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
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
|
/*
* 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
import java.io._
import java.net.URI
import java.util.concurrent.atomic.AtomicInteger
import java.util.{Properties, UUID}
import java.util.UUID.randomUUID
import scala.collection.{Map, Set}
import scala.collection.generic.Growable
import scala.collection.mutable.{ArrayBuffer, HashMap}
import scala.language.implicitConversions
import scala.reflect.{ClassTag, classTag}
import org.apache.hadoop.conf.Configuration
import org.apache.hadoop.fs.Path
import org.apache.hadoop.io.{ArrayWritable, BooleanWritable, BytesWritable, DoubleWritable, FloatWritable, IntWritable, LongWritable, NullWritable, Text, Writable}
import org.apache.hadoop.mapred.{FileInputFormat, InputFormat, JobConf, SequenceFileInputFormat, TextInputFormat}
import org.apache.hadoop.mapreduce.{InputFormat => NewInputFormat, Job => NewHadoopJob}
import org.apache.hadoop.mapreduce.lib.input.{FileInputFormat => NewFileInputFormat}
import org.apache.mesos.MesosNativeLibrary
import org.apache.spark.annotation.{DeveloperApi, Experimental}
import org.apache.spark.broadcast.Broadcast
import org.apache.spark.deploy.{LocalSparkCluster, SparkHadoopUtil}
import org.apache.spark.input.WholeTextFileInputFormat
import org.apache.spark.partial.{ApproximateEvaluator, PartialResult}
import org.apache.spark.rdd._
import org.apache.spark.scheduler._
import org.apache.spark.scheduler.cluster.{CoarseGrainedSchedulerBackend, SparkDeploySchedulerBackend, SimrSchedulerBackend}
import org.apache.spark.scheduler.cluster.mesos.{CoarseMesosSchedulerBackend, MesosSchedulerBackend}
import org.apache.spark.scheduler.local.LocalBackend
import org.apache.spark.storage.{BlockManagerSource, RDDInfo, StorageStatus, StorageUtils}
import org.apache.spark.ui.SparkUI
import org.apache.spark.util.{ClosureCleaner, MetadataCleaner, MetadataCleanerType, TimeStampedWeakValueHashMap, Utils}
/**
* :: DeveloperApi ::
* Main entry point for Spark functionality. A SparkContext represents the connection to a Spark
* cluster, and can be used to create RDDs, accumulators and broadcast variables on that cluster.
*
* @param config a Spark Config object describing the application configuration. Any settings in
* this config overrides the default configs as well as system properties.
*/
@DeveloperApi
class SparkContext(config: SparkConf) extends Logging {
// This is used only by YARN for now, but should be relevant to other cluster types (Mesos,
// etc) too. This is typically generated from InputFormatInfo.computePreferredLocations. It
// contains a map from hostname to a list of input format splits on the host.
private[spark] var preferredNodeLocationData: Map[String, Set[SplitInfo]] = Map()
/**
* :: DeveloperApi ::
* Alternative constructor for setting preferred locations where Spark will create executors.
*
* @param preferredNodeLocationData used in YARN mode to select nodes to launch containers on. Ca
* be generated using [[org.apache.spark.scheduler.InputFormatInfo.computePreferredLocations]]
* from a list of input files or InputFormats for the application.
*/
@DeveloperApi
def this(config: SparkConf, preferredNodeLocationData: Map[String, Set[SplitInfo]]) = {
this(config)
this.preferredNodeLocationData = preferredNodeLocationData
}
/**
* Alternative constructor that allows setting common Spark properties directly
*
* @param master Cluster URL to connect to (e.g. mesos://host:port, spark://host:port, local[4]).
* @param appName A name for your application, to display on the cluster web UI
* @param conf a [[org.apache.spark.SparkConf]] object specifying other Spark parameters
*/
def this(master: String, appName: String, conf: SparkConf) =
this(SparkContext.updatedConf(conf, master, appName))
/**
* Alternative constructor that allows setting common Spark properties directly
*
* @param master Cluster URL to connect to (e.g. mesos://host:port, spark://host:port, local[4]).
* @param appName A name for your application, to display on the cluster web UI.
* @param sparkHome Location where Spark is installed on cluster nodes.
* @param jars Collection of JARs to send to the cluster. These can be paths on the local file
* system or HDFS, HTTP, HTTPS, or FTP URLs.
* @param environment Environment variables to set on worker nodes.
*/
def this(
master: String,
appName: String,
sparkHome: String = null,
jars: Seq[String] = Nil,
environment: Map[String, String] = Map(),
preferredNodeLocationData: Map[String, Set[SplitInfo]] = Map()) =
{
this(SparkContext.updatedConf(new SparkConf(), master, appName, sparkHome, jars, environment))
this.preferredNodeLocationData = preferredNodeLocationData
}
// NOTE: The below constructors could be consolidated using default arguments. Due to
// Scala bug SI-8479, however, this causes the compile step to fail when generating docs.
// Until we have a good workaround for that bug the constructors remain broken out.
/**
* Alternative constructor that allows setting common Spark properties directly
*
* @param master Cluster URL to connect to (e.g. mesos://host:port, spark://host:port, local[4]).
* @param appName A name for your application, to display on the cluster web UI.
*/
private[spark] def this(master: String, appName: String) =
this(master, appName, null, Nil, Map(), Map())
/**
* Alternative constructor that allows setting common Spark properties directly
*
* @param master Cluster URL to connect to (e.g. mesos://host:port, spark://host:port, local[4]).
* @param appName A name for your application, to display on the cluster web UI.
* @param sparkHome Location where Spark is installed on cluster nodes.
*/
private[spark] def this(master: String, appName: String, sparkHome: String) =
this(master, appName, sparkHome, Nil, Map(), Map())
/**
* Alternative constructor that allows setting common Spark properties directly
*
* @param master Cluster URL to connect to (e.g. mesos://host:port, spark://host:port, local[4]).
* @param appName A name for your application, to display on the cluster web UI.
* @param sparkHome Location where Spark is installed on cluster nodes.
* @param jars Collection of JARs to send to the cluster. These can be paths on the local file
* system or HDFS, HTTP, HTTPS, or FTP URLs.
*/
private[spark] def this(master: String, appName: String, sparkHome: String, jars: Seq[String]) =
this(master, appName, sparkHome, jars, Map(), Map())
private[spark] val conf = config.clone()
conf.validateSettings()
/**
* Return a copy of this SparkContext's configuration. The configuration ''cannot'' be
* changed at runtime.
