PREHOOK: query: CREATE TABLE bucket3_1(key int, value string) partitioned by (ds string) CLUSTERED BY (key) INTO 2 BUCKETS PREHOOK: type: CREATETABLE POSTHOOK: query: CREATE TABLE bucket3_1(key int, value string) partitioned by (ds string) CLUSTERED BY (key) INTO 2 BUCKETS POSTHOOK: type: CREATETABLE POSTHOOK: Output: default@bucket3_1 PREHOOK: query: explain extended insert overwrite table bucket3_1 partition (ds='1') select * from src PREHOOK: type: QUERY POSTHOOK: query: explain extended insert overwrite table bucket3_1 partition (ds='1') select * from src POSTHOOK: type: QUERY ABSTRACT SYNTAX TREE: (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME src))) (TOK_INSERT (TOK_DESTINATION (TOK_TAB (TOK_TABNAME bucket3_1) (TOK_PARTSPEC (TOK_PARTVAL ds '1')))) (TOK_SELECT (TOK_SELEXPR TOK_ALLCOLREF)))) STAGE DEPENDENCIES: Stage-1 is a root stage Stage-0 depends on stages: Stage-1 Stage-2 depends on stages: Stage-0 STAGE PLANS: Stage: Stage-1 Map Reduce Alias -> Map Operator Tree: src TableScan alias: src GatherStats: false Select Operator expressions: expr: key type: string expr: value type: string outputColumnNames: _col0, _col1 Reduce Output Operator sort order: Map-reduce partition columns: expr: UDFToInteger(_col0) type: int tag: -1 value expressions: expr: _col0 type: string expr: _col1 type: string Path -> Alias: #### A masked pattern was here #### Path -> Partition: #### A masked pattern was here #### 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 #### A masked pattern was here #### name default.src numFiles 1 numPartitions 0 numRows 0 rawDataSize 0 serialization.ddl struct src { string key, string value} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe totalSize 5812 #### 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 string:string #### A masked pattern was here #### name default.src numFiles 1 numPartitions 0 numRows 0 rawDataSize 0 serialization.ddl struct src { string key, string value} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe totalSize 5812 #### A masked pattern was here #### serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.src name: default.src Truncated Path -> Alias: /src [src] Needs Tagging: false Reduce Operator Tree: Extract Select Operator expressions: expr: UDFToInteger(_col0) type: int expr: _col1 type: string outputColumnNames: _col0, _col1 File Output Operator compressed: false GlobalTableId: 1 #### A masked pattern was here #### NumFilesPerFileSink: 2 Static Partition Specification: ds=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 2 bucket_field_name key columns key,value columns.types int:string #### A masked pattern was here #### name default.bucket3_1 partition_columns ds serialization.ddl struct bucket3_1 { 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.bucket3_1 TotalFiles: 2 GatherStats: true MultiFileSpray: true Stage: Stage-0 Move Operator tables: partition: ds 1 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 2 bucket_field_name key columns key,value columns.types int:string #### A masked pattern was here #### name default.bucket3_1 partition_columns ds serialization.ddl struct bucket3_1 { 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.bucket3_1 #### A masked pattern was here #### Stage: Stage-2 Stats-Aggr Operator #### A masked pattern was here #### PREHOOK: query: insert overwrite table bucket3_1 partition (ds='1') select * from src PREHOOK: type: QUERY PREHOOK: Input: default@src PREHOOK: Output: default@bucket3_1@ds=1 POSTHOOK: query: insert overwrite table bucket3_1 partition (ds='1') select * from src POSTHOOK: type: QUERY POSTHOOK: Input: default@src POSTHOOK: Output: default@bucket3_1@ds=1 POSTHOOK: Lineage: bucket3_1 PARTITION(ds=1).