org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 65.0 failed 1 times, most recent failure: Lost task 0.0 in stage 65.0 (TID 2657, localhost): java.lang.IndexOutOfBoundsException: 2

DataStax JIRA | Alex Liu | 2 years ago
tip
Do you know that we can give you better hits? Get more relevant results from Samebug’s stack trace search.
  1. 0

    Test SPARKC-218 on b1.4 fails for the following error {code} INFO 12:19:51,265 org.apache.spark.Logging$class (Logging.scala:59) - filters: INFO 12:19:51,265 org.apache.spark.Logging$class (Logging.scala:59) - pushdown filters: ArrayBuffer() ERROR 12:19:51,315 org.apache.spark.Logging$class (Logging.scala:96) - Exception in task 0.0 in stage 65.0 (TID 2657) java.lang.IndexOutOfBoundsException: 2 at com.datastax.spark.connector.UDTValue.productElement(UDTValue.scala:11) at scala.runtime.ScalaRunTime$$anon$1.next(ScalaRunTime.scala:181) at org.apache.spark.sql.catalyst.CatalystTypeConverters$$anonfun$createToCatalystConverter$4.apply(CatalystTypeConverters.scala:187) at org.apache.spark.sql.execution.RDDConversions$$anonfun$rowToRowRdd$1$$anonfun$apply$2.apply(ExistingRDD.scala:62) at org.apache.spark.sql.execution.RDDConversions$$anonfun$rowToRowRdd$1$$anonfun$apply$2.apply(ExistingRDD.scala:59) 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 scala.collection.generic.Growable$class.$plus$plus$eq(Growable.scala:48) at scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:103) at scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:47) at scala.collection.TraversableOnce$class.to(TraversableOnce.scala:273) at scala.collection.AbstractIterator.to(Iterator.scala:1157) at scala.collection.TraversableOnce$class.toBuffer(TraversableOnce.scala:265) at scala.collection.AbstractIterator.toBuffer(Iterator.scala:1157) at scala.collection.TraversableOnce$class.toArray(TraversableOnce.scala:252) at scala.collection.AbstractIterator.toArray(Iterator.scala:1157) at org.apache.spark.rdd.RDD$$anonfun$collect$1$$anonfun$12.apply(RDD.scala:885) at org.apache.spark.rdd.RDD$$anonfun$collect$1$$anonfun$12.apply(RDD.scala:885) at org.apache.spark.SparkContext$$anonfun$runJob$5.apply(SparkContext.scala:1765) at org.apache.spark.SparkContext$$anonfun$runJob$5.apply(SparkContext.scala:1765) at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:63) at org.apache.spark.scheduler.Task.run(Task.scala:70) at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:213) at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145) at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615) at java.lang.Thread.run(Thread.java:745) WARN 12:19:51,316 org.apache.spark.Logging$class (Logging.scala:71) - Lost task 0.0 in stage 65.0 (TID 2657, localhost): java.lang.IndexOutOfBoundsException: 2 at com.datastax.spark.connector.UDTValue.productElement(UDTValue.scala:11) at scala.runtime.ScalaRunTime$$anon$1.next(ScalaRunTime.scala:181) at org.apache.spark.sql.catalyst.CatalystTypeConverters$$anonfun$createToCatalystConverter$4.apply(CatalystTypeConverters.scala:187) at org.apache.spark.sql.execution.RDDConversions$$anonfun$rowToRowRdd$1$$anonfun$apply$2.apply(ExistingRDD.scala:62) at org.apache.spark.sql.execution.RDDConversions$$anonfun$rowToRowRdd$1$$anonfun$apply$2.apply(ExistingRDD.scala:59) 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 scala.collection.generic.Growable$class.$plus$plus$eq(Growable.scala:48) at scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:103) at scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:47) at scala.collection.TraversableOnce$class.to(TraversableOnce.scala:273) at scala.collection.AbstractIterator.to(Iterator.scala:1157) at scala.collection.TraversableOnce$class.toBuffer(TraversableOnce.scala:265) at scala.collection.AbstractIterator.toBuffer(Iterator.scala:1157) at scala.collection.TraversableOnce$class.toArray(TraversableOnce.scala:252) at scala.collection.AbstractIterator.toArray(Iterator.scala:1157) at org.apache.spark.rdd.RDD$$anonfun$collect$1$$anonfun$12.apply(RDD.scala:885) at org.apache.spark.rdd.RDD$$anonfun$collect$1$$anonfun$12.apply(RDD.scala:885) at org.apache.spark.SparkContext$$anonfun$runJob$5.apply(SparkContext.scala:1765) at