/tags/release-0.0.0-rc0/hive/external/ql/src/test/results/clientpositive/bucket_groupby.q.out
text | 1849 lines | 1780 code | 69 blank | 0 comment | 0 complexity | 03ae5c4b271adb9683bda8460a989aca MD5 | raw file
1PREHOOK: query: create table clustergroupby(key string, value string) partitioned by(ds string) 2PREHOOK: type: CREATETABLE 3POSTHOOK: query: create table clustergroupby(key string, value string) partitioned by(ds string) 4POSTHOOK: type: CREATETABLE 5POSTHOOK: Output: default@clustergroupby 6PREHOOK: query: describe extended clustergroupby 7PREHOOK: type: DESCTABLE 8POSTHOOK: query: describe extended clustergroupby 9POSTHOOK: type: DESCTABLE 10key string 11value string 12ds string 13 14Detailed Table Information Table(tableName:clustergroupby, dbName:default, owner:sdong, createTime:1297330264, lastAccessTime:0, retention:0, sd:StorageDescriptor(cols:[FieldSchema(name:key, type:string, comment:null), FieldSchema(name:value, type:string, comment:null), FieldSchema(name:ds, type:string, comment:null)], location:pfile:/data/users/sdong/www/open-source-hive1/build/ql/test/data/warehouse/clustergroupby, inputFormat:org.apache.hadoop.mapred.TextInputFormat, outputFormat:org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat, compressed:false, numBuckets:-1, serdeInfo:SerDeInfo(name:null, serializationLib:org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe, parameters:{serialization.format=1}), bucketCols:[], sortCols:[], parameters:{}), partitionKeys:[FieldSchema(name:ds, type:string, comment:null)], parameters:{transient_lastDdlTime=1297330264}, viewOriginalText:null, viewExpandedText:null, tableType:MANAGED_TABLE) 15PREHOOK: query: insert overwrite table clustergroupby partition (ds='100') select key, value from src sort by key 16PREHOOK: type: QUERY 17PREHOOK: Input: default@src 18PREHOOK: Output: default@clustergroupby@ds=100 19POSTHOOK: query: insert overwrite table clustergroupby partition (ds='100') select key, value from src sort by key 20POSTHOOK: type: QUERY 21POSTHOOK: Input: default@src 22POSTHOOK: Output: default@clustergroupby@ds=100 23POSTHOOK: Lineage: clustergroupby PARTITION(ds=100).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] 24POSTHOOK: Lineage: clustergroupby PARTITION(ds=100).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] 25PREHOOK: query: explain 26select key, count(1) from clustergroupby where ds='100' group by key limit 10 27PREHOOK: type: QUERY 28POSTHOOK: query: explain 29select key, count(1) from clustergroupby where ds='100' group by key limit 10 30POSTHOOK: type: QUERY 31POSTHOOK: Lineage: clustergroupby PARTITION(ds=100).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] 32POSTHOOK: Lineage: clustergroupby PARTITION(ds=100).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] 33ABSTRACT SYNTAX TREE: 34 (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME clustergroupby))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_TABLE_OR_COL key)) (TOK_SELEXPR (TOK_FUNCTION count 1))) (TOK_WHERE (= (TOK_TABLE_OR_COL ds) '100')) (TOK_GROUPBY (TOK_TABLE_OR_COL key)) (TOK_LIMIT 10))) 35 36STAGE DEPENDENCIES: 37 Stage-1 is a root stage 38 Stage-0 is a root stage 39 40STAGE PLANS: 41 Stage: Stage-1 42 Map Reduce 43 Alias -> Map Operator Tree: 44 clustergroupby 45 TableScan 46 alias: clustergroupby 47 Filter Operator 48 predicate: 49 expr: (ds = '100') 50 type: boolean 51 Select Operator 52 expressions: 53 expr: key 54 type: string 55 outputColumnNames: key 56 Group By Operator 57 aggregations: 58 expr: count(1) 59 bucketGroup: false 60 keys: 61 expr: key 62 type: string 63 mode: hash 64 outputColumnNames: _col0, _col1 65 Reduce Output Operator 66 key expressions: 67 expr: _col0 68 type: string 69 sort order: + 70 Map-reduce partition columns: 71 expr: _col0 72 type: string 73 tag: -1 74 value expressions: 75 expr: _col1 76 type: bigint 77 Reduce Operator Tree: 78 Group By Operator 79 aggregations: 80 expr: count(VALUE._col0) 81 bucketGroup: false 82 keys: 83 expr: KEY._col0 84 type: string 85 mode: mergepartial 86 outputColumnNames: _col0, _col1 87 Select Operator 88 expressions: 89 expr: _col0 90 type: string 91 expr: _col1 92 type: bigint 93 outputColumnNames: _col0, _col1 94 Limit 95 File Output Operator 96 compressed: false 97 GlobalTableId: 0 98 table: 99 input format: org.apache.hadoop.mapred.TextInputFormat 100 output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat 101 102 Stage: Stage-0 103 Fetch Operator 104 limit: 10 105 106 107PREHOOK: query: select key, count(1) from clustergroupby where ds='100' group by key limit 10 108PREHOOK: type: QUERY 109PREHOOK: Input: default@clustergroupby@ds=100 110PREHOOK: Output: file:/tmp/sdong/hive_2011-02-10_01-31-09_571_4785800205176349032/-mr-10000 111POSTHOOK: query: select key, count(1) from clustergroupby where ds='100' group by key limit 10 112POSTHOOK: type: QUERY 113POSTHOOK: Input: default@clustergroupby@ds=100 114POSTHOOK: Output: file:/tmp/sdong/hive_2011-02-10_01-31-09_571_4785800205176349032/-mr-10000 115POSTHOOK: Lineage: clustergroupby PARTITION(ds=100).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] 116POSTHOOK: Lineage: clustergroupby PARTITION(ds=100).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] 1170 3 11810 1 119100 2 120103 2 121104 2 122105 1 12311 1 124111 1 125113 2 126114 1 127PREHOOK: query: alter table clustergroupby clustered by (key) into 1 buckets 128PREHOOK: type: ALTERTABLE_CLUSTER_SORT 129PREHOOK: Input: default@clustergroupby 130PREHOOK: Output: default@clustergroupby 131POSTHOOK: query: alter table clustergroupby clustered by (key) into 1 buckets 132POSTHOOK: type: ALTERTABLE_CLUSTER_SORT 133POSTHOOK: Input: default@clustergroupby 134POSTHOOK: Output: default@clustergroupby 135POSTHOOK: Lineage: clustergroupby PARTITION(ds=100).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] 136POSTHOOK: Lineage: clustergroupby PARTITION(ds=100).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] 137PREHOOK: query: describe extended clustergroupby 138PREHOOK: type: DESCTABLE 139POSTHOOK: query: describe extended clustergroupby 140POSTHOOK: type: DESCTABLE 141POSTHOOK: Lineage: clustergroupby PARTITION(ds=100).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] 142POSTHOOK: Lineage: clustergroupby PARTITION(ds=100).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] 143key string 144value string 145ds string 146 147Detailed Table Information Table(tableName:clustergroupby, dbName:default, owner:sdong, createTime:1297330264, lastAccessTime:0, retention:0, sd:StorageDescriptor(cols:[FieldSchema(name:key, type:string, comment:null), FieldSchema(name:value, type:string, comment:null), FieldSchema(name:ds, type:string, comment:null)], location:pfile:/data/users/sdong/www/open-source-hive1/build/ql/test/data/warehouse/clustergroupby, inputFormat:org.apache.hadoop.mapred.TextInputFormat, outputFormat:org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat, compressed:false, numBuckets:1, serdeInfo:SerDeInfo(name:null, serializationLib:org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe, parameters:{serialization.format=1}), bucketCols:[key], sortCols:[], parameters:{}), partitionKeys:[FieldSchema(name:ds, type:string, comment:null)], parameters:{numPartitions=1, numFiles=1, last_modified_by=sdong, last_modified_time=1297330273, transient_lastDdlTime=1297330273, numRows=500, totalSize=5812}, viewOriginalText:null, viewExpandedText:null, tableType:MANAGED_TABLE) 148PREHOOK: query: insert overwrite table clustergroupby partition (ds='101') select key, value from src distribute by key 149PREHOOK: type: QUERY 150PREHOOK: Input: default@src 151PREHOOK: Output: default@clustergroupby@ds=101 152POSTHOOK: query: insert overwrite table clustergroupby partition (ds='101') select key, value from src distribute by key 153POSTHOOK: type: QUERY 154POSTHOOK: Input: default@src 155POSTHOOK: Output: default@clustergroupby@ds=101 156POSTHOOK: Lineage: clustergroupby PARTITION(ds=100).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] 157POSTHOOK: Lineage: clustergroupby PARTITION(ds=100).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] 158POSTHOOK: Lineage: clustergroupby PARTITION(ds=101).