[
https://issues.apache.org/jira/browse/HDDS-11360?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
JiangHua Zhu updated HDDS-11360:
--------------------------------
Description:
Found some NullPointerException in OMRatisHelper. Here are some cases.
om ha switch:
{code:java}
2024-08-23 13:41:35,785 [om22-server-thread545] INFO
org.apache.ratis.server.RaftServer$Division: om22@group-61C56C563FC9: receive
transferLeadership
TransferLeadershipRequest:client-CBC5546B4108->om22@group-61C56C563FC9, cid=3,
seq=null, RO, null
2024-08-23 13:41:35,786 [om22-server-thread545] INFO
org.apache.ratis.server.impl.TransferLeadership: om22@group-61C56C563FC9: start
transferring leadership to om21
2024-08-23 13:41:35,787 [om22-server-thread545] INFO
org.apache.ratis.server.impl.TransferLeadership: om22@group-61C56C563FC9:
sendStartLeaderElection to follower om21, lastEntry=(t:77, i:12154700362)
2024-08-23 13:41:35,787 [om22-server-thread545] INFO
org.apache.ratis.server.impl.TransferLeadership: om22@group-61C56C563FC9:
SUCCESS sent StartLeaderElection to transferee om21 immediately as it already
has up-to-date log
{code}
OMRatisHelper:
{code:java}
2024-08-23 13:41:35,869 [IPC Server handler 113 on default port 9862] WARN
org.apache.hadoop.ipc.Server: IPC Server handler 113 on default port 9862, call
Call#8836 Retry#0
org.apache.hadoop.ozone.om.protocol.OzoneManagerProtocol.submitRequest from
xxx.xxx.xxx.xxx:33796 / xx.xx.xx.xx:33796
java.lang.NullPointerException: Cannot invoke
"org.apache.ratis.protocol.Message.getContent()" because the return value of
"org.apache.ratis.protocol.RaftClientReply.getMessage()" is null
at
org.apache.hadoop.ozone.om.helpers.OMRatisHelper.getOMResponseFromRaftClientReply(OMRatisHelper.java:66)
at
org.apache.hadoop.ozone.om.ratis.OzoneManagerRatisServer.createOmResponseImpl(OzoneManagerRatisServer.java:524)
at
org.apache.hadoop.ozone.om.ratis.OzoneManagerRatisServer.lambda$1(OzoneManagerRatisServer.java:279)
at
org.apache.hadoop.util.MetricUtil.captureLatencyNs(MetricUtil.java:45)
at
org.apache.hadoop.ozone.om.ratis.OzoneManagerRatisServer.createOmResponse(OzoneManagerRatisServer.java:277)
at
org.apache.hadoop.ozone.om.ratis.OzoneManagerRatisServer.submitRequest(OzoneManagerRatisServer.java:257)
at
org.apache.hadoop.ozone.protocolPB.OzoneManagerProtocolServerSideTranslatorPB.submitRequestToRatis(OzoneManagerProtocolServerSideTranslatorPB.java:257)
at
org.apache.hadoop.ozone.protocolPB.OzoneManagerProtocolServerSideTranslatorPB.internalProcessRequest(OzoneManagerProtocolServerSideTranslatorPB.java:236)
at
org.apache.hadoop.ozone.protocolPB.OzoneManagerProtocolServerSideTranslatorPB.processRequest(OzoneManagerProtocolServerSideTranslatorPB.java:172)
at
org.apache.hadoop.hdds.server.OzoneProtocolMessageDispatcher.processRequest(OzoneProtocolMessageDispatcher.java:89)
at
org.apache.hadoop.ozone.protocolPB.OzoneManagerProtocolServerSideTranslatorPB.submitRequest(OzoneManagerProtocolServerSideTranslatorPB.java:163)
at
org.apache.hadoop.ozone.protocol.proto.OzoneManagerProtocolProtos$OzoneManagerService$2.callBlockingMethod(OzoneManagerProtocolProtos.java)
at
org.apache.hadoop.ipc.ProtobufRpcEngine$Server.processCall(ProtobufRpcEngine.java:484)
at
org.apache.hadoop.ipc.ProtobufRpcEngine2$Server$ProtoBufRpcInvoker.call(ProtobufRpcEngine2.java:595)
at
org.apache.hadoop.ipc.ProtobufRpcEngine2$Server$ProtoBufRpcInvoker.call(ProtobufRpcEngine2.java:573)
at org.apache.hadoop.ipc.RPC$Server.call(RPC.java:1227)
at org.apache.hadoop.ipc.Server$RpcCall.run(Server.java:1098)
