Spark (using Scala) throws SocketException: Connection reset and SocketTimeoutException: Read timed out - scala

I am trying to load a (very big) serialized RDD of objects into the memory of a cluster of ec2 nodes, and then do some extraction on those objects and store the resulting RDD on disk (as object files). Unluckily I get SocketException: Connection reset once and SocketTimeoutException: Read timed out a few times.
Here is the relevant part of my code:
val pairsLocation = args(0)
val pairsRDD = sc.objectFile[Pair](pairLocation)
// taking individual objects out of "Pair" objects (containing two of those simple objects)
val extracted = pairsRDD.filter(myFunc(_._1)).
flatMap(x => List(x._1, x._2)).distinct
val savePath = "s3 URI"
extracted.saveAsObjectFile(savePath)
Here are the details of the errors (warnings) I get:
15/03/12 18:40:27 WARN scheduler.TaskSetManager: Lost task 574.0 in stage 0.0 (TID 574, ip-10-45-14-27.us-west-2.compute.internal):
java.net.SocketException: Connection reset
at java.net.SocketInputStream.read(SocketInputStream.java:196)
at java.net.SocketInputStream.read(SocketInputStream.java:122)
at sun.security.ssl.InputRecord.readFully(InputRecord.java:442)
at sun.security.ssl.InputRecord.readV3Record(InputRecord.java:554)
at sun.security.ssl.InputRecord.read(InputRecord.java:509)
at sun.security.ssl.SSLSocketImpl.readRecord(SSLSocketImpl.java:934)
at sun.security.ssl.SSLSocketImpl.readDataRecord(SSLSocketImpl.java:891)
at sun.security.ssl.AppInputStream.read(AppInputStream.java:102)
at java.io.BufferedInputStream.read1(BufferedInputStream.java:273)
at java.io.BufferedInputStream.read(BufferedInputStream.java:334)
at org.apache.commons.httpclient.ContentLengthInputStream.read(ContentLengthInputStream.java:170)
at java.io.FilterInputStream.read(FilterInputStream.java:133)
at org.apache.commons.httpclient.AutoCloseInputStream.read(AutoCloseInputStream.java:108)
at org.jets3t.service.io.InterruptableInputStream.read(InterruptableInputStream.java:76)
at org.jets3t.service.impl.rest.httpclient.HttpMethodReleaseInputStream.read(HttpMethodReleaseInputStream.java:136)
at org.apache.hadoop.fs.s3native.NativeS3FileSystem$NativeS3FsInputStream.read(NativeS3FileSystem.java:98)
at java.io.BufferedInputStream.fill(BufferedInputStream.java:235)
at java.io.BufferedInputStream.read1(BufferedInputStream.java:275)
at java.io.BufferedInputStream.read(BufferedInputStream.java:334)
at java.io.DataInputStream.readFully(DataInputStream.java:195)
at org.apache.hadoop.io.DataOutputBuffer$Buffer.write(DataOutputBuffer.java:63)
at org.apache.hadoop.io.DataOutputBuffer.write(DataOutputBuffer.java:101)
at org.apache.hadoop.io.SequenceFile$Reader.next(SequenceFile.java:1988)
at org.apache.hadoop.io.SequenceFile$Reader.next(SequenceFile.java:2120)
at org.apache.hadoop.mapred.SequenceFileRecordReader.next(SequenceFileRecordReader.java:76)
at org.apache.spark.rdd.HadoopRDD$$anon$1.getNext(HadoopRDD.scala:244)
at org.apache.spark.rdd.HadoopRDD$$anon$1.getNext(HadoopRDD.scala:210)
at org.apache.spark.util.NextIterator.hasNext(NextIterator.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:39)
at scala.collection.Iterator$$anon$13.hasNext(Iterator.scala:371)
at scala.collection.Iterator$$anon$14.hasNext(Iterator.scala:388)
at scala.collection.Iterator$$anon$13.hasNext(Iterator.scala:371)
at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:327)
at org.apache.spark.util.collection.ExternalSorter.insertAll(ExternalSorter.scala:202)
at org.apache.spark.shuffle.sort.SortShuffleWriter.write(SortShuffleWriter.scala:58)
at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:68)
at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:41)
at org.apache.spark.scheduler.Task.run(Task.scala:56)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:196)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
at java.lang.Thread.run(Thread.java:745)
15/03/12 18:42:16 WARN scheduler.TaskSetManager: Lost task 380.0 in stage 0.0 (TID 380, ip-10-47-3-111.us-west-2.compute.internal):
java.net.SocketTimeoutException: Read timed out
at java.net.SocketInputStream.socketRead0(Native Method)
at java.net.SocketInputStream.read(SocketInputStream.java:152)
at java.net.SocketInputStream.read(SocketInputStream.java:122)
at sun.security.ssl.InputRecord.readFully(InputRecord.java:442)
at sun.security.ssl.InputRecord.readV3Record(InputRecord.java:554)
at sun.security.ssl.InputRecord.read(InputRecord.java:509)
at sun.security.ssl.SSLSocketImpl.readRecord(SSLSocketImpl.java:934)
at sun.security.ssl.SSLSocketImpl.readDataRecord(SSLSocketImpl.java:891)
at sun.security.ssl.AppInputStream.read(AppInputStream.java:102)
at java.io.BufferedInputStream.read1(BufferedInputStream.java:273)
at java.io.BufferedInputStream.read(BufferedInputStream.java:334)
at org.apache.commons.httpclient.ContentLengthInputStream.read(ContentLengthInputStream.java:170)
at java.io.FilterInputStream.read(FilterInputStream.java:133)
at org.apache.commons.httpclient.AutoCloseInputStream.read(AutoCloseInputStream.java:108)
at org.jets3t.service.io.InterruptableInputStream.read(InterruptableInputStream.java:76)
at org.jets3t.service.impl.rest.httpclient.HttpMethodReleaseInputStream.read(HttpMethodReleaseInputStream.java:136)
at org.apache.hadoop.fs.s3native.NativeS3FileSystem$NativeS3FsInputStream.read(NativeS3FileSystem.java:98)
at java.io.BufferedInputStream.fill(BufferedInputStream.java:235)
at java.io.BufferedInputStream.read1(BufferedInputStream.java:275)
at java.io.BufferedInputStream.read(BufferedInputStream.java:334)
at java.io.DataInputStream.readFully(DataInputStream.java:195)
at org.apache.hadoop.io.DataOutputBuffer$Buffer.write(DataOutputBuffer.java:63)
at org.apache.hadoop.io.DataOutputBuffer.write(DataOutputBuffer.java:101)
at org.apache.hadoop.io.SequenceFile$Reader.next(SequenceFile.java:1988)
at org.apache.hadoop.io.SequenceFile$Reader.next(SequenceFile.java:2120)
at org.apache.hadoop.mapred.SequenceFileRecordReader.next(SequenceFileRecordReader.java:76)
at org.apache.spark.rdd.HadoopRDD$$anon$1.getNext(HadoopRDD.scala:244)
at org.apache.spark.rdd.HadoopRDD$$anon$1.getNext(HadoopRDD.scala:210)
at org.apache.spark.util.NextIterator.hasNext(NextIterator.scala:71)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:39)
at scala.collection.Iterator$$anon$13.hasNext(Iterator.scala:371)
at scala.collection.Iterator$$anon$14.hasNext(Iterator.scala:388)
at scala.collection.Iterator$$anon$13.hasNext(Iterator.scala:371)
at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:327)
at org.apache.spark.util.collection.ExternalSorter.insertAll(ExternalSorter.scala:202)
at org.apache.spark.shuffle.sort.SortShuffleWriter.write(SortShuffleWriter.scala:58)
at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:68)
at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:41)
at org.apache.spark.scheduler.Task.run(Task.scala:56)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:196)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
at java.lang.Thread.run(Thread.java:745)

Related

org.apache.spark.SparkException ... java.io.IOException: Failed to connect to /IP_ADDRESS

I want to use apache-zeppelin but I cannot make a simple RDD.collect() to work.
Here is the issue:
org.apache.spark.SparkException: Job aborted due to stage failure: Task 2 in stage 0.0 failed 1 times, most recent failure: Lost task 2.0 in stage 0.0 (TID 2, localhost, executor driver): java.io.IOException: Failed to connect to /IP_ADDRESS
Here is my code:
%spark
val df = sc.parallelize(1 to 10, 5)
df.collect()
Installation/configuration:
mac OS X El Capitan
apache-spark (from brew) - 2.2.0
apache-zeppelin (from brew) - 0.7.3
getifaddr en0 = IP_ADDRESS (in the error)
The port looks a bit suspicious to me but I haven't found a way to set it differently.
Any help on this issue would be much appreciated !
Many thanks.
The full traceback:
org.apache.spark.SparkException: Job aborted due to stage failure: Task 2 in stage 0.0 failed 1 times, most recent failure: Lost task 2.0 in stage 0.0 (TID 2, localhost, executor driver): java.io.IOException: Failed to connect to /IP_ADDRESS:PORT
at org.apache.spark.network.client.TransportClientFactory.createClient(TransportClientFactory.java:232)
at org.apache.spark.network.client.TransportClientFactory.createClient(TransportClientFactory.java:182)
at org.apache.spark.rpc.netty.NettyRpcEnv.downloadClient(NettyRpcEnv.scala:366)
at org.apache.spark.rpc.netty.NettyRpcEnv.openChannel(NettyRpcEnv.scala:332)
at org.apache.spark.util.Utils$.doFetchFile(Utils.scala:654)
at org.apache.spark.util.Utils$.fetchFile(Utils.scala:480)
at org.apache.spark.executor.Executor$$anonfun$org$apache$spark$executor$Executor$$updateDependencies$5.apply(Executor.scala:696)
at org.apache.spark.executor.Executor$$anonfun$org$apache$spark$executor$Executor$$updateDependencies$5.apply(Executor.scala:688)
at scala.collection.TraversableLike$WithFilter$$anonfun$foreach$1.apply(TraversableLike.scala:733)
at scala.collection.Iterator$class.foreach(Iterator.scala:893)
at scala.collection.AbstractIterator.foreach(Iterator.scala:1336)
at scala.collection.IterableLike$class.foreach(IterableLike.scala:72)
at scala.collection.AbstractIterable.foreach(Iterable.scala:54)
at scala.collection.TraversableLike$WithFilter.foreach(TraversableLike.scala:732)
at org.apache.spark.executor.Executor.org$apache$spark$executor$Executor$$updateDependencies(Executor.scala:688)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:308)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1149)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:624)
at java.lang.Thread.run(Thread.java:748)
Caused by: io.netty.channel.AbstractChannel$AnnotatedConnectException: Operation timed out: /IP_ADDRESS:PORT
at sun.nio.ch.SocketChannelImpl.checkConnect(Native Method)
