Re: 1.12.0版本启动异常 on yarn per job方式

2021-01-19 文章 Xintong Song 
检查一下你的作业 jar 包里是否把 hadoop 依赖也打进去了。一般情况下 hadoop 依赖应该设成 provided，如果作业确实有需要用到和
yarn 集群不同版本的 hadoop 依赖，需要 shade。

Thank you~
Xintong Song



Thank you~

Xintong Song



On Tue, Jan 19, 2021 at 3:31 PM guanyq  wrote:

> 看错误是与hadoop-common-2.7.4.jar冲突,但是不知道如何解决。
> help
> 2021-01-1915:12:47,922ERRORorg.apache.flink.runtime.resourcemanager.active.ActiveResourceManager
> [] - Fatal error occurred in ResourceManager.
> org.apache.flink.runtime.resourcemanager.exceptions.ResourceManagerException:
> Could not start the ResourceManager akka.tcp://flink@dn138.hadoop.unicom
> :45554/user/rpc/resourcemanager_0
> at
> org.apache.flink.runtime.resourcemanager.ResourceManager.onStart(ResourceManager.java:220)
> ~[flink-dist_2.12-1.12.0.jar:1.12.0]
> at
> org.apache.flink.runtime.rpc.RpcEndpoint.internalCallOnStart(RpcEndpoint.java:183)
> ~[flink-dist_2.12-1.12.0.jar:1.12.0]
> at
> org.apache.flink.runtime.rpc.akka.AkkaRpcActor$StoppedState.start(AkkaRpcActor.java:551)
> ~[flink-dist_2.12-1.12.0.jar:1.12.0]
> at
> org.apache.flink.runtime.rpc.akka.AkkaRpcActor.handleControlMessage(AkkaRpcActor.java:172)
> ~[flink-dist_2.12-1.12.0.jar:1.12.0]
> at akka.japi.pf.UnitCaseStatement.apply(CaseStatements.scala:26)
> [flink-dist_2.12-1.12.0.jar:1.12.0]
> at akka.japi.pf.UnitCaseStatement.apply(CaseStatements.scala:21)
> [flink-dist_2.12-1.12.0.jar:1.12.0]
> at scala.PartialFunction.applyOrElse(PartialFunction.scala:123)
> [flink-dist_2.12-1.12.0.jar:1.12.0]
> at scala.PartialFunction.applyOrElse$(PartialFunction.scala:122)
> [flink-dist_2.12-1.12.0.jar:1.12.0]
> at akka.japi.pf.UnitCaseStatement.applyOrElse(CaseStatements.scala:21)
> [flink-dist_2.12-1.12.0.jar:1.12.0]
> at scala.PartialFunction$OrElse.applyOrElse(PartialFunction.scala:171)
> [flink-dist_2.12-1.12.0.jar:1.12.0]
> at scala.PartialFunction$OrElse.applyOrElse(PartialFunction.scala:172)
> [flink-dist_2.12-1.12.0.jar:1.12.0]
> at akka.actor.Actor.aroundReceive(Actor.scala:517)
> [flink-dist_2.12-1.12.0.jar:1.12.0]
> at akka.actor.Actor.aroundReceive$(Actor.scala:515)
> [flink-dist_2.12-1.12.0.jar:1.12.0]
> at akka.actor.AbstractActor.aroundReceive(AbstractActor.scala:225)
> [flink-dist_2.12-1.12.0.jar:1.12.0]
> at akka.actor.ActorCell.receiveMessage(ActorCell.scala:592)
> [flink-dist_2.12-1.12.0.jar:1.12.0]
> at akka.actor.ActorCell.invoke(ActorCell.scala:561)
> [flink-dist_2.12-1.12.0.jar:1.12.0]
> at akka.dispatch.Mailbox.processMailbox(Mailbox.scala:258)
> [flink-dist_2.12-1.12.0.jar:1.12.0]
> at akka.dispatch.Mailbox.run(Mailbox.scala:225)
> [flink-dist_2.12-1.12.0.jar:1.12.0]
> at akka.dispatch.Mailbox.exec(Mailbox.scala:235)
> [flink-dist_2.12-1.12.0.jar:1.12.0]
> at akka.dispatch.forkjoin.ForkJoinTask.doExec(ForkJoinTask.java:260)
> [flink-dist_2.12-1.12.0.jar:1.12.0]
> at
> akka.dispatch.forkjoin.ForkJoinPool$WorkQueue.runTask(ForkJoinPool.java:1339)
> [flink-dist_2.12-1.12.0.jar:1.12.0]
> at akka.dispatch.forkjoin.ForkJoinPool.runWorker(ForkJoinPool.java:1979)
> [flink-dist_2.12-1.12.0.jar:1.12.0]
> at
> akka.dispatch.forkjoin.ForkJoinWorkerThread.run(ForkJoinWorkerThread.java:107)
> [flink-dist_2.12-1.12.0.jar:1.12.0]
> Caused by: java.lang.NoSuchMethodError:
> org.apache.hadoop.io.retry.RetryPolicies.retryForeverWithFixedSleep(JLjava/util/concurrent/TimeUnit;)Lorg/apache/hadoop/io/retry/RetryPolicy;
> at
> org.apache.hadoop.yarn.client.RMProxy.createRetryPolicy(RMProxy.java:280)
> ~[hadoop-yarn-common-2.7.3.2.6.0.3-8.jar:?]
> at
> org.apache.hadoop.yarn.client.RMProxy.createRetryPolicy(RMProxy.java:211)
> ~[hadoop-yarn-common-2.7.3.2.6.0.3-8.jar:?]
> at
> org.apache.hadoop.yarn.client.RequestHedgingRMFailoverProxyProvider.createRetriableProxy(RequestHedgingRMFailoverProxyProvider.java:95)
> ~[hadoop-yarn-common-2.7.3.2.6.0.3-8.jar:?]
> at
> org.apache.hadoop.yarn.client.RequestHedgingRMFailoverProxyProvider.init(RequestHedgingRMFailoverProxyProvider.java:77)
> ~[hadoop-yarn-common-2.7.3.2.6.0.3-8.jar:?]
> at
> org.apache.hadoop.yarn.client.RMProxy.createRMFailoverProxyProvider(RMProxy.java:190)
> ~[hadoop-yarn-common-2.7.3.2.6.0.3-8.jar:?]
> at
> org.apache.hadoop.yarn.client.RMProxy.newProxyInstance(RMProxy.java:120)
> ~[hadoop-yarn-common-2.7.3.2.6.0.3-8.jar:?]
> at org.apache.hadoop.yarn.client.RMProxy.createRMProxy(RMProxy.java:94)
> ~[hadoop-yarn-common-2.7.3.2.6.0.3-8.jar:?]
> at
> org.apache.hadoop.yarn.client.ClientRMProxy.createRMProxy(ClientRMProxy.java:72)
> ~[hadoop-yarn-common-2.7.3.2.6.0.3-8.jar:?]
> at
> org.apache.hadoop.yarn.client.api.impl.AMRMClientImpl.serviceStart(AMRMClientImpl.java:186)
> ~[hadoop-yarn-client-2.7.3.2.6.0.3-8.jar:?]
> at
> org.apache.hadoop.service.AbstractService.start(AbstractService.java:193)
> ~[FlinkDataProcess.jar:?]
> at
> org.apache.hadoop.yarn.client.api.async.impl.AMRMClientAsyncImpl.serviceStart(AMRMClientAsyncImpl.java:93)
> ~[hadoop-yarn-client-2.7.3.2.6.0.3-8.jar:?]
> at
> org.apache.hadoop.service.AbstractService.start(AbstractService.java:193)
> ~[FlinkDataProcess.jar:?]
> at
> org.apache.flink.yarn.YarnRes

1.12.0版本启动异常 on yarn per job方式

2021-01-18 文章 guanyq 
看错误是与hadoop-common-2.7.4.jar冲突,但是不知道如何解决。
help
2021-01-1915:12:47,922ERRORorg.apache.flink.runtime.resourcemanager.active.ActiveResourceManager
 [] - Fatal error occurred in ResourceManager.
org.apache.flink.runtime.resourcemanager.exceptions.ResourceManagerException: 
Could not start the ResourceManager 
akka.tcp://flink@dn138.hadoop.unicom:45554/user/rpc/resourcemanager_0
at 
org.apache.flink.runtime.resourcemanager.ResourceManager.onStart(ResourceManager.java:220)
 ~[flink-dist_2.12-1.12.0.jar:1.12.0]
at 
org.apache.flink.runtime.rpc.RpcEndpoint.internalCallOnStart(RpcEndpoint.java:183)
 ~[flink-dist_2.12-1.12.0.jar:1.12.0]
at 
org.apache.flink.runtime.rpc.akka.AkkaRpcActor$StoppedState.start(AkkaRpcActor.java:551)
 ~[flink-dist_2.12-1.12.0.jar:1.12.0]
at 
org.apache.flink.runtime.rpc.akka.AkkaRpcActor.handleControlMessage(AkkaRpcActor.java:172)
 ~[flink-dist_2.12-1.12.0.jar:1.12.0]
at akka.japi.pf.UnitCaseStatement.apply(CaseStatements.scala:26) 
[flink-dist_2.12-1.12.0.jar:1.12.0]
at akka.japi.pf.UnitCaseStatement.apply(CaseStatements.scala:21) 
[flink-dist_2.12-1.12.0.jar:1.12.0]
at scala.PartialFunction.applyOrElse(PartialFunction.scala:123) 
[flink-dist_2.12-1.12.0.jar:1.12.0]
at scala.PartialFunction.applyOrElse$(PartialFunction.scala:122) 
[flink-dist_2.12-1.12.0.jar:1.12.0]
at akka.japi.pf.UnitCaseStatement.applyOrElse(CaseStatements.scala:21) 
[flink-dist_2.12-1.12.0.jar:1.12.0]
at scala.PartialFunction$OrElse.applyOrElse(PartialFunction.scala:171) 
[flink-dist_2.12-1.12.0.jar:1.12.0]
at scala.PartialFunction$OrElse.applyOrElse(PartialFunction.scala:172) 
[flink-dist_2.12-1.12.0.jar:1.12.0]
at akka.actor.Actor.aroundReceive(Actor.scala:517) 
[flink-dist_2.12-1.12.0.jar:1.12.0]
at akka.actor.Actor.aroundReceive$(Actor.scala:515) 
[flink-dist_2.12-1.12.0.jar:1.12.0]
at akka.actor.AbstractActor.aroundReceive(AbstractActor.scala:225) 
[flink-dist_2.12-1.12.0.jar:1.12.0]
at akka.actor.ActorCell.receiveMessage(ActorCell.scala:592) 
[flink-dist_2.12-1.12.0.jar:1.12.0]
at akka.actor.ActorCell.invoke(ActorCell.scala:561) 
[flink-dist_2.12-1.12.0.jar:1.12.0]
at akka.dispatch.Mailbox.processMailbox(Mailbox.scala:258) 
[flink-dist_2.12-1.12.0.jar:1.12.0]
at akka.dispatch.Mailbox.run(Mailbox.scala:225) 
[flink-dist_2.12-1.12.0.jar:1.12.0]
at akka.dispatch.Mailbox.exec(Mailbox.scala:235) 
[flink-dist_2.12-1.12.0.jar:1.12.0]
at akka.dispatch.forkjoin.ForkJoinTask.doExec(ForkJoinTask.java:260) 
[flink-dist_2.12-1.12.0.jar:1.12.0]
at 
akka.dispatch.forkjoin.ForkJoinPool$WorkQueue.runTask(ForkJoinPool.java:1339) 
[flink-dist_2.12-1.12.0.jar:1.12.0]
at akka.dispatch.forkjoin.ForkJoinPool.runWorker(ForkJoinPool.java:1979) 
[flink-dist_2.12-1.12.0.jar:1.12.0]
at 
akka.dispatch.forkjoin.ForkJoinWorkerThread.run(ForkJoinWorkerThread.java:107) 
[flink-dist_2.12-1.12.0.jar:1.12.0]
Caused by: java.lang.NoSuchMethodError: 
org.apache.hadoop.io.retry.RetryPolicies.retryForeverWithFixedSleep(JLjava/util/concurrent/TimeUnit;)Lorg/apache/hadoop/io/retry/RetryPolicy;
at org.apache.hadoop.yarn.client.RMProxy.createRetryPolicy(RMProxy.java:280) 
~[hadoop-yarn-common-2.7.3.2.6.0.3-8.jar:?]
at org.apache.hadoop.yarn.client.RMProxy.createRetryPolicy(RMProxy.java:211) 
~[hadoop-yarn-common-2.7.3.2.6.0.3-8.jar:?]
at 
org.apache.hadoop.yarn.client.RequestHedgingRMFailoverProxyProvider.createRetriableProxy(RequestHedgingRMFailoverProxyProvider.java:95)
 ~[hadoop-yarn-common-2.7.3.2.6.0.3-8.jar:?]
at 
org.apache.hadoop.yarn.client.RequestHedgingRMFailoverProxyProvider.init(RequestHedgingRMFailoverProxyProvider.java:77)
 ~[hadoop-yarn-common-2.7.3.2.6.0.3-8.jar:?]
at 
org.apache.hadoop.yarn.client.RMProxy.createRMFailoverProxyProvider(RMProxy.java:190)
 ~[hadoop-yarn-common-2.7.3.2.6.0.3-8.jar:?]
at org.apache.hadoop.yarn.client.RMProxy.newProxyInstance(RMProxy.java:120) 
~[hadoop-yarn-common-2.7.3.2.6.0.3-8.jar:?]
at org.apache.hadoop.yarn.client.RMProxy.createRMProxy(RMProxy.java:94) 
~[hadoop-yarn-common-2.7.3.2.6.0.3-8.jar:?]
at 
org.apache.hadoop.yarn.client.ClientRMProxy.createRMProxy(ClientRMProxy.java:72)
 ~[hadoop-yarn-common-2.7.3.2.6.0.3-8.jar:?]
at 
org.apache.hadoop.yarn.client.api.impl.AMRMClientImpl.serviceStart(AMRMClientImpl.java:186)
 ~[hadoop-yarn-client-2.7.3.2.6.0.3-8.jar:?]
at org.apache.hadoop.service.AbstractService.start(AbstractService.java:193) 
~[FlinkDataProcess.jar:?]
at 
org.apache.hadoop.yarn.client.api.async.impl.AMRMClientAsyncImpl.serviceStart(AMRMClientAsyncImpl.java:93)
 ~[hadoop-yarn-client-2.7.3.2.6.0.3-8.jar:?]
at org.apache.hadoop.service.AbstractService.start(AbstractService.java:193) 
~[FlinkDataProcess.jar:?]
at 
org.apache.flink.yarn.YarnResourceManagerDriver.initializeInternal(YarnResourceManagerDriver.java:159)
 ~[flink-dist_2.12-1.12.0.jar:1.12.0]
at 
org.apache.flink.runtime.resourcemanager.active.AbstractResourceManagerDriver.initialize(AbstractResourceManagerDriver.java:80)
 ~[flink-dist_2.12-1.12.0.jar:1.12.0]
at 
org.apache.flink.runtime.resourcemanager.active.ActiveResourceManager.in