org.apache.spark.SparkException: Job aborted due to stage failure: Task 21.0:0 failed 4 times, most recent failure: Exception failure in TID 34 on host krbda1anode01.kr.test.com: scala.MatchError: 2.0 (of class java.lang.Double) org.apache.spark.mllib.tree.DecisionTree$.classificationBinSeqOp$1(DecisionTree.scala:568) org.apache.spark.mllib.tree.DecisionTree$.org$apache$spark$mllib$tree$DecisionTree$$binSeqOp$1(DecisionTree.scala:623) org.apache.spark.mllib.tree.DecisionTree$$anonfun$4.apply(DecisionTree.scala:657) org.apache.spark.mllib.tree.DecisionTree$$anonfun$4.apply(DecisionTree.scala:657) scala.collection.TraversableOnce$$anonfun$foldLeft$1.apply(TraversableOnce.scala:144) scala.collection.TraversableOnce$$anonfun$foldLeft$1.apply(TraversableOnce.scala:144) scala.collection.Iterator$class.foreach(Iterator.scala:727) scala.collection.AbstractIterator.foreach(Iterator.scala:1157) scala.collection.TraversableOnce$class.foldLeft(TraversableOnce.scala:144) scala.collection.AbstractIterator.foldLeft(Iterator.scala:1157) scala.collection.TraversableOnce$class.aggregate(TraversableOnce.scala:201) scala.collection.AbstractIterator.aggregate(Iterator.scala:1157) org.apache.spark.rdd.RDD$$anonfun$21.apply(RDD.scala:838) org.apache.spark.rdd.RDD$$anonfun$21.apply(RDD.scala:838) org.apache.spark.SparkContext$$anonfun$23.apply(SparkContext.scala:1116) org.apache.spark.SparkContext$$anonfun$23.apply(SparkContext.scala:1116) org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:111) org.apache.spark.scheduler.Task.run(Task.scala:51) org.apache.spark.executor.Executor$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:

spark-user | jake Lim | 2 years ago
tip
Your exception is missing from the Samebug knowledge base.
Here are the best solutions we found on the Internet.
Click on the to mark the helpful solution and get rewards for you help.
  1. 0

    Q about Spark MLlib- Decision tree - scala.MatchError: 2.0 (of class java.lang.Double)

    spark-user | 2 years ago | jake Lim
    org.apache.spark.SparkException: Job aborted due to stage failure: Task 21.0:0 failed 4 times, most recent failure: Exception failure in TID 34 on host krbda1anode01.kr.test.com: scala.MatchError: 2.0 (of class java.lang.Double) org.apache.spark.mllib.tree.DecisionTree$.classificationBinSeqOp$1(DecisionTree.scala:568) org.apache.spark.mllib.tree.DecisionTree$.org$apache$spark$mllib$tree$DecisionTree$$binSeqOp$1(DecisionTree.scala:623) org.apache.spark.mllib.tree.DecisionTree$$anonfun$4.apply(DecisionTree.scala:657) org.apache.spark.mllib.tree.DecisionTree$$anonfun$4.apply(DecisionTree.scala:657) scala.collection.TraversableOnce$$anonfun$foldLeft$1.apply(TraversableOnce.scala:144) scala.collection.TraversableOnce$$anonfun$foldLeft$1.apply(TraversableOnce.scala:144) scala.collection.Iterator$class.foreach(Iterator.scala:727) scala.collection.AbstractIterator.foreach(Iterator.scala:1157) scala.collection.TraversableOnce$class.foldLeft(TraversableOnce.scala:144) scala.collection.AbstractIterator.foldLeft(Iterator.scala:1157) scala.collection.TraversableOnce$class.aggregate(TraversableOnce.scala:201) scala.collection.AbstractIterator.aggregate(Iterator.scala:1157) org.apache.spark.rdd.RDD$$anonfun$21.apply(RDD.scala:838) org.apache.spark.rdd.RDD$$anonfun$21.apply(RDD.scala:838) org.apache.spark.SparkContext$$anonfun$23.apply(SparkContext.scala:1116) org.apache.spark.SparkContext$$anonfun$23.apply(SparkContext.scala:1116) org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:111) org.apache.spark.scheduler.Task.run(Task.scala:51) org.apache.spark.executor.Executor$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:
  2. 0

    How to use foreach (each record add to solr) in foreachRDD to spark streaming?

    Stack Overflow | 2 years ago | user1976546
    org.apache.spark.SparkException: Job aborted due to stage failure: All masters are unresponsive! Giving up.
  3. 0

    Apache Spark: A Task failed with java.lang.ArrayIndexOutOfBoundsException at com.ning.compress.lzf.impl.UnsafeChunkDecoder.copyOverlappingLong

    Stack Overflow | 3 years ago | zeodtr
    org.apache.spark.SparkException: Job aborted due to stage failure: Task 0.0:359 failed 4 times, most recent failure: Exception failure in TID 1622 on host cluster02: java.lang.ArrayIndexOutOfBoundsException: 65535 com.ning.compress.lzf.impl.UnsafeChunkDecoder.copyOverlappingLong(UnsafeChunkDecoder.java:221) com.ning.compress.lzf.impl.UnsafeChunkDecoder.decodeChunk(UnsafeChunkDecoder.java:117) com.ning.compress.lzf.impl.UnsafeChunkDecoder.decodeChunk(UnsafeChunkDecoder.java:66) com.ning.compress.lzf.LZFInputStream.readyBuffer(LZFInputStream.java:339) com.ning.compress.lzf.LZFInputStream.read(LZFInputStream.java:169) java.io.ObjectInputStream$PeekInputStream.read(ObjectInputStream.java:2310) java.io.ObjectInputStream$PeekInputStream.readFully(ObjectInputStream.java:2323) java.io.ObjectInputStream$BlockDataInputStream.readUTFBody(ObjectInputStream.java:3063) java.io.ObjectInputStream$BlockDataInputStream.readUTF(ObjectInputStream.java:2864) java.io.ObjectInputStream.readString(ObjectInputStream.java:1638) java.io.ObjectInputStream.readObject0(ObjectInputStream.java:1341) java.io.ObjectInputStream.defaultReadFields(ObjectInputStream.java:1990) java.io.ObjectInputStream.readSerialData(ObjectInputStream.java:1915) java.io.ObjectInputStream.readOrdinaryObject(ObjectInputStream.java:1798) java.io.ObjectInputStream.readObject0(ObjectInputStream.java:1350) java.io.ObjectInputStream.readObject(ObjectInputStream.java:370) org.apache.spark.serializer.JavaDeserializationStream.readObject(JavaSerializer.scala:63) org.apache.spark.serializer.DeserializationStream$$anon$1.getNext(Serializer.scala:125) org.apache.spark.util.NextIterator.hasNext(NextIterator.scala:71) scala.collection.Iterator$$anon$13.hasNext(Iterator.scala:371) org.apache.spark.util.CompletionIterator.hasNext(CompletionIterator.scala:30) org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:39) org.apache.spark.Aggregator.combineValuesByKey(Aggregator.scala:58) org.apache.spark.rdd.PairRDDFunctions$$anonfun$combineByKey$4.apply(PairRDDFunctions.scala:107) org.apache.spark.rdd.PairRDDFunctions$$anonfun$combineByKey$4.apply(PairRDDFunctions.scala:106) org.apache.spark.rdd.RDD$$anonfun$14.apply(RDD.scala:582) org.apache.spark.rdd.RDD$$anonfun$14.apply(RDD.scala:582) org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:35) org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:262) org.apache.spark.rdd.RDD.iterator(RDD.scala:229) org.apache.spark.rdd.MappedValuesRDD.compute(MappedValuesRDD.scala:31) org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:262) org.apache.spark.rdd.RDD.iterator(RDD.scala:229) org.apache.spark.rdd.MappedValuesRDD.compute(MappedValuesRDD.scala:31) org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:262) org.apache.spark.rdd.RDD.iterator(RDD.scala:229) org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:111) org.apache.spark.scheduler.Task.run(Task.scala:51) org.apache.spark.executor.Executor$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:744) Driver stacktrace:
  4. Speed up your debug routine!

    Automated exception search integrated into your IDE

  5. 0

    SparkException: Job aborted due to stage failure

    Stack Overflow | 3 years ago | manjunath k
    org.apache.spark.SparkException: Job aborted due to stage failure: Master removed our application: FAILED
  6. 0

    simple mapping partitions job in (py)spark

    Stack Overflow | 3 years ago | lollercoaster
    org.apache.spark.SparkException: Job aborted due to stage failure: Task 2.0:0 failed 1 times, most recent failure: Exception failure in TID 0 on host localhost: org.apache.spark.api.python.PythonException: Traceback (most recent call last): File "/usr/bin/spark-1.0.0-bin-hadoop2/python/pyspark/worker.py", line 77, in main serializer.dump_stream(func(split_index, iterator), outfile) File "/usr/bin/spark-1.0.0-bin-hadoop2/python/pyspark/serializers.py", line 191, in dump_stream self.serializer.dump_stream(self._batched(iterator), stream) File "/usr/bin/spark-1.0.0-bin-hadoop2/python/pyspark/serializers.py", line 123, in dump_stream for obj in iterator: File "/usr/bin/spark-1.0.0-bin-hadoop2/python/pyspark/serializers.py", line 180, in _batched for item in iterator: TypeError: 'NoneType' object is not iterable org.apache.spark.api.python.PythonRDD$$anon$1.read(PythonRDD.scala:115) org.apache.spark.api.python.PythonRDD$$anon$1.<init>(PythonRDD.scala:145) org.apache.spark.api.python.PythonRDD.compute(PythonRDD.scala:78) org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:262) org.apache.spark.rdd.RDD.iterator(RDD.scala:229) org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:111) org.apache.spark.scheduler.Task.run(Task.scala:51) org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:187) java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142) java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617) java.lang.Thread.run(Thread.java:745) Driver stacktrace:

  1. johnxfly 1 times, last 4 days ago
  2. tyson925 3 times, last 1 month ago
  3. Nikolay Rybak 1 times, last 2 months ago
  4. meneal 1 times, last 8 months ago
20 unregistered visitors
Not finding the right solution?
Take a tour to get the most out of Samebug.

Tired of useless tips?

Automated exception search integrated into your IDE

Root Cause Analysis

  1. org.apache.spark.SparkException

    Job aborted due to stage failure: Task 21.0:0 failed 4 times, most recent failure: Exception failure in TID 34 on host krbda1anode01.kr.test.com: scala.MatchError: 2.0 (of class java.lang.Double) org.apache.spark.mllib.tree.DecisionTree$.classificationBinSeqOp$1(DecisionTree.scala:568) org.apache.spark.mllib.tree.DecisionTree$.org$apache$spark$mllib$tree$DecisionTree$$binSeqOp$1(DecisionTree.scala:623) org.apache.spark.mllib.tree.DecisionTree$$anonfun$4.apply(DecisionTree.scala:657) org.apache.spark.mllib.tree.DecisionTree$$anonfun$4.apply(DecisionTree.scala:657) scala.collection.TraversableOnce$$anonfun$foldLeft$1.apply(TraversableOnce.scala:144) scala.collection.TraversableOnce$$anonfun$foldLeft$1.apply(TraversableOnce.scala:144) scala.collection.Iterator$class.foreach(Iterator.scala:727) scala.collection.AbstractIterator.foreach(Iterator.scala:1157) scala.collection.TraversableOnce$class.foldLeft(TraversableOnce.scala:144) scala.collection.AbstractIterator.foldLeft(Iterator.scala:1157) scala.collection.TraversableOnce$class.aggregate(TraversableOnce.scala:201) scala.collection.AbstractIterator.aggregate(Iterator.scala:1157) org.apache.spark.rdd.RDD$$anonfun$21.apply(RDD.scala:838) org.apache.spark.rdd.RDD$$anonfun$21.apply(RDD.scala:838) org.apache.spark.SparkContext$$anonfun$23.apply(SparkContext.scala:1116) org.apache.spark.SparkContext$$anonfun$23.apply(SparkContext.scala:1116) org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:111) org.apache.spark.scheduler.Task.run(Task.scala:51) org.apache.spark.executor.Executor$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$$failJobAndIndependentStages()
  2. Spark
    DAGScheduler$$anonfun$abortStage$1.apply
    1. org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$failJobAndIndependentStages(DAGScheduler.scala:1033)
    2. org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1017)
    3. org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1015)
    3 frames
  3. Scala
    ArrayBuffer.foreach
    1. scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
    2. scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:47)
    2 frames
  4. Spark
    DAGScheduler$$anonfun$handleTaskSetFailed$1.apply
    1. org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1015)
    2. org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:633)
    3. org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:633)
    3 frames
  5. Scala
    Option.foreach
    1. scala.Option.foreach(Option.scala:236)
    1 frame
  6. Spark
    DAGSchedulerEventProcessActor$$anonfun$receive$2.applyOrElse
    1. org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:633)
    2. org.apache.spark.scheduler.DAGSchedulerEventProcessActor$$anonfun$receive$2.applyOrElse(DAGScheduler.scala:1207)
    2 frames
  7. Akka Actor
    ForkJoinExecutorConfigurator$AkkaForkJoinTask.exec
    1. akka.actor.ActorCell.receiveMessage(ActorCell.scala:498)
    2. akka.actor.ActorCell.invoke(ActorCell.scala:456)
    3. akka.dispatch.Mailbox.processMailbox(Mailbox.scala:237)
    4. akka.dispatch.Mailbox.run(Mailbox.scala:219)
    5. akka.dispatch.ForkJoinExecutorConfigurator$AkkaForkJoinTask.exec(AbstractDispatcher.scala:386)
    5 frames
  8. Scala
    ForkJoinWorkerThread.run
    1. scala.concurrent.forkjoin.ForkJoinTask.doExec(ForkJoinTask.java:260)
    2. scala.concurrent.forkjoin.ForkJoinPool$WorkQueue.runTask(ForkJoinPool.java:1339)
    3. scala.concurrent.forkjoin.ForkJoinPool.runWorker(ForkJoinPool.java:1979)
    4. scala.concurrent.forkjoin.ForkJoinWorkerThread.run(ForkJoinWorkerThread.java:107)
    4 frames