PREHOOK: query: CREATE TABLE dest_j1(key STRING, value STRING, val2 STRING) STORED AS TEXTFILE PREHOOK: type: CREATETABLE POSTHOOK: query: CREATE TABLE dest_j1(key STRING, value STRING, val2 STRING) STORED AS TEXTFILE POSTHOOK: type: CREATETABLE POSTHOOK: Output: default@dest_j1 PREHOOK: query: EXPLAIN EXTENDED INSERT OVERWRITE TABLE dest_j1 SELECT /*+ MAPJOIN(x,y) */ x.key, z.value, y.value FROM src1 x JOIN src y ON (x.key = y.key) JOIN srcpart z ON (x.key = z.key) WHERE z.ds='2008-04-08' and z.hr=11 PREHOOK: type: QUERY POSTHOOK: query: EXPLAIN EXTENDED INSERT OVERWRITE TABLE dest_j1 SELECT /*+ MAPJOIN(x,y) */ x.key, z.value, y.value FROM src1 x JOIN src y ON (x.key = y.key) JOIN srcpart z ON (x.key = z.key) WHERE z.ds='2008-04-08' and z.hr=11 POSTHOOK: type: QUERY ABSTRACT SYNTAX TREE: (TOK_QUERY (TOK_FROM (TOK_JOIN (TOK_JOIN (TOK_TABREF (TOK_TABNAME src1) x) (TOK_TABREF (TOK_TABNAME src) y) (= (. (TOK_TABLE_OR_COL x) key) (. (TOK_TABLE_OR_COL y) key))) (TOK_TABREF (TOK_TABNAME srcpart) z) (= (. (TOK_TABLE_OR_COL x) key) (. (TOK_TABLE_OR_COL z) key)))) (TOK_INSERT (TOK_DESTINATION (TOK_TAB (TOK_TABNAME dest_j1))) (TOK_SELECT (TOK_HINTLIST (TOK_HINT TOK_MAPJOIN (TOK_HINTARGLIST x y))) (TOK_SELEXPR (. (TOK_TABLE_OR_COL x) key)) (TOK_SELEXPR (. (TOK_TABLE_OR_COL z) value)) (TOK_SELEXPR (. (TOK_TABLE_OR_COL y) value))) (TOK_WHERE (and (= (. (TOK_TABLE_OR_COL z) ds) '2008-04-08') (= (. (TOK_TABLE_OR_COL z) hr) 11))))) STAGE DEPENDENCIES: Stage-8 is a root stage Stage-1 depends on stages: Stage-8 Stage-5 depends on stages: Stage-1 , consists of Stage-4, Stage-3 Stage-4 Stage-0 depends on stages: Stage-4, Stage-3 Stage-2 depends on stages: Stage-0 Stage-3 STAGE PLANS: Stage: Stage-8 Map Reduce Local Work Alias -> Map Local Tables: x Fetch Operator limit: -1 y Fetch Operator limit: -1 Alias -> Map Local Operator Tree: x TableScan alias: x GatherStats: false HashTable Sink Operator condition expressions: 0 {key} 1 {value} 2 {value} {ds} {hr} handleSkewJoin: false keys: 0 [Column[key]] 1 [Column[key]] 2 [Column[key]] Position of Big Table: 2 y TableScan alias: y GatherStats: false HashTable Sink Operator condition expressions: 0 {key} 1 {value} 2 {value} {ds} {hr} handleSkewJoin: false keys: 0 [Column[key]] 1 [Column[key]] 2 [Column[key]] Position of Big Table: 2 Stage: Stage-1 Map Reduce Alias -> Map Operator Tree: z TableScan alias: z GatherStats: false Map Join Operator condition map: Inner Join 0 to 1 Inner Join 0 to 2 condition expressions: 0 {key} 1 {value} 2 {value} {ds} {hr} handleSkewJoin: false keys: 0 [Column[key]] 1 [Column[key]] 2 [Column[key]] outputColumnNames: _col0, _col5, _col9, _col10, _col11 Position of Big Table: 2 Select Operator expressions: expr: _col0 type: string expr: _col5 type: string expr: _col9 type: string expr: _col10 type: string expr: _col11 type: string outputColumnNames: _col0, _col5, _col9, _col10, _col11 Select Operator expressions: expr: _col0 type: string expr: _col9 type: string expr: _col5 type: string outputColumnNames: _col0, _col1, _col2 File Output Operator compressed: false GlobalTableId: 1 directory: pfile:/home/amarsri/workspace/hive/build/ql/scratchdir/hive_2011-07-11_02-22-41_288_1522348091919369375/-ext-10002 NumFilesPerFileSink: 1 Stats Publishing Key Prefix: pfile:/home/amarsri/workspace/hive/build/ql/scratchdir/hive_2011-07-11_02-22-41_288_1522348091919369375/-ext-10000/ table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat properties: bucket_count -1 columns key,value,val2 columns.types string:string:string file.inputformat org.apache.hadoop.mapred.TextInputFormat file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat location pfile:/home/amarsri/workspace/hive/build/ql/test/data/warehouse/dest_j1 name default.dest_j1 serialization.ddl struct dest_j1 { string key, string value, string val2} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe transient_lastDdlTime 1310376161 serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.dest_j1 