PREHOOK: query: drop table dest_j1 PREHOOK: type: DROPTABLE POSTHOOK: query: drop table dest_j1 POSTHOOK: type: DROPTABLE 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) */ x.key, x.value, subq1.value FROM ( SELECT x.key as key, x.value as value from src x where x.key < 20 UNION ALL SELECT x1.key as key, x1.value as value from src x1 where x1.key > 100 ) subq1 JOIN src1 x ON (x.key = subq1.key) PREHOOK: type: QUERY POSTHOOK: query: EXPLAIN EXTENDED INSERT OVERWRITE TABLE dest_j1 SELECT /*+ MAPJOIN(x) */ x.key, x.value, subq1.value FROM ( SELECT x.key as key, x.value as value from src x where x.key < 20 UNION ALL SELECT x1.key as key, x1.value as value from src x1 where x1.key > 100 ) subq1 JOIN src1 x ON (x.key = subq1.key) POSTHOOK: type: QUERY ABSTRACT SYNTAX TREE: (TOK_QUERY (TOK_FROM (TOK_JOIN (TOK_SUBQUERY (TOK_UNION (TOK_QUERY (TOK_FROM (TOK_TABREF src x)) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (. (TOK_TABLE_OR_COL x) key) key) (TOK_SELEXPR (. (TOK_TABLE_OR_COL x) value) value)) (TOK_WHERE (< (. (TOK_TABLE_OR_COL x) key) 20)))) (TOK_QUERY (TOK_FROM (TOK_TABREF src x1)) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (. (TOK_TABLE_OR_COL x1) key) key) (TOK_SELEXPR (. (TOK_TABLE_OR_COL x1) value) value)) (TOK_WHERE (> (. (TOK_TABLE_OR_COL x1) key) 100))))) subq1) (TOK_TABREF src1 x) (= (. (TOK_TABLE_OR_COL x) key) (. (TOK_TABLE_OR_COL subq1) key)))) (TOK_INSERT (TOK_DESTINATION (TOK_TAB dest_j1)) (TOK_SELECT (TOK_HINTLIST (TOK_HINT TOK_MAPJOIN (TOK_HINTARGLIST x))) (TOK_SELEXPR (. (TOK_TABLE_OR_COL x) key)) (TOK_SELEXPR (. (TOK_TABLE_OR_COL x) value)) (TOK_SELEXPR (. (TOK_TABLE_OR_COL subq1) value))))) STAGE DEPENDENCIES: Stage-1 is a root stage Stage-4 depends on stages: Stage-1 , consists of Stage-3, Stage-2 Stage-3 Stage-0 depends on stages: Stage-3, Stage-2 Stage-2 STAGE PLANS: Stage: Stage-1 Map Reduce Alias -> Map Operator Tree: null-subquery1:subq1-subquery1:x TableScan alias: x Filter Operator isSamplingPred: false predicate: expr: (key < 20) type: boolean Filter Operator isSamplingPred: false predicate: expr: (key < 20) type: boolean Select Operator expressions: expr: key type: string expr: value type: string outputColumnNames: _col0, _col1 Union Common Join Operator condition map: Inner Join 0 to 1 condition expressions: 0 {_col1} 1 {key} {value} handleSkewJoin: false keys: 0 [Column[_col0]] 1 [Column[key]] outputColumnNames: _col1, _col2, _col3 Position of Big Table: 0 Select Operator expressions: expr: _col1 type: string expr: _col2 type: string expr: _col3 type: string outputColumnNames: _col1, _col2, _col3 Select Operator expressions: expr: _col2 type: string expr: _col3 type: string expr: _col1 type: string outputColumnNames: _col0, _col1, _col2 File Output Operator compressed: false GlobalTableId: 1 directory: file:/data/users/nzhang/reviews/0.6/branch-0.6/build/ql/scratchdir/hive_2010-08-22_13-49-44_530_368280846116244432/10002 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 file:/data/users/nzhang/reviews/0.6/branch-0.6/build/ql/test/data/warehouse/dest_j1 name 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 1282510184 serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: dest_j1 TotalFiles: 1 MultiFileSpray: false null-subquery2:subq1-subquery2:x1 TableScan alias: x1 Filter Operator isSamplingPred: false predicate: expr: (key > 100) type: boolean Filter Operator isSamplingPred: false predicate: expr: (key > 100) type: boolean Select Operator expressions: expr: key type: string expr: value type: string outputColumnNames: _col0, _col1 Union Common Join Operator condition map: Inner Join 0 to 1 condition expressions: 0 {_col1} 1 {key} {value} handleSkewJoin: false keys: 0 [Column[_col0]] 1 [Column[key]] outputColumnNames: _col1, _col2, _col3 Position of Big Table: 0 Select Operator expressions: expr: _col1 type: string expr: _col2 type: string expr: _col3 type: string outputColumnNames: _col1, _col2, _col3 Select Operator expressions: expr: _col2 type: string