| PREHOOK: query: CREATE TABLE filter_join_breaktask(key int, value string) partitioned by (ds string) |
| PREHOOK: type: CREATETABLE |
| PREHOOK: Output: database:default |
| PREHOOK: Output: default@filter_join_breaktask |
| POSTHOOK: query: CREATE TABLE filter_join_breaktask(key int, value string) partitioned by (ds string) |
| POSTHOOK: type: CREATETABLE |
| POSTHOOK: Output: database:default |
| POSTHOOK: Output: default@filter_join_breaktask |
| PREHOOK: query: INSERT OVERWRITE TABLE filter_join_breaktask PARTITION(ds='2008-04-08') |
| SELECT key, value from src1 |
| PREHOOK: type: QUERY |
| PREHOOK: Input: default@src1 |
| PREHOOK: Output: default@filter_join_breaktask@ds=2008-04-08 |
| POSTHOOK: query: INSERT OVERWRITE TABLE filter_join_breaktask PARTITION(ds='2008-04-08') |
| SELECT key, value from src1 |
| POSTHOOK: type: QUERY |
| POSTHOOK: Input: default@src1 |
| POSTHOOK: Output: default@filter_join_breaktask@ds=2008-04-08 |
| POSTHOOK: Lineage: filter_join_breaktask PARTITION(ds=2008-04-08).key EXPRESSION [(src1)src1.FieldSchema(name:key, type:string, comment:default), ] |
| POSTHOOK: Lineage: filter_join_breaktask PARTITION(ds=2008-04-08).value SIMPLE [(src1)src1.FieldSchema(name:value, type:string, comment:default), ] |
| PREHOOK: query: EXPLAIN EXTENDED |
| SELECT f.key, g.value |
| FROM filter_join_breaktask f JOIN filter_join_breaktask m ON( f.key = m.key AND f.ds='2008-04-08' AND m.ds='2008-04-08' AND f.key is not null) |
| JOIN filter_join_breaktask g ON(g.value = m.value AND g.ds='2008-04-08' AND m.ds='2008-04-08' AND m.value is not null AND m.value !='') |
| PREHOOK: type: QUERY |
| POSTHOOK: query: EXPLAIN EXTENDED |
| SELECT f.key, g.value |
| FROM filter_join_breaktask f JOIN filter_join_breaktask m ON( f.key = m.key AND f.ds='2008-04-08' AND m.ds='2008-04-08' AND f.key is not null) |
| JOIN filter_join_breaktask g ON(g.value = m.value AND g.ds='2008-04-08' AND m.ds='2008-04-08' AND m.value is not null AND m.value !='') |
| POSTHOOK: type: QUERY |
| STAGE DEPENDENCIES: |
| Stage-1 is a root stage |
| Stage-2 depends on stages: Stage-1 |
| Stage-0 depends on stages: Stage-2 |
| |
| STAGE PLANS: |
| Stage: Stage-1 |
| Map Reduce |
| Map Operator Tree: |
| TableScan |
| alias: f |
| Statistics: Num rows: 25 Data size: 211 Basic stats: COMPLETE Column stats: NONE |
| GatherStats: false |
| Filter Operator |
| isSamplingPred: false |
| predicate: key is not null (type: boolean) |
| Statistics: Num rows: 25 Data size: 211 Basic stats: COMPLETE Column stats: NONE |
| Select Operator |
| expressions: key (type: int) |
| outputColumnNames: _col0 |
| Statistics: Num rows: 25 Data size: 211 Basic stats: COMPLETE Column stats: NONE |
| Reduce Output Operator |
| key expressions: _col0 (type: int) |
| null sort order: a |
| sort order: + |
| Map-reduce partition columns: _col0 (type: int) |
| Statistics: Num rows: 25 Data size: 211 Basic stats: COMPLETE Column stats: NONE |
| tag: 0 |
| auto parallelism: false |
| TableScan |
| alias: m |
| Statistics: Num rows: 25 Data size: 211 Basic stats: COMPLETE Column stats: NONE |
| GatherStats: false |
| Filter Operator |
| isSamplingPred: false |
| predicate: ((value <> '') and key is not null) (type: boolean) |
| Statistics: Num rows: 25 Data size: 211 Basic stats: COMPLETE Column stats: NONE |
| Select Operator |
| expressions: key (type: int), value (type: string) |
| outputColumnNames: _col0, _col1 |
| Statistics: Num rows: 25 Data size: 211 Basic stats: COMPLETE Column stats: NONE |
| Reduce Output Operator |
| key expressions: _col0 (type: int) |
| null sort order: a |
| sort order: + |
| Map-reduce partition columns: _col0 (type: int) |
| Statistics: Num rows: 25 Data size: 211 Basic stats: COMPLETE Column stats: NONE |