TotalFiles: 1 GatherStats: true MultiFileSpray: false Local Work: Map Reduce Local Work Needs Tagging: false Path -> Alias: pfile:/data/users/tomasz/apache-hive/build/ql/test/data/warehouse/srcpart/ds=2008-04-08/hr=11 [z] Path -> Partition: pfile:/data/users/tomasz/apache-hive/build/ql/test/data/warehouse/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 pfile:/data/users/tomasz/apache-hive/build/ql/test/data/warehouse/srcpart/ds=2008-04-08/hr=11 name default.srcpart partition_columns ds/hr serialization.ddl struct srcpart { string key, string value} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe transient_lastDdlTime 1306977859 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 pfile:/data/users/tomasz/apache-hive/build/ql/test/data/warehouse/srcpart name default.srcpart partition_columns ds/hr serialization.ddl struct srcpart { string key, string value} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe transient_lastDdlTime 1306977857 serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.srcpart name: default.srcpart Stage: Stage-5 Conditional Operator Stage: Stage-4 Move Operator files: hdfs directory: true source: pfile:/data/users/tomasz/apache-hive/build/ql/scratchdir/hive_2011-06-01_19-43-21_478_8339235676581259155/-ext-10002 destination: pfile:/data/users/tomasz/apache-hive/build/ql/scratchdir/hive_2011-06-01_19-43-21_478_8339235676581259155/-ext-10000 Stage: Stage-0 Move Operator tables: replace: true source: pfile:/data/users/tomasz/apache-hive/build/ql/scratchdir/hive_2011-06-01_19-43-21_478_8339235676581259155/-ext-10000 table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat properties: bucket_count -1 columns key,value,val2 columns.types string:string:string file.inputformat org.apache.hadoop.mapred.TextInputFormat file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat location pfile:/data/users/tomasz/apache-hive/build/ql/test/data/warehouse/dest_j1 name default.dest_j1 serialization.ddl struct dest_j1 { string key, string value, string val2} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe transient_lastDdlTime 1306982601 serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.dest_j1 tmp directory: pfile:/data/users/tomasz/apache-hive/build/ql/scratchdir/hive_2011-06-01_19-43-21_478_8339235676581259155/-ext-10001 Stage: Stage-2 Stats-Aggr Operator Stats Aggregation Key Prefix: pfile:/data/users/tomasz/apache-hive/build/ql/scratchdir/hive_2011-06-01_19-43-21_478_8339235676581259155/-ext-10000/ Stage: Stage-3 Map Reduce Alias -> Map Operator Tree: pfile:/data/users/tomasz/apache-hive/build/ql/scratchdir/hive_2011-06-01_19-43-21_478_8339235676581259155/-ext-10002 File Output Operator compressed: false GlobalTableId: 0 directory: pfile:/data/users/tomasz/apache-hive/build/ql/scratchdir/hive_2011-06-01_19-43-21_478_8339235676581259155/-ext-10000 NumFilesPerFileSink: 1 table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat properties: bucket_count -1 columns key,value,val2 columns.types string:string:string file.inputformat org.apache.hadoop.mapred.TextInputFormat file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat location pfile:/data/users/tomasz/apache-hive/build/ql/test/data/warehouse/dest_j1 name default.dest_j1 serialization.ddl struct dest_j1 { string key, string value, string val2} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe transient_lastDdlTime 1306982601 serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.dest_j1 TotalFiles: 1 GatherStats: false MultiFileSpray: false Needs Tagging: false Path -> Alias: pfile:/data/users/tomasz/apache-hive/build/ql/scratchdir/hive_2011-06-01_19-43-21_478_8339235676581259155/-ext-10002 [pfile:/data/users/tomasz/apache-hive/build/ql/scratchdir/hive_2011-06-01_19-43-21_478_8339235676581259155/-ext-10002] Path -> Partition: pfile:/data/users/tomasz/apache-hive/build/ql/scratchdir/hive_2011-06-01_19-43-21_478_8339235676581259155/-ext-10002 Partition