapjoin_tmp_result
- select /*+mapjoin(b)*/ a.key, a.value, b.value
- from srcbucket_mapjoin a join srcbucket_mapjoin b
- on a.key=b.key
- POSTHOOK: type: QUERY
- ABSTRACT SYNTAX TREE:
- (TOK_QUERY (TOK_FROM (TOK_JOIN (TOK_TABREF (TOK_TABNAME srcbucket_mapjoin) a) (TOK_TABREF (TOK_TABNAME srcbucket_mapjoin) b) (= (. (TOK_TABLE_OR_COL a) key) (. (TOK_TABLE_OR_COL b) key)))) (TOK_INSERT (TOK_DESTINATION (TOK_TAB (TOK_TABNAME bucketmapjoin_tmp_result))) (TOK_SELECT (TOK_HINTLIST (TOK_HINT TOK_MAPJOIN (TOK_HINTARGLIST b))) (TOK_SELEXPR (. (TOK_TABLE_OR_COL a) key)) (TOK_SELEXPR (. (TOK_TABLE_OR_COL a) value)) (TOK_SELEXPR (. (TOK_TABLE_OR_COL b) value)))))
- STAGE DEPENDENCIES:
- Stage-7 is a root stage
- Stage-1 depends on stages: Stage-7
- Stage-5 depends on stages: Stage-1 , consists of Stage-4, Stage-3
- Stage-4
- Stage-0 depends on stages: Stage-4, Stage-3
- Stage-2 depends on stages: Stage-0
- Stage-3
- STAGE PLANS:
- Stage: Stage-7
- Map Reduce Local Work
- Alias -> Map Local Tables:
- b
- Fetch Operator
- limit: -1
- Alias -> Map Local Operator Tree:
- b
- TableScan
- alias: b
- GatherStats: false
- HashTable Sink Operator
- condition expressions:
- 0 {key} {value}
- 1 {value}
- handleSkewJoin: false
- keys:
- 0 [Column[key]]
- 1 [Column[key]]
- Position of Big Table: 0
- Bucket Mapjoin Context:
- Alias Bucket Base File Name Mapping:
- b {srcbucket20.txt=[srcbucket20.txt], srcbucket21.txt=[srcbucket21.txt]}
- Alias Bucket File Name Mapping:
- b {pfile:/data/users/tomasz/apache-hive/build/ql/test/data/warehouse/srcbucket_mapjoin/srcbucket20.txt=[pfile:/data/users/tomasz/apache-hive/build/ql/test/data/warehouse/srcbucket_mapjoin/srcbucket20.txt], pfile:/data/users/tomasz/apache-hive/build/ql/test/data/warehouse/srcbucket_mapjoin/srcbucket21.txt=[pfile:/data/users/tomasz/apache-hive/build/ql/test/data/warehouse/srcbucket_mapjoin/srcbucket21.txt]}
- Alias Bucket Output File Name Mapping:
- pfile:/data/users/tomasz/apache-hive/build/ql/test/data/warehouse/srcbucket_mapjoin/srcbucket20.txt 0
- pfile:/data/users/tomasz/apache-hive/build/ql/test/data/warehouse/srcbucket_mapjoin/srcbucket21.txt 1
- Stage: Stage-1
- Map Reduce
- Alias -> Map Operator Tree:
- a
- TableScan
- alias: a
- GatherStats: false
- Map Join Operator
- condition map:
- Inner Join 0 to 1
- condition expressions:
- 0 {key} {value}
- 1 {value}
- handleSkewJoin: false
- keys:
- 0 [Column[key]]
- 1 [Column[key]]
- outputColumnNames: _col0, _col1, _col5
- Position of Big Table: 0
- Select Operator
- expressions:
- expr: _col0
- type: int
- expr: _col1
- type: string
- expr: _col5
- type: string
- outputColumnNames: _col0, _col1, _col5
- Select Operator
- expressions:
- expr: _col0
- type: int
- expr: _col1
- type: string
- expr: _col5
- type: string
- outputColumnNames: _col0, _col1, _col2
- File Output Operator
- compressed: false
- GlobalTableId: 1
- directory: pfile:/data/users/tomasz/apache-hive/build/ql/scratchdir/hive_2011-06-01_18-47-24_202_6585306882290425835/-ext-10002
- NumFilesPerFileSink: 1
- Stats Publishing Key Prefix: pfile:/data/users/tomasz/apache-hive/build/ql/scratchdir/hive_2011-06-01_18-47-24_202_6585306882290425835/-ext-10000/
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- bucket_count -1
- columns key,value1,value2
- columns.types string:string:string
- file.inputformat org.apache.hadoop.mapred.TextInputFormat
- file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- location pfile:/data/users/tomasz/apache-hive/build/ql/test/data/warehouse/bucketmapjoin_tmp_result
- name default.bucketmapjoin_tmp_result
- serialization.ddl struct bucketmapjoin_tmp_result { string key, string value1, string value2}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- transient_lastDdlTime 1306979244
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.bucketmapjoin_tmp_result
- TotalFiles: 1
- GatherStats: true
- MultiFileSpray: false
- Local Work:
- Map Reduce Local Work
- Needs Tagging: false
- Path -> Alias:
- pfile:/data/users/tomasz/apache-hive/build/ql/test/data/warehouse/srcbucket_mapjoin [a]
- Path -> Partition:
- pfile:/data/users/tomasz/apache-hive/build/ql/test/data/warehouse/srcbucket_mapjoin
- Partition
- base file name: srcbucket_mapjoin
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- bucket_count 2
- bucket_field_name key
- columns key,value
- columns.types int:string
- file.inputformat org.apache.hadoop.mapred.TextInputFormat
- file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- location pfile:/data/users/tomasz/apache-hive/build/ql/test/data/warehouse/srcbucket_mapjoin
- name default.srcbucket_mapjoin
- serialization.ddl struct srcbucket_mapjoin { i32 key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- transient_lastDdlTime 1306979239
- 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:
- bucket_count 2
- bucket_field_name key
- columns key,value
- columns.types int:string
- file.inputformat org.apache.hadoop.mapred.TextInputFormat
- file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- location pfile:/data/users/tomasz/apache-hive/build/ql/test/data/warehouse/srcbucket_mapjoin
- name default.srcbucket_mapjoin
- serialization.ddl struct srcbucket_mapjoin { i32 key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- transient_lastDdlTime 1306979239
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.srcbucket_mapjoin
- name: default.srcbucket_mapjoin
- Stage: Stage-5
- Conditional Operator
- Stage: Stage-4
- Move Operator
- files:
- hdfs directory: true
- source: pfile:/data/users/tomasz/apache-hive/build/ql/scratchdir/hive_2011-06-01_18-47-24_202_6585306882290425835/-ext-10002
- destination: pfile:/data/users/tomasz/apache-hive/build/ql/scratchdir/hive_2011-06-01_18-47-24_202_6585306882290425835/-ext-10000
- Stage: Stage-0
- Move Operator
- tables:
- replace: true
- source: pfile:/data/users/tomasz/apache-hive/build/ql/scratchdir/hive_2011-06-01_18-47-24_202_6585306882290425835/-ext-10000
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- bucket_count -1
- columns key,value1,value2
- columns.types string:string:string
- file.inputformat org.apache.hadoop.mapred.TextInputFormat
- file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- location pfile:/data/users/tomasz/apache-hive/build/ql/test/data/warehouse/bucketmapjoin_tmp_result
- name default.bucketmapjoin_tmp_result
- serialization.ddl struct bucketmapjoin_tmp_result { string key, string value1, string value2}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- transient_lastDdlTime 1306979244
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.bucketmapjoin_tmp_result
- tmp directory: pfile:/data/users/tomasz/apache-hive/build/ql/scratchdir/hive_2011-06-01_18-47-24_202_6585306882290425835/-ext-10001
- Stage: Stage-2
- Stats-Aggr Operator
- Stats Aggregation Key Prefix: pfile:/data/users/tomasz/apache-hive/build/ql/scratchdir/hive_2011-06-01_18-47-24_202_6585306882290425835/-ext-10000/
- Stage: Stage-3
- Map Reduce
- Alias -> Map Operator Tree:
- pfile:/data/users/tomasz/apache-hive/build/ql/scratchdir/hive_2011-06-01_18-47-24_202_6585306882290425835/-ext-10002
- File Output Operator
