lework created ZEPPELIN-1998: -------------------------------- Summary: zeppelin spark on yarn mode, java.lang.ClassNotFoundException Key: ZEPPELIN-1998 URL: https://issues.apache.org/jira/browse/ZEPPELIN-1998 Project: Zeppelin Issue Type: Bug Components: Interpreters Affects Versions: 0.6.1 Environment: export MASTER=yarn-client export HADOOP_CONF_DIR=/etc/hadoop/conf export SPARK_HOME=/opt/cloudera/parcels/CDH-5.9.0-1.cdh5.9.0.p0.23/lib/spark export HBASE_HOME=/opt/cloudera/parcels/CDH-5.9.0-1.cdh5.9.0.p0.23/lib/hbase export HADOOP_HOME=/opt/cloudera/parcels/CDH-5.9.0-1.cdh5.9.0.p0.23/bin/../lib/hadoop
Reporter: lework Priority: Blocker version: cdh: 5.9.0 spark:1.6 zeppelin: 0.6.1 build option: mvn clean package -Pbuild-distr -Pyarn -Pspark-1.6 -Dspark.version=1.6.0 -Phadoop-2.6.0 -Dhadoop.version=2.6.0-cdh5.9.0 -Ppyspark -Psparkr -Dhbase.hbase.version=1.2.0 -Dhbase.hadoop.version=2.6.0 -Pvendor-repo -DskipTests zeppelin notebook: %spark sc.version sc.getConf.get("spark.home") System.getenv().get("PYTHONPATH") System.getenv().get("SPARK_HOME") val threshold = "book1" val products = Seq("book1", "book2", "book3", "book4") val rdd = sc.makeRDD(products,2) val result = rdd.filter{ p => p.equals(threshold) }.count() println("!!!!!!!!!!!!!!================result=" + result) output: res0: String = 1.6.0 res1: String = /opt/cloudera/parcels/CDH-5.9.0-1.cdh5.9.0.p0.23/lib/spark res2: String = /opt/cloudera/parcels/CDH-5.9.0-1.cdh5.9.0.p0.23/lib/spark/python/lib/py4j-0.9-src.zip:/opt/cloudera/parcels/CDH-5.9.0-1.cdh5.9.0.p0.23/lib/spark/python/: res3: String = /opt/cloudera/parcels/CDH-5.9.0-1.cdh5.9.0.p0.23/lib/spark threshold: String = book1 products: Seq[String] = List(book1, book2, book3, book4) rdd: org.apache.spark.rdd.RDD[String] = ParallelCollectionRDD[0] at makeRDD at <console>:31 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, node5, executor 1): java.lang.ClassNotFoundException: $iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$anonfun$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:274) at org.apache.spark.serializer.JavaDeserializationStream$$anon$1.resolveClass(JavaSerializer.scala:68) at java.io.ObjectInputStream.readNonProxyDesc(ObjectInputStream.java:1612) at java.io.ObjectInputStream.readClassDesc(ObjectInputStream.java:1517) at java.io.ObjectInputStream.readOrdinaryObject(ObjectInputStream.java:1771) at java.io.ObjectInputStream.readObject0(ObjectInputStream.java:1350) at java.io.ObjectInputStream.defaultReadFields(ObjectInputStream.java:1990) at java.io.ObjectInputStream.readSerialData(ObjectInputStream.java:1915) at java.io.ObjectInputStream.readOrdinaryObject(ObjectInputStream.java:1798) at java.io.ObjectInputStream.readObject0(ObjectInputStream.java:1350) at java.io.ObjectInputStream.defaultReadFields(ObjectInputStream.java:1990) at java.io.ObjectInputStream.readSerialData(ObjectInputStream.java:1915) at java.io.ObjectInputStream.readOrdinaryObject(ObjectInputStream.java:1798) at java.io.ObjectInputStream.readObject0(ObjectInputStream.java:1350) at java.io.ObjectInputStream.defaultReadFields(ObjectInputStream.java:1990) at java.io.ObjectInputStream.readSerialData(ObjectInputStream.java:1915) at java.io.ObjectInputStream.readOrdinaryObject(ObjectInputStream.java:1798) at java.io.ObjectInputStream.readObject0(ObjectInputStream.java:1350) at java.io.ObjectInputStream.readObject(ObjectInputStream.java:370) at org.apache.spark.serializer.JavaDeserializationStream.readObject(JavaSerializer.scala:76) at org.apache.spark.serializer.JavaSerializerInstance.deserialize(JavaSerializer.scala:115) at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:61) at org.apache.spark.scheduler.Task.run(Task.scala:89) at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:229) at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145) at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615) at java.lang.Thread.run(Thread.java:745) Driver stacktrace: at org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$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:1642) at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1601) at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1590) at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:48) at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:620) at org.apache.spark.SparkContext.runJob(SparkContext.scala:1844) at org.apache.spark.SparkContext.runJob(SparkContext.scala:1857) at org.apache.spark.SparkContext.runJob(SparkContext.scala:1870) at org.apache.spark.SparkContext.runJob(SparkContext.scala:1941) at org.apache.spark.rdd.RDD.count(RDD.scala:1157) at $iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:37) at $iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:42) at $iwC$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:44) at $iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:46) at $iwC$$iwC$$iwC$$iwC.