*/
def getConf: SparkConf = conf.clone()
if (!conf.contains("spark.master")) {
throw new SparkException("A master URL must be set in your configuration")
}
if (!conf.contains("spark.app.name")) {
throw new SparkException("An application name must be set in your configuration")
}
if (conf.getBoolean("spark.logConf", false)) {
logInfo("Spark configuration:\n" + conf.toDebugString)
}
// Set Spark driver host and port system properties
conf.setIfMissing("spark.driver.host", Utils.localHostName())
conf.setIfMissing("spark.driver.port", "0")
val jars: Seq[String] =
conf.getOption("spark.jars").map(_.split(",")).map(_.filter(_.size != 0)).toSeq.flatten
val files: Seq[String] =
conf.getOption("spark.files").map(_.split(",")).map(_.filter(_.size != 0)).toSeq.flatten
val master = conf.get("spark.master")
val appName = conf.get("spark.app.name")
// Generate the random name for a temp folder in Tachyon
// Add a timestamp as the suffix here to make it more safe
val tachyonFolderName = "spark-" + randomUUID.toString()
conf.set("spark.tachyonStore.folderName", tachyonFolderName)
val isLocal = (master == "local" || master.startsWith("local["))
if (master == "yarn-client") System.setProperty("SPARK_YARN_MODE", "true")
// An asynchronous listener bus for Spark events
private[spark] val listenerBus = new LiveListenerBus
// Create the Spark execution environment (cache, map output tracker, etc)
private[spark] val env = SparkEnv.create(
conf,
"<driver>",
conf.get("spark.driver.host"),
conf.get("spark.driver.port").toInt,
isDriver = true,
isLocal = isLocal,
listenerBus = listenerBus)
SparkEnv.set(env)
// Used to store a URL for each static file/jar together with the file's local timestamp
private[spark] val addedFiles = HashMap[String, Long]()
private[spark] val addedJars = HashMap[String, Long]()
// Keeps track of all persisted RDDs
private[spark] val persistentRdds = new TimeStampedWeakValueHashMap[Int, RDD[_]]
private[spark] val metadataCleaner =
new MetadataCleaner(MetadataCleanerType.SPARK_CONTEXT, this.cleanup, conf)
// Initialize the Spark UI, registering all associated listeners
private[spark] val ui = new SparkUI(this)
ui.bind()
/** A default Hadoop Configuration for the Hadoop code (e.g. file systems) that we reuse. */
val hadoopConfiguration: Configuration = {
val env = SparkEnv.get
val hadoopConf = SparkHadoopUtil.get.newConfiguration()
// Explicitly check for S3 environment variables
if (System.getenv("AWS_ACCESS_KEY_ID") != null &&
System.getenv("AWS_SECRET_ACCESS_KEY") != null) {
hadoopConf.set("fs.s3.awsAccessKeyId", System.getenv("AWS_ACCESS_KEY_ID"))
hadoopConf.set("fs.s3n.awsAccessKeyId", System.getenv("AWS_ACCESS_KEY_ID"))
hadoopConf.set("fs.s3.awsSecretAccessKey", System.getenv("AWS_SECRET_ACCESS_KEY"))
hadoopConf.set("fs.s3n.awsSecretAccessKey", System.getenv("AWS_SECRET_ACCESS_KEY"))
}
// Copy any "spark.hadoop.foo=bar" system properties into conf as "foo=bar"
conf.getAll.foreach { case (key, value) =>
if (key.startsWith("spark.hadoop.")) {
hadoopConf.set(key.substring("spark.hadoop.".length), value)
}
}
val bufferSize = conf.get("spark.buffer.size", "65536")
hadoopConf.set("io.file.buffer.size", bufferSize)
hadoopConf
}
// Optionally log Spark events
private[spark] val eventLogger: Option[EventLoggingListener] = {
if (conf.getBoolean("spark.eventLog.enabled", false)) {
val logger = new EventLoggingListener(appName, conf, hadoopConfiguration)
logger.start()
listenerBus.addListener(logger)
Some(logger)
} else None
}
// At this point, all relevant SparkListeners have been registered, so begin releasing events
listenerBus.start()
val startTime = System.currentTimeMillis()
// Add each JAR given through the constructor
if (jars != null) {
jars.foreach(addJar)
}
if (files != null) {
files.foreach(addFile)
}
private def warnSparkMem(value: String): String = {
logWarning("Using SPARK_MEM to set amount of memory to use per executor process is " +
"deprecated, please use spark.executor.memory instead.")
value
}
private[spark] val executorMemory = conf.getOption("spark.executor.memory")
.orElse(Option(System.getenv("SPARK_EXECUTOR_MEMORY")))
.orElse(Option(System.getenv("SPARK_MEM")).map(warnSparkMem))
.map(Utils.memoryStringToMb)
.getOrElse(512)
// Environment variables to pass to our executors.
// NOTE: This should only be used for test related settings.
private[spark] val testExecutorEnvs = HashMap[String, String]()
// Convert java options to env vars as a work around
// since we can't set env vars directly in sbt.
for { (envKey, propKey) <- Seq(("SPARK_TESTING", "spark.testing"))
value <- Option(System.getenv(envKey)).orElse(Option(System.getProperty(propKey)))} {
testExecutorEnvs(envKey) = value
}
// The Mesos scheduler backend relies on this environment variable to set executor memory.
// TODO: Set this only in the Mesos scheduler.
testExecutorEnvs("SPARK_EXECUTOR_MEMORY") = executorMemory + "m"
testExecutorEnvs ++= conf.getExecutorEnv
// Set SPARK_USER for user who is running SparkContext.
val sparkUser = Option {
Option(System.getProperty("user.name")).getOrElse(System.getenv("SPARK_USER"))
}.getOrElse {
SparkContext.SPARK_UNKNOWN_USER
}
testExecutorEnvs("SPARK_USER") = sparkUser
// Create and start the scheduler
private[spark] var taskScheduler = SparkContext.createTaskScheduler(this, master)
@volatile private[spark] var dagScheduler: DAGScheduler = _
try {
dagScheduler = new DAGScheduler(this)
} catch {
case e: Exception => throw
new SparkException("DAGScheduler cannot be initialized due to %s".format(e.getMessage))
}
// start TaskScheduler after taskScheduler sets DAGScheduler reference in DAGScheduler's
// constructor
taskScheduler.start()
private[spark] val cleaner: Option[ContextCleaner] = {
if (conf.getBoolean("spark.cleaner.referenceTracking", true)) {
Some(new ContextCleaner(this))
} else {
None
}
}
cleaner.foreach(_.start())
postEnvironmentUpdate()
postApplicationStart()
private[spark] var checkpointDir: Option[String] = None
// Thread Local variable that can be used by users to pass information down the stack
private val localProperties = new InheritableThreadLocal[Properties] {
override protected def childValue(parent: Properties): Properties = new Properties(parent)
}
private[spark] def getLocalProperties: Properties = localProperties.get()
private[spark] def setLocalProperties(props: Properties) {
localProperties.set(props)
}
@deprecated("Properties no longer need to be explicitly initialized.", "1.0.0")
def initLocalProperties() {
localProperties.set(new Properties())
}
/**
* Set a local property that affects jobs submitted from this thread, such as the
* Spark fair scheduler pool.
*/
def setLocalProperty(key: String, value: String) {
if (localProperties.get() == null) {
localProperties.set(new Properties())
}
if (value == null) {
localProperties.get.remove(key)
} else {
localProperties.get.setProperty(key, value)
}
}
/**
* Get a local property set in this thread, or null if it is missing. See
* [[org.apache.spark.SparkContext.setLocalProperty]].
*/
def getLocalProperty(key: String): String =
Option(localProperties.get).map(_.getProperty(key)).getOrElse(null)
/** Set a human readable description of the current job. */
@deprecated("use setJobGroup", "0.8.1")
def setJobDescription(value: String) {
setLocalProperty(SparkContext.SPARK_JOB_DESCRIPTION, value)
}
/**
* Assigns a group ID to all the jobs started by this thread until the group ID is set to a
* different value or cleared.
*
* Often, a unit of execution in an application consists of multiple Spark actions or jobs.
* Application programmers can use this method to group all those jobs together and give a
* group description. Once set, the Spark web UI will associate such jobs with this group.