- compressed: false
- GlobalTableId: 0
- directory: pfile:/data/users/tomasz/apache-hive/build/ql/scratchdir/hive_2011-06-01_18-47-24_202_6585306882290425835/-ext-10000
- NumFilesPerFileSink: 1
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- bucket_count -1
- columns key,value1,value2
- columns.types string:string:string
- file.inputformat org.apache.hadoop.mapred.TextInputFormat
- file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- location pfile:/data/users/tomasz/apache-hive/build/ql/test/data/warehouse/bucketmapjoin_tmp_result
- name default.bucketmapjoin_tmp_result
- serialization.ddl struct bucketmapjoin_tmp_result { string key, string value1, string value2}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- transient_lastDdlTime 1306979244
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.bucketmapjoin_tmp_result
- TotalFiles: 1
- GatherStats: false
- MultiFileSpray: false
- Needs Tagging: false
- Path -> Alias:
- pfile:/data/users/tomasz/apache-hive/build/ql/scratchdir/hive_2011-06-01_18-47-24_202_6585306882290425835/-ext-10002 [pfile:/data/users/tomasz/apache-hive/build/ql/scratchdir/hive_2011-06-01_18-47-24_202_6585306882290425835/-ext-10002]
- Path -> Partition:
- pfile:/data/users/tomasz/apache-hive/build/ql/scratchdir/hive_2011-06-01_18-47-24_202_6585306882290425835/-ext-10002
- Partition
- base file name: -ext-10002
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- bucket_count -1
- columns key,value1,value2
- columns.types string:string:string
- file.inputformat org.apache.hadoop.mapred.TextInputFormat
- file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- location pfile:/data/users/tomasz/apache-hive/build/ql/test/data/warehouse/bucketmapjoin_tmp_result
- name default.bucketmapjoin_tmp_result
- serialization.ddl struct bucketmapjoin_tmp_result { string key, string value1, string value2}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- transient_lastDdlTime 1306979244
- 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:
- bucket_count -1
- columns key,value1,value2
- columns.types string:string:string
- file.inputformat org.apache.hadoop.mapred.TextInputFormat
- file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- location pfile:/data/users/tomasz/apache-hive/build/ql/test/data/warehouse/bucketmapjoin_tmp_result
- name default.bucketmapjoin_tmp_result
- serialization.ddl struct bucketmapjoin_tmp_result { string key, string value1, string value2}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- transient_lastDdlTime 1306979244
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.bucketmapjoin_tmp_result
- name: default.bucketmapjoin_tmp_result
- PREHOOK: query: insert overwrite table bucketmapjoin_tmp_result
- select /*+mapjoin(b)*/ a.key, a.value, b.value
- from srcbucket_mapjoin a join srcbucket_mapjoin b
- on a.key=b.key
- PREHOOK: type: QUERY
- PREHOOK: Input: default@srcbucket_mapjoin
- PREHOOK: Output: default@bucketmapjoin_tmp_result
- POSTHOOK: query: insert overwrite table bucketmapjoin_tmp_result
- select /*+mapjoin(b)*/ a.key, a.value, b.value
- from srcbucket_mapjoin a join srcbucket_mapjoin b
- on a.key=b.key
- POSTHOOK: type: QUERY
- POSTHOOK: Input: default@srcbucket_mapjoin
- POSTHOOK: Output: default@bucketmapjoin_tmp_result
- POSTHOOK: Lineage: bucketmapjoin_tmp_result.key SIMPLE [(srcbucket_mapjoin)a.FieldSchema(name:key, type:int, comment:null), ]
- POSTHOOK: Lineage: bucketmapjoin_tmp_result.value1 SIMPLE [(srcbucket_mapjoin)a.FieldSchema(name:value, type:string, comment:null), ]
- POSTHOOK: Lineage: bucketmapjoin_tmp_result.value2 SIMPLE [(srcbucket_mapjoin)b.FieldSchema(name:value, type:string, comment:null), ]
- PREHOOK: query: select count(1) from bucketmapjoin_tmp_result
- PREHOOK: type: QUERY
- PREHOOK: Input: default@bucketmapjoin_tmp_result
- PREHOOK: Output: file:/tmp/tomasz/hive_2011-06-01_18-47-33_354_3111033757385788525/-mr-10000
- POSTHOOK: query: select count(1) from bucketmapjoin_tmp_result
- POSTHOOK: type: QUERY
- POSTHOOK: Input: default@bucketmapjoin_tmp_result
- POSTHOOK: Output: file:/tmp/tomasz/hive_2011-06-01_18-47-33_354_3111033757385788525/-mr-10000
- POSTHOOK: Lineage: bucketmapjoin_tmp_result.key SIMPLE [(srcbucket_mapjoin)a.FieldSchema(name:key, type:int, comment:null), ]
- POSTHOOK: Lineage: bucketmapjoin_tmp_result.value1 SIMPLE [(srcbucket_mapjoin)a.FieldSchema(name:value, type:string, comment:null), ]
- POSTHOOK: Lineage: bucketmapjoin_tmp_result.value2 SIMPLE [(srcbucket_mapjoin)b.FieldSchema(name:value, type:string, comment:null), ]
- 464
- PREHOOK: query: insert overwrite table bucketmapjoin_hash_result_1
- select sum(hash(key)), sum(hash(value1)), sum(hash(value2)) from bucketmapjoin_tmp_result
- PREHOOK: type: QUERY
- PREHOOK: Input: default@bucketmapjoin_tmp_result
- PREHOOK: Output: default@bucketmapjoin_hash_result_1
- POSTHOOK: query: insert overwrite table bucketmapjoin_hash_result_1
- select sum(hash(key)), sum(hash(value1)), sum(hash(value2)) from bucketmapjoin_tmp_result
- POSTHOOK: type: QUERY
- POSTHOOK: Input: default@bucketmapjoin_tmp_result
- POSTHOOK: Output: default@bucketmapjoin_hash_result_1
- POSTHOOK: Lineage: bucketmapjoin_hash_result_1.key EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:key, type:string, comment:null), ]
- POSTHOOK: Lineage: bucketmapjoin_hash_result_1.value1 EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:value1, type:string, comment:null), ]
- POSTHOOK: Lineage: bucketmapjoin_hash_result_1.value2 EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:value2, type:string, comment:null), ]
- POSTHOOK: Lineage: bucketmapjoin_tmp_result.key SIMPLE [(srcbucket_mapjoin)a.FieldSchema(name:key, type:int, comment:null), ]
- POSTHOOK: Lineage: bucketmapjoin_tmp_result.value1 SIMPLE [(srcbucket_mapjoin)a.FieldSchema(name:value, type:string, comment:null), ]
- POSTHOOK: Lineage: bucketmapjoin_tmp_result.value2 SIMPLE [(srcbucket_mapjoin)b.FieldSchema(name:value, type:string, comment:null), ]
- PREHOOK: query: insert overwrite table bucketmapjoin_tmp_result
- select /*+mapjoin(b)*/ a.key, a.value, b.value
- from srcbucket_mapjoin a join srcbucket_mapjoin b
- on a.key=b.key
- PREHOOK: type: QUERY
- PREHOOK: Input: default@srcbucket_mapjoin
- PREHOOK: Output: default@bucketmapjoin_tmp_result
- POSTHOOK: query: insert overwrite table bucketmapjoin_tmp_result
- select /*+mapjoin(b)*/ a.key, a.value, b.value
- from srcbucket_mapjoin a join srcbucket_mapjoin b
- on a.key=b.key
- POSTHOOK: type: QUERY
- POSTHOOK: Input: default@srcbucket_mapjoin
- POSTHOOK: Output: default@bucketmapjoin_tmp_result
- POSTHOOK: Lineage: bucketmapjoin_hash_result_1.key EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:key, type:string, comment:null), ]
- POSTHOOK: Lineage: bucketmapjoin_hash_result_1.value1 EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:value1, type:string, comment:null), ]
- POSTHOOK: Lineage: bucketmapjoin_hash_result_1.value2 EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:value2, type:string, comment:null), ]
- POSTHOOK: Lineage: bucketmapjoin_tmp_result.key SIMPLE [(srcbucket_mapjoin)a.FieldSchema(name:key, type:int, comment:null), ]
- POSTHOOK: Lineage: bucketmapjoin_tmp_result.key SIMPLE [(srcbucket_mapjoin)a.FieldSchema(name:key, type:int, comment:null), ]
- POSTHOOK: Lineage: bucketmapjoin_tmp_result.value1 SIMPLE [(srcbucket_mapjoin)a.FieldSchema(name:value, type:string, comment:null), ]
- POSTHOOK: Lineage: bucketmapjoin_tmp_result.value1 SIMPLE [(srcbucket_mapjoin)a.FieldSchema(name:value, type:string, comment:null), ]
- POSTHOOK: Lineage: bucketmapjoin_tmp_result.value2 SIMPLE [(srcbucket_mapjoin)b.FieldSchema(name:value, type:string, comment:null), ]
- POSTHOOK: Lineage: bucketmapjoin_tmp_result.value2 SIMPLE [(srcbucket_mapjoin)b.FieldSchema(name:value, type:string, comment:null), ]
- PREHOOK: query: select count(1) from bucketmapjoin_tmp_result
- PREHOOK: type: QUERY
- PREHOOK: Input: default@bucketmapjoin_tmp_result
- PREHOOK: Output: file:/tmp/tomasz/hive_2011-06-01_18-47-49_331_2976822432880371649/-mr-10000
- POSTHOOK: query: select count(1) from bucketmapjoin_tmp_result
- POSTHOOK: type: QUERY
- POSTHOOK: Input: default@bucketmapjoin_tmp_result
- POSTHOOK: Output: file:/tmp/tomasz/hive_2011-06-01_18-47-49_331_2976822432880371649/-mr-10000
- POSTHOOK: Lineage: bucketmapjoin_hash_result_1.key EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:key, type:string, comment:null), ]
- POSTHOOK: Lineage: bucketmapjoin_hash_result_1.value1 EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:value1, type:string, comment:null), ]
- POSTHOOK: Lineage: bucketmapjoin_hash_result_1.value2 EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:value2, type:string, comment:null), ]
- POSTHOOK: Lineage: bucketmapjoin_tmp_result.key SIMPLE [(srcbucket_mapjoin)a.FieldSchema(name:key, type:int, comment:null), ]
- POSTHOOK: Lineage: bucketmapjoin_tmp_result.key SIMPLE [(srcbucket_mapjoin)a.FieldSchema(name:key, type:int, comment:null), ]
- POSTHOOK: Lineage: bucketmapjoin_tmp_result.value1 SIMPLE [(srcbucket_mapjoin)a.FieldSchema(name:value, type:string, comment:null), ]
- POSTHOOK: Lineage: bucketmapjoin_tmp_result.value1 SIMPLE [(srcbucket_mapjoin)a.FieldSchema(name:value, type:string, comment:null), ]
- POSTHOOK: Lineage: bucketmapjoin_tmp_result.value2 SIMPLE [(srcbucket_mapjoin)b.FieldSchema(name:value, type:string, comment:null), ]
- POSTHOOK: Lineage: bucketmapjoin_tmp_result.value2 SIMPLE [(srcbucket_mapjoin)b.FieldSchema(name:value, type:string, comment:null), ]
- 464
- PREHOOK: query: insert overwrite table bucketmapjoin_hash_result_2
- select sum(hash(key)), sum(hash(value1)), sum(hash(value2)) from bucketmapjoin_tmp_result
- PREHOOK: type: QUERY
- PREHOOK: Input: default@bucketmapjoin_tmp_result
- PREHOOK: Output: default@bucketmapjoin_hash_result_2
- POSTHOOK: query: insert overwrite table bucketmapjoin_hash_result_2
- select sum(hash(key)), sum(hash(value1)), sum(hash(value2)) from bucketmapjoin_tmp_result
- POSTHOOK: type: QUERY
- POSTHOOK: Input: default@bucketmapjoin_tmp_result
- POSTHOOK: Output: default@bucketmapjoin_hash_result_2
- POSTHOOK: Lineage: bucketmapjoin_hash_result_1.key EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:key, type:string, comment:null), ]
- POSTHOOK: Lineage: bucketmapjoin_hash_result_1.value1 EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:value1, type:string, comment:null), ]
- POSTHOOK: Lineage: bucketmapjoin_hash_result_1.value2 EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:value2, type:string, comment:null), ]
- POSTHOOK: Lineage: bucketmapjoin_hash_result_2.key EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:key, type:string, comment:null), ]
- POSTHOOK: Lineage: bucketmapjoin_hash_result_2.value1 EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:value1, type:string, comment:null), ]
- POSTHOOK: Lineage: bucketmapjoin_hash_result_2.value2 EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:value2, type:string, comment:null), ]
- POSTHOOK: Lineage: bucketmapjoin_tmp_result.key SIMPLE [(srcbucket_mapjoin)a.FieldSchema(name:key, type:int, comment:null), ]
- POSTHOOK: Lineage: bucketmapjoin_tmp_result.key SIMPLE [(srcbucket_mapjoin)a.FieldSchema(name:key, type:int, comment:null), ]
- POSTHOOK: Lineage: bucketmapjoin_tmp_result.value1 SIMPLE [(srcbucket_mapjoin)a.FieldSchema(name:value, type:string, comment:null), ]
- POSTHOOK: Lineage: bucketmapjoin_tmp_result.value1 SIMPLE [(srcbucket_mapjoin)a.FieldSchema(name:value, type:string, comment:null), ]
- POSTHOOK: Lineage: bucketmapjoin_tmp_result.value2 SIMPLE [(srcbucket_mapjoin)b.FieldSchema(name:value, type:string, comment:null), ]
- POSTHOOK: Lineage: bucketmapjoin_tmp_result.value2 SIMPLE [(srcbucket_mapjoin)b.FieldSchema(name:value, type:string, comment:null), ]
- PREHOOK: query: select a.key-b.key, a.value1-b.value1, a.value2-b.value2
- from bucketmapjoin_hash_result_1 a left outer join bucketmapjoin_hash_result_2 b
- on a.key = b.key
- PREHOOK: type: QUERY
- PREHOOK: Input: default@bucketmapjoin_hash_result_1
- PREHOOK: Input: default@bucketmapjoin_hash_result_2
- PREHOOK: Output: file:/tmp/tomasz/hive_2011-06-01_18-47-56_317_7787039686001016086/-mr-10000
- POSTHOOK: query: select a.key-b.key, a.value1-b.value1, a.value2-b.value2
- from bucketmapjoin_hash_result_1 a left outer join bucketmapjoin_hash_result_2 b
- on a.key = b.key
- POSTHOOK: type: QUERY
- POSTHOOK: Input: default@bucketmapjoin_hash_result_1
- POSTHOOK: Input: default@bucketmapjoin_hash_result_2
- POSTHOOK: Output: file:/tmp/tomasz/hive_2011-06-01_18-47-56_317_7787039686001016086/-mr-10000
- POSTHOOK: Lineage: bucketmapjoin_hash_result_1.key EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:key, type:string, comment:null), ]
- POSTHOOK: Lineage: bucketmapjoin_hash_result_1.value1 EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:value1, type:string, comment:null), ]
- POSTHOOK: Lineage: bucketmapjoin_hash_result_1.value2 EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:value2, type:string, comment:null), ]
- POSTHOOK: Lineage: bucketmapjoin_hash_result_2.key EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:key, type:string, comment:null), ]
- POSTHOOK: Lineage: bucketmapjoin_hash_result_2.value1 EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:value1, type:string, comment:null), ]
- POSTHOOK: Lineage: bucketmapjoin_hash_result_2.value2 EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:value2, type:string, comment:null), ]
- POSTHOOK: Lineage: bucketmapjoin_tmp_result.key SIMPLE [(srcbucket_mapjoin)a.FieldSchema(name:key, type:int, comment:null), ]
- POSTHOOK: Lineage: bucketmapjoin_tmp_result.key SIMPLE [(srcbucket_mapjoin)a.FieldSchema(name:key, type:int, comment:null), ]
- POSTHOOK: Lineage: bucketmapjoin_tmp_result.value1 SIMPLE [(srcbucket_mapjoin)a.FieldSchema(name:value, type:string, comment:null), ]
- POSTHOOK: Lineage: bucketmapjoin_tmp_result.value1 SIMPLE [(srcbucket_mapjoin)a.FieldSchema(name:value, type:string, comment:null), ]
- POSTHOOK: Lineage: bucketmapjoin_tmp_result.value2 SIMPLE [(srcbucket_mapjoin)b.FieldSchema(name:value, type:string, comment:null), ]
- POSTHOOK: Lineage: bucketmapjoin_tmp_result.value2 SIMPLE [(srcbucket_mapjoin)b.FieldSchema(name:value, type:string, comment:null), ]