at sun.nio.ch.SocketChannelImpl.finishConnect(SocketChannelImpl.java:717)
at io.netty.channel.socket.nio.NioSocketChannel.doFinishConnect(NioSocketChannel.java:257)
at io.netty.channel.nio.AbstractNioChannel$AbstractNioUnsafe.finishConnect(AbstractNioChannel.java:291)
at io.netty.channel.nio.NioEventLoop.processSelectedKey(NioEventLoop.java:631)
at io.netty.channel.nio.NioEventLoop.processSelectedKeysOptimized(NioEventLoop.java:566)
at io.netty.channel.nio.NioEventLoop.processSelectedKeys(NioEventLoop.java:480)
at io.netty.channel.nio.NioEventLoop.run(NioEventLoop.java:442)
at io.netty.util.concurrent.SingleThreadEventExecutor$2.run(SingleThreadEventExecutor.java:131)
at io.netty.util.concurrent.DefaultThreadFactory$DefaultRunnableDecorator.run(DefaultThreadFactory.java:144)
... 1 more
Driver stacktrace:
at org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$failJobAndIndependentStages(DAGScheduler.scala:1499)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1487)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1486)
at scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:48)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1486)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:814)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:814)
at scala.Option.foreach(Option.scala:257)
at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:814)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:1714)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1669)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1658)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:48)
at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:630)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2022)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2043)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2062)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:2087)
at org.apache.spark.rdd.RDD$$anonfun$collect$1.apply(RDD.scala:936)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:112)
at org.apache.spark.rdd.RDD.withScope(RDD.scala:362)
at org.apache.spark.rdd.RDD.collect(RDD.scala:935)
... 47 elided
Caused by: java.io.IOException: Failed to connect to /IP_ADDRESS:PORT
at org.apache.spark.network.client.TransportClientFactory.createClient(TransportClientFactory.java:232)
at org.apache.spark.network.client.TransportClientFactory.createClient(TransportClientFactory.java:182)
at org.apache.spark.rpc.netty.NettyRpcEnv.downloadClient(NettyRpcEnv.scala:366)
at org.apache.spark.rpc.netty.NettyRpcEnv.openChannel(NettyRpcEnv.scala:332)
at org.apache.spark.util.Utils$.doFetchFile(Utils.scala:654)
at org.apache.spark.util.Utils$.fetchFile(Utils.scala:480)
at org.apache.spark.executor.Executor$$anonfun$org$apache$spark$executor$Executor$$updateDependencies$5.apply(Executor.scala:696)
at org.apache.spark.executor.Executor$$anonfun$org$apache$spark$executor$Executor$$updateDependencies$5.apply(Executor.scala:688)
at scala.collection.TraversableLike$WithFilter$$anonfun$foreach$1.apply(TraversableLike.scala:733)
at scala.collection.Iterator$class.foreach(Iterator.scala:893)
at scala.collection.AbstractIterator.foreach(Iterator.scala:1336)
at scala.collection.IterableLike$class.foreach(IterableLike.scala:72)
at scala.collection.AbstractIterable.foreach(Iterable.scala:54)
at scala.collection.TraversableLike$WithFilter.foreach(TraversableLike.scala:732)
at org.apache.spark.executor.Executor.org$apache$spark$executor$Executor$$updateDependencies(Executor.scala:688)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:308)
... 3 more
Caused by: io.netty.channel.AbstractChannel$AnnotatedConnectException: Operation timed out: /IP_ADDRESS: PORT
at sun.nio.ch.SocketChannelImpl.checkConnect(Native Method)
at sun.nio.ch.SocketChannelImpl.finishConnect(SocketChannelImpl.java:717)
at io.netty.channel.socket.nio.NioSocketChannel.doFinishConnect(NioSocketChannel.java:257)
at io.netty.channel.nio.AbstractNioChannel$AbstractNioUnsafe.finishConnect(AbstractNioChannel.java:291)
at io.netty.channel.nio.NioEventLoop.processSelectedKey(NioEventLoop.java:631)
at io.netty.channel.nio.NioEventLoop.processSelectedKeysOptimized(NioEventLoop.java:566)
at io.netty.channel.nio.NioEventLoop.processSelectedKeys(NioEventLoop.java:480)
at io.netty.channel.nio.NioEventLoop.run(NioEventLoop.java:442)
at io.netty.util.concurrent.SingleThreadEventExecutor$2.run(SingleThreadEventExecutor.java:131)
at io.netty.util.concurrent.DefaultThreadFactory$DefaultRunnableDecorator.run(DefaultThreadFactory.java:144)
... 1 more

Sparkling water local mode cluster error

I'm trying to extend the hamorspam example(https://github.com/h2oai/sparkling-water/blob/master/examples/scripts/hamOrSpam.script.scala
) to make parallel predictions for large dataset using spark's parallel computation power(during the inference stage, not the training phase).
Below is the code I have written for the same. Moreover, it perfectly works fine in single node localmode (for export MASTER="local[*] ``), but fails when I run with export MASTER="local-cluster[2,2,1024] when 2 worker nodes are spawn.(to check the prediction parallelisation)
val data_test = load("smsData.txt") // Should be a large(in GBs) test dataset - using same training data for testing purposes just to test the workflow
val message_test = data.map( r => r(1))
message.take(1000).map(x => isSpam(x, dlModel, hashingTF, idfModel, h2oContext))
So the code fails when executing scala> val table:H2OFrame = resultRDD (
https://github.com/h2oai/sparkling-water/blob/master/examples/scripts/hamOrSpam.script.scala#L110)
I have attached the error from the console below:
17/06/26 20:25:49 WARN TaskSetManager: Lost task 0.0 in stage 6.0 (TID 43, 144.27.27.98, executor 1): java.lang.NoClassDefFoundError: Could not ini
tialize class $line32.$read$
at $line41.$read$$iw$$iw$$iw$$iw$$iw$$iw$$iw$$iw$$iw$$iw$$iw$$iw$$iw$$iw$$iw$$iw$$anonfun$1.apply(<console>:57)
at $line41.$read$$iw$$iw$$iw$$iw$$iw$$iw$$iw$$iw$$iw$$iw$$iw$$iw$$iw$$iw$$iw$$iw$$anonfun$1.apply(<console>:57)
at scala.collection.Iterator$$anon$11.next(Iterator.scala:409)
at scala.collection.Iterator$$anon$11.next(Iterator.scala:409)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIterator.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenExec$$anonfun$8$$anon$1.hasNext(WholeStageCodegenExec.scala:377)
at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:408)
at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:408)
at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:408)
at org.apache.spark.rdd.RDD$$anonfun$reduce$1$$anonfun$15.apply(RDD.scala:1010)
at org.apache.spark.rdd.RDD$$anonfun$reduce$1$$anonfun$15.apply(RDD.scala:1009)
at org.apache.spark.SparkContext$$anonfun$33.apply(SparkContext.scala:1980)
at org.apache.spark.SparkContext$$anonfun$33.apply(SparkContext.scala:1980)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:87)
at org.apache.spark.scheduler.Task.run(Task.scala:99)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:282)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)
at java.lang.Thread.run(Thread.java:748)
17/06/26 20:25:49 ERROR TaskSetManager: Task 0 in stage 6.0 failed 4 times; aborting job
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 6.0 failed 4 times, most recent failure: Lost task 0.3 in stage
6.0 (TID 49, 144.27.27.98, executor 0): java.lang.NoClassDefFoundError: Could not initialize class
at $anonfun$1.apply(<console>:57)
at $anonfun$1.apply(<console>:57)
at scala.collection.Iterator$$anon$11.next(Iterator.scala:409)
at scala.collection.Iterator$$anon$11.next(Iterator.scala:409)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIterator.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenExec$$anonfun$8$$anon$1.hasNext(WholeStageCodegenExec.scala:377)
at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:408)
at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:408)
at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:408)
at org.apache.spark.rdd.RDD$$anonfun$reduce$1$$anonfun$15.apply(RDD.scala:1010)
at org.apache.spark.rdd.RDD$$anonfun$reduce$1$$anonfun$15.apply(RDD.scala:1009)
at org.apache.spark.SparkContext$$anonfun$33.apply(SparkContext.scala:1980)
at org.apache.spark.SparkContext$$anonfun$33.apply(SparkContext.scala:1980)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:87)
at org.apache.spark.scheduler.Task.run(Task.scala:99)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:282)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)
at java.lang.Thread.run(Thread.java:748)
Driver stacktrace:
at org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$failJobAndIndependentStages(DAGScheduler.scala:1435)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1423)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1422)
at scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:48)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1422)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:802)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:802)
at scala.Option.foreach(Option.scala:257)
at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:802)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:1650)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1605)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1594)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:48)
at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:628)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:1918)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:1981)
at org.apache.spark.rdd.RDD$$anonfun$reduce$1.apply(RDD.scala:1025)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:112)
at org.apache.spark.rdd.RDD.withScope(RDD.scala:362)
at org.apache.spark.rdd.RDD.reduce(RDD.scala:1007)
at org.apache.spark.h2o.utils.H2OSchemaUtils$.collectMaxArrays(H2OSchemaUtils.scala:229)
at org.apache.spark.h2o.utils.H2OSchemaUtils$.expandedSchema(H2OSchemaUtils.scala:107)
at org.apache.spark.h2o.converters.SparkDataFrameConverter$.toH2OFrame(SparkDataFrameConverter.scala:59)
at org.apache.spark.h2o.H2OContext.asH2OFrame(H2OContext.scala:167)
at org.apache.spark.h2o.H2OContextImplicits.asH2OFrameFromDataFrame(H2OContextImplicits.scala:54)
... 58 elided
Caused by: java.lang.NoClassDefFoundError: Could not initialize class
at $anonfun$1.apply(<console>:57)
at $anonfun$1.apply(<console>:57)
at scala.collection.Iterator$$anon$11.next(Iterator.scala:409)
at scala.collection.Iterator$$anon$11.next(Iterator.scala:409)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIterator.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenExec$$anonfun$8$$anon$1.hasNext(WholeStageCodegenExec.scala:377)
at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:408)
at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:408)
at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:408)
at org.apache.spark.rdd.RDD$$anonfun$reduce$1$$anonfun$15.apply(RDD.scala:1010)
at org.apache.spark.rdd.RDD$$anonfun$reduce$1$$anonfun$15.apply(RDD.scala:1009)
at org.apache.spark.SparkContext$$anonfun$33.apply(SparkContext.scala:1980)
at org.apache.spark.SparkContext$$anonfun$33.apply(SparkContext.scala:1980)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:87)
at org.apache.spark.scheduler.Task.run(Task.scala:99)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:282)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)
at java.lang.Thread.run(Thread.java:748)
Any ideas?. Thanks in advance.

Read non empty multiple files in Spark

I use sc.textFile() to read multiple files from S3 in Spark. But, the input S3 path also has a few empty files that give NullPointerException. Is there a way that I can ignore these files?
val inputFile = sc.textfile("s3n://mypath/*file")
val inputRDD = inputFile.map(_.split(",")).map(line => {
//processing
})
Edit: Adding stack trace
Exception in thread "main" org.apache.spark.SparkException: Job aborted due to stage failure: Task 128 in stage 0.0 failed 1 times, most recent failure: Lost task 128.0 in stage 0.0 (TID 128, localhost): java.lang.NullPointerException
at org.apache.hadoop.fs.s3native.NativeS3FileSystem$NativeS3FsInputStream.read(NativeS3FileSystem.java:130)
at java.io.BufferedInputStream.read1(BufferedInputStream.java:284)
at java.io.BufferedInputStream.read(BufferedInputStream.java:345)
at java.io.DataInputStream.read(DataInputStream.java:100)
at org.apache.hadoop.util.LineReader.fillBuffer(LineReader.java:180)
at org.apache.hadoop.util.LineReader.readDefaultLine(LineReader.java:216)
at org.apache.hadoop.util.LineReader.readLine(LineReader.java:174)
at org.apache.hadoop.mapred.LineRecordReader.next(LineRecordReader.java:209)
at org.apache.hadoop.mapred.LineRecordReader.next(LineRecordReader.java:47)
at org.apache.spark.rdd.HadoopRDD$$anon$1.getNext(HadoopRDD.scala:248)
at org.apache.spark.rdd.HadoopRDD$$anon$1.getNext(HadoopRDD.scala:216)
at org.apache.spark.util.NextIterator.hasNext(NextIterator.scala:73)
at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:39)
at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:327)
at scala.collection.Iterator$$anon$14.hasNext(Iterator.scala:388)
at scala.collection.Iterator$class.foreach(Iterator.scala:727)
at scala.collection.AbstractIterator.foreach(Iterator.scala:1157)
at org.apache.spark.rdd.RDD$$anonfun$foreach$1$$anonfun$apply$28.apply(RDD.scala:894)
at org.apache.spark.rdd.RDD$$anonfun$foreach$1$$anonfun$apply$28.apply(RDD.scala:894)
at org.apache.spark.SparkContext$$anonfun$runJob$5.apply(SparkContext.scala:1850)
at org.apache.spark.SparkContext$$anonfun$runJob$5.apply(SparkContext.scala:1850)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:66)
at org.apache.spark.scheduler.Task.run(Task.scala:88)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:214)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)
at java.lang.Thread.run(Thread.java:745)

Spark Code works for 1000 document but as it is increased to 1200 or more it fails with None.get?

I am developing a application, where i have to read multiple files from HDFS and then process them and save the result in the Cassandra Table.
This is my pseudo code !
val files = sc.wholeTextFiles(s"hdfs://$ipaddress:9000/xhtml/2016/09/*").map(_._1).take(1000)
val fileNameRDD = sc.parallelize(files)
Here i am extracting the path of 1000 documents and then pass into a function that takes path, reads the document , perform the operation and return a case class.
Hence this function is like :
def doSomething(path:String):Foo={...}
What my biggest concern is the code works fine for 1000 documents ! But as soon as I increase it to 1200 or 1500 it fails with the following exception:
[Stage 2:=============================> (6 + 6) / 12]16/12/06 11:09:48 WARN TaskSetManager: Lost task 10.0 in stage 2.0 (TID 12, 10.178.149.243): java.io.IOException: Failed to write statements to elsevier.rnf.
at com.datastax.spark.connector.writer.TableWriter$$anonfun$write$1.apply(TableWriter.scala:167)
at com.datastax.spark.connector.writer.TableWriter$$anonfun$write$1.apply(TableWriter.scala:135)
at com.datastax.spark.connector.cql.CassandraConnector$$anonfun$withSessionDo$1.apply(CassandraConnector.scala:111)
at com.datastax.spark.connector.cql.CassandraConnector$$anonfun$withSessionDo$1.apply(CassandraConnector.scala:110)
at com.datastax.spark.connector.cql.CassandraConnector.closeResourceAfterUse(CassandraConnector.scala:140)
at com.datastax.spark.connector.cql.CassandraConnector.withSessionDo(CassandraConnector.scala:110)
at com.datastax.spark.connector.writer.TableWriter.write(TableWriter.scala:135)
at com.datastax.spark.connector.RDDFunctions$$anonfun$saveToCassandra$1.apply(RDDFunctions.scala:37)
at com.datastax.spark.connector.RDDFunctions$$anonfun$saveToCassandra$1.apply(RDDFunctions.scala:37)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:70)
at org.apache.spark.scheduler.Task.run(Task.scala:85)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:274)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)
at java.lang.Thread.run(Thread.java:745)
16/12/06 11:09:48 WARN TaskSetManager: Lost task 10.1 in stage 2.0 (TID 14, 10.178.149.243): java.util.NoSuchElementException: None.get
at scala.None$.get(Option.scala:347)
at scala.None$.get(Option.scala:345)
at org.apache.spark.storage.BlockInfoManager.releaseAllLocksForTask(BlockInfoManager.scala:343)
at org.apache.spark.storage.BlockManager.releaseAllLocksForTask(BlockManager.scala:644)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:281)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)
at java.lang.Thread.run(Thread.java:745)
16/12/06 11:09:48 ERROR TaskSetManager: Task 10 in stage 2.0 failed 4 times; aborting job
Exception in thread "main" org.apache.spark.SparkException: Job aborted due to stage failure: Task 10 in stage 2.0 failed 4 times, most recent failure: Lost task 10.3 in stage 2.0 (TID 16, 10.178.149.243): java.util.NoSuchElementException: None.get
at scala.None$.get(Option.scala:347)
at scala.None$.get(Option.scala:345)
at org.apache.spark.storage.BlockInfoManager.releaseAllLocksForTask(BlockInfoManager.scala:343)
at org.apache.spark.storage.BlockManager.releaseAllLocksForTask(BlockManager.scala:644)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:281)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)
at java.lang.Thread.run(Thread.java:745)
Driver stacktrace:
at org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$failJobAndIndependentStages(DAGScheduler.scala:1450)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1438)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1437)
at scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:48)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1437)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:811)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:811)
at scala.Option.foreach(Option.scala:257)
at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:811)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:1659)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1618)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1607)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:48)
at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:632)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:1871)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:1884)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:1904)
at com.datastax.spark.connector.RDDFunctions.saveToCassandra(RDDFunctions.scala:37)
at com.knoldus.xml.RNF2Driver$.main(RNFIngestPipeline.scala:38)
at com.knoldus.xml.RNF2Driver.main(RNFIngestPipeline.scala)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:498)
at org.apache.spark.deploy.SparkSubmit$.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:729)
at org.apache.spark.deploy.SparkSubmit$.doRunMain$1(SparkSubmit.scala:185)
at org.apache.spark.deploy.SparkSubmit$.submit(SparkSubmit.scala:210)
at org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:124)
at org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
Caused by: java.util.NoSuchElementException: None.get
at scala.None$.get(Option.scala:347)
at scala.None$.get(Option.scala:345)
at org.apache.spark.storage.BlockInfoManager.releaseAllLocksForTask(BlockInfoManager.scala:343)
at org.apache.spark.storage.BlockManager.releaseAllLocksForTask(BlockManager.scala:644)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:281)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)
at java.lang.Thread.run(Thread.java:745)
16/12/06 11:09:48 ERROR TransportRequestHandler: Error while invoking RpcHandler#receive() for one-way message.
org.apache.spark.SparkException: Could not find CoarseGrainedScheduler.
at org.apache.spark.rpc.netty.Dispatcher.postMessage(Dispatcher.scala:152)
at org.apache.spark.rpc.netty.Dispatcher.postOneWayMessage(Dispatcher.scala:132)
at org.apache.spark.rpc.netty.NettyRpcHandler.receive(NettyRpcEnv.scala:571)
at org.apache.spark.network.server.TransportRequestHandler.processOneWayMessage(TransportRequestHandler.java:179)
at org.apache.spark.network.server.TransportRequestHandler.handle(TransportRequestHandler.java:108)
at org.apache.spark.network.server.TransportChannelHandler.channelRead0(TransportChannelHandler.java:119)
at org.apache.spark.network.server.TransportChannelHandler.channelRead0(TransportChannelHandler.java:51)
at io.netty.channel.SimpleChannelInboundHandler.channelRead(SimpleChannelInboundHandler.java:105)
at io.netty.channel.AbstractChannelHandlerContext.invokeChannelRead(AbstractChannelHandlerContext.java:308)
at io.netty.channel.AbstractChannelHandlerContext.fireChannelRead(AbstractChannelHandlerContext.java:294)
at io.netty.handler.timeout.IdleStateHandler.channelRead(IdleStateHandler.java:266)
at io.netty.channel.AbstractChannelHandlerContext.invokeChannelRead(AbstractChannelHandlerContext.java:308)
at io.netty.channel.AbstractChannelHandlerContext.fireChannelRead(AbstractChannelHandlerContext.java:294)
at io.netty.handler.codec.MessageToMessageDecoder.channelRead(MessageToMessageDecoder.java:103)
at io.netty.channel.AbstractChannelHandlerContext.invokeChannelRead(AbstractChannelHandlerContext.java:308)
at io.netty.channel.AbstractChannelHandlerContext.fireChannelRead(AbstractChannelHandlerContext.java:294)
at org.apache.spark.network.util.TransportFrameDecoder.channelRead(TransportFrameDecoder.java:85)
at io.netty.channel.AbstractChannelHandlerContext.invokeChannelRead(AbstractChannelHandlerContext.java:308)
at io.netty.channel.AbstractChannelHandlerContext.fireChannelRead(AbstractChannelHandlerContext.java:294)
at io.netty.channel.DefaultChannelPipeline.fireChannelRead(DefaultChannelPipeline.java:846)
at io.netty.channel.nio.AbstractNioByteChannel$NioByteUnsafe.read(AbstractNioByteChannel.java:131)
at io.netty.channel.nio.NioEventLoop.processSelectedKey(NioEventLoop.java:511)
at io.netty.channel.nio.NioEventLoop.processSelectedKeysOptimized(NioEventLoop.java:468)
at io.netty.channel.nio.NioEventLoop.processSelectedKeys(NioEventLoop.java:382)
at io.netty.channel.nio.NioEventLoop.run(NioEventLoop.java:354)
at io.netty.util.concurrent.SingleThreadEventExecutor$2.run(SingleThreadEventExecutor.java:111)
at java.lang.Thread.run(Thread.java:745)
When I try to do the Show it displays my document path correctly !
Is there some setting that i am missing ???
I am using Spark 1.6 ! Any help is appreciated !

Spark GraphX : requirement failed: Invalid initial capacity

I am new to Spark, Scala.
I am trying to perform Triangle Counts in this dataset : DataSet
for a hobby project
This is the code I have written so far :
import org.apache.spark.SparkConf
import org.apache.spark.SparkContext
import org.apache.spark.graphx.Edge
import org.apache.spark.graphx.Graph
import org.apache.spark.graphx.Graph.graphToGraphOps
import org.apache.spark.graphx.PartitionStrategy
import org.apache.spark.rdd.RDD
import org.apache.spark.rdd.RDD.rddToPairRDDFunctions
object GraphXApps {
def main(args: Array[String]): Unit = {
val conf = new SparkConf()
.setAppName("GraphXApps")
.setSparkHome(System.getenv("SPARK_HOME"))
.setJars(SparkContext.jarOfClass(this.getClass).toList)
val sc = new SparkContext(conf)
// Load the edges in canonical order and partition the graph for triangle count
val edges: RDD[Edge[String]] =
sc.textFile(args(0)).map { line =>
val fields = line.split("\t")
Edge(fields(0).toLong, fields(1).toLong)
}
val graph : Graph[String, String] = Graph.fromEdges(edges.sortBy(_.srcId, ascending = true, 1), "defaultProperty").partitionBy(PartitionStrategy.RandomVertexCut)
// Find the triangle count for each vertex
val triCounts = graph.triangleCount().vertices
val triCountById = graph.vertices.join(triCounts).map(_._2._2)
// Print the result
println(triCountById.collect().mkString("\n"))
sc.stop()
}
}
But I am getting this error : java.lang.IllegalArgumentException: requirement failed: Invalid initial capacity
Please let me know where I am going wrong. It would be really helpful.
Full Stack Trace
16/10/31 01:03:08 ERROR TaskSetManager: Task 0 in stage 8.0 failed 1 times; aborting job
16/10/31 01:03:08 INFO TaskSchedulerImpl: Removed TaskSet 8.0, whose tasks have all completed, from pool
16/10/31 01:03:08 INFO TaskSchedulerImpl: Cancelling stage 8
16/10/31 01:03:08 INFO DAGScheduler: ShuffleMapStage 8 (mapPartitions at VertexRDDImpl.scala:245) failed in 0.131 s
16/10/31 01:03:08 INFO DAGScheduler: Job 0 failed: collect at GraphXApps.scala:47, took 3.128921 s
Exception in thread "main" org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 8.0 failed 1 times, most recent failure: Lost task 0.0 in stage 8.0 (TID 8, localhost): java.lang.IllegalArgumentException: requirement failed: Invalid initial capacity
at scala.Predef$.require(Predef.scala:224)
at org.apache.spark.util.collection.OpenHashSet$mcJ$sp.<init>(OpenHashSet.scala:51)
at org.apache.spark.util.collection.OpenHashSet$mcJ$sp.<init>(OpenHashSet.scala:57)
at org.apache.spark.graphx.lib.TriangleCount$$anonfun$5.apply(TriangleCount.scala:70)
at org.apache.spark.graphx.lib.TriangleCount$$anonfun$5.apply(TriangleCount.scala:69)
at org.apache.spark.graphx.impl.VertexPartitionBaseOps.map(VertexPartitionBaseOps.scala:61)
at org.apache.spark.graphx.impl.VertexRDDImpl$$anonfun$mapValues$2.apply(VertexRDDImpl.scala:102)
at org.apache.spark.graphx.impl.VertexRDDImpl$$anonfun$mapValues$2.apply(VertexRDDImpl.scala:102)
at scala.collection.Iterator$$anon$11.next(Iterator.scala:409)
at org.apache.spark.graphx.impl.VertexRDDImpl$$anonfun$3.apply(VertexRDDImpl.scala:156)
at org.apache.spark.graphx.impl.VertexRDDImpl$$anonfun$3.apply(VertexRDDImpl.scala:154)
at org.apache.spark.rdd.ZippedPartitionsRDD2.compute(ZippedPartitionsRDD.scala:89)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:319)
at org.apache.spark.rdd.RDD$$anonfun$8.apply(RDD.scala:332)
at org.apache.spark.rdd.RDD$$anonfun$8.apply(RDD.scala:330)
at org.apache.spark.storage.BlockManager$$anonfun$doPutIterator$1.apply(BlockManager.scala:919)
at org.apache.spark.storage.BlockManager$$anonfun$doPutIterator$1.apply(BlockManager.scala:910)
at org.apache.spark.storage.BlockManager.doPut(BlockManager.scala:866)
at org.apache.spark.storage.BlockManager.doPutIterator(BlockManager.scala:910)
at org.apache.spark.storage.BlockManager.getOrElseUpdate(BlockManager.scala:668)
at org.apache.spark.rdd.RDD.getOrCompute(RDD.scala:330)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:281)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:319)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:283)
at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:79)
at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:47)
at org.apache.spark.scheduler.Task.run(Task.scala:85)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:274)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)
at java.lang.Thread.run(Thread.java:745)
