Hi
I am trying to use spark to write to a protected zone in hdfs, I am
able to create and list file using the hdfs client but when writing
via Spark I get this exception.
I could not find any mention of CryptoProtocolVersion in the spark doc.
Any idea what could have gone wrong?
spark (1.5.0), hadoop (2.6.1)
Thanks
org.apache.hadoop.ipc.RemoteException(org.apache.hadoop.hdfs.UnknownCryptoProtocolVersionException):
No crypto protocol versions provided by the client are supported.
Client provided: [] NameNode supports:
[CryptoProtocolVersion{description='Unknown', version=1,
unknownValue=null}, CryptoProtocolVersion{description='Encryption
zones', version=2, unknownValue=null}]
at
org.apache.hadoop.hdfs.server.namenode.FSNamesystem.chooseProtocolVersion(FSNamesystem.java:2468)
at
org.apache.hadoop.hdfs.server.namenode.FSNamesystem.startFileInt(FSNamesystem.java:2600)
at
org.apache.hadoop.hdfs.server.namenode.FSNamesystem.startFile(FSNamesystem.java:2520)
at
org.apache.hadoop.hdfs.server.namenode.NameNodeRpcServer.create(NameNodeRpcServer.java:579)
at
org.apache.hadoop.hdfs.protocolPB.ClientNamenodeProtocolServerSideTranslatorPB.create(ClientNamenodeProtocolServerSideTranslatorPB.java:394)
at
org.apache.hadoop.hdfs.protocol.proto.ClientNamenodeProtocolProtos$ClientNamenodeProtocol$2.callBlockingMethod(ClientNamenodeProtocolProtos.java)
at
org.apache.hadoop.ipc.ProtobufRpcEngine$Server$ProtoBufRpcInvoker.call(ProtobufRpcEngine.java:619)
at org.apache.hadoop.ipc.RPC$Server.call(RPC.java:962)
at org.apache.hadoop.ipc.Server$Handler$1.run(Server.java:2040)
at org.apache.hadoop.ipc.Server$Handler$1.run(Server.java:2036)
at java.security.AccessController.doPrivileged(Native Method)
at javax.security.auth.Subject.doAs(Subject.java:415)
at
org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1656)
at org.apache.hadoop.ipc.Server$Handler.run(Server.java:2034)
at org.apache.hadoop.ipc.Client.call(Client.java:1411)
at org.apache.hadoop.ipc.Client.call(Client.java:1364)
at
org.apache.hadoop.ipc.ProtobufRpcEngine$Invoker.invoke(ProtobufRpcEngine.java:206)
at com.sun.proxy.$Proxy13.create(Unknown Source)
at
org.apache.hadoop.hdfs.protocolPB.ClientNamenodeProtocolTranslatorPB.create(ClientNamenodeProtocolTranslatorPB.java:264)
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.$Proxy14.create(Unknown Source)
at
org.apache.hadoop.hdfs.DFSOutputStream.newStreamForCreate(DFSOutputStream.java:1612)
at org.apache.hadoop.hdfs.DFSClient.create(DFSClient.java:1488)
at org.apache.hadoop.hdfs.DFSClient.create(DFSClient.java:1413)
at
org.apache.hadoop.hdfs.DistributedFileSystem$6.doCall(DistributedFileSystem.java:387)
at
org.apache.hadoop.hdfs.DistributedFileSystem$6.doCall(DistributedFileSystem.java:383)
at
org.apache.hadoop.fs.FileSystemLinkResolver.resolve(FileSystemLinkResolver.java:81)
at
org.apache.hadoop.hdfs.DistributedFileSystem.create(DistributedFileSystem.java:383)
at
org.apache.hadoop.hdfs.DistributedFileSystem.create(DistributedFileSystem.java:327)
at org.apache.hadoop.fs.FileSystem.create(FileSystem.java:906)
at org.apache.hadoop.fs.FileSystem.create(FileSystem.java:799)
at
org.apache.hadoop.mapred.TextOutputFormat.getRecordWriter(TextOutputFormat.java:123)
at org.apache.spark.SparkHadoopWriter.open(SparkHadoopWriter.scala:91)
at
org.apache.spark.rdd.PairRDDFunctions$$anonfun$saveAsHadoopDataset$1$$anonfun$13.apply(PairRDDFunctions.scala:1104)
at
org.apache.spark.rdd.PairRDDFunctions$$anonfun$saveAsHadoopDataset$1$$anonfun$13.apply(PairRDDFunctions.scala:1095)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:66)
at org.apache.spark.scheduler.Task.run(Task.scala:88)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:214)
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)
