| PREHOOK: query: CREATE TABLE srcbucket_mapjoin_part_n19 (key int, value string) partitioned by (ds string) CLUSTERED BY (key) INTO 4 BUCKETS STORED AS TEXTFILE |
| PREHOOK: type: CREATETABLE |
| PREHOOK: Output: database:default |
| PREHOOK: Output: default@srcbucket_mapjoin_part_n19 |
| POSTHOOK: query: CREATE TABLE srcbucket_mapjoin_part_n19 (key int, value string) partitioned by (ds string) CLUSTERED BY (key) INTO 4 BUCKETS STORED AS TEXTFILE |
| POSTHOOK: type: CREATETABLE |
| POSTHOOK: Output: database:default |
| POSTHOOK: Output: default@srcbucket_mapjoin_part_n19 |
| PREHOOK: query: load data local inpath '../../data/files/bmj/000000_0' INTO TABLE srcbucket_mapjoin_part_n19 partition(ds='2008-04-08') |
| PREHOOK: type: LOAD |
| #### A masked pattern was here #### |
| PREHOOK: Output: default@srcbucket_mapjoin_part_n19 |
| POSTHOOK: query: load data local inpath '../../data/files/bmj/000000_0' INTO TABLE srcbucket_mapjoin_part_n19 partition(ds='2008-04-08') |
| POSTHOOK: type: LOAD |
| #### A masked pattern was here #### |
| POSTHOOK: Output: default@srcbucket_mapjoin_part_n19 |
| POSTHOOK: Output: default@srcbucket_mapjoin_part_n19@ds=2008-04-08 |
| PREHOOK: query: load data local inpath '../../data/files/bmj/000001_0' INTO TABLE srcbucket_mapjoin_part_n19 partition(ds='2008-04-08') |
| PREHOOK: type: LOAD |
| #### A masked pattern was here #### |
| PREHOOK: Output: default@srcbucket_mapjoin_part_n19@ds=2008-04-08 |
| POSTHOOK: query: load data local inpath '../../data/files/bmj/000001_0' INTO TABLE srcbucket_mapjoin_part_n19 partition(ds='2008-04-08') |
| POSTHOOK: type: LOAD |
| #### A masked pattern was here #### |
| POSTHOOK: Output: default@srcbucket_mapjoin_part_n19@ds=2008-04-08 |
| PREHOOK: query: load data local inpath '../../data/files/bmj/000002_0' INTO TABLE srcbucket_mapjoin_part_n19 partition(ds='2008-04-08') |
| PREHOOK: type: LOAD |
| #### A masked pattern was here #### |
| PREHOOK: Output: default@srcbucket_mapjoin_part_n19@ds=2008-04-08 |
| POSTHOOK: query: load data local inpath '../../data/files/bmj/000002_0' INTO TABLE srcbucket_mapjoin_part_n19 partition(ds='2008-04-08') |
| POSTHOOK: type: LOAD |
| #### A masked pattern was here #### |
| POSTHOOK: Output: default@srcbucket_mapjoin_part_n19@ds=2008-04-08 |
| PREHOOK: query: load data local inpath '../../data/files/bmj/000003_0' INTO TABLE srcbucket_mapjoin_part_n19 partition(ds='2008-04-08') |
| PREHOOK: type: LOAD |
| #### A masked pattern was here #### |
| PREHOOK: Output: default@srcbucket_mapjoin_part_n19@ds=2008-04-08 |
| POSTHOOK: query: load data local inpath '../../data/files/bmj/000003_0' INTO TABLE srcbucket_mapjoin_part_n19 partition(ds='2008-04-08') |
| POSTHOOK: type: LOAD |
| #### A masked pattern was here #### |
| POSTHOOK: Output: default@srcbucket_mapjoin_part_n19@ds=2008-04-08 |
| PREHOOK: query: CREATE TABLE srcbucket_mapjoin_part_2_n16 (key int, value string) partitioned by (ds string) CLUSTERED BY (key) INTO 4 BUCKETS STORED AS TEXTFILE |
| PREHOOK: type: CREATETABLE |
| PREHOOK: Output: database:default |
| PREHOOK: Output: default@srcbucket_mapjoin_part_2_n16 |
| POSTHOOK: query: CREATE TABLE srcbucket_mapjoin_part_2_n16 (key int, value string) partitioned by (ds string) CLUSTERED BY (key) INTO 4 BUCKETS STORED AS TEXTFILE |
| POSTHOOK: type: CREATETABLE |
| POSTHOOK: Output: database:default |
| POSTHOOK: Output: default@srcbucket_mapjoin_part_2_n16 |
| PREHOOK: query: load data local inpath '../../data/files/bmj/000000_0' INTO TABLE srcbucket_mapjoin_part_2_n16 partition(ds='2008-04-08') |
| PREHOOK: type: LOAD |
| #### A masked pattern was here #### |
| PREHOOK: Output: default@srcbucket_mapjoin_part_2_n16 |
| POSTHOOK: query: load data local inpath '../../data/files/bmj/000000_0' INTO TABLE srcbucket_mapjoin_part_2_n16 partition(ds='2008-04-08') |
| POSTHOOK: type: LOAD |
| #### A masked pattern was here #### |
| POSTHOOK: Output: default@srcbucket_mapjoin_part_2_n16 |
| POSTHOOK: Output: default@srcbucket_mapjoin_part_2_n16@ds=2008-04-08 |
| PREHOOK: query: load data local inpath '../../data/files/bmj/000001_0' INTO TABLE srcbucket_mapjoin_part_2_n16 partition(ds='2008-04-08') |
| PREHOOK: type: LOAD |
| #### A masked pattern was here #### |
| PREHOOK: Output: default@srcbucket_mapjoin_part_2_n16@ds=2008-04-08 |
| POSTHOOK: query: load data local inpath '../../data/files/bmj/000001_0' INTO TABLE srcbucket_mapjoin_part_2_n16 partition(ds='2008-04-08') |
| POSTHOOK: type: LOAD |
| #### A masked pattern was here #### |
| POSTHOOK: Output: default@srcbucket_mapjoin_part_2_n16@ds=2008-04-08 |
| PREHOOK: query: load data local inpath '../../data/files/bmj/000002_0' INTO TABLE srcbucket_mapjoin_part_2_n16 partition(ds='2008-04-08') |
| PREHOOK: type: LOAD |
| #### A masked pattern was here #### |
