scala list类型转rdd时候报错:SparkException: Task not serializable

发布于 2022-09-30 23:10:38 字数 8129 浏览 68 评论 0

完整的错误是:

org.apache.spark.SparkException: Task not serializable
    at org.apache.spark.util.ClosureCleaner$.ensureSerializable(ClosureCleaner.scala:416)
    at org.apache.spark.util.ClosureCleaner$.clean(ClosureCleaner.scala:406)
    at org.apache.spark.util.ClosureCleaner$.clean(ClosureCleaner.scala:162)
    at org.apache.spark.SparkContext.clean(SparkContext.scala:2459)
    at org.apache.spark.rdd.RDD.$anonfun$foreach$1(RDD.scala:1011)
    at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
    at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:112)
    at org.apache.spark.rdd.RDD.withScope(RDD.scala:414)
    at org.apache.spark.rdd.RDD.foreach(RDD.scala:1010)
    at main.ylcx.mallRec.recommend$.$anonfun$main$1(recommend.scala:51)
    at main.ylcx.mallRec.recommend$.$anonfun$main$1$adapted(recommend.scala:41)
    at org.apache.spark.streaming.dstream.DStream.$anonfun$foreachRDD$2(DStream.scala:629)
    at org.apache.spark.streaming.dstream.DStream.$anonfun$foreachRDD$2$adapted(DStream.scala:629)
    at org.apache.spark.streaming.dstream.ForEachDStream.$anonfun$generateJob$2(ForEachDStream.scala:51)
    at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
    at org.apache.spark.streaming.dstream.DStream.createRDDWithLocalProperties(DStream.scala:417)
    at org.apache.spark.streaming.dstream.ForEachDStream.$anonfun$generateJob$1(ForEachDStream.scala:51)
    at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
    at scala.util.Try$.apply(Try.scala:213)
    at org.apache.spark.streaming.scheduler.Job.run(Job.scala:39)
    at org.apache.spark.streaming.scheduler.JobScheduler$JobHandler.$anonfun$run$1(JobScheduler.scala:256)
    at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
    at scala.util.DynamicVariable.withValue(DynamicVariable.scala:62)
    at org.apache.spark.streaming.scheduler.JobScheduler$JobHandler.run(JobScheduler.scala:256)
    at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)
    at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)
    at java.lang.Thread.run(Thread.java:748)
Caused by: java.io.NotSerializableException: org.apache.spark.SparkContext
Serialization stack:
    - object not serializable (class: org.apache.spark.SparkContext, value: [email protected])
    - element of array (index: 0)
    - array (class [Ljava.lang.Object;, size 1)
    - field (class: java.lang.invoke.SerializedLambda, name: capturedArgs, type: class [Ljava.lang.Object;)
    - object (class java.lang.invoke.SerializedLambda, SerializedLambda[capturingClass=class main.ylcx.mallRec.recommend$, functionalInterfaceMethod=scala/Function1.apply:(Ljava/lang/Object;)Ljava/lang/Object;, implementation=invokeStatic main/ylcx/mallRec/recommend$.$anonfun$main$6$adapted:(Lorg/apache/spark/SparkContext;Lscala/Tuple2;)Ljava/lang/Object;, instantiatedMethodType=(Lscala/Tuple2;)Ljava/lang/Object;, numCaptured=1])
    - writeReplace data (class: java.lang.invoke.SerializedLambda)
    - object (class main.ylcx.mallRec.recommend$$$Lambda$1272/1717720516, main.ylcx.mallRec.recommend$$$Lambda$1272/[email protected])
    at org.apache.spark.serializer.SerializationDebugger$.improveException(SerializationDebugger.scala:41)
    at org.apache.spark.serializer.JavaSerializationStream.writeObject(JavaSerializer.scala:47)
    at org.apache.spark.serializer.JavaSerializerInstance.serialize(JavaSerializer.scala:101)
    at org.apache.spark.util.ClosureCleaner$.ensureSerializable(ClosureCleaner.scala:413)
    ... 26 more
Exception in thread "main" org.apache.spark.SparkException: Task not serializable
    at org.apache.spark.util.ClosureCleaner$.ensureSerializable(ClosureCleaner.scala:416)