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] POSTHOOK: Lineage: bucket3_1 PARTITION(ds=1).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] PREHOOK: query: insert overwrite table bucket3_1 partition (ds='2') select * from src PREHOOK: type: QUERY PREHOOK: Input: default@src PREHOOK: Output: default@bucket3_1@ds=2 POSTHOOK: query: insert overwrite table bucket3_1 partition (ds='2') select * from src POSTHOOK: type: QUERY POSTHOOK: Input: default@src POSTHOOK: Output: default@bucket3_1@ds=2 POSTHOOK: Lineage: bucket3_1 PARTITION(ds=1).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] POSTHOOK: Lineage: bucket3_1 PARTITION(ds=1).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] POSTHOOK: Lineage: bucket3_1 PARTITION(ds=2).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] POSTHOOK: Lineage: bucket3_1 PARTITION(ds=2).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] PREHOOK: query: explain select * from bucket3_1 tablesample (bucket 1 out of 2) s where ds = '1' order by key PREHOOK: type: QUERY POSTHOOK: query: explain select * from bucket3_1 tablesample (bucket 1 out of 2) s where ds = '1' order by key POSTHOOK: type: QUERY POSTHOOK: Lineage: bucket3_1 PARTITION(ds=1).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] POSTHOOK: Lineage: bucket3_1 PARTITION(ds=1).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] POSTHOOK: Lineage: bucket3_1 PARTITION(ds=2).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] POSTHOOK: Lineage: bucket3_1 PARTITION(ds=2).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] ABSTRACT SYNTAX TREE: (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME bucket3_1) (TOK_TABLEBUCKETSAMPLE 1 2) s)) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR TOK_ALLCOLREF)) (TOK_WHERE (= (TOK_TABLE_OR_COL ds) '1')) (TOK_ORDERBY (TOK_TABSORTCOLNAMEASC (TOK_TABLE_OR_COL key))))) STAGE DEPENDENCIES: Stage-1 is a root stage Stage-0 is a root stage STAGE PLANS: Stage: Stage-1 Map Reduce Alias -> Map Operator Tree: s TableScan alias: s Filter Operator predicate: expr: (((hash(key) & 2147483647) % 2) = 0) type: boolean Select Operator expressions: expr: key type: int expr: value type: string expr: ds type: string outputColumnNames: _col0, _col1, _col2 Reduce Output Operator key expressions: expr: _col0 type: int sort order: + tag: -1 value expressions: expr: _col0 type: int expr: _col1 type: string expr: _col2 type: string Reduce Operator Tree: Extract File Output Operator compressed: false GlobalTableId: 0 table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat Stage: Stage-0 Fetch Operator limit: -1 PREHOOK: query: select * from bucket3_1 tablesample (bucket 1 out of 2) s where ds = '1' order by key PREHOOK: type: QUERY PREHOOK: Input: default@bucket3_1 PREHOOK: Input: default@bucket3_1@ds=1 #### A masked pattern was here #### POSTHOOK: query: select * from bucket3_1 tablesample (bucket 1 out of 2) s where ds = '1' order by key POSTHOOK: type: QUERY POSTHOOK: Input: default@bucket3_1 POSTHOOK: Input: default@bucket3_1@ds=1 #### A masked pattern was here #### POSTHOOK: Lineage: bucket3_1 PARTITION(ds=1).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] POSTHOOK: Lineage: bucket3_1 PARTITION(ds=1).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] POSTHOOK: Lineage: bucket3_1 PARTITION(ds=2).