*
* The application can also use [[org.apache.spark.SparkContext.cancelJobGroup]] to cancel all
* running jobs in this group. For example,
* {{{
* // In the main thread:
* sc.setJobGroup("some_job_to_cancel", "some job description")
* sc.parallelize(1 to 10000, 2).map { i => Thread.sleep(10); i }.count()
*
* // In a separate thread:
* sc.cancelJobGroup("some_job_to_cancel")
* }}}
*
* If interruptOnCancel is set to true for the job group, then job cancellation will result
* in Thread.interrupt() being called on the job's executor threads. This is useful to help ensure
* that the tasks are actually stopped in a timely manner, but is off by default due to HDFS-1208,
* where HDFS may respond to Thread.interrupt() by marking nodes as dead.
*/
def setJobGroup(groupId: String, description: String, interruptOnCancel: Boolean = false) {
setLocalProperty(SparkContext.SPARK_JOB_DESCRIPTION, description)
setLocalProperty(SparkContext.SPARK_JOB_GROUP_ID, groupId)
// Note: Specifying interruptOnCancel in setJobGroup (rather than cancelJobGroup) avoids
// changing several public APIs and allows Spark cancellations outside of the cancelJobGroup
// APIs to also take advantage of this property (e.g., internal job failures or canceling from
// JobProgressTab UI) on a per-job basis.
setLocalProperty(SparkContext.SPARK_JOB_INTERRUPT_ON_CANCEL, interruptOnCancel.toString)
}
/** Clear the current thread's job group ID and its description. */
def clearJobGroup() {
setLocalProperty(SparkContext.SPARK_JOB_DESCRIPTION, null)
setLocalProperty(SparkContext.SPARK_JOB_GROUP_ID, null)
setLocalProperty(SparkContext.SPARK_JOB_INTERRUPT_ON_CANCEL, null)
}
// Post init
taskScheduler.postStartHook()
private val dagSchedulerSource = new DAGSchedulerSource(this.dagScheduler, this)
private val blockManagerSource = new BlockManagerSource(SparkEnv.get.blockManager, this)
private def initDriverMetrics() {
SparkEnv.get.metricsSystem.registerSource(dagSchedulerSource)
SparkEnv.get.metricsSystem.registerSource(blockManagerSource)
}
initDriverMetrics()
// Methods for creating RDDs
/** Distribute a local Scala collection to form an RDD. */
def parallelize[T: ClassTag](seq: Seq[T], numSlices: Int = defaultParallelism): RDD[T] = {
new ParallelCollectionRDD[T](this, seq, numSlices, Map[Int, Seq[String]]())
}
/** Distribute a local Scala collection to form an RDD. */
def makeRDD[T: ClassTag](seq: Seq[T], numSlices: Int = defaultParallelism): RDD[T] = {
parallelize(seq, numSlices)
}
/** Distribute a local Scala collection to form an RDD, with one or more
* location preferences (hostnames of Spark nodes) for each object.
* Create a new partition for each collection item. */
def makeRDD[T: ClassTag](seq: Seq[(T, Seq[String])]): RDD[T] = {
val indexToPrefs = seq.zipWithIndex.map(t => (t._2, t._1._2)).toMap
new ParallelCollectionRDD[T](this, seq.map(_._1), seq.size, indexToPrefs)
}
/**
* Read a text file from HDFS, a local file system (available on all nodes), or any
* Hadoop-supported file system URI, and return it as an RDD of Strings.
*/
def textFile(path: String, minPartitions: Int = defaultMinPartitions): RDD[String] = {
hadoopFile(path, classOf[TextInputFormat], classOf[LongWritable], classOf[Text],
minPartitions).map(pair => pair._2.toString)
}
/**
* Read a directory of text files from HDFS, a local file system (available on all nodes), or any
* Hadoop-supported file system URI. Each file is read as a single record and returned in a
* key-value pair, where the key is the path of each file, the value is the content of each file.
*
* <p> For example, if you have the following files:
* {{{
* hdfs://a-hdfs-path/part-00000
* hdfs://a-hdfs-path/part-00001
* ...
* hdfs://a-hdfs-path/part-nnnnn
* }}}
*
* Do `val rdd = sparkContext.wholeTextFile("hdfs://a-hdfs-path")`,
*
* <p> then `rdd` contains
* {{{
* (a-hdfs-path/part-00000, its content)
* (a-hdfs-path/part-00001, its content)
* ...
* (a-hdfs-path/part-nnnnn, its content)
* }}}
*
* @note Small files are preferred, large file is also allowable, but may cause bad performance.
*
* @param minPartitions A suggestion value of the minimal splitting number for input data.
*/
def wholeTextFiles(path: String, minPartitions: Int = defaultMinPartitions):
RDD[(String, String)] = {
val job = new NewHadoopJob(hadoopConfiguration)
NewFileInputFormat.addInputPath(job, new Path(path))
val updateConf = job.getConfiguration
new WholeTextFileRDD(
this,
classOf[WholeTextFileInputFormat],
classOf[String],
classOf[String],
updateConf,
minPartitions)
}
/**
* Get an RDD for a Hadoop-readable dataset from a Hadoop JobConf given its InputFormat and other
* necessary info (e.g. file name for a filesystem-based dataset, table name for HyperTable),
* using the older MapReduce API (`org.apache.hadoop.mapred`).
*
* @param conf JobConf for setting up the dataset
* @param inputFormatClass Class of the InputFormat
* @param keyClass Class of the keys
* @param valueClass Class of the values
* @param minPartitions Minimum number of Hadoop Splits to generate.
*
* '''Note:''' Because Hadoop's RecordReader class re-uses the same Writable object for each
* record, directly caching the returned RDD will create many references to the same object.
* If you plan to directly cache Hadoop writable objects, you should first copy them using
* a `map` function.
*/
def hadoopRDD[K, V](
conf: JobConf,
inputFormatClass: Class[_ <: InputFormat[K, V]],
keyClass: Class[K],
valueClass: Class[V],
minPartitions: Int = defaultMinPartitions
): RDD[(K, V)] = {
// Add necessary security credentials to the JobConf before broadcasting it.
SparkHadoopUtil.get.addCredentials(conf)
new HadoopRDD(this, conf, inputFormatClass, keyClass, valueClass, minPartitions)
}
/** Get an RDD for a Hadoop file with an arbitrary InputFormat
*
* '''Note:''' Because Hadoop's RecordReader class re-uses the same Writable object for each
* record, directly caching the returned RDD will create many references to the same object.
* If you plan to directly cache Hadoop writable objects, you should first copy them using
* a `map` function.
* */
def hadoopFile[K, V](
path: String,
inputFormatClass: Class[_ <: InputFormat[K, V]],
keyClass: Class[K],
valueClass: Class[V],
minPartitions: Int = defaultMinPartitions
): RDD[(K, V)] = {
// A Hadoop configuration can be about 10 KB, which is pretty big, so broadcast it.
val confBroadcast = broadcast(new SerializableWritable(hadoopConfiguration))
val setInputPathsFunc = (jobConf: JobConf) => FileInputFormat.setInputPaths(jobConf, path)
new HadoopRDD(
this,
confBroadcast,
Some(setInputPathsFunc),
inputFormatClass,
keyClass,
valueClass,
minPartitions)
}
/**
* Smarter version of hadoopFile() that uses class tags to figure out the classes of keys,
* values and the InputFormat so that users don't need to pass them directly. Instead, callers
* can just write, for example,
* {{{
* val file = sparkContext.hadoopFile[LongWritable, Text, TextInputFormat](path, minPartitions)
* }}}
*
* '''Note:''' Because Hadoop's RecordReader class re-uses the same Writable object for each
* record, directly caching the returned RDD will create many references to the same object.
* If you plan to directly cache Hadoop writable objects, you should first copy them using
* a `map` function.