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] 159POSTHOOK: Lineage: clustergroupby PARTITION(ds=101).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] 160PREHOOK: query: --normal-- 161explain 162select key, count(1) from clustergroupby where ds='101' group by key limit 10 163PREHOOK: type: QUERY 164POSTHOOK: query: --normal-- 165explain 166select key, count(1) from clustergroupby where ds='101' group by key limit 10 167POSTHOOK: type: QUERY 168POSTHOOK: Lineage: clustergroupby PARTITION(ds=100).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] 169POSTHOOK: Lineage: clustergroupby PARTITION(ds=100).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] 170POSTHOOK: Lineage: clustergroupby PARTITION(ds=101).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] 171POSTHOOK: Lineage: clustergroupby PARTITION(ds=101).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] 172ABSTRACT SYNTAX TREE: 173 (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME clustergroupby))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_TABLE_OR_COL key)) (TOK_SELEXPR (TOK_FUNCTION count 1))) (TOK_WHERE (= (TOK_TABLE_OR_COL ds) '101')) (TOK_GROUPBY (TOK_TABLE_OR_COL key)) (TOK_LIMIT 10))) 174 175STAGE DEPENDENCIES: 176 Stage-1 is a root stage 177 Stage-0 is a root stage 178 179STAGE PLANS: 180 Stage: Stage-1 181 Map Reduce 182 Alias -> Map Operator Tree: 183 clustergroupby 184 TableScan 185 alias: clustergroupby 186 Filter Operator 187 predicate: 188 expr: (ds = '101') 189 type: boolean 190 Select Operator 191 expressions: 192 expr: key 193 type: string 194 outputColumnNames: key 195 Group By Operator 196 aggregations: 197 expr: count(1) 198 bucketGroup: true 199 keys: 200 expr: key 201 type: string 202 mode: hash 203 outputColumnNames: _col0, _col1 204 Reduce Output Operator 205 key expressions: 206 expr: _col0 207 type: string 208 sort order: + 209 Map-reduce partition columns: 210 expr: _col0 211 type: string 212 tag: -1 213 value expressions: 214 expr: _col1 215 type: bigint 216 Reduce Operator Tree: 217 Group By Operator 218 aggregations: 219 expr: count(VALUE._col0) 220 bucketGroup: false 221 keys: 222 expr: KEY._col0 223 type: string 224 mode: mergepartial 225 outputColumnNames: _col0, _col1 226 Select Operator 227 expressions: 228 expr: _col0 229 type: string 230 expr: _col1 231 type: bigint 232 outputColumnNames: _col0, _col1 233 Limit 234 File Output Operator 235 compressed: false 236 GlobalTableId: 0 237 table: 238 input format: org.apache.hadoop.mapred.TextInputFormat 239 output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat 240 241 Stage: Stage-0 242 Fetch Operator 243 limit: 10 244 245 246PREHOOK: query: select key, count(1) from clustergroupby where ds='101' group by key limit 10 247PREHOOK: type: QUERY 248PREHOOK: Input: default@clustergroupby@ds=101 249PREHOOK: Output: file:/tmp/sdong/hive_2011-02-10_01-31-18_109_2103582873568530260/-mr-10000 250POSTHOOK: query: select key, count(1) from clustergroupby where ds='101' group by key limit 10 251POSTHOOK: type: QUERY 252POSTHOOK: Input: default@clustergroupby@ds=101 253POSTHOOK: Output: file:/tmp/sdong/hive_2011-02-10_01-31-18_109_2103582873568530260/-mr-10000 254POSTHOOK: Lineage: clustergroupby PARTITION(ds=100).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] 255POSTHOOK: Lineage: clustergroupby PARTITION(ds=100).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] 256POSTHOOK: Lineage: clustergroupby PARTITION(ds=101).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] 257POSTHOOK: Lineage: clustergroupby PARTITION(ds=101).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] 2580 3 25910 1 260100 2 261103 2 262104 2 263105 1 26411 1 265111 1 266113 2 267114 1 268PREHOOK: query: --function-- 269explain 270select length(key), count(1) from clustergroupby where ds='101' group by length(key) limit 10 271PREHOOK: type: QUERY 272POSTHOOK: query: --function-- 273explain 274select length(key), count(1) from clustergroupby where ds='101' group by length(key) limit 10 275POSTHOOK: type: QUERY 276POSTHOOK: Lineage: clustergroupby PARTITION(ds=100).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] 277POSTHOOK: Lineage: clustergroupby PARTITION(ds=100).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] 278POSTHOOK: Lineage: clustergroupby PARTITION(ds=101).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] 279POSTHOOK: Lineage: clustergroupby PARTITION(ds=101).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] 280ABSTRACT SYNTAX TREE: 281 (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME clustergroupby))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_FUNCTION length (TOK_TABLE_OR_COL key))) (TOK_SELEXPR (TOK_FUNCTION count 1))) (TOK_WHERE (= (TOK_TABLE_OR_COL ds) '101')) (TOK_GROUPBY (TOK_FUNCTION length (TOK_TABLE_OR_COL key))) (TOK_LIMIT 10))) 282 283STAGE DEPENDENCIES: 284 Stage-1 is a root stage 285 Stage-0 is a root stage 286 287STAGE PLANS: 288 Stage: Stage-1 289 Map Reduce 290 Alias -> Map Operator Tree: 291 clustergroupby 292 TableScan 293 alias: clustergroupby 294 Filter Operator 295 predicate: 296 expr: (ds = '101') 297 type: boolean 298 Select Operator 299 expressions: 300 expr: key 301 type: string 302 outputColumnNames: key 303 Group By Operator 304 aggregations: 305 expr: count(1) 306 bucketGroup: true 307 keys: 308 expr: length(key) 309 type: int 310 mode: hash 311 outputColumnNames: _col0, _col1 312 Reduce Output Operator 313 key expressions: 314 expr: _col0 315 type: int 316 sort order: + 317 Map-reduce partition columns: 318 expr: _col0 319 type: int 320 tag: -1 321 value expressions: 322 expr: _col1 323 type: bigint 324 Reduce Operator Tree: 325 Group By Operator 326 aggregations: 327 expr: count(VALUE._col0) 328 bucketGroup: false 329 keys: 330 expr: KEY._col0 331 type: int 332 mode: mergepartial 333 outputColumnNames: _col0, _col1 334 Select Operator 335 expressions: 336 expr: _col0 337 type: int 338 expr: _col1 339 type: bigint 340 outputColumnNames: _col0, _col1 341 Limit 342 File Output Operator 343 compressed: false 344 GlobalTableId: 0 345 table: 346 input format: org.apache.hadoop.mapred.TextInputFormat 347 output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat 348 349 Stage: Stage-0 350 Fetch Operator 351 limit: 10 352 353 354PREHOOK: query: select length(key), count(1) from clustergroupby where ds='101' group by length(key) limit 10 355PREHOOK: type: QUERY 356PREHOOK: Input: default@clustergroupby@ds=101 357PREHOOK: Output: file:/tmp/sdong/hive_2011-02-10_01-31-21_764_2109263664206229253/-mr-10000 358POSTHOOK: query: select length(key), count(1) from clustergroupby where ds='101' group by length(key) limit 10 359POSTHOOK: type: QUERY 360POSTHOOK: Input: default@clustergroupby@ds=101 361POSTHOOK: Output: file:/tmp/sdong/hive_2011-02-10_01-31-21_764_2109263664206229253/-mr-10000 362POSTHOOK: Lineage: clustergroupby PARTITION(ds=100).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] 363POSTHOOK: Lineage: clustergroupby PARTITION(ds=100).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] 364POSTHOOK: Lineage: clustergroupby PARTITION(ds=101).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] 365POSTHOOK: Lineage: clustergroupby PARTITION(ds=101).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] 3661 10 3672 74 3683 416 369PREHOOK: query: explain 370select abs(length(key)), count(1) from clustergroupby where ds='101' group by abs(length(key)) limit 10 371PREHOOK: type: QUERY 372POSTHOOK: query: explain 373select abs(length(key)), count(1) from clustergroupby where ds='101' group by abs(length(key)) limit 10 374POSTHOOK: type: QUERY 375POSTHOOK: Lineage: clustergroupby PARTITION(ds=100).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] 376POSTHOOK: Lineage: clustergroupby PARTITION(ds=100).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] 377POSTHOOK: Lineage: clustergroupby PARTITION(ds=101).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] 378POSTHOOK: Lineage: clustergroupby PARTITION(ds=101).