http://git-wip-us.apache.org/repos/asf/hive/blob/975a49b6/ql/src/test/results/clientpositive/tez/optimize_nullscan.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/tez/optimize_nullscan.q.out b/ql/src/test/results/clientpositive/tez/optimize_nullscan.q.out deleted file mode 100644 index 561dbb0..0000000 --- a/ql/src/test/results/clientpositive/tez/optimize_nullscan.q.out +++ /dev/null @@ -1,1862 +0,0 @@ -PREHOOK: query: -- SORT_QUERY_RESULTS - --- Disable CBO here, because it messes with the cases specifically crafted for the optimizer. --- Instead, we could improve the optimizer to recognize more cases, e.g. filter before join. - -explain extended -select key from src where false -PREHOOK: type: QUERY -POSTHOOK: query: -- SORT_QUERY_RESULTS - --- Disable CBO here, because it messes with the cases specifically crafted for the optimizer. --- Instead, we could improve the optimizer to recognize more cases, e.g. filter before join. - -explain extended -select key from src where false -POSTHOOK: type: QUERY -STAGE DEPENDENCIES: - Stage-0 is a root stage - -STAGE PLANS: - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - TableScan - alias: src - GatherStats: false - Filter Operator - isSamplingPred: false - predicate: false (type: boolean) - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 - ListSink - -PREHOOK: query: select key from src where false -PREHOOK: type: QUERY -PREHOOK: Input: default@src -#### A masked pattern was here #### -POSTHOOK: query: select key from src where false -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -#### A masked pattern was here #### -PREHOOK: query: explain extended -select count(key) from srcpart where 1=2 group by key -PREHOOK: type: QUERY -POSTHOOK: query: explain extended -select count(key) from srcpart where 1=2 group by key -POSTHOOK: type: QUERY -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Tez -#### A masked pattern was here #### - Edges: - Reducer 2 <- Map 1 (SIMPLE_EDGE) -#### A masked pattern was here #### - Vertices: - Map 1 - Map Operator Tree: - TableScan - alias: srcpart - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - GatherStats: false - Filter Operator - isSamplingPred: false - predicate: false (type: boolean) - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count(key) - keys: key (type: string) - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 8 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: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - tag: -1 - value expressions: _col1 (type: bigint) - auto parallelism: true - Reducer 2 - Needs Tagging: false - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0) - keys: KEY._col0 (type: string) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col1 (type: bigint) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 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: 8 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 - columns.types bigint - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.escape.crlf true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: select count(key) from srcpart where 1=2 group by key -PREHOOK: type: QUERY -PREHOOK: Input: default@srcpart -#### A masked pattern was here #### -POSTHOOK: query: select count(key) from srcpart where 1=2 group by key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@srcpart -#### A masked pattern was here #### -PREHOOK: query: explain extended -select * from (select key from src where false) a left outer join (select key from srcpart limit 0) b on a.key=b.key -PREHOOK: type: QUERY -POSTHOOK: query: explain extended -select * from (select key from src where false) a left outer join (select key from srcpart limit 0) b on a.key=b.key -POSTHOOK: type: QUERY -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Tez -#### A masked pattern was here #### - Edges: - Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 4 (SIMPLE_EDGE) - Reducer 4 <- Map 3 (SIMPLE_EDGE) -#### A masked pattern was here #### - Vertices: - Map 1 - Map Operator Tree: - TableScan - alias: src - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - GatherStats: false - Filter Operator - isSamplingPred: false - predicate: false (type: boolean) - Statistics: Num rows: 1 Data size: 87 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 87 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: a - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 87 Basic stats: COMPLETE Column stats: COMPLETE - tag: 0 - auto parallelism: true - Path -> Alias: - nullscan://null/default.src/part_ [src] - Path -> Partition: - nullscan://null/default.src/part_ - Partition - input format: org.apache.hadoop.hive.ql.io.OneNullRowInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.src - numFiles 1 - numRows 500 - rawDataSize 5312 - serialization.ddl struct src { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.NullStructSerDe - totalSize 5812 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.NullStructSerDe - - 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","value":"true"}} - bucket_count -1 - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.src - numFiles 1 - numRows 500 - rawDataSize 5312 - serialization.ddl struct src { string 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 - name: default.src - name: default.src - Truncated Path -> Alias: - nullscan://null/default.src/part_ [src] - Map 3 - Map Operator Tree: - TableScan - alias: srcpart - Statistics: Num rows: 2000 Data size: 174000 Basic stats: COMPLETE Column stats: COMPLETE - GatherStats: false - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 2000 Data size: 174000 Basic stats: COMPLETE Column stats: COMPLETE - Limit - Number of rows: 0 - Statistics: Num rows: 1 Data size: 87 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 87 Basic stats: COMPLETE Column stats: COMPLETE - tag: -1 - value expressions: _col0 (type: string) - auto parallelism: false - Path -> Alias: - nullscan://null/default.srcpart/part_ds=2008-04-08_hr=11_ [srcpart] - nullscan://null/default.srcpart/part_ds=2008-04-08_hr=12_ [srcpart] - nullscan://null/default.srcpart/part_ds=2008-04-09_hr=11_ [srcpart] - nullscan://null/default.srcpart/part_ds=2008-04-09_hr=12_ [srcpart] - Path -> Partition: - nullscan://null/default.srcpart/part_ds=2008-04-08_hr=11_ - Partition - input format: org.apache.hadoop.hive.ql.io.OneNullRowInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - partition values: - ds 2008-04-08 - hr 11 - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.srcpart - numFiles 1 - numRows 500 - partition_columns ds/hr - partition_columns.types string:string - rawDataSize 5312 - serialization.ddl struct srcpart { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.NullStructSerDe - totalSize 5812 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.NullStructSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.srcpart - partition_columns ds/hr - partition_columns.types string:string - serialization.ddl struct srcpart { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.srcpart - name: default.srcpart - nullscan://null/default.srcpart/part_ds=2008-04-08_hr=12_ - Partition - input format: org.apache.hadoop.hive.ql.io.OneNullRowInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - partition values: - ds 2008-04-08 - hr 12 - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.srcpart - numFiles 1 - numRows 500 - partition_columns ds/hr - partition_columns.types string:string - rawDataSize 5312 - serialization.ddl struct srcpart { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.NullStructSerDe - totalSize 5812 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.NullStructSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.srcpart - partition_columns ds/hr - partition_columns.types string:string - serialization.ddl struct srcpart { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.srcpart - name: default.srcpart - nullscan://null/default.srcpart/part_ds=2008-04-09_hr=11_ - Partition - input format: org.apache.hadoop.hive.ql.io.OneNullRowInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - partition values: - ds 2008-04-09 - hr 11 - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.srcpart - numFiles 1 - numRows 500 - partition_columns ds/hr - partition_columns.types string:string - rawDataSize 5312 - serialization.ddl struct srcpart { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.NullStructSerDe - totalSize 5812 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.NullStructSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.srcpart - partition_columns ds/hr - partition_columns.types string:string - serialization.ddl struct srcpart { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.srcpart - name: default.srcpart - nullscan://null/default.srcpart/part_ds=2008-04-09_hr=12_ - Partition - input format: org.apache.hadoop.hive.ql.io.OneNullRowInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - partition values: - ds 2008-04-09 - hr 12 - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.srcpart - numFiles 1 - numRows 500 - partition_columns ds/hr - partition_columns.types string:string - rawDataSize 5312 - serialization.ddl struct srcpart { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.NullStructSerDe - totalSize 5812 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.NullStructSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.srcpart - partition_columns ds/hr - partition_columns.types string:string - serialization.ddl struct srcpart { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.srcpart - name: default.srcpart - Truncated Path -> Alias: - nullscan://null/default.srcpart/part_ds=2008-04-08_hr=11_ [srcpart] - nullscan://null/default.srcpart/part_ds=2008-04-08_hr=12_ [srcpart] - nullscan://null/default.srcpart/part_ds=2008-04-09_hr=11_ [srcpart] - nullscan://null/default.srcpart/part_ds=2008-04-09_hr=12_ [srcpart] - Reducer 2 - Needs Tagging: false - Reduce Operator Tree: - Merge Join Operator - condition map: - Left Outer Join0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1 - Position of Big Table: 0 - Statistics: Num rows: 1 Data size: 174 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - Statistics: Num rows: 1 Data size: 174 Basic stats: COMPLETE Column stats: COMPLETE -#### 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 string: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 - Reducer 4 - Needs Tagging: false - Reduce Operator Tree: - Select Operator - expressions: VALUE._col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 87 Basic stats: COMPLETE Column stats: COMPLETE - Limit - Number of rows: 0 - Statistics: Num rows: 1 Data size: 87 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: a - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 87 Basic stats: COMPLETE Column stats: COMPLETE - tag: 1 - auto parallelism: true - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: select * from (select key from src where false) a left outer join (select key from srcpart limit 0) b on a.key=b.key -PREHOOK: type: QUERY -PREHOOK: Input: default@src -PREHOOK: Input: default@srcpart -PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 -PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 -PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 -PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 -#### A masked pattern was here #### -POSTHOOK: query: select * from (select key from src where false) a left outer join (select key from srcpart limit 0) b on a.key=b.key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -POSTHOOK: Input: default@srcpart -POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 -POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 -POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 -POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 -#### A masked pattern was here #### -PREHOOK: query: explain extended -select count(key) from src where false union all select count(key) from srcpart -PREHOOK: type: QUERY -POSTHOOK: query: explain extended -select count(key) from src where false union all select count(key) from srcpart -POSTHOOK: type: QUERY -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Tez -#### A masked pattern was here #### - Edges: - Reducer 2 <- Map 1 (SIMPLE_EDGE), Union 3 (CONTAINS) - Reducer 5 <- Map 4 (SIMPLE_EDGE), Union 3 (CONTAINS) -#### A masked pattern was here #### - Vertices: - Map 1 - Map Operator Tree: - TableScan - alias: src - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - GatherStats: false - Filter Operator - isSamplingPred: false - predicate: false (type: boolean) - Statistics: Num rows: 1 Data size: 87 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: count(key) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - tag: -1 - value expressions: _col0 (type: bigint) - auto parallelism: false - Path -> Alias: - nullscan://null/default.src/part_ [src] - Path -> Partition: - nullscan://null/default.src/part_ - Partition - input format: org.apache.hadoop.hive.ql.io.OneNullRowInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.src - numFiles 1 - numRows 500 - rawDataSize 5312 - serialization.ddl struct src { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.NullStructSerDe - totalSize 5812 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.NullStructSerDe - - 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","value":"true"}} - bucket_count -1 - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.src - numFiles 1 - numRows 500 - rawDataSize 5312 - serialization.ddl struct src { string 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 - name: default.src - name: default.src - Truncated Path -> Alias: - nullscan://null/default.src/part_ [src] - Map 4 - Map Operator Tree: - TableScan - alias: srcpart - Statistics: Num rows: 2000 Data size: 174000 Basic stats: COMPLETE Column stats: COMPLETE - GatherStats: false - Select Operator - expressions: key (type: string) - outputColumnNames: key - Statistics: Num rows: 2000 Data size: 174000 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: count(key) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - tag: -1 - value expressions: _col0 (type: bigint) - auto parallelism: false - Path -> Alias: -#### A masked pattern was here #### - Path -> Partition: -#### A masked pattern was here #### - Partition - base file name: hr=11 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - partition values: - ds 2008-04-08 - hr 11 - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.srcpart - numFiles 1 - numRows 500 - partition_columns ds/hr - partition_columns.types string:string - rawDataSize 5312 - serialization.ddl struct srcpart { string 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 -1 - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.srcpart - partition_columns ds/hr - partition_columns.types string:string - serialization.ddl struct srcpart { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.srcpart - name: default.srcpart -#### A masked pattern was here #### - Partition - base file name: hr=12 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - partition values: - ds 2008-04-08 - hr 12 - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.srcpart - numFiles 1 - numRows 500 - partition_columns ds/hr - partition_columns.types string:string - rawDataSize 5312 - serialization.ddl struct srcpart { string 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 -1 - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.srcpart - partition_columns ds/hr - partition_columns.types string:string - serialization.ddl struct srcpart { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.srcpart - name: default.srcpart -#### A masked pattern was here #### - Partition - base file name: hr=11 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - partition values: - ds 2008-04-09 - hr 11 - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.srcpart - numFiles 1 - numRows 500 - partition_columns ds/hr - partition_columns.types string:string - rawDataSize 5312 - serialization.ddl struct srcpart { string 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 -1 - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.srcpart - partition_columns ds/hr - partition_columns.types string:string - serialization.ddl struct srcpart { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.srcpart - name: default.srcpart -#### A masked pattern was here #### - Partition - base file name: hr=12 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - partition values: - ds 2008-04-09 - hr 12 - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.srcpart - numFiles 1 - numRows 500 - partition_columns ds/hr - partition_columns.types string:string - rawDataSize 5312 - serialization.ddl struct srcpart { string 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 -1 - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.srcpart - partition_columns ds/hr - partition_columns.types string:string - serialization.ddl struct srcpart { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.srcpart - name: default.srcpart - Truncated Path -> Alias: - /srcpart/ds=2008-04-08/hr=11 [srcpart] - /srcpart/ds=2008-04-08/hr=12 [srcpart] - /srcpart/ds=2008-04-09/hr=11 [srcpart] - /srcpart/ds=2008-04-09/hr=12 [srcpart] - Reducer 2 - Needs Tagging: false - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0) - mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - columns _col0 - columns.types bigint - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.escape.crlf true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false - Reducer 5 - Needs Tagging: false - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0) - mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - columns _col0 - columns.types bigint - escape.delim \ - hive.serialization.extend.additional.nesting.levels true - serialization.escape.crlf true - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false - Union 3 - Vertex: Union 3 - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: select count(key) from src where false union all select count(key) from srcpart -PREHOOK: type: QUERY -PREHOOK: Input: default@src -PREHOOK: Input: default@srcpart -PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 -PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 -PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 -PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 -#### A masked pattern was here #### -POSTHOOK: query: select count(key) from src where false union all select count(key) from srcpart -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -POSTHOOK: Input: default@srcpart -POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 -POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 -POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 -POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 -#### A masked pattern was here #### -0 -2000 -Warning: Shuffle Join MERGEJOIN[15][tables = [a, b]] in Stage 'Reducer 2' is a cross product -PREHOOK: query: explain extended -select * from (select key from src where false) a left outer join (select value from srcpart limit 0) b -PREHOOK: type: QUERY -POSTHOOK: query: explain extended -select * from (select key from src where false) a left outer join (select value from srcpart limit 0) b -POSTHOOK: type: QUERY -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Tez -#### A masked pattern was here #### - Edges: - Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 4 (SIMPLE_EDGE) - Reducer 4 <- Map 3 (SIMPLE_EDGE) -#### A masked pattern was here #### - Vertices: - Map 1 - Map Operator Tree: - TableScan - alias: src - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - GatherStats: false - Filter Operator - isSamplingPred: false - predicate: false (type: boolean) - Statistics: Num rows: 1 Data size: 87 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 87 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 87 Basic stats: COMPLETE Column stats: COMPLETE - tag: 0 - value expressions: _col0 (type: string) - auto parallelism: false - Path -> Alias: - nullscan://null/default.src/part_ [src] - Path -> Partition: - nullscan://null/default.src/part_ - Partition - input format: org.apache.hadoop.hive.ql.io.OneNullRowInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.src - numFiles 1 - numRows 500 - rawDataSize 5312 - serialization.ddl struct src { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.NullStructSerDe - totalSize 5812 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.NullStructSerDe - - 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","value":"true"}} - bucket_count -1 - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.src - numFiles 1 - numRows 500 - rawDataSize 5312 - serialization.ddl struct src { string 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 - name: default.src - name: default.src - Truncated Path -> Alias: - nullscan://null/default.src/part_ [src] - Map 3 - Map Operator Tree: - TableScan - alias: srcpart - Statistics: Num rows: 2000 Data size: 182000 Basic stats: COMPLETE Column stats: COMPLETE - GatherStats: false - Select Operator - expressions: value (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 2000 Data size: 182000 Basic stats: COMPLETE Column stats: COMPLETE - Limit - Number of rows: 0 - Statistics: Num rows: 1 Data size: 91 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 91 Basic stats: COMPLETE Column stats: COMPLETE - tag: -1 - value expressions: _col0 (type: string) - auto parallelism: false - Path -> Alias: - nullscan://null/default.srcpart/part_ds=2008-04-08_hr=11_ [srcpart] - nullscan://null/default.srcpart/part_ds=2008-04-08_hr=12_ [srcpart] - nullscan://null/default.srcpart/part_ds=2008-04-09_hr=11_ [srcpart] - nullscan://null/default.srcpart/part_ds=2008-04-09_hr=12_ [srcpart] - Path -> Partition: - nullscan://null/default.srcpart/part_ds=2008-04-08_hr=11_ - Partition - input format: org.apache.hadoop.hive.ql.io.OneNullRowInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - partition values: - ds 2008-04-08 - hr 11 - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.srcpart - numFiles 1 - numRows 500 - partition_columns ds/hr - partition_columns.types string:string - rawDataSize 5312 - serialization.ddl struct srcpart { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.NullStructSerDe - totalSize 5812 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.NullStructSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.srcpart - partition_columns ds/hr - partition_columns.types string:string - serialization.ddl struct srcpart { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.srcpart - name: default.srcpart - nullscan://null/default.srcpart/part_ds=2008-04-08_hr=12_ - Partition - input format: org.apache.hadoop.hive.ql.io.OneNullRowInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - partition values: - ds 2008-04-08 - hr 12 - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.srcpart - numFiles 1 - numRows 500 - partition_columns ds/hr - partition_columns.types string:string - rawDataSize 5312 - serialization.ddl struct srcpart { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.NullStructSerDe - totalSize 5812 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.NullStructSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.srcpart - partition_columns ds/hr - partition_columns.types string:string - serialization.ddl struct srcpart { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.srcpart - name: default.srcpart - nullscan://null/default.srcpart/part_ds=2008-04-09_hr=11_ - Partition - input format: org.apache.hadoop.hive.ql.io.OneNullRowInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - partition values: - ds 2008-04-09 - hr 11 - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.srcpart - numFiles 1 - numRows 500 - partition_columns ds/hr - partition_columns.types string:string - rawDataSize 5312 - serialization.ddl struct srcpart { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.NullStructSerDe - totalSize 5812 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.NullStructSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.srcpart - partition_columns ds/hr - partition_columns.types string:string - serialization.ddl struct srcpart { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.srcpart - name: default.srcpart - nullscan://null/default.srcpart/part_ds=2008-04-09_hr=12_ - Partition - input format: org.apache.hadoop.hive.ql.io.OneNullRowInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - partition values: - ds 2008-04-09 - hr 12 - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.srcpart - numFiles 1 - numRows 500 - partition_columns ds/hr - partition_columns.types string:string - rawDataSize 5312 - serialization.ddl struct srcpart { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.NullStructSerDe - totalSize 5812 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.NullStructSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - bucket_count -1 - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.srcpart - partition_columns ds/hr - partition_columns.types string:string - serialization.ddl struct srcpart { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.srcpart - name: default.srcpart - Truncated Path -> Alias: - nullscan://null/default.srcpart/part_ds=2008-04-08_hr=11_ [srcpart] - nullscan://null/default.srcpart/part_ds=2008-04-08_hr=12_ [srcpart] - nullscan://null/default.srcpart/part_ds=2008-04-09_hr=11_ [srcpart] - nullscan://null/default.srcpart/part_ds=2008-04-09_hr=12_ [srcpart] - Reducer 2 - Needs Tagging: false - Reduce Operator Tree: - Merge Join Operator - condition map: - Left Outer Join0 to 1 - keys: - 0 - 1 - outputColumnNames: _col0, _col1 - Position of Big Table: 0 - Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE -#### 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 string: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 - Reducer 4 - Needs Tagging: false - Reduce Operator Tree: - Select Operator - expressions: VALUE._col0 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 91 Basic stats: COMPLETE Column stats: COMPLETE - Limit - Number of rows: 0 - Statistics: Num rows: 1 Data size: 91 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 91 Basic stats: COMPLETE Column stats: COMPLETE - tag: 1 - value expressions: _col0 (type: string) - auto parallelism: false - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -Warning: Shuffle Join MERGEJOIN[15][tables = [a, b]] in Stage 'Reducer 2' is a cross product -PREHOOK: query: select * from (select key from src where false) a left outer join (select value from srcpart limit 0) b -PREHOOK: type: QUERY -PREHOOK: Input: default@src -PREHOOK: Input: default@srcpart -PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 -PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 -PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 -PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 -#### A masked pattern was here #### -POSTHOOK: query: select * from (select key from src where false) a left outer join (select value from srcpart limit 0) b -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -POSTHOOK: Input: default@srcpart -POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 -POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 -POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 -POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 -#### A masked pattern was here #### -PREHOOK: query: explain extended -select * from (select key from src union all select src.key from src left