| PREHOOK: Output: default@srcbucket_mapjoin_part_2_n16@ds=2008-04-08 |
| POSTHOOK: query: load data local inpath '../../data/files/bmj/000002_0' INTO TABLE srcbucket_mapjoin_part_2_n16 partition(ds='2008-04-08') |
| POSTHOOK: type: LOAD |
| #### A masked pattern was here #### |
| POSTHOOK: Output: default@srcbucket_mapjoin_part_2_n16@ds=2008-04-08 |
| PREHOOK: query: load data local inpath '../../data/files/bmj/000003_0' INTO TABLE srcbucket_mapjoin_part_2_n16 partition(ds='2008-04-08') |
| PREHOOK: type: LOAD |
| #### A masked pattern was here #### |
| PREHOOK: Output: default@srcbucket_mapjoin_part_2_n16@ds=2008-04-08 |
| POSTHOOK: query: load data local inpath '../../data/files/bmj/000003_0' INTO TABLE srcbucket_mapjoin_part_2_n16 partition(ds='2008-04-08') |
| POSTHOOK: type: LOAD |
| #### A masked pattern was here #### |
| POSTHOOK: Output: default@srcbucket_mapjoin_part_2_n16@ds=2008-04-08 |
| PREHOOK: query: create table bucketmapjoin_hash_result_1_n7 (key bigint , value1 bigint, value2 bigint) |
| PREHOOK: type: CREATETABLE |
| PREHOOK: Output: database:default |
| PREHOOK: Output: default@bucketmapjoin_hash_result_1_n7 |
| POSTHOOK: query: create table bucketmapjoin_hash_result_1_n7 (key bigint , value1 bigint, value2 bigint) |
| POSTHOOK: type: CREATETABLE |
| POSTHOOK: Output: database:default |
| POSTHOOK: Output: default@bucketmapjoin_hash_result_1_n7 |
| PREHOOK: query: create table bucketmapjoin_hash_result_2_n7 (key bigint , value1 bigint, value2 bigint) |
| PREHOOK: type: CREATETABLE |
| PREHOOK: Output: database:default |
| PREHOOK: Output: default@bucketmapjoin_hash_result_2_n7 |
| POSTHOOK: query: create table bucketmapjoin_hash_result_2_n7 (key bigint , value1 bigint, value2 bigint) |
| POSTHOOK: type: CREATETABLE |
| POSTHOOK: Output: database:default |
| POSTHOOK: Output: default@bucketmapjoin_hash_result_2_n7 |
| PREHOOK: query: create table bucketmapjoin_tmp_result_n9 (key string , value1 string, value2 string) |
| PREHOOK: type: CREATETABLE |
| PREHOOK: Output: database:default |
| PREHOOK: Output: default@bucketmapjoin_tmp_result_n9 |
| POSTHOOK: query: create table bucketmapjoin_tmp_result_n9 (key string , value1 string, value2 string) |
| POSTHOOK: type: CREATETABLE |
| POSTHOOK: Output: database:default |
| POSTHOOK: Output: default@bucketmapjoin_tmp_result_n9 |
| PREHOOK: query: explain extended |
| insert overwrite table bucketmapjoin_tmp_result_n9 |
| select a.key, a.value, b.value |
| from srcbucket_mapjoin_part_n19 a join srcbucket_mapjoin_part_2_n16 b |
| on a.key=b.key and b.ds="2008-04-08" |
| PREHOOK: type: QUERY |
| POSTHOOK: query: explain extended |
| insert overwrite table bucketmapjoin_tmp_result_n9 |
| select a.key, a.value, b.value |
| from srcbucket_mapjoin_part_n19 a join srcbucket_mapjoin_part_2_n16 b |
| on a.key=b.key and b.ds="2008-04-08" |
| POSTHOOK: type: QUERY |
| STAGE DEPENDENCIES: |
| Stage-6 is a root stage |
| Stage-5 depends on stages: Stage-6 |
| Stage-0 depends on stages: Stage-5 |
| Stage-2 depends on stages: Stage-0, Stage-3 |
| Stage-3 depends on stages: Stage-5 |
| |
| STAGE PLANS: |
| Stage: Stage-6 |
| 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 4 |
| bucket_field_name key |
| column.name.delimiter , |
| columns key,value |
| columns.comments |
| columns.types int:string |
| #### A masked pattern was here #### |
| name default.srcbucket_mapjoin_part_n19 |
| numFiles 4 |
| numRows 0 |
| partition_columns ds |
| partition_columns.types string |
| rawDataSize 0 |
| serialization.ddl struct srcbucket_mapjoin_part_n19 { i32 key, string value} |
| serialization.format 1 |
| serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe |
| totalSize 5812 |
| #### 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: |
| bucket_count 4 |
| bucket_field_name key |
| bucketing_version 2 |
| column.name.delimiter , |
| columns key,value |
| columns.comments |
| columns.types int:string |
| #### A masked pattern was here #### |
| name default.srcbucket_mapjoin_part_n19 |
| partition_columns ds |
| partition_columns.types string |
| serialization.ddl struct srcbucket_mapjoin_part_n19 { i32 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.srcbucket_mapjoin_part_n19 |
| name: default.srcbucket_mapjoin_part_n19 |
| Alias -> Map Local Operator Tree: |
| $hdt$_0:a |
| TableScan |
| alias: a |
| Statistics: Num rows: 149 Data size: 58120 Basic stats: COMPLETE Column stats: NONE |
| GatherStats: false |
| Filter Operator |
| isSamplingPred: false |
| predicate: key is not null (type: boolean) |
| Statistics: Num rows: 149 Data size: 58120 Basic stats: COMPLETE Column stats: NONE |
| Select Operator |
| expressions: key (type: int), value (type: string) |
| outputColumnNames: _col0, _col1 |
| Statistics: Num rows: 149 Data size: 58120 Basic stats: COMPLETE Column stats: NONE |