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] 379ABSTRACT SYNTAX TREE: 380 (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME clustergroupby))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_FUNCTION abs (TOK_FUNCTION length (TOK_TABLE_OR_COL key)))) (TOK_SELEXPR (TOK_FUNCTION count 1))) (TOK_WHERE (= (TOK_TABLE_OR_COL ds) '101')) (TOK_GROUPBY (TOK_FUNCTION abs (TOK_FUNCTION length (TOK_TABLE_OR_COL key)))) (TOK_LIMIT 10))) 381 382STAGE DEPENDENCIES: 383 Stage-1 is a root stage 384 Stage-0 is a root stage 385 386STAGE PLANS: 387 Stage: Stage-1 388 Map Reduce 389 Alias -> Map Operator Tree: 390 clustergroupby 391 TableScan 392 alias: clustergroupby 393 Filter Operator 394 predicate: 395 expr: (ds = '101') 396 type: boolean 397 Select Operator 398 expressions: 399 expr: key 400 type: string 401 outputColumnNames: key 402 Group By Operator 403 aggregations: 404 expr: count(1) 405 bucketGroup: true 406 keys: 407 expr: abs(length(key)) 408 type: int 409 mode: hash 410 outputColumnNames: _col0, _col1 411 Reduce Output Operator 412 key expressions: 413 expr: _col0 414 type: int 415 sort order: + 416 Map-reduce partition columns: 417 expr: _col0 418 type: int 419 tag: -1 420 value expressions: 421 expr: _col1 422 type: bigint 423 Reduce Operator Tree: 424 Group By Operator 425 aggregations: 426 expr: count(VALUE._col0) 427 bucketGroup: false 428 keys: 429 expr: KEY._col0 430 type: int 431 mode: mergepartial 432 outputColumnNames: _col0, _col1 433 Select Operator 434 expressions: 435 expr: _col0 436 type: int 437 expr: _col1 438 type: bigint 439 outputColumnNames: _col0, _col1 440 Limit 441 File Output Operator 442 compressed: false 443 GlobalTableId: 0 444 table: 445 input format: org.apache.hadoop.mapred.TextInputFormat 446 output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat 447 448 Stage: Stage-0 449 Fetch Operator 450 limit: 10 451 452 453PREHOOK: query: select abs(length(key)), count(1) from clustergroupby where ds='101' group by abs(length(key)) limit 10 454PREHOOK: type: QUERY 455PREHOOK: Input: default@clustergroupby@ds=101 456PREHOOK: Output: file:/tmp/sdong/hive_2011-02-10_01-31-26_110_671172006622360339/-mr-10000 457POSTHOOK: query: select abs(length(key)), count(1) from clustergroupby where ds='101' group by abs(length(key)) limit 10 458POSTHOOK: type: QUERY 459POSTHOOK: Input: default@clustergroupby@ds=101 460POSTHOOK: Output: file:/tmp/sdong/hive_2011-02-10_01-31-26_110_671172006622360339/-mr-10000 461POSTHOOK: Lineage: clustergroupby PARTITION(ds=100).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] 462POSTHOOK: Lineage: clustergroupby PARTITION(ds=100).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] 463POSTHOOK: Lineage: clustergroupby PARTITION(ds=101).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] 464POSTHOOK: Lineage: clustergroupby PARTITION(ds=101).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] 4651 10 4662 74 4673 416 468PREHOOK: query: --constant-- 469explain 470select key, count(1) from clustergroupby where ds='101' group by key,3 limit 10 471PREHOOK: type: QUERY 472POSTHOOK: query: --constant-- 473explain 474select key, count(1) from clustergroupby where ds='101' group by key,3 limit 10 475POSTHOOK: type: QUERY 476POSTHOOK: Lineage: clustergroupby PARTITION(ds=100).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] 477POSTHOOK: Lineage: clustergroupby PARTITION(ds=100).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] 478POSTHOOK: Lineage: clustergroupby PARTITION(ds=101).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] 479POSTHOOK: Lineage: clustergroupby PARTITION(ds=101).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] 480ABSTRACT SYNTAX TREE: 481 (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME clustergroupby))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_TABLE_OR_COL key)) (TOK_SELEXPR (TOK_FUNCTION count 1))) (TOK_WHERE (= (TOK_TABLE_OR_COL ds) '101')) (TOK_GROUPBY (TOK_TABLE_OR_COL key) 3) (TOK_LIMIT 10))) 482 483STAGE DEPENDENCIES: 484 Stage-1 is a root stage 485 Stage-0 is a root stage 486 487STAGE PLANS: 488 Stage: Stage-1 489 Map Reduce 490 Alias -> Map Operator Tree: 491 clustergroupby 492 TableScan 493 alias: clustergroupby 494 Filter Operator 495 predicate: 496 expr: (ds = '101') 497 type: boolean 498 Select Operator 499 expressions: 500 expr: key 501 type: string 502 outputColumnNames: key 503 Group By Operator 504 aggregations: 505 expr: count(1) 506 bucketGroup: true 507 keys: 508 expr: key 509 type: string 510 expr: 3 511 type: int 512 mode: hash 513 outputColumnNames: _col0, _col1, _col2 514 Reduce Output Operator 515 key expressions: 516 expr: _col0 517 type: string 518 expr: _col1 519 type: int 520 sort order: ++ 521 Map-reduce partition columns: 522 expr: _col0 523 type: string 524 expr: _col1 525 type: int 526 tag: -1 527 value expressions: 528 expr: _col2 529 type: bigint 530 Reduce Operator Tree: 531 Group By Operator 532 aggregations: 533 expr: count(VALUE._col0) 534 bucketGroup: false 535 keys: 536 expr: KEY._col0 537 type: string 538 expr: KEY._col1 539 type: int 540 mode: mergepartial 541 outputColumnNames: _col0, _col1, _col2 542 Select Operator 543 expressions: 544 expr: _col0 545 type: string 546 expr: _col2 547 type: bigint 548 outputColumnNames: _col0, _col1 549 Limit 550 File Output Operator 551 compressed: false 552 GlobalTableId: 0 553 table: 554 input format: org.apache.hadoop.mapred.TextInputFormat 555 output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat 556 557 Stage: Stage-0 558 Fetch Operator 559 limit: 10 560 561 562PREHOOK: query: select key, count(1) from clustergroupby where ds='101' group by key,3 limit 10 563PREHOOK: type: QUERY 564PREHOOK: Input: default@clustergroupby@ds=101 565PREHOOK: Output: file:/tmp/sdong/hive_2011-02-10_01-31-29_764_2397216315877695624/-mr-10000 566POSTHOOK: query: select key, count(1) from clustergroupby where ds='101' group by key,3 limit 10 567POSTHOOK: type: QUERY 568POSTHOOK: Input: default@clustergroupby@ds=101 569POSTHOOK: Output: file:/tmp/sdong/hive_2011-02-10_01-31-29_764_2397216315877695624/-mr-10000 570POSTHOOK: Lineage: clustergroupby PARTITION(ds=100).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] 571POSTHOOK: Lineage: clustergroupby PARTITION(ds=100).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] 572POSTHOOK: Lineage: clustergroupby PARTITION(ds=101).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] 573POSTHOOK: Lineage: clustergroupby PARTITION(ds=101).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] 5740 3 57510 1 576100 2 577103 2 578104 2 579105 1 58011 1 581111 1 582113 2 583114 1 584PREHOOK: query: --subquery-- 585explain 586select key, count(1) from (select value as key, key as value from clustergroupby where ds='101')subq group by key limit 10 587PREHOOK: type: QUERY 588POSTHOOK: query: --subquery-- 589explain 590select key, count(1) from (select value as key, key as value from clustergroupby where ds='101')subq group by key limit 10 591POSTHOOK: type: QUERY 592POSTHOOK: Lineage: clustergroupby PARTITION(ds=100).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] 593POSTHOOK: Lineage: clustergroupby PARTITION(ds=100).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] 594POSTHOOK: Lineage: clustergroupby PARTITION(ds=101).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] 595POSTHOOK: Lineage: clustergroupby PARTITION(ds=101).