<init>(<console>:48) at $iwC$$iwC$$iwC.<init>(<console>:50) at $iwC$$iwC.<init>(<console>:52) at $iwC.<init>(<console>:54) at <init>(<console>:56) at .<init>(<console>:60) at .<clinit>(<console>) at .<init>(<console>:7) at .<clinit>(<console>) at $print(<console>) 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 org.apache.spark.repl.SparkIMain$ReadEvalPrint.call(SparkIMain.scala:1045) at org.apache.spark.repl.SparkIMain$Request.loadAndRun(SparkIMain.scala:1326) at org.apache.spark.repl.SparkIMain.loadAndRunReq$1(SparkIMain.scala:821) at org.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:852) at org.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:800) at sun.reflect.GeneratedMethodAccessor10.invoke(Unknown Source) at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43) at java.lang.reflect.Method.invoke(Method.java:606) at org.apache.zeppelin.spark.Utils.invokeMethod(Utils.java:38) at org.apache.zeppelin.spark.SparkInterpreter.interpret(SparkInterpreter.java:878) at org.apache.zeppelin.spark.SparkInterpreter.interpretInput(SparkInterpreter.java:1093) at org.apache.zeppelin.spark.SparkInterpreter.interpret(SparkInterpreter.java:1036) at org.apache.zeppelin.spark.SparkInterpreter.interpret(SparkInterpreter.java:1029) at org.apache.zeppelin.interpreter.LazyOpenInterpreter.interpret(LazyOpenInterpreter.java:94) at org.apache.zeppelin.interpreter.remote.RemoteInterpreterServer$InterpretJob.jobRun(RemoteInterpreterServer.java:341) at org.apache.zeppelin.scheduler.Job.run(Job.java:176) at org.apache.zeppelin.scheduler.FIFOScheduler$1.run(FIFOScheduler.java:139) at java.util.concurrent.Executors$RunnableAdapter.call(Executors.java:471) at java.util.concurrent.FutureTask.run(FutureTask.java:262) at java.util.concurrent.ScheduledThreadPoolExecutor$ScheduledFutureTask.access$201(ScheduledThreadPoolExecutor.java:178) at java.util.concurrent.ScheduledThreadPoolExecutor$ScheduledFutureTask.run(ScheduledThreadPoolExecutor.java:292) 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:745) Caused by: java.lang.ClassNotFoundException: $iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$anonfun$1 at java.net.URLClassLoader$1.run(URLClassLoader.java:366) at java.net.URLClassLoader$1.run(URLClassLoader.java:355) at java.security.AccessController.doPrivileged(Native Method) at java.net.URLClassLoader.findClass(URLClassLoader.java:354) at java.lang.ClassLoader.loadClass(ClassLoader.java:425) at java.lang.ClassLoader.loadClass(ClassLoader.java:358) at java.lang.Class.forName0(Native Method) at java.lang.Class.forName(Class.java:274) at org.apache.spark.serializer.JavaDeserializationStream$$anon$1.resolveClass(JavaSerializer.scala:68) at java.io.ObjectInputStream.readNonProxyDesc(ObjectInputStream.java:1612) at java.io.ObjectInputStream.readClassDesc(ObjectInputStream.java:1517) at java.io.ObjectInputStream.readOrdinaryObject(ObjectInputStream.java:1771) at java.io.ObjectInputStream.readObject0(ObjectInputStream.java:1350) at java.io.ObjectInputStream.defaultReadFields(ObjectInputStream.java:1990) at java.io.ObjectInputStream.readSerialData(ObjectInputStream.java:1915) at j ava.io.ObjectInputStream.readOrdinaryObject(ObjectInputStream.java:1798) at java.io.ObjectInputStream.readObject0(ObjectInputStream.java:1350) at java.io.ObjectInputStream.defaultReadFields(ObjectInputStream.java:1990) at java.io.ObjectInputStream.readSerialData(ObjectInputStream.java:1915) at java.io.ObjectInputStream.readOrdinaryObject(ObjectInputStream.java:1798) at java.io.ObjectInputStream.readObject0(ObjectInputStream.java:1350) at java.io.ObjectInputStream.defaultReadFields(ObjectInputStream.java:1990) at java.io.ObjectInputStream.readSerialData(ObjectInputStream.java:1915) at java.io.ObjectInputStream.readOrdinaryObject(ObjectInputStream.java:1798) at java.io.ObjectInputStream.readObject0(ObjectInputStream.java:1350) at java.io.ObjectInputStream.readObject(ObjectInputStream.java:370) at org.apache.spark.serializer.JavaDeserializationStream.readObject(JavaSerializer.scala:76) at org.apache.spark.serializer.JavaSerializerInstance.deserialize(JavaSerializer.scala:115) at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:61) at org.apache.spark.scheduler.Task.run(Task.scala:89) at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:229) ... 3 more -- This message was sent by Atlassian JIRA (v6.3.4#6332)