Saving all output to "!!{outputDirectory}!!/rand_partitionpruner2.q.raw". Enter "record" with no arguments to stop it. >>> !run !!{qFileDirectory}!!/rand_partitionpruner2.q >>> -- scanning partitioned data >>> >>> create table tmptable(key string, value string, hr string, ds string); No rows affected >>> >>> explain extended insert overwrite table tmptable select a.* from srcpart a where rand(1) < 0.1 and a.ds = '2008-04-08'; 'Explain' 'ABSTRACT SYNTAX TREE:' ' (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME srcpart) a)) (TOK_INSERT (TOK_DESTINATION (TOK_TAB (TOK_TABNAME tmptable))) (TOK_SELECT (TOK_SELEXPR (TOK_ALLCOLREF (TOK_TABNAME a)))) (TOK_WHERE (and (< (TOK_FUNCTION rand 1) 0.1) (= (. (TOK_TABLE_OR_COL a) ds) '2008-04-08')))))' '' 'STAGE DEPENDENCIES:' ' Stage-1 is a root stage' ' Stage-7 depends on stages: Stage-1 , consists of Stage-4, Stage-3, Stage-5' ' Stage-4' ' Stage-0 depends on stages: Stage-4, Stage-3, Stage-6' ' Stage-2 depends on stages: Stage-0' ' Stage-3' ' Stage-5' ' Stage-6 depends on stages: Stage-5' '' 'STAGE PLANS:' ' Stage: Stage-1' ' Map Reduce' ' Alias -> Map Operator Tree:' ' a ' ' TableScan' ' alias: a' ' GatherStats: false' ' Filter Operator' ' isSamplingPred: false' ' predicate:' ' expr: (rand(1) < 0.1)' ' type: boolean' ' Select Operator' ' expressions:' ' expr: key' ' type: string' ' expr: value' ' type: string' ' expr: ds' ' type: string' ' expr: hr' ' type: string' ' outputColumnNames: _col0, _col1, _col2, _col3' ' File Output Operator' ' compressed: false' ' GlobalTableId: 1' ' directory: pfile:!!{hive.exec.scratchdir}!!' ' NumFilesPerFileSink: 1' ' Stats Publishing Key Prefix: pfile:!!{hive.exec.scratchdir}!!' ' table:' ' input format: org.apache.hadoop.mapred.TextInputFormat' ' output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat' ' properties:' ' bucket_count -1' ' columns key,value,hr,ds' ' columns.types string:string:string:string' ' file.inputformat org.apache.hadoop.mapred.TextInputFormat' ' file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat' ' location !!{hive.metastore.warehouse.dir}!!/rand_partitionpruner2.db/tmptable' ' name rand_partitionpruner2.tmptable' ' serialization.ddl struct tmptable { string key, string value, string hr, string ds}' ' serialization.format 1' ' serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe' ' transient_lastDdlTime !!UNIXTIME!!' ' serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe' ' name: rand_partitionpruner2.tmptable' ' TotalFiles: 1' ' GatherStats: true' ' MultiFileSpray: false' ' Needs Tagging: false' ' Path -> Alias:' ' !!{hive.metastore.warehouse.dir}!!/rand_partitionpruner2.db/srcpart/ds=2008-04-08/hr=11 [a]' ' !!{hive.metastore.warehouse.dir}!!/rand_partitionpruner2.db/srcpart/ds=2008-04-08/hr=12 [a]' ' Path -> Partition:' ' !!{hive.metastore.warehouse.dir}!!/rand_partitionpruner2.db/srcpart/ds=2008-04-08/hr=11 ' ' 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:' ' bucket_count -1' ' columns key,value' ' columns.types string:string' ' file.inputformat org.apache.hadoop.mapred.TextInputFormat' ' file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat' ' location !!{hive.metastore.warehouse.dir}!!/rand_partitionpruner2.db/srcpart/ds=2008-04-08/hr=11' ' name rand_partitionpruner2.srcpart' ' numFiles 1' ' numPartitions 4' ' numRows 0' ' partition_columns ds/hr' ' rawDataSize 0' ' serialization.ddl struct srcpart { string key, string value}' ' serialization.format 1' ' serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe' ' totalSize 5812' ' transient_lastDdlTime !!UNIXTIME!!' ' 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.types string:string' ' file.inputformat org.apache.hadoop.mapred.TextInputFormat' ' file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat' ' location !!{hive.metastore.warehouse.dir}!!/rand_partitionpruner2.db/srcpart' ' name rand_partitionpruner2.srcpart' ' numFiles 4' ' numPartitions 4' ' numRows 0' ' partition_columns ds/hr' ' rawDataSize 0' ' serialization.ddl struct srcpart { string key, string value}' ' serialization.format 1' ' serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe' ' totalSize 23248' ' transient_lastDdlTime !!UNIXTIME!!' ' serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe' ' name: rand_partitionpruner2.srcpart' ' name: rand_partitionpruner2.srcpart' ' !!