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] 596ABSTRACT SYNTAX TREE: 597 (TOK_QUERY (TOK_FROM (TOK_SUBQUERY (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME clustergroupby))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_TABLE_OR_COL value) key) (TOK_SELEXPR (TOK_TABLE_OR_COL key) value)) (TOK_WHERE (= (TOK_TABLE_OR_COL ds) '101')))) subq)) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_TABLE_OR_COL key)) (TOK_SELEXPR (TOK_FUNCTION count 1))) (TOK_GROUPBY (TOK_TABLE_OR_COL key)) (TOK_LIMIT 10))) 598 599STAGE DEPENDENCIES: 600 Stage-1 is a root stage 601 Stage-0 is a root stage 602 603STAGE PLANS: 604 Stage: Stage-1 605 Map Reduce 606 Alias -> Map Operator Tree: 607 subq:clustergroupby 608 TableScan 609 alias: clustergroupby 610 Filter Operator 611 predicate: 612 expr: (ds = '101') 613 type: boolean 614 Select Operator 615 expressions: 616 expr: value 617 type: string 618 outputColumnNames: _col0 619 Select Operator 620 expressions: 621 expr: _col0 622 type: string 623 outputColumnNames: _col0 624 Group By Operator 625 aggregations: 626 expr: count(1) 627 bucketGroup: false 628 keys: 629 expr: _col0 630 type: string 631 mode: hash 632 outputColumnNames: _col0, _col1 633 Reduce Output Operator 634 key expressions: 635 expr: _col0 636 type: string 637 sort order: + 638 Map-reduce partition columns: 639 expr: _col0 640 type: string 641 tag: -1 642 value expressions: 643 expr: _col1 644 type: bigint 645 Reduce Operator Tree: 646 Group By Operator 647 aggregations: 648 expr: count(VALUE._col0) 649 bucketGroup: false 650 keys: 651 expr: KEY._col0 652 type: string 653 mode: mergepartial 654 outputColumnNames: _col0, _col1 655 Select Operator 656 expressions: 657 expr: _col0 658 type: string 659 expr: _col1 660 type: bigint 661 outputColumnNames: _col0, _col1 662 Limit 663 File Output Operator 664 compressed: false 665 GlobalTableId: 0 666 table: 667 input format: org.apache.hadoop.mapred.TextInputFormat 668 output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat 669 670 Stage: Stage-0 671 Fetch Operator 672 limit: 10 673 674 675PREHOOK: query: select key, count(1) from (select value as key, key as value from clustergroupby where ds='101')subq group by key limit 10 676PREHOOK: type: QUERY 677PREHOOK: Input: default@clustergroupby@ds=101 678PREHOOK: Output: file:/tmp/sdong/hive_2011-02-10_01-31-33_487_1431386357774433664/-mr-10000 679POSTHOOK: query: select key, count(1) from (select value as key, key as value from clustergroupby where ds='101')subq group by key limit 10 680POSTHOOK: type: QUERY 681POSTHOOK: Input: default@clustergroupby@ds=101 682POSTHOOK: Output: file:/tmp/sdong/hive_2011-02-10_01-31-33_487_1431386357774433664/-mr-10000 683POSTHOOK: Lineage: clustergroupby PARTITION(ds=100).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] 684POSTHOOK: Lineage: clustergroupby PARTITION(ds=100).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] 685POSTHOOK: Lineage: clustergroupby PARTITION(ds=101).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] 686POSTHOOK: Lineage: clustergroupby PARTITION(ds=101).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] 687val_0 3 688val_10 1 689val_100 2 690val_103 2 691val_104 2 692val_105 1 693val_11 1 694val_111 1 695val_113 2 696val_114 1 697PREHOOK: query: explain 698select key, count(1) from clustergroupby group by key 699PREHOOK: type: QUERY 700POSTHOOK: query: explain 701select key, count(1) from clustergroupby group by key 702POSTHOOK: type: QUERY 703POSTHOOK: Lineage: clustergroupby PARTITION(ds=100).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] 704POSTHOOK: Lineage: clustergroupby PARTITION(ds=100).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] 705POSTHOOK: Lineage: clustergroupby PARTITION(ds=101).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] 706POSTHOOK: Lineage: clustergroupby PARTITION(ds=101).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] 707ABSTRACT SYNTAX TREE: 708 (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME clustergroupby))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_TABLE_OR_COL key)) (TOK_SELEXPR (TOK_FUNCTION count 1))) (TOK_GROUPBY (TOK_TABLE_OR_COL key)))) 709 710STAGE DEPENDENCIES: 711 Stage-1 is a root stage 712 Stage-0 is a root stage 713 714STAGE PLANS: 715 Stage: Stage-1 716 Map Reduce 717 Alias -> Map Operator Tree: 718 clustergroupby 719 TableScan 720 alias: clustergroupby 721 Select Operator 722 expressions: 723 expr: key 724 type: string 725 outputColumnNames: key 726 Group By Operator 727 aggregations: 728 expr: count(1) 729 bucketGroup: false 730 keys: 731 expr: key 732 type: string 733 mode: hash 734 outputColumnNames: _col0, _col1 735 Reduce Output Operator 736 key expressions: 737 expr: _col0 738 type: string 739 sort order: + 740 Map-reduce partition columns: 741 expr: _col0 742 type: string 743 tag: -1 744 value expressions: 745 expr: _col1 746 type: bigint 747 Reduce Operator Tree: 748 Group By Operator 749 aggregations: 750 expr: count(VALUE._col0) 751 bucketGroup: false 752 keys: 753 expr: KEY._col0 754 type: string 755 mode: mergepartial 756 outputColumnNames: _col0, _col1 757 Select Operator 758 expressions: 759 expr: _col0 760 type: string 761 expr: _col1 762 type: bigint 763 outputColumnNames: _col0, _col1 764 File Output Operator 765 compressed: false 766 GlobalTableId: 0 767 table: 768 input format: org.apache.hadoop.mapred.TextInputFormat 769 output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat 770 771 Stage: Stage-0 772 Fetch Operator 773 limit: -1 774 775 776PREHOOK: query: select key, count(1) from clustergroupby group by key 777PREHOOK: type: QUERY 778PREHOOK: Input: default@clustergroupby@ds=100 779PREHOOK: Input: default@clustergroupby@ds=101 780PREHOOK: Output: file:/tmp/sdong/hive_2011-02-10_01-31-37_126_6695656183965608913/-mr-10000 781POSTHOOK: query: select key, count(1) from clustergroupby group by key 782POSTHOOK: type: QUERY 783POSTHOOK: Input: default@clustergroupby@ds=100 784POSTHOOK: Input: default@clustergroupby@ds=101 785POSTHOOK: Output: file:/tmp/sdong/hive_2011-02-10_01-31-37_126_6695656183965608913/-mr-10000 786POSTHOOK: Lineage: clustergroupby PARTITION(ds=100).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] 787POSTHOOK: Lineage: clustergroupby PARTITION(ds=100).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] 788POSTHOOK: Lineage: clustergroupby PARTITION(ds=101).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] 789POSTHOOK: Lineage: clustergroupby PARTITION(ds=101).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] 7900 6 79110 2 792100 4 793103 4 794104 4 795105 2 79611 2 797111 2 798113 4 799114 2 800116 2 801118 4 802119 6 80312 4 804120 4 805125 4 806126 2 807128 6 808129 4 809131 2 810133 2 811134 4 812136 2 813137 4 814138 8 815143 2 816145 2 817146 4 818149 4 81915 4 820150 2 821152 4 822153 2 823155 2 824156 2 825157 2 826158 2 827160 2 828162 2 829163 2 830164 4 831165 4 832166 2 833167 6 834168 2 835169 8 83617 2 837170 2 838172 4 839174 4 840175 4 841176 4 842177 2 843178 2 844179 4 84518 4 846180 2 847181 2 848183 2 849186 2 850187 6 851189 2 85219 2 853190 2 854191 4 855192 2 856193 6 857194 2 858195 4 859196 2 860197 4 861199 6 8622 2 86320 2 864200 4 865201 2 866202 2 867203 4 868205 4 869207 4 870208 6 871209 4 872213 4 873214 2 874216 4 875217 4 876218 2 877219 4 878221 4 879222 2 880223 4 881224 4 882226 2 883228 2 884229 4 885230 10 886233 4 887235 2 888237 4 889238 4 890239 4 89124 4 892241 2 893242 4 894244 2 895247 2 896248 2 897249 2 898252 2 899255 4 900256 4 901257 2 902258 2 90326 4 904260 2 905262 2 906263 2 907265 4 908266 2 90927 2 910272 4 911273 6 912274 2 913275 2 914277 8 915278 4 91628 2 917280 4 918281 4 919282 4 920283 2 921284 2 922285 2 923286 2 924287 2 925288 4 926289 2 927291 2 928292 2 929296 2 930298 6 93130 2 932302 2 933305 2 934306 2 935307 4 936308 2 937309 4 938310 2 939311 6 940315 2 941316 6 942317 4 943318 6 944321 4 945322 4 946323 2 947325 4 948327 6 94933 2 950331 4 951332 2 952333 4 953335 2 954336 2 955338 2 956339 2 95734 2 958341 2 959342 4 960344 4 961345 2 962348 10 96335 6 964351 2 965353 4 966356 2 967360 2 968362 2 969364 2 970365 2 971366 2 972367 4 973368 2 974369 6 97537 4 976373 2 977374 2 978375 2 979377 2 980378 2 981379 2 982382 4 983384 6 984386 2 985389 2 986392 2 987393 2 988394 2 989395 4 990396 6 991397 4 992399 4 9934 2 994400 2 995401 10 996402 2 997403 6 998404 4 999406 8 1000407 2 1001409 6 100241 2 1003411 2 1004413 4 1005414 4 1006417 6 1007418 2 1008419 2 100942 4 1010421 2 1011424 4 1012427 2 1013429 4 101443 2 1015430 6 1016431 6 1017432 2 1018435 2 1019436 2 1020437 2 1021438 6 1022439 4 102344 2 1024443 2 1025444 2 1026446 2 1027448 2 1028449 2 1029452 2 1030453 2 1031454 6 1032455 2 1033457 2 1034458 4 1035459 4 1036460 2 1037462 4 1038463 4 1039466 6 1040467 2 1041468 8 1042469 10 104347 2 1044470 2 1045472 2 1046475 2 1047477 2 1048478 4 1049479 2 1050480 6 1051481 2 1052482 2 1053483 2 1054484 2 1055485 2 1056487 2 1057489 8 1058490 2 1059491 2 1060492 4 1061493 2 1062494 2 1063495 2 1064496 2 1065497 2 1066498 6 10675 6 106851 4 106953 2 107054 2 107157 2 107258 4 107364 2 107465 2 107566 2 107667 4 107769 2 107870 6 107972 4 108074 2 108176 4 108277 2 108378 2 10848 2 108580 2 108682 2 108783 4 108884 4 108985 2 109086 2 109187 2 10929 2 109390 6 109492 2 109595 4 109696 2 109797 4 109898 4 1099PREHOOK: query: explain 1100select key, count(1) from clustergroupby group by key, 3 1101PREHOOK: type: QUERY 1102POSTHOOK: query: explain 1103select key, count(1) from clustergroupby group by key, 3 1104POSTHOOK: type: QUERY 1105POSTHOOK: Lineage: clustergroupby PARTITION(ds=100).