*/
def hadoopFile[K, V, F <: InputFormat[K, V]]
(path: String, minPartitions: Int)
(implicit km: ClassTag[K], vm: ClassTag[V], fm: ClassTag[F]): RDD[(K, V)] = {
hadoopFile(path,
fm.runtimeClass.asInstanceOf[Class[F]],
km.runtimeClass.asInstanceOf[Class[K]],
vm.runtimeClass.asInstanceOf[Class[V]],
minPartitions)
}
/**
* Smarter version of hadoopFile() that uses class tags to figure out the classes of keys,
* values and the InputFormat so that users don't need to pass them directly. Instead, callers
* can just write, for example,
* {{{
* val file = sparkContext.hadoopFile[LongWritable, Text, TextInputFormat](path)
* }}}
*
* '''Note:''' Because Hadoop's RecordReader class re-uses the same Writable object for each
* record, directly caching the returned RDD will create many references to the same object.
* If you plan to directly cache Hadoop writable objects, you should first copy them using
* a `map` function.
*/
def hadoopFile[K, V, F <: InputFormat[K, V]](path: String)
(implicit km: ClassTag[K], vm: ClassTag[V], fm: ClassTag[F]): RDD[(K, V)] =
hadoopFile[K, V, F](path, defaultMinPartitions)
/** Get an RDD for a Hadoop file with an arbitrary new API InputFormat. */
def newAPIHadoopFile[K, V, F <: NewInputFormat[K, V]]
(path: String)
(implicit km: ClassTag[K], vm: ClassTag[V], fm: ClassTag[F]): RDD[(K, V)] = {
newAPIHadoopFile(
path,
fm.runtimeClass.asInstanceOf[Class[F]],
km.runtimeClass.asInstanceOf[Class[K]],
vm.runtimeClass.asInstanceOf[Class[V]])
}
/**
* Get an RDD for a given Hadoop file with an arbitrary new API InputFormat
* and extra configuration options to pass to the input format.
*
* '''Note:''' Because Hadoop's RecordReader class re-uses the same Writable object for each
* record, directly caching the returned RDD will create many references to the same object.
* If you plan to directly cache Hadoop writable objects, you should first copy them using
* a `map` function.
*/
def newAPIHadoopFile[K, V, F <: NewInputFormat[K, V]](
path: String,
fClass: Class[F],
kClass: Class[K],
vClass: Class[V],
conf: Configuration = hadoopConfiguration): RDD[(K, V)] = {
val job = new NewHadoopJob(conf)
NewFileInputFormat.addInputPath(job, new Path(path))
val updatedConf = job.getConfiguration
new NewHadoopRDD(this, fClass, kClass, vClass, updatedConf)
}
/**
* Get an RDD for a given Hadoop file with an arbitrary new API InputFormat
* and extra configuration options to pass to the input format.
*
* '''Note:''' Because Hadoop's RecordReader class re-uses the same Writable object for each
* record, directly caching the returned RDD will create many references to the same object.
* If you plan to directly cache Hadoop writable objects, you should first copy them using
* a `map` function.
*/
def newAPIHadoopRDD[K, V, F <: NewInputFormat[K, V]](
conf: Configuration = hadoopConfiguration,
fClass: Class[F],
kClass: Class[K],
vClass: Class[V]): RDD[(K, V)] = {
new NewHadoopRDD(this, fClass, kClass, vClass, conf)
}
/** Get an RDD for a Hadoop SequenceFile with given key and value types.
*
* '''Note:''' Because Hadoop's RecordReader class re-uses the same Writable object for each
* record, directly caching the returned RDD will create many references to the same object.
* If you plan to directly cache Hadoop writable objects, you should first copy them using
* a `map` function.
*/
def sequenceFile[K, V](path: String,
keyClass: Class[K],
valueClass: Class[V],
minPartitions: Int
): RDD[(K, V)] = {
val inputFormatClass = classOf[SequenceFileInputFormat[K, V]]
hadoopFile(path, inputFormatClass, keyClass, valueClass, minPartitions)
}
/** Get an RDD for a Hadoop SequenceFile with given key and value types.
*
* '''Note:''' Because Hadoop's RecordReader class re-uses the same Writable object for each
* record, directly caching the returned RDD will create many references to the same object.
* If you plan to directly cache Hadoop writable objects, you should first copy them using
* a `map` function.
* */
def sequenceFile[K, V](path: String, keyClass: Class[K], valueClass: Class[V]
): RDD[(K, V)] =
sequenceFile(path, keyClass, valueClass, defaultMinPartitions)
/**
* Version of sequenceFile() for types implicitly convertible to Writables through a
* WritableConverter. For example, to access a SequenceFile where the keys are Text and the
* values are IntWritable, you could simply write
* {{{
* sparkContext.sequenceFile[String, Int](path, ...)
* }}}
*
* WritableConverters are provided in a somewhat strange way (by an implicit function) to support
* both subclasses of Writable and types for which we define a converter (e.g. Int to
* IntWritable). The most natural thing would've been to have implicit objects for the
* converters, but then we couldn't have an object for every subclass of Writable (you can't
* have a parameterized singleton object). We use functions instead to create a new converter
* for the appropriate type. In addition, we pass the converter a ClassTag of its type to
* allow it to figure out the Writable class to use in the subclass case.
*
* '''Note:''' Because Hadoop's RecordReader class re-uses the same Writable object for each
* record, directly caching the returned RDD will create many references to the same object.
* If you plan to directly cache Hadoop writable objects, you should first copy them using
* a `map` function.
*/
def sequenceFile[K, V]
(path: String, minPartitions: Int = defaultMinPartitions)
(implicit km: ClassTag[K], vm: ClassTag[V],
kcf: () => WritableConverter[K], vcf: () => WritableConverter[V])
: RDD[(K, V)] = {
val kc = kcf()
val vc = vcf()
val format = classOf[SequenceFileInputFormat[Writable, Writable]]
val writables = hadoopFile(path, format,
kc.writableClass(km).asInstanceOf[Class[Writable]],
vc.writableClass(vm).asInstanceOf[Class[Writable]], minPartitions)
writables.map { case (k, v) => (kc.convert(k), vc.convert(v)) }
}
/**
* Load an RDD saved as a SequenceFile containing serialized objects, with NullWritable keys and
* BytesWritable values that contain a serialized partition. This is still an experimental
* storage format and may not be supported exactly as is in future Spark releases. It will also
* be pretty slow if you use the default serializer (Java serialization),
* though the nice thing about it is that there's very little effort required to save arbitrary
* objects.
*/
def objectFile[T: ClassTag](
path: String,
minPartitions: Int = defaultMinPartitions
): RDD[T] = {
sequenceFile(path, classOf[NullWritable], classOf[BytesWritable], minPartitions)
.flatMap(x => Utils.deserialize[Array[T]](x._2.getBytes))
}
protected[spark] def checkpointFile[T: ClassTag](
path: String
): RDD[T] = {
new CheckpointRDD[T](this, path)
}
/** Build the union of a list of RDDs. */
def union[T: ClassTag](rdds: Seq[RDD[T]]): RDD[T] = new UnionRDD(this, rdds)
/** Build the union of a list of RDDs passed as variable-length arguments. */
def union[T: ClassTag](first: RDD[T], rest: RDD[T]*): RDD[T] =
new UnionRDD(this, Seq(first) ++ rest)
/** Get an RDD that has no partitions or elements. */
def emptyRDD[T: ClassTag] = new EmptyRDD[T](this)
// Methods for creating shared variables
/**
* Create an [[org.apache.spark.Accumulator]] variable of a given type, which tasks can "add"
* values to using the `+=` method. Only the driver can access the accumulator's `value`.