| HashTable Sink Operator |
| keys: |
| 0 _col0 (type: int) |
| 1 _col0 (type: int) |
| Position of Big Table: 1 |
| |
| Stage: Stage-5 |
| Map Reduce |
| Map Operator Tree: |
| TableScan |
| alias: b |
| Statistics: Num rows: 149 Data size: 58120 Basic stats: COMPLETE Column stats: NONE |
| GatherStats: false |
| Filter Operator |
| isSamplingPred: false |
| predicate: key is not null (type: boolean) |
| Statistics: Num rows: 149 Data size: 58120 Basic stats: COMPLETE Column stats: NONE |
| Select Operator |
| expressions: key (type: int), value (type: string) |
| outputColumnNames: _col0, _col1 |
| Statistics: Num rows: 149 Data size: 58120 Basic stats: COMPLETE Column stats: NONE |
| Map Join Operator |
| condition map: |
| Inner Join 0 to 1 |
| keys: |
| 0 _col0 (type: int) |
| 1 _col0 (type: int) |
| outputColumnNames: _col0, _col1, _col3 |
| Position of Big Table: 1 |
| Statistics: Num rows: 163 Data size: 63932 Basic stats: COMPLETE Column stats: NONE |
| Select Operator |
| expressions: UDFToString(_col0) (type: string), _col1 (type: string), _col3 (type: string) |
| outputColumnNames: _col0, _col1, _col2 |
| Statistics: Num rows: 163 Data size: 63932 Basic stats: COMPLETE Column stats: NONE |
| File Output Operator |
| compressed: false |
| GlobalTableId: 1 |
| #### A masked pattern was here #### |
| NumFilesPerFileSink: 1 |
| Statistics: Num rows: 163 Data size: 63932 Basic stats: COMPLETE Column stats: NONE |
| #### A masked pattern was here #### |
| table: |
| input format: org.apache.hadoop.mapred.TextInputFormat |
| output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat |
| properties: |
| COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value1":"true","value2":"true"}} |
| bucket_count -1 |
| bucketing_version 2 |
| column.name.delimiter , |
| columns key,value1,value2 |
| columns.comments |
| columns.types string:string:string |
| #### A masked pattern was here #### |
| name default.bucketmapjoin_tmp_result_n9 |
| numFiles 0 |
| numRows 0 |
| rawDataSize 0 |
| serialization.ddl struct bucketmapjoin_tmp_result_n9 { string key, string value1, string value2} |
| serialization.format 1 |
| serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe |
| totalSize 0 |
| #### A masked pattern was here #### |
| serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe |
| name: default.bucketmapjoin_tmp_result_n9 |
| TotalFiles: 1 |
| GatherStats: true |
| MultiFileSpray: false |
| Select Operator |
| expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) |
| outputColumnNames: key, value1, value2 |
| Statistics: Num rows: 163 Data size: 63932 Basic stats: COMPLETE Column stats: NONE |
| Group By Operator |
| aggregations: compute_stats(key, 'hll'), compute_stats(value1, 'hll'), compute_stats(value2, 'hll') |
| mode: hash |
| outputColumnNames: _col0, _col1, _col2 |
| Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE |
| File Output Operator |
| compressed: false |
| GlobalTableId: 0 |
| #### A masked pattern was here #### |
| NumFilesPerFileSink: 1 |
| table: |
| input format: org.apache.hadoop.mapred.SequenceFileInputFormat |
| output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat |
| properties: |
| column.name.delimiter , |
| columns _col0,_col1,_col2 |
| columns.types struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>,struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>,struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary> |
| escape.delim \ |
| serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe |
| serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe |
| TotalFiles: 1 |
| GatherStats: false |
| MultiFileSpray: false |
| 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 4 |
| bucket_field_name key |
| column.name.delimiter , |
| columns key,value |
| columns.comments |
| columns.types int:string |
| #### A masked pattern was here #### |
| name default.srcbucket_mapjoin_part_2_n16 |
| numFiles 4 |
| numRows 0 |
| partition_columns ds |
| partition_columns.types string |
| rawDataSize 0 |
| serialization.ddl struct srcbucket_mapjoin_part_2_n16 { i32 key, string value} |
| serialization.format 1 |
| serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe |
| totalSize 5812 |
| #### 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: |
| bucket_count 4 |
| bucket_field_name key |
| bucketing_version 2 |
| column.name.delimiter , |
| columns key,value |
| columns.comments |
| columns.types int:string |
| #### A masked pattern was here #### |
| name default.srcbucket_mapjoin_part_2_n16 |
| partition_columns ds |
| partition_columns.types string |
| serialization.ddl struct srcbucket_mapjoin_part_2_n16 { i32 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.srcbucket_mapjoin_part_2_n16 |