- 0 0 0
- PREHOOK: query: explain extended
- insert overwrite table bucketmapjoin_tmp_result
- select /*+mapjoin(a)*/ a.key, a.value, b.value
- from srcbucket_mapjoin a join srcbucket_mapjoin b
- on a.key=b.key
- PREHOOK: type: QUERY
- POSTHOOK: query: explain extended
- insert overwrite table bucketmapjoin_tmp_result
- select /*+mapjoin(a)*/ a.key, a.value, b.value
- from srcbucket_mapjoin a join srcbucket_mapjoin b
- on a.key=b.key
- POSTHOOK: type: QUERY
- POSTHOOK: Lineage: bucketmapjoin_hash_result_1.key EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:key, type:string, comment:null), ]
- POSTHOOK: Lineage: bucketmapjoin_hash_result_1.value1 EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:value1, type:string, comment:null), ]
- POSTHOOK: Lineage: bucketmapjoin_hash_result_1.value2 EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:value2, type:string, comment:null), ]
- POSTHOOK: Lineage: bucketmapjoin_hash_result_2.key EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:key, type:string, comment:null), ]
- POSTHOOK: Lineage: bucketmapjoin_hash_result_2.value1 EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:value1, type:string, comment:null), ]
- POSTHOOK: Lineage: bucketmapjoin_hash_result_2.value2 EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:value2, type:string, comment:null), ]
- POSTHOOK: Lineage: bucketmapjoin_tmp_result.key SIMPLE [(srcbucket_mapjoin)a.FieldSchema(name:key, type:int, comment:null), ]
- POSTHOOK: Lineage: bucketmapjoin_tmp_result.key SIMPLE [(srcbucket_mapjoin)a.FieldSchema(name:key, type:int, comment:null), ]
- POSTHOOK: Lineage: bucketmapjoin_tmp_result.value1 SIMPLE [(srcbucket_mapjoin)a.FieldSchema(name:value, type:string, comment:null), ]
- POSTHOOK: Lineage: bucketmapjoin_tmp_result.value1 SIMPLE [(srcbucket_mapjoin)a.FieldSchema(name:value, type:string, comment:null), ]
- POSTHOOK: Lineage: bucketmapjoin_tmp_result.value2 SIMPLE [(srcbucket_mapjoin)b.FieldSchema(name:value, type:string, comment:null), ]
- POSTHOOK: Lineage: bucketmapjoin_tmp_result.value2 SIMPLE [(srcbucket_mapjoin)b.FieldSchema(name:value, type:string, comment:null), ]
- ABSTRACT SYNTAX TREE:
- (TOK_QUERY (TOK_FROM (TOK_JOIN (TOK_TABREF (TOK_TABNAME srcbucket_mapjoin) a) (TOK_TABREF (TOK_TABNAME srcbucket_mapjoin) b) (= (. (TOK_TABLE_OR_COL a) key) (. (TOK_TABLE_OR_COL b) key)))) (TOK_INSERT (TOK_DESTINATION (TOK_TAB (TOK_TABNAME bucketmapjoin_tmp_result))) (TOK_SELECT (TOK_HINTLIST (TOK_HINT TOK_MAPJOIN (TOK_HINTARGLIST a))) (TOK_SELEXPR (. (TOK_TABLE_OR_COL a) key)) (TOK_SELEXPR (. (TOK_TABLE_OR_COL a) value)) (TOK_SELEXPR (. (TOK_TABLE_OR_COL b) value)))))
- STAGE DEPENDENCIES:
- Stage-7 is a root stage
- Stage-1 depends on stages: Stage-7
- Stage-5 depends on stages: Stage-1 , consists of Stage-4, Stage-3
- Stage-4
- Stage-0 depends on stages: Stage-4, Stage-3
- Stage-2 depends on stages: Stage-0
- Stage-3
- STAGE PLANS:
- Stage: Stage-7
- Map Reduce Local Work
- Alias -> Map Local Tables:
- a
- Fetch Operator
- limit: -1
- Alias -> Map Local Operator Tree:
- a
- TableScan
- alias: a
- GatherStats: false
- HashTable Sink Operator
- condition expressions:
- 0 {key} {value}
- 1 {value}
- handleSkewJoin: false
- keys:
- 0 [Column[key]]
- 1 [Column[key]]
- Position of Big Table: 1
- Bucket Mapjoin Context:
- Alias Bucket Base File Name Mapping:
- a {srcbucket20.txt=[srcbucket20.txt], srcbucket21.txt=[srcbucket21.txt]}
- Alias Bucket File Name Mapping:
- a {pfile:/data/users/tomasz/apache-hive/build/ql/test/data/warehouse/srcbucket_mapjoin/srcbucket20.txt=[pfile:/data/users/tomasz/apache-hive/build/ql/test/data/warehouse/srcbucket_mapjoin/srcbucket20.txt], pfile:/data/users/tomasz/apache-hive/build/ql/test/data/warehouse/srcbucket_mapjoin/srcbucket21.txt=[pfile:/data/users/tomasz/apache-hive/build/ql/test/data/warehouse/srcbucket_mapjoin/srcbucket21.txt]}
- Alias Bucket Output File Name Mapping:
- pfile:/data/users/tomasz/apache-hive/build/ql/test/data/warehouse/srcbucket_mapjoin/srcbucket20.txt 0
- pfile:/data/users/tomasz/apache-hive/build/ql/test/data/warehouse/srcbucket_mapjoin/srcbucket21.txt 1
- Stage: Stage-1
- Map Reduce
- Alias -> Map Operator Tree:
- b
- TableScan
- alias: b
- GatherStats: false
- Map Join Operator
- condition map:
- Inner Join 0 to 1
- condition expressions:
- 0 {key} {value}
- 1 {value}
- handleSkewJoin: false
- keys:
- 0 [Column[key]]
- 1 [Column[key]]
- outputColumnNames: _col0, _col1, _col5
- Position of Big Table: 1
- Select Operator
- expressions:
- expr: _col0
- type: int
- expr: _col1
- type: string
- expr: _col5
- type: string
- outputColumnNames: _col0, _col1, _col5
- Select Operator
- expressions:
- expr: _col0
- type: int
- expr: _col1
- type: string
- expr: _col5
- type: string
- outputColumnNames: _col0, _col1, _col2
- File Output Operator
- compressed: false
- GlobalTableId: 1
- directory: pfile:/data/users/tomasz/apache-hive/build/ql/scratchdir/hive_2011-06-01_18-47-59_537_2542627376244877759/-ext-10002
- NumFilesPerFileSink: 1
- Stats Publishing Key Prefix: pfile:/data/users/tomasz/apache-hive/build/ql/scratchdir/hive_2011-06-01_18-47-59_537_2542627376244877759/-ext-10000/
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- bucket_count -1
- columns key,value1,value2
- columns.types string:string:string
- file.inputformat org.apache.hadoop.mapred.TextInputFormat
- file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- location pfile:/data/users/tomasz/apache-hive/build/ql/test/data/warehouse/bucketmapjoin_tmp_result
- name default.bucketmapjoin_tmp_result
- numFiles 1
- numPartitions 0
- numRows 464
- rawDataSize 8519
- serialization.ddl struct bucketmapjoin_tmp_result { string key, string value1, string value2}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 8983
- transient_lastDdlTime 1306979269
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.bucketmapjoin_tmp_result
- TotalFiles: 1
- GatherStats: true
- MultiFileSpray: false
- Local Work:
- Map Reduce Local Work
- Needs Tagging: false
- Path -> Alias:
- pfile:/data/users/tomasz/apache-hive/build/ql/test/data/warehouse/srcbucket_mapjoin [b]
- Path -> Partition:
- pfile:/data/users/tomasz/apache-hive/build/ql/test/data/warehouse/srcbucket_mapjoin
- Partition
- base file name: srcbucket_mapjoin
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- bucket_count 2
- bucket_field_name key
- columns key,value
- columns.types int:string
- file.inputformat org.apache.hadoop.mapred.TextInputFormat
- file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- location pfile:/data/users/tomasz/apache-hive/build/ql/test/data/warehouse/srcbucket_mapjoin
- name default.srcbucket_mapjoin
- serialization.ddl struct srcbucket_mapjoin { i32 key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- transient_lastDdlTime 1306979239
- 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:
- bucket_count 2
- bucket_field_name key
- columns key,value
- columns.types int:string
- file.inputformat org.apache.hadoop.mapred.TextInputFormat