*/
def accumulator[T](initialValue: T)(implicit param: AccumulatorParam[T]) =
new Accumulator(initialValue, param)
/**
* Create an [[org.apache.spark.Accumulable]] shared variable, to which tasks can add values
* with `+=`. Only the driver can access the accumuable's `value`.
* @tparam T accumulator type
* @tparam R type that can be added to the accumulator
*/
def accumulable[T, R](initialValue: T)(implicit param: AccumulableParam[T, R]) =
new Accumulable(initialValue, param)
/**
* Create an accumulator from a "mutable collection" type.
*
* Growable and TraversableOnce are the standard APIs that guarantee += and ++=, implemented by
* standard mutable collections. So you can use this with mutable Map, Set, etc.
*/
def accumulableCollection[R <% Growable[T] with TraversableOnce[T] with Serializable, T]
(initialValue: R): Accumulable[R, T] = {
val param = new GrowableAccumulableParam[R,T]
new Accumulable(initialValue, param)
}
/**
* Broadcast a read-only variable to the cluster, returning a
* [[org.apache.spark.broadcast.Broadcast]] object for reading it in distributed functions.
* The variable will be sent to each cluster only once.
*/
def broadcast[T](value: T): Broadcast[T] = {
val bc = env.broadcastManager.newBroadcast[T](value, isLocal)
cleaner.foreach(_.registerBroadcastForCleanup(bc))
bc
}
/**
* Add a file to be downloaded with this Spark job on every node.
* The `path` passed can be either a local file, a file in HDFS (or other Hadoop-supported
* filesystems), or an HTTP, HTTPS or FTP URI. To access the file in Spark jobs,
* use `SparkFiles.get(path)` to find its download location.
*/
def addFile(path: String) {
val uri = new URI(path)
val key = uri.getScheme match {
case null | "file" => env.httpFileServer.addFile(new File(uri.getPath))
case "local" => "file:" + uri.getPath
case _ => path
}
addedFiles(key) = System.currentTimeMillis
// Fetch the file locally in case a job is executed using DAGScheduler.runLocally().
Utils.fetchFile(path, new File(SparkFiles.getRootDirectory), conf, env.securityManager)
logInfo("Added file " + path + " at " + key + " with timestamp " + addedFiles(key))
postEnvironmentUpdate()
}
/**
* :: DeveloperApi ::
* Register a listener to receive up-calls from events that happen during execution.
*/
@DeveloperApi
def addSparkListener(listener: SparkListener) {
listenerBus.addListener(listener)
}
/** The version of Spark on which this application is running. */
def version = SparkContext.SPARK_VERSION
/**
* Return a map from the slave to the max memory available for caching and the remaining
* memory available for caching.
*/
def getExecutorMemoryStatus: Map[String, (Long, Long)] = {
env.blockManager.master.getMemoryStatus.map { case(blockManagerId, mem) =>
(blockManagerId.host + ":" + blockManagerId.port, mem)
}
}
/**
* Return information about what RDDs are cached, if they are in mem or on disk, how much space
* they take, etc.
*/
def getRDDStorageInfo: Array[RDDInfo] = {
StorageUtils.rddInfoFromStorageStatus(getExecutorStorageStatus, this)
}
/**
* Returns an immutable map of RDDs that have marked themselves as persistent via cache() call.
* Note that this does not necessarily mean the caching or computation was successful.
*/
def getPersistentRDDs: Map[Int, RDD[_]] = persistentRdds.toMap
/**
* Return information about blocks stored in all of the slaves
*/
def getExecutorStorageStatus: Array[StorageStatus] = {
env.blockManager.master.getStorageStatus
}
/**
* Return pools for fair scheduler
* TODO(xiajunluan): We should take nested pools into account
*/
def getAllPools: ArrayBuffer[Schedulable] = {
taskScheduler.rootPool.schedulableQueue
}
/**
* Return the pool associated with the given name, if one exists
*/
def getPoolForName(pool: String): Option[Schedulable] = {
taskScheduler.rootPool.schedulableNameToSchedulable.get(pool)
}
/**
* Return current scheduling mode
*/
def getSchedulingMode: SchedulingMode.SchedulingMode = {
taskScheduler.schedulingMode
}
/**
* Clear the job's list of files added by `addFile` so that they do not get downloaded to
* any new nodes.
*/
@deprecated("adding files no longer creates local copies that need to be deleted", "1.0.0")
def clearFiles() {
addedFiles.clear()
}
/**
* Gets the locality information associated with the partition in a particular rdd
* @param rdd of interest
* @param partition to be looked up for locality
* @return list of preferred locations for the partition
*/
private [spark] def getPreferredLocs(rdd: RDD[_], partition: Int): Seq[TaskLocation] = {
dagScheduler.getPreferredLocs(rdd, partition)
}
/**
* Register an RDD to be persisted in memory and/or disk storage
*/
private[spark] def persistRDD(rdd: RDD[_]) {
persistentRdds(rdd.id) = rdd
}
/**
* Unpersist an RDD from memory and/or disk storage
*/
private[spark] def unpersistRDD(rddId: Int, blocking: Boolean = true) {
env.blockManager.master.removeRdd(rddId, blocking)
persistentRdds.remove(rddId)
listenerBus.post(SparkListenerUnpersistRDD(rddId))
}
/**
* Adds a JAR dependency for all tasks to be executed on this SparkContext in the future.
* The `path` passed can be either a local file, a file in HDFS (or other Hadoop-supported
* filesystems), an HTTP, HTTPS or FTP URI, or local:/path for a file on every worker node.
*/
def addJar(path: String) {
if (path == null) {
logWarning("null specified as parameter to addJar")
} else {
var key = ""
if (path.contains("\\")) {
// For local paths with backslashes on Windows, URI throws an exception
key = env.httpFileServer.addJar(new File(path))
} else {
val uri = new URI(path)
key = uri.getScheme match {
// A JAR file which exists only on the driver node
case null | "file" =>
// yarn-standalone is deprecated, but still supported
if (SparkHadoopUtil.get.isYarnMode() &&
(master == "yarn-standalone" || master == "yarn-cluster")) {
// In order for this to work in yarn-cluster mode the user must specify the
// --addjars option to the client to upload the file into the distributed cache
// of the AM to make it show up in the current working directory.
val fileName = new Path(uri.getPath).getName()
try {
env.httpFileServer.addJar(new File(fileName))
} catch {
case e: Exception => {
// For now just log an error but allow to go through so spark examples work.
// The spark examples don't really need the jar distributed since its also
// the app jar.
logError("Error adding jar (" + e + "), was the --addJars option used?")
null
}
}
} else {
env.httpFileServer.addJar(new File(uri.getPath))
}
// A JAR file which exists locally on every worker node
case "local" =>
"file:" + uri.getPath
case _ =>
path
}
}
if (key != null) {
addedJars(key) = System.currentTimeMillis
logInfo("Added JAR " + path + " at " + key + " with timestamp " + addedJars(key))
}
}
postEnvironmentUpdate()
}
/**
* Clear the job's list of JARs added by `addJar` so that they do not get downloaded to
* any new nodes.
*/
@deprecated("adding jars no longer creates local copies that need to be deleted", "1.0.0")
def clearJars() {
addedJars.clear()
}
/** Shut down the SparkContext. */
def stop() {
postApplicationEnd()
ui.stop()
// Do this only if not stopped already - best case effort.