at org.apache.hadoop.ipc.Server$RpcCall.run(Server.java:1021)
at
java.base/java.security.AccessController.doPrivileged(AccessController.java:712)
at java.base/javax.security.auth.Subject.doAs(Subject.java:439)
at
org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1953)
at org.apache.hadoop.ipc.Server$Handler.run(Server.java:3060)
{code}
s3gateway log:
{code:java}
2024-08-23 13:41:35,801 [qtp1396431506-4981] INFO
org.apache.hadoop.io.retry.RetryInvocationHandler:
com.google.protobuf.ServiceException:
org.apache.hadoop.ipc.RemoteException(java.lang.NullPointerException): Cannot
invoke "org.apache.ratis.protocol.Message.getContent()" because the return
value of "org.apache.ratis.protocol.RaftClientReply.getMessage()" is null
at
org.apache.hadoop.ozone.om.helpers.OMRatisHelper.getOMResponseFromRaftClientReply(OMRatisHelper.java:66)
at
org.apache.hadoop.ozone.om.ratis.OzoneManagerRatisServer.createOmResponseImpl(OzoneManagerRatisServer.java:524)
at
org.apache.hadoop.ozone.om.ratis.OzoneManagerRatisServer.lambda$1(OzoneManagerRatisServer.java:279)
at
org.apache.hadoop.util.MetricUtil.captureLatencyNs(MetricUtil.java:45)
at
org.apache.hadoop.ozone.om.ratis.OzoneManagerRatisServer.createOmResponse(OzoneManagerRatisServer.java:277)
at
org.apache.hadoop.ozone.om.ratis.OzoneManagerRatisServer.submitRequest(OzoneManagerRatisServer.java:257)
at
org.apache.hadoop.ozone.protocolPB.OzoneManagerProtocolServerSideTranslatorPB.submitRequestToRatis(OzoneManagerProtocolServerSideTranslatorPB.java:257)
at
org.apache.hadoop.ozone.protocolPB.OzoneManagerProtocolServerSideTranslatorPB.internalProcessRequest(OzoneManagerProtocolServerSideTranslatorPB.java:236)
at
org.apache.hadoop.ozone.protocolPB.OzoneManagerProtocolServerSideTranslatorPB.processRequest(OzoneManagerProtocolServerSideTranslatorPB.java:172)
at
org.apache.hadoop.hdds.server.OzoneProtocolMessageDispatcher.processRequest(OzoneProtocolMessageDispatcher.java:89)
at
org.apache.hadoop.ozone.protocolPB.OzoneManagerProtocolServerSideTranslatorPB.submitRequest(OzoneManagerProtocolServerSideTranslatorPB.java:163)
at
org.apache.hadoop.ozone.protocol.proto.OzoneManagerProtocolProtos$OzoneManagerService$2.callBlockingMethod(OzoneManagerProtocolProtos.java)
at
org.apache.hadoop.ipc.ProtobufRpcEngine$Server.processCall(ProtobufRpcEngine.java:484)
at
org.apache.hadoop.ipc.ProtobufRpcEngine2$Server$ProtoBufRpcInvoker.call(ProtobufRpcEngine2.java:595)
at
org.apache.hadoop.ipc.ProtobufRpcEngine2$Server$ProtoBufRpcInvoker.call(ProtobufRpcEngine2.java:573)
at org.apache.hadoop.ipc.RPC$Server.call(RPC.java:1227)
at org.apache.hadoop.ipc.Server$RpcCall.run(Server.java:1098)
at org.apache.hadoop.ipc.Server$RpcCall.run(Server.java:1021)
at
java.base/java.security.AccessController.doPrivileged(AccessController.java:712)
at java.base/javax.security.auth.Subject.doAs(Subject.java:439)
at
org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1953)
at org.apache.hadoop.ipc.Server$Handler.run(Server.java:3060)
, while invoking $Proxy124.submitRequest over
nodeId=om22,nodeAddress=xx.xx.xx.xx:9862. Trying to failover after sleeping for
2000ms. Current retry count: 0.
{code}
Looks like this is related to om ha switch.
> NPE in OMRatisHelper
> --------------------
>
> Key: HDDS-11360
> URL: https://issues.apache.org/jira/browse/HDDS-11360
> Project: Apache Ozone
> Issue Type: Improvement
> Components: OM
> Affects Versions: 1.4.0
> Reporter: JiangHua Zhu
> Priority: Major
>
> Found some NullPointerException in OMRatisHelper. Here are some cases.
