1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
|
/*
* Licensed to the Apache Software Foundation (ASF) under one or more
* contributor license agreements. See the NOTICE file distributed with
* this work for additional information regarding copyright ownership.
* The ASF licenses this file to You under the Apache License, Version 2.0
* (the "License"); you may not use this file except in compliance with
* the License. You may obtain a copy of the License at
*
* http://www.apache.org/licenses/LICENSE-2.0
*
* Unless required by applicable law or agreed to in writing, software
* distributed under the License is distributed on an "AS IS" BASIS,
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
* See the License for the specific language governing permissions and
* limitations under the License.
*/
package org.apache.spark.rdd
import java.nio.ByteBuffer
import java.text.SimpleDateFormat
import java.util.{Date, HashMap => JHashMap}
import scala.collection.{Map, mutable}
import scala.collection.JavaConversions._
import scala.collection.mutable.ArrayBuffer
import scala.reflect.ClassTag
import scala.util.DynamicVariable
import com.clearspring.analytics.stream.cardinality.HyperLogLogPlus
import org.apache.hadoop.conf.{Configurable, Configuration}
import org.apache.hadoop.fs.FileSystem
import org.apache.hadoop.io.SequenceFile.CompressionType
import org.apache.hadoop.io.compress.CompressionCodec
import org.apache.hadoop.mapred.{FileOutputCommitter, FileOutputFormat, JobConf, OutputFormat}
import org.apache.hadoop.mapreduce.{Job => NewAPIHadoopJob, OutputFormat => NewOutputFormat,
RecordWriter => NewRecordWriter}
import org.apache.spark._
import org.apache.spark.Partitioner.defaultPartitioner
import org.apache.spark.annotation.Experimental
import org.apache.spark.deploy.SparkHadoopUtil
import org.apache.spark.executor.{DataWriteMethod, OutputMetrics}
import org.apache.spark.mapreduce.SparkHadoopMapReduceUtil
import org.apache.spark.partial.{BoundedDouble, PartialResult}
import org.apache.spark.serializer.Serializer
import org.apache.spark.util.{SerializableConfiguration, Utils}
import org.apache.spark.util.collection.CompactBuffer
import org.apache.spark.util.random.StratifiedSamplingUtils
/**
* Extra functions available on RDDs of (key, value) pairs through an implicit conversion.
*/
class PairRDDFunctions[K, V](self: RDD[(K, V)])
(implicit kt: ClassTag[K], vt: ClassTag[V], ord: Ordering[K] = null)
extends Logging
with SparkHadoopMapReduceUtil
with Serializable
{
/**
* Generic function to combine the elements for each key using a custom set of aggregation
* functions. Turns an RDD[(K, V)] into a result of type RDD[(K, C)], for a "combined type" C
* Note that V and C can be different -- for example, one might group an RDD of type
* (Int, Int) into an RDD of type (Int, Seq[Int]). Users provide three functions:
*
* - `createCombiner`, which turns a V into a C (e.g., creates a one-element list)
* - `mergeValue`, to merge a V into a C (e.g., adds it to the end of a list)
* - `mergeCombiners`, to combine two C's into a single one.
*
* In addition, users can control the partitioning of the output RDD, and whether to perform
* map-side aggregation (if a mapper can produce multiple items with the same key).
*/
def combineByKey[C](createCombiner: V => C,
mergeValue: (C, V) => C,
mergeCombiners: (C, C) => C,
partitioner: Partitioner,
mapSideCombine: Boolean = true,
serializer: Serializer = null): RDD[(K, C)] = self.withScope {
require(mergeCombiners != null, "mergeCombiners must be defined") // required as of Spark 0.9.0
if (keyClass.isArray) {
if (mapSideCombine) {
throw new SparkException("Cannot use map-side combining with array keys.")
}
if (partitioner.isInstanceOf[HashPartitioner]) {
throw new SparkException("Default partitioner cannot partition array keys.")
}
}
val aggregator = new Aggregator[K, V, C](
self.context.clean(createCombiner),
self.context.clean(mergeValue),
self.context.clean(mergeCombiners))
if (self.partitioner == Some(partitioner)) {
self.mapPartitions(iter => {
val context = TaskContext.get()
new InterruptibleIterator(context, aggregator.combineValuesByKey(iter, context))
}, preservesPartitioning = true)
} else {
new ShuffledRDD[K, V, C](self, partitioner)
.setSerializer(serializer)
.setAggregator(aggregator)
.setMapSideCombine(mapSideCombine)
}
}
/**
* Simplified version of combineByKey that hash-partitions the output RDD.
*/
def combineByKey[C](createCombiner: V => C,
mergeValue: (C, V) => C,
mergeCombiners: (C, C) => C,
numPartitions: Int): RDD[(K, C)] = self.withScope {
combineByKey(createCombiner, mergeValue, mergeCombiners, new HashPartitioner(numPartitions))
}
/**
* Aggregate the values of each key, using given combine functions and a neutral "zero value".
* This function can return a different result type, U, than the type of the values in this RDD,
* V. Thus, we need one operation for merging a V into a U and one operation for merging two U's,
* as in scala.TraversableOnce. The former operation is used for merging values within a
* partition, and the latter is used for merging values between partitions. To avoid memory
* allocation, both of these functions are allowed to modify and return their first argument
* instead of creating a new U.
*/
def aggregateByKey[U: ClassTag](zeroValue: U, partitioner: Partitioner)(seqOp: (U, V) => U,
combOp: (U, U) => U): RDD[(K, U)] = self.withScope {
// Serialize the zero value to a byte array so that we can get a new clone of it on each key
val zeroBuffer = SparkEnv.get.serializer.newInstance().serialize(zeroValue)
val zeroArray = new Array[Byte](zeroBuffer.limit)
zeroBuffer.get(zeroArray)
lazy val cachedSerializer = SparkEnv.get.serializer.newInstance()
val createZero = () => cachedSerializer.deserialize[U](ByteBuffer.wrap(zeroArray))
// We will clean the combiner closure later in `combineByKey`
val cleanedSeqOp = self.context.clean(seqOp)
combineByKey[U]((v: V) => cleanedSeqOp(createZero(), v), cleanedSeqOp, combOp, partitioner)
}
/**
* Aggregate the values of each key, using given combine functions and a neutral "zero value".
* This function can return a different result type, U, than the type of the values in this RDD,
* V. Thus, we need one operation for merging a V into a U and one operation for merging two U's,
* as in scala.TraversableOnce. The former operation is used for merging values within a
* partition, and the latter is used for merging values between partitions. To avoid memory
* allocation, both of these functions are allowed to modify and return their first argument
* instead of creating a new U.