org.apache.spark.SparkContext$$anonfun$runJob$5.apply(SparkContext.scala:1765) at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:63) at org.apache.spark.scheduler.Task.run(Task.scala:70) at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:213) at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145) at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615) at java.lang.Thread.run(Thread.java:745) ERROR 12:19:51,316 org.apache.spark.Logging$class (Logging.scala:75) - Task 0 in stage 65.0 failed 1 times; aborting job [info] - should allow to select specified non-UDT columns from a table containing some UDT columns *** FAILED *** (57 milliseconds) [info] org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 65.0 failed 1 times, most recent failure: Lost task 0.0 in stage 65.0 (TID 2657, localhost): java.lang.IndexOutOfBoundsException: 2 [info] at com.datastax.spark.connector.UDTValue.productElement(UDTValue.scala:11) [info] at scala.runtime.ScalaRunTime$$anon$1.next(ScalaRunTime.scala:181) [info] at org.apache.spark.sql.catalyst.CatalystTypeConverters$$anonfun$createToCatalystConverter$4.apply(CatalystTypeConverters.scala:187) [info] at org.apache.spark.sql.execution.RDDConversions$$anonfun$rowToRowRdd$1$$anonfun$apply$2.apply(ExistingRDD.scala:62) [info] at org.apache.spark.sql.execution.RDDConversions$$anonfun$rowToRowRdd$1$$anonfun$apply$2.apply(ExistingRDD.scala:59) [info] at scala.collection.Iterator$$anon$11.next(Iterator.scala:328) [info] at scala.collection.Iterator$$anon$11.next(Iterator.scala:328) [info] at scala.collection.Iterator$class.foreach(Iterator.scala:727) [info] at scala.collection.AbstractIterator.foreach(Iterator.scala:1157) [info] at scala.collection.generic.Growable$class.$plus$plus$eq(Growable.scala:48) [info] at scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:103) [info] at scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:47) [info] at scala.collection.TraversableOnce$class.to(TraversableOnce.scala:273) [info] at scala.collection.AbstractIterator.to(Iterator.scala:1157) [info] at scala.collection.TraversableOnce$class.toBuffer(TraversableOnce.scala:265) [info] at scala.collection.AbstractIterator.toBuffer(Iterator.scala:1157) [info] at scala.collection.TraversableOnce$class.toArray(TraversableOnce.scala:252) [info] at scala.collection.AbstractIterator.toArray(Iterator.scala:1157) [info] at org.apache.spark.rdd.RDD$$anonfun$collect$1$$anonfun$12.apply(RDD.scala:885) [info] at org.apache.spark.rdd.RDD$$anonfun$collect$1$$anonfun$12.apply(RDD.scala:885) [info] at org.apache.spark.SparkContext$$anonfun$runJob$5.apply(SparkContext.scala:1765) [info] at org.apache.spark.SparkContext$$anonfun$runJob$5.apply(SparkContext.scala:1765) [info] at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:63) [info] at org.apache.spark.scheduler.Task.run(Task.scala:70) [info] at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:213) [info] at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145) [info] at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615) [info] at java.lang.Thread.run(Thread.java:745) [info] [info] Driver stacktrace: [info] at org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$failJobAndIndependentStages(DAGScheduler.scala:1266) [info] at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1257) [info] at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1256) [info] at scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59) [info] at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:47) [info] at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1256) [info] at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:730) [info] at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:730) [info] at scala.Option.foreach(Option.scala:236) [info] at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:730) [info] at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1450) [info] at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1411) [info] at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:48) {code} It's due to the new code change in OSS Spark 1.4

