blob: 932962845cab92e69704bd68899d143466f6eea4 [file] [log] [blame]
PREHOOK: query: CREATE TABLE bucket4_1(key int, value string) CLUSTERED BY (key) SORTED BY (key) INTO 2 BUCKETS
PREHOOK: type: CREATETABLE
PREHOOK: Output: database:default
PREHOOK: Output: default@bucket4_1
POSTHOOK: query: CREATE TABLE bucket4_1(key int, value string) CLUSTERED BY (key) SORTED BY (key) INTO 2 BUCKETS
POSTHOOK: type: CREATETABLE
POSTHOOK: Output: database:default
POSTHOOK: Output: default@bucket4_1
PREHOOK: query: explain extended
insert overwrite table bucket4_1
select * from src
PREHOOK: type: QUERY
PREHOOK: Input: default@src
PREHOOK: Output: default@bucket4_1
POSTHOOK: query: explain extended
insert overwrite table bucket4_1
select * from src
POSTHOOK: type: QUERY
POSTHOOK: Input: default@src
POSTHOOK: Output: default@bucket4_1
OPTIMIZED SQL: SELECT `key`, `value`
FROM `default`.`src`
STAGE DEPENDENCIES:
Stage-1 is a root stage
Stage-2 depends on stages: Stage-1
Stage-0 depends on stages: Stage-2
Stage-3 depends on stages: Stage-0
STAGE PLANS:
Stage: Stage-1
Tez
#### A masked pattern was here ####
Edges:
Reducer 2 <- Map 1 (SIMPLE_EDGE)
#### A masked pattern was here ####
Vertices:
Map 1
Map Operator Tree:
TableScan
alias: src
Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
GatherStats: false
Select Operator
expressions: UDFToInteger(key) (type: int), value (type: string)
outputColumnNames: _col0, _col1
Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
bucketingVersion: 2
key expressions: _col0 (type: int)
null sort order: a
numBuckets: -1
sort order: +
Map-reduce partition columns: _col0 (type: int)
Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE
tag: -1
value expressions: _col1 (type: string)
auto parallelism: false
Execution mode: vectorized, llap
LLAP IO: all inputs
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
bucketing_version 2
column.name.delimiter ,
columns key,value
columns.types string:string
#### A masked pattern was here ####
name default.src
serialization.format 1
serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
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:
bucketing_version 2
column.name.delimiter ,
columns key,value
columns.comments 'default','default'
columns.types string:string
#### A masked pattern was here ####
name default.src
serialization.format 1
serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.src
name: default.src
Truncated Path -> Alias:
/src [src]
Reducer 2
Execution mode: llap
Needs Tagging: false
Reduce Operator Tree:
Select Operator
expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: string)
outputColumnNames: _col0, _col1
Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
bucketingVersion: 2
compressed: false
GlobalTableId: 1
#### A masked pattern was here ####
NumFilesPerFileSink: 2
Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE
#### A masked pattern was here ####
table:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
SORTBUCKETCOLSPREFIX TRUE
bucket_count 2
bucket_field_name key
bucketing_version 2
column.name.delimiter ,
columns key,value
columns.comments
columns.types int:string
#### A masked pattern was here ####
name default.bucket4_1
serialization.format 1
serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.bucket4_1
TotalFiles: 2
GatherStats: true
MultiFileSpray: true
Select Operator
expressions: _col0 (type: int), _col1 (type: string)
outputColumnNames: key, value
Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: min(key), max(key), count(1), count(key), compute_bit_vector(key, 'hll'), max(length(value)), avg(COALESCE(length(value),0)), count(value), compute_bit_vector(value, 'hll')
mode: complete
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8
Statistics: Num rows: 1 Data size: 332 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: 'LONG' (type: string), UDFToLong(_col0) (type: bigint), UDFToLong(_col1) (type: bigint), (_col2 - _col3) (type: bigint), COALESCE(ndv_compute_bit_vector(_col4),0) (type: bigint), _col4 (type: binary), 'STRING' (type: string), UDFToLong(COALESCE(_col5,0)) (type: bigint), COALESCE(_col6,0) (type: double), (_col2 - _col7) (type: bigint), COALESCE(ndv_compute_bit_vector(_col8),0) (type: bigint), _col8 (type: binary)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11
Statistics: Num rows: 1 Data size: 530 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
bucketingVersion: 2
compressed: false
GlobalTableId: 0
#### A masked pattern was here ####
NumFilesPerFileSink: 1
Statistics: Num rows: 1 Data size: 530 Basic stats: COMPLETE Column stats: COMPLETE
#### A masked pattern was here ####
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
properties:
bucketing_version -1
columns _col0,_col1,_col2,_col3,_col4,_col5,_col6,_col7,_col8,_col9,_col10,_col11
columns.types string:bigint:bigint:bigint:bigint:binary:string:bigint:double:bigint:bigint:binary
escape.delim \
hive.serialization.extend.additional.nesting.levels true
serialization.escape.crlf true
serialization.format 1
serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
TotalFiles: 1
GatherStats: false
MultiFileSpray: false
Stage: Stage-2
Dependency Collection
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:
SORTBUCKETCOLSPREFIX TRUE
bucket_count 2
bucket_field_name key
bucketing_version 2
column.name.delimiter ,
columns key,value
columns.comments
columns.types int:string
#### A masked pattern was here ####
name default.bucket4_1
serialization.format 1
serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.bucket4_1
Stage: Stage-3
Stats Work
Basic Stats Work:
#### A masked pattern was here ####
Column Stats Desc:
Columns: key, value
Column Types: int, string
Table: default.bucket4_1
Is Table Level Stats: true
PREHOOK: query: insert overwrite table bucket4_1
select * from src
PREHOOK: type: QUERY
PREHOOK: Input: default@src
PREHOOK: Output: default@bucket4_1
POSTHOOK: query: insert overwrite table bucket4_1
select * from src
POSTHOOK: type: QUERY
POSTHOOK: Input: default@src
POSTHOOK: Output: default@bucket4_1
POSTHOOK: Lineage: bucket4_1.key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
POSTHOOK: Lineage: bucket4_1.value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
PREHOOK: query: explain
select * from bucket4_1 tablesample (bucket 1 out of 2) s
PREHOOK: type: QUERY
PREHOOK: Input: default@bucket4_1
#### A masked pattern was here ####
POSTHOOK: query: explain
select * from bucket4_1 tablesample (bucket 1 out of 2) s
POSTHOOK: type: QUERY
POSTHOOK: Input: default@bucket4_1
#### A masked pattern was here ####
STAGE DEPENDENCIES:
Stage-0 is a root stage
STAGE PLANS:
Stage: Stage-0
Fetch Operator
limit: -1
Processor Tree:
TableScan
alias: s
Filter Operator
predicate: (((hash(key) & 2147483647) % 2) = 0) (type: boolean)
Select Operator
expressions: key (type: int), value (type: string)
outputColumnNames: _col0, _col1
ListSink
PREHOOK: query: select * from bucket4_1 tablesample (bucket 1 out of 2) s
PREHOOK: type: QUERY
PREHOOK: Input: default@bucket4_1
#### A masked pattern was here ####
POSTHOOK: query: select * from bucket4_1 tablesample (bucket 1 out of 2) s
POSTHOOK: type: QUERY
POSTHOOK: Input: default@bucket4_1
#### A masked pattern was here ####
2 val_2
10 val_10
17 val_17
19 val_19
20 val_20
27 val_27
30 val_30
41 val_41
43 val_43
51 val_51
51 val_51
54 val_54
57 val_57
58 val_58
58 val_58
64 val_64
65 val_65
67 val_67
67 val_67
69 val_69
70 val_70
70 val_70
70 val_70
77 val_77
80 val_80
83 val_83
83 val_83
84 val_84
84 val_84
85 val_85
86 val_86
90 val_90
90 val_90
90 val_90
96 val_96
97 val_97
97 val_97
98 val_98
98 val_98
105 val_105
113 val_113
113 val_113
116 val_116
119 val_119
119 val_119
119 val_119
126 val_126
133 val_133
134 val_134
134 val_134
137 val_137
137 val_137
146 val_146
146 val_146
149 val_149
149 val_149
153 val_153
156 val_156
157 val_157
158 val_158
162 val_162
163 val_163
164 val_164
164 val_164
165 val_165
165 val_165
169 val_169
169 val_169
169 val_169
169 val_169
177 val_177
178 val_178
181 val_181
187 val_187
187 val_187
187 val_187
190 val_190
191 val_191
191 val_191
195 val_195
195 val_195
197 val_197
197 val_197
199 val_199
199 val_199
199 val_199
201 val_201
202 val_202
208 val_208
208 val_208
208 val_208
214 val_214
216 val_216
216 val_216
221 val_221
221 val_221
226 val_226
229 val_229
229 val_229
233 val_233
233 val_233
237 val_237
237 val_237
238 val_238
238 val_238
239 val_239
239 val_239
244 val_244
248 val_248
249 val_249
252 val_252
255 val_255
255 val_255
256 val_256
256 val_256
260 val_260
266 val_266
272 val_272
272 val_272
284 val_284
286 val_286
287 val_287
289 val_289
291 val_291
292 val_292
307 val_307
307 val_307
308 val_308
310 val_310
311 val_311
311 val_311
311 val_311
315 val_315
316 val_316
316 val_316
316 val_316
317 val_317
317 val_317
325 val_325
325 val_325
327 val_327
327 val_327
327 val_327
332 val_332
336 val_336
338 val_338
339 val_339
341 val_341
342 val_342
342 val_342
344 val_344
344 val_344
348 val_348
348 val_348
348 val_348
348 val_348
348 val_348
351 val_351
353 val_353
353 val_353
360 val_360
362 val_362
364 val_364
365 val_365
368 val_368
369 val_369
369 val_369
369 val_369
377 val_377
378 val_378
384 val_384
384 val_384
384 val_384
386 val_386
392 val_392
393 val_393
394 val_394
396 val_396
396 val_396
396 val_396
397 val_397
397 val_397
399 val_399
399 val_399
402 val_402
404 val_404
404 val_404
407 val_407
409 val_409
409 val_409
409 val_409
411 val_411
414 val_414
414 val_414
417 val_417
417 val_417
417 val_417
419 val_419
421 val_421
427 val_427
430 val_430
430 val_430
430 val_430
432 val_432
435 val_435
437 val_437
443 val_443
444 val_444
446 val_446
449 val_449
452 val_452
453 val_453
454 val_454
454 val_454
454 val_454
458 val_458
458 val_458
459 val_459
459 val_459
463 val_463
463 val_463
466 val_466
466 val_466
466 val_466
467 val_467
472 val_472
478 val_478
478 val_478
479 val_479
480 val_480
480 val_480
480 val_480
482 val_482
483 val_483
484 val_484
485 val_485
490 val_490
491 val_491
495 val_495
497 val_497
498 val_498
498 val_498
498 val_498