Looks like the delegation token should be renewed. Mind trying the following ?
Thanks diff --git a/yarn/src/main/scala/org/apache/spark/scheduler/cluster/YarnClientSchedulerBackend.scala b/yarn/src/main/scala/org/apache/spark/scheduler/cluster/YarnClientSchedulerB index 20771f6..e3c4a5a 100644 --- a/yarn/src/main/scala/org/apache/spark/scheduler/cluster/YarnClientSchedulerBackend.scala +++ b/yarn/src/main/scala/org/apache/spark/scheduler/cluster/YarnClientSchedulerBackend.scala @@ -53,6 +53,12 @@ private[spark] class YarnClientSchedulerBackend( logDebug("ClientArguments called with: " + argsArrayBuf.mkString(" ")) val args = new ClientArguments(argsArrayBuf.toArray, conf) totalExpectedExecutors = args.numExecutors + // SPARK-8851: In yarn-client mode, the AM still does the credentials refresh. The driver + // reads the credentials from HDFS, just like the executors and updates its own credentials + // cache. + if (conf.contains("spark.yarn.credentials.file")) { + YarnSparkHadoopUtil.get.startExecutorDelegationTokenRenewer(conf) + } client = new Client(args, conf) appId = client.submitApplication() @@ -63,12 +69,6 @@ private[spark] class YarnClientSchedulerBackend( waitForApplication() - // SPARK-8851: In yarn-client mode, the AM still does the credentials refresh. The driver - // reads the credentials from HDFS, just like the executors and updates its own credentials - // cache. - if (conf.contains("spark.yarn.credentials.file")) { - YarnSparkHadoopUtil.get.startExecutorDelegationTokenRenewer(conf) - } monitorThread = asyncMonitorApplication() monitorThread.start() } On Wed, Nov 11, 2015 at 10:23 AM, mvle <m...@us.ibm.com> wrote: > Hi, > > I've deployed a Secure YARN 2.7.1 cluster with HDFS encryption and am > trying > to run the pyspark shell using Spark 1.5.1 > > pyspark shell works and I can run a sample code to calculate PI just fine. > However, when I try to stop the current context (e.g., sc.stop()) and then > create a new context (sc = SparkContext()), I get the error below. > > I have also seen errors such as: "token (HDFS_DELEGATION_TOKEN token 42 for > hadoop) can't be found in cache", > > Does anyone know if it is possible to stop and create a new Spark context > within a single JVM process (driver) and have that work when dealing with > delegation tokens from Secure YARN/HDFS? > > Thanks. > > 15/11/11 10:19:53 INFO yarn.Client: Setting up container launch context for > our AM > 15/11/11 10:19:53 INFO yarn.Client: Setting up the launch environment for > our AM container > 15/11/11 10:19:53 INFO yarn.Client: Credentials file set to: > credentials-37915c3e-1e90-44b9-add1-521598cea846 > 15/11/11 10:19:53 INFO yarn.YarnSparkHadoopUtil: getting token for > namenode: > > hdfs://test6-allwkrbsec-001:9000/user/hadoop/.sparkStaging/application_1446695132208_0042 > 15/11/11 10:19:53 ERROR spark.SparkContext: Error initializing > SparkContext. > org.apache.hadoop.ipc.RemoteException(java.io.IOException): Delegation > Token > can be issued only with kerberos or web authentication > at > > org.apache.hadoop.hdfs.server.namenode.FSNamesystem.getDelegationToken(FSNamesystem.java:6638) > at > > org.apache.hadoop.hdfs.server.namenode.NameNodeRpcServer.getDelegationToken(NameNodeRpcServer.java:563) > at > > org.apache.hadoop.hdfs.protocolPB.ClientNamenodeProtocolServerSideTranslatorPB.getDelegationToken(ClientNamenodeProtocolServerSideTranslatorPB.java:987) > at > > org.apache.hadoop.hdfs.protocol.proto.ClientNamenodeProtocolProtos$ClientNamenodeProtocol$2.callBlockingMethod(ClientNamenodeProtocolProtos.java) > at > > org.apache.hadoop.ipc.ProtobufRpcEngine$Server$ProtoBufRpcInvoker.call(ProtobufRpcEngine.java:616) > at org.apache.hadoop.ipc.RPC$Server.call(RPC.java:969) > at org.apache.hadoop.ipc.Server$Handler$1.run(Server.java:2049) > at org.apache.hadoop.ipc.Server$Handler$1.run(Server.java:2045) > at java.security.AccessController.doPrivileged(Native Method) > at javax.security.auth.Subject.doAs(Subject.java:415) > at > > org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1657) > at org.apache.hadoop.ipc.Server$Handler.run(Server.java:2043) > > at org.apache.hadoop.ipc.Client.call(Client.java:1476) > at org.apache.hadoop.ipc.Client.call(Client.java:1407) > at > > org.apache.hadoop.ipc.ProtobufRpcEngine$Invoker.invoke(ProtobufRpcEngine.java:229) > at com.sun.proxy.