I'm using the spark-shell locally and working on a dataset of size 900MB. I initially ran into "java.lang.OutOfMemoryError: GC overhead limit exceeded" error and upon researching set "SPARK_DRIVER_MEMORY" to 4g.
Now I run into ArrayIndexOutOfBoundsException, please let me know if there is some way to fix this: ERROR Executor: Exception in task ID 8 java.lang.ArrayIndexOutOfBoundsException: 1 at $line14.$read$$iwC$$iwC$$iwC$$iwC$$anonfun$2.apply(<console>:21) at $line14.$read$$iwC$$iwC$$iwC$$iwC$$anonfun$2.apply(<console>:21) at scala.collection.Iterator$$anon$11.next(Iterator.scala:328) at scala.collection.Iterator$$anon$1.next(Iterator.scala:853) at scala.collection.Iterator$$anon$11.next(Iterator.scala:328) at scala.collection.Iterator$$anon$11.next(Iterator.scala:328) at scala.collection.Iterator$$anon$11.next(Iterator.scala:328) at scala.collection.Iterator$class.foreach(Iterator.scala:727) at scala.collection.AbstractIterator.foreach(Iterator.scala:1157) at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:158) at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:99) at org.apache.spark.scheduler.Task.run(Task.scala:51) at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:187) at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145) at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615) at java.lang.Thread.run(Thread.java:745) 14/07/23 01:39:12 ERROR Executor: Exception in task ID 2 java.lang.ArrayIndexOutOfBoundsException: 3 at $line14.$read$$iwC$$iwC$$iwC$$iwC$$anonfun$2.apply(<console>:21) at $line14.$read$$iwC$$iwC$$iwC$$iwC$$anonfun$2.apply(<console>:21) at scala.collection.Iterator$$anon$11.next(Iterator.scala:328) at scala.collection.Iterator$$anon$1.next(Iterator.scala:853) at scala.collection.Iterator$$anon$11.next(Iterator.scala:328) at scala.collection.Iterator$$anon$11.next(Iterator.scala:328) at scala.collection.Iterator$$anon$11.next(Iterator.scala:328) at scala.collection.Iterator$class.foreach(Iterator.scala:727) at scala.collection.AbstractIterator.foreach(Iterator.scala:1157) at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:158) at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:99) at org.apache.spark.scheduler.Task.run(Task.scala:51) at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:187) at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145) at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615) at java.lang.Thread.run(Thread.java:745) 14/07/23 01:39:12 WARN TaskSetManager: Lost TID 8 (task 1.0:8) 14/07/23 01:39:12 WARN TaskSetManager: Loss was due to java.lang.ArrayIndexOutOfBoundsException java.lang.ArrayIndexOutOfBoundsException: 1 at $line14.$read$$iwC$$iwC$$iwC$$iwC$$anonfun$2.apply(<console>:21) at $line14.$read$$iwC$$iwC$$iwC$$iwC$$anonfun$2.apply(<console>:21) at scala.collection.Iterator$$anon$11.next(Iterator.scala:328) at scala.collection.Iterator$$anon$1.next(Iterator.scala:853) at scala.collection.Iterator$$anon$11.next(Iterator.scala:328) at scala.collection.Iterator$$anon$11.next(Iterator.scala:328) at scala.collection.Iterator$$anon$11.next(Iterator.scala:328) at scala.collection.Iterator$class.foreach(Iterator.scala:727) at scala.collection.AbstractIterator.foreach(Iterator.scala:1157) at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:158) at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:99) at org.apache.spark.scheduler.Task.run(Task.scala:51) at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:187) at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145) at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615) at java.lang.Thread.run(Thread.java:745) 14/07/23 01:39:12 ERROR TaskSetManager: Task 1.0:8 failed 1 times; aborting job 14/07/23 01:39:12 WARN TaskSetManager: Loss was due to java.lang.ArrayIndexOutOfBoundsException java.lang.ArrayIndexOutOfBoundsException: 3 at $line14.$read$$iwC$$iwC$$iwC$$iwC$$anonfun$2.apply(<console>:21) at $line14.