- file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- location pfile:/data/users/tomasz/apache-hive/build/ql/test/data/warehouse/srcbucket_mapjoin
- name default.srcbucket_mapjoin
- serialization.ddl struct srcbucket_mapjoin { i32 key, string value}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- transient_lastDdlTime 1306979239
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.srcbucket_mapjoin
- name: default.srcbucket_mapjoin
- Stage: Stage-5
- Conditional Operator
- Stage: Stage-4
- Move Operator
- files:
- hdfs directory: true
- source: pfile:/data/users/tomasz/apache-hive/build/ql/scratchdir/hive_2011-06-01_18-47-59_537_2542627376244877759/-ext-10002
- destination: pfile:/data/users/tomasz/apache-hive/build/ql/scratchdir/hive_2011-06-01_18-47-59_537_2542627376244877759/-ext-10000
- Stage: Stage-0
- Move Operator
- tables:
- replace: true
- source: pfile:/data/users/tomasz/apache-hive/build/ql/scratchdir/hive_2011-06-01_18-47-59_537_2542627376244877759/-ext-10000
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- bucket_count -1
- columns key,value1,value2
- columns.types string:string:string
- file.inputformat org.apache.hadoop.mapred.TextInputFormat
- file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- location pfile:/data/users/tomasz/apache-hive/build/ql/test/data/warehouse/bucketmapjoin_tmp_result
- name default.bucketmapjoin_tmp_result
- numFiles 1
- numPartitions 0
- numRows 464
- rawDataSize 8519
- serialization.ddl struct bucketmapjoin_tmp_result { string key, string value1, string value2}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 8983
- transient_lastDdlTime 1306979269
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.bucketmapjoin_tmp_result
- tmp directory: pfile:/data/users/tomasz/apache-hive/build/ql/scratchdir/hive_2011-06-01_18-47-59_537_2542627376244877759/-ext-10001
- Stage: Stage-2
- Stats-Aggr Operator
- Stats Aggregation Key Prefix: pfile:/data/users/tomasz/apache-hive/build/ql/scratchdir/hive_2011-06-01_18-47-59_537_2542627376244877759/-ext-10000/
- Stage: Stage-3
- Map Reduce
- Alias -> Map Operator Tree:
- pfile:/data/users/tomasz/apache-hive/build/ql/scratchdir/hive_2011-06-01_18-47-59_537_2542627376244877759/-ext-10002
- File Output Operator
- compressed: false
- GlobalTableId: 0
- directory: pfile:/data/users/tomasz/apache-hive/build/ql/scratchdir/hive_2011-06-01_18-47-59_537_2542627376244877759/-ext-10000
- NumFilesPerFileSink: 1
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- bucket_count -1
- columns key,value1,value2
- columns.types string:string:string
- file.inputformat org.apache.hadoop.mapred.TextInputFormat
- file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- location pfile:/data/users/tomasz/apache-hive/build/ql/test/data/warehouse/bucketmapjoin_tmp_result
- name default.bucketmapjoin_tmp_result
- numFiles 1
- numPartitions 0
- numRows 464
- rawDataSize 8519
- serialization.ddl struct bucketmapjoin_tmp_result { string key, string value1, string value2}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 8983
- transient_lastDdlTime 1306979269
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.bucketmapjoin_tmp_result
- TotalFiles: 1
- GatherStats: false
- MultiFileSpray: false
- Needs Tagging: false
- Path -> Alias:
- pfile:/data/users/tomasz/apache-hive/build/ql/scratchdir/hive_2011-06-01_18-47-59_537_2542627376244877759/-ext-10002 [pfile:/data/users/tomasz/apache-hive/build/ql/scratchdir/hive_2011-06-01_18-47-59_537_2542627376244877759/-ext-10002]
- Path -> Partition:
- pfile:/data/users/tomasz/apache-hive/build/ql/scratchdir/hive_2011-06-01_18-47-59_537_2542627376244877759/-ext-10002
- Partition
- base file name: -ext-10002
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- bucket_count -1
- columns key,value1,value2
- columns.types string:string:string
- file.inputformat org.apache.hadoop.mapred.TextInputFormat
- file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- location pfile:/data/users/tomasz/apache-hive/build/ql/test/data/warehouse/bucketmapjoin_tmp_result
- name default.bucketmapjoin_tmp_result
- numFiles 1
- numPartitions 0
- numRows 464
- rawDataSize 8519
- serialization.ddl struct bucketmapjoin_tmp_result { string key, string value1, string value2}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 8983
- transient_lastDdlTime 1306979269
- 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:
- bucket_count -1
- columns key,value1,value2
- columns.types string:string:string
- file.inputformat org.apache.hadoop.mapred.TextInputFormat
- file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- location pfile:/data/users/tomasz/apache-hive/build/ql/test/data/warehouse/bucketmapjoin_tmp_result
- name default.bucketmapjoin_tmp_result
- numFiles 1
- numPartitions 0
- numRows 464
- rawDataSize 8519
- serialization.ddl struct bucketmapjoin_tmp_result { string key, string value1, string value2}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 8983
- transient_lastDdlTime 1306979269
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.bucketmapjoin_tmp_result
- name: default.bucketmapjoin_tmp_result
- PREHOOK: query: insert overwrite table bucketmapjoin_tmp_result
- select /*+mapjoin(a)*/ a.key, a.value, b.value
- from srcbucket_mapjoin a join srcbucket_mapjoin b
- on a.key=b.key
- PREHOOK: type: QUERY
- PREHOOK: Input: default@srcbucket_mapjoin
- PREHOOK: Output: default@bucketmapjoin_tmp_result
- POSTHOOK: query: insert overwrite table bucketmapjoin_tmp_result
- select /*+mapjoin(a)*/ a.key, a.value, b.value
- from srcbucket_mapjoin a join srcbucket_mapjoin b
- on a.key=b.key
- POSTHOOK: type: QUERY
- POSTHOOK: Input: default@srcbucket_mapjoin
- POSTHOOK: Output: default@bucketmapjoin_tmp_result
- POSTHOOK: Lineage: bucketmapjoin_hash_result_1.key EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:key, type:string, comment:null), ]
- POSTHOOK: Lineage: bucketmapjoin_hash_result_1.value1 EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:value1, type:string, comment:null), ]
- POSTHOOK: Lineage: bucketmapjoin_hash_result_1.value2 EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:value2, type:string, comment:null), ]
- POSTHOOK: Lineage: bucketmapjoin_hash_result_2.key EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:key, type:string, comment:null), ]
- POSTHOOK: Lineage: bucketmapjoin_hash_result_2.value1 EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:value1, type:string, comment:null), ]
- POSTHOOK: Lineage: bucketmapjoin_hash_result_2.value2 EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:value2, type:string, comment:null), ]
- POSTHOOK: Lineage: bucketmapjoin_tmp_result.key SIMPLE [(srcbucket_mapjoin)a.FieldSchema(name:key, type:int, comment:null), ]
- POSTHOOK: Lineage: bucketmapjoin_tmp_result.key SIMPLE [(srcbucket_mapjoin)a.FieldSchema(name:key, type:int, comment:null), ]
- POSTHOOK: Lineage: bucketmapjoin_tmp_result.key SIMPLE [(srcbucket_mapjoin)a.FieldSchema(name:key, type:int, comment:null), ]
- POSTHOOK: Lineage: bucketmapjoin_tmp_result.value1 SIMPLE [(srcbucket_mapjoin)a.FieldSchema(name:value, type:string, comment:null), ]