*/
def aggregateByKey[U: ClassTag](zeroValue: U, numPartitions: Int)(seqOp: (U, V) => U,
combOp: (U, U) => U): RDD[(K, U)] = self.withScope {
aggregateByKey(zeroValue, new HashPartitioner(numPartitions))(seqOp, combOp)
}
/**
* Aggregate the values of each key, using given combine functions and a neutral "zero value".
* This function can return a different result type, U, than the type of the values in this RDD,
* V. Thus, we need one operation for merging a V into a U and one operation for merging two U's,
* as in scala.TraversableOnce. The former operation is used for merging values within a
* partition, and the latter is used for merging values between partitions. To avoid memory
* allocation, both of these functions are allowed to modify and return their first argument
* instead of creating a new U.
*/
def aggregateByKey[U: ClassTag](zeroValue: U)(seqOp: (U, V) => U,
combOp: (U, U) => U): RDD[(K, U)] = self.withScope {
aggregateByKey(zeroValue, defaultPartitioner(self))(seqOp, combOp)
}
/**
* Merge the values for each key using an associative function and a neutral "zero value" which
* may be added to the result an arbitrary number of times, and must not change the result
* (e.g., Nil for list concatenation, 0 for addition, or 1 for multiplication.).
*/
def foldByKey(
zeroValue: V,
partitioner: Partitioner)(func: (V, V) => V): RDD[(K, V)] = self.withScope {
// Serialize the zero value to a byte array so that we can get a new clone of it on each key
val zeroBuffer = SparkEnv.get.serializer.newInstance().serialize(zeroValue)
val zeroArray = new Array[Byte](zeroBuffer.limit)
zeroBuffer.get(zeroArray)
// When deserializing, use a lazy val to create just one instance of the serializer per task
lazy val cachedSerializer = SparkEnv.get.serializer.newInstance()
val createZero = () => cachedSerializer.deserialize[V](ByteBuffer.wrap(zeroArray))
val cleanedFunc = self.context.clean(func)
combineByKey[V]((v: V) => cleanedFunc(createZero(), v), cleanedFunc, cleanedFunc, partitioner)
}
/**
* Merge the values for each key using an associative function and a neutral "zero value" which
* may be added to the result an arbitrary number of times, and must not change the result
* (e.g., Nil for list concatenation, 0 for addition, or 1 for multiplication.).
*/
def foldByKey(zeroValue: V, numPartitions: Int)(func: (V, V) => V): RDD[(K, V)] = self.withScope {
foldByKey(zeroValue, new HashPartitioner(numPartitions))(func)
}
/**
* Merge the values for each key using an associative function and a neutral "zero value" which
* may be added to the result an arbitrary number of times, and must not change the result
* (e.g., Nil for list concatenation, 0 for addition, or 1 for multiplication.).
*/
def foldByKey(zeroValue: V)(func: (V, V) => V): RDD[(K, V)] = self.withScope {
foldByKey(zeroValue, defaultPartitioner(self))(func)
}
/**
* Return a subset of this RDD sampled by key (via stratified sampling).
*
* Create a sample of this RDD using variable sampling rates for different keys as specified by
* `fractions`, a key to sampling rate map, via simple random sampling with one pass over the
* RDD, to produce a sample of size that's approximately equal to the sum of
* math.ceil(numItems * samplingRate) over all key values.
*
* @param withReplacement whether to sample with or without replacement
* @param fractions map of specific keys to sampling rates
* @param seed seed for the random number generator
* @return RDD containing the sampled subset
*/
def sampleByKey(withReplacement: Boolean,
fractions: Map[K, Double],
seed: Long = Utils.random.nextLong): RDD[(K, V)] = self.withScope {
require(fractions.values.forall(v => v >= 0.0), "Negative sampling rates.")
val samplingFunc = if (withReplacement) {
StratifiedSamplingUtils.getPoissonSamplingFunction(self, fractions, false, seed)
} else {
StratifiedSamplingUtils.getBernoulliSamplingFunction(self, fractions, false, seed)
}
self.mapPartitionsWithIndex(samplingFunc, preservesPartitioning = true)
}
/**
* ::Experimental::
* Return a subset of this RDD sampled by key (via stratified sampling) containing exactly
* math.ceil(numItems * samplingRate) for each stratum (group of pairs with the same key).
*
* This method differs from [[sampleByKey]] in that we make additional passes over the RDD to
* create a sample size that's exactly equal to the sum of math.ceil(numItems * samplingRate)
* over all key values with a 99.99% confidence. When sampling without replacement, we need one
* additional pass over the RDD to guarantee sample size; when sampling with replacement, we need
* two additional passes.
*
* @param withReplacement whether to sample with or without replacement
* @param fractions map of specific keys to sampling rates
* @param seed seed for the random number generator
* @return RDD containing the sampled subset
*/
@Experimental
def sampleByKeyExact(
withReplacement: Boolean,
fractions: Map[K, Double],
seed: Long = Utils.random.nextLong): RDD[(K, V)] = self.withScope {
require(fractions.values.forall(v => v >= 0.0), "Negative sampling rates.")
val samplingFunc = if (withReplacement) {
StratifiedSamplingUtils.getPoissonSamplingFunction(self, fractions, true, seed)
} else {
StratifiedSamplingUtils.getBernoulliSamplingFunction(self, fractions, true, seed)
}
self.mapPartitionsWithIndex(samplingFunc, preservesPartitioning = true)
}
/**
* Merge the values for each key using an associative reduce function. This will also perform
* the merging locally on each mapper before sending results to a reducer, similarly to a
* "combiner" in MapReduce.
*/
def reduceByKey(partitioner: Partitioner, func: (V, V) => V): RDD[(K, V)] = self.withScope {
combineByKey[V]((v: V) => v, func, func, partitioner)
}
/**
* Merge the values for each key using an associative reduce function. This will also perform
* the merging locally on each mapper before sending results to a reducer, similarly to a
* "combiner" in MapReduce. Output will be hash-partitioned with numPartitions partitions.
*/
def reduceByKey(func: (V, V) => V, numPartitions: Int): RDD[(K, V)] = self.withScope {
reduceByKey(new HashPartitioner(numPartitions), func)
}
/**
* Merge the values for each key using an associative reduce function. This will also perform
* the merging locally on each mapper before sending results to a reducer, similarly to a
* "combiner" in MapReduce. Output will be hash-partitioned with the existing partitioner/
* parallelism level.