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] 1106POSTHOOK: Lineage: clustergroupby PARTITION(ds=100).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] 1107POSTHOOK: Lineage: clustergroupby PARTITION(ds=101).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] 1108POSTHOOK: Lineage: clustergroupby PARTITION(ds=101).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] 1109ABSTRACT SYNTAX TREE: 1110 (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME clustergroupby))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_TABLE_OR_COL key)) (TOK_SELEXPR (TOK_FUNCTION count 1))) (TOK_GROUPBY (TOK_TABLE_OR_COL key) 3))) 1111 1112STAGE DEPENDENCIES: 1113 Stage-1 is a root stage 1114 Stage-0 is a root stage 1115 1116STAGE PLANS: 1117 Stage: Stage-1 1118 Map Reduce 1119 Alias -> Map Operator Tree: 1120 clustergroupby 1121 TableScan 1122 alias: clustergroupby 1123 Select Operator 1124 expressions: 1125 expr: key 1126 type: string 1127 outputColumnNames: key 1128 Group By Operator 1129 aggregations: 1130 expr: count(1) 1131 bucketGroup: false 1132 keys: 1133 expr: key 1134 type: string 1135 expr: 3 1136 type: int 1137 mode: hash 1138 outputColumnNames: _col0, _col1, _col2 1139 Reduce Output Operator 1140 key expressions: 1141 expr: _col0 1142 type: string 1143 expr: _col1 1144 type: int 1145 sort order: ++ 1146 Map-reduce partition columns: 1147 expr: _col0 1148 type: string 1149 expr: _col1 1150 type: int 1151 tag: -1 1152 value expressions: 1153 expr: _col2 1154 type: bigint 1155 Reduce Operator Tree: 1156 Group By Operator 1157 aggregations: 1158 expr: count(VALUE._col0) 1159 bucketGroup: false 1160 keys: 1161 expr: KEY._col0 1162 type: string 1163 expr: KEY._col1 1164 type: int 1165 mode: mergepartial 1166 outputColumnNames: _col0, _col1, _col2 1167 Select Operator 1168 expressions: 1169 expr: _col0 1170 type: string 1171 expr: _col2 1172 type: bigint 1173 outputColumnNames: _col0, _col1 1174 File Output Operator 1175 compressed: false 1176 GlobalTableId: 0 1177 table: 1178 input format: org.apache.hadoop.mapred.TextInputFormat 1179 output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat 1180 1181 Stage: Stage-0 1182 Fetch Operator 1183 limit: -1 1184 1185 1186PREHOOK: query: --sort columns-- 1187alter table clustergroupby clustered by (value) sorted by (key, value) into 1 buckets 1188PREHOOK: type: ALTERTABLE_CLUSTER_SORT 1189PREHOOK: Input: default@clustergroupby 1190PREHOOK: Output: default@clustergroupby 1191POSTHOOK: query: --sort columns-- 1192alter table clustergroupby clustered by (value) sorted by (key, value) into 1 buckets 1193POSTHOOK: type: ALTERTABLE_CLUSTER_SORT 1194POSTHOOK: Input: default@clustergroupby 1195POSTHOOK: Output: default@clustergroupby 1196POSTHOOK: Lineage: clustergroupby PARTITION(ds=100).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] 1197POSTHOOK: Lineage: clustergroupby PARTITION(ds=100).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] 1198POSTHOOK: Lineage: clustergroupby PARTITION(ds=101).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] 1199POSTHOOK: Lineage: clustergroupby PARTITION(ds=101).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] 1200PREHOOK: query: describe extended clustergroupby 1201PREHOOK: type: DESCTABLE 1202POSTHOOK: query: describe extended clustergroupby 1203POSTHOOK: type: DESCTABLE 1204POSTHOOK: Lineage: clustergroupby PARTITION(ds=100).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] 1205POSTHOOK: Lineage: clustergroupby PARTITION(ds=100).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] 1206POSTHOOK: Lineage: clustergroupby PARTITION(ds=101).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] 1207POSTHOOK: Lineage: clustergroupby PARTITION(ds=101).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] 1208key string 1209value string 1210ds string 1211 1212Detailed Table Information Table(tableName:clustergroupby, dbName:default, owner:sdong, createTime:1297330264, lastAccessTime:0, retention:0, sd:StorageDescriptor(cols:[FieldSchema(name:key, type:string, comment:null), FieldSchema(name:value, type:string, comment:null), FieldSchema(name:ds, type:string, comment:null)], location:pfile:/data/users/sdong/www/open-source-hive1/build/ql/test/data/warehouse/clustergroupby, inputFormat:org.apache.hadoop.mapred.TextInputFormat, outputFormat:org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat, compressed:false, numBuckets:1, serdeInfo:SerDeInfo(name:null, serializationLib:org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe, parameters:{serialization.format=1}), bucketCols:[value], sortCols:[Order(col:key, order:1), Order(col:value, order:1)], parameters:{}), partitionKeys:[FieldSchema(name:ds, type:string, comment:null)], parameters:{numPartitions=2, numFiles=2, last_modified_by=sdong, last_modified_time=1297330300, transient_lastDdlTime=1297330300, numRows=1000, totalSize=11624}, viewOriginalText:null, viewExpandedText:null, tableType:MANAGED_TABLE) 1213PREHOOK: query: insert overwrite table clustergroupby partition (ds='102') select key, value from src distribute by value sort by key, value 1214PREHOOK: type: QUERY 1215PREHOOK: Input: default@src 1216PREHOOK: Output: default@clustergroupby@ds=102 1217POSTHOOK: query: insert overwrite table clustergroupby partition (ds='102') select key, value from src distribute by value sort by key, value 1218POSTHOOK: type: QUERY 1219POSTHOOK: Input: default@src 1220POSTHOOK: Output: default@clustergroupby@ds=102 1221POSTHOOK: Lineage: clustergroupby PARTITION(ds=100).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] 1222POSTHOOK: Lineage: clustergroupby PARTITION(ds=100).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] 1223POSTHOOK: Lineage: clustergroupby PARTITION(ds=101).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] 1224POSTHOOK: Lineage: clustergroupby PARTITION(ds=101).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] 1225POSTHOOK: Lineage: clustergroupby PARTITION(ds=102).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] 1226POSTHOOK: Lineage: clustergroupby PARTITION(ds=102).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] 1227PREHOOK: query: explain 1228select key, count(1) from clustergroupby where ds='102' group by key limit 10 1229PREHOOK: type: QUERY 1230POSTHOOK: query: explain 1231select key, count(1) from clustergroupby where ds='102' group by key limit 10 1232POSTHOOK: type: QUERY 1233POSTHOOK: Lineage: clustergroupby PARTITION(ds=100).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] 1234POSTHOOK: Lineage: clustergroupby PARTITION(ds=100).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] 1235POSTHOOK: Lineage: clustergroupby PARTITION(ds=101).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] 1236POSTHOOK: Lineage: clustergroupby PARTITION(ds=101).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] 1237POSTHOOK: Lineage: clustergroupby PARTITION(ds=102).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] 1238POSTHOOK: Lineage: clustergroupby PARTITION(ds=102).