// prevent NPE if stopped more than once.
val dagSchedulerCopy = dagScheduler
dagScheduler = null
if (dagSchedulerCopy != null) {
metadataCleaner.cancel()
cleaner.foreach(_.stop())
dagSchedulerCopy.stop()
taskScheduler = null
// TODO: Cache.stop()?
env.stop()
SparkEnv.set(null)
ShuffleMapTask.clearCache()
ResultTask.clearCache()
listenerBus.stop()
eventLogger.foreach(_.stop())
logInfo("Successfully stopped SparkContext")
} else {
logInfo("SparkContext already stopped")
}
}
/**
* Get Spark's home location from either a value set through the constructor,
* or the spark.home Java property, or the SPARK_HOME environment variable
* (in that order of preference). If neither of these is set, return None.
*/
private[spark] def getSparkHome(): Option[String] = {
conf.getOption("spark.home").orElse(Option(System.getenv("SPARK_HOME")))
}
/**
* Support function for API backtraces.
*/
def setCallSite(site: String) {
setLocalProperty("externalCallSite", site)
}
/**
* Support function for API backtraces.
*/
def clearCallSite() {
setLocalProperty("externalCallSite", null)
}
/**
* Capture the current user callsite and return a formatted version for printing. If the user
* has overridden the call site, this will return the user's version.
*/
private[spark] def getCallSite(): String = {
val defaultCallSite = Utils.getCallSiteInfo
Option(getLocalProperty("externalCallSite")).getOrElse(defaultCallSite.toString)
}
/**
* Run a function on a given set of partitions in an RDD and pass the results to the given
* handler function. This is the main entry point for all actions in Spark. The allowLocal
* flag specifies whether the scheduler can run the computation on the driver rather than
* shipping it out to the cluster, for short actions like first().
*/
def runJob[T, U: ClassTag](
rdd: RDD[T],
func: (TaskContext, Iterator[T]) => U,
partitions: Seq[Int],
allowLocal: Boolean,
resultHandler: (Int, U) => Unit) {
if (dagScheduler == null) {
throw new SparkException("SparkContext has been shutdown")
}
val callSite = getCallSite
val cleanedFunc = clean(func)
logInfo("Starting job: " + callSite)
val start = System.nanoTime
dagScheduler.runJob(rdd, cleanedFunc, partitions, callSite, allowLocal,
resultHandler, localProperties.get)
logInfo("Job finished: " + callSite + ", took " + (System.nanoTime - start) / 1e9 + " s")
rdd.doCheckpoint()
}
/**
* Run a function on a given set of partitions in an RDD and return the results as an array. The
* allowLocal flag specifies whether the scheduler can run the computation on the driver rather
* than shipping it out to the cluster, for short actions like first().
*/
def runJob[T, U: ClassTag](
rdd: RDD[T],
func: (TaskContext, Iterator[T]) => U,
partitions: Seq[Int],
allowLocal: Boolean
): Array[U] = {
val results = new Array[U](partitions.size)
runJob[T, U](rdd, func, partitions, allowLocal, (index, res) => results(index) = res)
results
}
/**
* Run a job on a given set of partitions of an RDD, but take a function of type
* `Iterator[T] => U` instead of `(TaskContext, Iterator[T]) => U`.
*/
def runJob[T, U: ClassTag](
rdd: RDD[T],
func: Iterator[T] => U,
partitions: Seq[Int],
allowLocal: Boolean
): Array[U] = {
runJob(rdd, (context: TaskContext, iter: Iterator[T]) => func(iter), partitions, allowLocal)
}
/**
* Run a job on all partitions in an RDD and return the results in an array.
*/
def runJob[T, U: ClassTag](rdd: RDD[T], func: (TaskContext, Iterator[T]) => U): Array[U] = {
runJob(rdd, func, 0 until rdd.partitions.size, false)
}
/**
* Run a job on all partitions in an RDD and return the results in an array.
*/
def runJob[T, U: ClassTag](rdd: RDD[T], func: Iterator[T] => U): Array[U] = {
runJob(rdd, func, 0 until rdd.partitions.size, false)
}
/**
* Run a job on all partitions in an RDD and pass the results to a handler function.
*/
def runJob[T, U: ClassTag](
rdd: RDD[T],
processPartition: (TaskContext, Iterator[T]) => U,
resultHandler: (Int, U) => Unit)
{
runJob[T, U](rdd, processPartition, 0 until rdd.partitions.size, false, resultHandler)
}
/**
* Run a job on all partitions in an RDD and pass the results to a handler function.
*/
def runJob[T, U: ClassTag](
rdd: RDD[T],
processPartition: Iterator[T] => U,
resultHandler: (Int, U) => Unit)
{
val processFunc = (context: TaskContext, iter: Iterator[T]) => processPartition(iter)
runJob[T, U](rdd, processFunc, 0 until rdd.partitions.size, false, resultHandler)
}
/**
* :: DeveloperApi ::
* Run a job that can return approximate results.
*/
@DeveloperApi
def runApproximateJob[T, U, R](
rdd: RDD[T],
func: (TaskContext, Iterator[T]) => U,
evaluator: ApproximateEvaluator[U, R],
timeout: Long): PartialResult[R] = {
val callSite = getCallSite
logInfo("Starting job: " + callSite)
val start = System.nanoTime
val result = dagScheduler.runApproximateJob(rdd, func, evaluator, callSite, timeout,
localProperties.get)
logInfo("Job finished: " + callSite + ", took " + (System.nanoTime - start) / 1e9 + " s")
result
}
/**
* :: Experimental ::
* Submit a job for execution and return a FutureJob holding the result.
*/
@Experimental
def submitJob[T, U, R](
rdd: RDD[T],
processPartition: Iterator[T] => U,
partitions: Seq[Int],
resultHandler: (Int, U) => Unit,
resultFunc: => R): SimpleFutureAction[R] =
{
val cleanF = clean(processPartition)
val callSite = getCallSite
val waiter = dagScheduler.submitJob(
rdd,
(context: TaskContext, iter: Iterator[T]) => cleanF(iter),
partitions,
callSite,
allowLocal = false,
resultHandler,
localProperties.get)
new SimpleFutureAction(waiter, resultFunc)
}
/**
* Cancel active jobs for the specified group. See [[org.apache.spark.SparkContext.setJobGroup]]
* for more information.
*/
def cancelJobGroup(groupId: String) {
dagScheduler.cancelJobGroup(groupId)
}
/** Cancel all jobs that have been scheduled or are running. */
def cancelAllJobs() {
dagScheduler.cancelAllJobs()
}
/** Cancel a given job if it's scheduled or running */
private[spark] def cancelJob(jobId: Int) {
dagScheduler.cancelJob(jobId)
}
/** Cancel a given stage and all jobs associated with it */
private[spark] def cancelStage(stageId: Int) {
dagScheduler.cancelStage(stageId)
}
/**
* Clean a closure to make it ready to serialized and send to tasks
* (removes unreferenced variables in $outer's, updates REPL variables)
*/
private[spark] def clean[F <: AnyRef](f: F): F = {
ClosureCleaner.clean(f)
f
}
/**
* Set the directory under which RDDs are going to be checkpointed. The directory must
* be a HDFS path if running on a cluster.
