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: -- bucket column is the same as table sample -- No need for sample filter EXPLAIN EXTENDED INSERT OVERWRITE TABLE dest1 SELECT s.* FROM srcbucket TABLESAMPLE (BUCKET 1 OUT OF 2 on key) s PREHOOK: type: QUERY POSTHOOK: query: -- bucket column is the same as table sample -- No need for sample filter EXPLAIN EXTENDED INSERT OVERWRITE TABLE dest1 SELECT s.* FROM srcbucket TABLESAMPLE (BUCKET 1 OUT OF 2 on key) s POSTHOOK: type: QUERY ABSTRACT SYNTAX TREE: (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME srcbucket) (TOK_TABLEBUCKETSAMPLE 1 2 (TOK_TABLE_OR_COL key)) s)) (TOK_INSERT (TOK_DESTINATION (TOK_TAB (TOK_TABNAME dest1))) (TOK_SELECT (TOK_SELEXPR (TOK_ALLCOLREF (TOK_TABNAME s)))))) 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: s TableScan alias: s GatherStats: false Filter Operator isSamplingPred: true predicate: expr: (((hash(key) & 2147483647) % 2) = 0) type: boolean Select Operator expressions: expr: key type: int expr: value type: string outputColumnNames: _col0, _col1 File Output Operator compressed: false GlobalTableId: 1 #### A masked pattern was here #### NumFilesPerFileSink: 1 #### A masked pattern was here #### 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 #### A masked pattern was here #### name default.dest1 serialization.ddl struct dest1 { i32 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.dest1 TotalFiles: 1 GatherStats: true MultiFileSpray: false Path -> Alias: #### A masked pattern was here #### Path -> Partition: #### A masked pattern was here #### 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 #### A masked pattern was here #### name default.srcbucket numFiles 2 numPartitions 0 numRows 0 rawDataSize 0 serialization.ddl struct srcbucket { i32 key, string value} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe totalSize 11603 #### 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 2 bucket_field_name key columns key,value columns.types int:string #### A masked pattern was here #### name default.srcbucket numFiles 2 numPartitions 0 numRows 0 rawDataSize 0 serialization.ddl struct srcbucket { i32 key, string value} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe totalSize 11603 #### A masked pattern was here #### serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.srcbucket name: default.srcbucket Truncated Path -> Alias: /srcbucket/srcbucket0.txt [s] Stage: Stage-7 Conditional Operator Stage: Stage-4 Move Operator files: hdfs directory: true #### A masked pattern was here #### Stage: Stage-0 Move Operator tables: replace: true #### A masked pattern was here #### 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 #### A masked pattern was here #### name default.dest1 serialization.ddl struct dest1 { i32 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.dest1 #### A masked pattern was here #### Stage: Stage-2 Stats-Aggr Operator #### A masked pattern was here #### Stage: Stage-3 Map Reduce Alias -> Map Operator Tree: #### A masked pattern was here #### File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### 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 #### A masked pattern was here #### name default.dest1 serialization.ddl struct dest1 { i32 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.dest1 TotalFiles: 1 GatherStats: false MultiFileSpray: false Path -> Alias: #### A masked pattern was here #### Path -> Partition: #### A masked pattern was here #### 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 columns.types int:string #### A masked pattern was here #### name default.dest1 serialization.ddl struct dest1 { i32 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 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 #### A masked pattern was here #### name default.dest1 serialization.ddl struct dest1 { i32 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.dest1 name: default.dest1 Truncated Path -> Alias: #### A masked pattern was here #### Stage: Stage-5 Map Reduce Alias -> Map Operator Tree: #### A masked pattern was here #### File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### 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 #### A masked pattern was here #### name default.dest1 serialization.ddl struct dest1 { i32 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.dest1 TotalFiles: 1 GatherStats: false MultiFileSpray: false Path -> Alias: #### A masked pattern was here #### Path -> Partition: #### A masked pattern was here #### 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 columns.types int:string #### A masked pattern was here #### name default.dest1 serialization.ddl struct dest1 { i32 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 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 #### A masked pattern was here #### name default.dest1 serialization.ddl struct dest1 { i32 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.dest1 name: default.dest1 Truncated Path -> Alias: #### A masked pattern was here #### Stage: Stage-6 Move Operator files: hdfs directory: true #### A masked pattern was here #### PREHOOK: query: INSERT OVERWRITE TABLE dest1 SELECT s.* FROM srcbucket TABLESAMPLE (BUCKET 1 OUT OF 2 on key) s 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 2 on key) s 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 #### A masked pattern was here #### POSTHOOK: query: SELECT dest1.* FROM dest1 POSTHOOK: type: QUERY POSTHOOK: Input: default@dest1 #### A masked pattern was here #### 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), ] 474 val_475 62 val_63 468 val_469 272 val_273 448 val_449 246 val_247 440 val_441 278 val_279 296 val_297 428 val_429 126 val_127 106 val_107 356 val_357 490 val_491 402 val_403 128 val_129 10 val_11 226 val_227 110 val_111 0 val_1 240 val_241 286 val_287 408 val_409 476 val_477 482 val_483 48 val_49 424 val_425 226 val_227 494 val_495 488 val_489 94 val_95 50 val_51 402 val_403 128 val_129 468 val_469 314 val_315 224 val_225 344 val_345 4 val_5 206 val_207 114 val_115 56 val_57 114 val_115 254 val_255 390 val_391 304 val_305 264 val_265 196 val_197 238 val_239 20 val_21 492 val_493 82 val_83 58 val_59 86 val_87 438 val_439 360 val_361 222 val_223 42 val_43 338 val_339 68 val_69 16 val_17 492 val_493 376 val_377 120 val_121 306 val_307 426 val_427 132 val_133 446 val_447 386 val_387 388 val_389 184 val_185 284 val_285 246 val_247 262 val_263 122 val_123 438 val_439 390 val_391 352 val_353 226 val_227 328 val_329 382 val_383 342 val_343 480 val_481 102 val_103 480 val_481 318 val_319 392 val_393 476 val_477 258 val_259 174 val_175 252 val_253 114 val_115 264 val_265 48 val_49 336 val_337 340 val_341 390 val_391 484 val_485 6 val_7 260 val_261 2 val_3 170 val_171 164 val_165 118 val_119 310 val_311 104 val_105 80 val_81 326 val_327 450 val_451 140 val_141 212 val_213 308 val_309 30 val_31 358 val_359 416 val_417 42 val_43 386 val_387 454 val_455 364 val_365 20 val_21 52 val_53 40 val_41 8 val_9 168 val_169 384 val_385 324 val_325 310 val_311 206 val_207 404 val_405 206 val_207 226 val_227 262 val_263 260 val_261 328 val_329 322 val_323 122 val_123 404 val_405 384 val_385 76 val_77 116 val_117 42 val_43 104 val_105 406 val_407 32 val_33 132 val_133 192 val_193 58 val_59 70 val_71 356 val_357 352 val_353 52 val_53 330 val_331 138 val_139 160 val_161 454 val_455 76 val_77 174 val_175 412 val_413 16 val_17 204 val_205 126 val_127 274 val_275 374 val_375 494 val_495 216 val_217 470 val_471 196 val_197 302 val_303 450 val_451 12 val_13 398 val_399 334 val_335 384 val_385 60 val_61 442 val_443 52 val_53 404 val_405 446 val_447 300 val_301 0 val_1 268 val_269 392 val_393 104 val_105 436 val_437 156 val_157 118 val_119 172 val_173 244 val_245 6 val_7 284 val_285 164 val_165 136 val_137 462 val_463 432 val_433 496 val_497 144 val_145 408 val_409 152 val_153 382 val_383 348 val_349 122 val_123 292 val_293 182 val_183 474 val_475 310 val_311 52 val_53 486 val_487 152 val_153 378 val_379 414 val_415 256 val_257 292 val_293 412 val_413 40 val_41 478 val_479 178 val_179 100 val_101 156 val_157 228 val_229 22 val_23 248 val_249 402 val_403 62 val_63 162 val_163 244 val_245 276 val_277 46 val_47 78 val_79 134 val_135 196 val_197 410 val_411 82 val_83 440 val_441 100 val_101 308 val_309 430 val_431 468 val_469 152 val_153 138 val_139 76 val_77 300 val_301 478 val_479 118 val_119 178 val_179 242 val_243 244 val_245 238 val_238 86 val_86 278 val_278 98 val_98 484 val_484 150 val_150 224 val_224 66 val_66 128 val_128 146 val_146 406 val_406 374 val_374 152 val_152 82 val_82 166 val_166 430 val_430 252 val_252 292 val_292 338 val_338 446 val_446 394 val_394 482 val_482 174 val_174 494 val_494 466 val_466 208 val_208 174 val_174 396 val_396 162 val_162 266 val_266 342 val_342 0 val_0 128 val_128 316 val_316 302 val_302 438 val_438 170 val_170 20 val_20 378 val_378 92 val_92 72 val_72 4 val_4 280 val_280 208 val_208 356 val_356 382 val_382 498 val_498 386 val_386 192 val_192 286 val_286 176 val_176 54 val_54 138 val_138 216 val_216 430 val_430 278 val_278 176 val_176 318 val_318 332 val_332 180 val_180 284 val_284 12 val_12 230 val_230 260 val_260 404 val_404 384 val_384 272 val_272 138 val_138 84 val_84 348 val_348 466 val_466 58 val_58 8 val_8 230 val_230 208 val_208 348 val_348 24 val_24 172 val_172 42 val_42 158 val_158 496 val_496 0 val_0 322 val_322 468 val_468 454 val_454 100 val_100 298 val_298 418 val_418 96 val_96 26 val_26 230 val_230 120 val_120 404 val_404 436 val_436 156 val_156 468 val_468 308 val_308 196 val_196 288 val_288 98 val_98 282 val_282 318 val_318 318 val_318 470 val_470 316 val_316 0 val_0 490 val_490 364 val_364 118 val_118 134 val_134 282 val_282 138 val_138 238 val_238 118 val_118 72 val_72 90 val_90 10 val_10 306 val_306 224 val_224 242 val_242 392 val_392 272 val_272 242 val_242 452 val_452 226 val_226 402 val_402 396 val_396 58 val_58 336 val_336 168 val_168 34 val_34 472 val_472 322 val_322 498 val_498 160 val_160 42 val_42 430 val_430 458 val_458 78 val_78 76 val_76 492 val_492 218 val_218 228 val_228 138 val_138 30 val_30 64 val_64 468 val_468 76 val_76 74 val_74 342 val_342 230 val_230 368 val_368 296 val_296 216 val_216 344 val_344 274 val_274 116 val_116 256 val_256 70 val_70 480 val_480 288 val_288 244 val_244 438 val_438 128 val_128 432 val_432 202 val_202 316 val_316 280 val_280 2 val_2 80 val_80 44 val_44 104 val_104 466 val_466 366 val_366 406 val_406 190 val_190 406 val_406 114 val_114 258 val_258 90 val_90 262 val_262 348 val_348 424 val_424 12 val_12 396 val_396 164 val_164 454 val_454 478 val_478 298 val_298 164 val_164 424 val_424 382 val_382 70 val_70 480 val_480 24 val_24 104 val_104 70 val_70 438 val_438 414 val_414 200 val_200 360 val_360 248 val_248 444 val_444 120 val_120 230 val_230 478 val_478 178 val_178 468 val_468 310 val_310 460 val_460 480 val_480 136 val_136 172 val_172 214 val_214 462 val_462 406 val_406 454 val_454 384 val_384 256 val_256 26 val_26 134 val_134 384 val_384 18 val_18 462 val_462 492 val_492 100 val_100 298 val_298 498 val_498 146 val_146 458 val_458 362 val_362 186 val_186 348 val_348 18 val_18 344 val_344 84 val_84 28 val_28 448 val_448 152 val_152 348 val_348 194 val_194 414 val_414 222 val_222 126 val_126 90 val_90 400 val_400 200 val_200