| tag: 1 |
| value expressions: _col1 (type: string) |
| auto parallelism: false |
| Path -> Alias: |
| #### A masked pattern was here #### |
| Path -> Partition: |
| #### A masked pattern was here #### |
| Partition |
| base file name: ds=2008-04-08 |
| input format: org.apache.hadoop.mapred.TextInputFormat |
| output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat |
| partition values: |
| ds 2008-04-08 |
| properties: |
| COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} |
| bucket_count -1 |
| column.name.delimiter , |
| columns key,value |
| columns.comments |
| columns.types int:string |
| #### A masked pattern was here #### |
| name default.filter_join_breaktask |
| numFiles 1 |
| numRows 25 |
| partition_columns ds |
| partition_columns.types string |
| rawDataSize 211 |
| serialization.ddl struct filter_join_breaktask { i32 key, string value} |
| serialization.format 1 |
| serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe |
| totalSize 236 |
| #### 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 -1 |
| bucketing_version 2 |
| column.name.delimiter , |
| columns key,value |
| columns.comments |
| columns.types int:string |
| #### A masked pattern was here #### |
| name default.filter_join_breaktask |
| partition_columns ds |
| partition_columns.types string |
| serialization.ddl struct filter_join_breaktask { 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.filter_join_breaktask |
| name: default.filter_join_breaktask |
| Truncated Path -> Alias: |
| /filter_join_breaktask/ds=2008-04-08 [$hdt$_1:f, $hdt$_2:m] |
| Needs Tagging: true |
| Reduce Operator Tree: |
| Join Operator |
| condition map: |
| Inner Join 0 to 1 |
| keys: |
| 0 _col0 (type: int) |
| 1 _col0 (type: int) |
| outputColumnNames: _col0, _col3 |
| Statistics: Num rows: 27 Data size: 232 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,_col3 |
| columns.types int,string |
| 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 |
| |
| Stage: Stage-2 |
| Map Reduce |
| Map Operator Tree: |
| TableScan |
| GatherStats: false |
| Reduce Output Operator |
| key expressions: _col3 (type: string) |
| null sort order: a |
| sort order: + |
| Map-reduce partition columns: _col3 (type: string) |
| Statistics: Num rows: 27 Data size: 232 Basic stats: COMPLETE Column stats: NONE |
| tag: 0 |
| value expressions: _col0 (type: int) |
| auto parallelism: false |
| TableScan |
| alias: g |
| Statistics: Num rows: 25 Data size: 211 Basic stats: COMPLETE Column stats: NONE |
| GatherStats: false |
| Filter Operator |
| isSamplingPred: false |
| predicate: (value <> '') (type: boolean) |
| Statistics: Num rows: 25 Data size: 211 Basic stats: COMPLETE Column stats: NONE |
| Select Operator |
| expressions: value (type: string) |
| outputColumnNames: _col0 |
| Statistics: Num rows: 25 Data size: 211 Basic stats: COMPLETE Column stats: NONE |
| Reduce Output Operator |
| key expressions: _col0 (type: string) |
| null sort order: a |
| sort order: + |
| Map-reduce partition columns: _col0 (type: string) |
| Statistics: Num rows: 25 Data size: 211 Basic stats: COMPLETE Column stats: NONE |
| tag: 1 |
| auto parallelism: false |
| Path -> Alias: |
| #### A masked pattern was here #### |
| Path -> Partition: |
| #### A masked pattern was here #### |
| Partition |
| base file name: -mr-10004 |
| input format: org.apache.hadoop.mapred.SequenceFileInputFormat |
| output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat |
| properties: |
| column.name.delimiter , |
| columns _col0,_col3 |
| columns.types int,string |
| 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,_col3 |
| columns.types int,string |
| escape.delim \ |
| serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe |
| serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe |
| #### 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: |
| COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} |
| bucket_count -1 |
| column.name.delimiter , |
| columns key,value |
| columns.comments |
| columns.types int:string |
| #### A masked pattern was here #### |
| name default.filter_join_breaktask |
| numFiles 1 |
| numRows 25 |
| partition_columns ds |
| partition_columns.types string |
| rawDataSize 211 |
| serialization.ddl struct filter_join_breaktask { i32 key, string value} |
| serialization.format 1 |
| serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe |
| totalSize 236 |
| #### 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 -1 |
| bucketing_version 2 |
| column.name.delimiter , |
| columns key,value |
| columns.comments |
| columns.types int:string |
| #### A masked pattern was here #### |
| name default.filter_join_breaktask |
| partition_columns ds |
| partition_columns.types string |
| serialization.ddl struct filter_join_breaktask { 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.filter_join_breaktask |
| name: default.filter_join_breaktask |
| Truncated Path -> Alias: |
| /filter_join_breaktask/ds=2008-04-08 [$hdt$_0:g] |
| #### A masked pattern was here #### |
| Needs Tagging: true |
| Reduce Operator Tree: |
| Join Operator |
| condition map: |
| Inner Join 0 to 1 |
| keys: |
| 0 _col3 (type: string) |
| 1 _col0 (type: string) |
| outputColumnNames: _col0, _col5 |
| Statistics: Num rows: 29 Data size: 255 Basic stats: COMPLETE Column stats: NONE |
| Select Operator |
| expressions: _col0 (type: int), _col5 (type: string) |
| outputColumnNames: _col0, _col1 |
| Statistics: Num rows: 29 Data size: 255 Basic stats: COMPLETE Column stats: NONE |
| File Output Operator |
| compressed: false |
| GlobalTableId: 0 |
| #### A masked pattern was here #### |
| NumFilesPerFileSink: 1 |
| Statistics: Num rows: 29 Data size: 255 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 |
| columns.types int:string |
| escape.delim \ |
| hive.serialization.extend.additional.nesting.levels true |
| serialization.escape.crlf true |
| serialization.format 1 |
| serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe |
| serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe |
| TotalFiles: 1 |
| GatherStats: false |
| MultiFileSpray: false |
| |
| Stage: Stage-0 |
| Fetch Operator |
| limit: -1 |
| Processor Tree: |
| ListSink |
| |
| PREHOOK: query: SELECT f.key, g.value |
| FROM filter_join_breaktask f JOIN filter_join_breaktask m ON( f.key = m.key AND f.ds='2008-04-08' AND m.ds='2008-04-08' AND f.key is not null) |
| JOIN filter_join_breaktask g ON(g.value = m.value AND g.ds='2008-04-08' AND m.ds='2008-04-08' AND m.value is not null AND m.value !='') |
| PREHOOK: type: QUERY |
| PREHOOK: Input: default@filter_join_breaktask |
| PREHOOK: Input: default@filter_join_breaktask@ds=2008-04-08 |
| #### A masked pattern was here #### |
| POSTHOOK: query: SELECT f.key, g.value |
| FROM filter_join_breaktask f JOIN filter_join_breaktask m ON( f.key = m.key AND f.ds='2008-04-08' AND m.ds='2008-04-08' AND f.key is not null) |
| JOIN filter_join_breaktask g ON(g.value = m.value AND g.ds='2008-04-08' AND m.ds='2008-04-08' AND m.value is not null AND m.value !='') |
| POSTHOOK: type: QUERY |
| POSTHOOK: Input: default@filter_join_breaktask |
| POSTHOOK: Input: default@filter_join_breaktask@ds=2008-04-08 |
| #### A masked pattern was here #### |
| 146 val_146 |
| 150 val_150 |
| 213 val_213 |
| 238 val_238 |
| 255 val_255 |
| 273 val_273 |
| 278 val_278 |
| 311 val_311 |
| 401 val_401 |
| 406 val_406 |
| 66 val_66 |
| 98 val_98 |