*/
def reduceByKey(func: (V, V) => V): RDD[(K, V)] = self.withScope {
reduceByKey(defaultPartitioner(self), func)
}
/**
* Merge the values for each key using an associative reduce function, but return the results
* immediately to the master as a Map. This will also perform the merging locally on each mapper
* before sending results to a reducer, similarly to a "combiner" in MapReduce.
*/
def reduceByKeyLocally(func: (V, V) => V): Map[K, V] = self.withScope {
val cleanedF = self.sparkContext.clean(func)
if (keyClass.isArray) {
throw new SparkException("reduceByKeyLocally() does not support array keys")
}
val reducePartition = (iter: Iterator[(K, V)]) => {
val map = new JHashMap[K, V]
iter.foreach { pair =>
val old = map.get(pair._1)
map.put(pair._1, if (old == null) pair._2 else cleanedF(old, pair._2))
}
Iterator(map)
} : Iterator[JHashMap[K, V]]
val mergeMaps = (m1: JHashMap[K, V], m2: JHashMap[K, V]) => {
m2.foreach { pair =>
val old = m1.get(pair._1)
m1.put(pair._1, if (old == null) pair._2 else cleanedF(old, pair._2))
}
m1
} : JHashMap[K, V]
self.mapPartitions(reducePartition).reduce(mergeMaps)
}
/** Alias for reduceByKeyLocally */
@deprecated("Use reduceByKeyLocally", "1.0.0")
def reduceByKeyToDriver(func: (V, V) => V): Map[K, V] = self.withScope {
reduceByKeyLocally(func)
}
/**
* Count the number of elements for each key, collecting the results to a local Map.
*
* Note that this method should only be used if the resulting map is expected to be small, as
* the whole thing is loaded into the driver's memory.
* To handle very large results, consider using rdd.mapValues(_ => 1L).reduceByKey(_ + _), which
* returns an RDD[T, Long] instead of a map.
*/
def countByKey(): Map[K, Long] = self.withScope {
self.mapValues(_ => 1L).reduceByKey(_ + _).collect().toMap
}
/**
* :: Experimental ::
* Approximate version of countByKey that can return a partial result if it does
* not finish within a timeout.
*/
@Experimental
def countByKeyApprox(timeout: Long, confidence: Double = 0.95)
: PartialResult[Map[K, BoundedDouble]] = self.withScope {
self.map(_._1).countByValueApprox(timeout, confidence)
}
/**
* :: Experimental ::
*
* Return approximate number of distinct values for each key in this RDD.
*
* The algorithm used is based on streamlib's implementation of "HyperLogLog in Practice:
* Algorithmic Engineering of a State of The Art Cardinality Estimation Algorithm", available
* <a href="http://dx.doi.org/10.1145/2452376.2452456">here</a>.
*
* The relative accuracy is approximately `1.054 / sqrt(2^p)`. Setting a nonzero `sp > p`
* would trigger sparse representation of registers, which may reduce the memory consumption
* and increase accuracy when the cardinality is small.
*
* @param p The precision value for the normal set.
* `p` must be a value between 4 and `sp` if `sp` is not zero (32 max).
* @param sp The precision value for the sparse set, between 0 and 32.
* If `sp` equals 0, the sparse representation is skipped.
* @param partitioner Partitioner to use for the resulting RDD.
*/
@Experimental
def countApproxDistinctByKey(
p: Int,
sp: Int,
partitioner: Partitioner): RDD[(K, Long)] = self.withScope {
require(p >= 4, s"p ($p) must be >= 4")
require(sp <= 32, s"sp ($sp) must be <= 32")
require(sp == 0 || p <= sp, s"p ($p) cannot be greater than sp ($sp)")
val createHLL = (v: V) => {
val hll = new HyperLogLogPlus(p, sp)
hll.offer(v)
hll
}
val mergeValueHLL = (hll: HyperLogLogPlus, v: V) => {
hll.offer(v)
hll
}
val mergeHLL = (h1: HyperLogLogPlus, h2: HyperLogLogPlus) => {
h1.addAll(h2)
h1
}
combineByKey(createHLL, mergeValueHLL, mergeHLL, partitioner).mapValues(_.cardinality())
}
/**
* Return approximate number of distinct values for each key in this RDD.
*
* The algorithm used is based on streamlib's implementation of "HyperLogLog in Practice:
* Algorithmic Engineering of a State of The Art Cardinality Estimation Algorithm", available
* <a href="http://dx.doi.org/10.1145/2452376.2452456">here</a>.
*
* @param relativeSD Relative accuracy. Smaller values create counters that require more space.
* It must be greater than 0.000017.
* @param partitioner partitioner of the resulting RDD
*/
def countApproxDistinctByKey(
relativeSD: Double,
partitioner: Partitioner): RDD[(K, Long)] = self.withScope {
require(relativeSD > 0.000017, s"accuracy ($relativeSD) must be greater than 0.000017")
val p = math.ceil(2.0 * math.log(1.054 / relativeSD) / math.log(2)).toInt
assert(p <= 32)
countApproxDistinctByKey(if (p < 4) 4 else p, 0, partitioner)
}
/**
* Return approximate number of distinct values for each key in this RDD.
*
* The algorithm used is based on streamlib's implementation of "HyperLogLog in Practice:
* Algorithmic Engineering of a State of The Art Cardinality Estimation Algorithm", available
* <a href="http://dx.doi.org/10.1145/2452376.2452456">here</a>.
*
* @param relativeSD Relative accuracy. Smaller values create counters that require more space.
* It must be greater than 0.000017.
* @param numPartitions number of partitions of the resulting RDD
*/
def countApproxDistinctByKey(
relativeSD: Double,
numPartitions: Int): RDD[(K, Long)] = self.withScope {
countApproxDistinctByKey(relativeSD, new HashPartitioner(numPartitions))
}
/**
* Return approximate number of distinct values for each key in this RDD.
*
* The algorithm used is based on streamlib's implementation of "HyperLogLog in Practice:
* Algorithmic Engineering of a State of The Art Cardinality Estimation Algorithm", available
* <a href="http://dx.doi.org/10.1145/2452376.2452456">here</a>.
*
* @param relativeSD Relative accuracy. Smaller values create counters that require more space.
* It must be greater than 0.000017.
*/
def countApproxDistinctByKey(relativeSD: Double = 0.05): RDD[(K, Long)] = self.withScope {
countApproxDistinctByKey(relativeSD, defaultPartitioner(self))
}
/**
* Group the values for each key in the RDD into a single sequence. Allows controlling the
* partitioning of the resulting key-value pair RDD by passing a Partitioner.
* The ordering of elements within each group is not guaranteed, and may even differ
* each time the resulting RDD is evaluated.
*
* Note: This operation may be very expensive. If you are grouping in order to perform an
* aggregation (such as a sum or average) over each key, using [[PairRDDFunctions.aggregateByKey]]
* or [[PairRDDFunctions.reduceByKey]] will provide much better performance.
*
* Note: As currently implemented, groupByKey must be able to hold all the key-value pairs for any
* key in memory. If a key has too many values, it can result in an [[OutOfMemoryError]].
*/
def groupByKey(partitioner: Partitioner): RDD[(K, Iterable[V])] = self.withScope {
// groupByKey shouldn't use map side combine because map side combine does not
// reduce the amount of data shuffled and requires all map side data be inserted
// into a hash table, leading to more objects in the old gen.
val createCombiner = (v: V) => CompactBuffer(v)
val mergeValue = (buf: CompactBuffer[V], v: V) => buf += v
val mergeCombiners = (c1: CompactBuffer[V], c2: CompactBuffer[V]) => c1 ++= c2
val bufs = combineByKey[CompactBuffer[V]](
createCombiner, mergeValue, mergeCombiners, partitioner, mapSideCombine = false)
bufs.asInstanceOf[RDD[(K, Iterable[V])]]
}
/**
* Group the values for each key in the RDD into a single sequence. Hash-partitions the
* resulting RDD with into `numPartitions` partitions. The ordering of elements within
* each group is not guaranteed, and may even differ each time the resulting RDD is evaluated.
*
* Note: This operation may be very expensive. If you are grouping in order to perform an
* aggregation (such as a sum or average) over each key, using [[PairRDDFunctions.aggregateByKey]]
* or [[PairRDDFunctions.reduceByKey]] will provide much better performance.
*
* Note: As currently implemented, groupByKey must be able to hold all the key-value pairs for any
* key in memory. If a key has too many values, it can result in an [[OutOfMemoryError]].
*/
def groupByKey(numPartitions: Int): RDD[(K, Iterable[V])] = self.withScope {
groupByKey(new HashPartitioner(numPartitions))
}
/**
* Return a copy of the RDD partitioned using the specified partitioner.
*/
def partitionBy(partitioner: Partitioner): RDD[(K, V)] = self.withScope {
if (keyClass.isArray && partitioner.isInstanceOf[HashPartitioner]) {
throw new SparkException("Default partitioner cannot partition array keys.")
}
if (self.partitioner == Some(partitioner)) {
self
} else {
new ShuffledRDD[K, V, V](self, partitioner)
}
}
/**
* Return an RDD containing all pairs of elements with matching keys in `this` and `other`. Each
* pair of elements will be returned as a (k, (v1, v2)) tuple, where (k, v1) is in `this` and
* (k, v2) is in `other`. Uses the given Partitioner to partition the output RDD.
*/
def join[W](other: RDD[(K, W)], partitioner: Partitioner): RDD[(K, (V, W))] = self.withScope {
this.cogroup(other, partitioner).flatMapValues( pair =>
for (v <- pair._1.iterator; w <- pair._2.iterator) yield (v, w)
)
}
/**
* Perform a left outer join of `this` and `other`. For each element (k, v) in `this`, the
* resulting RDD will either contain all pairs (k, (v, Some(w))) for w in `other`, or the
* pair (k, (v, None)) if no elements in `other` have key k. Uses the given Partitioner to
* partition the output RDD.
*/
def leftOuterJoin[W](
other: RDD[(K, W)],
partitioner: Partitioner): RDD[(K, (V, Option[W]))] = self.withScope {
this.cogroup(other, partitioner).flatMapValues { pair =>
if (pair._2.isEmpty) {
pair._1.iterator.map(v => (v, None))
} else {
for (v <- pair._1.iterator; w <- pair._2.iterator) yield (v, Some(w))
}
}
}
/**
* Perform a right outer join of `this` and `other`. For each element (k, w) in `other`, the
* resulting RDD will either contain all pairs (k, (Some(v), w)) for v in `this`, or the
* pair (k, (None, w)) if no elements in `this` have key k. Uses the given Partitioner to
* partition the output RDD.
*/
def rightOuterJoin[W](other: RDD[(K, W)], partitioner: Partitioner)
: RDD[(K, (Option[V], W))] = self.withScope {
this.cogroup(other, partitioner).flatMapValues { pair =>
if (pair._1.isEmpty) {
pair._2.iterator.map(w => (None, w))
} else {
for (v <- pair._1.iterator; w <- pair._2.iterator) yield (Some(v), w)
}
}
}
/**
* Perform a full outer join of `this` and `other`. For each element (k, v) in `this`, the
* resulting RDD will either contain all pairs (k, (Some(v), Some(w))) for w in `other`, or
* the pair (k, (Some(v), None)) if no elements in `other` have key k. Similarly, for each
* element (k, w) in `other`, the resulting RDD will either contain all pairs
* (k, (Some(v), Some(w))) for v in `this`, or the pair (k, (None, Some(w))) if no elements
* in `this` have key k. Uses the given Partitioner to partition the output RDD.
*/
def fullOuterJoin[W](other: RDD[(K, W)], partitioner: Partitioner)
: RDD[(K, (Option[V], Option[W]))] = self.withScope {
this.cogroup(other, partitioner).flatMapValues {
case (vs, Seq()) => vs.iterator.map(v => (Some(v), None))
case (Seq(), ws) => ws.iterator.map(w => (None, Some(w)))
case (vs, ws) => for (v <- vs.iterator; w <- ws.iterator) yield (Some(v), Some(w))
}
}
/**
* Simplified version of combineByKey that hash-partitions the resulting RDD using the
* existing partitioner/parallelism level.
*/
def combineByKey[C](createCombiner: V => C, mergeValue: (C, V) => C, mergeCombiners: (C, C) => C)
: RDD[(K, C)] = self.withScope {
combineByKey(createCombiner, mergeValue, mergeCombiners, defaultPartitioner(self))
}
/**
* Group the values for each key in the RDD into a single sequence. Hash-partitions the
* resulting RDD with the existing partitioner/parallelism level. The ordering of elements
* within each group is not guaranteed, and may even differ each time the resulting RDD is
* evaluated.
*
* Note: This operation may be very expensive. If you are grouping in order to perform an
* aggregation (such as a sum or average) over each key, using [[PairRDDFunctions.aggregateByKey]]
* or [[PairRDDFunctions.reduceByKey]] will provide much better performance.
