现象

使用spark-submit提交一个Spark Streaming Application至yarn集群, 报错

Caused by: java.lang.ClassNotFoundException: XXXStartup$$anonfun$9
    at java.net.URLClassLoader$1.run(URLClassLoader.java:366)
    at java.net.URLClassLoader$1.run(URLClassLoader.java:355)
    at java.security.AccessController.doPrivileged(Native Method)
    at java.net.URLClassLoader.findClass(URLClassLoader.java:354)
    at java.lang.ClassLoader.loadClass(ClassLoader.java:423)
    at sun.misc.Launcher$AppClassLoader.loadClass(Launcher.java:308)
    at java.lang.ClassLoader.loadClass(ClassLoader.java:356)
    at java.lang.Class.forName0(Native Method)
    at java.lang.Class.forName(Class.java:266)
    at java.io.ObjectInputStream.resolveClass(ObjectInputStream.java:623)
    at org.apache.spark.streaming.ObjectInputStreamWithLoader.resolveClass(Checkpoint.scala:286)
    at java.io.ObjectInputStream.readNonProxyDesc(ObjectInputStream.java:1610)
    at java.io.ObjectInputStream.readClassDesc(ObjectInputStream.java:1515)
    at java.io.ObjectInputStream.readOrdinaryObject(ObjectInputStream.java:1769)
    at java.io.ObjectInputStream.readObject0(ObjectInputStream.java:1348)
    at java.io.ObjectInputStream.defaultReadFields(ObjectInputStream.java:1989)
    at java.io.ObjectInputStream.readSerialData(ObjectInputStream.java:1913)
    at java.io.ObjectInputStream.readOrdinaryObject(ObjectInputStream.java:1796)
    at java.io.ObjectInputStream.readObject0(ObjectInputStream.java:1348)
    at java.io.ObjectInputStream.readArray(ObjectInputStream.java:1704)
    at java.io.ObjectInputStream.readObject0(ObjectInputStream.java:1342)
    at java.io.ObjectInputStream.defaultReadFields(ObjectInputStream.java:1989)
    at java.io.ObjectInputStream.readSerialData(ObjectInputStream.java:1913)
    at java.io.ObjectInputStream.readOrdinaryObject(ObjectInputStream.java:1796)
    at java.io.ObjectInputStream.readObject0(ObjectInputStream.java:1348)
    at java.io.ObjectInputStream.defaultReadFields(ObjectInputStream.java:1989)
    at java.io.ObjectInputStream.readSerialData(ObjectInputStream.java:1913)
    at java.io.ObjectInputStream.readOrdinaryObject(ObjectInputStream.java:1796)
    at java.io.ObjectInputStream.readObject0(ObjectInputStream.java:1348)
    at java.io.ObjectInputStream.readArray(ObjectInputStream.java:1704)
    at java.io.ObjectInputStream.readObject0(ObjectInputStream.java:1342)
    at java.io.ObjectInputStream.defaultReadFields(ObjectInputStream.java:1989)
    at java.io.ObjectInputStream.readSerialData(ObjectInputStream.java:1913)
    at java.io.ObjectInputStream.readOrdinaryObject(ObjectInputStream.java:1796)
    at java.io.ObjectInputStream.readObject0(ObjectInputStream.java:1348)
    at java.io.ObjectInputStream.defaultReadFields(ObjectInputStream.java:1989)
    at java.io.ObjectInputStream.defaultReadObject(ObjectInputStream.java:499)
    at org.apache.spark.streaming.DStreamGraph$$anonfun$readObject$1.apply$mcV$sp(DStreamGraph.scala:188)
    at org.apache.spark.util.Utils$.tryOrIOException(Utils.scala:1138)
    ... 31 more
Exception in thread "main" org.apache.spark.SparkException: Failed to read checkpoint from directory XXX_startup
    at org.apache.spark.streaming.CheckpointReader$.read(Checkpoint.scala:272)
    at org.apache.spark.streaming.StreamingContext$.getOrCreate(StreamingContext.scala:624)
    at XXXStartup$.main(XXXStartup.scala:79)
    at XXXStartup.main(XXXStartup.scala)
    at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
    at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57)
    at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
    at java.lang.reflect.Method.invoke(Method.java:601)
    at org.apache.spark.deploy.SparkSubmit$.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:569)
    at org.apache.spark.deploy.SparkSubmit$.doRunMain$1(SparkSubmit.scala:166)
    at org.apache.spark.deploy.SparkSubmit$.submit(SparkSubmit.scala:189)
    at org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:110)
    at org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)

解决方案及原因

StreamingContext是这样创建的:

    val createStreamingContext = (checkPointDir: String) => {
      val sparkConf = new SparkConf().setAppName(topic)
      val sparkContext = new SparkContext(sparkConf)
      @transient val streamingContext = new StreamingContext(sparkContext, Seconds(args(1).toInt))
      streamingContext.checkpoint(checkPointDir)
      streamingContext
    }
    val checkPointDir = AppConf.strCheckPointPrefix + topic
    val streamingContext = StreamingContext.getOrCreate(checkPointDir, () => createStreamingContext(checkPointDir))

重新编译application jar包之后, 再次提交app之前没有清除checkpoint目录下已经存在的之前的application生成的checkpoint文件导致. 清除之后再提交即可