$Proxy12.getDelegationToken(Unknown Source) > at > > org.apache.hadoop.hdfs.protocolPB.ClientNamenodeProtocolTranslatorPB.getDelegationToken(ClientNamenodeProtocolTranslatorPB.java:933) > 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.hadoop.io.retry.RetryInvocationHandler.invokeMethod(RetryInvocationHandler.java:187) > at > > org.apache.hadoop.io.retry.RetryInvocationHandler.invoke(RetryInvocationHandler.java:102) > at com.sun.proxy.$Proxy13.getDelegationToken(Unknown Source) > at > org.apache.hadoop.hdfs.DFSClient.getDelegationToken(DFSClient.java:1044) > at > > org.apache.hadoop.hdfs.DistributedFileSystem.getDelegationToken(DistributedFileSystem.java:1543) > at > > org.apache.hadoop.fs.FileSystem.collectDelegationTokens(FileSystem.java:530) > at > org.apache.hadoop.fs.FileSystem.addDelegationTokens(FileSystem.java:508) > at > > org.apache.hadoop.hdfs.DistributedFileSystem.addDelegationTokens(DistributedFileSystem.java:2228) > at > > org.apache.spark.deploy.yarn.YarnSparkHadoopUtil$$anonfun$obtainTokensForNamenodes$1.apply(YarnSparkHadoopUtil.scala:126) > at > > org.apache.spark.deploy.yarn.YarnSparkHadoopUtil$$anonfun$obtainTokensForNamenodes$1.apply(YarnSparkHadoopUtil.scala:123) > at scala.collection.immutable.Set$Set1.foreach(Set.scala:74) > at > > org.apache.spark.deploy.yarn.YarnSparkHadoopUtil.obtainTokensForNamenodes(YarnSparkHadoopUtil.scala:123) > at > > org.apache.spark.deploy.yarn.Client.getTokenRenewalInterval(Client.scala:495) > at > org.apache.spark.deploy.yarn.Client.setupLaunchEnv(Client.scala:528) > at > > org.apache.spark.deploy.yarn.Client.createContainerLaunchContext(Client.scala:628) > at > org.apache.spark.deploy.yarn.Client.submitApplication(Client.scala:119) > at > > org.apache.spark.scheduler.cluster.YarnClientSchedulerBackend.start(YarnClientSchedulerBackend.scala:56) > at > > org.apache.spark.scheduler.TaskSchedulerImpl.start(TaskSchedulerImpl.scala:144) > at org.apache.spark.SparkContext.<init>(SparkContext.scala:523) > at > > org.apache.spark.api.java.JavaSparkContext.<init>(JavaSparkContext.scala:61) > at sun.reflect.NativeConstructorAccessorImpl.newInstance0(Native > Method) > at > > sun.reflect.NativeConstructorAccessorImpl.newInstance(NativeConstructorAccessorImpl.java:57) > at > > sun.reflect.DelegatingConstructorAccessorImpl.newInstance(DelegatingConstructorAccessorImpl.java:45) > at java.lang.reflect.Constructor.newInstance(Constructor.java:526) > at py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:234) > at > py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:379) > at py4j.Gateway.invoke(Gateway.java:214) > at > > py4j.commands.ConstructorCommand.invokeConstructor(ConstructorCommand.java:79) > at > py4j.commands.ConstructorCommand.execute(ConstructorCommand.java:68) > at py4j.GatewayConnection.run(GatewayConnection.java:207) > at java.lang.Thread.run(Thread.java:745) > > > > > > > > -- > View this message in context: > http://apache-spark-user-list.1001560.n3.nabble.com/Creating-new-Spark-context-when-running-in-Secure-YARN-fails-tp25361.html > Sent from the Apache Spark User List mailing list archive at Nabble.com. > > --------------------------------------------------------------------- > To unsubscribe, e-mail: user-unsubscr...@spark.apache.org > For additional commands, e-mail: user-h...@spark.apache.org > >