*/
def groupByKey(): RDD[(K, Iterable[V])] = self.withScope {
groupByKey(defaultPartitioner(self))
}
/**
* Return an RDD containing all pairs of elements with matching keys in `this` and `other`. Each
* pair of elements will be returned as a (k, (v1, v2)) tuple, where (k, v1) is in `this` and
* (k, v2) is in `other`. Performs a hash join across the cluster.
*/
def join[W](other: RDD[(K, W)]): RDD[(K, (V, W))] = self.withScope {
join(other, defaultPartitioner(self, other))
}
/**
* Return an RDD containing all pairs of elements with matching keys in `this` and `other`. Each
* pair of elements will be returned as a (k, (v1, v2)) tuple, where (k, v1) is in `this` and
* (k, v2) is in `other`. Performs a hash join across the cluster.
*/
def join[W](other: RDD[(K, W)], numPartitions: Int): RDD[(K, (V, W))] = self.withScope {
join(other, new HashPartitioner(numPartitions))
}
/**
* Perform a left outer join of `this` and `other`. For each element (k, v) in `this`, the
* resulting RDD will either contain all pairs (k, (v, Some(w))) for w in `other`, or the
* pair (k, (v, None)) if no elements in `other` have key k. Hash-partitions the output
* using the existing partitioner/parallelism level.
*/
def leftOuterJoin[W](other: RDD[(K, W)]): RDD[(K, (V, Option[W]))] = self.withScope {
leftOuterJoin(other, defaultPartitioner(self, other))
}
/**
* Perform a left outer join of `this` and `other`. For each element (k, v) in `this`, the
* resulting RDD will either contain all pairs (k, (v, Some(w))) for w in `other`, or the
* pair (k, (v, None)) if no elements in `other` have key k. Hash-partitions the output
* into `numPartitions` partitions.
*/
def leftOuterJoin[W](
other: RDD[(K, W)],
numPartitions: Int): RDD[(K, (V, Option[W]))] = self.withScope {
leftOuterJoin(other, new HashPartitioner(numPartitions))
}
/**
* Perform a right outer join of `this` and `other`. For each element (k, w) in `other`, the
* resulting RDD will either contain all pairs (k, (Some(v), w)) for v in `this`, or the
* pair (k, (None, w)) if no elements in `this` have key k. Hash-partitions the resulting
* RDD using the existing partitioner/parallelism level.
*/
def rightOuterJoin[W](other: RDD[(K, W)]): RDD[(K, (Option[V], W))] = self.withScope {
rightOuterJoin(other, defaultPartitioner(self, other))
}
/**
* Perform a right outer join of `this` and `other`. For each element (k, w) in `other`, the
* resulting RDD will either contain all pairs (k, (Some(v), w)) for v in `this`, or the
* pair (k, (None, w)) if no elements in `this` have key k. Hash-partitions the resulting
* RDD into the given number of partitions.
*/
def rightOuterJoin[W](
other: RDD[(K, W)],
numPartitions: Int): RDD[(K, (Option[V], W))] = self.withScope {
rightOuterJoin(other, new HashPartitioner(numPartitions))
}
/**
* Perform a full outer join of `this` and `other`. For each element (k, v) in `this`, the
* resulting RDD will either contain all pairs (k, (Some(v), Some(w))) for w in `other`, or
* the pair (k, (Some(v), None)) if no elements in `other` have key k. Similarly, for each
* element (k, w) in `other`, the resulting RDD will either contain all pairs
* (k, (Some(v), Some(w))) for v in `this`, or the pair (k, (None, Some(w))) if no elements
* in `this` have key k. Hash-partitions the resulting RDD using the existing partitioner/
* parallelism level.
*/
def fullOuterJoin[W](other: RDD[(K, W)]): RDD[(K, (Option[V], Option[W]))] = self.withScope {
fullOuterJoin(other, defaultPartitioner(self, other))
}
/**
* Perform a full outer join of `this` and `other`. For each element (k, v) in `this`, the
* resulting RDD will either contain all pairs (k, (Some(v), Some(w))) for w in `other`, or
* the pair (k, (Some(v), None)) if no elements in `other` have key k. Similarly, for each
* element (k, w) in `other`, the resulting RDD will either contain all pairs
* (k, (Some(v), Some(w))) for v in `this`, or the pair (k, (None, Some(w))) if no elements
* in `this` have key k. Hash-partitions the resulting RDD into the given number of partitions.
*/
def fullOuterJoin[W](
other: RDD[(K, W)],
numPartitions: Int): RDD[(K, (Option[V], Option[W]))] = self.withScope {
fullOuterJoin(other, new HashPartitioner(numPartitions))
}
/**
* Return the key-value pairs in this RDD to the master as a Map.
*
* Warning: this doesn't return a multimap (so if you have multiple values to the same key, only
* one value per key is preserved in the map returned)
*/
def collectAsMap(): Map[K, V] = self.withScope {
val data = self.collect()
val map = new mutable.HashMap[K, V]
map.sizeHint(data.length)
data.foreach { pair => map.put(pair._1, pair._2) }
map
}
/**
* Pass each value in the key-value pair RDD through a map function without changing the keys;
* this also retains the original RDD's partitioning.
*/
def mapValues[U](f: V => U): RDD[(K, U)] = self.withScope {
val cleanF = self.context.clean(f)
new MapPartitionsRDD[(K, U), (K, V)](self,
(context, pid, iter) => iter.map { case (k, v) => (k, cleanF(v)) },
preservesPartitioning = true)
}
/**
* Pass each value in the key-value pair RDD through a flatMap function without changing the
* keys; this also retains the original RDD's partitioning.
*/
def flatMapValues[U](f: V => TraversableOnce[U]): RDD[(K, U)] = self.withScope {
val cleanF = self.context.clean(f)
new MapPartitionsRDD[(K, U), (K, V)](self,
(context, pid, iter) => iter.flatMap { case (k, v) =>
cleanF(v).map(x => (k, x))
},
preservesPartitioning = true)
}
/**
* For each key k in `this` or `other1` or `other2` or `other3`,
* return a resulting RDD that contains a tuple with the list of values
* for that key in `this`, `other1`, `other2` and `other3`.
*/
def cogroup[W1, W2, W3](other1: RDD[(K, W1)],
other2: RDD[(K, W2)],
other3: RDD[(K, W3)],
partitioner: Partitioner)
: RDD[(K, (Iterable[V], Iterable[W1], Iterable[W2], Iterable[W3]))] = self.withScope {
if (partitioner.isInstanceOf[HashPartitioner] && keyClass.isArray) {
throw new SparkException("Default partitioner cannot partition array keys.")
