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
|
/*
* 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.deploy
import java.io.{File, PrintStream}
import java.lang.reflect.{InvocationTargetException, Modifier, UndeclaredThrowableException}
import java.net.URL
import java.security.PrivilegedExceptionAction
import scala.collection.mutable.{ArrayBuffer, HashMap, Map}
import org.apache.commons.lang3.StringUtils
import org.apache.hadoop.fs.Path
import org.apache.hadoop.security.UserGroupInformation
import org.apache.ivy.Ivy
import org.apache.ivy.core.LogOptions
import org.apache.ivy.core.module.descriptor._
import org.apache.ivy.core.module.id.{ArtifactId, ModuleId, ModuleRevisionId}
import org.apache.ivy.core.report.ResolveReport
import org.apache.ivy.core.resolve.ResolveOptions
import org.apache.ivy.core.retrieve.RetrieveOptions
import org.apache.ivy.core.settings.IvySettings
import org.apache.ivy.plugins.matcher.GlobPatternMatcher
import org.apache.ivy.plugins.repository.file.FileRepository
import org.apache.ivy.plugins.resolver.{FileSystemResolver, ChainResolver, IBiblioResolver}
import org.apache.spark.{SparkUserAppException, SPARK_VERSION}
import org.apache.spark.api.r.RUtils
import org.apache.spark.deploy.rest._
import org.apache.spark.util.{ChildFirstURLClassLoader, MutableURLClassLoader, Utils}
/**
* Whether to submit, kill, or request the status of an application.
* The latter two operations are currently supported only for standalone cluster mode.
*/
private[deploy] object SparkSubmitAction extends Enumeration {
type SparkSubmitAction = Value
val SUBMIT, KILL, REQUEST_STATUS = Value
}
/**
* Main gateway of launching a Spark application.
*
* This program handles setting up the classpath with relevant Spark dependencies and provides
* a layer over the different cluster managers and deploy modes that Spark supports.
*/
object SparkSubmit {
// Cluster managers
private val YARN = 1
private val STANDALONE = 2
private val MESOS = 4
private val LOCAL = 8
private val ALL_CLUSTER_MGRS = YARN | STANDALONE | MESOS | LOCAL
// Deploy modes
private val CLIENT = 1
private val CLUSTER = 2
private val ALL_DEPLOY_MODES = CLIENT | CLUSTER
// A special jar name that indicates the class being run is inside of Spark itself, and therefore
// no user jar is needed.
private val SPARK_INTERNAL = "spark-internal"
// Special primary resource names that represent shells rather than application jars.
private val SPARK_SHELL = "spark-shell"
private val PYSPARK_SHELL = "pyspark-shell"
private val SPARKR_SHELL = "sparkr-shell"
private val SPARKR_PACKAGE_ARCHIVE = "sparkr.zip"
private val CLASS_NOT_FOUND_EXIT_STATUS = 101
// scalastyle:off println
// Exposed for testing
private[spark] var exitFn: Int => Unit = (exitCode: Int) => System.exit(exitCode)
private[spark] var printStream: PrintStream = System.err
private[spark] def printWarning(str: String): Unit = printStream.println("Warning: " + str)
private[spark] def printErrorAndExit(str: String): Unit = {
printStream.println("Error: " + str)
printStream.println("Run with --help for usage help or --verbose for debug output")
exitFn(1)
}
private[spark] def printVersionAndExit(): Unit = {
printStream.println("""Welcome to
____ __
/ __/__ ___ _____/ /__
_\ \/ _ \/ _ `/ __/ '_/
/___/ .__/\_,_/_/ /_/\_\ version %s
/_/
""".format(SPARK_VERSION))
printStream.println("Type --help for more information.")
exitFn(0)
}
// scalastyle:on println
def main(args: Array[String]): Unit = {
val appArgs = new SparkSubmitArguments(args)
if (appArgs.verbose) {
// scalastyle:off println
printStream.println(appArgs)
// scalastyle:on println
}
appArgs.action match {
case SparkSubmitAction.SUBMIT => submit(appArgs)
case SparkSubmitAction.KILL => kill(appArgs)
case SparkSubmitAction.REQUEST_STATUS => requestStatus(appArgs)
}
}
/**
* Kill an existing submission using the REST protocol. Standalone and Mesos cluster mode only.
*/
private def kill(args: SparkSubmitArguments): Unit = {
new RestSubmissionClient(args.master)
.killSubmission(args.submissionToKill)
}
/**
* Request the status of an existing submission using the REST protocol.
* Standalone and Mesos cluster mode only.
*/
private def requestStatus(args: SparkSubmitArguments): Unit = {
new RestSubmissionClient(args.master)
.requestSubmissionStatus(args.submissionToRequestStatusFor)
}
/**
* Submit the application using the provided parameters.
*
* This runs in two steps. First, we prepare the launch environment by setting up
* the appropriate classpath, system properties, and application arguments for
* running the child main class based on the cluster manager and the deploy mode.
* Second, we use this launch environment to invoke the main method of the child
* main class.
*/
private def submit(args: SparkSubmitArguments): Unit = {
val (childArgs, childClasspath, sysProps, childMainClass) = prepareSubmitEnvironment(args)
def doRunMain(): Unit = {
if (args.proxyUser != null) {
val proxyUser = UserGroupInformation.createProxyUser(args.proxyUser,
UserGroupInformation.getCurrentUser())
try {
proxyUser.doAs(new PrivilegedExceptionAction[Unit]() {
override def run(): Unit = {
runMain(childArgs, childClasspath, sysProps, childMainClass, args.verbose)
}
})
} catch {
case e: Exception =>
// Hadoop's AuthorizationException suppresses the exception's stack trace, which
// makes the message printed to the output by the JVM not very helpful. Instead,
// detect exceptions with empty stack traces here, and treat them differently.
if (e.getStackTrace().length == 0) {
// scalastyle:off println
printStream.println(s"ERROR: ${e.getClass().getName()}: ${e.getMessage()}")
// scalastyle:on println
exitFn(1)
} else {
throw e
}
}
} else {
runMain(childArgs, childClasspath, sysProps, childMainClass, args.verbose)
}
}
// In standalone cluster mode, there are two submission gateways:
// (1) The traditional Akka gateway using o.a.s.deploy.Client as a wrapper
// (2) The new REST-based gateway introduced in Spark 1.3
// The latter is the default behavior as of Spark 1.3, but Spark submit will fail over
// to use the legacy gateway if the master endpoint turns out to be not a REST server.
if (args.isStandaloneCluster && args.useRest) {
try {
// scalastyle:off println
printStream.println("Running Spark using the REST application submission protocol.")
// scalastyle:on println
doRunMain()
} catch {
// Fail over to use the legacy submission gateway
case e: SubmitRestConnectionException =>
printWarning(s"Master endpoint ${args.master} was not a REST server. " +
"Falling back to legacy submission gateway instead.")
args.useRest = false
submit(args)
}
// In all other modes, just run the main class as prepared
} else {
doRunMain()
}
}
/**
* Prepare the environment for submitting an application.
* This returns a 4-tuple:
* (1) the arguments for the child process,
* (2) a list of classpath entries for the child,
* (3) a map of system properties, and
* (4) the main class for the child
* Exposed for testing.
*/
private[deploy] def prepareSubmitEnvironment(args: SparkSubmitArguments)
: (Seq[String], Seq[String], Map[String, String], String) = {
// Return values
val childArgs = new ArrayBuffer[String]()
val childClasspath = new ArrayBuffer[String]()
val sysProps = new HashMap[String, String]()
var childMainClass = ""
// Set the cluster manager
val clusterManager: Int = args.master match {
case m if m.startsWith("yarn") => YARN
case m if m.startsWith("spark") => STANDALONE
case m if m.startsWith("mesos") => MESOS
case m if m.startsWith("local") => LOCAL
case _ => printErrorAndExit("Master must start with yarn, spark, mesos, or local"); -1
}
// Set the deploy mode; default is client mode
var deployMode: Int = args.deployMode match {
case "client" | null => CLIENT
case "cluster" => CLUSTER
case _ => printErrorAndExit("Deploy mode must be either client or cluster"); -1
}
// Because "yarn-cluster" and "yarn-client" encapsulate both the master
// and deploy mode, we have some logic to infer the master and deploy mode
// from each other if only one is specified, or exit early if they are at odds.
if (clusterManager == YARN) {
if (args.master == "yarn-standalone") {
printWarning("\"yarn-standalone\" is deprecated. Use \"yarn-cluster\" instead.")
args.master = "yarn-cluster"
}
(args.master, args.deployMode) match {
case ("yarn-cluster", null) =>
deployMode = CLUSTER
case ("yarn-cluster", "client") =>
printErrorAndExit("Client deploy mode is not compatible with master \"yarn-cluster\"")
case ("yarn-client", "cluster") =>
printErrorAndExit("Cluster deploy mode is not compatible with master \"yarn-client\"")
case (_, mode) =>
args.master = "yarn-" + Option(mode).getOrElse("client")
}
// Make sure YARN is included in our build if we're trying to use it
if (!Utils.classIsLoadable("org.apache.spark.deploy.yarn.Client") && !Utils.isTesting) {
printErrorAndExit(
"Could not load YARN classes. " +
"This copy of Spark may not have been compiled with YARN support.")
}
}
// Update args.deployMode if it is null. It will be passed down as a Spark property later.
(args.deployMode, deployMode) match {
case (null, CLIENT) => args.deployMode = "client"
case (null, CLUSTER) => args.deployMode = "cluster"
case _ =>
}
val isYarnCluster = clusterManager == YARN && deployMode == CLUSTER
val isMesosCluster = clusterManager == MESOS && deployMode == CLUSTER
// Resolve maven dependencies if there are any and add classpath to jars. Add them to py-files
// too for packages that include Python code
val exclusions: Seq[String] =
if (!StringUtils.isBlank(args.packagesExclusions)) {
args.packagesExclusions.split(",")
} else {
Nil
}
val resolvedMavenCoordinates = SparkSubmitUtils.resolveMavenCoordinates(args.packages,
Option(args.repositories), Option(args.ivyRepoPath), exclusions = exclusions)
if (!StringUtils.isBlank(resolvedMavenCoordinates)) {
args.jars = mergeFileLists(args.jars, resolvedMavenCoordinates)
if (args.isPython) {
args.pyFiles = mergeFileLists(args.pyFiles, resolvedMavenCoordinates)
}
}
// install any R packages that may have been passed through --jars or --packages.
// Spark Packages may contain R source code inside the jar.
if (args.isR && !StringUtils.isBlank(args.jars)) {
RPackageUtils.checkAndBuildRPackage(args.jars, printStream, args.verbose)
}
// Require all python files to be local, so we can add them to the PYTHONPATH
// In YARN cluster mode, python files are distributed as regular files, which can be non-local
if (args.isPython && !isYarnCluster) {
if (Utils.nonLocalPaths(args.primaryResource).nonEmpty) {
printErrorAndExit(s"Only local python files are supported: $args.primaryResource")
}
val nonLocalPyFiles = Utils.nonLocalPaths(args.pyFiles).mkString(",")
if (nonLocalPyFiles.nonEmpty) {
printErrorAndExit(s"Only local additional python files are supported: $nonLocalPyFiles")
}
}
// Require all R files to be local
if (args.isR && !isYarnCluster) {
if (Utils.nonLocalPaths(args.primaryResource).nonEmpty) {
printErrorAndExit(s"Only local R files are supported: $args.primaryResource")
}
}
// The following modes are not supported or applicable
(clusterManager, deployMode) match {
case (MESOS, CLUSTER) if args.isR =>
printErrorAndExit("Cluster deploy mode is currently not supported for R " +
"applications on Mesos clusters.")
case (STANDALONE, CLUSTER) if args.isPython =>
printErrorAndExit("Cluster deploy mode is currently not supported for python " +
"applications on standalone clusters.")
case (STANDALONE, CLUSTER) if args.isR =>
printErrorAndExit("Cluster deploy mode is currently not supported for R " +
"applications on standalone clusters.")
case (LOCAL, CLUSTER) =>
printErrorAndExit("Cluster deploy mode is not compatible with master \"local\"")
case (_, CLUSTER) if isShell(args.primaryResource) =>
printErrorAndExit("Cluster deploy mode is not applicable to Spark shells.")
case (_, CLUSTER) if isSqlShell(args.mainClass) =>
printErrorAndExit("Cluster deploy mode is not applicable to Spark SQL shell.")
case (_, CLUSTER) if isThriftServer(args.mainClass) =>
printErrorAndExit("Cluster deploy mode is not applicable to Spark Thrift server.")
case _ =>
}
// If we're running a python app, set the main class to our specific python runner
if (args.isPython && deployMode == CLIENT) {
if (args.primaryResource == PYSPARK_SHELL) {
args.mainClass = "org.apache.spark.api.python.PythonGatewayServer"
} else {
// If a python file is provided, add it to the child arguments and list of files to deploy.
// Usage: PythonAppRunner <main python file> <extra python files> [app arguments]
args.mainClass = "org.apache.spark.deploy.PythonRunner"
args.childArgs = ArrayBuffer(args.primaryResource, args.pyFiles) ++ args.childArgs
if (clusterManager != YARN) {
// The YARN backend distributes the primary file differently, so don't merge it.
args.files = mergeFileLists(args.files, args.primaryResource)
}
}
if (clusterManager != YARN) {
// The YARN backend handles python files differently, so don't merge the lists.
args.files = mergeFileLists(args.files, args.pyFiles)
}
if (args.pyFiles != null) {
sysProps("spark.submit.pyFiles") = args.pyFiles
}
}
// In YARN mode for an R app, add the SparkR package archive to archives
// that can be distributed with the job
if (args.isR && clusterManager == YARN) {
val rPackagePath = RUtils.localSparkRPackagePath
if (rPackagePath.isEmpty) {
printErrorAndExit("SPARK_HOME does not exist for R application in YARN mode.")
}
val rPackageFile =
RPackageUtils.zipRLibraries(new File(rPackagePath.get), SPARKR_PACKAGE_ARCHIVE)
if (!rPackageFile.exists()) {
printErrorAndExit(s"$SPARKR_PACKAGE_ARCHIVE does not exist for R application in YARN mode.")
}
val localURI = Utils.resolveURI(rPackageFile.getAbsolutePath)
// Assigns a symbol link name "sparkr" to the shipped package.
args.archives = mergeFileLists(args.archives, localURI.toString + "#sparkr")
}
// If we're running a R app, set the main class to our specific R runner
if (args.isR && deployMode == CLIENT) {
if (args.primaryResource == SPARKR_SHELL) {
args.mainClass = "org.apache.spark.api.r.RBackend"
} else {
// If a R file is provided, add it to the child arguments and list of files to deploy.
