blob: 2d8ea6f8bc6055cac47fae351657ac4d4a1de353 [file] [log] [blame]
PREHOOK: query: CREATE TABLE DEST1_n71(key INT, value STRING) STORED AS TEXTFILE
PREHOOK: type: CREATETABLE
PREHOOK: Output: database:default
PREHOOK: Output: default@DEST1_n71
POSTHOOK: query: CREATE TABLE DEST1_n71(key INT, value STRING) STORED AS TEXTFILE
POSTHOOK: type: CREATETABLE
POSTHOOK: Output: database:default
POSTHOOK: Output: default@DEST1_n71
PREHOOK: query: CREATE TABLE DEST2_n15(key INT, value STRING) STORED AS TEXTFILE
PREHOOK: type: CREATETABLE
PREHOOK: Output: database:default
PREHOOK: Output: default@DEST2_n15
POSTHOOK: query: CREATE TABLE DEST2_n15(key INT, value STRING) STORED AS TEXTFILE
POSTHOOK: type: CREATETABLE
POSTHOOK: Output: database:default
POSTHOOK: Output: default@DEST2_n15
PREHOOK: query: EXPLAIN
FROM SRC
INSERT OVERWRITE TABLE DEST1_n71 SELECT SRC.key, COUNT(DISTINCT SUBSTR(SRC.value,5)) GROUP BY SRC.key
INSERT OVERWRITE TABLE DEST2_n15 SELECT SRC.key, COUNT(DISTINCT SUBSTR(SRC.value,5)) GROUP BY SRC.key
PREHOOK: type: QUERY
POSTHOOK: query: EXPLAIN
FROM SRC
INSERT OVERWRITE TABLE DEST1_n71 SELECT SRC.key, COUNT(DISTINCT SUBSTR(SRC.value,5)) GROUP BY SRC.key
INSERT OVERWRITE TABLE DEST2_n15 SELECT SRC.key, COUNT(DISTINCT SUBSTR(SRC.value,5)) GROUP BY SRC.key
POSTHOOK: type: QUERY
STAGE DEPENDENCIES:
Stage-2 is a root stage
Stage-3 depends on stages: Stage-2
Stage-0 depends on stages: Stage-3
Stage-4 depends on stages: Stage-0, Stage-6, Stage-11
Stage-5 depends on stages: Stage-3
Stage-6 depends on stages: Stage-5
Stage-9 depends on stages: Stage-1, Stage-6, Stage-11
Stage-7 depends on stages: Stage-2
Stage-8 depends on stages: Stage-7
Stage-1 depends on stages: Stage-8
Stage-10 depends on stages: Stage-8
Stage-11 depends on stages: Stage-10
STAGE PLANS:
Stage: Stage-2
Map Reduce
Map Operator Tree:
TableScan
alias: src
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: key (type: string), value (type: string)
outputColumnNames: key, value
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: key (type: string), substr(value, 5) (type: string)
sort order: ++
Map-reduce partition columns: key (type: string)
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: key (type: string), value (type: string)
outputColumnNames: key, value
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
Execution mode: vectorized
Reduce Operator Tree:
Group By Operator
aggregations: count(DISTINCT KEY._col1:0._col0)
keys: KEY._col0 (type: string)
mode: partial1
outputColumnNames: _col0, _col1
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
Stage: Stage-3
Map Reduce
Map Operator Tree:
TableScan
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: bigint)
Execution mode: vectorized
Reduce Operator Tree:
Group By Operator
aggregations: count(VALUE._col0)
keys: KEY._col0 (type: string)
mode: final
outputColumnNames: _col0, _col1
Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: UDFToInteger(_col0) (type: int), UDFToString(_col1) (type: string)
outputColumnNames: _col0, _col1
Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.dest1_n71
Select Operator
expressions: _col0 (type: int), _col1 (type: string)
outputColumnNames: key, value
Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
Stage: Stage-0
Move Operator
tables:
replace: true
table:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.dest1_n71