*/
def setCheckpointDir(directory: String) {
checkpointDir = Option(directory).map { dir =>
val path = new Path(dir, UUID.randomUUID().toString)
val fs = path.getFileSystem(hadoopConfiguration)
fs.mkdirs(path)
fs.getFileStatus(path).getPath.toString
}
}
def getCheckpointDir = checkpointDir
/** Default level of parallelism to use when not given by user (e.g. parallelize and makeRDD). */
def defaultParallelism: Int = taskScheduler.defaultParallelism
/** Default min number of partitions for Hadoop RDDs when not given by user */
@deprecated("use defaultMinPartitions", "1.0.0")
def defaultMinSplits: Int = math.min(defaultParallelism, 2)
/** Default min number of partitions for Hadoop RDDs when not given by user */
def defaultMinPartitions: Int = math.min(defaultParallelism, 2)
private val nextShuffleId = new AtomicInteger(0)
private[spark] def newShuffleId(): Int = nextShuffleId.getAndIncrement()
private val nextRddId = new AtomicInteger(0)
/** Register a new RDD, returning its RDD ID */
private[spark] def newRddId(): Int = nextRddId.getAndIncrement()
/** Post the application start event */
private def postApplicationStart() {
listenerBus.post(SparkListenerApplicationStart(appName, startTime, sparkUser))
}
/** Post the application end event */
private def postApplicationEnd() {
listenerBus.post(SparkListenerApplicationEnd(System.currentTimeMillis))
}
/** Post the environment update event once the task scheduler is ready */
private def postEnvironmentUpdate() {
if (taskScheduler != null) {
val schedulingMode = getSchedulingMode.toString
val addedJarPaths = addedJars.keys.toSeq
val addedFilePaths = addedFiles.keys.toSeq
val environmentDetails =
SparkEnv.environmentDetails(conf, schedulingMode, addedJarPaths, addedFilePaths)
val environmentUpdate = SparkListenerEnvironmentUpdate(environmentDetails)
listenerBus.post(environmentUpdate)
}
}
/** Called by MetadataCleaner to clean up the persistentRdds map periodically */
private[spark] def cleanup(cleanupTime: Long) {
persistentRdds.clearOldValues(cleanupTime)
}
}
/**
* The SparkContext object contains a number of implicit conversions and parameters for use with
* various Spark features.
*/
object SparkContext extends Logging {
private[spark] val SPARK_VERSION = "1.0.0"
private[spark] val SPARK_JOB_DESCRIPTION = "spark.job.description"
private[spark] val SPARK_JOB_GROUP_ID = "spark.jobGroup.id"
private[spark] val SPARK_JOB_INTERRUPT_ON_CANCEL = "spark.job.interruptOnCancel"
private[spark] val SPARK_UNKNOWN_USER = "<unknown>"
implicit object DoubleAccumulatorParam extends AccumulatorParam[Double] {
def addInPlace(t1: Double, t2: Double): Double = t1 + t2
def zero(initialValue: Double) = 0.0
}
implicit object IntAccumulatorParam extends AccumulatorParam[Int] {
def addInPlace(t1: Int, t2: Int): Int = t1 + t2
def zero(initialValue: Int) = 0
}
implicit object LongAccumulatorParam extends AccumulatorParam[Long] {
def addInPlace(t1: Long, t2: Long) = t1 + t2
def zero(initialValue: Long) = 0L
}
implicit object FloatAccumulatorParam extends AccumulatorParam[Float] {
def addInPlace(t1: Float, t2: Float) = t1 + t2
def zero(initialValue: Float) = 0f
}
// TODO: Add AccumulatorParams for other types, e.g. lists and strings
implicit def rddToPairRDDFunctions[K, V](rdd: RDD[(K, V)])
(implicit kt: ClassTag[K], vt: ClassTag[V], ord: Ordering[K] = null) = {
new PairRDDFunctions(rdd)
}
implicit def rddToAsyncRDDActions[T: ClassTag](rdd: RDD[T]) = new AsyncRDDActions(rdd)
implicit def rddToSequenceFileRDDFunctions[K <% Writable: ClassTag, V <% Writable: ClassTag](
rdd: RDD[(K, V)]) =
new SequenceFileRDDFunctions(rdd)
implicit def rddToOrderedRDDFunctions[K : Ordering : ClassTag, V: ClassTag](
rdd: RDD[(K, V)]) =
new OrderedRDDFunctions[K, V, (K, V)](rdd)
implicit def doubleRDDToDoubleRDDFunctions(rdd: RDD[Double]) = new DoubleRDDFunctions(rdd)
implicit def numericRDDToDoubleRDDFunctions[T](rdd: RDD[T])(implicit num: Numeric[T]) =
new DoubleRDDFunctions(rdd.map(x => num.toDouble(x)))
// Implicit conversions to common Writable types, for saveAsSequenceFile
implicit def intToIntWritable(i: Int) = new IntWritable(i)
implicit def longToLongWritable(l: Long) = new LongWritable(l)
implicit def floatToFloatWritable(f: Float) = new FloatWritable(f)
implicit def doubleToDoubleWritable(d: Double) = new DoubleWritable(d)
implicit def boolToBoolWritable (b: Boolean) = new BooleanWritable(b)
implicit def bytesToBytesWritable (aob: Array[Byte]) = new BytesWritable(aob)
implicit def stringToText(s: String) = new Text(s)
private implicit def arrayToArrayWritable[T <% Writable: ClassTag](arr: Traversable[T])
: ArrayWritable = {
def anyToWritable[U <% Writable](u: U): Writable = u
new ArrayWritable(classTag[T].runtimeClass.asInstanceOf[Class[Writable]],
arr.map(x => anyToWritable(x)).toArray)
}
// Helper objects for converting common types to Writable
private def simpleWritableConverter[T, W <: Writable: ClassTag](convert: W => T)
: WritableConverter[T] = {
val wClass = classTag[W].runtimeClass.asInstanceOf[Class[W]]
new WritableConverter[T](_ => wClass, x => convert(x.asInstanceOf[W]))
}
implicit def intWritableConverter(): WritableConverter[Int] =
simpleWritableConverter[Int, IntWritable](_.get)
implicit def longWritableConverter(): WritableConverter[Long] =
simpleWritableConverter[Long, LongWritable](_.get)
implicit def doubleWritableConverter(): WritableConverter[Double] =
simpleWritableConverter[Double, DoubleWritable](_.get)
implicit def floatWritableConverter(): WritableConverter[Float] =
simpleWritableConverter[Float, FloatWritable](_.get)
implicit def booleanWritableConverter(): WritableConverter[Boolean] =
simpleWritableConverter[Boolean, BooleanWritable](_.get)
implicit def bytesWritableConverter(): WritableConverter[Array[Byte]] = {
simpleWritableConverter[Array[Byte], BytesWritable](_.getBytes)
}
implicit def stringWritableConverter(): WritableConverter[String] =
simpleWritableConverter[String, Text](_.toString)
implicit def writableWritableConverter[T <: Writable]() =
new WritableConverter[T](_.runtimeClass.asInstanceOf[Class[T]], _.asInstanceOf[T])
/**
* Find the JAR from which a given class was loaded, to make it easy for users to pass
* their JARs to SparkContext.
*/
def jarOfClass(cls: Class[_]): Option[String] = {
val uri = cls.getResource("/" + cls.getName.replace('.', '/') + ".class")
if (uri != null) {
val uriStr = uri.toString
if (uriStr.startsWith("jar:file:")) {
// URI will be of the form "jar:file:/path/foo.jar!/package/cls.class",
// so pull out the /path/foo.jar
Some(uriStr.substring("jar:file:".length, uriStr.indexOf('!')))
} else {
None
}
} else {
None
}
}
/**
* Find the JAR that contains the class of a particular object, to make it easy for users
* to pass their JARs to SparkContext. In most cases you can call jarOfObject(this) in
* your driver program.