expr: _col3 type: string expr: _col1 type: string outputColumnNames: _col0, _col1, _col2 File Output Operator compressed: false GlobalTableId: 1 directory: file:/data/users/nzhang/reviews/0.6/branch-0.6/build/ql/scratchdir/hive_2010-08-22_13-49-44_530_368280846116244432/10002 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 file:/data/users/nzhang/reviews/0.6/branch-0.6/build/ql/test/data/warehouse/dest_j1 name 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 1282510184 serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: dest_j1 TotalFiles: 1 MultiFileSpray: false Local Work: Map Reduce Local Work Alias -> Map Local Tables: x Fetch Operator limit: -1 Alias -> Map Local Operator Tree: x TableScan alias: x Common Join Operator condition map: Inner Join 0 to 1 condition expressions: 0 {_col1} 1 {key} {value} handleSkewJoin: false keys: 0 [Column[_col0]] 1 [Column[key]] outputColumnNames: _col1, _col2, _col3 Position of Big Table: 0 Select Operator expressions: expr: _col1 type: string expr: _col2 type: string expr: _col3 type: string outputColumnNames: _col1, _col2, _col3 Select Operator expressions: expr: _col2 type: string expr: _col3 type: string expr: _col1 type: string outputColumnNames: _col0, _col1, _col2 File Output Operator compressed: false GlobalTableId: 1 directory: file:/data/users/nzhang/reviews/0.6/branch-0.6/build/ql/scratchdir/hive_2010-08-22_13-49-44_530_368280846116244432/10002 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 file:/data/users/nzhang/reviews/0.6/branch-0.6/build/ql/test/data/warehouse/dest_j1 name 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 1282510184 serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: dest_j1 TotalFiles: 1 MultiFileSpray: false Needs Tagging: false Path -> Alias: file:/data/users/nzhang/reviews/0.6/branch-0.6/build/ql/test/data/warehouse/src [null-subquery1:subq1-subquery1:x, null-subquery2:subq1-subquery2:x1] Path -> Partition: file:/data/users/nzhang/reviews/0.6/branch-0.6/build/ql/test/data/warehouse/src Partition base file name: src 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 file:/data/users/nzhang/reviews/0.6/branch-0.6/build/ql/test/data/warehouse/src name src serialization.ddl struct src { string key, string value} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe transient_lastDdlTime 1282510183 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 file:/data/users/nzhang/reviews/0.6/branch-0.6/build/ql/test/data/warehouse/src name src serialization.ddl struct src { string key, string value} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe transient_lastDdlTime 1282510183 serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: src name: src Stage: Stage-4 Conditional Operator Stage: Stage-3 Move Operator files: hdfs directory: true source: file:/data/users/nzhang/reviews/0.6/branch-0.6/build/ql/scratchdir/hive_2010-08-22_13-49-44_530_368280846116244432/10002 destination: file:/data/users/nzhang/reviews/0.6/branch-0.6/build/ql/scratchdir/hive_2010-08-22_13-49-44_530_368280846116244432/10000 Stage: Stage-0 Move Operator tables: replace: true source: file:/data/users/nzhang/reviews/0.6/branch-0.6/build/ql/scratchdir/hive_2010-08-22_13-49-44_530_368280846116244432/10000 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 file:/data/users/nzhang/reviews/0.6/branch-0.6/build/ql/test/data/warehouse/dest_j1 name 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 1282510184 serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: dest_j1 tmp directory: file:/data/users/nzhang/reviews/0.6/branch-0.6/build/ql/scratchdir/hive_2010-08-22_13-49-44_530_368280846116244432/10001 Stage: Stage-2 Map Reduce Alias -> Map Operator Tree: file:/data/users/nzhang/reviews/0.6/branch-0.6/build/ql/scratchdir/hive_2010-08-22_13-49-44_530_368280846116244432/10002 File Output Operator compressed: false GlobalTableId: 0 directory: file:/data/users/nzhang/reviews/0.6/branch-0.6/build/ql/scratchdir/hive_2010-08-22_13-49-44_530_368280846116244432/10000 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 file:/data/users/nzhang/reviews/0.6/branch-0.6/build/ql/test/data/warehouse/dest_j1 name 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 1282510184 serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: dest_j1 TotalFiles: 1 MultiFileSpray: false Needs Tagging: false Path -> Alias: file:/data/users/nzhang/reviews/0.6/branch-0.6/build/ql/scratchdir/hive_2010-08-22_13-49-44_530_368280846116244432/10002 [file:/data/users/nzhang/reviews/0.6/branch-0.6/build/ql/scratchdir/hive_2010-08-22_13-49-44_530_368280846116244432/10002] Path -> Partition: file:/data/users/nzhang/reviews/0.6/branch-0.6/build/ql/scratchdir/hive_2010-08-22_13-49-44_530_368280846116244432/10002 Partition base file name: 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 file:/data/users/nzhang/reviews/0.6/branch-0.6/build/ql/test/data/warehouse/dest_j1 name 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 1282510184 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 file:/data/users/nzhang/reviews/0.6/branch-0.6/build/ql/test/data/warehouse/dest_j1 name 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 1282510184 serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: dest_j1 name: dest_j1 PREHOOK: query: INSERT OVERWRITE TABLE dest_j1 SELECT /*+ MAPJOIN(x) */ x.key, x.value, subq1.value FROM ( SELECT x.key as key, x.value as value from src x where x.key < 20 UNION ALL SELECT x1.key as key, x1.value as value from src x1 where x1.key > 100 ) subq1 JOIN src1 x ON (x.key = subq1.key) PREHOOK: type: QUERY PREHOOK: Input: default@src PREHOOK: Input: default@src1 PREHOOK: Output: default@dest_j1 POSTHOOK: query: INSERT OVERWRITE TABLE dest_j1 SELECT /*+ MAPJOIN(x) */ x.key, x.value, subq1.value FROM ( SELECT x.key as key, x.value as value from src x where x.key < 20 UNION ALL SELECT x1.key as key, x1.value as value from src x1 where x1.key > 100 ) subq1 JOIN src1 x ON (x.key = subq1.key) POSTHOOK: type: QUERY POSTHOOK: Input: default@src POSTHOOK: Input: default@src1 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 EXPRESSION [(src)x.FieldSchema(name:value, type:string, comment:default), (src)x1.FieldSchema(name:value, type:string, comment:default), ] POSTHOOK: Lineage: dest_j1.value SIMPLE [(src1)x.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/nzhang/hive_2010-08-22_13-49-48_810_7706361304357525455/10000 POSTHOOK: query: select * from dest_j1 x order by x.key POSTHOOK: type: QUERY POSTHOOK: Input: default@dest_j1 POSTHOOK: Output: file:/tmp/nzhang/hive_2010-08-22_13-49-48_810_7706361304357525455/10000 POSTHOOK: Lineage: dest_j1.key SIMPLE [(src1)x.FieldSchema(name:key, type:string, comment:default), ] POSTHOOK: Lineage: dest_j1.val2 EXPRESSION [(src)x.FieldSchema(name:value, type:string, comment:default), (src)x1.FieldSchema(name:value, type:string, comment:default), ] POSTHOOK: Lineage: dest_j1.value SIMPLE [(src1)x.FieldSchema(name:value, type:string, comment:default), ] 128 val_128 128 val_128 128 val_128 146 val_146 val_146 146 val_146 val_146 150 val_150 val_150 213 val_213 val_213 213 val_213 val_213 224 val_224 224 val_224 238 val_238 val_238 238 val_238 val_238 255 val_255 val_255 255 val_255 val_255 273 val_273 val_273 273 val_273 val_273 273 val_273 val_273 278 val_278 val_278 278 val_278 val_278 311 val_311 val_311 311 val_311 val_311 311 val_311 val_311 369 val_369 369 val_369 369 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_401 406 val_406 val_406 406 val_406 val_406 406 val_406 val_406 406 val_406 val_406 PREHOOK: query: drop table dest_j1 PREHOOK: type: DROPTABLE POSTHOOK: query: drop table dest_j1 POSTHOOK: type: DROPTABLE 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 EXPRESSION [(src)x.FieldSchema(name:value, type:string, comment:default), (src)x1.FieldSchema(name:value, type:string, comment:default), ] POSTHOOK: Lineage: dest_j1.value SIMPLE [(src1)x.FieldSchema(name:value, type:string, comment:default), ]