- POSTHOOK: Lineage: bucketmapjoin_tmp_result.value1 SIMPLE [(srcbucket_mapjoin)a.FieldSchema(name:value, type:string, comment:null), ]
- POSTHOOK: Lineage: bucketmapjoin_tmp_result.value1 SIMPLE [(srcbucket_mapjoin)a.FieldSchema(name:value, type:string, comment:null), ]
- POSTHOOK: Lineage: bucketmapjoin_tmp_result.value2 SIMPLE [(srcbucket_mapjoin)b.FieldSchema(name:value, type:string, comment:null), ]
- POSTHOOK: Lineage: bucketmapjoin_tmp_result.value2 SIMPLE [(srcbucket_mapjoin)b.FieldSchema(name:value, type:string, comment:null), ]
- POSTHOOK: Lineage: bucketmapjoin_tmp_result.value2 SIMPLE [(srcbucket_mapjoin)b.FieldSchema(name:value, type:string, comment:null), ]
- PREHOOK: query: select count(1) from bucketmapjoin_tmp_result
- PREHOOK: type: QUERY
- PREHOOK: Input: default@bucketmapjoin_tmp_result
- PREHOOK: Output: file:/tmp/tomasz/hive_2011-06-01_18-48-08_798_4661195801405656601/-mr-10000
- POSTHOOK: query: select count(1) from bucketmapjoin_tmp_result
- POSTHOOK: type: QUERY
- POSTHOOK: Input: default@bucketmapjoin_tmp_result
- POSTHOOK: Output: file:/tmp/tomasz/hive_2011-06-01_18-48-08_798_4661195801405656601/-mr-10000
- POSTHOOK: Lineage: bucketmapjoin_hash_result_1.key EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:key, type:string, comment:null), ]
- POSTHOOK: Lineage: bucketmapjoin_hash_result_1.value1 EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:value1, type:string, comment:null), ]
- POSTHOOK: Lineage: bucketmapjoin_hash_result_1.value2 EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:value2, type:string, comment:null), ]
- POSTHOOK: Lineage: bucketmapjoin_hash_result_2.key EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:key, type:string, comment:null), ]
- POSTHOOK: Lineage: bucketmapjoin_hash_result_2.value1 EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:value1, type:string, comment:null), ]
- POSTHOOK: Lineage: bucketmapjoin_hash_result_2.value2 EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:value2, type:string, comment:null), ]
- POSTHOOK: Lineage: bucketmapjoin_tmp_result.key SIMPLE [(srcbucket_mapjoin)a.FieldSchema(name:key, type:int, comment:null), ]
- POSTHOOK: Lineage: bucketmapjoin_tmp_result.key SIMPLE [(srcbucket_mapjoin)a.FieldSchema(name:key, type:int, comment:null), ]
- POSTHOOK: Lineage: bucketmapjoin_tmp_result.key SIMPLE [(srcbucket_mapjoin)a.FieldSchema(name:key, type:int, comment:null), ]
- POSTHOOK: Lineage: bucketmapjoin_tmp_result.value1 SIMPLE [(srcbucket_mapjoin)a.FieldSchema(name:value, type:string, comment:null), ]
- POSTHOOK: Lineage: bucketmapjoin_tmp_result.value1 SIMPLE [(srcbucket_mapjoin)a.FieldSchema(name:value, type:string, comment:null), ]
- POSTHOOK: Lineage: bucketmapjoin_tmp_result.value1 SIMPLE [(srcbucket_mapjoin)a.FieldSchema(name:value, type:string, comment:null), ]
- POSTHOOK: Lineage: bucketmapjoin_tmp_result.value2 SIMPLE [(srcbucket_mapjoin)b.FieldSchema(name:value, type:string, comment:null), ]
- POSTHOOK: Lineage: bucketmapjoin_tmp_result.value2 SIMPLE [(srcbucket_mapjoin)b.FieldSchema(name:value, type:string, comment:null), ]
- POSTHOOK: Lineage: bucketmapjoin_tmp_result.value2 SIMPLE [(srcbucket_mapjoin)b.FieldSchema(name:value, type:string, comment:null), ]
- 464
- PREHOOK: query: insert overwrite table bucketmapjoin_hash_result_1
- select sum(hash(key)), sum(hash(value1)), sum(hash(value2)) from bucketmapjoin_tmp_result
- PREHOOK: type: QUERY
- PREHOOK: Input: default@bucketmapjoin_tmp_result
- PREHOOK: Output: default@bucketmapjoin_hash_result_1
- POSTHOOK: query: insert overwrite table bucketmapjoin_hash_result_1
- select sum(hash(key)), sum(hash(value1)), sum(hash(value2)) from bucketmapjoin_tmp_result
- POSTHOOK: type: QUERY
- POSTHOOK: Input: default@bucketmapjoin_tmp_result
- POSTHOOK: Output: default@bucketmapjoin_hash_result_1
- POSTHOOK: Lineage: bucketmapjoin_hash_result_1.key EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:key, type:string, comment:null), ]
- POSTHOOK: Lineage: bucketmapjoin_hash_result_1.key EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:key, type:string, comment:null), ]
- POSTHOOK: Lineage: bucketmapjoin_hash_result_1.value1 EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:value1, type:string, comment:null), ]
- POSTHOOK: Lineage: bucketmapjoin_hash_result_1.value1 EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:value1, type:string, comment:null), ]
- POSTHOOK: Lineage: bucketmapjoin_hash_result_1.value2 EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:value2, type:string, comment:null), ]
- POSTHOOK: Lineage: bucketmapjoin_hash_result_1.value2 EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:value2, type:string, comment:null), ]
- POSTHOOK: Lineage: bucketmapjoin_hash_result_2.key EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:key, type:string, comment:null), ]
- POSTHOOK: Lineage: bucketmapjoin_hash_result_2.value1 EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:value1, type:string, comment:null), ]
- POSTHOOK: Lineage: bucketmapjoin_hash_result_2.value2 EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:value2, type:string, comment:null), ]
- POSTHOOK: Lineage: bucketmapjoin_tmp_result.key SIMPLE [(srcbucket_mapjoin)a.FieldSchema(name:key, type:int, comment:null), ]
- POSTHOOK: Lineage: bucketmapjoin_tmp_result.key SIMPLE [(srcbucket_mapjoin)a.FieldSchema(name:key, type:int, comment:null), ]
- POSTHOOK: Lineage: bucketmapjoin_tmp_result.key SIMPLE [(srcbucket_mapjoin)a.FieldSchema(name:key, type:int, comment:null), ]
- POSTHOOK: Lineage: bucketmapjoin_tmp_result.value1 SIMPLE [(srcbucket_mapjoin)a.FieldSchema(name:value, type:string, comment:null), ]
- POSTHOOK: Lineage: bucketmapjoin_tmp_result.value1 SIMPLE [(srcbucket_mapjoin)a.FieldSchema(name:value, type:string, comment:null), ]
- POSTHOOK: Lineage: bucketmapjoin_tmp_result.value1 SIMPLE [(srcbucket_mapjoin)a.FieldSchema(name:value, type:string, comment:null), ]
- POSTHOOK: Lineage: bucketmapjoin_tmp_result.value2 SIMPLE [(srcbucket_mapjoin)b.FieldSchema(name:value, type:string, comment:null), ]
- POSTHOOK: Lineage: bucketmapjoin_tmp_result.value2 SIMPLE [(srcbucket_mapjoin)b.FieldSchema(name:value, type:string, comment:null), ]
- POSTHOOK: Lineage: bucketmapjoin_tmp_result.value2 SIMPLE [(srcbucket_mapjoin)b.FieldSchema(name:value, type:string, comment:null), ]
- PREHOOK: query: insert overwrite table bucketmapjoin_tmp_result
- select /*+mapjoin(a)*/ a.key, a.value, b.value
- from srcbucket_mapjoin a join srcbucket_mapjoin b
- on a.key=b.key
- PREHOOK: type: QUERY
- PREHOOK: Input: default@srcbucket_mapjoin
- PREHOOK: Output: default@bucketmapjoin_tmp_result
- POSTHOOK: query: insert overwrite table bucketmapjoin_tmp_result
- select /*+mapjoin(a)*/ a.key, a.value, b.value
- from srcbucket_mapjoin a join srcbucket_mapjoin b
- on a.key=b.key
- POSTHOOK: type: QUERY
- POSTHOOK: Input: default@srcbucket_mapjoin
- POSTHOOK: Output: default@bucketmapjoin_tmp_result
- POSTHOOK: Lineage: bucketmapjoin_hash_result_1.key EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:key, type:string, comment:null), ]
