[ https://issues.apache.org/jira/browse/AMBARI-18178?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]
Jayush Luniya updated AMBARI-18178: ----------------------------------- Labels: 240RMApproved (was: ) > yarn capacity scheduler queue issue > ----------------------------------- > > Key: AMBARI-18178 > URL: https://issues.apache.org/jira/browse/AMBARI-18178 > Project: Ambari > Issue Type: Bug > Components: ambari-views > Affects Versions: 2.4.0 > Reporter: Akhil PB > Assignee: Akhil PB > Priority: Blocker > Labels: 240RMApproved > Fix For: 2.4.0 > > Attachments: AMBARI-18178.001_branch-2.4.patch > > > Configure yarn queue using the yarn queue manager view. ( Below configuration > hints at how the queue was configured using UI and this was not set using the > configs under "YARN" service ) > {code} > yarn.scheduler.capacity.root.hive.capacity=80 > yarn.scheduler.capacity.root.hive.maximum-capacity=80 > yarn.scheduler.capacity.root.queues=default,hive > yarn.scheduler.capacity.root.hive.queues=microstrategy,tpcds,tpch > yarn.scheduler.capacity.root.default.capacity=20 > yarn.scheduler.capacity.root.hive.tpcds.capacity=25 > yarn.scheduler.capacity.root.hive.tpcds.maximum-capacity=25 > yarn.scheduler.capacity.root.hive.tpch.capacity=25 > yarn.scheduler.capacity.root.hive.tpch.maximum-capacity=25 > yarn.scheduler.capacity.root.hive.microstrategy.capacity=50 > yarn.scheduler.capacity.root.hive.microstrategy.maximum-capacity=50 > {code} > Below error is thrown while refreshing the queues. > {code} > esource_management.core.exceptions.Fail: Execution of '/usr/bin/kinit -kt > /etc/security/keytabs/rm.service.keytab > rm/ctr-e25-1471039652053-0001-01-000002.hwx.s...@hwx.vibgyor.com; export > HADOOP_LIBEXEC_DIR=/usr/hdp/current/hadoop-client/libexec && > /usr/hdp/current/hadoop-yarn-resourcemanager/bin/yarn rmadmin -refreshQueues' > returned 255. 16/08/16 05:01:39 INFO > client.ConfiguredRMFailoverProxyProvider: Failing over to rm2 > 16/08/16 05:01:39 WARN retry.RetryInvocationHandler: Exception while invoking > ResourceManagerAdministrationProtocolPBClientImpl.refreshQueues over rm2. Not > retrying because try once and fail. > org.apache.hadoop.yarn.exceptions.YarnException: java.io.IOException: Failed > to re-init queues > at > org.apache.hadoop.yarn.ipc.RPCUtil.getRemoteException(RPCUtil.java:38) > at > org.apache.hadoop.yarn.server.resourcemanager.AdminService.logAndWrapException(AdminService.java:762) > at > org.apache.hadoop.yarn.server.resourcemanager.AdminService.refreshQueues(AdminService.java:398) > at > org.apache.hadoop.yarn.server.api.impl.pb.service.ResourceManagerAdministrationProtocolPBServiceImpl.refreshQueues(ResourceManagerAdministrationProtocolPBServiceImpl.java:102) > at > org.apache.hadoop.yarn.proto.ResourceManagerAdministrationProtocol$ResourceManagerAdministrationProtocolService$2.callBlockingMethod(ResourceManagerAdministrationProtocol.java:239) > at > org.apache.hadoop.ipc.ProtobufRpcEngine$Server$ProtoBufRpcInvoker.call(ProtobufRpcEngine.java:640) > at org.apache.hadoop.ipc.RPC$Server.call(RPC.java:982) > at org.apache.hadoop.ipc.Server$Handler$1.run(Server.java:2313) > at org.apache.hadoop.ipc.Server$Handler$1.run(Server.java:2309) > at java.security.AccessController.doPrivileged(Native Method) > at javax.security.auth.Subject.doAs(Subject.java:422) > at > org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1724) > at org.apache.hadoop.ipc.Server$Handler.run(Server.java:2307) > Caused by: java.io.IOException: Failed to re-init queues > at > org.apache.hadoop.yarn.server.resourcemanager.scheduler.capacity.CapacityScheduler.reinitialize(CapacityScheduler.java:364) > at > org.apache.hadoop.yarn.server.resourcemanager.AdminService.refreshQueues(AdminService.java:388) > ... 10 more > Caused by: java.lang.NumberFormatException: For input string: "10000.0" > at > java.lang.NumberFormatException.forInputString(NumberFormatException.java:65) > at java.lang.Integer.parseInt(Integer.java:580) > at java.lang.Integer.parseInt(Integer.java:615) > at org.apache.hadoop.conf.Configuration.getInt(Configuration.java:1258) > at > org.apache.hadoop.yarn.server.resourcemanager.scheduler.capacity.CapacitySchedulerConfiguration.getMaximumSystemApplications(CapacitySchedulerConfiguration.java:289) > at > org.apache.hadoop.yarn.server.resourcemanager.scheduler.capacity.LeafQueue.setupQueueConfigs(LeafQueue.java:166) > at > org.apache.hadoop.yarn.server.resourcemanager.scheduler.capacity.LeafQueue.<init>(LeafQueue.java:139) > at > org.apache.hadoop.yarn.server.resourcemanager.scheduler.capacity.CapacityScheduler.parseQueue(CapacityScheduler.java:629) > at > org.apache.hadoop.yarn.server.resourcemanager.scheduler.capacity.CapacityScheduler.parseQueue(CapacityScheduler.java:649) > at > org.apache.hadoop.yarn.server.resourcemanager.scheduler.capacity.CapacityScheduler.reinitializeQueues(CapacityScheduler.java:513) > at > org.apache.hadoop.yarn.server.resourcemanager.scheduler.capacity.CapacityScheduler.reinitialize(CapacityScheduler.java:360) > ... 11 more > at sun.reflect.NativeConstructorAccessorImpl.newInstance0(Native Method) > at > sun.reflect.NativeConstructorAccessorImpl.newInstance(NativeConstructorAccessorImpl.java:62) > at > sun.reflect.DelegatingConstructorAccessorImpl.newInstance(DelegatingConstructorAccessorImpl.java:45) > at java.lang.reflect.Constructor.newInstance(Constructor.java:422) > at > org.apache.hadoop.yarn.ipc.RPCUtil.instantiateException(RPCUtil.java:53) > at > org.apache.hadoop.yarn.ipc.RPCUtil.unwrapAndThrowException(RPCUtil.java:101) > at > org.apache.hadoop.yarn.server.api.impl.pb.client.ResourceManagerAdministrationProtocolPBClientImpl.refreshQueues(ResourceManagerAdministrationProtocolPBClientImpl.java:123) > at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method) > at > sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62) > at > sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43) > at java.lang.reflect.Method.invoke(Method.java:497) > at > org.apache.hadoop.io.retry.RetryInvocationHandler.invokeMethod(RetryInvocationHandler.java:278) > at > org.apache.hadoop.io.retry.RetryInvocationHandler.invoke(RetryInvocationHandler.java:194) > at > org.apache.hadoop.io.retry.RetryInvocationHandler.invoke(RetryInvocationHandler.java:176) > at com.sun.proxy.$Proxy8.refreshQueues(Unknown Source) > at > org.apache.hadoop.yarn.client.cli.RMAdminCLI.refreshQueues(RMAdminCLI.java:290) > at org.apache.hadoop.yarn.client.cli.RMAdminCLI.run(RMAdminCLI.java:648) > at org.apache.hadoop.util.ToolRunner.run(ToolRunner.java:76) > at org.apache.hadoop.util.ToolRunner.run(ToolRunner.java:90) > at > org.apache.hadoop.yarn.client.cli.RMAdminCLI.main(RMAdminCLI.java:793) > Caused by: > org.apache.hadoop.ipc.RemoteException(org.apache.hadoop.yarn.exceptions.YarnException): > java.io.IOException: Failed to re-init queues > at > org.apache.hadoop.yarn.ipc.RPCUtil.getRemoteException(RPCUtil.java:38) > at > org.apache.hadoop.yarn.server.resourcemanager.AdminService.logAndWrapException(AdminService.java:762) > at > org.apache.hadoop.yarn.server.resourcemanager.AdminService.refreshQueues(AdminService.java:398) > at > org.apache.hadoop.yarn.server.api.impl.pb.service.ResourceManagerAdministrationProtocolPBServiceImpl.refreshQueues(ResourceManagerAdministrationProtocolPBServiceImpl.java:102) > at > org.apache.hadoop.yarn.proto.ResourceManagerAdministrationProtocol$ResourceManagerAdministrationProtocolService$2.callBlockingMethod(ResourceManagerAdministrationProtocol.java:239) > at > org.apache.hadoop.ipc.ProtobufRpcEngine$Server$ProtoBufRpcInvoker.call(ProtobufRpcEngine.java:640) > at org.apache.hadoop.ipc.RPC$Server.call(RPC.java:982) > at org.apache.hadoop.ipc.Server$Handler$1.run(Server.java:2313) > at org.apache.hadoop.ipc.Server$Handler$1.run(Server.java:2309) > at java.security.AccessController.doPrivileged(Native Method) > at javax.security.auth.Subject.doAs(Subject.java:422) > at > org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1724) > at org.apache.hadoop.ipc.Server$Handler.run(Server.java:2307) > Caused by: java.io.IOException: Failed to re-init queues > at > org.apache.hadoop.yarn.server.resourcemanager.scheduler.capacity.CapacityScheduler.reinitialize(CapacityScheduler.java:364) > at > org.apache.hadoop.yarn.server.resourcemanager.AdminService.refreshQueues(AdminService.java:388) > ... 10 more > Caused by: java.lang.NumberFormatException: For input string: "10000.0" > at > java.lang.NumberFormatException.forInputString(NumberFormatException.java:65) > at java.lang.Integer.parseInt(Integer.java:580) > at java.lang.Integer.parseInt(Integer.java:615) > at org.apache.hadoop.conf.Configuration.getInt(Configuration.java:1258) > at > org.apache.hadoop.yarn.server.resourcemanager.scheduler.capacity.CapacitySchedulerConfiguration.getMaximumSystemApplications(CapacitySchedulerConfiguration.java:289) > at > org.apache.hadoop.yarn.server.resourcemanager.scheduler.capacity.LeafQueue.setupQueueConfigs(LeafQueue.java:166) > at > org.apache.hadoop.yarn.server.resourcemanager.scheduler.capacity.LeafQueue.<init>(LeafQueue.java:139) > at > org.apache.hadoop.yarn.server.resourcemanager.scheduler.capacity.CapacityScheduler.parseQueue(CapacityScheduler.java:629) > at > org.apache.hadoop.yarn.server.resourcemanager.scheduler.capacity.CapacityScheduler.parseQueue(CapacityScheduler.java:649) > at > org.apache.hadoop.yarn.server.resourcemanager.scheduler.capacity.CapacityScheduler.reinitializeQueues(CapacityScheduler.java:513) > at > org.apache.hadoop.yarn.server.resourcemanager.scheduler.capacity.CapacityScheduler.reinitialize(CapacityScheduler.java:360) > ... 11 more > at org.apache.hadoop.ipc.Client.getRpcResponse(Client.java:1552) > at org.apache.hadoop.ipc.Client.call(Client.java:1496) > at org.apache.hadoop.ipc.Client.call(Client.java:1396) > at > org.apache.hadoop.ipc.ProtobufRpcEngine$Invoker.invoke(ProtobufRpcEngine.java:233) > at com.sun.proxy.$Proxy7.refreshQueues(Unknown Source) > at > org.apache.hadoop.yarn.server.api.impl.pb.client.ResourceManagerAdministrationProtocolPBClientImpl.refreshQueues(ResourceManagerAdministrationProtocolPBClientImpl.java:120) > ... 13 more > refreshQueues: java.io.IOException: Failed to re-init queues > at > org.apache.hadoop.yarn.ipc.RPCUtil.getRemoteException(RPCUtil.java:38) > at > org.apache.hadoop.yarn.server.resourcemanager.AdminService.logAndWrapException(AdminService.java:762) > at > org.apache.hadoop.yarn.server.resourcemanager.AdminService.refreshQueues(AdminService.java:398) > at > org.apache.hadoop.yarn.server.api.impl.pb.service.ResourceManagerAdministrationProtocolPBServiceImpl.refreshQueues(ResourceManagerAdministrationProtocolPBServiceImpl.java:102) > at > org.apache.hadoop.yarn.proto.ResourceManagerAdministrationProtocol$ResourceManagerAdministrationProtocolService$2.callBlockingMethod(ResourceManagerAdministrationProtocol.java:239) > at > org.apache.hadoop.ipc.ProtobufRpcEngine$Server$ProtoBufRpcInvoker.call(ProtobufRpcEngine.java:640) > at org.apache.hadoop.ipc.RPC$Server.call(RPC.java:982) > at org.apache.hadoop.ipc.Server$Handler$1.run(Server.java:2313) > at org.apache.hadoop.ipc.Server$Handler$1.run(Server.java:2309) > at java.security.AccessController.doPrivileged(Native Method) > at javax.security.auth.Subject.doAs(Subject.java:422) > at > org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1724) > at org.apache.hadoop.ipc.Server$Handler.run(Server.java:2307) > Caused by: java.io.IOException: Failed to re-init queues > at > org.apache.hadoop.yarn.server.resourcemanager.scheduler.capacity.CapacityScheduler.reinitialize(CapacityScheduler.java:364) > at > org.apache.hadoop.yarn.server.resourcemanager.AdminService.refreshQueues(AdminService.java:388) > ... 10 more > Caused by: java.lang.NumberFormatException: For input string: "10000.0" > at > java.lang.NumberFormatException.forInputString(NumberFormatException.java:65) > at java.lang.Integer.parseInt(Integer.java:580) > at java.lang.Integer.parseInt(Integer.java:615) > at org.apache.hadoop.conf.Configuration.getInt(Configuration.java:1258) > at > org.apache.hadoop.yarn.server.resourcemanager.scheduler.capacity.CapacitySchedulerConfiguration.getMaximumSystemApplications(CapacitySchedulerConfiguration.java:289) > at > org.apache.hadoop.yarn.server.resourcemanager.scheduler.capacity.LeafQueue.setupQueueConfigs(LeafQueue.java:166) > at > org.apache.hadoop.yarn.server.resourcemanager.scheduler.capacity.LeafQueue.<init>(LeafQueue.java:139) > at > org.apache.hadoop.yarn.server.resourcemanager.scheduler.capacity.CapacityScheduler.parseQueue(CapacityScheduler.java:629) > at > org.apache.hadoop.yarn.server.resourcemanager.scheduler.capacity.CapacityScheduler.parseQueue(CapacityScheduler.java:649) > at > org.apache.hadoop.yarn.server.resourcemanager.scheduler.capacity.CapacityScheduler.reinitializeQueues(CapacityScheduler.java:513) > at > org.apache.hadoop.yarn.server.resourcemanager.scheduler.capacity.CapacityScheduler.reinitialize(CapacityScheduler.java:360) > {code} -- This message was sent by Atlassian JIRA (v6.3.4#6332)