> om ha switch:
> {code:java}
> 2024-08-23 13:41:35,785 [om22-server-thread545] INFO
> org.apache.ratis.server.RaftServer$Division: om22@group-61C56C563FC9: receive
> transferLeadership
> TransferLeadershipRequest:client-CBC5546B4108->om22@group-61C56C563FC9,
> cid=3, seq=null, RO, null
> 2024-08-23 13:41:35,786 [om22-server-thread545] INFO
> org.apache.ratis.server.impl.TransferLeadership: om22@group-61C56C563FC9:
> start transferring leadership to om21
> 2024-08-23 13:41:35,787 [om22-server-thread545] INFO
> org.apache.ratis.server.impl.TransferLeadership: om22@group-61C56C563FC9:
> sendStartLeaderElection to follower om21, lastEntry=(t:77, i:12154700362)
> 2024-08-23 13:41:35,787 [om22-server-thread545] INFO
> org.apache.ratis.server.impl.TransferLeadership: om22@group-61C56C563FC9:
> SUCCESS sent StartLeaderElection to transferee om21 immediately as it already
> has up-to-date log
> {code}
> OMRatisHelper:
> {code:java}
> 2024-08-23 13:41:35,869 [IPC Server handler 113 on default port 9862] WARN
> org.apache.hadoop.ipc.Server: IPC Server handler 113 on default port 9862,
> call Call#8836 Retry#0
> org.apache.hadoop.ozone.om.protocol.OzoneManagerProtocol.submitRequest from
> xxx.xxx.xxx.xxx:33796 / xx.xx.xx.xx:33796
> java.lang.NullPointerException: Cannot invoke
> "org.apache.ratis.protocol.Message.getContent()" because the return value of
> "org.apache.ratis.protocol.RaftClientReply.getMessage()" is null
> at
> org.apache.hadoop.ozone.om.helpers.OMRatisHelper.getOMResponseFromRaftClientReply(OMRatisHelper.java:66)
> at
> org.apache.hadoop.ozone.om.ratis.OzoneManagerRatisServer.createOmResponseImpl(OzoneManagerRatisServer.java:524)
> at
> org.apache.hadoop.ozone.om.ratis.OzoneManagerRatisServer.lambda$1(OzoneManagerRatisServer.java:279)
> at
> org.apache.hadoop.util.MetricUtil.captureLatencyNs(MetricUtil.java:45)
> at
> org.apache.hadoop.ozone.om.ratis.OzoneManagerRatisServer.createOmResponse(OzoneManagerRatisServer.java:277)
> at
> org.apache.hadoop.ozone.om.ratis.OzoneManagerRatisServer.submitRequest(OzoneManagerRatisServer.java:257)
> at
> org.apache.hadoop.ozone.protocolPB.OzoneManagerProtocolServerSideTranslatorPB.submitRequestToRatis(OzoneManagerProtocolServerSideTranslatorPB.java:257)
> at
> org.apache.hadoop.ozone.protocolPB.OzoneManagerProtocolServerSideTranslatorPB.internalProcessRequest(OzoneManagerProtocolServerSideTranslatorPB.java:236)
> at
> org.apache.hadoop.ozone.protocolPB.OzoneManagerProtocolServerSideTranslatorPB.processRequest(OzoneManagerProtocolServerSideTranslatorPB.java:172)
> at
> org.apache.hadoop.hdds.server.OzoneProtocolMessageDispatcher.processRequest(OzoneProtocolMessageDispatcher.java:89)
> at
> org.apache.hadoop.ozone.protocolPB.OzoneManagerProtocolServerSideTranslatorPB.submitRequest(OzoneManagerProtocolServerSideTranslatorPB.java:163)
> at
> org.apache.hadoop.ozone.protocol.proto.OzoneManagerProtocolProtos$OzoneManagerService$2.callBlockingMethod(OzoneManagerProtocolProtos.java)
> at
> org.apache.hadoop.ipc.ProtobufRpcEngine$Server.processCall(ProtobufRpcEngine.java:484)
> at
> org.apache.hadoop.ipc.ProtobufRpcEngine2$Server$ProtoBufRpcInvoker.call(ProtobufRpcEngine2.java:595)
> at
> org.apache.hadoop.ipc.ProtobufRpcEngine2$Server$ProtoBufRpcInvoker.call(ProtobufRpcEngine2.java:573)
> at org.apache.hadoop.ipc.RPC$Server.call(RPC.java:1227)
> at org.apache.hadoop.ipc.Server$RpcCall.run(Server.java:1098)