*/
def jarOfObject(obj: AnyRef): Option[String] = jarOfClass(obj.getClass)
/**
* Creates a modified version of a SparkConf with the parameters that can be passed separately
* to SparkContext, to make it easier to write SparkContext's constructors. This ignores
* parameters that are passed as the default value of null, instead of throwing an exception
* like SparkConf would.
*/
private[spark] def updatedConf(
conf: SparkConf,
master: String,
appName: String,
sparkHome: String = null,
jars: Seq[String] = Nil,
environment: Map[String, String] = Map()): SparkConf =
{
val res = conf.clone()
res.setMaster(master)
res.setAppName(appName)
if (sparkHome != null) {
res.setSparkHome(sparkHome)
}
if (jars != null && !jars.isEmpty) {
res.setJars(jars)
}
res.setExecutorEnv(environment.toSeq)
res
}
/** Creates a task scheduler based on a given master URL. Extracted for testing. */
private def createTaskScheduler(sc: SparkContext, master: String): TaskScheduler = {
// Regular expression used for local[N] and local[*] master formats
val LOCAL_N_REGEX = """local\[([0-9\*]+)\]""".r
// Regular expression for local[N, maxRetries], used in tests with failing tasks
val LOCAL_N_FAILURES_REGEX = """local\[([0-9]+)\s*,\s*([0-9]+)\]""".r
// Regular expression for simulating a Spark cluster of [N, cores, memory] locally
val LOCAL_CLUSTER_REGEX = """local-cluster\[\s*([0-9]+)\s*,\s*([0-9]+)\s*,\s*([0-9]+)\s*]""".r
// Regular expression for connecting to Spark deploy clusters
val SPARK_REGEX = """spark://(.*)""".r
// Regular expression for connection to Mesos cluster by mesos:// or zk:// url
val MESOS_REGEX = """(mesos|zk)://.*""".r
// Regular expression for connection to Simr cluster
val SIMR_REGEX = """simr://(.*)""".r
// When running locally, don't try to re-execute tasks on failure.
val MAX_LOCAL_TASK_FAILURES = 1
master match {
case "local" =>
val scheduler = new TaskSchedulerImpl(sc, MAX_LOCAL_TASK_FAILURES, isLocal = true)
val backend = new LocalBackend(scheduler, 1)
scheduler.initialize(backend)
scheduler
case LOCAL_N_REGEX(threads) =>
def localCpuCount = Runtime.getRuntime.availableProcessors()
// local[*] estimates the number of cores on the machine; local[N] uses exactly N threads.
val threadCount = if (threads == "*") localCpuCount else threads.toInt
val scheduler = new TaskSchedulerImpl(sc, MAX_LOCAL_TASK_FAILURES, isLocal = true)
val backend = new LocalBackend(scheduler, threadCount)
scheduler.initialize(backend)
scheduler
case LOCAL_N_FAILURES_REGEX(threads, maxFailures) =>
val scheduler = new TaskSchedulerImpl(sc, maxFailures.toInt, isLocal = true)
val backend = new LocalBackend(scheduler, threads.toInt)
scheduler.initialize(backend)
scheduler
case SPARK_REGEX(sparkUrl) =>
val scheduler = new TaskSchedulerImpl(sc)
val masterUrls = sparkUrl.split(",").map("spark://" + _)
val backend = new SparkDeploySchedulerBackend(scheduler, sc, masterUrls)
scheduler.initialize(backend)
scheduler
case LOCAL_CLUSTER_REGEX(numSlaves, coresPerSlave, memoryPerSlave) =>
// Check to make sure memory requested <= memoryPerSlave. Otherwise Spark will just hang.
val memoryPerSlaveInt = memoryPerSlave.toInt
if (sc.executorMemory > memoryPerSlaveInt) {
throw new SparkException(
"Asked to launch cluster with %d MB RAM / worker but requested %d MB/worker".format(
memoryPerSlaveInt, sc.executorMemory))
}
val scheduler = new TaskSchedulerImpl(sc)
val localCluster = new LocalSparkCluster(
numSlaves.toInt, coresPerSlave.toInt, memoryPerSlaveInt)
val masterUrls = localCluster.start()
val backend = new SparkDeploySchedulerBackend(scheduler, sc, masterUrls)
scheduler.initialize(backend)
backend.shutdownCallback = (backend: SparkDeploySchedulerBackend) => {
localCluster.stop()
}
scheduler
case "yarn-standalone" | "yarn-cluster" =>
if (master == "yarn-standalone") {
logWarning(
"\"yarn-standalone\" is deprecated as of Spark 1.0. Use \"yarn-cluster\" instead.")
}
val scheduler = try {
val clazz = Class.forName("org.apache.spark.scheduler.cluster.YarnClusterScheduler")
val cons = clazz.getConstructor(classOf[SparkContext])
cons.newInstance(sc).asInstanceOf[TaskSchedulerImpl]
} catch {
// TODO: Enumerate the exact reasons why it can fail
// But irrespective of it, it means we cannot proceed !
case th: Throwable => {
throw new SparkException("YARN mode not available ?", th)
}
}
val backend = new CoarseGrainedSchedulerBackend(scheduler, sc.env.actorSystem)
scheduler.initialize(backend)
scheduler
case "yarn-client" =>
val scheduler = try {
val clazz =
Class.forName("org.apache.spark.scheduler.cluster.YarnClientClusterScheduler")
val cons = clazz.getConstructor(classOf[SparkContext])
cons.newInstance(sc).asInstanceOf[TaskSchedulerImpl]
} catch {
case th: Throwable => {
throw new SparkException("YARN mode not available ?", th)
}
}
val backend = try {
val clazz =
Class.forName("org.apache.spark.scheduler.cluster.YarnClientSchedulerBackend")
val cons = clazz.getConstructor(classOf[TaskSchedulerImpl], classOf[SparkContext])
cons.newInstance(scheduler, sc).asInstanceOf[CoarseGrainedSchedulerBackend]
} catch {
case th: Throwable => {
throw new SparkException("YARN mode not available ?", th)
}
}
scheduler.initialize(backend)
scheduler
case mesosUrl @ MESOS_REGEX(_) =>
MesosNativeLibrary.load()
val scheduler = new TaskSchedulerImpl(sc)
val coarseGrained = sc.conf.getBoolean("spark.mesos.coarse", false)
val url = mesosUrl.stripPrefix("mesos://") // strip scheme from raw Mesos URLs
val backend = if (coarseGrained) {
new CoarseMesosSchedulerBackend(scheduler, sc, url)
} else {
new MesosSchedulerBackend(scheduler, sc, url)
}
scheduler.initialize(backend)
scheduler
case SIMR_REGEX(simrUrl) =>
val scheduler = new TaskSchedulerImpl(sc)
val backend = new SimrSchedulerBackend(scheduler, sc, simrUrl)
scheduler.initialize(backend)
scheduler
case _ =>
throw new SparkException("Could not parse Master URL: '" + master + "'")
}
}
}
/**
* A class encapsulating how to convert some type T to Writable. It stores both the Writable class
* corresponding to T (e.g. IntWritable for Int) and a function for doing the conversion.
* The getter for the writable class takes a ClassTag[T] in case this is a generic object
* that doesn't know the type of T when it is created. This sounds strange but is necessary to
* support converting subclasses of Writable to themselves (writableWritableConverter).
*/
private[spark] class WritableConverter[T](
val writableClass: ClassTag[T] => Class[_ <: Writable],
val convert: Writable => T)
extends Serializable
|