Hi all, I'm using CDH 5.0.1 (Spark 0.9) and submitting a job in Spark Standalone Cluster mode.
The job is quite simple as follows: object HBaseApp { def main(args:Array[String]) { testHBase("student", "/test/xt/saveRDD") } def testHBase(tableName: String, outFile:String) { val sparkConf = new SparkConf() .setAppName("-- Test HBase --") .set("spark.executor.memory", "2g") .set("spark.cores.max", "16") val sparkContext = new SparkContext(sparkConf) val rdd = sparkContext.parallelize(List(1,2,3,4,5,6,7,8,9,10), 3) val c = rdd.count // successful println("\n\n\n" + c + "\n\n\n") rdd.saveAsTextFile(outFile) // This line will throw "java.lang.ClassNotFoundException: com.xt.scala.HBaseApp$$anonfun$testHBase$1" println("\n down \n") } } I submitted this job using the following script: #!/bin/bash HBASE_CLASSPATH=$(hbase classpath) APP_JAR=/usr/games/spark/xt/SparkDemo-0.0.1-SNAPSHOT.jar SPARK_ASSEMBLY_JAR=/usr/games/spark/xt/spark-assembly_2.10-0.9.0-cdh5.0.1-hadoop2.3.0-cdh5.0.1.jar SPARK_MASTER=spark://b02.jsepc.com:7077 CLASSPATH=$CLASSPATH:$APP_JAR:$SPARK_ASSEMBLY_JAR:$HBASE_CLASSPATH export SPARK_CLASSPATH=/usr/lib/hbase/lib/* CONFIG_OPTS="-Dspark.master=$SPARK_MASTER" java -cp $CLASSPATH $CONFIG_OPTS com.xt.scala.HBaseApp $@ After I submitted the job, the count of rdd could be computed successfully, but that rdd could not be saved into HDFS and the following exception was thrown: 14/10/11 16:09:33 WARN scheduler.TaskSetManager: Loss was due to java.lang.ClassNotFoundException java.lang.ClassNotFoundException: com.xt.scala.HBaseApp$$anonfun$testHBase$1 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:425) at java.lang.ClassLoader.loadClass(ClassLoader.java:358) at java.lang.Class.forName0(Native Method) at java.lang.Class.forName(Class.java:270) at org.apache.spark.serializer.JavaDeserializationStream$$anon$1.resolveClass(JavaSerializer.scala:37) at java.io.ObjectInputStream.readNonProxyDesc(ObjectInputStream.java:1612) at java.io.ObjectInputStream.readClassDesc(ObjectInputStream.java:1517) at java.io.ObjectInputStream.readOrdinaryObject(ObjectInputStream.java:1771) at java.io.ObjectInputStream.readObject0(ObjectInputStream.java:1350) at java.io.ObjectInputStream.defaultReadFields(ObjectInputStream.java:1990) at java.io.ObjectInputStream.readSerialData(ObjectInputStream.java:1915) at java.io.ObjectInputStream.readOrdinaryObject(ObjectInputStream.java:1798) at java.io.ObjectInputStream.readObject0(ObjectInputStream.java:1350) at java.io.ObjectInputStream.defaultReadFields(ObjectInputStream.java:1990) at java.io.ObjectInputStream.readSerialData(ObjectInputStream.java:1915) at java.io.ObjectInputStream.readOrdinaryObject(ObjectInputStream.java:1798) at java.io.ObjectInputStream.readObject0(ObjectInputStream.java:1350) at java.io.ObjectInputStream.readObject(ObjectInputStream.java:370) at scala.collection.immutable.$colon$colon.readObject(List.scala:362) 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:606) at java.io.ObjectStreamClass.invokeReadObject(ObjectStreamClass.java:1017) at java.io.ObjectInputStream.readSerialData(ObjectInputStream.java:1893) at java.io.ObjectInputStream.readOrdinaryObject(ObjectInputStream.java:1798) at java.io.ObjectInputStream.readObject0(ObjectInputStream.java:1350) at java.io.ObjectInputStream.defaultReadFields(ObjectInputStream.java:1990) at java.io.ObjectInputStream.readSerialData(ObjectInputStream.java:1915) at java.io.ObjectInputStream.readOrdinaryObject(ObjectInputStream.java:1798) at java.io.ObjectInputStream.readObject0(ObjectInputStream.java:1350) at java.io.ObjectInputStream.readObject(ObjectInputStream.java:370) at org.apache.spark.serializer.JavaDeserializationStream.readObject(JavaSerializer.scala:40) at org.apache.spark.scheduler.ResultTask$.deserializeInfo(ResultTask.scala:63) at org.apache.spark.scheduler.ResultTask.readExternal(ResultTask.scala:139) at java.io.ObjectInputStream.readExternalData(ObjectInputStream.java:1837) at java.io.ObjectInputStream.readOrdinaryObject(ObjectInputStream.java:1796) at java.io.ObjectInputStream.readObject0(ObjectInputStream.java:1350) at java.io.ObjectInputStream.readObject(ObjectInputStream.java:370) at org.apache.spark.serializer.JavaDeserializationStream.readObject(JavaSerializer.scala:40) at org.apache.spark.serializer.JavaSerializerInstance.deserialize(JavaSerializer.scala:62) at org.apache.spark.executor.Executor$TaskRunner$$anonfun$run$1.apply$mcV$sp(Executor.scala:195) at org.apache.spark.deploy.SparkHadoopUtil$$anon$1.run(SparkHadoopUtil.scala:42) at org.apache.spark.deploy.SparkHadoopUtil$$anon$1.run(SparkHadoopUtil.scala:41) at java.security.AccessController.doPrivileged(Native Method) at javax.security.auth.Subject.doAs(Subject.java:415) at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1548) at org.apache.spark.deploy.SparkHadoopUtil.runAsUser(SparkHadoopUtil.scala:41) at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:178) at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145) at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615) at java.lang.Thread.run(Thread.java:744) I also noted that, if I add "-Dspark.jars=$APP_JAR" to the variable *CONFIG_OPTS*, i.e., CONFIG_OPTS="-Dspark.master=$SPARK_MASTER Dspark.jars=$APP_JAR", the job will finish successfully and rdd can be written into HDFS. So, what does "java.lang.ClassNotFoundException: com.xt.scala.HBaseApp$$anonfun$testHBase$1" mean and why would it be thrown ? Thanks