| name: default.srcbucket_mapjoin_part_2_n16 |
| #### 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 4 |
| bucket_field_name key |
| column.name.delimiter , |
| columns key,value |
| columns.comments |
| columns.types int:string |
| #### A masked pattern was here #### |
| name default.srcbucket_mapjoin_part_n19 |
| numFiles 4 |
| numRows 0 |
| partition_columns ds |
| partition_columns.types string |
| rawDataSize 0 |
| serialization.ddl struct srcbucket_mapjoin_part_n19 { i32 key, string value} |
| serialization.format 1 |
| serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe |
| totalSize 5812 |
| #### 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: |
| bucket_count 4 |
| bucket_field_name key |
| bucketing_version 2 |
| column.name.delimiter , |
| columns key,value |
| columns.comments |
| columns.types int:string |
| #### A masked pattern was here #### |
| name default.srcbucket_mapjoin_part_n19 |
| partition_columns ds |
| partition_columns.types string |
| serialization.ddl struct srcbucket_mapjoin_part_n19 { i32 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.srcbucket_mapjoin_part_n19 |
| name: default.srcbucket_mapjoin_part_n19 |
| Truncated Path -> Alias: |
| /srcbucket_mapjoin_part_2_n16/ds=2008-04-08 [$hdt$_1:b] |
| |
| Stage: Stage-0 |
| Move Operator |
| tables: |
| replace: true |
| #### A masked pattern was here #### |
| table: |
| input format: org.apache.hadoop.mapred.TextInputFormat |
| output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat |
| properties: |
| COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value1":"true","value2":"true"}} |
| bucket_count -1 |
| bucketing_version 2 |
| column.name.delimiter , |
| columns key,value1,value2 |
| columns.comments |
| columns.types string:string:string |
| #### A masked pattern was here #### |
| name default.bucketmapjoin_tmp_result_n9 |
| numFiles 0 |
| numRows 0 |
| rawDataSize 0 |
| serialization.ddl struct bucketmapjoin_tmp_result_n9 { string key, string value1, string value2} |
| serialization.format 1 |
| serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe |
| totalSize 0 |
| #### A masked pattern was here #### |
| serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe |
| name: default.bucketmapjoin_tmp_result_n9 |
| |
| Stage: Stage-2 |
| Stats Work |
| Basic Stats Work: |
| #### A masked pattern was here #### |
| Column Stats Desc: |
| Columns: key, value1, value2 |
| Column Types: string, string, string |
| Table: default.bucketmapjoin_tmp_result_n9 |
| Is Table Level Stats: true |
| |
| Stage: Stage-3 |
| Map Reduce |
| Map Operator Tree: |
| TableScan |
| GatherStats: false |
| Reduce Output Operator |
| null sort order: |
| sort order: |
| Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE |
| tag: -1 |
| value expressions: _col0 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col2 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>) |
| auto parallelism: false |
| Path -> Alias: |
| #### A masked pattern was here #### |
| Path -> Partition: |
| #### A masked pattern was here #### |
| Partition |
| base file name: -mr-10002 |
| input format: org.apache.hadoop.mapred.SequenceFileInputFormat |
| output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat |
| properties: |
| column.name.delimiter , |
| columns _col0,_col1,_col2 |
| columns.types struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>,struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>,struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary> |
| escape.delim \ |
| serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe |
| serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe |
| |
| input format: org.apache.hadoop.mapred.SequenceFileInputFormat |
| output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat |
| properties: |
| column.name.delimiter , |
| columns _col0,_col1,_col2 |
| columns.types struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>,struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>,struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary> |
| escape.delim \ |
| serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe |
| serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe |
| Truncated Path -> Alias: |
| #### A masked pattern was here #### |
| Needs Tagging: false |
| Reduce Operator Tree: |
| Group By Operator |
| aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2) |
| mode: mergepartial |
| outputColumnNames: _col0, _col1, _col2 |
| Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE |
| File Output Operator |
| compressed: false |
| GlobalTableId: 0 |
| #### A masked pattern was here #### |
| NumFilesPerFileSink: 1 |
| Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE |
| #### A masked pattern was here #### |
| table: |