}
val cg = new CoGroupedRDD[K](Seq(self, other1, other2, other3), partitioner)
cg.mapValues { case Array(vs, w1s, w2s, w3s) =>
(vs.asInstanceOf[Iterable[V]],
w1s.asInstanceOf[Iterable[W1]],
w2s.asInstanceOf[Iterable[W2]],
w3s.asInstanceOf[Iterable[W3]])
}
}
/**
* For each key k in `this` or `other`, return a resulting RDD that contains a tuple with the
* list of values for that key in `this` as well as `other`.
*/
def cogroup[W](other: RDD[(K, W)], partitioner: Partitioner)
: RDD[(K, (Iterable[V], Iterable[W]))] = self.withScope {
if (partitioner.isInstanceOf[HashPartitioner] && keyClass.isArray) {
throw new SparkException("Default partitioner cannot partition array keys.")
}
val cg = new CoGroupedRDD[K](Seq(self, other), partitioner)
cg.mapValues { case Array(vs, w1s) =>
(vs.asInstanceOf[Iterable[V]], w1s.asInstanceOf[Iterable[W]])
}
}
/**
* For each key k in `this` or `other1` or `other2`, return a resulting RDD that contains a
* tuple with the list of values for that key in `this`, `other1` and `other2`.
*/
def cogroup[W1, W2](other1: RDD[(K, W1)], other2: RDD[(K, W2)], partitioner: Partitioner)
: RDD[(K, (Iterable[V], Iterable[W1], Iterable[W2]))] = self.withScope {
if (partitioner.isInstanceOf[HashPartitioner] && keyClass.isArray) {
throw new SparkException("Default partitioner cannot partition array keys.")
}
val cg = new CoGroupedRDD[K](Seq(self, other1, other2), partitioner)
cg.mapValues { case Array(vs, w1s, w2s) =>
(vs.asInstanceOf[Iterable[V]],
w1s.asInstanceOf[Iterable[W1]],
w2s.asInstanceOf[Iterable[W2]])
}
}
/**
* For each key k in `this` or `other1` or `other2` or `other3`,
* return a resulting RDD that contains a tuple with the list of values
* for that key in `this`, `other1`, `other2` and `other3`.
*/
def cogroup[W1, W2, W3](other1: RDD[(K, W1)], other2: RDD[(K, W2)], other3: RDD[(K, W3)])
: RDD[(K, (Iterable[V], Iterable[W1], Iterable[W2], Iterable[W3]))] = self.withScope {
cogroup(other1, other2, other3, defaultPartitioner(self, other1, other2, other3))
}
/**
* For each key k in `this` or `other`, return a resulting RDD that contains a tuple with the
* list of values for that key in `this` as well as `other`.
*/
def cogroup[W](other: RDD[(K, W)]): RDD[(K, (Iterable[V], Iterable[W]))] = self.withScope {
cogroup(other, defaultPartitioner(self, other))
}
/**
* For each key k in `this` or `other1` or `other2`, return a resulting RDD that contains a
* tuple with the list of values for that key in `this`, `other1` and `other2`.
*/
def cogroup[W1, W2](other1: RDD[(K, W1)], other2: RDD[(K, W2)])
: RDD[(K, (Iterable[V], Iterable[W1], Iterable[W2]))] = self.withScope {
cogroup(other1, other2, defaultPartitioner(self, other1, other2))
}
/**
* For each key k in `this` or `other`, return a resulting RDD that contains a tuple with the
* list of values for that key in `this` as well as `other`.
*/
def cogroup[W](
other: RDD[(K, W)],
numPartitions: Int): RDD[(K, (Iterable[V], Iterable[W]))] = self.withScope {
cogroup(other, new HashPartitioner(numPartitions))
}
/**
* For each key k in `this` or `other1` or `other2`, return a resulting RDD that contains a
* tuple with the list of values for that key in `this`, `other1` and `other2`.
*/
def cogroup[W1, W2](other1: RDD[(K, W1)], other2: RDD[(K, W2)], numPartitions: Int)
: RDD[(K, (Iterable[V], Iterable[W1], Iterable[W2]))] = self.withScope {
cogroup(other1, other2, new HashPartitioner(numPartitions))
}
/**
* For each key k in `this` or `other1` or `other2` or `other3`,
* return a resulting RDD that contains a tuple with the list of values
* for that key in `this`, `other1`, `other2` and `other3`.
*/
def cogroup[W1, W2, W3](other1: RDD[(K, W1)],
other2: RDD[(K, W2)],
other3: RDD[(K, W3)],
numPartitions: Int)
: RDD[(K, (Iterable[V], Iterable[W1], Iterable[W2], Iterable[W3]))] = self.withScope {
cogroup(other1, other2, other3, new HashPartitioner(numPartitions))
}
/** Alias for cogroup. */
def groupWith[W](other: RDD[(K, W)]): RDD[(K, (Iterable[V], Iterable[W]))] = self.withScope {
cogroup(other, defaultPartitioner(self, other))
}
/** Alias for cogroup. */
def groupWith[W1, W2](other1: RDD[(K, W1)], other2: RDD[(K, W2)])
: RDD[(K, (Iterable[V], Iterable[W1], Iterable[W2]))] = self.withScope {
cogroup(other1, other2, defaultPartitioner(self, other1, other2))
}
/** Alias for cogroup. */
def groupWith[W1, W2, W3](other1: RDD[(K, W1)], other2: RDD[(K, W2)], other3: RDD[(K, W3)])
: RDD[(K, (Iterable[V], Iterable[W1], Iterable[W2], Iterable[W3]))] = self.withScope {
cogroup(other1, other2, other3, defaultPartitioner(self, other1, other2, other3))
}
/**
* Return an RDD with the pairs from `this` whose keys are not in `other`.
*
* Uses `this` partitioner/partition size, because even if `other` is huge, the resulting
* RDD will be <= us.
*/
def subtractByKey[W: ClassTag](other: RDD[(K, W)]): RDD[(K, V)] = self.withScope {
subtractByKey(other, self.partitioner.getOrElse(new HashPartitioner(self.partitions.length)))
}
/** Return an RDD with the pairs from `this` whose keys are not in `other`. */
def subtractByKey[W: ClassTag](
other: RDD[(K, W)],
numPartitions: Int): RDD[(K, V)] = self.withScope {
subtractByKey(other, new HashPartitioner(numPartitions))
}
/** Return an RDD with the pairs from `this` whose keys are not in `other`. */
def subtractByKey[W: ClassTag](other: RDD[(K, W)], p: Partitioner): RDD[(K, V)] = self.withScope {
new SubtractedRDD[K, V, W](self, other, p)
}
/**
* Return the list of values in the RDD for key `key`. This operation is done efficiently if the
* RDD has a known partitioner by only searching the partition that the key maps to.