Driver stacktrace:
at org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$failJobAndIndependentStages(DAGScheduler.scala:1450)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1438)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1437)
at scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:48)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1437)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:811)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:811)
at scala.Option.foreach(Option.scala:257)
at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:811)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:1659)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1618)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1607)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:48)
at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:632)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:1871)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:1884)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:1897)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:1911)
at org.apache.spark.rdd.RDD$$anonfun$collect$1.apply(RDD.scala:893)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:112)
at org.apache.spark.rdd.RDD.withScope(RDD.scala:358)
at org.apache.spark.rdd.RDD.collect(RDD.scala:892)
at GraphXApps$.main(GraphXApps.scala:47)
at GraphXApps.main(GraphXApps.scala)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:498)
at org.apache.spark.deploy.SparkSubmit$.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:729)
at org.apache.spark.deploy.SparkSubmit$.doRunMain$1(SparkSubmit.scala:185)
at org.apache.spark.deploy.SparkSubmit$.submit(SparkSubmit.scala:210)
at org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:124)
at org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
Caused by: java.lang.IllegalArgumentException: requirement failed: Invalid initial capacity
at scala.Predef$.require(Predef.scala:224)
at org.apache.spark.util.collection.OpenHashSet$mcJ$sp.<init>(OpenHashSet.scala:51)
at org.apache.spark.util.collection.OpenHashSet$mcJ$sp.<init>(OpenHashSet.scala:57)
at org.apache.spark.graphx.lib.TriangleCount$$anonfun$5.apply(TriangleCount.scala:70)
at org.apache.spark.graphx.lib.TriangleCount$$anonfun$5.apply(TriangleCount.scala:69)
at org.apache.spark.graphx.impl.VertexPartitionBaseOps.map(VertexPartitionBaseOps.scala:61)
at org.apache.spark.graphx.impl.VertexRDDImpl$$anonfun$mapValues$2.apply(VertexRDDImpl.scala:102)
at org.apache.spark.graphx.impl.VertexRDDImpl$$anonfun$mapValues$2.apply(VertexRDDImpl.scala:102)
at scala.collection.Iterator$$anon$11.next(Iterator.scala:409)
at org.apache.spark.graphx.impl.VertexRDDImpl$$anonfun$3.apply(VertexRDDImpl.scala:156)
at org.apache.spark.graphx.impl.VertexRDDImpl$$anonfun$3.apply(VertexRDDImpl.scala:154)
at org.apache.spark.rdd.ZippedPartitionsRDD2.compute(ZippedPartitionsRDD.scala:89)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:319)
at org.apache.spark.rdd.RDD$$anonfun$8.apply(RDD.scala:332)
at org.apache.spark.rdd.RDD$$anonfun$8.apply(RDD.scala:330)
at org.apache.spark.storage.BlockManager$$anonfun$doPutIterator$1.apply(BlockManager.scala:919)
at org.apache.spark.storage.BlockManager$$anonfun$doPutIterator$1.apply(BlockManager.scala:910)
at org.apache.spark.storage.BlockManager.doPut(BlockManager.scala:866)
at org.apache.spark.storage.BlockManager.doPutIterator(BlockManager.scala:910)
at org.apache.spark.storage.BlockManager.getOrElseUpdate(BlockManager.scala:668)
at org.apache.spark.rdd.RDD.getOrCompute(RDD.scala:330)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:281)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:319)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:283)
at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:79)
at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:47)
at org.apache.spark.scheduler.Task.run(Task.scala:85)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:274)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)
at java.lang.Thread.run(Thread.java:745)
This appears to be a bug within Spark 2.0 (so far, have tested this against 2.0, 2.0.1, and 2.0.2). Jira [SPARK-18200]: GraphX Invalid initial capacity when running triangleCount has been created to address this.
Your code should work okay with Spark 1.6 as noted in this linked notebook.
But as you noted, it failed in Spark 2.0, as noted in this linked notebook.
In the interim, please try Spark 1.6 or try using GraphFrames, as noted in this linked notebook.
HTH!