// Usage: RRunner <main R file> [app arguments]
args.mainClass = "org.apache.spark.deploy.RRunner"
args.childArgs = ArrayBuffer(args.primaryResource) ++ args.childArgs
args.files = mergeFileLists(args.files, args.primaryResource)
}
}
if (isYarnCluster && args.isR) {
// In yarn-cluster mode for a R app, add primary resource to files
// that can be distributed with the job
args.files = mergeFileLists(args.files, args.primaryResource)
}
// Special flag to avoid deprecation warnings at the client
sysProps("SPARK_SUBMIT") = "true"
// A list of rules to map each argument to system properties or command-line options in
// each deploy mode; we iterate through these below
val options = List[OptionAssigner](
// All cluster managers
OptionAssigner(args.master, ALL_CLUSTER_MGRS, ALL_DEPLOY_MODES, sysProp = "spark.master"),
OptionAssigner(args.deployMode, ALL_CLUSTER_MGRS, ALL_DEPLOY_MODES,
sysProp = "spark.submit.deployMode"),
OptionAssigner(args.name, ALL_CLUSTER_MGRS, ALL_DEPLOY_MODES, sysProp = "spark.app.name"),
OptionAssigner(args.jars, ALL_CLUSTER_MGRS, CLIENT, sysProp = "spark.jars"),
OptionAssigner(args.ivyRepoPath, ALL_CLUSTER_MGRS, CLIENT, sysProp = "spark.jars.ivy"),
OptionAssigner(args.driverMemory, ALL_CLUSTER_MGRS, CLIENT,
sysProp = "spark.driver.memory"),
OptionAssigner(args.driverExtraClassPath, ALL_CLUSTER_MGRS, ALL_DEPLOY_MODES,
sysProp = "spark.driver.extraClassPath"),
OptionAssigner(args.driverExtraJavaOptions, ALL_CLUSTER_MGRS, ALL_DEPLOY_MODES,
sysProp = "spark.driver.extraJavaOptions"),
OptionAssigner(args.driverExtraLibraryPath, ALL_CLUSTER_MGRS, ALL_DEPLOY_MODES,
sysProp = "spark.driver.extraLibraryPath"),
// Yarn client only
OptionAssigner(args.queue, YARN, CLIENT, sysProp = "spark.yarn.queue"),
OptionAssigner(args.numExecutors, YARN, ALL_DEPLOY_MODES,
sysProp = "spark.executor.instances"),
OptionAssigner(args.files, YARN, CLIENT, sysProp = "spark.yarn.dist.files"),
OptionAssigner(args.archives, YARN, CLIENT, sysProp = "spark.yarn.dist.archives"),
OptionAssigner(args.principal, YARN, CLIENT, sysProp = "spark.yarn.principal"),
OptionAssigner(args.keytab, YARN, CLIENT, sysProp = "spark.yarn.keytab"),
// Yarn cluster only
OptionAssigner(args.name, YARN, CLUSTER, clOption = "--name"),
OptionAssigner(args.driverMemory, YARN, CLUSTER, clOption = "--driver-memory"),
OptionAssigner(args.driverCores, YARN, CLUSTER, clOption = "--driver-cores"),
OptionAssigner(args.queue, YARN, CLUSTER, clOption = "--queue"),
OptionAssigner(args.executorMemory, YARN, CLUSTER, clOption = "--executor-memory"),
OptionAssigner(args.executorCores, YARN, CLUSTER, clOption = "--executor-cores"),
OptionAssigner(args.files, YARN, CLUSTER, clOption = "--files"),
OptionAssigner(args.archives, YARN, CLUSTER, clOption = "--archives"),
OptionAssigner(args.jars, YARN, CLUSTER, clOption = "--addJars"),
OptionAssigner(args.principal, YARN, CLUSTER, clOption = "--principal"),
OptionAssigner(args.keytab, YARN, CLUSTER, clOption = "--keytab"),
// Other options
OptionAssigner(args.executorCores, STANDALONE | YARN, ALL_DEPLOY_MODES,
sysProp = "spark.executor.cores"),
OptionAssigner(args.executorMemory, STANDALONE | MESOS | YARN, ALL_DEPLOY_MODES,
sysProp = "spark.executor.memory"),
OptionAssigner(args.totalExecutorCores, STANDALONE | MESOS, ALL_DEPLOY_MODES,
sysProp = "spark.cores.max"),
OptionAssigner(args.files, LOCAL | STANDALONE | MESOS, ALL_DEPLOY_MODES,
sysProp = "spark.files"),
OptionAssigner(args.jars, STANDALONE | MESOS, CLUSTER, sysProp = "spark.jars"),
OptionAssigner(args.driverMemory, STANDALONE | MESOS, CLUSTER,
sysProp = "spark.driver.memory"),
OptionAssigner(args.driverCores, STANDALONE | MESOS, CLUSTER,
sysProp = "spark.driver.cores"),
OptionAssigner(args.supervise.toString, STANDALONE | MESOS, CLUSTER,
sysProp = "spark.driver.supervise"),
OptionAssigner(args.ivyRepoPath, STANDALONE, CLUSTER, sysProp = "spark.jars.ivy")
)
// In client mode, launch the application main class directly
// In addition, add the main application jar and any added jars (if any) to the classpath
if (deployMode == CLIENT) {
childMainClass = args.mainClass
if (isUserJar(args.primaryResource)) {
childClasspath += args.primaryResource
}
if (args.jars != null) { childClasspath ++= args.jars.split(",") }
if (args.childArgs != null) { childArgs ++= args.childArgs }
}
// Map all arguments to command-line options or system properties for our chosen mode
for (opt <- options) {
if (opt.value != null &&
(deployMode & opt.deployMode) != 0 &&
(clusterManager & opt.clusterManager) != 0) {
if (opt.clOption != null) { childArgs += (opt.clOption, opt.value) }
if (opt.sysProp != null) { sysProps.put(opt.sysProp, opt.value) }
}
}
// Add the application jar automatically so the user doesn't have to call sc.addJar
// For YARN cluster mode, the jar is already distributed on each node as "app.jar"
// For python and R files, the primary resource is already distributed as a regular file
if (!isYarnCluster && !args.isPython && !args.isR) {
var jars = sysProps.get("spark.jars").map(x => x.split(",").toSeq).getOrElse(Seq.empty)
if (isUserJar(args.primaryResource)) {
jars = jars ++ Seq(args.primaryResource)
}
sysProps.put("spark.jars", jars.mkString(","))
}
// In standalone cluster mode, use the REST client to submit the application (Spark 1.3+).