    DataStax JIRA | 2 years ago | Alex Liu
    org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 65.0 failed 1 times, most recent failure: Lost task 0.0 in stage 65.0 (TID 2657, localhost): java.lang.IndexOutOfBoundsException: 2
  2. 0

    RE: Not Serializable exception when integrating SQL and Spark Streaming

    apache.org | 1 year ago
    org.apache.spark.SparkException: Task not serializable at org.apache.spark.util.ClosureCleaner$.ensureSerializable(ClosureCleaner.scala:166) at org.apache.spark.util.ClosureCleaner$.clean(ClosureCleaner.scala:158) at org.apache.spark.SparkContext.clean(SparkContext.scala:1435) at org.apache.spark.rdd.RDD.map(RDD.scala:271) at org.apache.spark.api.java.JavaRDDLike$class.map(JavaRDDLike.scala:78) at org.apache.spark.sql.api.java.JavaSchemaRDD.map(JavaSchemaRDD.scala:42) at com.basic.spark.NumberCount$2.call(NumberCount.java:79) at com.basic.spark.NumberCount$2.call(NumberCount.java:67) at org.apache.spark.streaming.api.java.JavaDStreamLike$anonfun$foreachRDD$1.apply(JavaDStreamLike.scala:274) at org.apache.spark.streaming.api.java.JavaDStreamLike$anonfun$foreachRDD$1.apply(JavaDStreamLike.scala:274) at org.apache.spark.streaming.dstream.DStream$anonfun$foreachRDD$1.apply(DStream.scala:529) at org.apache.spark.streaming.dstream.DStream$anonfun$foreachRDD$1.apply(DStream.scala:529) at org.apache.spark.streaming.dstream.ForEachDStream$anonfun$1.apply$mcV$sp(ForEachDStream.scala:42) at org.apache.spark.streaming.dstream.ForEachDStream$anonfun$1.apply(ForEachDStream.scala:40) at org.apache.spark.streaming.dstream.ForEachDStream$anonfun$1.apply(ForEachDStream.scala:40) at scala.util.Try$.apply(Try.scala:161) at org.apache.spark.streaming.scheduler.Job.run(Job.scala:32) at org.apache.spark.streaming.scheduler.JobScheduler$JobHandler.run(JobScheduler.scala:171) at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145) at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
  3. 0

    RE: Not Serializable exception when integrating SQL and Spark Streaming

    apache.org | 1 year ago
    org.apache.spark.SparkException: Task not serializable at org.apache.spark.util.ClosureCleaner$.ensureSerializable(ClosureCleaner.scala:166) at org.apache.spark.util.ClosureCleaner$.clean(ClosureCleaner.scala:158) at org.apache.spark.SparkContext.clean(SparkContext.scala:1435) at org.apache.spark.rdd.RDD.map(RDD.scala:271) at org.apache.spark.api.java.JavaRDDLike$class.map(JavaRDDLike.scala:78) at org.apache.spark.sql.api.java.JavaSchemaRDD.map(JavaSchemaRDD.scala:42) at com.basic.spark.NumberCount$2.call(NumberCount.java:79) at com.basic.spark.NumberCount$2.call(NumberCount.java:67) at org.apache.spark.streaming.api.java.JavaDStreamLike$anonfun$foreachRDD$1.apply(JavaDStreamLike.scala:274) at org.apache.spark.streaming.api.java.JavaDStreamLike$anonfun$foreachRDD$1.apply(JavaDStreamLike.scala:274) at org.apache.spark.streaming.dstream.DStream$anonfun$foreachRDD$1.apply(DStream.scala:529) at org.apache.spark.streaming.dstream.DStream$anonfun$foreachRDD$1.apply(DStream.scala:529) at org.apache.spark.streaming.dstream.ForEachDStream$anonfun$1.apply$mcV$sp(ForEachDStream.scala:42) at org.apache.spark.streaming.dstream.ForEachDStream$anonfun$1.apply(ForEachDStream.scala:40) at org.apache.spark.streaming.dstream.ForEachDStream$anonfun$1.apply(ForEachDStream.scala:40) at scala.util.Try$.apply(Try.scala:161) at org.apache.spark.streaming.scheduler.Job.run(Job.scala:32) at org.apache.spark.streaming.scheduler.JobScheduler$JobHandler.run(JobScheduler.scala:171) at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145) at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
  4. Speed up your debug routine!