outer join srcpart on src.key = srcpart.key) a where false -PREHOOK: type: QUERY -POSTHOOK: query: explain extended -select * from (select key from src union all select src.key from src left outer join srcpart on src.key = srcpart.key) a where false -POSTHOOK: type: QUERY -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Tez -#### A masked pattern was here #### - Edges: - Map 1 <- Union 2 (CONTAINS) - Reducer 4 <- Map 3 (SIMPLE_EDGE), Map 5 (SIMPLE_EDGE), Union 2 (CONTAINS) -#### A masked pattern was here #### - Vertices: - Map 1 - Map Operator Tree: - TableScan - alias: src - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - GatherStats: false - Filter Operator - isSamplingPred: false - predicate: false (type: boolean) - Statistics: Num rows: 1 Data size: 87 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 87 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - Statistics: Num rows: 2 Data size: 182 Basic stats: COMPLETE Column stats: PARTIAL -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - columns _col0 - columns.types 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 - Path -> Alias: -#### A masked pattern was here #### - Path -> Partition: -#### A masked pattern was here #### - Partition - base file name: src - 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","value":"true"}} - bucket_count -1 - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.src - numFiles 1 - numRows 500 - rawDataSize 5312 - serialization.ddl struct src { string 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: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.src - numFiles 1 - numRows 500 - rawDataSize 5312 - serialization.ddl struct src { string 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 - name: default.src - name: default.src - Truncated Path -> Alias: - /src [src] - Map 3 - Map Operator Tree: - TableScan - alias: src - Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE - GatherStats: false - Filter Operator - isSamplingPred: false - predicate: false (type: boolean) - Statistics: Num rows: 1 Data size: 87 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: key (type: string) - null sort order: a - sort order: + - Map-reduce partition columns: key (type: string) - Statistics: Num rows: 1 Data size: 87 Basic stats: COMPLETE Column stats: COMPLETE - tag: 0 - auto parallelism: true - Path -> Alias: - nullscan://null/default.src/part_ [src] - Path -> Partition: - nullscan://null/default.src/part_ - Partition - input format: org.apache.hadoop.hive.ql.io.OneNullRowInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.src - numFiles 1 - numRows 500 - rawDataSize 5312 - serialization.ddl struct src { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.NullStructSerDe - totalSize 5812 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.NullStructSerDe - - 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","value":"true"}} - bucket_count -1 - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.src - numFiles 1 - numRows 500 - rawDataSize 5312 - serialization.ddl struct src { string 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 - name: default.src - name: default.src - Truncated Path -> Alias: - nullscan://null/default.src/part_ [src] - Map 5 - Map Operator Tree: - TableScan - alias: srcpart - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - GatherStats: false - Filter Operator - isSamplingPred: false - predicate: false (type: boolean) - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: key (type: string) - null sort order: a - sort order: + - Map-reduce partition columns: key (type: string) - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - tag: 1 - auto parallelism: true - Reducer 4 - Needs Tagging: false - Reduce Operator Tree: - Merge Join Operator - condition map: - Left Outer Join0 to 1 - keys: - 0 key (type: string) - 1 key (type: string) - outputColumnNames: _col0 - Position of Big Table: 0 - Statistics: Num rows: 1 Data size: 95 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - Statistics: Num rows: 2 Data size: 182 Basic stats: COMPLETE Column stats: PARTIAL -#### A masked pattern was here #### - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - columns _col0 - columns.types 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 - Union 2 - Vertex: Union 2 - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: select * from (select key from src union all select src.key from src left outer join srcpart on src.key = srcpart.key) a where false -PREHOOK: type: QUERY -PREHOOK: Input: default@src -PREHOOK: Input: default@srcpart -#### A masked pattern was here #### -POSTHOOK: query: select * from (select key from src union all select src.key from src left outer join srcpart on src.key = srcpart.key) a where false -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -POSTHOOK: Input: default@srcpart -#### A masked pattern was here #### -PREHOOK: query: explain extended -select * from src s1, src s2 where false and s1.value = s2.value -PREHOOK: type: QUERY -POSTHOOK: query: explain extended -select * from src s1, src s2 where false and s1.value = s2.value -POSTHOOK: type: QUERY -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Tez -#### A masked pattern was here #### - Edges: - Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 3 (SIMPLE_EDGE) -#### A masked pattern was here #### - Vertices: - Map 1 - Map Operator Tree: - TableScan - alias: s1 - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - GatherStats: false - Filter Operator - isSamplingPred: false - predicate: false (type: boolean) - Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: value (type: string) - null sort order: a - sort order: + - Map-reduce partition columns: value (type: string) - Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE - tag: 0 - value expressions: key (type: string) - auto parallelism: true - Path -> Alias: - nullscan://null/default.src/part_ [s1] - Path -> Partition: - nullscan://null/default.src/part_ - Partition - input format: org.apache.hadoop.hive.ql.io.OneNullRowInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.src - numFiles 1 - numRows 500 - rawDataSize 5312 - serialization.ddl struct src { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.NullStructSerDe - totalSize 5812 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.NullStructSerDe - - 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","value":"true"}} - bucket_count -1 - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.src - numFiles 1 - numRows 500 - rawDataSize 5312 - serialization.ddl struct src { string 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 - name: default.src - name: default.src - Truncated Path -> Alias: - nullscan://null/default.src/part_ [s1] - Map 3 - Map Operator Tree: - TableScan - alias: s2 - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE - GatherStats: false - Filter Operator - isSamplingPred: false - predicate: false (type: boolean) - Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: value (type: string) - null sort order: a - sort order: + - Map-reduce partition columns: value (type: string) - Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE - tag: 1 - value expressions: key (type: string) - auto parallelism: true - Path -> Alias: - nullscan://null/default.src/part_ [s2] - Path -> Partition: - nullscan://null/default.src/part_ - Partition - input format: org.apache.hadoop.hive.ql.io.OneNullRowInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.src - numFiles 1 - numRows 500 - rawDataSize 5312 - serialization.ddl struct src { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.NullStructSerDe - totalSize 5812 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.NullStructSerDe - - 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","value":"true"}} - bucket_count -1 - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.src - numFiles 1 - numRows 500 - rawDataSize 5312 - serialization.ddl struct src { string 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 - name: default.src - name: default.src - Truncated Path -> Alias: - nullscan://null/default.src/part_ [s2] - Reducer 2 - Needs Tagging: false - Reduce Operator Tree: - Merge Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 value (type: string) - 1 value (type: string) - outputColumnNames: _col0, _col1, _col5, _col6 - Position of Big Table: 0 - Statistics: Num rows: 1 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 1 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE - File Output Operator - compressed: false - GlobalTableId: 0 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - Statistics: Num rows: 1 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE -#### 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,_col3 - columns.types string:string:string: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 * from src s1, src s2 where false and s1.value = s2.value -PREHOOK: type: QUERY -PREHOOK: Input: default@src -#### A masked pattern was here #### -POSTHOOK: query: select * from src s1, src s2 where false and s1.value = s2.value -POSTHOOK: type: QUERY -POSTHOOK: Input: default@src -#### A masked pattern was here #### -PREHOOK: query: explain extended -select count(1) from src where null = 1 -PREHOOK: type: QUERY -POSTHOOK: query: explain extended -select count(1) from src where null = 1 -POSTHOOK: type: QUERY -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Tez -#### A masked pattern was here #### - Edges: - Reducer 2 <- Map 1 (SIMPLE_EDGE) -#### A masked pattern was here #### - Vertices: - Map 1 - Map Operator Tree: - TableScan - alias: src - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE - GatherStats: false - Filter Operator - isSamplingPred: false - predicate: false (type: boolean) - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Group By Operator - aggregations: count(1) - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - null sort order: - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE - tag: -1 - value expressions: _col0 (type: bigint) - auto parallelism: false - Path -> Alias: - nullscan://null/default.src/part_ [src] - Path -> Partition: - nullscan://null/default.src/part_ - Partition - input format: org.apache.hadoop.hive.ql.io.OneNullRowInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}} - bucket_count -1 - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.src - numFiles 1 - numRows 500 - rawDataSize 5312 - serialization.ddl struct src { string key, string value} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.NullStructSerDe - totalSize 5812 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.NullStructSerDe - - 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","value":"true"}} - bucket_count -1 - columns key,value - columns.comments 'default','default' - columns.types string:string -#### A masked pattern was here #### - name default.src - numFiles 1 - numRows 500 - rawDataSize 5312 - serialization.ddl struct src { string 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.ser
<TRUNCATED>