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] POSTHOOK: Lineage: bucket3_1 PARTITION(ds=2).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] 0 val_0 1 0 val_0 1 0 val_0 1 2 val_2 1 4 val_4 1 8 val_8 1 10 val_10 1 12 val_12 1 12 val_12 1 18 val_18 1 18 val_18 1 20 val_20 1 24 val_24 1 24 val_24 1 26 val_26 1 26 val_26 1 28 val_28 1 30 val_30 1 34 val_34 1 42 val_42 1 42 val_42 1 44 val_44 1 54 val_54 1 58 val_58 1 58 val_58 1 64 val_64 1 66 val_66 1 70 val_70 1 70 val_70 1 70 val_70 1 72 val_72 1 72 val_72 1 74 val_74 1 76 val_76 1 76 val_76 1 78 val_78 1 80 val_80 1 82 val_82 1 84 val_84 1 84 val_84 1 86 val_86 1 90 val_90 1 90 val_90 1 90 val_90 1 92 val_92 1 96 val_96 1 98 val_98 1 98 val_98 1 100 val_100 1 100 val_100 1 104 val_104 1 104 val_104 1 114 val_114 1 116 val_116 1 118 val_118 1 118 val_118 1 120 val_120 1 120 val_120 1 126 val_126 1 128 val_128 1 128 val_128 1 128 val_128 1 134 val_134 1 134 val_134 1 136 val_136 1 138 val_138 1 138 val_138 1 138 val_138 1 138 val_138 1 146 val_146 1 146 val_146 1 150 val_150 1 152 val_152 1 152 val_152 1 156 val_156 1 158 val_158 1 160 val_160 1 162 val_162 1 164 val_164 1 164 val_164 1 166 val_166 1 168 val_168 1 170 val_170 1 172 val_172 1 172 val_172 1 174 val_174 1 174 val_174 1 176 val_176 1 176 val_176 1 178 val_178 1 180 val_180 1 186 val_186 1 190 val_190 1 192 val_192 1 194 val_194 1 196 val_196 1 200 val_200 1 200 val_200 1 202 val_202 1 208 val_208 1 208 val_208 1 208 val_208 1 214 val_214 1 216 val_216 1 216 val_216 1 218 val_218 1 222 val_222 1 224 val_224 1 224 val_224 1 226 val_226 1 228 val_228 1 230 val_230 1 230 val_230 1 230 val_230 1 230 val_230 1 230 val_230 1 238 val_238 1 238 val_238 1 242 val_242 1 242 val_242 1 244 val_244 1 248 val_248 1 252 val_252 1 256 val_256 1 256 val_256 1 258 val_258 1 260 val_260 1 262 val_262 1 266 val_266 1 272 val_272 1 272 val_272 1 274 val_274 1 278 val_278 1 278 val_278 1 280 val_280 1 280 val_280 1 282 val_282 1 282 val_282 1 284 val_284 1 286 val_286 1 288 val_288 1 288 val_288 1 292 val_292 1 296 val_296 1 298 val_298 1 298 val_298 1 298 val_298 1 302 val_302 1 306 val_306 1 308 val_308 1 310 val_310 1 316 val_316 1 316 val_316 1 316 val_316 1 318 val_318 1 318 val_318 1 318 val_318 1 322 val_322 1 322 val_322 1 332 val_332 1 336 val_336 1 338 val_338 1 342 val_342 1 342 val_342 1 344 val_344 1 344 val_344 1 348 val_348 1 348 val_348 1 348 val_348 1 348 val_348 1 348 val_348 1 356 val_356 1 360 val_360 1 362 val_362 1 364 val_364 1 366 val_366 1 368 val_368 1 374 val_374 1 378 val_378 1 382 val_382 1 382 val_382 1 384 val_384 1 384 val_384 1 384 val_384 1 386 val_386 1 392 val_392 1 394 val_394 1 396 val_396 1 396 val_396 1 396 val_396 1 400 val_400 1 402 val_402 1 404 val_404 1 404 val_404 1 406 val_406 1 406 val_406 1 406 val_406 1 406 val_406 1 414 val_414 1 414 val_414 1 418 val_418 1 424 val_424 1 424 val_424 1 430 val_430 1 430 val_430 1 430 val_430 1 432 val_432 1 436 val_436 1 438 val_438 1 438 val_438 1 438 val_438 1 444 val_444 1 446 val_446 1 448 val_448 1 452 val_452 1 454 val_454 1 454 val_454 1 454 val_454 1 458 val_458 1 458 val_458 1 460 val_460 1 462 val_462 1 462 val_462 1 466 val_466 1 466 val_466 1 466 val_466 1 468 val_468 1 468 val_468 1 468 val_468 1 468 val_468 1 470 val_470 1 472 val_472 1 478 val_478 1 478 val_478 1 480 val_480 1 480 val_480 1 480 val_480 1 482 val_482 1 484 val_484 1 490 val_490 1 492 val_492 1 492 val_492 1 494 val_494 1 496 val_496 1 498 val_498 1 498 val_498 1 498 val_498 1