spark streaming NotSerializableException

在使用spark streaming时，会出现无法序列化异常，代码如下：

SparkConf conf = new SparkConf().setAppName("NetworkWordCount");JavaStreamingContext jssc = new JavaStreamingContext(conf, new Duration(5000));JavaReceiverInputDStream<String> lines = jssc.socketTextStream("10.0.3.19", 9999);JavaDStream<String> words = lines.flatMap(  new FlatMapFunction<String, String>() {    public Iterable<String> call(String x) {    System.out.println(x);    String str = JSON.toJSONString(x);    System.out.println("json:"+str);      return Arrays.asList(x.split(" "));    }  });new FunNext(<span style="font-family: Arial, Helvetica, sans-serif;">words</span>).next();

public class FunNext{JavaDStream<String> words;public FunNext(JavaDStream<String> words) {this.words = words;}public JavaDStream<String> getWords() {return words;}public void setWords(JavaDStream<String> words) {this.words = words;}public void next(){JavaPairDStream<String, Integer> pairs = words.mapToPair(  new PairFunction<String, String, Integer>() {    public Tuple2<String, Integer> call(String s) throws Exception {      return new Tuple2<String, Integer>(s, 1);    }  });JavaPairDStream<String, Integer> wordCounts = pairs.reduceByKey(  new Function2<Integer, Integer, Integer>() {    public Integer call(Integer i1, Integer i2) throws Exception {      return i1 + i2;    }  });wordCounts.print();}}

异常信息如下：

5/01/24 16:56:20 ERROR JobScheduler: Error running job streaming job 1422089780000 ms.0
org.apache.spark.SparkException: Job aborted due to stage failure: Task not serializable: java.io.NotSerializableException: com.kingsoft.spark.FunNext
at org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$failJobAndIndependentStages(DAGScheduler.scala:1033)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1017)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1015)
at scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:47)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1015)
at org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$submitMissingTasks(DAGScheduler.scala:770)
at org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$submitStage(DAGScheduler.scala:713)
at org.apache.spark.scheduler.DAGScheduler.handleJobSubmitted(DAGScheduler.scala:697)
at org.apache.spark.scheduler.DAGSchedulerEventProcessActor$$anonfun$receive$2.applyOrElse(DAGScheduler.scala:1176)
at akka.actor.ActorCell.receiveMessage(ActorCell.scala:498)
at akka.actor.ActorCell.invoke(ActorCell.scala:456)
at akka.dispatch.Mailbox.processMailbox(Mailbox.scala:237)
at akka.dispatch.Mailbox.run(Mailbox.scala:219)
at akka.dispatch.ForkJoinExecutorConfigurator$AkkaForkJoinTask.exec(AbstractDispatcher.scala:386)
at scala.concurrent.forkjoin.ForkJoinTask.doExec(ForkJoinTask.java:260)
at scala.concurrent.forkjoin.ForkJoinPool$WorkQueue.runTask(ForkJoinPool.java:1339)
at scala.concurrent.forkjoin.ForkJoinPool.runWorker(ForkJoinPool.java:1979)
at scala.concurrent.forkjoin.ForkJoinWorkerThread.run(ForkJoinWorkerThread.java:107)

发现是类FunNext不能被序列化，然后给函数FunNext实现 implements Serializable。打包运行，发现还是异常，分析了半天发现是该类里的words属性不能被序列化，也就是RDD不能被序列化，解决办法就是在words前面加上transient 来修饰即可。也可以将words作为next()函数的参数传进去，这样FunNext类也能被序列化了。