> at org.apache.hadoop.ipc.Server$RpcCall.run(Server.java:1021)
> at
> java.base/java.security.AccessController.doPrivileged(AccessController.java:712)
> at java.base/javax.security.auth.Subject.doAs(Subject.java:439)
> at
> org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1953)
> at org.apache.hadoop.ipc.Server$Handler.run(Server.java:3060)
> {code}
> s3gateway log:
> {code:java}
> 2024-08-23 13:41:35,801 [qtp1396431506-4981] INFO
> org.apache.hadoop.io.retry.RetryInvocationHandler:
> com.google.protobuf.ServiceException:
> org.apache.hadoop.ipc.RemoteException(java.lang.NullPointerException): Cannot
> invoke "org.apache.ratis.protocol.Message.getContent()" because the return
> value of "org.apache.ratis.protocol.RaftClientReply.getMessage()" is null
> at
> org.apache.hadoop.ozone.om.helpers.OMRatisHelper.getOMResponseFromRaftClientReply(OMRatisHelper.java:66)
> at
> org.apache.hadoop.ozone.om.ratis.OzoneManagerRatisServer.createOmResponseImpl(OzoneManagerRatisServer.java:524)
> at
> org.apache.hadoop.ozone.om.ratis.OzoneManagerRatisServer.lambda$1(OzoneManagerRatisServer.java:279)
> at
> org.apache.hadoop.util.MetricUtil.captureLatencyNs(MetricUtil.java:45)
> at
> org.apache.hadoop.ozone.om.ratis.OzoneManagerRatisServer.createOmResponse(OzoneManagerRatisServer.java:277)
> at
> org.apache.hadoop.ozone.om.ratis.OzoneManagerRatisServer.submitRequest(OzoneManagerRatisServer.java:257)
> at
> org.apache.hadoop.ozone.protocolPB.OzoneManagerProtocolServerSideTranslatorPB.submitRequestToRatis(OzoneManagerProtocolServerSideTranslatorPB.java:257)
> at
> org.apache.hadoop.ozone.protocolPB.OzoneManagerProtocolServerSideTranslatorPB.internalProcessRequest(OzoneManagerProtocolServerSideTranslatorPB.java:236)
> at
> org.apache.hadoop.ozone.protocolPB.OzoneManagerProtocolServerSideTranslatorPB.processRequest(OzoneManagerProtocolServerSideTranslatorPB.java:172)
> at
> org.apache.hadoop.hdds.server.OzoneProtocolMessageDispatcher.processRequest(OzoneProtocolMessageDispatcher.java:89)
> at
> org.apache.hadoop.ozone.protocolPB.OzoneManagerProtocolServerSideTranslatorPB.submitRequest(OzoneManagerProtocolServerSideTranslatorPB.java:163)
> at
> org.apache.hadoop.ozone.protocol.proto.OzoneManagerProtocolProtos$OzoneManagerService$2.callBlockingMethod(OzoneManagerProtocolProtos.java)
> at
> org.apache.hadoop.ipc.ProtobufRpcEngine$Server.processCall(ProtobufRpcEngine.java:484)
> at
> org.apache.hadoop.ipc.ProtobufRpcEngine2$Server$ProtoBufRpcInvoker.call(ProtobufRpcEngine2.java:595)
> at
> org.apache.hadoop.ipc.ProtobufRpcEngine2$Server$ProtoBufRpcInvoker.call(ProtobufRpcEngine2.java:573)
> at org.apache.hadoop.ipc.RPC$Server.call(RPC.java:1227)
> at org.apache.hadoop.ipc.Server$RpcCall.run(Server.java:1098)
> at org.apache.hadoop.ipc.Server$RpcCall.run(Server.java:1021)
> at
> java.base/java.security.AccessController.doPrivileged(AccessController.java:712)
> at java.base/javax.security.auth.Subject.doAs(Subject.java:439)
> at
> org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1953)
> at org.apache.hadoop.ipc.Server$Handler.run(Server.java:3060)
> , while invoking $Proxy124.submitRequest over
> nodeId=om22,nodeAddress=xx.xx.xx.xx:9862. Trying to failover after sleeping
> for 2000ms. Current retry count: 0.
> {code}
> Looks like this is related to om ha switch.
--
This message was sent by Atlassian Jira
(v8.20.10#820010)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]