base file name: -ext-10002 input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat properties: bucket_count -1 columns key,value,val2 columns.types string:string:string file.inputformat org.apache.hadoop.mapred.TextInputFormat file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat location pfile:/data/users/tomasz/apache-hive/build/ql/test/data/warehouse/dest_j1 name default.dest_j1 serialization.ddl struct dest_j1 { string key, string value, string val2} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe transient_lastDdlTime 1306982601 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,val2 columns.types string:string:string file.inputformat org.apache.hadoop.mapred.TextInputFormat file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat location pfile:/data/users/tomasz/apache-hive/build/ql/test/data/warehouse/dest_j1 name default.dest_j1 serialization.ddl struct dest_j1 { string key, string value, string val2} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe transient_lastDdlTime 1306982601 serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.dest_j1 name: default.dest_j1 PREHOOK: query: INSERT OVERWRITE TABLE dest_j1 SELECT /*+ MAPJOIN(x,y) */ x.key, z.value, y.value FROM src1 x JOIN src y ON (x.key = y.key) JOIN srcpart z ON (x.key = z.key) WHERE z.ds='2008-04-08' and z.hr=11 PREHOOK: type: QUERY PREHOOK: Input: default@src PREHOOK: Input: default@src1 PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 PREHOOK: Output: default@dest_j1 POSTHOOK: query: INSERT OVERWRITE TABLE dest_j1 SELECT /*+ MAPJOIN(x,y) */ x.key, z.value, y.value FROM src1 x JOIN src y ON (x.key = y.key) JOIN srcpart z ON (x.key = z.key) WHERE z.ds='2008-04-08' and z.hr=11 POSTHOOK: type: QUERY POSTHOOK: Input: default@src POSTHOOK: Input: default@src1 POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 POSTHOOK: Output: default@dest_j1 POSTHOOK: Lineage: dest_j1.key SIMPLE [(src1)x.FieldSchema(name:key, type:string, comment:default), ] POSTHOOK: Lineage: dest_j1.val2 SIMPLE [(src)y.FieldSchema(name:value, type:string, comment:default), ] POSTHOOK: Lineage: dest_j1.value SIMPLE [(srcpart)z.FieldSchema(name:value, type:string, comment:default), ] PREHOOK: query: select * from dest_j1 x order by x.key PREHOOK: type: QUERY PREHOOK: Input: default@dest_j1 PREHOOK: Output: file:/tmp/tomasz/hive_2011-06-01_19-43-27_865_1221380812504796408/-mr-10000 POSTHOOK: query: select * from dest_j1 x order by x.key POSTHOOK: type: QUERY POSTHOOK: Input: default@dest_j1 POSTHOOK: Output: file:/tmp/tomasz/hive_2011-06-01_19-43-27_865_1221380812504796408/-mr-10000 POSTHOOK: Lineage: dest_j1.key SIMPLE [(src1)x.FieldSchema(name:key, type:string, comment:default), ] POSTHOOK: Lineage: dest_j1.val2 SIMPLE [(src)y.FieldSchema(name:value, type:string, comment:default), ] POSTHOOK: Lineage: dest_j1.value SIMPLE [(srcpart)z.FieldSchema(name:value, type:string, comment:default), ] 128 val_128 val_128 128 val_128 val_128 128 val_128 val_128 128 val_128 val_128 128 val_128 val_128 128 val_128 val_128 128 val_128 val_128 128 val_128 val_128 128 val_128 val_128 146 val_146 val_146 146 val_146 val_146 146 val_146 val_146 146 val_146 val_146 150 val_150 val_150 213 val_213 val_213 213 val_213 val_213 213 val_213 val_213 213 val_213 val_213 224 val_224 val_224 224 val_224 val_224 224 val_224 val_224 224 val_224 val_224 238 val_238 val_238 238 val_238 val_238 238 val_238 val_238 238 val_238 val_238 255 val_255 val_255 255 val_255 val_255 255 val_255 val_255 255 val_255 val_255 273 val_273 val_273 273 val_273 val_273 273 val_273 val_273 273 val_273 val_273 273 val_273 val_273 273 val_273 val_273 273 val_273 val_273 273 val_273 val_273 273 val_273 val_273 278 val_278 val_278 278 val_278 val_278 278 val_278 val_278 278 val_278 val_278 311 val_311 val_311 311 val_311 val_311 311 val_311 val_311 311 val_311 val_311 311 val_311 val_311 311 val_311 val_311 311 val_311 val_311 311 val_311 val_311 311 val_311 val_311 369 val_369 val_369 369 val_369 val_369 369 val_369 val_369 369 val_369 val_369 369 val_369 val_369 369 val_369 val_369 369 val_369 val_369 369 val_369 val_369 369 val_369 val_369 401 val_401 val_401 401 val_401 val_401 401 val_401 val_401 401 val_401 val_401 401 val_401 val_401 401 val_401 val_401 401 val_401 val_401 401 val_401 val_401 401 val_401 val_401 401 val_401 val_401 401 val_401 val_401 401 val_401 val_401 401 val_401 val_401 401 val_401 val_401 401 val_401 val_401 401 val_401 val_401 401 val_401 val_401 401 val_401 val_401 401 val_401 val_401 401 val_401 val_401 401 val_401 val_401 401 val_401 val_401 401 val_401 val_401 401 val_401 val_401 401 val_401 val_401 406 val_406 val_406 406 val_406 val_406 406 val_406 val_406 406 val_406 val_406 406 val_406 val_406 406 val_406 val_406 406 val_406 val_406 406 val_406 val_406 406 val_406 val_406 406 val_406 val_406 406 val_406 val_406 406 val_406 val_406 406 val_406 val_406 406 val_406 val_406 406 val_406 val_406 406 val_406 val_406 66 val_66 val_66 98 val_98 val_98 98 val_98 val_98 98 val_98 val_98 98 val_98 val_98 PREHOOK: query: CREATE TABLE src_copy(key int, value string) PREHOOK: type: CREATETABLE POSTHOOK: query: CREATE TABLE src_copy(key int, value string) POSTHOOK: type: CREATETABLE POSTHOOK: Output: default@src_copy POSTHOOK: Lineage: dest_j1.key SIMPLE [(src1)x.FieldSchema(name:key, type:string, comment:default), ] POSTHOOK: Lineage: dest_j1.val2 SIMPLE [(src)y.FieldSchema(name:value, type:string, comment:default), ] POSTHOOK: Lineage: dest_j1.value SIMPLE [(srcpart)z.FieldSchema(name:value, type:string, comment:default), ] PREHOOK: query: CREATE TABLE src1_copy(key string, value string) PREHOOK: type: CREATETABLE POSTHOOK: query: CREATE TABLE src1_copy(key string, value string) POSTHOOK: type: CREATETABLE POSTHOOK: Output: default@src1_copy POSTHOOK: Lineage: dest_j1.key SIMPLE [(src1)x.FieldSchema(name:key, type:string, comment:default), ] POSTHOOK: Lineage: dest_j1.val2 SIMPLE [(src)y.FieldSchema(name:value, type:string, comment:default), ] POSTHOOK: Lineage: dest_j1.value SIMPLE [(srcpart)z.FieldSchema(name:value, type:string, comment:default), ] PREHOOK: query: INSERT OVERWRITE TABLE src_copy select key, value from src PREHOOK: type: QUERY PREHOOK: Input: default@src PREHOOK: Output: default@src_copy POSTHOOK: query: INSERT OVERWRITE TABLE src_copy select key, value from src POSTHOOK: type: QUERY POSTHOOK: Input: default@src POSTHOOK: Output: default@src_copy POSTHOOK: Lineage: dest_j1.key SIMPLE [(src1)x.FieldSchema(name:key, type:string, comment:default), ] POSTHOOK: Lineage: dest_j1.val2 SIMPLE [(src)y.FieldSchema(name:value, type:string, comment:default), ] POSTHOOK: Lineage: dest_j1.value SIMPLE [(srcpart)z.FieldSchema(name:value, type:string, comment:default), ] POSTHOOK: Lineage: src_copy.key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] POSTHOOK: Lineage: src_copy.value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] PREHOOK: query: INSERT OVERWRITE TABLE src1_copy select key, value from src1 PREHOOK: type: QUERY PREHOOK: Input: default@src1 PREHOOK: Output: default@src1_copy POSTHOOK: query: INSERT OVERWRITE TABLE src1_copy select key, value from src1 POSTHOOK: type: QUERY POSTHOOK: Input: default@src1 POSTHOOK: Output: default@src1_copy POSTHOOK: Lineage: dest_j1.key SIMPLE [(src1)x.FieldSchema(name:key, type:string, comment:default), ] POSTHOOK: Lineage: dest_j1.val2 SIMPLE [(src)y.FieldSchema(name:value, type:string, comment:default), ] POSTHOOK: Lineage: dest_j1.value SIMPLE [(srcpart)z.FieldSchema(name:value, type:string, comment:default), ] POSTHOOK: Lineage: src1_copy.key SIMPLE [(src1)src1.FieldSchema(name:key, type:string, comment:default), ] POSTHOOK: Lineage: src1_copy.value SIMPLE [(src1)src1.FieldSchema(name:value, type:string, comment:default), ] POSTHOOK: Lineage: src_copy.key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] POSTHOOK: Lineage: src_copy.value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] PREHOOK: query: EXPLAIN EXTENDED INSERT OVERWRITE TABLE dest_j1 SELECT /*+ MAPJOIN(x,y) */ x.key, z.value, y.value FROM src1_copy x JOIN src_copy y ON (x.key = y.key) JOIN srcpart z ON (x.key = z.key) WHERE z.ds='2008-04-08' and z.hr=11 PREHOOK: type: QUERY POSTHOOK: query: EXPLAIN EXTENDED INSERT OVERWRITE TABLE dest_j1 SELECT /*+ MAPJOIN(x,y) */ x.key, z.value, y.value FROM src1_copy x JOIN src_copy y ON (x.key = y.key) JOIN srcpart z ON (x.key = z.key) WHERE z.ds='2008-04-08' and z.hr=11 POSTHOOK: type: QUERY POSTHOOK: Lineage: dest_j1.key SIMPLE [(src1)x.FieldSchema(name:key, type:string, comment:default), ] POSTHOOK: Lineage: dest_j1.val2 SIMPLE [(src)y.FieldSchema(name:value, type:string, comment:default), ] POSTHOOK: Lineage: dest_j1.value SIMPLE [(srcpart)z.FieldSchema(name:value, type:string, comment:default), ] POSTHOOK: Lineage: src1_copy.key SIMPLE [(src1)src1.FieldSchema(name:key, type:string, comment:default), ] POSTHOOK: Lineage: src1_copy.value SIMPLE [(src1)src1.FieldSchema(name:value, type:string, comment:default), ] POSTHOOK: Lineage: src_copy.key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] POSTHOOK: Lineage: src_copy.value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] ABSTRACT SYNTAX TREE: (TOK_QUERY (TOK_FROM (TOK_JOIN (TOK_JOIN (TOK_TABREF (TOK_TABNAME src1_copy) x) (TOK_TABREF (TOK_TABNAME src_copy) y) (= (. (TOK_TABLE_OR_COL x) key) (. (TOK_TABLE_OR_COL y) key))) (TOK_TABREF (TOK_TABNAME srcpart) z) (= (. (TOK_TABLE_OR_COL x) key) (. (TOK_TABLE_OR_COL z) key)))) (TOK_INSERT (TOK_DESTINATION (TOK_TAB (TOK_TABNAME dest_j1))) (TOK_SELECT (TOK_HINTLIST (TOK_HINT TOK_MAPJOIN (TOK_HINTARGLIST x y))) (TOK_SELEXPR (. (TOK_TABLE_OR_COL x) key)) (TOK_SELEXPR (. (TOK_TABLE_OR_COL z) value)) (TOK_SELEXPR (. (TOK_TABLE_OR_COL y) value))) (TOK_WHERE (and (= (. (TOK_TABLE_OR_COL z) ds) '2008-04-08') (= (. (TOK_TABLE_OR_COL z) hr) 11))))) STAGE DEPENDENCIES: Stage-8 is a root stage Stage-1 depends on stages: Stage-8 Stage-5 depends on stages: Stage-1 , consists of Stage-4, Stage-3 Stage-4 Stage-0 depends on stages: Stage-4, Stage-3 Stage-2 depends on stages: Stage-0 Stage-3 STAGE PLANS: Stage: Stage-8 Map Reduce Local Work Alias -> Map Local Tables: x Fetch Operator limit: -1 y Fetch Operator limit: -1 Alias -> Map Local Operator Tree: x TableScan alias: x GatherStats: false HashTable Sink Operator condition expressions: 0 {key} 1 {value} 2 {value} {ds} {hr} handleSkewJoin: false keys: 0 [class org.apache.hadoop.hive.ql.udf.generic.GenericUDFBridge(Column[key]()] 1 [class org.apache.hadoop.hive.ql.udf.generic.GenericUDFBridge(Column[key]()] 2 [class org.apache.hadoop.hive.ql.udf.generic.GenericUDFBridge(Column[key]()] Position of Big Table: 2 y TableScan alias: y GatherStats: false HashTable Sink Operator condition expressions: 0 {key} 1 {value} 2 {value} {ds} {hr} handleSkewJoin: false keys: 0 [class org.apache.hadoop.hive.ql.udf.generic.GenericUDFBridge(Column[key]()] 1 [class org.apache.hadoop.hive.ql.udf.generic.GenericUDFBridge(Column[key]()] 2 [class org.apache.hadoop.hive.ql.udf.generic.GenericUDFBridge(Column[key]()] Position of Big Table: 2 Stage: Stage-1 Map Reduce Alias -> Map Operator Tree: z TableScan alias: z GatherStats: false Map Join Operator condition map: Inner Join 0 to 1 Inner Join 0 to 2 condition expressions: 0 {key} 1 {value} 2 {value} {ds} {hr} handleSkewJoin: false keys: 0 [class org.apache.hadoop.hive.ql.udf.generic.GenericUDFBridge(Column[key]()] 1 [class org.apache.hadoop.hive.ql.udf.generic.GenericUDFBridge(Column[key]()] 2 [class org.apache.hadoop.hive.ql.udf.generic.GenericUDFBridge(Column[key]()] outputColumnNames: _col0, _col5, _col9, _col10, _col11 Position of Big Table: 2 Select Operator expressions: expr: _col0 type: string expr: _col5 type: string expr: _col9 type: string expr: _col10 type: string expr: _col11 type: string outputColumnNames: _col0, _col5, _col9, _col10, _col11 Select Operator expressions: expr: _col0 type: string expr: _col9 type: string expr: _col5 type: string outputColumnNames: _col0, _col1, _col2 File Output Operator compressed: false GlobalTableId: 1 directory: pfile:/home/amarsri/workspace/hive/build/ql/scratchdir/hive_2011-07-11_02-22-56_227_1785331413587992732/-ext-10002 NumFilesPerFileSink: 1 Stats Publishing Key Prefix: pfile:/home/amarsri/workspace/hive/build/ql/scratchdir/hive_2011-07-11_02-22-56_227_1785331413587992732/-ext-10000/ table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat properties: bucket_count -1 columns key,value,val2 columns.types string:string:string file.inputformat org.apache.hadoop.mapred.TextInputFormat file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat location pfile:/home/amarsri/workspace/hive/build/ql/test/data/warehouse/dest_j1 name default.dest_j1 numFiles 1 numPartitions 0 numRows 107 rawDataSize 2018 serialization.ddl struct dest_j1 { string key, string value, string val2} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe totalSize 2125 transient_lastDdlTime 1310376166 serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.dest_j1 TotalFiles: 1 GatherStats: true MultiFileSpray: false Local Work: Map Reduce Local Work Needs Tagging: false Path -> Alias: pfile:/data/users/tomasz/apache-hive/build/ql/test/data/warehouse/srcpart/ds=2008-04-08/hr=11 [z] Path -> Partition: pfile:/data/users/tomasz/apache-hive/build/ql/test/data/warehouse/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 pfile:/data/users/tomasz/apache-hive/build/ql/test/data/warehouse/srcpart/ds=2008-04-08/hr=11 name default.srcpart partition_columns ds/hr serialization.ddl struct srcpart { string key, string value} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe transient_lastDdlTime 1306977859 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 pfile:/data/users/tomasz/apache-hive/build/ql/test/data/warehouse/srcpart name default.srcpart partition_columns ds/hr serialization.ddl struct srcpart { string key, string value} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe transient_lastDdlTime 1306977857 serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.srcpart name: default.srcpart Stage: Stage-5 Conditional Operator Stage: Stage-4 Move Operator files: hdfs directory: true source: pfile:/data/users/tomasz/apache-hive/build/ql/scratchdir/hive_2011-06-01_19-43-39_193_3629767743822800153/-ext-10002 destination: pfile:/data/users/tomasz/apache-hive/build/ql/scratchdir/hive_2011-06-01_19-43-39_193_3629767743822800153/-ext-10000 Stage: Stage-0 Move Operator tables: replace: true source: pfile:/data/users/tomasz/apache-hive/build/ql/scratchdir/hive_2011-06-01_19-43-39_193_3629767743822800153/-ext-10000 table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat properties: bucket_count -1 columns key,value,val2 columns.types string:string:string file.inputformat org.apache.hadoop.mapred.TextInputFormat file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat location pfile:/data/users/tomasz/apache-hive/build/ql/test/data/warehouse/dest_j1 name default.dest_j1 numFiles 1 numPartitions 0 numRows 107 rawDataSize 2018 serialization.ddl struct dest_j1 { string key, string value, string val2} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe totalSize 2125 transient_lastDdlTime 1306982607 serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.dest_j1 tmp directory: pfile:/data/users/tomasz/apache-hive/build/ql/scratchdir/hive_2011-06-01_19-43-39_193_3629767743822800153/-ext-10001 Stage: Stage-2 Stats-Aggr Operator Stats Aggregation Key Prefix: pfile:/data/users/tomasz/apache-hive/build/ql/scratchdir/hive_2011-06-01_19-43-39_193_3629767743822800153/-ext-10000/ Stage: Stage-3 Map Reduce Alias -> Map Operator Tree: pfile:/data/users/tomasz/apache-hive/build/ql/scratchdir/hive_2011-06-01_19-43-39_193_3629767743822800153/-ext-10002 File Output Operator compressed: false GlobalTableId: 0 directory: pfile:/data/users/tomasz/apache-hive/build/ql/scratchdir/hive_2011-06-01_19-43-39_193_3629767743822800153/-ext-10000 NumFilesPerFileSink: 1 table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat properties: bucket_count -1 columns key,value,val2 columns.types string:string:string file.inputformat org.apache.hadoop.mapred.TextInputFormat file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat location pfile:/data/users/tomasz/apache-hive/build/ql/test/data/warehouse/dest_j1 name default.dest_j1 numFiles 1 numPartitions 0 numRows 107 rawDataSize 2018 serialization.ddl struct dest_j1 { string key, string value, string val2} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe totalSize 2125 transient_lastDdlTime 1306982607 serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.dest_j1 TotalFiles: 1 GatherStats: false MultiFileSpray: false Needs Tagging: false Path -> Alias: pfile:/data/users/tomasz/apache-hive/build/ql/scratchdir/hive_2011-06-01_19-43-39_193_3629767743822800153/-ext-10002 [pfile:/data/users/tomasz/apache-hive/build/ql/scratchdir/hive_2011-06-01_19-43-39_193_3629767743822800153/-ext-10002] Path -> Partition: pfile:/data/users/tomasz/apache-hive/build/ql/scratchdir/hive_2011-06-01_19-43-39_193_3629767743822800153/-ext-10002 Partition base file name: -ext-10002 input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat properties: bucket_count -1 columns key,value,val2 columns.types string:string:string file.inputformat org.apache.hadoop.mapred.TextInputFormat file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat location pfile:/data/users/tomasz/apache-hive/build/ql/test/data/warehouse/dest_j1 name default.dest_j1 numFiles 1 numPartitions 0 numRows 107 rawDataSize 2018 serialization.ddl struct dest_j1 { string key, string value, string val2} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe totalSize 2125 transient_lastDdlTime 1306982607 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,val2 columns.types string:string:string file.inputformat org.apache.hadoop.mapred.TextInputFormat file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat location pfile:/data/users/tomasz/apache-hive/build/ql/test/data/warehouse/dest_j1 name default.dest_j1 numFiles 1 numPartitions 0 numRows 107 rawDataSize 2018 serialization.ddl struct dest_j1 { string key, string value, string val2} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe totalSize 2125 transient_lastDdlTime 1306982607 serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.dest_j1 name: default.dest_j1 PREHOOK: query: INSERT OVERWRITE TABLE dest_j1 SELECT /*+ MAPJOIN(x,y) */ x.key, z.value, y.value FROM src1_copy x JOIN src_copy y ON (x.key = y.key) JOIN srcpart z ON (x.key = z.key) WHERE z.ds='2008-04-08' and z.hr=11 PREHOOK: type: QUERY PREHOOK: Input: default@src1_copy PREHOOK: Input: default@src_copy PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 PREHOOK: Output: default@dest_j1 POSTHOOK: query: INSERT OVERWRITE TABLE dest_j1 SELECT /*+ MAPJOIN(x,y) */ x.key, z.value, y.value FROM src1_copy x JOIN src_copy y ON (x.key = y.key) JOIN srcpart z ON (x.key = z.key) WHERE z.ds='2008-04-08' and z.hr=11 POSTHOOK: type: QUERY POSTHOOK: Input: default@src1_copy POSTHOOK: Input: default@src_copy POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 POSTHOOK: Output: default@dest_j1 POSTHOOK: Lineage: dest_j1.key SIMPLE [(src1)x.FieldSchema(name:key, type:string, comment:default), ] POSTHOOK: Lineage: dest_j1.key SIMPLE [(src1_copy)x.FieldSchema(name:key, type:string, comment:null), ] POSTHOOK: Lineage: dest_j1.val2 SIMPLE [(src)y.FieldSchema(name:value, type:string, comment:default), ] POSTHOOK: Lineage: dest_j1.val2 SIMPLE [(src_copy)y.FieldSchema(name:value, type:string, comment:null), ] POSTHOOK: Lineage: dest_j1.value SIMPLE [(srcpart)z.FieldSchema(name:value, type:string, comment:default), ] POSTHOOK: Lineage: dest_j1.value SIMPLE [(srcpart)z.FieldSchema(name:value, type:string, comment:default), ] POSTHOOK: Lineage: src1_copy.key SIMPLE [(src1)src1.FieldSchema(name:key, type:string, comment:default), ] POSTHOOK: Lineage: src1_copy.value SIMPLE [(src1)src1.FieldSchema(name:value, type:string, comment:default), ] POSTHOOK: Lineage: src_copy.key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] POSTHOOK: Lineage: src_copy.value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] PREHOOK: query: select * from dest_j1 x order by x.key PREHOOK: type: QUERY PREHOOK: Input: default@dest_j1 PREHOOK: Output: file:/tmp/tomasz/hive_2011-06-01_19-43-45_996_4339642545835333367/-mr-10000 POSTHOOK: query: select * from dest_j1 x order by x.key POSTHOOK: type: QUERY POSTHOOK: Input: default@dest_j1 POSTHOOK: Output: file:/tmp/tomasz/hive_2011-06-01_19-43-45_996_4339642545835333367/-mr-10000 POSTHOOK: Lineage: dest_j1.key SIMPLE [(src1)x.FieldSchema(name:key, type:string, comment:default), ] POSTHOOK: Lineage: dest_j1.key SIMPLE [(src1_copy)x.FieldSchema(name:key, type:string, comment:null), ] POSTHOOK: Lineage: dest_j1.val2 SIMPLE [(src)y.FieldSchema(name:value, type:string, comment:default), ] POSTHOOK: Lineage: dest_j1.val2 SIMPLE [(src_copy)y.FieldSchema(name:value, type:string, comment:null), ] POSTHOOK: Lineage: dest_j1.value SIMPLE [(srcpart)z.FieldSchema(name:value, type:string, comment:default), ] POSTHOOK: Lineage: dest_j1.value SIMPLE [(srcpart)z.FieldSchema(name:value, type:string, comment:default), ] POSTHOOK: Lineage: src1_copy.key SIMPLE [(src1)src1.FieldSchema(name:key, type:string, comment:default), ] POSTHOOK: Lineage: src1_copy.value SIMPLE [(src1)src1.FieldSchema(name:value, type:string, comment:default), ] POSTHOOK: Lineage: src_copy.key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] POSTHOOK: Lineage: src_copy.value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] 128 val_128 val_128 128 val_128 val_128 128 val_128 val_128 128 val_128 val_128 128 val_128 val_128 128 val_128 val_128 128 val_128 val_128 128 val_128 val_128 128 val_128 val_128 146 val_146 val_146 146 val_146 val_146 146 val_146 val_146 146 val_146 val_146 150 val_150 val_150 213 val_213 val_213 213 val_213 val_213 213 val_213 val_213 213 val_213 val_213 224 val_224 val_224 224 val_224 val_224 224 val_224 val_224 224 val_224 val_224 238 val_238 val_238 238 val_238 val_238 238 val_238 val_238 238 val_238 val_238 255 val_255 val_255 255 val_255 val_255 255 val_255 val_255 255 val_255 val_255 273 val_273 val_273 273 val_273 val_273 273 val_273 val_273 273 val_273 val_273 273 val_273 val_273 273 val_273 val_273 273 val_273 val_273 273 val_273 val_273 273 val_273 val_273 278 val_278 val_278 278 val_278 val_278 278 val_278 val_278 278 val_278 val_278 311 val_311 val_311 311 val_311 val_311 311 val_311 val_311 311 val_311 val_311 311 val_311 val_311 311 val_311 val_311 311 val_311 val_311 311 val_311 val_311 311 val_311 val_311 369 val_369 val_369 369 val_369 val_369 369 val_369 val_369 369 val_369 val_369 369 val_369 val_369 369 val_369 val_369 369 val_369 val_369 369 val_369 val_369 369 val_369 val_369 401 val_401 val_401 401 val_401 val_401 401 val_401 val_401 401 val_401 val_401 401 val_401 val_401 401 val_401 val_401 401 val_401 val_401 401 val_401 val_401 401 val_401 val_401 401 val_401 val_401 401 val_401 val_401 401 val_401 val_401 401 val_401 val_401 401 val_401 val_401 401 val_401 val_401 401 val_401 val_401 401 val_401 val_401 401 val_401 val_401 401 val_401 val_401 401 val_401 val_401 401 val_401 val_401 401 val_401 val_401 401 val_401 val_401 401 val_401 val_401 401 val_401 val_401 406 val_406 val_406 406 val_406 val_406 406 val_406 val_406 406 val_406 val_406 406 val_406 val_406 406 val_406 val_406 406 val_406 val_406 406 val_406 val_406 406 val_406 val_406 406 val_406 val_406 406 val_406 val_406 406 val_406 val_406 406 val_406 val_406 406 val_406 val_406 406 val_406 val_406 406 val_406 val_406 66 val_66 val_66 98 val_98 val_98 98 val_98 val_98 98 val_98 val_98 98 val_98 val_98