Uploaded image for project: 'Spark'
  1. Spark
  2. SPARK-18851

DataSet Limit into Aggregate Results in NPE in Codegen

    XMLWordPrintableJSON

    Details

    • Type: Bug
    • Status: Resolved
    • Priority: Critical
    • Resolution: Duplicate
    • Affects Version/s: 2.0.2
    • Fix Version/s: None
    • Component/s: SQL
    • Labels:

      Description

      Performing a limit and then an aggregate seems to generate NPE vulnerable code.

      Simple example here

      case class ABCD ( a: Int, b:Int , c:Int, d: Option[Int])
      val ds = sc.parallelize(1 to 50).map( i => ABCD(i, i, i, if (i%2==0) None else Some(i))).toDS
      ds.limit(5).distinct.show
      
      16/12/13 14:02:37 ERROR Executor: Exception in task 0.0 in stage 31.0 (TID 597)
      java.lang.NullPointerException
      	at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIterator.agg_doAggregateWithKeys$(Unknown Source)
      	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:370)
      	at org.apache.spark.sql.execution.SparkPlan$$anonfun$4.apply(SparkPlan.scala:246)
      	at org.apache.spark.sql.execution.SparkPlan$$anonfun$4.apply(SparkPlan.scala:240)
      	at org.apache.spark.rdd.RDD$$anonfun$mapPartitionsInternal$1$$anonfun$apply$24.apply(RDD.scala:803)
      	at org.apache.spark.rdd.RDD$$anonfun$mapPartitionsInternal$1$$anonfun$apply$24.apply(RDD.scala:803)
      	at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
      	at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:319)
      	at org.apache.spark.rdd.RDD.iterator(RDD.scala:283)
      	at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:70)
      	at org.apache.spark.scheduler.Task.run(Task.scala:86)
      	at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:274)
      	at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)
      	at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)
      	at java.lang.Thread.run(Thread.java:745)
      16/12/13 14:02:37 WARN TaskSetManager: Lost task 0.0 in stage 31.0 (TID 597, localhost): java.lang.NullPointerException
      	at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIterator.agg_doAggregateWithKeys$(Unknown Source)
      	at org.apache.spark.sql.catalyst.expressions.GeneratedClass$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:370)
      	at org.apache.spark.sql.execution.SparkPlan$$anonfun$4.apply(SparkPlan.scala:246)
      	at org.apache.spark.sql.execution.SparkPlan$$anonfun$4.apply(SparkPlan.scala:240)
      	at org.apache.spark.rdd.RDD$$anonfun$mapPartitionsInternal$1$$anonfun$apply$24.apply(RDD.scala:803)
      	at org.apache.spark.rdd.RDD$$anonfun$mapPartitionsInternal$1$$anonfun$apply$24.apply(RDD.scala:803)
      	at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
      	at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:319)
      	at org.apache.spark.rdd.RDD.iterator(RDD.scala:283)
      	at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:70)
      	at org.apache.spark.scheduler.Task.run(Task.scala:86)
      	at org.apache.spark.executor.Executor$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)
      
      16/12/13 14:02:37 ERROR TaskSetManager: Task 0 in stage 31.0 failed 1 times; aborting job
      org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 31.0 failed 1 times, most recent failure: Lost task 0.0 in stage 31.0 (TID 597, localhost): java.lang.NullPointerException
      	at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIterator.agg_doAggregateWithKeys$(Unknown Source)
      	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:370)
      	at org.apache.spark.sql.execution.SparkPlan$$anonfun$4.apply(SparkPlan.scala:246)
      	at org.apache.spark.sql.execution.SparkPlan$$anonfun$4.apply(SparkPlan.scala:240)
      	at org.apache.spark.rdd.RDD$$anonfun$mapPartitionsInternal$1$$anonfun$apply$24.apply(RDD.scala:803)
      	at org.apache.spark.rdd.RDD$$anonfun$mapPartitionsInternal$1$$anonfun$apply$24.apply(RDD.scala:803)
      	at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
      	at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:319)
      	at org.apache.spark.rdd.RDD.iterator(RDD.scala:283)
      	at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:70)
      	at org.apache.spark.scheduler.Task.run(Task.scala:86)
      	at org.apache.spark.executor.Executor$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$$failJobAndIndependentStages(DAGScheduler.scala:1454)
        at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1442)
        at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1441)
        at scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
        at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:48)
        at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1441)
        at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:811)
        at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:811)
        at scala.Option.foreach(Option.scala:257)
        at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:811)
        at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:1667)
        at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1622)
        at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1611)
        at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:48)
        at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:632)
        at org.apache.spark.SparkContext.runJob(SparkContext.scala:1873)
        at org.apache.spark.SparkContext.runJob(SparkContext.scala:1886)
        at org.apache.spark.SparkContext.runJob(SparkContext.scala:1899)
        at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:347)
        at org.apache.spark.sql.execution.CollectLimitExec.executeCollect(limit.scala:39)
        at org.apache.spark.sql.Dataset$$anonfun$org$apache$spark$sql$Dataset$$execute$1$1.apply(Dataset.scala:2193)
        at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:57)
        at org.apache.spark.sql.Dataset.withNewExecutionId(Dataset.scala:2546)
        at org.apache.spark.sql.Dataset.org$apache$spark$sql$Dataset$$execute$1(Dataset.scala:2192)
        at org.apache.spark.sql.Dataset.org$apache$spark$sql$Dataset$$collect(Dataset.scala:2199)
        at org.apache.spark.sql.Dataset$$anonfun$head$1.apply(Dataset.scala:1935)
        at org.apache.spark.sql.Dataset$$anonfun$head$1.apply(Dataset.scala:1934)
        at org.apache.spark.sql.Dataset.withTypedCallback(Dataset.scala:2576)
        at org.apache.spark.sql.Dataset.head(Dataset.scala:1934)
        at org.apache.spark.sql.Dataset.take(Dataset.scala:2149)
        at org.apache.spark.sql.Dataset.showString(Dataset.scala:239)
        at org.apache.spark.sql.Dataset.show(Dataset.scala:526)
        at org.apache.spark.sql.Dataset.show(Dataset.scala:486)
        at org.apache.spark.sql.Dataset.show(Dataset.scala:495)
        ... 54 elided
      Caused by: java.lang.NullPointerException
        at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIterator.agg_doAggregateWithKeys$(Unknown Source)
        at org.apache.spark.sql.catalyst.expressions.GeneratedClass$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:370)
        at org.apache.spark.sql.execution.SparkPlan$$anonfun$4.apply(SparkPlan.scala:246)
        at org.apache.spark.sql.execution.SparkPlan$$anonfun$4.apply(SparkPlan.scala:240)
        at org.apache.spark.rdd.RDD$$anonfun$mapPartitionsInternal$1$$anonfun$apply$24.apply(RDD.scala:803)
        at org.apache.spark.rdd.RDD$$anonfun$mapPartitionsInternal$1$$anonfun$apply$24.apply(RDD.scala:803)
        at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
        at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:319)
        at org.apache.spark.rdd.RDD.iterator(RDD.scala:283)
        at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:70)
        at org.apache.spark.scheduler.Task.run(Task.scala:86)
        at org.apache.spark.executor.Executor$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)
      
      

        Attachments

          Issue Links

            Activity

              People

              • Assignee:
                Unassigned
                Reporter:
                rspitzer Russell Spitzer
              • Votes:
                0 Vote for this issue
                Watchers:
                3 Start watching this issue

                Dates

                • Created:
                  Updated:
                  Resolved: