PREHOOK: query: CREATE TABLE dest1(key INT, value STRING) STORED AS TEXTFILE PREHOOK: type: CREATETABLE POSTHOOK: query: CREATE TABLE dest1(key INT, value STRING) STORED AS TEXTFILE POSTHOOK: type: CREATETABLE POSTHOOK: Output: default@dest1 PREHOOK: query: -- both input pruning and sample filter EXPLAIN EXTENDED INSERT OVERWRITE TABLE dest1 SELECT s.* FROM srcbucket TABLESAMPLE (BUCKET 1 OUT OF 4 on key) s WHERE s.key > 100 PREHOOK: type: QUERY POSTHOOK: query: -- both input pruning and sample filter EXPLAIN EXTENDED INSERT OVERWRITE TABLE dest1 SELECT s.* FROM srcbucket TABLESAMPLE (BUCKET 1 OUT OF 4 on key) s WHERE s.key > 100 POSTHOOK: type: QUERY ABSTRACT SYNTAX TREE: (TOK_QUERY (TOK_FROM (TOK_TABREF srcbucket (TOK_TABLESAMPLE 1 4 (TOK_TABLE_OR_COL key)) s)) (TOK_INSERT (TOK_DESTINATION (TOK_TAB dest1)) (TOK_SELECT (TOK_SELEXPR (TOK_ALLCOLREF s))) (TOK_WHERE (> (. (TOK_TABLE_OR_COL s) key) 100)))) 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: s TableScan alias: s Filter Operator isSamplingPred: false predicate: expr: ((((hash(key) & 2147483647) % 4) = 0) and (key > 100)) type: boolean Filter Operator isSamplingPred: true predicate: expr: (((hash(key) & 2147483647) % 4) = 0) type: boolean Filter Operator isSamplingPred: false predicate: expr: (key > 100) type: boolean Select Operator expressions: expr: key type: int expr: value type: string outputColumnNames: _col0, _col1 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_14-17-10_442_2893644706247210749/10002 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 columns.types int: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/dest1 name dest1 serialization.ddl struct dest1 { i32 key, string value} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe transient_lastDdlTime 1282511830 serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: dest1 TotalFiles: 1 MultiFileSpray: false Needs Tagging: false Path -> Alias: file:/data/users/nzhang/reviews/0.6/branch-0.6/build/ql/test/data/warehouse/srcbucket/srcbucket0.txt [s] Path -> Partition: file:/data/users/nzhang/reviews/0.6/branch-0.6/build/ql/test/data/warehouse/srcbucket/srcbucket0.txt Partition base file name: srcbucket0.txt input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat properties: bucket_count 2 bucket_field_name key columns key,value columns.types int: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/srcbucket name srcbucket serialization.ddl struct srcbucket { i32 key, string value} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe transient_lastDdlTime 1282511829 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 2 bucket_field_name key columns key,value columns.types int: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/srcbucket name srcbucket serialization.ddl struct srcbucket { i32 key, string value} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe transient_lastDdlTime 1282511829 serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: srcbucket name: srcbucket 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_14-17-10_442_2893644706247210749/10002 destination: file:/data/users/nzhang/reviews/0.6/branch-0.6/build/ql/scratchdir/hive_2010-08-22_14-17-10_442_2893644706247210749/10000 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_14-17-10_442_2893644706247210749/10000 table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat properties: bucket_count -1 columns key,value columns.types int: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/dest1 name dest1 serialization.ddl struct dest1 { i32 key, string value} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe transient_lastDdlTime 1282511830 serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: dest1 tmp directory: file:/data/users/nzhang/reviews/0.6/branch-0.6/build/ql/scratchdir/hive_2010-08-22_14-17-10_442_2893644706247210749/10001 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_14-17-10_442_2893644706247210749/10002 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_14-17-10_442_2893644706247210749/10000 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 columns.types int: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/dest1 name dest1 serialization.ddl struct dest1 { i32 key, string value} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe transient_lastDdlTime 1282511830 serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: dest1 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_14-17-10_442_2893644706247210749/10002 [file:/data/users/nzhang/reviews/0.6/branch-0.6/build/ql/scratchdir/hive_2010-08-22_14-17-10_442_2893644706247210749/10002] Path -> Partition: file:/data/users/nzhang/reviews/0.6/branch-0.6/build/ql/scratchdir/hive_2010-08-22_14-17-10_442_2893644706247210749/10002 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 columns.types int: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/dest1 name dest1 serialization.ddl struct dest1 { i32 key, string value} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe transient_lastDdlTime 1282511830 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 int: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/dest1 name dest1 serialization.ddl struct dest1 { i32 key, string value} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe transient_lastDdlTime 1282511830 serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: dest1 name: dest1 PREHOOK: query: INSERT OVERWRITE TABLE dest1 SELECT s.* FROM srcbucket TABLESAMPLE (BUCKET 1 OUT OF 4 on key) s WHERE s.key > 100 PREHOOK: type: QUERY PREHOOK: Input: default@srcbucket PREHOOK: Output: default@dest1 POSTHOOK: query: INSERT OVERWRITE TABLE dest1 SELECT s.* FROM srcbucket TABLESAMPLE (BUCKET 1 OUT OF 4 on key) s WHERE s.key > 100 POSTHOOK: type: QUERY POSTHOOK: Input: default@srcbucket POSTHOOK: Output: default@dest1 POSTHOOK: Lineage: dest1.key SIMPLE [(srcbucket)s.FieldSchema(name:key, type:int, comment:null), ] POSTHOOK: Lineage: dest1.value SIMPLE [(srcbucket)s.FieldSchema(name:value, type:string, comment:null), ] PREHOOK: query: SELECT dest1.* FROM dest1 PREHOOK: type: QUERY PREHOOK: Input: default@dest1 PREHOOK: Output: file:/tmp/nzhang/hive_2010-08-22_14-17-13_989_4736960841457816218/10000 POSTHOOK: query: SELECT dest1.* FROM dest1 POSTHOOK: type: QUERY POSTHOOK: Input: default@dest1 POSTHOOK: Output: file:/tmp/nzhang/hive_2010-08-22_14-17-13_989_4736960841457816218/10000 POSTHOOK: Lineage: dest1.key SIMPLE [(srcbucket)s.FieldSchema(name:key, type:int, comment:null), ] POSTHOOK: Lineage: dest1.value SIMPLE [(srcbucket)s.FieldSchema(name:value, type:string, comment:null), ] 468 val_469 272 val_273 448 val_449 440 val_441 296 val_297 428 val_429 356 val_357 128 val_129 240 val_241 408 val_409 476 val_477 424 val_425 488 val_489 128 val_129 468 val_469 224 val_225 344 val_345 304 val_305 264 val_265 196 val_197 492 val_493 360 val_361 492 val_493 376 val_377 120 val_121 132 val_133 388 val_389 184 val_185 284 val_285 352 val_353 328 val_329 480 val_481 480 val_481 392 val_393 476 val_477 252 val_253 264 val_265 336 val_337 340 val_341 484 val_485 260 val_261 164 val_165 104 val_105 140 val_141 212 val_213 308 val_309 416 val_417 364 val_365 168 val_169 384 val_385 324 val_325 404 val_405 260 val_261 328 val_329 404 val_405 384 val_385 116 val_117 104 val_105 132 val_133 192 val_193 356 val_357 352 val_353 160 val_161 412 val_413 204 val_205 216 val_217 196 val_197 384 val_385 404 val_405 300 val_301 268 val_269 392 val_393 104 val_105 436 val_437 156 val_157 172 val_173 244 val_245 284 val_285 164 val_165 136 val_137 432 val_433 496 val_497 144 val_145 408 val_409 152 val_153 348 val_349 292 val_293 152 val_153 256 val_257 292 val_293 412 val_413 156 val_157 228 val_229 248 val_249 244 val_245 276 val_277 196 val_197 440 val_441 308 val_309 468 val_469 152 val_153 300 val_301 244 val_245 484 val_484 224 val_224 128 val_128 152 val_152 252 val_252 292 val_292 208 val_208 396 val_396 128 val_128 316 val_316 280 val_280 208 val_208 356 val_356 192 val_192 176 val_176 216 val_216 176 val_176 332 val_332 180 val_180 284 val_284 260 val_260 404 val_404 384 val_384 272 val_272 348 val_348 208 val_208 348 val_348 172 val_172 496 val_496 468 val_468 120 val_120 404 val_404 436 val_436 156 val_156 468 val_468 308 val_308 196 val_196 288 val_288 316 val_316 364 val_364 224 val_224 392 val_392 272 val_272 452 val_452 396 val_396 336 val_336 168 val_168 472 val_472 160 val_160 492 val_492 228 val_228 468 val_468 368 val_368 296 val_296 216 val_216 344 val_344 116 val_116 256 val_256 480 val_480 288 val_288 244 val_244 128 val_128 432 val_432 316 val_316 280 val_280 104 val_104 348 val_348 424 val_424 396 val_396 164 val_164 164 val_164 424 val_424 480 val_480 104 val_104 200 val_200 360 val_360 248 val_248 444 val_444 120 val_120 468 val_468 460 val_460 480 val_480 136 val_136 172 val_172 384 val_384 256 val_256 384 val_384 492 val_492 348 val_348 344 val_344 448 val_448 152 val_152 348 val_348 400 val_400 200 val_200