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] 1239ABSTRACT SYNTAX TREE: 1240 (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME clustergroupby))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_TABLE_OR_COL key)) (TOK_SELEXPR (TOK_FUNCTION count 1))) (TOK_WHERE (= (TOK_TABLE_OR_COL ds) '102')) (TOK_GROUPBY (TOK_TABLE_OR_COL key)) (TOK_LIMIT 10))) 1241 1242STAGE DEPENDENCIES: 1243 Stage-1 is a root stage 1244 Stage-0 is a root stage 1245 1246STAGE PLANS: 1247 Stage: Stage-1 1248 Map Reduce 1249 Alias -> Map Operator Tree: 1250 clustergroupby 1251 TableScan 1252 alias: clustergroupby 1253 Filter Operator 1254 predicate: 1255 expr: (ds = '102') 1256 type: boolean 1257 Select Operator 1258 expressions: 1259 expr: key 1260 type: string 1261 outputColumnNames: key 1262 Group By Operator 1263 aggregations: 1264 expr: count(1) 1265 bucketGroup: true 1266 keys: 1267 expr: key 1268 type: string 1269 mode: hash 1270 outputColumnNames: _col0, _col1 1271 Reduce Output Operator 1272 key expressions: 1273 expr: _col0 1274 type: string 1275 sort order: + 1276 Map-reduce partition columns: 1277 expr: _col0 1278 type: string 1279 tag: -1 1280 value expressions: 1281 expr: _col1 1282 type: bigint 1283 Reduce Operator Tree: 1284 Group By Operator 1285 aggregations: 1286 expr: count(VALUE._col0) 1287 bucketGroup: false 1288 keys: 1289 expr: KEY._col0 1290 type: string 1291 mode: mergepartial 1292 outputColumnNames: _col0, _col1 1293 Select Operator 1294 expressions: 1295 expr: _col0 1296 type: string 1297 expr: _col1 1298 type: bigint 1299 outputColumnNames: _col0, _col1 1300 Limit 1301 File Output Operator 1302 compressed: false 1303 GlobalTableId: 0 1304 table: 1305 input format: org.apache.hadoop.mapred.TextInputFormat 1306 output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat 1307 1308 Stage: Stage-0 1309 Fetch Operator 1310 limit: 10 1311 1312 1313PREHOOK: query: select key, count(1) from clustergroupby where ds='102' group by key limit 10 1314PREHOOK: type: QUERY 1315PREHOOK: Input: default@clustergroupby@ds=102 1316PREHOOK: Output: file:/tmp/sdong/hive_2011-02-10_01-31-45_956_2691533777800757183/-mr-10000 1317POSTHOOK: query: select key, count(1) from clustergroupby where ds='102' group by key limit 10 1318POSTHOOK: type: QUERY 1319POSTHOOK: Input: default@clustergroupby@ds=102 1320POSTHOOK: Output: file:/tmp/sdong/hive_2011-02-10_01-31-45_956_2691533777800757183/-mr-10000 1321POSTHOOK: Lineage: clustergroupby PARTITION(ds=100).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] 1322POSTHOOK: Lineage: clustergroupby PARTITION(ds=100).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] 1323POSTHOOK: Lineage: clustergroupby PARTITION(ds=101).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] 1324POSTHOOK: Lineage: clustergroupby PARTITION(ds=101).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] 1325POSTHOOK: Lineage: clustergroupby PARTITION(ds=102).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] 1326POSTHOOK: Lineage: clustergroupby PARTITION(ds=102).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] 13270 3 132810 1 1329100 2 1330103 2 1331104 2 1332105 1 133311 1 1334111 1 1335113 2 1336114 1 1337PREHOOK: query: explain 1338select value, count(1) from clustergroupby where ds='102' group by value limit 10 1339PREHOOK: type: QUERY 1340POSTHOOK: query: explain 1341select value, count(1) from clustergroupby where ds='102' group by value limit 10 1342POSTHOOK: type: QUERY 1343POSTHOOK: Lineage: clustergroupby PARTITION(ds=100).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] 1344POSTHOOK: Lineage: clustergroupby PARTITION(ds=100).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] 1345POSTHOOK: Lineage: clustergroupby PARTITION(ds=101).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] 1346POSTHOOK: Lineage: clustergroupby PARTITION(ds=101).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] 1347POSTHOOK: Lineage: clustergroupby PARTITION(ds=102).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] 1348POSTHOOK: Lineage: clustergroupby PARTITION(ds=102).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] 1349ABSTRACT SYNTAX TREE: 1350 (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME clustergroupby))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_TABLE_OR_COL value)) (TOK_SELEXPR (TOK_FUNCTION count 1))) (TOK_WHERE (= (TOK_TABLE_OR_COL ds) '102')) (TOK_GROUPBY (TOK_TABLE_OR_COL value)) (TOK_LIMIT 10))) 1351 1352STAGE DEPENDENCIES: 1353 Stage-1 is a root stage 1354 Stage-0 is a root stage 1355 1356STAGE PLANS: 1357 Stage: Stage-1 1358 Map Reduce 1359 Alias -> Map Operator Tree: 1360 clustergroupby 1361 TableScan 1362 alias: clustergroupby 1363 Filter Operator 1364 predicate: 1365 expr: (ds = '102') 1366 type: boolean 1367 Select Operator 1368 expressions: 1369 expr: value 1370 type: string 1371 outputColumnNames: value 1372 Group By Operator 1373 aggregations: 1374 expr: count(1) 1375 bucketGroup: false 1376 keys: 1377 expr: value 1378 type: string 1379 mode: hash 1380 outputColumnNames: _col0, _col1 1381 Reduce Output Operator 1382 key expressions: 1383 expr: _col0 1384 type: string 1385 sort order: + 1386 Map-reduce partition columns: 1387 expr: _col0 1388 type: string 1389 tag: -1 1390 value expressions: 1391 expr: _col1 1392 type: bigint 1393 Reduce Operator Tree: 1394 Group By Operator 1395 aggregations: 1396 expr: count(VALUE._col0) 1397 bucketGroup: false 1398 keys: 1399 expr: KEY._col0 1400 type: string 1401 mode: mergepartial 1402 outputColumnNames: _col0, _col1 1403 Select Operator 1404 expressions: 1405 expr: _col0 1406 type: string 1407 expr: _col1 1408 type: bigint 1409 outputColumnNames: _col0, _col1 1410 Limit 1411 File Output Operator 1412 compressed: false 1413 GlobalTableId: 0 1414 table: 1415 input format: org.apache.hadoop.mapred.TextInputFormat 1416 output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat 1417 1418 Stage: Stage-0 1419 Fetch Operator 1420 limit: 10 1421 1422 1423PREHOOK: query: select value, count(1) from clustergroupby where ds='102' group by value limit 10 1424PREHOOK: type: QUERY 1425PREHOOK: Input: default@clustergroupby@ds=102 1426PREHOOK: Output: file:/tmp/sdong/hive_2011-02-10_01-31-49_553_601799080303065238/-mr-10000 1427POSTHOOK: query: select value, count(1) from clustergroupby where ds='102' group by value limit 10 1428POSTHOOK: type: QUERY 1429POSTHOOK: Input: default@clustergroupby@ds=102 1430POSTHOOK: Output: file:/tmp/sdong/hive_2011-02-10_01-31-49_553_601799080303065238/-mr-10000 1431POSTHOOK: Lineage: clustergroupby PARTITION(ds=100).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] 1432POSTHOOK: Lineage: clustergroupby PARTITION(ds=100).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] 1433POSTHOOK: Lineage: clustergroupby PARTITION(ds=101).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] 1434POSTHOOK: Lineage: clustergroupby PARTITION(ds=101).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] 1435POSTHOOK: Lineage: clustergroupby PARTITION(ds=102).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] 1436POSTHOOK: Lineage: clustergroupby PARTITION(ds=102).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] 1437val_0 3 1438val_10 1 1439val_100 2 1440val_103 2 1441val_104 2 1442val_105 1 1443val_11 1 1444val_111 1 1445val_113 2 1446val_114 1 1447PREHOOK: query: explain 1448select key, count(1) from clustergroupby where ds='102' group by key, value limit 10 1449PREHOOK: type: QUERY 1450POSTHOOK: query: explain 1451select key, count(1) from clustergroupby where ds='102' group by key, value limit 10 1452POSTHOOK: type: QUERY 1453POSTHOOK: Lineage: clustergroupby PARTITION(ds=100).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] 1454POSTHOOK: Lineage: clustergroupby PARTITION(ds=100).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] 1455POSTHOOK: Lineage: clustergroupby PARTITION(ds=101).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] 1456POSTHOOK: Lineage: clustergroupby PARTITION(ds=101).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] 1457POSTHOOK: Lineage: clustergroupby PARTITION(ds=102).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] 1458POSTHOOK: Lineage: clustergroupby PARTITION(ds=102).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] 1459ABSTRACT SYNTAX TREE: 1460 (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME clustergroupby))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_TABLE_OR_COL key)) (TOK_SELEXPR (TOK_FUNCTION count 1))) (TOK_WHERE (= (TOK_TABLE_OR_COL ds) '102')) (TOK_GROUPBY (TOK_TABLE_OR_COL key) (TOK_TABLE_OR_COL value)) (TOK_LIMIT 10))) 1461 1462STAGE DEPENDENCIES: 1463 Stage-1 is a root stage 1464 Stage-0 is a root stage 1465 1466STAGE PLANS: 1467 Stage: Stage-1 1468 Map Reduce 1469 Alias -> Map Operator Tree: 1470 clustergroupby 1471 TableScan 1472 alias: clustergroupby 1473 Filter Operator 1474 predicate: 1475 expr: (ds = '102') 1476 type: boolean 1477 Select Operator 1478 expressions: 1479 expr: key 1480 type: string 1481 expr: value 1482 type: string 1483 outputColumnNames: key, value 1484 Group By Operator 1485 aggregations: 1486 expr: count(1) 1487 bucketGroup: true 1488 keys: 1489 expr: key 1490 type: string 1491 expr: value 1492 type: string 1493 mode: hash 1494 outputColumnNames: _col0, _col1, _col2 1495 Reduce Output Operator 1496 key expressions: 1497 expr: _col0 1498 type: string 1499 expr: _col1 1500 type: string 1501 sort order: ++ 1502 Map-reduce partition columns: 1503 expr: _col0 1504 type: string 1505 expr: _col1 1506 type: string 1507 tag: -1 1508 value expressions: 1509 expr: _col2 1510 type: bigint 1511 Reduce Operator Tree: 1512 Group By Operator 1513 aggregations: 1514 expr: count(VALUE._col0) 1515 bucketGroup: false 1516 keys: 1517 expr: KEY._col0 1518 type: string 1519 expr: KEY._col1 1520 type: string 1521 mode: mergepartial 1522 outputColumnNames: _col0, _col1, _col2 1523 Select Operator 1524 expressions: 1525 expr: _col0 1526 type: string 1527 expr: _col2 1528 type: bigint 1529 outputColumnNames: _col0, _col1 1530 Limit 1531 File Output Operator 1532 compressed: false 1533 GlobalTableId: 0 1534 table: 1535 input format: org.apache.hadoop.mapred.TextInputFormat 1536 output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat 1537 1538 Stage: Stage-0 1539 Fetch Operator 1540 limit: 10 1541 1542 1543PREHOOK: query: select key, count(1) from clustergroupby where ds='102' group by key, value limit 10 1544PREHOOK: type: QUERY 1545PREHOOK: Input: default@clustergroupby@ds=102 1546PREHOOK: Output: file:/tmp/sdong/hive_2011-02-10_01-31-53_197_8563057494828766352/-mr-10000 1547POSTHOOK: query: select key, count(1) from clustergroupby where ds='102' group by key, value limit 10 1548POSTHOOK: type: QUERY 1549POSTHOOK: Input: default@clustergroupby@ds=102 1550POSTHOOK: Output: file:/tmp/sdong/hive_2011-02-10_01-31-53_197_8563057494828766352/-mr-10000 1551POSTHOOK: Lineage: clustergroupby PARTITION(ds=100).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] 1552POSTHOOK: Lineage: clustergroupby PARTITION(ds=100).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] 1553POSTHOOK: Lineage: clustergroupby PARTITION(ds=101).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] 1554POSTHOOK: Lineage: clustergroupby PARTITION(ds=101).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] 1555POSTHOOK: Lineage: clustergroupby PARTITION(ds=102).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] 1556POSTHOOK: Lineage: clustergroupby PARTITION(ds=102).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] 15570 3 155810 1 1559100 2 1560103 2 1561104 2 1562105 1 156311 1 1564111 1 1565113 2 1566114 1 1567PREHOOK: query: alter table clustergroupby clustered by (value, key) sorted by (key) into 1 buckets 1568PREHOOK: type: ALTERTABLE_CLUSTER_SORT 1569PREHOOK: Input: default@clustergroupby 1570PREHOOK: Output: default@clustergroupby 1571POSTHOOK: query: alter table clustergroupby clustered by (value, key) sorted by (key) into 1 buckets 1572POSTHOOK: type: ALTERTABLE_CLUSTER_SORT 1573POSTHOOK: Input: default@clustergroupby 1574POSTHOOK: Output: default@clustergroupby 1575POSTHOOK: Lineage: clustergroupby PARTITION(ds=100).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] 1576POSTHOOK: Lineage: clustergroupby PARTITION(ds=100).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] 1577POSTHOOK: Lineage: clustergroupby PARTITION(ds=101).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] 1578POSTHOOK: Lineage: clustergroupby PARTITION(ds=101).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] 1579POSTHOOK: Lineage: clustergroupby PARTITION(ds=102).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] 1580POSTHOOK: Lineage: clustergroupby PARTITION(ds=102).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] 1581PREHOOK: query: describe extended clustergroupby 1582PREHOOK: type: DESCTABLE 1583POSTHOOK: query: describe extended clustergroupby 1584POSTHOOK: type: DESCTABLE 1585POSTHOOK: Lineage: clustergroupby PARTITION(ds=100).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] 1586POSTHOOK: Lineage: clustergroupby PARTITION(ds=100).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] 1587POSTHOOK: Lineage: clustergroupby PARTITION(ds=101).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] 1588POSTHOOK: Lineage: clustergroupby PARTITION(ds=101).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] 1589POSTHOOK: Lineage: clustergroupby PARTITION(ds=102).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] 1590POSTHOOK: Lineage: clustergroupby PARTITION(ds=102).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] 1591key string 1592value string 1593ds string 1594 1595Detailed Table Information Table(tableName:clustergroupby, dbName:default, owner:sdong, createTime:1297330264, lastAccessTime:0, retention:0, sd:StorageDescriptor(cols:[FieldSchema(name:key, type:string, comment:null), FieldSchema(name:value, type:string, comment:null), FieldSchema(name:ds, type:string, comment:null)], location:pfile:/data/users/sdong/www/open-source-hive1/build/ql/test/data/warehouse/clustergroupby, inputFormat:org.apache.hadoop.mapred.TextInputFormat, outputFormat:org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat, compressed:false, numBuckets:1, serdeInfo:SerDeInfo(name:null, serializationLib:org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe, parameters:{serialization.format=1}), bucketCols:[value, key], sortCols:[Order(col:key, order:1)], parameters:{}), partitionKeys:[FieldSchema(name:ds, type:string, comment:null)], parameters:{numPartitions=3, numFiles=3, last_modified_by=sdong, last_modified_time=1297330316, transient_lastDdlTime=1297330316, numRows=1500, totalSize=17436}, viewOriginalText:null, viewExpandedText:null, tableType:MANAGED_TABLE) 1596PREHOOK: query: insert overwrite table clustergroupby partition (ds='103') select key, value from src distribute by value, key sort by key 1597PREHOOK: type: QUERY 1598PREHOOK: Input: default@src 1599PREHOOK: Output: default@clustergroupby@ds=103 1600POSTHOOK: query: insert overwrite table clustergroupby partition (ds='103') select key, value from src distribute by value, key sort by key 1601POSTHOOK: type: QUERY 1602POSTHOOK: Input: default@src 1603POSTHOOK: Output: default@clustergroupby@ds=103 1604POSTHOOK: Lineage: clustergroupby PARTITION(ds=100).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] 1605POSTHOOK: Lineage: clustergroupby PARTITION(ds=100).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] 1606POSTHOOK: Lineage: clustergroupby PARTITION(ds=101).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] 1607POSTHOOK: Lineage: clustergroupby PARTITION(ds=101).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] 1608POSTHOOK: Lineage: clustergroupby PARTITION(ds=102).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] 1609POSTHOOK: Lineage: clustergroupby PARTITION(ds=102).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] 1610POSTHOOK: Lineage: clustergroupby PARTITION(ds=103).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] 1611POSTHOOK: Lineage: clustergroupby PARTITION(ds=103).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] 1612PREHOOK: query: explain 1613select key, count(1) from clustergroupby where ds='103' group by key limit 10 1614PREHOOK: type: QUERY 1615POSTHOOK: query: explain 1616select key, count(1) from clustergroupby where ds='103' group by key limit 10 1617POSTHOOK: type: QUERY 1618POSTHOOK: Lineage: clustergroupby PARTITION(ds=100).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] 1619POSTHOOK: Lineage: clustergroupby PARTITION(ds=100).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] 1620POSTHOOK: Lineage: clustergroupby PARTITION(ds=101).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] 1621POSTHOOK: Lineage: clustergroupby PARTITION(ds=101).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] 1622POSTHOOK: Lineage: clustergroupby PARTITION(ds=102).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] 1623POSTHOOK: Lineage: clustergroupby PARTITION(ds=102).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] 1624POSTHOOK: Lineage: clustergroupby PARTITION(ds=103).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] 1625POSTHOOK: Lineage: clustergroupby PARTITION(ds=103).