[FLINK-5468] Restoring from a semi async rocksdb statebackend (1.1) to 1.2 fails with ClassNotFoundException

• Type: Bug
• Status: Closed
• Priority: Major
• Resolution: Fixed
• Affects Version/s: 1.2.0
• Fix Version/s: 1.2.0, 1.3.0
• Component/s: Runtime / State Backends
• Assignee: Stefan Richter
• Reporter: Robert Metzger
• Created: 12/Jan/17 11:36
• Updated: 20/Jan/17 15:11
• Resolved: 20/Jan/17 15:11

Description

I think we should catch this exception and explain what's going on and how users can resolve the issue.

org.apache.flink.client.program.ProgramInvocationException: The program execution failed: Job execution failed
	at org.apache.flink.client.program.ClusterClient.run(ClusterClient.java:427)
	at org.apache.flink.yarn.YarnClusterClient.submitJob(YarnClusterClient.java:210)
	at org.apache.flink.client.program.ClusterClient.run(ClusterClient.java:400)
	at org.apache.flink.streaming.api.environment.StreamContextEnvironment.execute(StreamContextEnvironment.java:66)
	at com.dataartisans.eventwindow.Generator.main(Generator.java:60)
	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.flink.client.program.PackagedProgram.callMainMethod(PackagedProgram.java:528)
	at org.apache.flink.client.program.PackagedProgram.invokeInteractiveModeForExecution(PackagedProgram.java:419)
	at org.apache.flink.client.program.ClusterClient.run(ClusterClient.java:339)
	at org.apache.flink.client.CliFrontend.executeProgram(CliFrontend.java:831)
	at org.apache.flink.client.CliFrontend.run(CliFrontend.java:256)
	at org.apache.flink.client.CliFrontend.parseParameters(CliFrontend.java:1073)
	at org.apache.flink.client.CliFrontend$2.call(CliFrontend.java:1120)
	at org.apache.flink.client.CliFrontend$2.call(CliFrontend.java:1117)
	at org.apache.flink.runtime.security.HadoopSecurityContext$1.run(HadoopSecurityContext.java:43)
	at java.security.AccessController.doPrivileged(Native Method)
	at javax.security.auth.Subject.doAs(Subject.java:415)
	at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1548)
	at org.apache.flink.runtime.security.HadoopSecurityContext.runSecured(HadoopSecurityContext.java:40)
	at org.apache.flink.client.CliFrontend.main(CliFrontend.java:1116)
Caused by: org.apache.flink.runtime.client.JobExecutionException: Job execution failed
	at org.apache.flink.runtime.client.JobClient.awaitJobResult(JobClient.java:328)
	at org.apache.flink.runtime.client.JobClient.submitJobAndWait(JobClient.java:382)
	at org.apache.flink.client.program.ClusterClient.run(ClusterClient.java:423)
	... 22 more
Caused by: java.io.IOException: java.lang.ClassNotFoundException: org.apache.flink.contrib.streaming.state.RocksDBStateBackend$FinalSemiAsyncSnapshot
	at org.apache.flink.migration.runtime.checkpoint.savepoint.SavepointV0Serializer.deserialize(SavepointV0Serializer.java:162)
	at org.apache.flink.migration.runtime.checkpoint.savepoint.SavepointV0Serializer.deserialize(SavepointV0Serializer.java:70)
	at org.apache.flink.runtime.checkpoint.savepoint.SavepointStore.loadSavepoint(SavepointStore.java:138)
	at org.apache.flink.runtime.checkpoint.savepoint.SavepointLoader.loadAndValidateSavepoint(SavepointLoader.java:64)
	at org.apache.flink.runtime.jobmanager.JobManager$$anonfun$org$apache$flink$runtime$jobmanager$JobManager$$submitJob$1.apply$mcV$sp(JobManager.scala:1348)
	at org.apache.flink.runtime.jobmanager.JobManager$$anonfun$org$apache$flink$runtime$jobmanager$JobManager$$submitJob$1.apply(JobManager.scala:1330)
	at org.apache.flink.runtime.jobmanager.JobManager$$anonfun$org$apache$flink$runtime$jobmanager$JobManager$$submitJob$1.apply(JobManager.scala:1330)
	at scala.concurrent.impl.Future$PromiseCompletingRunnable.liftedTree1$1(Future.scala:24)
	at scala.concurrent.impl.Future$PromiseCompletingRunnable.run(Future.scala:24)
	at akka.dispatch.TaskInvocation.run(AbstractDispatcher.scala:40)
	at akka.dispatch.ForkJoinExecutorConfigurator$AkkaForkJoinTask.exec(AbstractDispatcher.scala:397)
	at scala.concurrent.forkjoin.ForkJoinTask.doExec(ForkJoinTask.java:260)
	at scala.concurrent.forkjoin.ForkJoinPool$WorkQueue.runTask(ForkJoinPool.java:1339)
	at scala.concurrent.forkjoin.ForkJoinPool.runWorker(ForkJoinPool.java:1979)
	at scala.concurrent.forkjoin.ForkJoinWorkerThread.run(ForkJoinWorkerThread.java:107)
Caused by: java.lang.ClassNotFoundException: org.apache.flink.contrib.streaming.state.RocksDBStateBackend$FinalSemiAsyncSnapshot
	at java.net.URLClassLoader$1.run(URLClassLoader.java:366)
	at java.net.URLClassLoader$1.run(URLClassLoader.java:355)
	at java.security.AccessController.doPrivileged(Native Method)
	at java.net.URLClassLoader.findClass(URLClassLoader.java:354)
	at java.lang.ClassLoader.loadClass(ClassLoader.java:425)
	at java.lang.ClassLoader.loadClass(ClassLoader.java:358)
	at java.lang.Class.forName0(Native Method)
	at java.lang.Class.forName(Class.java:270)
	at org.apache.flink.util.InstantiationUtil$ClassLoaderObjectInputStream.resolveClass(InstantiationUtil.java:66)
	at org.apache.flink.migration.util.MigrationInstantiationUtil$ClassLoaderObjectInputStream.resolveClass(MigrationInstantiationUtil.java:66)
	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.readObject(ObjectInputStream.java:370)
	at java.util.HashMap.readObject(HashMap.java:1180)
	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.readArray(ObjectInputStream.java:1706)
	at java.io.ObjectInputStream.readObject0(ObjectInputStream.java:1344)
	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.flink.migration.util.MigrationInstantiationUtil.deserializeObject(MigrationInstantiationUtil.java:79)
	at org.apache.flink.migration.util.MigrationInstantiationUtil.deserializeObject(MigrationInstantiationUtil.java:71)
	at org.apache.flink.migration.util.SerializedValue.deserializeValue(SerializedValue.java:56)
	at org.apache.flink.migration.runtime.checkpoint.savepoint.SavepointV0Serializer.determineOperatorChainLength(SavepointV0Serializer.java:327)
	at org.apache.flink.migration.runtime.checkpoint.savepoint.SavepointV0Serializer.convertTaskState(SavepointV0Serializer.java:187)
	at org.apache.flink.migration.runtime.checkpoint.savepoint.SavepointV0Serializer.convertSavepoint(SavepointV0Serializer.java:174)
	at org.apache.flink.migration.runtime.checkpoint.savepoint.SavepointV0Serializer.deserialize(SavepointV0Serializer.java:160)
	... 14 more

Issue Links

• links to: GitHub Pull Request #3119