$read$$iwC$$iwC$$iwC$$iwC$$anonfun$2.apply(<console>:21) at scala.collection.Iterator$$anon$11.next(Iterator.scala:328) at scala.collection.Iterator$$anon$1.next(Iterator.scala:853) at scala.collection.Iterator$$anon$11.next(Iterator.scala:328) at scala.collection.Iterator$$anon$11.next(Iterator.scala:328) at scala.collection.Iterator$$anon$11.next(Iterator.scala:328) at scala.collection.Iterator$class.foreach(Iterator.scala:727) at scala.collection.AbstractIterator.foreach(Iterator.scala:1157) at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:158) at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:99) at org.apache.spark.scheduler.Task.run(Task.scala:51) at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:187) at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145) at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615) at java.lang.Thread.run(Thread.java:745) 14/07/23 01:39:12 ERROR Executor: Exception in task ID 9 org.apache.spark.TaskKilledException at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:178) at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145) at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615) at java.lang.Thread.run(Thread.java:745) 14/07/23 01:39:12 WARN TaskSetManager: Loss was due to org.apache.spark.TaskKilledException org.apache.spark.TaskKilledException at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:178) at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145) at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615) at java.lang.Thread.run(Thread.java:745) 14/07/23 01:39:13 ERROR Executor: Exception in task ID 10 org.apache.spark.TaskKilledException at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:178) at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145) at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615) at java.lang.Thread.run(Thread.java:745) 14/07/23 01:39:13 WARN TaskSetManager: Task 1 was killed. 14/07/23 01:39:13 WARN TaskSetManager: Task 6 was killed. 14/07/23 01:39:13 WARN TaskSetManager: Task 0 was killed. 14/07/23 01:39:13 WARN TaskSetManager: Task 3 was killed. 14/07/23 01:39:13 WARN TaskSetManager: Task 4 was killed. 14/07/23 01:39:13 WARN TaskSetManager: Task 7 was killed. org.apache.spark.SparkException: Job aborted due to stage failure: Task 1.0:8 failed 1 times, most recent failure: Exception failure in TID 8 on host localhost: java.lang.ArrayIndexOutOfBoundsException: 1 $iwC$$iwC$$iwC$$iwC$$anonfun$2.apply(<console>:21) $iwC$$iwC$$iwC$$iwC$$anonfun$2.apply(<console>:21) scala.collection.Iterator$$anon$11.next(Iterator.scala:328) scala.collection.Iterator$$anon$1.next(Iterator.scala:853) scala.collection.Iterator$$anon$11.next(Iterator.scala:328) scala.collection.Iterator$$anon$11.next(Iterator.scala:328) scala.collection.Iterator$$anon$11.next(Iterator.scala:328) scala.collection.Iterator$class.foreach(Iterator.scala:727) scala.collection.AbstractIterator.foreach(Iterator.scala:1157) org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:158) org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:99) org.apache.spark.scheduler.Task.run(Task.scala:51) org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:187) java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145) java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615) java.lang.Thread.run(Thread.java:745) Driver stacktrace: at org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$failJobAndIndependentStages(DAGScheduler.scala:1033) at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1017) at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1015) at scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59) at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:47) at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1015) at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:633) at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:633) at scala.Option.foreach(Option.scala:236) at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:633) at org.apache.spark.scheduler.DAGSchedulerEventProcessActor$$anonfun$receive$2.applyOrElse(DAGScheduler.scala:1207) at akka.actor.ActorCell.receiveMessage(ActorCell.scala:498) at akka.actor.ActorCell.invoke(ActorCell.scala:456) at akka.dispatch.Mailbox.processMailbox(Mailbox.scala:237) at akka.dispatch.Mailbox.run(Mailbox.scala:219) at akka.dispatch.ForkJoinExecutorConfigurator$AkkaForkJoinTask.exec(AbstractDispatcher.scala:386) at scala.concurrent.forkjoin.ForkJoinTask.doExec(ForkJoinTask.java:260) at scala.concurrent.forkjoin.ForkJoinPool$WorkQueue.runTask(ForkJoinPool.java:1339) at scala.concurrent.forkjoin.ForkJoinPool.runWorker(ForkJoinPool.java:1979) at scala.concurrent.forkjoin.ForkJoinWorkerThread.run(ForkJoinWorkerThread.java:107) Thanks! -- View this message in context: http://apache-spark-user-list.1001560.n3.nabble.com/spark-shell-running-into-ArrayIndexOutOfBoundsException-tp10480.html Sent from the Apache Spark User List mailing list archive at Nabble.com.