// All Spark parameters are expected to be passed to the client through system properties.
if (args.isStandaloneCluster) {
if (args.useRest) {
childMainClass = "org.apache.spark.deploy.rest.RestSubmissionClient"
childArgs += (args.primaryResource, args.mainClass)
} else {
// In legacy standalone cluster mode, use Client as a wrapper around the user class
childMainClass = "org.apache.spark.deploy.Client"
if (args.supervise) { childArgs += "--supervise" }
Option(args.driverMemory).foreach { m => childArgs += ("--memory", m) }
Option(args.driverCores).foreach { c => childArgs += ("--cores", c) }
childArgs += "launch"
childArgs += (args.master, args.primaryResource, args.mainClass)
}
if (args.childArgs != null) {
childArgs ++= args.childArgs
}
}
// Let YARN know it's a pyspark app, so it distributes needed libraries.
if (clusterManager == YARN) {
if (args.isPython) {
sysProps.put("spark.yarn.isPython", "true")
}
if (args.principal != null) {
require(args.keytab != null, "Keytab must be specified when the keytab is specified")
UserGroupInformation.loginUserFromKeytab(args.principal, args.keytab)
}
}
// In yarn-cluster mode, use yarn.Client as a wrapper around the user class
if (isYarnCluster) {
childMainClass = "org.apache.spark.deploy.yarn.Client"
if (args.isPython) {
childArgs += ("--primary-py-file", args.primaryResource)
if (args.pyFiles != null) {
childArgs += ("--py-files", args.pyFiles)
}
childArgs += ("--class", "org.apache.spark.deploy.PythonRunner")
} else if (args.isR) {
val mainFile = new Path(args.primaryResource).getName
childArgs += ("--primary-r-file", mainFile)
childArgs += ("--class", "org.apache.spark.deploy.RRunner")
} else {
if (args.primaryResource != SPARK_INTERNAL) {
childArgs += ("--jar", args.primaryResource)
}
childArgs += ("--class", args.mainClass)
}
if (args.childArgs != null) {
args.childArgs.foreach { arg => childArgs += ("--arg", arg) }
}
}
if (isMesosCluster) {
assert(args.useRest, "Mesos cluster mode is only supported through the REST submission API")
childMainClass = "org.apache.spark.deploy.rest.RestSubmissionClient"
if (args.isPython) {
// Second argument is main class
childArgs += (args.primaryResource, "")
if (args.pyFiles != null) {
sysProps("spark.submit.pyFiles") = args.pyFiles
}
} else {
childArgs += (args.primaryResource, args.mainClass)
}
if (args.childArgs != null) {
childArgs ++= args.childArgs
}
}
// Load any properties specified through --conf and the default properties file
for ((k, v) <- args.sparkProperties) {
sysProps.getOrElseUpdate(k, v)
}
// Ignore invalid spark.driver.host in cluster modes.
if (deployMode == CLUSTER) {
sysProps -= "spark.driver.host"
}
// Resolve paths in certain spark properties
val pathConfigs = Seq(
"spark.jars",
"spark.files",
"spark.yarn.jar",
"spark.yarn.dist.files",
"spark.yarn.dist.archives")
pathConfigs.foreach { config =>
// Replace old URIs with resolved URIs, if they exist
sysProps.get(config).foreach { oldValue =>
sysProps(config) = Utils.resolveURIs(oldValue)
}
}
// Resolve and format python file paths properly before adding them to the PYTHONPATH.
// The resolving part is redundant in the case of --py-files, but necessary if the user
// explicitly sets `spark.submit.pyFiles` in his/her default properties file.
sysProps.get("spark.submit.pyFiles").foreach { pyFiles =>
val resolvedPyFiles = Utils.resolveURIs(pyFiles)
val formattedPyFiles = PythonRunner.formatPaths(resolvedPyFiles).mkString(",")
sysProps("spark.submit.pyFiles") = formattedPyFiles
}
(childArgs, childClasspath, sysProps, childMainClass)
}
/**
* Run the main method of the child class using the provided launch environment.
*
* Note that this main class will not be the one provided by the user if we're
* running cluster deploy mode or python applications.
*/
private def runMain(
childArgs: Seq[String],
childClasspath: Seq[String],
sysProps: Map[String, String],
childMainClass: String,
verbose: Boolean): Unit = {
// scalastyle:off println
if (verbose) {
printStream.println(s"Main class:\n$childMainClass")
printStream.println(s"Arguments:\n${childArgs.mkString("\n")}")
printStream.println(s"System properties:\n${sysProps.mkString("\n")}")
printStream.println(s"Classpath elements:\n${childClasspath.mkString("\n")}")
printStream.println("\n")
}
// scalastyle:on println
val loader =
if (sysProps.getOrElse("spark.driver.userClassPathFirst", "false").toBoolean) {
new ChildFirstURLClassLoader(new Array[URL](0),
Thread.currentThread.getContextClassLoader)
} else {
new MutableURLClassLoader(new Array[URL](0),
Thread.currentThread.getContextClassLoader)
}
Thread.currentThread.setContextClassLoader(loader)
for (jar <- childClasspath) {
addJarToClasspath(jar, loader)
}
for ((key, value) <- sysProps) {
System.setProperty(key, value)
}
var mainClass: Class[_] = null
try {
mainClass = Utils.classForName(childMainClass)
} catch {
case e: ClassNotFoundException =>
e.printStackTrace(printStream)
if (childMainClass.contains("thriftserver")) {
// scalastyle:off println
printStream.println(s"Failed to load main class $childMainClass.")
printStream.println("You need to build Spark with -Phive and -Phive-thriftserver.")