{hive.metastore.warehouse.dir}!!/rand_partitionpruner2.db/srcpart/ds=2008-04-08/hr=12 ' ' 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:' ' bucket_count -1' ' columns key,value' ' columns.types string:string' ' file.inputformat org.apache.hadoop.mapred.TextInputFormat' ' file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat' ' location !!{hive.metastore.warehouse.dir}!!/rand_partitionpruner2.db/srcpart/ds=2008-04-08/hr=12' ' name rand_partitionpruner2.srcpart' ' numFiles 1' ' numPartitions 4' ' numRows 0' ' partition_columns ds/hr' ' rawDataSize 0' ' serialization.ddl struct srcpart { string key, string value}' ' serialization.format 1' ' serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe' ' totalSize 5812' ' transient_lastDdlTime !!UNIXTIME!!' ' 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.types string:string' ' file.inputformat org.apache.hadoop.mapred.TextInputFormat' ' file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat' ' location !!{hive.metastore.warehouse.dir}!!/rand_partitionpruner2.db/srcpart' ' name rand_partitionpruner2.srcpart' ' numFiles 4' ' numPartitions 4' ' numRows 0' ' partition_columns ds/hr' ' rawDataSize 0' ' serialization.ddl struct srcpart { string key, string value}' ' serialization.format 1' ' serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe' ' totalSize 23248' ' transient_lastDdlTime !!UNIXTIME!!' ' serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe' ' name: rand_partitionpruner2.srcpart' ' name: rand_partitionpruner2.srcpart' '' ' Stage: Stage-7' ' Conditional Operator' '' ' Stage: Stage-4' ' Move Operator' ' files:' ' hdfs directory: true' ' source: pfile:!!{hive.exec.scratchdir}!!' ' destination: pfile:!!{hive.exec.scratchdir}!!' '' ' Stage: Stage-0' ' Move Operator' ' tables:' ' replace: true' ' source: pfile:!!{hive.exec.scratchdir}!!' ' table:' ' input format: org.apache.hadoop.mapred.TextInputFormat' ' output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat' ' properties:' ' bucket_count -1' ' columns key,value,hr,ds' ' columns.types string:string:string:string' ' file.inputformat org.apache.hadoop.mapred.TextInputFormat' ' file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat' ' location !!{hive.metastore.warehouse.dir}!!/rand_partitionpruner2.db/tmptable' ' name rand_partitionpruner2.tmptable' ' serialization.ddl struct tmptable { string key, string value, string hr, string ds}' ' serialization.format 1' ' serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe' ' transient_lastDdlTime !!UNIXTIME!!' ' serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe' ' name: rand_partitionpruner2.tmptable' ' tmp directory: pfile:!!{hive.exec.scratchdir}!!' '' ' Stage: Stage-2' ' Stats-Aggr Operator' ' Stats Aggregation Key Prefix: pfile:!!{hive.exec.scratchdir}!!' '' ' Stage: Stage-3' ' Map Reduce' ' Alias -> Map Operator Tree:' ' pfile:!!{hive.exec.scratchdir}!! ' ' File Output Operator' ' compressed: false' ' GlobalTableId: 0' ' directory: pfile:!!{hive.exec.scratchdir}!!' ' NumFilesPerFileSink: 1' ' table:' ' input format: org.apache.hadoop.mapred.TextInputFormat' ' output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat' ' properties:' ' bucket_count -1' ' columns key,value,hr,ds' ' columns.types string:string:string:string' ' file.inputformat org.apache.hadoop.mapred.TextInputFormat' ' file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat' ' location !!{hive.metastore.warehouse.dir}!!/rand_partitionpruner2.db/tmptable' ' name rand_partitionpruner2.tmptable' ' serialization.ddl struct tmptable { string key, string value, string hr, string ds}' ' serialization.format 1' ' serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe' ' transient_lastDdlTime !!UNIXTIME!!' ' serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe' ' name: rand_partitionpruner2.tmptable' ' TotalFiles: 1' ' GatherStats: false' ' MultiFileSpray: false' ' Needs Tagging: false' ' Path -> Alias:' ' pfile:!!{hive.exec.scratchdir}!! [pfile:!!{hive.exec.scratchdir}!!]' ' Path -> Partition:' ' pfile:!!