Stage: Stage-4
Stats Work
Basic Stats Work:
Column Stats Desc:
Columns: key, value
Column Types: int, string
Table: default.dest1_n71
Stage: Stage-5
Map Reduce
Map Operator Tree:
TableScan
Reduce Output Operator
sort order:
Map-reduce partition columns: rand() (type: double)
Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
value expressions: key (type: int), value (type: string)
Execution mode: vectorized
Reduce Operator Tree:
Group By Operator
aggregations: compute_stats(VALUE._col0, 'hll'), compute_stats(VALUE._col2, 'hll')
mode: partial1
outputColumnNames: _col0, _col1
Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
Stage: Stage-6
Map Reduce
Map Operator Tree:
TableScan
Reduce Output Operator
sort order:
Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE
value expressions: _col0 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>)
Execution mode: vectorized
Reduce Operator Tree:
Group By Operator
aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1)
mode: final
outputColumnNames: _col0, _col1
Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
Stage: Stage-9
Stats Work
Basic Stats Work:
Column Stats Desc:
Columns: key, value
Column Types: int, string
Table: default.dest2_n15
Stage: Stage-7
Map Reduce
Map Operator Tree:
TableScan
Reduce Output Operator
key expressions: key (type: string), substr(value, 5) (type: string)
sort order: ++
Map-reduce partition columns: key (type: string)
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
Execution mode: vectorized
Reduce Operator Tree:
Group By Operator
aggregations: count(DISTINCT KEY._col1:0._col0)
keys: KEY._col0 (type: string)
mode: partial1
outputColumnNames: _col0, _col1
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
Stage: Stage-8
Map Reduce
Map Operator Tree:
TableScan
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: bigint)
Execution mode: vectorized
Reduce Operator Tree:
Group By Operator
aggregations: count(VALUE._col0)
keys: KEY._col0 (type: string)
mode: final
outputColumnNames: _col0, _col1
Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: UDFToInteger(_col0) (type: int), UDFToString(_col1) (type: string)
outputColumnNames: _col0, _col1
Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.dest2_n15
Select Operator
expressions: _col0 (type: int), _col1 (type: string)
outputColumnNames: key, value
Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
Stage: Stage-1
Move Operator
tables:
replace: true
table:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.dest2_n15
Stage: Stage-10
Map Reduce
Map Operator Tree:
TableScan
Reduce Output Operator
sort order:
Map-reduce partition columns: rand() (type: double)
Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
value expressions: key (type: int), value (type: string)
Execution mode: vectorized
Reduce Operator Tree:
Group By Operator
aggregations: compute_stats(VALUE._col0, 'hll'), compute_stats(VALUE._col2, 'hll')
mode: partial1
outputColumnNames: _col0, _col1
Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
Stage: Stage-11
Map Reduce
Map Operator Tree:
TableScan
Reduce Output Operator
sort order:
Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE
value expressions: _col0 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>)
Execution mode: vectorized
Reduce Operator Tree:
Group By Operator
aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1)
mode: final
outputColumnNames: _col0, _col1
Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
PREHOOK: query: FROM SRC
INSERT OVERWRITE TABLE DEST1_n71 SELECT SRC.key, COUNT(DISTINCT SUBSTR(SRC.value,5)) GROUP BY SRC.key
INSERT OVERWRITE TABLE DEST2_n15 SELECT SRC.key, COUNT(DISTINCT SUBSTR(SRC.value,5)) GROUP BY SRC.key
PREHOOK: type: QUERY
PREHOOK: Input: default@src
PREHOOK: Output: default@dest1_n71
PREHOOK: Output: default@dest2_n15
POSTHOOK: query: FROM SRC
INSERT OVERWRITE TABLE DEST1_n71 SELECT SRC.key, COUNT(DISTINCT SUBSTR(SRC.value,5)) GROUP BY SRC.key
INSERT OVERWRITE TABLE DEST2_n15 SELECT SRC.key, COUNT(DISTINCT SUBSTR(SRC.value,5)) GROUP BY SRC.key
POSTHOOK: type: QUERY
POSTHOOK: Input: default@src
POSTHOOK: Output: default@dest1_n71
POSTHOOK: Output: default@dest2_n15
POSTHOOK: Lineage: dest1_n71.key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
POSTHOOK: Lineage: dest1_n71.value EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ]
POSTHOOK: Lineage: dest2_n15.key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
POSTHOOK: Lineage: dest2_n15.value EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ]
PREHOOK: query: SELECT DEST1_n71.* FROM DEST1_n71
PREHOOK: type: QUERY
PREHOOK: Input: default@dest1_n71
#### A masked pattern was here ####
POSTHOOK: query: SELECT DEST1_n71.* FROM DEST1_n71
POSTHOOK: type: QUERY
POSTHOOK: Input: default@dest1_n71
#### A masked pattern was here ####
0 1
10 1
100 1
103 1
104 1
105 1
11 1
111 1
113 1
114 1
116 1
118 1
119 1
12 1
120 1
125 1
126 1
128 1
129 1
131 1
133 1
134 1
136 1
137 1
138 1
143 1
145 1
146 1
149 1
15 1
150 1
152 1
153 1
155 1
156 1
157 1
158 1
160 1
162 1
163 1
164 1
165 1
166 1
167 1
168 1
169 1
17 1
170 1
172 1
174 1
175 1
176 1
177 1
178 1
179 1
18 1
180 1
181 1
183 1
186 1
187 1
189 1
19 1
190 1
191 1
192 1
193 1
194 1
195 1
196 1
197 1
199 1
2 1
20 1
200 1
201 1
202 1
203 1
205 1
207 1
208 1
209 1
213 1
214 1
216 1
217 1
218 1
219 1
221 1
222 1
223 1
224 1
226 1
228 1
229 1
230 1
233 1
235 1
237 1
238 1
239 1
24 1
241 1
242 1
244 1
247 1
248 1
249 1
252 1
255 1
256 1
257 1
258 1
26 1
260 1
262 1
263 1
265 1
266 1
27 1
272 1
273 1
274 1
275 1
277 1
278 1
28 1
280 1
281 1
282 1
283 1
284 1
285 1
286 1
287 1
288 1
289 1
291 1
292 1
296 1
298 1
30 1
302 1
305 1
306 1
307 1
308 1
309 1
310 1
311 1
315 1
316 1
317 1
318 1
321 1
322 1
323 1
325 1
327 1
33 1
331 1
332 1
333 1
335 1
336 1
338 1
339 1
34 1
341 1
342 1
344 1
345 1
348 1
35 1
351 1
353 1
356 1
360 1
362 1
364 1
365 1
366 1
367 1
368 1
369 1
37 1
373 1
374 1
375 1
377 1
378 1
379 1
382 1
384 1
386 1
389 1
392 1
393 1
394 1
395 1
396 1
397 1
399 1
4 1
400 1
401 1
402 1
403 1
404 1
406 1
407 1
409 1
41 1
411 1
413 1
414 1
417 1
418 1
419 1
42 1
421 1
424 1
427 1
429 1
43 1
430 1
431 1
432 1
435 1
436 1
437 1
438 1
439 1
44 1
443 1
444 1
446 1
448 1
449 1
452 1
453 1
454 1
455 1
457 1
458 1
459 1
460 1
462 1
463 1
466 1
467 1
468 1
469 1
47 1
470 1
472 1
475 1
477 1
478 1
479 1
480 1
481 1
482 1
483 1
484 1
485 1
487 1
489 1
490 1
491 1
492 1
493 1
494 1
495 1
496 1
497 1
498 1
5 1
51 1
53 1
54 1
57 1
58 1
64 1
65 1
66 1
67 1
69 1
70 1
72 1
74 1
76 1
77 1
78 1
8 1
80 1
82 1
83 1
84 1
85 1
86 1
87 1
9 1
90 1
92 1
95 1
96 1
97 1
98 1
PREHOOK: query: SELECT DEST2_n15.* FROM DEST2_n15
PREHOOK: type: QUERY
PREHOOK: Input: default@dest2_n15
#### A masked pattern was here ####
POSTHOOK: query: SELECT DEST2_n15.* FROM DEST2_n15
POSTHOOK: type: QUERY
POSTHOOK: Input: default@dest2_n15
#### A masked pattern was here ####
0 1
10 1
100 1
103 1
104 1
105 1
11 1
111 1
113 1
114 1
116 1
118 1
119 1
12 1
120 1
125 1
126 1
128 1
129 1
131 1
133 1
134 1
136 1
137 1
138 1
143 1
145 1
146 1
149 1
15 1
150 1
152 1
153 1
155 1
156 1
157 1
158 1
160 1
162 1
163 1
164 1
165 1
166 1
167 1
168 1
169 1
17 1
170 1
172 1
174 1
175 1
176 1
177 1
178 1
179 1
18 1
180 1
181 1
183 1
186 1
187 1
189 1
19 1
190 1
191 1
192 1
193 1
194 1
195 1
196 1
197 1
199 1
2 1
20 1
200 1
201 1
202 1
203 1
205 1
207 1
208 1
209 1
213 1
214 1
216 1
217 1
218 1
219 1
221 1
222 1
223 1
224 1
226 1
228 1
229 1
230 1
233 1
235 1
237 1
238 1
239 1
24 1
241 1
242 1
244 1
247 1
248 1
249 1
252 1
255 1
256 1
257 1
258 1
26 1
260 1
262 1
263 1
265 1
266 1
27 1
272 1
273 1
274 1
275 1
277 1
278 1
28 1
280 1
281 1
282 1
283 1
284 1
285 1
286 1
287 1
288 1
289 1
291 1
292 1
296 1
298 1
30 1
302 1
305 1
306 1
307 1
308 1
309 1
310 1
311 1
315 1
316 1
317 1
318 1
321 1
322 1
323 1
325 1
327 1
33 1
331 1
332 1
333 1
335 1
336 1
338 1
339 1
34 1
341 1
342 1
344 1
345 1
348 1
35 1
351 1
353 1
356 1
360 1
362 1
364 1
365 1
366 1
367 1
368 1
369 1
37 1
373 1
374 1
375 1
377 1
378 1
379 1
382 1
384 1
386 1
389 1
392 1
393 1
394 1
395 1
396 1
397 1
399 1
4 1
400 1
401 1
402 1
403 1
404 1
406 1
407 1
409 1
41 1
411 1
413 1
414 1
417 1
418 1
419 1
42 1
421 1
424 1
427 1
429 1
43 1
430 1
431 1
432 1
435 1
436 1
437 1
438 1
439 1
44 1
443 1
444 1
446 1
448 1
449 1
452 1
453 1
454 1
455 1
457 1
458 1
459 1
460 1
462 1
463 1
466 1
467 1
468 1
469 1
47 1
470 1
472 1
475 1
477 1
478 1
479 1
480 1
481 1
482 1
483 1
484 1
485 1
487 1
489 1
490 1
491 1
492 1
493 1
494 1
495 1
496 1
497 1
498 1
5 1
51 1
53 1
54 1
57 1
58 1
64 1
65 1
66 1
67 1
69 1
70 1
72 1
74 1
76 1
77 1
78 1
8 1
80 1
82 1
83 1
84 1
85 1
86 1
87 1
9 1
90 1
92 1
95 1
96 1
97 1
98 1
PREHOOK: query: EXPLAIN
FROM SRC
INSERT OVERWRITE TABLE DEST1_n71 SELECT SRC.key, COUNT(DISTINCT SUBSTR(SRC.value,5)) GROUP BY SRC.key
INSERT OVERWRITE TABLE DEST2_n15 SELECT SRC.key, COUNT(DISTINCT SUBSTR(SRC.value,5)) GROUP BY SRC.key
PREHOOK: type: QUERY
POSTHOOK: query: EXPLAIN
FROM SRC
INSERT OVERWRITE TABLE DEST1_n71 SELECT SRC.key, COUNT(DISTINCT SUBSTR(SRC.value,5)) GROUP BY SRC.key
INSERT OVERWRITE TABLE DEST2_n15 SELECT SRC.key, COUNT(DISTINCT SUBSTR(SRC.value,5)) GROUP BY SRC.key
POSTHOOK: type: QUERY
STAGE DEPENDENCIES:
Stage-2 is a root stage
Stage-3 depends on stages: Stage-2
Stage-0 depends on stages: Stage-3
Stage-4 depends on stages: Stage-0, Stage-6, Stage-11
Stage-5 depends on stages: Stage-3
Stage-6 depends on stages: Stage-5
Stage-9 depends on stages: Stage-1, Stage-6, Stage-11
Stage-7 depends on stages: Stage-2
Stage-8 depends on stages: Stage-7
Stage-1 depends on stages: Stage-8
Stage-10 depends on stages: Stage-8
Stage-11 depends on stages: Stage-10
STAGE PLANS:
Stage: Stage-2
Map Reduce
Map Operator Tree:
TableScan
alias: src
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: key (type: string), value (type: string)
outputColumnNames: key, value
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: key (type: string), substr(value, 5) (type: string)