*/
def lookup(key: K): Seq[V] = self.withScope {
self.partitioner match {
case Some(p) =>
val index = p.getPartition(key)
val process = (it: Iterator[(K, V)]) => {
val buf = new ArrayBuffer[V]
for (pair <- it if pair._1 == key) {
buf += pair._2
}
buf
} : Seq[V]
val res = self.context.runJob(self, process, Array(index), false)
res(0)
case None =>
self.filter(_._1 == key).map(_._2).collect()
}
}
/**
* Output the RDD to any Hadoop-supported file system, using a Hadoop `OutputFormat` class
* supporting the key and value types K and V in this RDD.
*/
def saveAsHadoopFile[F <: OutputFormat[K, V]](
path: String)(implicit fm: ClassTag[F]): Unit = self.withScope {
saveAsHadoopFile(path, keyClass, valueClass, fm.runtimeClass.asInstanceOf[Class[F]])
}
/**
* Output the RDD to any Hadoop-supported file system, using a Hadoop `OutputFormat` class
* supporting the key and value types K and V in this RDD. Compress the result with the
* supplied codec.
*/
def saveAsHadoopFile[F <: OutputFormat[K, V]](
path: String,
codec: Class[_ <: CompressionCodec])(implicit fm: ClassTag[F]): Unit = self.withScope {
val runtimeClass = fm.runtimeClass
saveAsHadoopFile(path, keyClass, valueClass, runtimeClass.asInstanceOf[Class[F]], codec)
}
/**
* Output the RDD to any Hadoop-supported file system, using a new Hadoop API `OutputFormat`
* (mapreduce.OutputFormat) object supporting the key and value types K and V in this RDD.
*/
def saveAsNewAPIHadoopFile[F <: NewOutputFormat[K, V]](
path: String)(implicit fm: ClassTag[F]): Unit = self.withScope {
saveAsNewAPIHadoopFile(path, keyClass, valueClass, fm.runtimeClass.asInstanceOf[Class[F]])
}
/**
* Output the RDD to any Hadoop-supported file system, using a new Hadoop API `OutputFormat`
* (mapreduce.OutputFormat) object supporting the key and value types K and V in this RDD.
*/
def saveAsNewAPIHadoopFile(
path: String,
keyClass: Class[_],
valueClass: Class[_],
outputFormatClass: Class[_ <: NewOutputFormat[_, _]],
conf: Configuration = self.context.hadoopConfiguration): Unit = self.withScope {
// Rename this as hadoopConf internally to avoid shadowing (see SPARK-2038).
val hadoopConf = conf
val job = new NewAPIHadoopJob(hadoopConf)
job.setOutputKeyClass(keyClass)
job.setOutputValueClass(valueClass)
job.setOutputFormatClass(outputFormatClass)
job.getConfiguration.set("mapred.output.dir", path)
saveAsNewAPIHadoopDataset(job.getConfiguration)
}
/**
* Output the RDD to any Hadoop-supported file system, using a Hadoop `OutputFormat` class
* supporting the key and value types K and V in this RDD. Compress with the supplied codec.
*/
def saveAsHadoopFile(
path: String,
keyClass: Class[_],
valueClass: Class[_],
outputFormatClass: Class[_ <: OutputFormat[_, _]],
codec: Class[_ <: CompressionCodec]): Unit = self.withScope {
saveAsHadoopFile(path, keyClass, valueClass, outputFormatClass,
new JobConf(self.context.hadoopConfiguration), Some(codec))
}
/**
* Output the RDD to any Hadoop-supported file system, using a Hadoop `OutputFormat` class
* supporting the key and value types K and V in this RDD.
*/
def saveAsHadoopFile(
path: String,
keyClass: Class[_],
valueClass: Class[_],
outputFormatClass: Class[_ <: OutputFormat[_, _]],
conf: JobConf = new JobConf(self.context.hadoopConfiguration),
codec: Option[Class[_ <: CompressionCodec]] = None): Unit = self.withScope {
// Rename this as hadoopConf internally to avoid shadowing (see SPARK-2038).
val hadoopConf = conf
hadoopConf.setOutputKeyClass(keyClass)
hadoopConf.setOutputValueClass(valueClass)
// Doesn't work in Scala 2.9 due to what may be a generics bug
// TODO: Should we uncomment this for Scala 2.10?
// conf.setOutputFormat(outputFormatClass)
hadoopConf.set("mapred.output.format.class", outputFormatClass.getName)
for (c <- codec) {
hadoopConf.setCompressMapOutput(true)
hadoopConf.set("mapred.output.compress", "true")
hadoopConf.setMapOutputCompressorClass(c)
hadoopConf.set("mapred.output.compression.codec", c.getCanonicalName)
hadoopConf.set("mapred.output.compression.type", CompressionType.BLOCK.toString)
}
// Use configured output committer if already set
if (conf.getOutputCommitter == null) {
hadoopConf.setOutputCommitter(classOf[FileOutputCommitter])
}
FileOutputFormat.setOutputPath(hadoopConf,
SparkHadoopWriter.createPathFromString(path, hadoopConf))
saveAsHadoopDataset(hadoopConf)
}
/**
* Output the RDD to any Hadoop-supported storage system with new Hadoop API, using a Hadoop
* Configuration object for that storage system. The Conf should set an OutputFormat and any
* output paths required (e.g. a table name to write to) in the same way as it would be
* configured for a Hadoop MapReduce job.