{hive.exec.scratchdir}!! ' ' Partition' ' base file name: -ext-10002' ' input format: org.apache.hadoop.mapred.TextInputFormat' ' output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat' ' properties:' ' bucket_count -1' ' columns key,value,hr,ds' ' columns.types string:string:string:string' ' file.inputformat org.apache.hadoop.mapred.TextInputFormat' ' file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat' ' location !!{hive.metastore.warehouse.dir}!!/rand_partitionpruner2.db/tmptable' ' name rand_partitionpruner2.tmptable' ' serialization.ddl struct tmptable { string key, string value, string hr, string ds}' ' serialization.format 1' ' serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe' ' transient_lastDdlTime !!UNIXTIME!!' ' 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,hr,ds' ' columns.types string:string:string:string' ' file.inputformat org.apache.hadoop.mapred.TextInputFormat' ' file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat' ' location !!{hive.metastore.warehouse.dir}!!/rand_partitionpruner2.db/tmptable' ' name rand_partitionpruner2.tmptable' ' serialization.ddl struct tmptable { string key, string value, string hr, string ds}' ' serialization.format 1' ' serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe' ' transient_lastDdlTime !!UNIXTIME!!' ' serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe' ' name: rand_partitionpruner2.tmptable' ' name: rand_partitionpruner2.tmptable' '' ' Stage: Stage-5' ' Map Reduce' ' Alias -> Map Operator Tree:' ' pfile:!!{hive.exec.scratchdir}!! ' ' File Output Operator' ' compressed: false' ' GlobalTableId: 0' ' directory: pfile:!!{hive.exec.scratchdir}!!' ' NumFilesPerFileSink: 1' ' table:' ' input format: org.apache.hadoop.mapred.TextInputFormat' ' output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat' ' properties:' ' bucket_count -1' ' columns key,value,hr,ds' ' columns.types string:string:string:string' ' file.inputformat org.apache.hadoop.mapred.TextInputFormat' ' file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat' ' location !!{hive.metastore.warehouse.dir}!!/rand_partitionpruner2.db/tmptable' ' name rand_partitionpruner2.tmptable' ' serialization.ddl struct tmptable { string key, string value, string hr, string ds}' ' serialization.format 1' ' serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe' ' transient_lastDdlTime !!UNIXTIME!!' ' serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe' ' name: rand_partitionpruner2.tmptable' ' TotalFiles: 1' ' GatherStats: false' ' MultiFileSpray: false' ' Needs Tagging: false' ' Path -> Alias:' ' pfile:!!{hive.exec.scratchdir}!! [pfile:!!{hive.exec.scratchdir}!!]' ' Path -> Partition:' ' pfile:!!{hive.exec.scratchdir}!! ' ' Partition' ' base file name: -ext-10002' ' input format: org.apache.hadoop.mapred.TextInputFormat' ' output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat' ' properties:' ' bucket_count -1' ' columns key,value,hr,ds' ' columns.types string:string:string:string' ' file.inputformat org.apache.hadoop.mapred.TextInputFormat' ' file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat' ' location !!{hive.metastore.warehouse.dir}!!/rand_partitionpruner2.db/tmptable' ' name rand_partitionpruner2.tmptable' ' serialization.ddl struct tmptable { string key, string value, string hr, string ds}' ' serialization.format 1' ' serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe' ' transient_lastDdlTime !!UNIXTIME!!' ' 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,hr,ds' ' columns.types string:string:string:string' ' file.inputformat org.apache.hadoop.mapred.TextInputFormat' ' file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat' ' location !!{hive.metastore.warehouse.dir}!!/rand_partitionpruner2.db/tmptable' ' name rand_partitionpruner2.tmptable' ' serialization.ddl struct tmptable { string key, string value, string hr, string ds}' ' serialization.format 1' ' serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe' ' transient_lastDdlTime !!UNIXTIME!!' ' serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe' ' name: rand_partitionpruner2.tmptable' ' name: rand_partitionpruner2.tmptable' '' ' Stage: Stage-6' ' Move Operator' ' files:' ' hdfs directory: true' ' source: pfile:!!{hive.exec.scratchdir}!!' ' destination: pfile:!!