| input format: org.apache.hadoop.mapred.SequenceFileInputFormat |
| output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat |
| properties: |
| columns _col0,_col1,_col2 |
| columns.types struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>:struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>:struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary> |
| 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 |
| |
| PREHOOK: query: insert overwrite table bucketmapjoin_tmp_result_n9 |
| select a.key, a.value, b.value |
| from srcbucket_mapjoin_part_n19 a join srcbucket_mapjoin_part_2_n16 b |
| on a.key=b.key and b.ds="2008-04-08" |
| PREHOOK: type: QUERY |
| PREHOOK: Input: default@srcbucket_mapjoin_part_2_n16 |
| PREHOOK: Input: default@srcbucket_mapjoin_part_2_n16@ds=2008-04-08 |
| PREHOOK: Input: default@srcbucket_mapjoin_part_n19 |
| PREHOOK: Input: default@srcbucket_mapjoin_part_n19@ds=2008-04-08 |
| PREHOOK: Output: default@bucketmapjoin_tmp_result_n9 |
| POSTHOOK: query: insert overwrite table bucketmapjoin_tmp_result_n9 |
| select a.key, a.value, b.value |
| from srcbucket_mapjoin_part_n19 a join srcbucket_mapjoin_part_2_n16 b |
| on a.key=b.key and b.ds="2008-04-08" |
| POSTHOOK: type: QUERY |
| POSTHOOK: Input: default@srcbucket_mapjoin_part_2_n16 |
| POSTHOOK: Input: default@srcbucket_mapjoin_part_2_n16@ds=2008-04-08 |
| POSTHOOK: Input: default@srcbucket_mapjoin_part_n19 |
| POSTHOOK: Input: default@srcbucket_mapjoin_part_n19@ds=2008-04-08 |
| POSTHOOK: Output: default@bucketmapjoin_tmp_result_n9 |
| POSTHOOK: Lineage: bucketmapjoin_tmp_result_n9.key EXPRESSION [(srcbucket_mapjoin_part_n19)a.FieldSchema(name:key, type:int, comment:null), ] |
| POSTHOOK: Lineage: bucketmapjoin_tmp_result_n9.value1 SIMPLE [(srcbucket_mapjoin_part_n19)a.FieldSchema(name:value, type:string, comment:null), ] |
| POSTHOOK: Lineage: bucketmapjoin_tmp_result_n9.value2 SIMPLE [(srcbucket_mapjoin_part_2_n16)b.FieldSchema(name:value, type:string, comment:null), ] |
| PREHOOK: query: select count(1) from bucketmapjoin_tmp_result_n9 |
| PREHOOK: type: QUERY |
| PREHOOK: Input: default@bucketmapjoin_tmp_result_n9 |
| #### A masked pattern was here #### |
| POSTHOOK: query: select count(1) from bucketmapjoin_tmp_result_n9 |
| POSTHOOK: type: QUERY |
| POSTHOOK: Input: default@bucketmapjoin_tmp_result_n9 |
| #### A masked pattern was here #### |
| 1028 |
| PREHOOK: query: insert overwrite table bucketmapjoin_hash_result_1_n7 |
| select sum(hash(key)), sum(hash(value1)), sum(hash(value2)) from bucketmapjoin_tmp_result_n9 |
| PREHOOK: type: QUERY |
| PREHOOK: Input: default@bucketmapjoin_tmp_result_n9 |
| PREHOOK: Output: default@bucketmapjoin_hash_result_1_n7 |
| POSTHOOK: query: insert overwrite table bucketmapjoin_hash_result_1_n7 |
| select sum(hash(key)), sum(hash(value1)), sum(hash(value2)) from bucketmapjoin_tmp_result_n9 |
| POSTHOOK: type: QUERY |
| POSTHOOK: Input: default@bucketmapjoin_tmp_result_n9 |
| POSTHOOK: Output: default@bucketmapjoin_hash_result_1_n7 |
| POSTHOOK: Lineage: bucketmapjoin_hash_result_1_n7.key EXPRESSION [(bucketmapjoin_tmp_result_n9)bucketmapjoin_tmp_result_n9.FieldSchema(name:key, type:string, comment:null), ] |
| POSTHOOK: Lineage: bucketmapjoin_hash_result_1_n7.value1 EXPRESSION [(bucketmapjoin_tmp_result_n9)bucketmapjoin_tmp_result_n9.FieldSchema(name:value1, type:string, comment:null), ] |
| POSTHOOK: Lineage: bucketmapjoin_hash_result_1_n7.value2 EXPRESSION [(bucketmapjoin_tmp_result_n9)bucketmapjoin_tmp_result_n9.FieldSchema(name:value2, type:string, comment:null), ] |
| PREHOOK: query: explain extended |
| insert overwrite table bucketmapjoin_tmp_result_n9 |
| select a.key, a.value, b.value |
| from srcbucket_mapjoin_part_n19 a join srcbucket_mapjoin_part_2_n16 b |
| on a.key=b.key and b.ds="2008-04-08" |
| PREHOOK: type: QUERY |
| POSTHOOK: query: explain extended |
| insert overwrite table bucketmapjoin_tmp_result_n9 |
| select a.key, a.value, b.value |
| from srcbucket_mapjoin_part_n19 a join srcbucket_mapjoin_part_2_n16 b |
| on a.key=b.key and b.ds="2008-04-08" |
| POSTHOOK: type: QUERY |
| STAGE DEPENDENCIES: |
| Stage-6 is a root stage |
| Stage-5 depends on stages: Stage-6 |
| Stage-0 depends on stages: Stage-5 |
| Stage-2 depends on stages: Stage-0, Stage-3 |
| Stage-3 depends on stages: Stage-5 |
| |
| STAGE PLANS: |
| Stage: Stage-6 |
| 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 4 |
| bucket_field_name key |
| column.name.delimiter , |
| columns key,value |
| columns.comments |
| columns.types int:string |
| #### A masked pattern was here #### |
| name default.srcbucket_mapjoin_part_n19 |
| numFiles 4 |
| numRows 0 |
| partition_columns ds |
| partition_columns.types string |
| rawDataSize 0 |
| serialization.ddl struct srcbucket_mapjoin_part_n19 { i32 key, string value} |
