一个spark的ClassNotFound的问题

资深工程师为你打call 2016-10-08 11:17:07

源代码如下：
package org.apache.spark.examples

import scala.math.random

import org.apache.spark._

/** Computes an approximation to pi */
object SparkPi {
def main(args: Array[String]) {
val conf = new SparkConf().setAppName("Spark Pi").setMaster("spark://192.168.70.24:7077").set("spark.executor.memory", "2g")
val spark = new SparkContext(conf)
spark.addJar("D:\\workspace\\JAR\\SparkPi_jar\\SparkPi.jar")
val slices = if (args.length > 0) args(0).toInt else 2
val n = math.min(100000L * slices, Int.MaxValue).toInt // avoid overflow
val count = spark.parallelize(1 until n, slices).map { i =>
val x = random * 2 - 1
val y = random * 2 - 1
if (x*x + y*y < 1) 1 else 0
}.reduce(_ + _)
println("Pi is roughly " + 4.0 * count / n)
spark.stop()
}
}

报错如下：
Exception in thread "main" org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 0.0 failed 4 times, most recent failure: Lost task 0.3 in stage 0.0 (TID 6, HadoopMaster): java.lang.ClassNotFoundException: org.apache.spark.examples.SparkPi$$anonfun$1
at java.net.URLClassLoader.findClass(URLClassLoader.java:381)
at java.lang.ClassLoader.loadClass(ClassLoader.java:424)
at java.lang.ClassLoader.loadClass(ClassLoader.java:357)
at java.lang.Class.forName0(Native Method)
at java.lang.Class.forName(Class.java:348)
at org.apache.spark.serializer.JavaDeserializationStream$$anon$1.resolveClass(JavaSerializer.scala:68)
at java.io.ObjectInputStream.readNonProxyDesc(ObjectInputStream.java:1620)
at java.io.ObjectInputStream.readClassDesc(ObjectInputStream.java:1521)
at java.io.ObjectInputStream.readOrdinaryObject(ObjectInputStream.java:1781)
at java.io.ObjectInputStream.readObject0(ObjectInputStream.java:1353)
at java.io.ObjectInputStream.defaultReadFields(ObjectInputStream.java:2018)
at java.io.ObjectInputStream.readSerialData(ObjectInputStream.java:1942)
at java.io.ObjectInputStream.readOrdinaryObject(ObjectInputStream.java:1808)
at java.io.ObjectInputStream.readObject0(ObjectInputStream.java:1353)
at java.io.ObjectInputStream.defaultReadFields(ObjectInputStream.java:2018)
at java.io.ObjectInputStream.readSerialData(ObjectInputStream.java:1942)
at java.io.ObjectInputStream.readOrdinaryObject(ObjectInputStream.java:1808)
at java.io.ObjectInputStream.readObject0(ObjectInputStream.java:1353)
at java.io.ObjectInputStream.defaultReadFields(ObjectInputStream.java:2018)
at java.io.ObjectInputStream.readSerialData(ObjectInputStream.java:1942)
at java.io.ObjectInputStream.readOrdinaryObject(ObjectInputStream.java:1808)
at java.io.ObjectInputStream.readObject0(ObjectInputStream.java:1353)
at java.io.ObjectInputStream.readObject(ObjectInputStream.java:373)
at org.apache.spark.serializer.JavaDeserializationStream.readObject(JavaSerializer.scala:76)
at org.apache.spark.serializer.JavaSerializerInstance.deserialize(JavaSerializer.scala:115)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:61)
at org.apache.spark.scheduler.Task.run(Task.scala:89)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:214)
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$$failJobAndIndependentStages(DAGScheduler.scala:1431)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1419)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1418)
at scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:47)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1418)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:799)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:799)
at scala.Option.foreach(Option.scala:236)
at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:799)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:1640)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1599)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1588)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:48)
at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:620)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:1832)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:1952)
at org.apache.spark.rdd.RDD$$anonfun$reduce$1.apply(RDD.scala:1025)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:150)
at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:111)
at org.apache.spark.rdd.RDD.withScope(RDD.scala:316)
at org.apache.spark.rdd.RDD.reduce(RDD.scala:1007)
at org.apache.spark.examples.SparkPi$.main(SparkPi.scala:37)
at org.apache.spark.examples.SparkPi.main(SparkPi.scala)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:497)
at com.intellij.rt.execution.application.AppMain.main(AppMain.java:147)
Caused by: java.lang.ClassNotFoundException: org.apache.spark.examples.SparkPi$$anonfun$1
at java.net.URLClassLoader.findClass(URLClassLoader.java:381)
at java.lang.ClassLoader.loadClass(ClassLoader.java:424)
at java.lang.ClassLoader.loadClass(ClassLoader.java:357)
at java.lang.Class.forName0(Native Method)
at java.lang.Class.forName(Class.java:348)
at org.apache.spark.serializer.JavaDeserializationStream$$anon$1.resolveClass(JavaSerializer.scala:68)
at java.io.ObjectInputStream.readNonProxyDesc(ObjectInputStream.java:1620)
at java.io.ObjectInputStream.readClassDesc(ObjectInputStream.java:1521)
at java.io.ObjectInputStream.readOrdinaryObject(ObjectInputStream.java:1781)
at java.io.ObjectInputStream.readObject0(ObjectInputStream.java:1353)
at java.io.ObjectInputStream.defaultReadFields(ObjectInputStream.java:2018)
at java.io.ObjectInputStream.readSerialData(ObjectInputStream.java:1942)
at java.io.ObjectInputStream.readOrdinaryObject(ObjectInputStream.java:1808)
at java.io.ObjectInputStream.readObject0(ObjectInputStream.java:1353)
at java.io.ObjectInputStream.defaultReadFields(ObjectInputStream.java:2018)
at java.io.ObjectInputStream.readSerialData(ObjectInputStream.java:1942)
at java.io.ObjectInputStream.readOrdinaryObject(ObjectInputStream.java:1808)
at java.io.ObjectInputStream.readObject0(ObjectInputStream.java:1353)
at java.io.ObjectInputStream.defaultReadFields(ObjectInputStream.java:2018)
at java.io.ObjectInputStream.readSerialData(ObjectInputStream.java:1942)
at java.io.ObjectInputStream.readOrdinaryObject(ObjectInputStream.java:1808)
at java.io.ObjectInputStream.readObject0(ObjectInputStream.java:1353)
at java.io.ObjectInputStream.readObject(ObjectInputStream.java:373)
at org.apache.spark.serializer.JavaDeserializationStream.readObject(JavaSerializer.scala:76)
at org.apache.spark.serializer.JavaSerializerInstance.deserialize(JavaSerializer.scala:115)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:61)
at org.apache.spark.scheduler.Task.run(Task.scala:89)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:214)
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)

...全文