*/
def saveAsNewAPIHadoopDataset(conf: Configuration): Unit = self.withScope {
// Rename this as hadoopConf internally to avoid shadowing (see SPARK-2038).
val hadoopConf = conf
val job = new NewAPIHadoopJob(hadoopConf)
val formatter = new SimpleDateFormat("yyyyMMddHHmm")
val jobtrackerID = formatter.format(new Date())
val stageId = self.id
val wrappedConf = new SerializableConfiguration(job.getConfiguration)
val outfmt = job.getOutputFormatClass
val jobFormat = outfmt.newInstance
if (isOutputSpecValidationEnabled) {
// FileOutputFormat ignores the filesystem parameter
jobFormat.checkOutputSpecs(job)
}
val writeShard = (context: TaskContext, iter: Iterator[(K, V)]) => {
val config = wrappedConf.value
/* "reduce task" <split #> <attempt # = spark task #> */
val attemptId = newTaskAttemptID(jobtrackerID, stageId, isMap = false, context.partitionId,
context.attemptNumber)
val hadoopContext = newTaskAttemptContext(config, attemptId)
val format = outfmt.newInstance
format match {
case c: Configurable => c.setConf(config)
case _ => ()
}
val committer = format.getOutputCommitter(hadoopContext)
committer.setupTask(hadoopContext)
val (outputMetrics, bytesWrittenCallback) = initHadoopOutputMetrics(context)
val writer = format.getRecordWriter(hadoopContext).asInstanceOf[NewRecordWriter[K, V]]
require(writer != null, "Unable to obtain RecordWriter")
var recordsWritten = 0L
Utils.tryWithSafeFinally {
while (iter.hasNext) {
val pair = iter.next()
writer.write(pair._1, pair._2)
// Update bytes written metric every few records
maybeUpdateOutputMetrics(bytesWrittenCallback, outputMetrics, recordsWritten)
recordsWritten += 1
}
} {
writer.close(hadoopContext)
}
committer.commitTask(hadoopContext)
bytesWrittenCallback.foreach { fn => outputMetrics.setBytesWritten(fn()) }
outputMetrics.setRecordsWritten(recordsWritten)
1
} : Int
val jobAttemptId = newTaskAttemptID(jobtrackerID, stageId, isMap = true, 0, 0)
val jobTaskContext = newTaskAttemptContext(wrappedConf.value, jobAttemptId)
val jobCommitter = jobFormat.getOutputCommitter(jobTaskContext)
jobCommitter.setupJob(jobTaskContext)
self.context.runJob(self, writeShard)
jobCommitter.commitJob(jobTaskContext)
}
/**
* Output the RDD to any Hadoop-supported storage system, using a Hadoop JobConf object for
* that storage system. The JobConf should set an OutputFormat and any output paths required
* (e.g. a table name to write to) in the same way as it would be configured for a Hadoop
* MapReduce job.
*/
def saveAsHadoopDataset(conf: JobConf): Unit = self.withScope {
// Rename this as hadoopConf internally to avoid shadowing (see SPARK-2038).
val hadoopConf = conf
val wrappedConf = new SerializableConfiguration(hadoopConf)
val outputFormatInstance = hadoopConf.getOutputFormat
val keyClass = hadoopConf.getOutputKeyClass
val valueClass = hadoopConf.getOutputValueClass
if (outputFormatInstance == null) {
throw new SparkException("Output format class not set")
}
if (keyClass == null) {
throw new SparkException("Output key class not set")
}
if (valueClass == null) {
throw new SparkException("Output value class not set")
}
SparkHadoopUtil.get.addCredentials(hadoopConf)
logDebug("Saving as hadoop file of type (" + keyClass.getSimpleName + ", " +
valueClass.getSimpleName + ")")
if (isOutputSpecValidationEnabled) {
// FileOutputFormat ignores the filesystem parameter
val ignoredFs = FileSystem.get(hadoopConf)
hadoopConf.getOutputFormat.checkOutputSpecs(ignoredFs, hadoopConf)
}
val writer = new SparkHadoopWriter(hadoopConf)
writer.preSetup()
val writeToFile = (context: TaskContext, iter: Iterator[(K, V)]) => {
val config = wrappedConf.value
// Hadoop wants a 32-bit task attempt ID, so if ours is bigger than Int.MaxValue, roll it
// around by taking a mod. We expect that no task will be attempted 2 billion times.
val taskAttemptId = (context.taskAttemptId % Int.MaxValue).toInt
val (outputMetrics, bytesWrittenCallback) = initHadoopOutputMetrics(context)
writer.setup(context.stageId, context.partitionId, taskAttemptId)
writer.open()
var recordsWritten = 0L
Utils.tryWithSafeFinally {
while (iter.hasNext) {
val record = iter.next()
writer.write(record._1.asInstanceOf[AnyRef], record._2.asInstanceOf[AnyRef])
// Update bytes written metric every few records
maybeUpdateOutputMetrics(bytesWrittenCallback, outputMetrics, recordsWritten)
recordsWritten += 1
}
} {
writer.close()
}
writer.commit()
bytesWrittenCallback.foreach { fn => outputMetrics.setBytesWritten(fn()) }
outputMetrics.setRecordsWritten(recordsWritten)
}
self.context.runJob(self, writeToFile)
writer.commitJob()
}
private def initHadoopOutputMetrics(context: TaskContext): (OutputMetrics, Option[() => Long]) = {
val bytesWrittenCallback = SparkHadoopUtil.get.getFSBytesWrittenOnThreadCallback()
val outputMetrics = new OutputMetrics(DataWriteMethod.Hadoop)
if (bytesWrittenCallback.isDefined) {
context.taskMetrics.outputMetrics = Some(outputMetrics)
}
(outputMetrics, bytesWrittenCallback)
}
private def maybeUpdateOutputMetrics(bytesWrittenCallback: Option[() => Long],
outputMetrics: OutputMetrics, recordsWritten: Long): Unit = {
if (recordsWritten % PairRDDFunctions.RECORDS_BETWEEN_BYTES_WRITTEN_METRIC_UPDATES == 0) {
bytesWrittenCallback.foreach { fn => outputMetrics.setBytesWritten(fn()) }
outputMetrics.setRecordsWritten(recordsWritten)
}
}
/**
* Return an RDD with the keys of each tuple.
*/
def keys: RDD[K] = self.map(_._1)
/**
* Return an RDD with the values of each tuple.
*/
def values: RDD[V] = self.map(_._2)
private[spark] def keyClass: Class[_] = kt.runtimeClass
private[spark] def valueClass: Class[_] = vt.runtimeClass
private[spark] def keyOrdering: Option[Ordering[K]] = Option(ord)
// Note: this needs to be a function instead of a 'val' so that the disableOutputSpecValidation
// setting can take effect:
private def isOutputSpecValidationEnabled: Boolean = {
val validationDisabled = PairRDDFunctions.disableOutputSpecValidation.value
val enabledInConf = self.conf.getBoolean("spark.hadoop.validateOutputSpecs", true)
enabledInConf && !validationDisabled
}
}
private[spark] object PairRDDFunctions {
val RECORDS_BETWEEN_BYTES_WRITTEN_METRIC_UPDATES = 256
/**
* Allows for the `spark.hadoop.validateOutputSpecs` checks to be disabled on a case-by-case
* basis; see SPARK-4835 for more details.
*/
val disableOutputSpecValidation: DynamicVariable[Boolean] = new DynamicVariable[Boolean](false)
}
|