| serialization.format 1 |
| serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe |
| totalSize 5812 |
| #### 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: |
| bucket_count 4 |
| bucket_field_name key |
| bucketing_version 2 |
| column.name.delimiter , |
| columns key,value |
| columns.comments |
| columns.types int:string |
| #### A masked pattern was here #### |
| name default.srcbucket_mapjoin_part_n19 |
| partition_columns ds |
| partition_columns.types string |
| serialization.ddl struct srcbucket_mapjoin_part_n19 { i32 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.srcbucket_mapjoin_part_n19 |
| name: default.srcbucket_mapjoin_part_n19 |
| Alias -> Map Local Operator Tree: |
| $hdt$_0:a |
| TableScan |
| alias: a |
| Statistics: Num rows: 149 Data size: 58120 Basic stats: COMPLETE Column stats: NONE |
| GatherStats: false |
| Filter Operator |
| isSamplingPred: false |
| predicate: key is not null (type: boolean) |
| Statistics: Num rows: 149 Data size: 58120 Basic stats: COMPLETE Column stats: NONE |
| Select Operator |
| expressions: key (type: int), value (type: string) |
| outputColumnNames: _col0, _col1 |
| Statistics: Num rows: 149 Data size: 58120 Basic stats: COMPLETE Column stats: NONE |
| HashTable Sink Operator |
| keys: |
| 0 _col0 (type: int) |
| 1 _col0 (type: int) |
| Position of Big Table: 1 |
| |
| Stage: Stage-5 |
| Map Reduce |
| Map Operator Tree: |
| TableScan |
| alias: b |
| Statistics: Num rows: 149 Data size: 58120 Basic stats: COMPLETE Column stats: NONE |
| GatherStats: false |
| Filter Operator |
| isSamplingPred: false |
| predicate: key is not null (type: boolean) |
| Statistics: Num rows: 149 Data size: 58120 Basic stats: COMPLETE Column stats: NONE |
| Select Operator |
| expressions: key (type: int), value (type: string) |
| outputColumnNames: _col0, _col1 |
| Statistics: Num rows: 149 Data size: 58120 Basic stats: COMPLETE Column stats: NONE |
| Map Join Operator |
| condition map: |
| Inner Join 0 to 1 |
| keys: |
| 0 _col0 (type: int) |
| 1 _col0 (type: int) |
| outputColumnNames: _col0, _col1, _col3 |
| Position of Big Table: 1 |
| Statistics: Num rows: 163 Data size: 63932 Basic stats: COMPLETE Column stats: NONE |
| Select Operator |
| expressions: UDFToString(_col0) (type: string), _col1 (type: string), _col3 (type: string) |
| outputColumnNames: _col0, _col1, _col2 |
| Statistics: Num rows: 163 Data size: 63932 Basic stats: COMPLETE Column stats: NONE |
| File Output Operator |
| compressed: false |
| GlobalTableId: 1 |
| #### A masked pattern was here #### |
| NumFilesPerFileSink: 1 |
| Statistics: Num rows: 163 Data size: 63932 Basic stats: COMPLETE Column stats: NONE |
| #### A masked pattern was here #### |
| table: |
| input format: org.apache.hadoop.mapred.TextInputFormat |
| output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat |
| properties: |
| COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value1":"true","value2":"true"}} |
| bucket_count -1 |
| bucketing_version 2 |
| column.name.delimiter , |
| columns key,value1,value2 |
| columns.comments |
| columns.types string:string:string |
| #### A masked pattern was here #### |
| name default.bucketmapjoin_tmp_result_n9 |
| numFiles 1 |
| numRows 1028 |
| rawDataSize 19022 |
| serialization.ddl struct bucketmapjoin_tmp_result_n9 { string key, string value1, string value2} |
| serialization.format 1 |
| serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe |
| totalSize 20050 |
| #### A masked pattern was here #### |
| serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe |
| name: default.bucketmapjoin_tmp_result_n9 |
| TotalFiles: 1 |
| GatherStats: true |
| MultiFileSpray: false |
| Select Operator |
| expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) |
| outputColumnNames: key, value1, value2 |
| Statistics: Num rows: 163 Data size: 63932 Basic stats: COMPLETE Column stats: NONE |
| Group By Operator |
| aggregations: compute_stats(key, 'hll'), compute_stats(value1, 'hll'), compute_stats(value2, 'hll') |
| mode: hash |
| outputColumnNames: _col0, _col1, _col2 |
| Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE |
| File Output Operator |
| compressed: false |
| GlobalTableId: 0 |
| #### A masked pattern was here #### |
| NumFilesPerFileSink: 1 |
| table: |
| input format: org.apache.hadoop.mapred.SequenceFileInputFormat |
| output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat |
| properties: |
| column.name.delimiter , |
| columns _col0,_col1,_col2 |
| columns.types struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>,struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>,struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary> |
| escape.delim \ |
| serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe |
| serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe |
| TotalFiles: 1 |
| GatherStats: false |
| MultiFileSpray: false |
| 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 4 |
| bucket_field_name key |
| column.name.delimiter , |
| columns key,value |
| columns.comments |
| columns.types int:string |
| #### A masked pattern was here #### |
| name default.srcbucket_mapjoin_part_2_n16 |
| numFiles 4 |
| numRows 0 |
| partition_columns ds |
| partition_columns.types string |
| rawDataSize 0 |
| serialization.ddl struct srcbucket_mapjoin_part_2_n16 { i32 key, string value} |
| serialization.format 1 |
| serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe |
| totalSize 5812 |
| #### 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: |
| bucket_count 4 |
| bucket_field_name key |
| bucketing_version 2 |
| column.name.delimiter , |
| columns key,value |
| columns.comments |
| columns.types int:string |
| #### A masked pattern was here #### |
| name default.srcbucket_mapjoin_part_2_n16 |
| partition_columns ds |
| partition_columns.types string |
| serialization.ddl struct srcbucket_mapjoin_part_2_n16 { i32 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.srcbucket_mapjoin_part_2_n16 |
| name: default.srcbucket_mapjoin_part_2_n16 |
| #### 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 4 |
| bucket_field_name key |
| column.name.delimiter , |
| columns key,value |
| columns.comments |
| columns.types int:string |
| #### A masked pattern was here #### |
| name default.srcbucket_mapjoin_part_n19 |
| numFiles 4 |
| numRows 0 |
| partition_columns ds |
| partition_columns.types string |
| rawDataSize 0 |
| serialization.ddl struct srcbucket_mapjoin_part_n19 { i32 key, string value} |
| serialization.format 1 |
| serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe |
| totalSize 5812 |
| #### 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: |
| bucket_count 4 |
| bucket_field_name key |
| bucketing_version 2 |
| column.name.delimiter , |
| columns key,value |
| columns.comments |
| columns.types int:string |
| #### A masked pattern was here #### |
| name default.srcbucket_mapjoin_part_n19 |
| partition_columns ds |
| partition_columns.types string |
| serialization.ddl struct srcbucket_mapjoin_part_n19 { i32 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.srcbucket_mapjoin_part_n19 |
| name: default.srcbucket_mapjoin_part_n19 |
| Truncated Path -> Alias: |
| /srcbucket_mapjoin_part_2_n16/ds=2008-04-08 [$hdt$_1:b] |
| |
| Stage: Stage-0 |
| Move Operator |
| tables: |
| replace: true |
| #### A masked pattern was here #### |
| table: |
| input format: org.apache.hadoop.mapred.TextInputFormat |
| output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat |
| properties: |
| COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value1":"true","value2":"true"}} |
| bucket_count -1 |
| bucketing_version 2 |
| column.name.delimiter , |
| columns key,value1,value2 |
| columns.comments |
| columns.types string:string:string |
| #### A masked pattern was here #### |
| name default.bucketmapjoin_tmp_result_n9 |
| numFiles 1 |
| numRows 1028 |
| rawDataSize 19022 |
| serialization.ddl struct bucketmapjoin_tmp_result_n9 { string key, string value1, string value2} |
| serialization.format 1 |
| serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe |
| totalSize 20050 |
| #### A masked pattern was here #### |
| serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe |
| name: default.bucketmapjoin_tmp_result_n9 |
| |
| Stage: Stage-2 |
| Stats Work |
| Basic Stats Work: |
| #### A masked pattern was here #### |
| Column Stats Desc: |
| Columns: key, value1, value2 |
| Column Types: string, string, string |
| Table: default.bucketmapjoin_tmp_result_n9 |
| Is Table Level Stats: true |
| |
| Stage: Stage-3 |
| Map Reduce |
| Map Operator Tree: |
| TableScan |
| GatherStats: false |
| Reduce Output Operator |
| null sort order: |
| sort order: |
| Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE |
| tag: -1 |
| value expressions: _col0 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col2 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>) |
| auto parallelism: false |
| Path -> Alias: |
| #### A masked pattern was here #### |
| Path -> Partition: |
| #### A masked pattern was here #### |
| Partition |
| base file name: -mr-10002 |
| input format: org.apache.hadoop.mapred.SequenceFileInputFormat |
| output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat |
| properties: |
| column.name.delimiter , |
| columns _col0,_col1,_col2 |
| columns.types struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>,struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>,struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary> |
| escape.delim \ |
| serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe |
| serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe |
| |
| input format: org.apache.hadoop.mapred.SequenceFileInputFormat |
| output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat |
| properties: |
| column.name.delimiter , |
| columns _col0,_col1,_col2 |
| columns.types struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>,struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>,struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary> |
| escape.delim \ |
| serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe |
| serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe |
| Truncated Path -> Alias: |
| #### A masked pattern was here #### |
| Needs Tagging: false |
| Reduce Operator Tree: |
| Group By Operator |
| aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2) |
| mode: mergepartial |
| outputColumnNames: _col0, _col1, _col2 |
| Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE |
| File Output Operator |
| compressed: false |
| GlobalTableId: 0 |
| #### A masked pattern was here #### |
| NumFilesPerFileSink: 1 |
| Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE |
| #### A masked pattern was here #### |
| table: |
| input format: org.apache.hadoop.mapred.SequenceFileInputFormat |
| output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat |
| properties: |
| columns _col0,_col1,_col2 |
| columns.types struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>:struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>:struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary> |
| 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 |
| |
| PREHOOK: query: insert overwrite table bucketmapjoin_tmp_result_n9 |
| select a.key, a.value, b.value |
| from srcbucket_mapjoin_part_n19 a join srcbucket_mapjoin_part_2_n16 b |
| on a.key=b.key and b.ds="2008-04-08" |
| PREHOOK: type: QUERY |
| PREHOOK: Input: default@srcbucket_mapjoin_part_2_n16 |
| PREHOOK: Input: default@srcbucket_mapjoin_part_2_n16@ds=2008-04-08 |
| PREHOOK: Input: default@srcbucket_mapjoin_part_n19 |
| PREHOOK: Input: default@srcbucket_mapjoin_part_n19@ds=2008-04-08 |
| PREHOOK: Output: default@bucketmapjoin_tmp_result_n9 |
| POSTHOOK: query: insert overwrite table bucketmapjoin_tmp_result_n9 |
| select a.key, a.value, b.value |
| from srcbucket_mapjoin_part_n19 a join srcbucket_mapjoin_part_2_n16 b |
| on a.key=b.key and b.ds="2008-04-08" |
| POSTHOOK: type: QUERY |
| POSTHOOK: Input: default@srcbucket_mapjoin_part_2_n16 |
| POSTHOOK: Input: default@srcbucket_mapjoin_part_2_n16@ds=2008-04-08 |
| POSTHOOK: Input: default@srcbucket_mapjoin_part_n19 |
| POSTHOOK: Input: default@srcbucket_mapjoin_part_n19@ds=2008-04-08 |
| POSTHOOK: Output: default@bucketmapjoin_tmp_result_n9 |
| POSTHOOK: Lineage: bucketmapjoin_tmp_result_n9.key EXPRESSION [(srcbucket_mapjoin_part_n19)a.FieldSchema(name:key, type:int, comment:null), ] |
| POSTHOOK: Lineage: bucketmapjoin_tmp_result_n9.value1 SIMPLE [(srcbucket_mapjoin_part_n19)a.FieldSchema(name:value, type:string, comment:null), ] |
| POSTHOOK: Lineage: bucketmapjoin_tmp_result_n9.value2 SIMPLE [(srcbucket_mapjoin_part_2_n16)b.FieldSchema(name:value, type:string, comment:null), ] |
| PREHOOK: query: select count(1) from bucketmapjoin_tmp_result_n9 |
| PREHOOK: type: QUERY |
| PREHOOK: Input: default@bucketmapjoin_tmp_result_n9 |
| #### A masked pattern was here #### |
| POSTHOOK: query: select count(1) from bucketmapjoin_tmp_result_n9 |
| POSTHOOK: type: QUERY |
| POSTHOOK: Input: default@bucketmapjoin_tmp_result_n9 |
| #### A masked pattern was here #### |
| 1028 |
| PREHOOK: query: insert overwrite table bucketmapjoin_hash_result_1_n7 |
| select sum(hash(key)), sum(hash(value1)), sum(hash(value2)) from bucketmapjoin_tmp_result_n9 |
| PREHOOK: type: QUERY |
| PREHOOK: Input: default@bucketmapjoin_tmp_result_n9 |
| PREHOOK: Output: default@bucketmapjoin_hash_result_1_n7 |
| POSTHOOK: query: insert overwrite table bucketmapjoin_hash_result_1_n7 |
| select sum(hash(key)), sum(hash(value1)), sum(hash(value2)) from bucketmapjoin_tmp_result_n9 |
| POSTHOOK: type: QUERY |
| POSTHOOK: Input: default@bucketmapjoin_tmp_result_n9 |
| POSTHOOK: Output: default@bucketmapjoin_hash_result_1_n7 |
| POSTHOOK: Lineage: bucketmapjoin_hash_result_1_n7.key EXPRESSION [(bucketmapjoin_tmp_result_n9)bucketmapjoin_tmp_result_n9.FieldSchema(name:key, type:string, comment:null), ] |
| POSTHOOK: Lineage: bucketmapjoin_hash_result_1_n7.value1 EXPRESSION [(bucketmapjoin_tmp_result_n9)bucketmapjoin_tmp_result_n9.FieldSchema(name:value1, type:string, comment:null), ] |
| POSTHOOK: Lineage: bucketmapjoin_hash_result_1_n7.value2 EXPRESSION [(bucketmapjoin_tmp_result_n9)bucketmapjoin_tmp_result_n9.FieldSchema(name:value2, type:string, comment:null), ] |