{hive.exec.scratchdir}!!' '' '' 357 rows selected >>> >>> >>> insert overwrite table tmptable select a.* from srcpart a where rand(1) < 0.1 and a.ds = '2008-04-08'; 'key','value','ds','hr' No rows selected >>> >>> select * from tmptable x sort by x.key,x.value,x.ds,x.hr; 'key','value','hr','ds' '103','val_103','2008-04-08','11' '118','val_118','2008-04-08','12' '119','val_119','2008-04-08','12' '119','val_119','2008-04-08','12' '126','val_126','2008-04-08','12' '131','val_131','2008-04-08','12' '133','val_133','2008-04-08','11' '134','val_134','2008-04-08','11' '138','val_138','2008-04-08','11' '143','val_143','2008-04-08','12' '152','val_152','2008-04-08','11' '153','val_153','2008-04-08','11' '162','val_162','2008-04-08','12' '169','val_169','2008-04-08','11' '170','val_170','2008-04-08','11' '175','val_175','2008-04-08','12' '176','val_176','2008-04-08','11' '176','val_176','2008-04-08','11' '18','val_18','2008-04-08','11' '18','val_18','2008-04-08','12' '191','val_191','2008-04-08','12' '197','val_197','2008-04-08','11' '199','val_199','2008-04-08','11' '200','val_200','2008-04-08','12' '201','val_201','2008-04-08','12' '202','val_202','2008-04-08','11' '203','val_203','2008-04-08','11' '209','val_209','2008-04-08','11' '214','val_214','2008-04-08','12' '217','val_217','2008-04-08','11' '218','val_218','2008-04-08','12' '221','val_221','2008-04-08','11' '223','val_223','2008-04-08','12' '224','val_224','2008-04-08','11' '229','val_229','2008-04-08','12' '230','val_230','2008-04-08','12' '233','val_233','2008-04-08','11' '233','val_233','2008-04-08','12' '237','val_237','2008-04-08','12' '238','val_238','2008-04-08','12' '256','val_256','2008-04-08','12' '26','val_26','2008-04-08','11' '265','val_265','2008-04-08','12' '273','val_273','2008-04-08','12' '277','val_277','2008-04-08','11' '277','val_277','2008-04-08','12' '280','val_280','2008-04-08','12' '286','val_286','2008-04-08','12' '288','val_288','2008-04-08','11' '298','val_298','2008-04-08','11' '309','val_309','2008-04-08','11' '309','val_309','2008-04-08','12' '310','val_310','2008-04-08','11' '317','val_317','2008-04-08','11' '322','val_322','2008-04-08','12' '323','val_323','2008-04-08','12' '325','val_325','2008-04-08','12' '331','val_331','2008-04-08','11' '332','val_332','2008-04-08','12' '336','val_336','2008-04-08','11' '336','val_336','2008-04-08','12' '339','val_339','2008-04-08','12' '341','val_341','2008-04-08','12' '342','val_342','2008-04-08','12' '348','val_348','2008-04-08','11' '348','val_348','2008-04-08','12' '35','val_35','2008-04-08','12' '364','val_364','2008-04-08','12' '37','val_37','2008-04-08','11' '378','val_378','2008-04-08','11' '384','val_384','2008-04-08','11' '389','val_389','2008-04-08','11' '400','val_400','2008-04-08','11' '403','val_403','2008-04-08','12' '407','val_407','2008-04-08','12' '409','val_409','2008-04-08','11' '417','val_417','2008-04-08','12' '42','val_42','2008-04-08','11' '424','val_424','2008-04-08','12' '429','val_429','2008-04-08','11' '429','val_429','2008-04-08','12' '430','val_430','2008-04-08','12' '431','val_431','2008-04-08','11' '432','val_432','2008-04-08','12' '44','val_44','2008-04-08','11' '453','val_453','2008-04-08','11' '454','val_454','2008-04-08','11' '457','val_457','2008-04-08','11' '457','val_457','2008-04-08','12' '458','val_458','2008-04-08','11' '466','val_466','2008-04-08','12' '467','val_467','2008-04-08','11' '469','val_469','2008-04-08','11' '469','val_469','2008-04-08','11' '469','val_469','2008-04-08','11' '47','val_47','2008-04-08','12' '470','val_470','2008-04-08','12' '489','val_489','2008-04-08','11' '491','val_491','2008-04-08','11' '496','val_496','2008-04-08','12' '498','val_498','2008-04-08','11' '498','val_498','2008-04-08','12' '51','val_51','2008-04-08','11' '58','val_58','2008-04-08','12' '70','val_70','2008-04-08','11' '72','val_72','2008-04-08','12' '74','val_74','2008-04-08','11' '77','val_77','2008-04-08','11' '77','val_77','2008-04-08','12' '78','val_78','2008-04-08','11' '82','val_82','2008-04-08','12' '87','val_87','2008-04-08','12' '90','val_90','2008-04-08','12' '97','val_97','2008-04-08','12' '97','val_97','2008-04-08','12' '98','val_98','2008-04-08','12' 116 rows selected >>> >>> !record