    Automated exception search integrated into your IDE

    Root Cause Analysis

    1. org.apache.spark.SparkException

      Job aborted due to stage failure: Task 0 in stage 65.0 failed 1 times, most recent failure: Lost task 0.0 in stage 65.0 (TID 2657, localhost): java.lang.IndexOutOfBoundsException: 2

      at com.datastax.spark.connector.UDTValue.productElement()
    2. spark-cassandra-connector
      UDTValue.productElement
      1. com.datastax.spark.connector.UDTValue.productElement(UDTValue.scala:11)
      1 frame
    3. Scala
      ScalaRunTime$$anon$1.next
      1. scala.runtime.ScalaRunTime$$anon$1.next(ScalaRunTime.scala:181)
      1 frame
    4. Spark Project Catalyst
      CatalystTypeConverters$$anonfun$createToCatalystConverter$4.apply
      1. org.apache.spark.sql.catalyst.CatalystTypeConverters$$anonfun$createToCatalystConverter$4.apply(CatalystTypeConverters.scala:187)
      1 frame
    5. Spark Project SQL
      RDDConversions$$anonfun$rowToRowRdd$1$$anonfun$apply$2.apply
      1. org.apache.spark.sql.execution.RDDConversions$$anonfun$rowToRowRdd$1$$anonfun$apply$2.apply(ExistingRDD.scala:62)
      2. org.apache.spark.sql.execution.RDDConversions$$anonfun$rowToRowRdd$1$$anonfun$apply$2.apply(ExistingRDD.scala:59)
      2 frames
    6. Scala
      AbstractIterator.toArray
      1. scala.collection.Iterator$$anon$11.next(Iterator.scala:328)
      2. scala.collection.Iterator$$anon$11.next(Iterator.scala:328)
      3. scala.collection.Iterator$class.foreach(Iterator.scala:727)
      4. scala.collection.AbstractIterator.foreach(Iterator.scala:1157)
      5. scala.collection.generic.Growable$class.$plus$plus$eq(Growable.scala:48)
      6. scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:103)
      7. scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:47)
      8. scala.collection.TraversableOnce$class.to(TraversableOnce.scala:273)
      9. scala.collection.AbstractIterator.to(Iterator.scala:1157)
      10. scala.collection.TraversableOnce$class.toBuffer(TraversableOnce.scala:265)
      11. scala.collection.AbstractIterator.toBuffer(Iterator.scala:1157)
      12. scala.collection.TraversableOnce$class.toArray(TraversableOnce.scala:252)
      13. scala.collection.AbstractIterator.toArray(Iterator.scala:1157)
      13 frames
    7. Spark
      Executor$TaskRunner.run
      1. org.apache.spark.rdd.RDD$$anonfun$collect$1$$anonfun$12.apply(RDD.scala:885)
      2. org.apache.spark.rdd.RDD$$anonfun$collect$1$$anonfun$12.apply(RDD.scala:885)
      3. org.apache.spark.SparkContext$$anonfun$runJob$5.apply(SparkContext.scala:1765)
      4. org.apache.spark.SparkContext$$anonfun$runJob$5.apply(SparkContext.scala:1765)
      5. org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:63)
      6. org.apache.spark.scheduler.Task.run(Task.scala:70)
      7. org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:213)
      7 frames
    8. Java RT
      Thread.run
      1. java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
      2. java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
      3. java.lang.Thread.run(Thread.java:745)
      3 frames