IDEA Spark程序报错处理
Posted soyosuyang
tags:
篇首语:本文由小常识网(cha138.com)小编为大家整理,主要介绍了IDEA Spark程序报错处理相关的知识,希望对你有一定的参考价值。
错误一:
17/11/02 16:19:55 ERROR Executor: Exception in task 0.0 in stage 0.0 (TID 0) java.lang.NoSuchMethodError: scala.Product.$init$(Lscala/Product;)V at Person.<init>(RDD_To_DataFrame.scala:8) at RDD_To_DataFrame$.$anonfun$main$2(RDD_To_DataFrame.scala:16) 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:335) at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142) at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617) at java.lang.Thread.run(Thread.java:745) 17/11/02 16:19:55 ERROR TaskSetManager: Task 0 in stage 0.0 failed 1 times; aborting job Exception in thread "main" org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 0.0 failed 1 times, most recent failure: Lost task 0.0 in stage 0.0 (TID 0, localhost, executor driver): java.lang.NoSuchMethodError: scala.Product.$init$(Lscala/Product;)V at Person.<init>(RDD_To_DataFrame.scala:8) at RDD_To_DataFrame$.$anonfun$main$2(RDD_To_DataFrame.scala:16) 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:335) 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$$failJobAndIndependentStages(DAGScheduler.scala:1499) at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1487) at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1486) at scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59) at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:48) at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1486) at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:814) at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:814) at scala.Option.foreach(Option.scala:257) at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:814) at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:1714) at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1669) at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1658) at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:48) at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:630) at org.apache.spark.SparkContext.runJob(SparkContext.scala:2022) at org.apache.spark.SparkContext.runJob(SparkContext.scala:2043) at org.apache.spark.SparkContext.runJob(SparkContext.scala:2062) at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:336) at org.apache.spark.sql.execution.CollectLimitExec.executeCollect(limit.scala:38) at org.apache.spark.sql.Dataset.org$apache$spark$sql$Dataset$$collectFromPlan(Dataset.scala:2853) at org.apache.spark.sql.Dataset$$anonfun$head$1.apply(Dataset.scala:2153) at org.apache.spark.sql.Dataset$$anonfun$head$1.apply(Dataset.scala:2153) at org.apache.spark.sql.Dataset$$anonfun$55.apply(Dataset.scala:2837) at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:65) at org.apache.spark.sql.Dataset.withAction(Dataset.scala:2836) at org.apache.spark.sql.Dataset.head(Dataset.scala:2153) at org.apache.spark.sql.Dataset.take(Dataset.scala:2366) at org.apache.spark.sql.Dataset.showString(Dataset.scala:245) at org.apache.spark.sql.Dataset.show(Dataset.scala:644) at org.apache.spark.sql.Dataset.show(Dataset.scala:603) at org.apache.spark.sql.Dataset.show(Dataset.scala:612) at RDD_To_DataFrame$.main(RDD_To_DataFrame.scala:20) at RDD_To_DataFrame.main(RDD_To_DataFrame.scala) at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method) at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62) at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43) at java.lang.reflect.Method.invoke(Method.java:498) at com.intellij.rt.execution.application.AppMain.main(AppMain.java:147) Caused by: java.lang.NoSuchMethodError: scala.Product.$init$(Lscala/Product;)V at Person.<init>(RDD_To_DataFrame.scala:8) at RDD_To_DataFrame$.$anonfun$main$2(RDD_To_DataFrame.scala:16) 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:335) at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142) at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617) at java.lang.Thread.run(Thread.java:745)
错误处理:将IDEA中的Scala 改为2.10.4版本
这个问题主要出现在 Spark程序使用 case class 类时
错误二:
Error:(14, 46) No TypeTag available for (Array[String],) val documentDF= spark.createDataFrame(Seq(
错误处理:将IDEA中的Scala 改为2.12.3版本
这个问题主要出现在 Spark程序使用 Seq时:
比如:
val df= spark.createDataFrame(Seq( (0,Array("soyo","spark","soyo2","soyo","8")), (1,Array("soyo","hadoop","soyo","hadoop","xiaozhou","soyo2","spark","8","8")), (2,Array("soyo","spark","soyo2","hadoop","soyo3","8")), (3,Array("soyo","spark","soyo20","hadoop","soyo2","8","8")), (4,Array("soyo","8","spark","8","spark","spark","8")) )).toDF("id","words")
以上是关于IDEA Spark程序报错处理的主要内容,如果未能解决你的问题,请参考以下文章
idea连接spark集群报错解析:Caused by: java.lang.ClassCastException
idea运行spark项目报错:org.apache.hadoop.io.nativeio.NativeIO$Windows.createDirectoryWithMode0