1
CDH 5.8.4 클러스터가 있습니다. 내가 clarnder 스파크 - hbase 커넥터 즉, HBaseContext를 사용하여 HBase에서 데이터를 읽고 쓰는 스파크 스트리밍 응용 프로그램을 실행 중입니다. 응용 프로그램을 시작할 때 spark-submit 스크립트에 주체와 kinit를 제공합니다. 7 일 후에 HBase 컨텍스트와 관련된 티켓 kerberos의 만료에 대한 오류와 함께 응용 프로그램이 충돌하는 것을보고 있습니다. 다음은 실행 프로그램 로그의 오류입니다.spark-hbase 커넥터가 만료 된 티켓 kerberos
ERROR executor.Executor: Exception in task 0.0 in stage 544265.0 (TID 1149098)
org.apache.hadoop.hbase.client.RetriesExhaustedException: Can't get the location
at org.apache.hadoop.hbase.client.RpcRetryingCallerWithReadReplicas.getRegionLocations(RpcRetryingCallerWithReadReplicas.java
:326)
at org.apache.hadoop.hbase.client.ScannerCallableWithReplicas.call(ScannerCallableWithReplicas.java:157)
at org.apache.hadoop.hbase.client.ScannerCallableWithReplicas.call(ScannerCallableWithReplicas.java:61)
at org.apache.hadoop.hbase.client.RpcRetryingCaller.callWithoutRetries(RpcRetryingCaller.java:200)
at org.apache.hadoop.hbase.client.ClientScanner.call(ClientScanner.java:320)
at org.apache.hadoop.hbase.client.ClientScanner.nextScanner(ClientScanner.java:295)
at org.apache.hadoop.hbase.client.ClientScanner.initializeScannerInConstruction(ClientScanner.java:160)
at org.apache.hadoop.hbase.client.ClientScanner.<init>(ClientScanner.java:155)
at org.apache.hadoop.hbase.client.HTable.getScanner(HTable.java:867)
at org.apache.hadoop.hbase.mapreduce.TableRecordReaderImpl.restart(TableRecordReaderImpl.java:91)
at org.apache.hadoop.hbase.mapreduce.TableRecordReaderImpl.initialize(TableRecordReaderImpl.java:169)
at org.apache.hadoop.hbase.mapreduce.TableRecordReader.initialize(TableRecordReader.java:134)
at org.apache.hadoop.hbase.mapreduce.TableInputFormatBase$1.initialize(TableInputFormatBase.java:211)
at org.apache.spark.rdd.NewHadoopRDD$$anon$1.<init>(NewHadoopRDD.scala:164)
at org.apache.spark.rdd.NewHadoopRDD.compute(NewHadoopRDD.scala:129)
at org.apache.hadoop.hbase.spark.NewHBaseRDD.compute(NewHBaseRDD.scala:34)
at org.apache.hadoop.hbase.spark.NewHBaseRDD.compute(NewHBaseRDD.scala:25)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:306)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:270)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:306)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:270)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:306)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:270)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:66)
at org.apache.spark.scheduler.Task.run(Task.scala:89)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:214)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)
at java.lang.Thread.run(Thread.java:745)
Caused by: org.apache.hadoop.security.token.SecretManager$InvalidToken: Token has expired
at sun.reflect.GeneratedConstructorAccessor58.newInstance(Unknown Source)
at sun.reflect.DelegatingConstructorAccessorImpl.newInstance(DelegatingConstructorAccessorImpl.java:45)
at java.lang.reflect.Constructor.newInstance(Constructor.java:423)
at org.apache.hadoop.ipc.RemoteException.instantiateException(RemoteException.java:106)
at org.apache.hadoop.ipc.RemoteException.unwrapRemoteException(RemoteException.java:95)
at org.apache.hadoop.hbase.protobuf.ProtobufUtil.getRemoteException(ProtobufUtil.java:327)
at org.apache.hadoop.hbase.protobuf.ProtobufUtil.getRowOrBefore(ProtobufUtil.java:1593)
at org.apache.hadoop.hbase.client.ConnectionManager$HConnectionImplementation.locateRegionInMeta(ConnectionManager.java:1398)
at org.apache.hadoop.hbase.client.ConnectionManager$HConnectionImplementation.locateRegion(ConnectionManager.java:1199)
at org.apache.hadoop.hbase.client.RpcRetryingCallerWithReadReplicas.getRegionLocations(RpcRetryingCallerWithReadReplicas.java:315)
... 30 more
Caused by: org.apache.hadoop.ipc.RemoteException(org.apache.hadoop.security.token.SecretManager$InvalidToken): Token has expired
at org.apache.hadoop.hbase.security.HBaseSaslRpcClient.readStatus(HBaseSaslRpcClient.java:155)
at org.apache.hadoop.hbase.security.HBaseSaslRpcClient.saslConnect(HBaseSaslRpcClient.java:222)
at org.apache.hadoop.hbase.ipc.RpcClientImpl$Connection.setupSaslConnection(RpcClientImpl.java:617)
at org.apache.hadoop.hbase.ipc.RpcClientImpl$Connection.access$700(RpcClientImpl.java:162)
at org.apache.hadoop.hbase.ipc.RpcClientImpl$Connection$2.run(RpcClientImpl.java:743)
at org.apache.hadoop.hbase.ipc.RpcClientImpl$Connection$2.run(RpcClientImpl.java:740)
at java.security.AccessController.doPrivileged(Native Method)
at javax.security.auth.Subject.doAs(Subject.java:422)
at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1783)
at org.apache.hadoop.hbase.ipc.RpcClientImpl$Connection.setupIOstreams(RpcClientImpl.java:740)
at org.apache.hadoop.hbase.ipc.RpcClientImpl$Connection.writeRequest(RpcClientImpl.java:906)
at org.apache.hadoop.hbase.ipc.RpcClientImpl$Connection.tracedWriteRequest(RpcClientImpl.java:873)
at org.apache.hadoop.hbase.ipc.RpcClientImpl.call(RpcClientImpl.java:1242)
at org.apache.hadoop.hbase.ipc.AbstractRpcClient.callBlockingMethod(AbstractRpcClient.java:227)
at org.apache.hadoop.hbase.ipc.AbstractRpcClient$BlockingRpcChannelImplementation.callBlockingMethod(AbstractRpcClient.java:336)
at org.apache.hadoop.hbase.protobuf.generated.ClientProtos$ClientService$BlockingStub.get(ClientProtos.java:34070)
at org.apache.hadoop.hbase.protobuf.ProtobufUtil.getRowOrBefore(ProtobufUtil.java:1589)
이 문제를 해결하는 방법을 아는 사람이 있습니까? 미리 감사드립니다. Beniamino
'spark-submit'을 실행할 때'--principal'과'--keytab' 옵션을 사용 했습니까? – MaxU
예. 실행기 캐시의 티켓이 만료 될 때마다 7 일마다 오류가 나타납니다. –
덤프를 포맷하여 '다소 읽을 수 있음'으로 지정하십시오. 비슷한 주제로 Chris Nauroth (HortonWorks, HBase 커미터)의 대답을 찾으십시오. –