sort order: ++
Map-reduce partition columns: key (type: string)
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: key (type: string), value (type: string)
outputColumnNames: key, value
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
Execution mode: vectorized
Reduce Operator Tree:
Group By Operator
aggregations: count(DISTINCT KEY._col1:0._col0)
keys: KEY._col0 (type: string)
mode: partial1
outputColumnNames: _col0, _col1
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
Stage: Stage-3
Map Reduce
Map Operator Tree:
TableScan
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: bigint)
Execution mode: vectorized
Reduce Operator Tree:
Group By Operator
aggregations: count(VALUE._col0)
keys: KEY._col0 (type: string)
mode: final
outputColumnNames: _col0, _col1
Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: UDFToInteger(_col0) (type: int), UDFToString(_col1) (type: string)
outputColumnNames: _col0, _col1
Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.dest1_n71
Select Operator
expressions: _col0 (type: int), _col1 (type: string)
outputColumnNames: key, value
Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
Stage: Stage-0
Move Operator
tables:
replace: true
table:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.dest1_n71
Stage: Stage-4
Stats Work
Basic Stats Work:
Column Stats Desc:
Columns: key, value
Column Types: int, string
Table: default.dest1_n71
Stage: Stage-5
Map Reduce
Map Operator Tree:
TableScan
Reduce Output Operator
sort order:
Map-reduce partition columns: rand() (type: double)
Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
value expressions: key (type: int), value (type: string)
Execution mode: vectorized
Reduce Operator Tree:
Group By Operator
aggregations: compute_stats(VALUE._col0, 'hll'), compute_stats(VALUE._col2, 'hll')
mode: partial1
outputColumnNames: _col0, _col1
Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
Stage: Stage-6
Map Reduce
Map Operator Tree:
TableScan
Reduce Output Operator
sort order:
Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE
value expressions: _col0 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>)
Execution mode: vectorized
Reduce Operator Tree:
Group By Operator
aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1)
mode: final
outputColumnNames: _col0, _col1
Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
Stage: Stage-9
Stats Work
Basic Stats Work:
Column Stats Desc:
Columns: key, value
Column Types: int, string
Table: default.dest2_n15
Stage: Stage-7
Map Reduce
Map Operator Tree:
TableScan
Reduce Output Operator
key expressions: key (type: string), substr(value, 5) (type: string)
sort order: ++
Map-reduce partition columns: key (type: string)
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
Execution mode: vectorized
Reduce Operator Tree:
Group By Operator
aggregations: count(DISTINCT KEY._col1:0._col0)
keys: KEY._col0 (type: string)
mode: partial1
outputColumnNames: _col0, _col1
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
Stage: Stage-8
Map Reduce
Map Operator Tree:
TableScan
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: bigint)
Execution mode: vectorized
Reduce Operator Tree:
Group By Operator
aggregations: count(VALUE._col0)
keys: KEY._col0 (type: string)
mode: final
outputColumnNames: _col0, _col1
Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: UDFToInteger(_col0) (type: int), UDFToString(_col1) (type: string)
outputColumnNames: _col0, _col1
Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.dest2_n15
Select Operator
expressions: _col0 (type: int), _col1 (type: string)
outputColumnNames: key, value
Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
Stage: Stage-1
Move Operator
tables:
replace: true
table:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.dest2_n15
Stage: Stage-10
Map Reduce
Map Operator Tree:
TableScan
Reduce Output Operator
sort order:
Map-reduce partition columns: rand() (type: double)
Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
value expressions: key (type: int), value (type: string)
Execution mode: vectorized
Reduce Operator Tree:
Group By Operator
aggregations: compute_stats(VALUE._col0, 'hll'), compute_stats(VALUE._col2, 'hll')
mode: partial1
outputColumnNames: _col0, _col1
Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
Stage: Stage-11
Map Reduce
Map Operator Tree:
TableScan
Reduce Output Operator
sort order:
Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE
value expressions: _col0 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>)
Execution mode: vectorized
Reduce Operator Tree:
Group By Operator
aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1)
mode: final
outputColumnNames: _col0, _col1
Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
PREHOOK: query: FROM SRC
INSERT OVERWRITE TABLE DEST1_n71 SELECT SRC.key, COUNT(DISTINCT SUBSTR(SRC.value,5)) GROUP BY SRC.key
INSERT OVERWRITE TABLE DEST2_n15 SELECT SRC.key, COUNT(DISTINCT SUBSTR(SRC.value,5)) GROUP BY SRC.key
PREHOOK: type: QUERY
PREHOOK: Input: default@src
PREHOOK: Output: default@dest1_n71
PREHOOK: Output: default@dest2_n15
POSTHOOK: query: FROM SRC
INSERT OVERWRITE TABLE DEST1_n71 SELECT SRC.key, COUNT(DISTINCT SUBSTR(SRC.value,5)) GROUP BY SRC.key
INSERT OVERWRITE TABLE DEST2_n15 SELECT SRC.key, COUNT(DISTINCT SUBSTR(SRC.value,5)) GROUP BY SRC.key
POSTHOOK: type: QUERY
POSTHOOK: Input: default@src
POSTHOOK: Output: default@dest1_n71
POSTHOOK: Output: default@dest2_n15
POSTHOOK: Lineage: dest1_n71.key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
POSTHOOK: Lineage: dest1_n71.value EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ]
POSTHOOK: Lineage: dest2_n15.key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
POSTHOOK: Lineage: dest2_n15.value EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ]
PREHOOK: query: SELECT DEST1_n71.* FROM DEST1_n71
PREHOOK: type: QUERY
PREHOOK: Input: default@dest1_n71
#### A masked pattern was here ####
POSTHOOK: query: SELECT DEST1_n71.* FROM DEST1_n71
POSTHOOK: type: QUERY
POSTHOOK: Input: default@dest1_n71
#### A masked pattern was here ####
0 1
10 1
100 1
103 1
104 1
105 1
11 1
111 1
113 1
114 1
116 1
118 1
119 1
12 1
120 1
125 1
126 1
128 1
129 1
131 1
133 1
134 1
136 1
137 1
138 1
143 1
145 1
146 1
149 1
15 1
150 1
152 1
153 1
155 1
156 1
157 1
158 1
160 1
162 1
163 1
164 1
165 1
166 1
167 1
168 1
169 1
17 1
170 1
172 1
174 1
175 1
176 1
177 1
178 1
179 1
18 1
180 1
181 1
183 1
186 1
187 1
189 1
19 1
190 1
191 1
192 1
193 1
194 1
195 1
196 1
197 1
199 1
2 1
20 1
200 1
201 1
202 1
203 1
205 1
207 1
208 1
209 1
213 1
214 1
216 1
217 1
218 1
219 1
221 1
222 1
223 1
224 1