    at org.apache.spark.util.ClosureCleaner$.clean(ClosureCleaner.scala:406)
    at org.apache.spark.util.ClosureCleaner$.clean(ClosureCleaner.scala:162)
    at org.apache.spark.SparkContext.clean(SparkContext.scala:2459)
    at org.apache.spark.rdd.RDD.$anonfun$foreach$1(RDD.scala:1011)
    at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
    at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:112)
    at org.apache.spark.rdd.RDD.withScope(RDD.scala:414)
    at org.apache.spark.rdd.RDD.foreach(RDD.scala:1010)
    at main.ylcx.mallRec.recommend$.$anonfun$main$1(recommend.scala:51)
    at main.ylcx.mallRec.recommend$.$anonfun$main$1$adapted(recommend.scala:41)
    at org.apache.spark.streaming.dstream.DStream.$anonfun$foreachRDD$2(DStream.scala:629)
    at org.apache.spark.streaming.dstream.DStream.$anonfun$foreachRDD$2$adapted(DStream.scala:629)
    at org.apache.spark.streaming.dstream.ForEachDStream.$anonfun$generateJob$2(ForEachDStream.scala:51)
    at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
    at org.apache.spark.streaming.dstream.DStream.createRDDWithLocalProperties(DStream.scala:417)
    at org.apache.spark.streaming.dstream.ForEachDStream.$anonfun$generateJob$1(ForEachDStream.scala:51)
    at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
    at scala.util.Try$.apply(Try.scala:213)
    at org.apache.spark.streaming.scheduler.Job.run(Job.scala:39)
    at org.apache.spark.streaming.scheduler.JobScheduler$JobHandler.$anonfun$run$1(JobScheduler.scala:256)
    at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
    at scala.util.DynamicVariable.withValue(DynamicVariable.scala:62)
    at org.apache.spark.streaming.scheduler.JobScheduler$JobHandler.run(JobScheduler.scala:256)
    at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)
    at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)
    at java.lang.Thread.run(Thread.java:748)
Caused by: java.io.NotSerializableException: org.apache.spark.SparkContext
Serialization stack:
    - object not serializable (class: org.apache.spark.SparkContext, value: [email protected])
    - element of array (index: 0)
    - array (class [Ljava.lang.Object;, size 1)
    - field (class: java.lang.invoke.SerializedLambda, name: capturedArgs, type: class [Ljava.lang.Object;)
    - object (class java.lang.invoke.SerializedLambda, SerializedLambda[capturingClass=class main.ylcx.mallRec.recommend$, functionalInterfaceMethod=scala/Function1.apply:(Ljava/lang/Object;)Ljava/lang/Object;, implementation=invokeStatic main/ylcx/mallRec/recommend$.$anonfun$main$6$adapted:(Lorg/apache/spark/SparkContext;Lscala/Tuple2;)Ljava/lang/Object;, instantiatedMethodType=(Lscala/Tuple2;)Ljava/lang/Object;, numCaptured=1])
    - writeReplace data (class: java.lang.invoke.SerializedLambda)
    - object (class main.ylcx.mallRec.recommend$$$Lambda$1272/1717720516, main.ylcx.mallRec.recommend$$$Lambda$1272/[email protected])
    at org.apache.spark.serializer.SerializationDebugger$.improveException(SerializationDebugger.scala:41)
    at org.apache.spark.serializer.JavaSerializationStream.writeObject(JavaSerializer.scala:47)
    at org.apache.spark.serializer.JavaSerializerInstance.serialize(JavaSerializer.scala:101)
    at org.apache.spark.util.ClosureCleaner$.ensureSerializable(ClosureCleaner.scala:413)
    ... 26 more

错误就在list转rdd的这一行代码:

val recordsRdd = sparkContext.makeRDD[Rating](recordsList)

由于sparkContext用的是StreamingContext.sparkContext

所以问题就在这儿 但是我要用makeRDD来转换

如何解决这个错误?或者有没有其他方式转换。

如果你对这篇内容有疑问,欢迎到本站社区发帖提问 参与讨论,获取更多帮助,或者扫码二维码加入 Web 技术交流群。

扫码二维码加入Web技术交流群

发布评论

需要 登录 才能够评论, 你可以免费 注册 一个本站的账号。
列表为空,暂无数据
我们使用 Cookies 和其他技术来定制您的体验包括您的登录状态等。通过阅读我们的 隐私政策 了解更多相关信息。 单击 接受 或继续使用网站,即表示您同意使用 Cookies 和您的相关数据。
原文