// scalastyle:on println
}
System.exit(CLASS_NOT_FOUND_EXIT_STATUS)
case e: NoClassDefFoundError =>
e.printStackTrace(printStream)
if (e.getMessage.contains("org/apache/hadoop/hive")) {
// scalastyle:off println
printStream.println(s"Failed to load hive class.")
printStream.println("You need to build Spark with -Phive and -Phive-thriftserver.")
// scalastyle:on println
}
System.exit(CLASS_NOT_FOUND_EXIT_STATUS)
}
// SPARK-4170
if (classOf[scala.App].isAssignableFrom(mainClass)) {
printWarning("Subclasses of scala.App may not work correctly. Use a main() method instead.")
}
val mainMethod = mainClass.getMethod("main", new Array[String](0).getClass)
if (!Modifier.isStatic(mainMethod.getModifiers)) {
throw new IllegalStateException("The main method in the given main class must be static")
}
def findCause(t: Throwable): Throwable = t match {
case e: UndeclaredThrowableException =>
if (e.getCause() != null) findCause(e.getCause()) else e
case e: InvocationTargetException =>
if (e.getCause() != null) findCause(e.getCause()) else e
case e: Throwable =>
e
}
try {
mainMethod.invoke(null, childArgs.toArray)
} catch {
case t: Throwable =>
findCause(t) match {
case SparkUserAppException(exitCode) =>
System.exit(exitCode)
case t: Throwable =>
throw t
}
}
}
private def addJarToClasspath(localJar: String, loader: MutableURLClassLoader) {
val uri = Utils.resolveURI(localJar)
uri.getScheme match {
case "file" | "local" =>
val file = new File(uri.getPath)
if (file.exists()) {
loader.addURL(file.toURI.toURL)
} else {
printWarning(s"Local jar $file does not exist, skipping.")
}
case _ =>
printWarning(s"Skip remote jar $uri.")
}
}
/**
* Return whether the given primary resource represents a user jar.
*/
private[deploy] def isUserJar(res: String): Boolean = {
!isShell(res) && !isPython(res) && !isInternal(res) && !isR(res)
}
/**
* Return whether the given primary resource represents a shell.
*/
private[deploy] def isShell(res: String): Boolean = {
(res == SPARK_SHELL || res == PYSPARK_SHELL || res == SPARKR_SHELL)
}
/**
* Return whether the given main class represents a sql shell.
*/
private[deploy] def isSqlShell(mainClass: String): Boolean = {
mainClass == "org.apache.spark.sql.hive.thriftserver.SparkSQLCLIDriver"
}
/**
* Return whether the given main class represents a thrift server.
*/
private def isThriftServer(mainClass: String): Boolean = {
mainClass == "org.apache.spark.sql.hive.thriftserver.HiveThriftServer2"
}
/**
* Return whether the given primary resource requires running python.
*/
private[deploy] def isPython(res: String): Boolean = {
res != null && res.endsWith(".py") || res == PYSPARK_SHELL
}
/**
* Return whether the given primary resource requires running R.
*/
private[deploy] def isR(res: String): Boolean = {
res != null && res.endsWith(".R") || res == SPARKR_SHELL
}
private[deploy] def isInternal(res: String): Boolean = {
res == SPARK_INTERNAL
}
/**
* Merge a sequence of comma-separated file lists, some of which may be null to indicate
* no files, into a single comma-separated string.
*/
private def mergeFileLists(lists: String*): String = {
val merged = lists.filterNot(StringUtils.isBlank)
.flatMap(_.split(","))
.mkString(",")
if (merged == "") null else merged
}
}
/** Provides utility functions to be used inside SparkSubmit. */
private[spark] object SparkSubmitUtils {
// Exposed for testing
var printStream = SparkSubmit.printStream
/**
* Represents a Maven Coordinate
* @param groupId the groupId of the coordinate
* @param artifactId the artifactId of the coordinate
* @param version the version of the coordinate
*/
private[deploy] case class MavenCoordinate(groupId: String, artifactId: String, version: String) {
override def toString: String = s"$groupId:$artifactId:$version"
}
/**
* Extracts maven coordinates from a comma-delimited string. Coordinates should be provided
* in the format `groupId:artifactId:version` or `groupId/artifactId:version`.