226 1
228 1
229 1
230 1
233 1
235 1
237 1
238 1
239 1
24 1
241 1
242 1
244 1
247 1
248 1
249 1
252 1
255 1
256 1
257 1
258 1
26 1
260 1
262 1
263 1
265 1
266 1
27 1
272 1
273 1
274 1
275 1
277 1
278 1
28 1
280 1
281 1
282 1
283 1
284 1
285 1
286 1
287 1
288 1
289 1
291 1
292 1
296 1
298 1
30 1
302 1
305 1
306 1
307 1
308 1
309 1
310 1
311 1
315 1
316 1
317 1
318 1
321 1
322 1
323 1
325 1
327 1
33 1
331 1
332 1
333 1
335 1
336 1
338 1
339 1
34 1
341 1
342 1
344 1
345 1
348 1
35 1
351 1
353 1
356 1
360 1
362 1
364 1
365 1
366 1
367 1
368 1
369 1
37 1
373 1
374 1
375 1
377 1
378 1
379 1
382 1
384 1
386 1
389 1
392 1
393 1
394 1
395 1
396 1
397 1
399 1
4 1
400 1
401 1
402 1
403 1
404 1
406 1
407 1
409 1
41 1
411 1
413 1
414 1
417 1
418 1
419 1
42 1
421 1
424 1
427 1
429 1
43 1
430 1
431 1
432 1
435 1
436 1
437 1
438 1
439 1
44 1
443 1
444 1
446 1
448 1
449 1
452 1
453 1
454 1
455 1
457 1
458 1
459 1
460 1
462 1
463 1
466 1
467 1
468 1
469 1
47 1
470 1
472 1
475 1
477 1
478 1
479 1
480 1
481 1
482 1
483 1
484 1
485 1
487 1
489 1
490 1
491 1
492 1
493 1
494 1
495 1
496 1
497 1
498 1
5 1
51 1
53 1
54 1
57 1
58 1
64 1
65 1
66 1
67 1
69 1
70 1
72 1
74 1
76 1
77 1
78 1
8 1
80 1
82 1
83 1
84 1
85 1
86 1
87 1
9 1
90 1
92 1
95 1
96 1
97 1
98 1
PREHOOK: query: SELECT DEST2_n15.* FROM DEST2_n15
PREHOOK: type: QUERY
PREHOOK: Input: default@dest2_n15
#### A masked pattern was here ####
POSTHOOK: query: SELECT DEST2_n15.* FROM DEST2_n15
POSTHOOK: type: QUERY
POSTHOOK: Input: default@dest2_n15
#### A masked pattern was here ####
0 1
10 1
100 1
103 1
104 1
105 1
11 1
111 1
113 1
114 1
116 1
118 1
119 1
12 1
120 1
125 1
126 1
128 1
129 1
131 1
133 1
134 1
136 1
137 1
138 1
143 1
145 1
146 1
149 1
15 1
150 1
152 1
153 1
155 1
156 1
157 1
158 1
160 1
162 1
163 1
164 1
165 1
166 1
167 1
168 1
169 1
17 1
170 1
172 1
174 1
175 1
176 1
177 1
178 1
179 1
18 1
180 1
181 1
183 1
186 1
187 1
189 1
19 1
190 1
191 1
192 1
193 1
194 1
195 1
196 1
197 1
199 1
2 1
20 1
200 1
201 1
202 1
203 1
205 1
207 1
208 1
209 1
213 1
214 1
216 1
217 1
218 1
219 1
221 1
222 1
223 1
224 1
226 1
228 1
229 1
230 1
233 1
235 1
237 1
238 1
239 1
24 1
241 1
242 1
244 1
247 1
248 1
249 1
252 1
255 1
256 1
257 1
258 1
26 1
260 1
262 1
263 1
265 1
266 1
27 1
272 1
273 1
274 1
275 1
277 1
278 1
28 1
280 1
281 1
282 1
283 1
284 1
285 1
286 1
287 1
288 1
289 1
291 1
292 1
296 1
298 1
30 1
302 1
305 1
306 1
307 1
308 1
309 1
310 1
311 1
315 1
316 1
317 1
318 1
321 1
322 1
323 1
325 1
327 1
33 1
331 1
332 1
333 1
335 1
336 1
338 1
339 1
34 1
341 1
342 1
344 1
345 1
348 1
35 1
351 1
353 1
356 1
360 1
362 1
364 1
365 1
366 1
367 1
368 1
369 1
37 1
373 1
374 1
375 1
377 1
378 1
379 1
382 1
384 1
386 1
389 1
392 1
393 1
394 1
395 1
396 1
397 1
399 1
4 1
400 1
401 1
402 1
403 1
404 1
406 1
407 1
409 1
41 1
411 1
413 1
414 1
417 1
418 1
419 1
42 1
421 1
424 1
427 1
429 1
43 1
430 1
431 1
432 1
435 1
436 1
437 1
438 1
439 1
44 1
443 1
444 1
446 1
448 1
449 1
452 1
453 1
454 1
455 1
457 1
458 1
459 1
460 1
462 1
463 1
466 1
467 1
468 1
469 1
47 1
470 1
472 1
475 1
477 1
478 1
479 1
480 1
481 1
482 1
483 1
484 1
485 1
487 1
489 1
490 1
491 1
492 1
493 1
494 1
495 1
496 1
497 1
498 1
5 1
51 1
53 1
54 1
57 1
58 1
64 1
65 1
66 1
67 1
69 1
70 1
72 1
74 1
76 1
77 1
78 1
8 1
80 1
82 1
83 1
84 1
85 1
86 1
87 1
9 1
90 1
92 1
95 1
96 1
97 1
98 1