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] 1626ABSTRACT SYNTAX TREE: 1627 (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME clustergroupby))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_TABLE_OR_COL key)) (TOK_SELEXPR (TOK_FUNCTION count 1))) (TOK_WHERE (= (TOK_TABLE_OR_COL ds) '103')) (TOK_GROUPBY (TOK_TABLE_OR_COL key)) (TOK_LIMIT 10))) 1628 1629STAGE DEPENDENCIES: 1630 Stage-1 is a root stage 1631 Stage-0 is a root stage 1632 1633STAGE PLANS: 1634 Stage: Stage-1 1635 Map Reduce 1636 Alias -> Map Operator Tree: 1637 clustergroupby 1638 TableScan 1639 alias: clustergroupby 1640 Filter Operator 1641 predicate: 1642 expr: (ds = '103') 1643 type: boolean 1644 Select Operator 1645 expressions: 1646 expr: key 1647 type: string 1648 outputColumnNames: key 1649 Group By Operator 1650 aggregations: 1651 expr: count(1) 1652 bucketGroup: true 1653 keys: 1654 expr: key 1655 type: string 1656 mode: hash 1657 outputColumnNames: _col0, _col1 1658 Reduce Output Operator 1659 key expressions: 1660 expr: _col0 1661 type: string 1662 sort order: + 1663 Map-reduce partition columns: 1664 expr: _col0 1665 type: string 1666 tag: -1 1667 value expressions: 1668 expr: _col1 1669 type: bigint 1670 Reduce Operator Tree: 1671 Group By Operator 1672 aggregations: 1673 expr: count(VALUE._col0) 1674 bucketGroup: false 1675 keys: 1676 expr: KEY._col0 1677 type: string 1678 mode: mergepartial 1679 outputColumnNames: _col0, _col1 1680 Select Operator 1681 expressions: 1682 expr: _col0 1683 type: string 1684 expr: _col1 1685 type: bigint 1686 outputColumnNames: _col0, _col1 1687 Limit 1688 File Output Operator 1689 compressed: false 1690 GlobalTableId: 0 1691 table: 1692 input format: org.apache.hadoop.mapred.TextInputFormat 1693 output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat 1694 1695 Stage: Stage-0 1696 Fetch Operator 1697 limit: 10 1698 1699 1700PREHOOK: query: select key, count(1) from clustergroupby where ds='103' group by key limit 10 1701PREHOOK: type: QUERY 1702PREHOOK: Input: default@clustergroupby@ds=103 1703PREHOOK: Output: file:/tmp/sdong/hive_2011-02-10_01-32-01_981_7801389614651227175/-mr-10000 1704POSTHOOK: query: select key, count(1) from clustergroupby where ds='103' group by key limit 10 1705POSTHOOK: type: QUERY 1706POSTHOOK: Input: default@clustergroupby@ds=103 1707POSTHOOK: Output: file:/tmp/sdong/hive_2011-02-10_01-32-01_981_7801389614651227175/-mr-10000 1708POSTHOOK: Lineage: clustergroupby PARTITION(ds=100).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] 1709POSTHOOK: Lineage: clustergroupby PARTITION(ds=100).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] 1710POSTHOOK: Lineage: clustergroupby PARTITION(ds=101).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] 1711POSTHOOK: Lineage: clustergroupby PARTITION(ds=101).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] 1712POSTHOOK: Lineage: clustergroupby PARTITION(ds=102).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] 1713POSTHOOK: Lineage: clustergroupby PARTITION(ds=102).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] 1714POSTHOOK: Lineage: clustergroupby PARTITION(ds=103).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] 1715POSTHOOK: Lineage: clustergroupby PARTITION(ds=103).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] 17160 3 171710 1 1718100 2 1719103 2 1720104 2 1721105 1 172211 1 1723111 1 1724113 2 1725114 1 1726PREHOOK: query: explain 1727select key, count(1) from clustergroupby where ds='103' group by value, key limit 10 1728PREHOOK: type: QUERY 1729POSTHOOK: query: explain 1730select key, count(1) from clustergroupby where ds='103' group by value, key limit 10 1731POSTHOOK: type: QUERY 1732POSTHOOK: Lineage: clustergroupby PARTITION(ds=100).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] 1733POSTHOOK: Lineage: clustergroupby PARTITION(ds=100).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] 1734POSTHOOK: Lineage: clustergroupby PARTITION(ds=101).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] 1735POSTHOOK: Lineage: clustergroupby PARTITION(ds=101).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] 1736POSTHOOK: Lineage: clustergroupby PARTITION(ds=102).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] 1737POSTHOOK: Lineage: clustergroupby PARTITION(ds=102).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] 1738POSTHOOK: Lineage: clustergroupby PARTITION(ds=103).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] 1739POSTHOOK: Lineage: clustergroupby PARTITION(ds=103).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] 1740ABSTRACT SYNTAX TREE: 1741 (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME clustergroupby))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_TABLE_OR_COL key)) (TOK_SELEXPR (TOK_FUNCTION count 1))) (TOK_WHERE (= (TOK_TABLE_OR_COL ds) '103')) (TOK_GROUPBY (TOK_TABLE_OR_COL value) (TOK_TABLE_OR_COL key)) (TOK_LIMIT 10))) 1742 1743STAGE DEPENDENCIES: 1744 Stage-1 is a root stage 1745 Stage-0 is a root stage 1746 1747STAGE PLANS: 1748 Stage: Stage-1 1749 Map Reduce 1750 Alias -> Map Operator Tree: 1751 clustergroupby 1752 TableScan 1753 alias: clustergroupby 1754 Filter Operator 1755 predicate: 1756 expr: (ds = '103') 1757 type: boolean 1758 Select Operator 1759 expressions: 1760 expr: value 1761 type: string 1762 expr: key 1763 type: string 1764 outputColumnNames: value, key 1765 Group By Operator 1766 aggregations: 1767 expr: count(1) 1768 bucketGroup: false 1769 keys: 1770 expr: value 1771 type: string 1772 expr: key 1773 type: string 1774 mode: hash 1775 outputColumnNames: _col0, _col1, _col2 1776 Reduce Output Operator 1777 key expressions: 1778 expr: _col0 1779 type: string 1780 expr: _col1 1781 type: string 1782 sort order: ++ 1783 Map-reduce partition columns: 1784 expr: _col0 1785 type: string 1786 expr: _col1 1787 type: string 1788 tag: -1 1789 value expressions: 1790 expr: _col2 1791 type: bigint 1792 Reduce Operator Tree: 1793 Group By Operator 1794 aggregations: 1795 expr: count(VALUE._col0) 1796 bucketGroup: false 1797 keys: 1798 expr: KEY._col0 1799 type: string 1800 expr: KEY._col1 1801 type: string 1802 mode: mergepartial 1803 outputColumnNames: _col0, _col1, _col2 1804 Select Operator 1805 expressions: 1806 expr: _col1 1807 type: string 1808 expr: _col2 1809 type: bigint 1810 outputColumnNames: _col0, _col1 1811 Limit 1812 File Output Operator 1813 compressed: false 1814 GlobalTableId: 0 1815 table: 1816 input format: org.apache.hadoop.mapred.TextInputFormat 1817 output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat 1818 1819 Stage: Stage-0 1820 Fetch Operator 1821 limit: 10 1822 1823 1824PREHOOK: query: select key, count(1) from clustergroupby where ds='103' group by value, key limit 10 1825PREHOOK: type: QUERY 1826PREHOOK: Input: default@clustergroupby@ds=103 1827PREHOOK: Output: file:/tmp/sdong/hive_2011-02-10_01-32-05_628_4341301404865471977/-mr-10000 1828POSTHOOK: query: select key, count(1) from clustergroupby where ds='103' group by value, key limit 10 1829POSTHOOK: type: QUERY 1830POSTHOOK: Input: default@clustergroupby@ds=103 1831POSTHOOK: Output: file:/tmp/sdong/hive_2011-02-10_01-32-05_628_4341301404865471977/-mr-10000 1832POSTHOOK: Lineage: clustergroupby PARTITION(ds=100).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] 1833POSTHOOK: Lineage: clustergroupby PARTITION(ds=100).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] 1834POSTHOOK: Lineage: clustergroupby PARTITION(ds=101).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] 1835POSTHOOK: Lineage: clustergroupby PARTITION(ds=101).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] 1836POSTHOOK: Lineage: clustergroupby PARTITION(ds=102).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] 1837POSTHOOK: Lineage: clustergroupby PARTITION(ds=102).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] 1838POSTHOOK: Lineage: clustergroupby PARTITION(ds=103).key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] 1839POSTHOOK: Lineage: clustergroupby PARTITION(ds=103).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] 18400 3 184110 1 1842100 2 1843103 2 1844104 2 1845105 1 184611 1 1847111 1 1848113 2 1849114 1