* @param coordinates Comma-delimited string of maven coordinates
* @return Sequence of Maven coordinates
*/
def extractMavenCoordinates(coordinates: String): Seq[MavenCoordinate] = {
coordinates.split(",").map { p =>
val splits = p.replace("/", ":").split(":")
require(splits.length == 3, s"Provided Maven Coordinates must be in the form " +
s"'groupId:artifactId:version'. The coordinate provided is: $p")
require(splits(0) != null && splits(0).trim.nonEmpty, s"The groupId cannot be null or " +
s"be whitespace. The groupId provided is: ${splits(0)}")
require(splits(1) != null && splits(1).trim.nonEmpty, s"The artifactId cannot be null or " +
s"be whitespace. The artifactId provided is: ${splits(1)}")
require(splits(2) != null && splits(2).trim.nonEmpty, s"The version cannot be null or " +
s"be whitespace. The version provided is: ${splits(2)}")
new MavenCoordinate(splits(0), splits(1), splits(2))
}
}
/** Path of the local Maven cache. */
private[spark] def m2Path: File = {
if (Utils.isTesting) {
// test builds delete the maven cache, and this can cause flakiness
new File("dummy", ".m2" + File.separator + "repository")
} else {
new File(System.getProperty("user.home"), ".m2" + File.separator + "repository")
}
}
/**
* Extracts maven coordinates from a comma-delimited string
* @param remoteRepos Comma-delimited string of remote repositories
* @param ivySettings The Ivy settings for this session
* @return A ChainResolver used by Ivy to search for and resolve dependencies.
*/
def createRepoResolvers(remoteRepos: Option[String], ivySettings: IvySettings): ChainResolver = {
// We need a chain resolver if we want to check multiple repositories
val cr = new ChainResolver
cr.setName("list")
val repositoryList = remoteRepos.getOrElse("")
// add any other remote repositories other than maven central
if (repositoryList.trim.nonEmpty) {
repositoryList.split(",").zipWithIndex.foreach { case (repo, i) =>
val brr: IBiblioResolver = new IBiblioResolver
brr.setM2compatible(true)
brr.setUsepoms(true)
brr.setRoot(repo)
brr.setName(s"repo-${i + 1}")
cr.add(brr)
// scalastyle:off println
printStream.println(s"$repo added as a remote repository with the name: ${brr.getName}")
// scalastyle:on println
}
}
val localM2 = new IBiblioResolver
localM2.setM2compatible(true)
localM2.setRoot(m2Path.toURI.toString)
localM2.setUsepoms(true)
localM2.setName("local-m2-cache")
cr.add(localM2)
val localIvy = new FileSystemResolver
val localIvyRoot = new File(ivySettings.getDefaultIvyUserDir, "local")
localIvy.setLocal(true)
localIvy.setRepository(new FileRepository(localIvyRoot))
val ivyPattern = Seq("[organisation]", "[module]", "[revision]", "[type]s",
"[artifact](-[classifier]).[ext]").mkString(File.separator)
localIvy.addIvyPattern(localIvyRoot.getAbsolutePath + File.separator + ivyPattern)
localIvy.setName("local-ivy-cache")
cr.add(localIvy)
// the biblio resolver resolves POM declared dependencies
val br: IBiblioResolver = new IBiblioResolver
br.setM2compatible(true)
br.setUsepoms(true)
br.setName("central")
cr.add(br)
val sp: IBiblioResolver = new IBiblioResolver
sp.setM2compatible(true)
sp.setUsepoms(true)
sp.setRoot("http://dl.bintray.com/spark-packages/maven")
sp.setName("spark-packages")
cr.add(sp)
cr
}
/**
* Output a comma-delimited list of paths for the downloaded jars to be added to the classpath
* (will append to jars in SparkSubmit).
* @param artifacts Sequence of dependencies that were resolved and retrieved
* @param cacheDirectory directory where jars are cached
* @return a comma-delimited list of paths for the dependencies
*/
def resolveDependencyPaths(
artifacts: Array[AnyRef],
cacheDirectory: File): String = {
artifacts.map { artifactInfo =>
val artifact = artifactInfo.asInstanceOf[Artifact].getModuleRevisionId
cacheDirectory.getAbsolutePath + File.separator +
s"${artifact.getOrganisation}_${artifact.getName}-${artifact.getRevision}.jar"
}.mkString(",")
}
/** Adds the given maven coordinates to Ivy's module descriptor. */
def addDependenciesToIvy(
md: DefaultModuleDescriptor,
artifacts: Seq[MavenCoordinate],
ivyConfName: String): Unit = {
artifacts.foreach { mvn =>
val ri = ModuleRevisionId.newInstance(mvn.groupId, mvn.artifactId, mvn.version)
val dd = new DefaultDependencyDescriptor(ri, false, false)
dd.addDependencyConfiguration(ivyConfName, ivyConfName)
// scalastyle:off println
printStream.println(s"${dd.getDependencyId} added as a dependency")
// scalastyle:on println
md.addDependency(dd)
}
}
/** Add exclusion rules for dependencies already included in the spark-assembly */
def addExclusionRules(
ivySettings: IvySettings,
ivyConfName: String,
md: DefaultModuleDescriptor): Unit = {
// Add scala exclusion rule
md.addExcludeRule(createExclusion("*:scala-library:*", ivySettings, ivyConfName))
// We need to specify each component explicitly, otherwise we miss spark-streaming-kafka and
// other spark-streaming utility components. Underscore is there to differentiate between
// spark-streaming_2.1x and spark-streaming-kafka-assembly_2.1x
val components = Seq("bagel_", "catalyst_", "core_", "graphx_", "hive_", "mllib_", "repl_",
"sql_", "streaming_", "yarn_", "network-common_", "network-shuffle_", "network-yarn_")
components.foreach { comp =>
md.addExcludeRule(createExclusion(s"org.apache.spark:spark-$comp*:*", ivySettings,
ivyConfName))
}
}
/** A nice function to use in tests as well. Values are dummy strings. */
def getModuleDescriptor: DefaultModuleDescriptor = DefaultModuleDescriptor.newDefaultInstance(
ModuleRevisionId.newInstance("org.apache.spark", "spark-submit-parent", "1.0"))
/**
* Resolves any dependencies that were supplied through maven coordinates
* @param coordinates Comma-delimited string of maven coordinates
* @param remoteRepos Comma-delimited string of remote repositories other than maven central
* @param ivyPath The path to the local ivy repository
* @param exclusions Exclusions to apply when resolving transitive dependencies
* @return The comma-delimited path to the jars of the given maven artifacts including their
* transitive dependencies
*/
def resolveMavenCoordinates(
coordinates: String,
remoteRepos: Option[String],
ivyPath: Option[String],
exclusions: Seq[String] = Nil,
isTest: Boolean = false): String = {
if (coordinates == null || coordinates.trim.isEmpty) {
""
} else {
val sysOut = System.out
try {
// To prevent ivy from logging to system out
System.setOut(printStream)
val artifacts = extractMavenCoordinates(coordinates)
// Default configuration name for ivy
val ivyConfName = "default"
// set ivy settings for location of cache
val ivySettings: IvySettings = new IvySettings
// Directories for caching downloads through ivy and storing the jars when maven coordinates
// are supplied to spark-submit
val alternateIvyCache = ivyPath.getOrElse("")
val packagesDirectory: File =
if (alternateIvyCache == null || alternateIvyCache.trim.isEmpty) {
new File(ivySettings.getDefaultIvyUserDir, "jars")
} else {
ivySettings.setDefaultIvyUserDir(new File(alternateIvyCache))
ivySettings.setDefaultCache(new File(alternateIvyCache, "cache"))
new File(alternateIvyCache, "jars")
}
// scalastyle:off println
printStream.println(
s"Ivy Default Cache set to: ${ivySettings.getDefaultCache.getAbsolutePath}")
printStream.println(s"The jars for the packages stored in: $packagesDirectory")
// scalastyle:on println
// create a pattern matcher
ivySettings.addMatcher(new GlobPatternMatcher)
// create the dependency resolvers
val repoResolver = createRepoResolvers(remoteRepos, ivySettings)
ivySettings.addResolver(repoResolver)
ivySettings.setDefaultResolver(repoResolver.getName)
val ivy = Ivy.newInstance(ivySettings)
// Set resolve options to download transitive dependencies as well
val resolveOptions = new ResolveOptions
resolveOptions.setTransitive(true)
val retrieveOptions = new RetrieveOptions
// Turn downloading and logging off for testing
if (isTest) {
resolveOptions.setDownload(false)
resolveOptions.setLog(LogOptions.LOG_QUIET)
retrieveOptions.setLog(LogOptions.LOG_QUIET)
} else {
resolveOptions.setDownload(true)
}
// A Module descriptor must be specified. Entries are dummy strings
val md = getModuleDescriptor
// clear ivy resolution from previous launches. The resolution file is usually at
// ~/.ivy2/org.apache.spark-spark-submit-parent-default.xml. In between runs, this file
// leads to confusion with Ivy when the files can no longer be found at the repository
// declared in that file/
val mdId = md.getModuleRevisionId
val previousResolution = new File(ivySettings.getDefaultCache,
s"${mdId.getOrganisation}-${mdId.getName}-$ivyConfName.xml")
if (previousResolution.exists) previousResolution.delete
md.setDefaultConf(ivyConfName)
// Add exclusion rules for Spark and Scala Library
addExclusionRules(ivySettings, ivyConfName, md)
// add all supplied maven artifacts as dependencies
addDependenciesToIvy(md, artifacts, ivyConfName)
exclusions.foreach { e =>
md.addExcludeRule(createExclusion(e + ":*", ivySettings, ivyConfName))
}
// resolve dependencies
val rr: ResolveReport = ivy.resolve(md, resolveOptions)
if (rr.hasError) {
throw new RuntimeException(rr.getAllProblemMessages.toString)
}
// retrieve all resolved dependencies
ivy.retrieve(rr.getModuleDescriptor.getModuleRevisionId,
packagesDirectory.getAbsolutePath + File.separator +
"[organization]_[artifact]-[revision].[ext]",
retrieveOptions.setConfs(Array(ivyConfName)))
resolveDependencyPaths(rr.getArtifacts.toArray, packagesDirectory)
} finally {
System.setOut(sysOut)
}
}
}
private[deploy] def createExclusion(
coords: String,
ivySettings: IvySettings,
ivyConfName: String): ExcludeRule = {
val c = extractMavenCoordinates(coords)(0)
val id = new ArtifactId(new ModuleId(c.groupId, c.artifactId), "*", "*", "*")
val rule = new DefaultExcludeRule(id, ivySettings.getMatcher("glob"), null)
rule.addConfiguration(ivyConfName)
rule
}
}
/**
* Provides an indirection layer for passing arguments as system properties or flags to
* the user's driver program or to downstream launcher tools.
*/
private case class OptionAssigner(
value: String,
clusterManager: Int,
deployMode: Int,
clOption: String = null,
sysProp: String = null)
|