ERROR Executor: Exception in task 0.0 in stage 91.0

遇到下面这种Executor报错的情况，多半是sparkRDD或者DataFrame定义的时候出了问题，因为sparkSql程序执行的机制是：transformation端不是真正的执行，只有action端才是执行的开始，所以会在action函数调用的时候，才会把之前transform端或者定义类方法的时候存在的错误显式的抛出来。
可以根据exception具体信息以及之前的代码确定哪儿出来问题。

18/02/14 11:11:40 ERROR Executor: Exception in task 0.0 in stage 91.0 (TID 1845)
java.lang.ArrayIndexOutOfBoundsException: 4
        at $line117.$read$$iw$$iw$$iw$$iw$$iw$$iw$$iw$$iw$$anonfun$2.apply(:32)
        at $line117.$read$$iw$$iw$$iw$$iw$$iw$$iw$$iw$$iw$$anonfun$2.apply(:32)
        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:395)
        at org.apache.spark.sql.execution.SparkPlan$$anonfun$2.apply(SparkPlan.scala:234)
        at org.apache.spark.sql.execution.SparkPlan$$anonfun$2.apply(SparkPlan.scala:228)
        at org.apache.spark.rdd.RDD$$anonfun$mapPartitionsInternal$1$$anonfun$apply$25.apply(RDD.scala:827)
        at org.apache.spark.rdd.RDD$$anonfun$mapPartitionsInternal$1$$anonfun$apply$25.apply(RDD.scala:827)
        at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
        at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:323)
        at org.apache.spark.rdd.RDD.iterator(RDD.scala:287)
        at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:87)
        at org.apache.spark.scheduler.Task.run(Task.scala:108)
        at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:338)
        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)
18/02/14 11:11:40 WARN TaskSetManager: Lost task 0.0 in stage 91.0 (TID 1845, localhost, executor driver): java.lang.ArrayIndexOutOfBoundsException: 4
        at $line117.$read$$iw$$iw$$iw$$iw$$iw$$iw$$iw$$iw$$anonfun$2.apply(:32)
        at $line117.$read$$iw$$iw$$iw$$iw$$iw$$iw$$iw$$iw$$anonfun$2.apply(:32)
        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:395)
        at org.apache.spark.sql.execution.SparkPlan$$anonfun$2.apply(SparkPlan.scala:234)
        at org.apache.spark.sql.execution.SparkPlan$$anonfun$2.apply(SparkPlan.scala:228)
        at org.apache.spark.rdd.RDD$$anonfun$mapPartitionsInternal$1$$anonfun$apply$25.apply(RDD.scala:827)
        at org.apache.spark.rdd.RDD$$anonfun$mapPartitionsInternal$1$$anonfun$apply$25.apply(RDD.scala:827)
        at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
        at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:323)
        at org.apache.spark.rdd.RDD.iterator(RDD.scala:287)
        at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:87)
        at org.apache.spark.scheduler.Task.run(Task.scala:108)
        at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:338)
        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)

18/02/14 11:11:40 ERROR TaskSetManager: Task 0 in stage 91.0 failed 1 times; aborting job
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 91.0 failed 1 times, most recent failure: Lost task 0.0 in stage 91.0 (TID 1845, localhost, executor driver): java.lang.ArrayIndexOutOfBoundsException: 4
        at $anonfun$2.apply(:32)
        at $anonfun$2.apply(:32)
        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:395)
        at org.apache.spark.sql.execution.SparkPlan$$anonfun$2.apply(SparkPlan.scala:234)
        at org.apache.spark.sql.execution.SparkPlan$$anonfun$2.apply(SparkPlan.scala:228)
        at org.apache.spark.rdd.RDD$$anonfun$mapPartitionsInternal$1$$anonfun$apply$25.apply(RDD.scala:827)
        at org.apache.spark.rdd.RDD$$anonfun$mapPartitionsInternal$1$$anonfun$apply$25.apply(RDD.scala:827)
        at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
        at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:323)
        at org.apache.spark.rdd.RDD.iterator(RDD.scala:287)
        at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:87)
        at org.apache.spark.scheduler.Task.run(Task.scala:108)
        at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:338)
        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)

Driver stacktrace:
  at org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$failJobAndIndependentStages(DAGScheduler.scala:1517)
  at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1505)
  at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1504)
  at scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
  at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:48)
  at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1504)
  at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:814)
  at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:814)
  at scala.Option.foreach(Option.scala:257)
  at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:814)
  at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:1732)
  at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1687)
  at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1676)
  at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:48)
  at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:630)
  at org.apache.spark.SparkContext.runJob(SparkContext.scala:2029)
  at org.apache.spark.SparkContext.runJob(SparkContext.scala:2050)
  at org.apache.spark.SparkContext.runJob(SparkContext.scala:2069)
  at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:336)
  at org.apache.spark.sql.execution.CollectLimitExec.executeCollect(limit.scala:38)
  at org.apache.spark.sql.Dataset.org$apache$spark$sql$Dataset$$collectFromPlan(Dataset.scala:2861)
  at org.apache.spark.sql.Dataset$$anonfun$head$1.apply(Dataset.scala:2150)
  at org.apache.spark.sql.Dataset$$anonfun$head$1.apply(Dataset.scala:2150)
  at org.apache.spark.sql.Dataset$$anonfun$55.apply(Dataset.scala:2842)
  at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:65)
  at org.apache.spark.sql.Dataset.withAction(Dataset.scala:2841)
  at org.apache.spark.sql.Dataset.head(Dataset.scala:2150)
  at org.apache.spark.sql.Dataset.take(Dataset.scala:2363)
  ... 48 elided
Caused by: java.lang.ArrayIndexOutOfBoundsException: 4
  at $anonfun$2.apply(:32)
  at $anonfun$2.apply(:32)
  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:395)
  at org.apache.spark.sql.execution.SparkPlan$$anonfun$2.apply(SparkPlan.scala:234)
  at org.apache.spark.sql.execution.SparkPlan$$anonfun$2.apply(SparkPlan.scala:228)
  at org.apache.spark.rdd.RDD$$anonfun$mapPartitionsInternal$1$$anonfun$apply$25.apply(RDD.scala:827)
  at org.apache.spark.rdd.RDD$$anonfun$mapPartitionsInternal$1$$anonfun$apply$25.apply(RDD.scala:827)
  at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
  at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:323)
  at org.apache.spark.rdd.RDD.iterator(RDD.scala:287)
  at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:87)
  at org.apache.spark.scheduler.Task.run(Task.scala:108)
  at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:338)
  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)