- POSTHOOK: Lineage: bucketmapjoin_hash_result_1.key EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:key, type:string, comment:null), ]
- POSTHOOK: Lineage: bucketmapjoin_hash_result_1.value1 EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:value1, type:string, comment:null), ]
- POSTHOOK: Lineage: bucketmapjoin_hash_result_1.value1 EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:value1, type:string, comment:null), ]
- POSTHOOK: Lineage: bucketmapjoin_hash_result_1.value2 EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:value2, type:string, comment:null), ]
- POSTHOOK: Lineage: bucketmapjoin_hash_result_1.value2 EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:value2, type:string, comment:null), ]
- POSTHOOK: Lineage: bucketmapjoin_hash_result_2.key EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:key, type:string, comment:null), ]
- POSTHOOK: Lineage: bucketmapjoin_hash_result_2.value1 EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:value1, type:string, comment:null), ]
- POSTHOOK: Lineage: bucketmapjoin_hash_result_2.value2 EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:value2, type:string, comment:null), ]
- POSTHOOK: Lineage: bucketmapjoin_tmp_result.key SIMPLE [(srcbucket_mapjoin)a.FieldSchema(name:key, type:int, comment:null), ]
- POSTHOOK: Lineage: bucketmapjoin_tmp_result.key SIMPLE [(srcbucket_mapjoin)a.FieldSchema(name:key, type:int, comment:null), ]
- POSTHOOK: Lineage: bucketmapjoin_tmp_result.key SIMPLE [(srcbucket_mapjoin)a.FieldSchema(name:key, type:int, comment:null), ]
- POSTHOOK: Lineage: bucketmapjoin_tmp_result.key SIMPLE [(srcbucket_mapjoin)a.FieldSchema(name:key, type:int, comment:null), ]
- POSTHOOK: Lineage: bucketmapjoin_tmp_result.value1 SIMPLE [(srcbucket_mapjoin)a.FieldSchema(name:value, type:string, comment:null), ]
- POSTHOOK: Lineage: bucketmapjoin_tmp_result.value1 SIMPLE [(srcbucket_mapjoin)a.FieldSchema(name:value, type:string, comment:null), ]
- POSTHOOK: Lineage: bucketmapjoin_tmp_result.value1 SIMPLE [(srcbucket_mapjoin)a.FieldSchema(name:value, type:string, comment:null), ]
- POSTHOOK: Lineage: bucketmapjoin_tmp_result.value1 SIMPLE [(srcbucket_mapjoin)a.FieldSchema(name:value, type:string, comment:null), ]
- POSTHOOK: Lineage: bucketmapjoin_tmp_result.value2 SIMPLE [(srcbucket_mapjoin)b.FieldSchema(name:value, type:string, comment:null), ]
- POSTHOOK: Lineage: bucketmapjoin_tmp_result.value2 SIMPLE [(srcbucket_mapjoin)b.FieldSchema(name:value, type:string, comment:null), ]
- POSTHOOK: Lineage: bucketmapjoin_tmp_result.value2 SIMPLE [(srcbucket_mapjoin)b.FieldSchema(name:value, type:string, comment:null), ]
- POSTHOOK: Lineage: bucketmapjoin_tmp_result.value2 SIMPLE [(srcbucket_mapjoin)b.FieldSchema(name:value, type:string, comment:null), ]
- PREHOOK: query: select count(1) from bucketmapjoin_tmp_result
- PREHOOK: type: QUERY
- PREHOOK: Input: default@bucketmapjoin_tmp_result
- PREHOOK: Output: file:/tmp/tomasz/hive_2011-06-01_18-48-24_754_566363396309899352/-mr-10000
- POSTHOOK: query: select count(1) from bucketmapjoin_tmp_result
- POSTHOOK: type: QUERY
- POSTHOOK: Input: default@bucketmapjoin_tmp_result
- POSTHOOK: Output: file:/tmp/tomasz/hive_2011-06-01_18-48-24_754_566363396309899352/-mr-10000
- POSTHOOK: Lineage: bucketmapjoin_hash_result_1.key EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:key, type:string, comment:null), ]
- POSTHOOK: Lineage: bucketmapjoin_hash_result_1.key EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:key, type:string, comment:null), ]
- POSTHOOK: Lineage: bucketmapjoin_hash_result_1.value1 EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:value1, type:string, comment:null), ]
- POSTHOOK: Lineage: bucketmapjoin_hash_result_1.value1 EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:value1, type:string, comment:null), ]
- POSTHOOK: Lineage: bucketmapjoin_hash_result_1.value2 EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:value2, type:string, comment:null), ]
- POSTHOOK: Lineage: bucketmapjoin_hash_result_1.value2 EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:value2, type:string, comment:null), ]
- POSTHOOK: Lineage: bucketmapjoin_hash_result_2.key EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:key, type:string, comment:null), ]
- POSTHOOK: Lineage: bucketmapjoin_hash_result_2.value1 EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:value1, type:string, comment:null), ]
- POSTHOOK: Lineage: bucketmapjoin_hash_result_2.value2 EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:value2, type:string, comment:null), ]
- POSTHOOK: Lineage: bucketmapjoin_tmp_result.key SIMPLE [(srcbucket_mapjoin)a.FieldSchema(name:key, type:int, comment:null), ]
- POSTHOOK: Lineage: bucketmapjoin_tmp_result.key SIMPLE [(srcbucket_mapjoin)a.FieldSchema(name:key, type:int, comment:null), ]
- POSTHOOK: Lineage: bucketmapjoin_tmp_result.key SIMPLE [(srcbucket_mapjoin)a.FieldSchema(name:key, type:int, comment:null), ]
- POSTHOOK: Lineage: bucketmapjoin_tmp_result.key SIMPLE [(srcbucket_mapjoin)a.FieldSchema(name:key, type:int, comment:null), ]
- POSTHOOK: Lineage: bucketmapjoin_tmp_result.value1 SIMPLE [(srcbucket_mapjoin)a.FieldSchema(name:value, type:string, comment:null), ]
- POSTHOOK: Lineage: bucketmapjoin_tmp_result.value1 SIMPLE [(srcbucket_mapjoin)a.FieldSchema(name:value, type:string, comment:null), ]
- POSTHOOK: Lineage: bucketmapjoin_tmp_result.value1 SIMPLE [(srcbucket_mapjoin)a.FieldSchema(name:value, type:string, comment:null), ]
- POSTHOOK: Lineage: bucketmapjoin_tmp_result.value1 SIMPLE [(srcbucket_mapjoin)a.FieldSchema(name:value, type:string, comment:null), ]
- POSTHOOK: Lineage: bucketmapjoin_tmp_result.value2 SIMPLE [(srcbucket_mapjoin)b.FieldSchema(name:value, type:string, comment:null), ]
- POSTHOOK: Lineage: bucketmapjoin_tmp_result.value2 SIMPLE [(srcbucket_mapjoin)b.FieldSchema(name:value, type:string, comment:null), ]
- POSTHOOK: Lineage: bucketmapjoin_tmp_result.value2 SIMPLE [(srcbucket_mapjoin)b.FieldSchema(name:value, type:string, comment:null), ]
- POSTHOOK: Lineage: bucketmapjoin_tmp_result.value2 SIMPLE [(srcbucket_mapjoin)b.FieldSchema(name:value, type:string, comment:null), ]
- 464
- PREHOOK: query: insert overwrite table bucketmapjoin_hash_result_2
- select sum(hash(key)), sum(hash(value1)), sum(hash(value2)) from bucketmapjoin_tmp_result
- PREHOOK: type: QUERY
- PREHOOK: Input: default@bucketmapjoin_tmp_result
- PREHOOK: Output: default@bucketmapjoin_hash_result_2
- POSTHOOK: query: insert overwrite table bucketmapjoin_hash_result_2
- select sum(hash(key)), sum(hash(value1)), sum(hash(value2)) from bucketmapjoin_tmp_result
- POSTHOOK: type: QUERY
- POSTHOOK: Input: default@bucketmapjoin_tmp_result
- POSTHOOK: Output: default@bucketmapjoin_hash_result_2
- POSTHOOK: Lineage: bucketmapjoin_hash_result_1.key EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:key, type:string, comment:null), ]
- POSTHOOK: Lineage: bucketmapjoin_hash_result_1.key EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:key, type:string, comment:null), ]
- POSTHOOK: Lineage: bucketmapjoin_hash_result_1.value1 EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:value1, type:string, comment:null), ]
- POSTHOOK: Lineage: bucketmapjoin_hash_result_1.value1 EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:value1, type:string, comment:null), ]
- POSTHOOK: Lineage: bucketmapjoin_hash_result_1.value2 EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:value2, type:string, comment:null), ]
- POSTHOOK: Lineage: bucketmapjoin_hash_result_1.value2 EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:value2, type:string, comment:null), ]
- POSTHOOK: Lineage: bucketmapjoin_hash_result_2.key EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:key, type:string, comment:null), ]
- POSTHOOK: Lineage: bucketmapjoin_hash_result_2.key EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:key, type:string, comment:null), ]
- POSTHOOK: Lineage: bucketmapjoin_hash_result_2.value1 EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:value1, type:string, comment:null), ]
- POSTHOOK: Lineage: bucketmapjoin_hash_result_2.value1 EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:value1, type:string, comment:null), ]
- POSTHOOK: Lineage: bucketmapjoin_hash_result_2.value2 EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:value2, type:string, comment:null), ]
- POSTHOOK: Lineage: bucketmapjoin_hash_result_2.value2 EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:value2, type:string, comment:null), ]
- POSTHOOK: Lineage: bucketmapjoin_tmp_result.key SIMPLE [(srcbucket_mapjoin)a.FieldSchema(name:key, type:int, comment:null), ]
- POSTHOOK: Lineage: bucketmapjoin_tmp_result.key SIMPLE [(srcbucket_mapjoin)a.FieldSchema(name:key, type:int, comment:null), ]
- POSTHOOK: Lineage: bucketmapjoin_tmp_result.key SIMPLE [(srcbucket_mapjoin)a.FieldSchema(name:key, type:int, comment:null), ]
- POSTHOOK: Lineage: bucketmapjoin_tmp_result.key SIMPLE [(srcbucket_mapjoin)a.FieldSchema(name:key, type:int, comment:null), ]
- POSTHOOK: Lineage: bucketmapjoin_tmp_result.value1 SIMPLE [(srcbucket_mapjoin)a.FieldSchema(name:value, type:string, comment:null), ]
- POSTHOOK: Lineage: bucketmapjoin_tmp_result.value1 SIMPLE [(srcbucket_mapjoin)a.FieldSchema(name:value, type:string, comment:null), ]
- POSTHOOK: Lineage: bucketmapjoin_tmp_result.value1 SIMPLE [(srcbucket_mapjoin)a.FieldSchema(name:value, type:string, comment:null), ]
- POSTHOOK: Lineage: bucketmapjoin_tmp_result.value1 SIMPLE [(srcbucket_mapjoin)a.FieldSchema(name:value, type:string, comment:null), ]
- POSTHOOK: Lineage: bucketmapjoin_tmp_result.value2 SIMPLE [(srcbucket_mapjoin)b.FieldSchema(name:value, type:string, comment:null), ]
- POSTHOOK: Lineage: bucketmapjoin_tmp_result.value2 SIMPLE [(srcbucket_mapjoin)b.FieldSchema(name:value, type:string, comment:null), ]
- POSTHOOK: Lineage: bucketmapjoin_tmp_result.value2 SIMPLE [(srcbucket_mapjoin)b.FieldSchema(name:value, type:string, comment:null), ]
- POSTHOOK: Lineage: bucketmapjoin_tmp_result.value2 SIMPLE [(srcbucket_mapjoin)b.FieldSchema(name:value, type:string, comment:null), ]
- PREHOOK: query: select a.key-b.key, a.value1-b.value1, a.value2-b.value2
- from bucketmapjoin_hash_result_1 a left outer join bucketmapjoin_hash_result_2 b
- on a.key = b.key
- PREHOOK: type: QUERY
- PREHOOK: Input: default@bucketmapjoin_hash_result_1
- PREHOOK: Input: default@bucketmapjoin_hash_result_2
- PREHOOK: Output: file:/tmp/tomasz/hive_2011-06-01_18-48-31_737_7723797880113602584/-mr-10000
- POSTHOOK: query: select a.key-b.key, a.value1-b.value1, a.value2-b.value2
- from bucketmapjoin_hash_result_1 a left outer join bucketmapjoin_hash_result_2 b
- on a.key = b.key
- POSTHOOK: type: QUERY
- POSTHOOK: Input: default@bucketmapjoin_hash_result_1
- POSTHOOK: Input: default@bucketmapjoin_hash_result_2
- POSTHOOK: Output: file:/tmp/tomasz/hive_2011-06-01_18-48-31_737_7723797880113602584/-mr-10000
- POSTHOOK: Lineage: bucketmapjoin_hash_result_1.key EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:key, type:string, comment:null), ]
- POSTHOOK: Lineage: bucketmapjoin_hash_result_1.key EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:key, type:string, comment:null), ]
- POSTHOOK: Lineage: bucketmapjoin_hash_result_1.value1 EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:value1, type:string, comment:null), ]
- POSTHOOK: Lineage: bucketmapjoin_hash_result_1.value1 EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:value1, type:string, comment:null), ]
- POSTHOOK: Lineage: bucketmapjoin_hash_result_1.value2 EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:value2, type:string, comment:null), ]
- POSTHOOK: Lineage: bucketmapjoin_hash_result_1.value2 EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:value2, type:string, comment:null), ]
- POSTHOOK: Lineage: bucketmapjoin_hash_result_2.key EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:key, type:string, comment:null), ]
- POSTHOOK: Lineage: bucketmapjoin_hash_result_2.key EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:key, type:string, comment:null), ]
- POSTHOOK: Lineage: bucketmapjoin_hash_result_2.value1 EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:value1, type:string, comment:null), ]
- POSTHOOK: Lineage: bucketmapjoin_hash_result_2.value1 EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:value1, type:string, comment:null), ]
- POSTHOOK: Lineage: bucketmapjoin_hash_result_2.value2 EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:value2, type:string, comment:null), ]
- POSTHOOK: Lineage: bucketmapjoin_hash_result_2.value2 EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:value2, type:string, comment:null), ]
- POSTHOOK: Lineage: bucketmapjoin_tmp_result.key SIMPLE [(srcbucket_mapjoin)a.FieldSchema(name:key, type:int, comment:null), ]
- POSTHOOK: Lineage: bucketmapjoin_tmp_result.key SIMPLE [(srcbucket_mapjoin)a.FieldSchema(name:key, type:int, comment:null), ]
- POSTHOOK: Lineage: bucketmapjoin_tmp_result.key SIMPLE [(srcbucket_mapjoin)a.FieldSchema(name:key, type:int, comment:null), ]
- POSTHOOK: Lineage: bucketmapjoin_tmp_result.key SIMPLE [(srcbucket_mapjoin)a.FieldSchema(name:key, type:int, comment:null), ]
- POSTHOOK: Lineage: bucketmapjoin_tmp_result.value1 SIMPLE [(srcbucket_mapjoin)a.FieldSchema(name:value, type:string, comment:null), ]
- POSTHOOK: Lineage: bucketmapjoin_tmp_result.value1 SIMPLE [(srcbucket_mapjoin)a.FieldSchema(name:value, type:string, comment:null), ]
- POSTHOOK: Lineage: bucketmapjoin_tmp_result.value1 SIMPLE [(srcbucket_mapjoin)a.FieldSchema(name:value, type:string, comment:null), ]
- POSTHOOK: Lineage: bucketmapjoin_tmp_result.value1 SIMPLE [(srcbucket_mapjoin)a.FieldSchema(name:value, type:string, comment:null), ]
- POSTHOOK: Lineage: bucketmapjoin_tmp_result.value2 SIMPLE [(srcbucket_mapjoin)b.FieldSchema(name:value, type:string, comment:null), ]
- POSTHOOK: Lineage: bucketmapjoin_tmp_result.value2 SIMPLE [(srcbucket_mapjoin)b.FieldSchema(name:value, type:string, comment:null), ]
- POSTHOOK: Lineage: bucketmapjoin_tmp_result.value2 SIMPLE [(srcbucket_mapjoin)b.FieldSchema(name:value, type:string, comment:null), ]
- POSTHOOK: Lineage: bucketmapjoin_tmp_result.value2 SIMPLE [(srcbucket_mapjoin)b.FieldSchema(name:value, type:string, comment:null), ]
- 0 0 0