[
https://issues.apache.org/jira/browse/HDDS-2356?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16968978#comment-16968978
]
Li Cheng commented on HDDS-2356:
--------------------------------
[~bharat] My program won't abort, but I see some errors in s3g logs with
timeline matching. Not sure if it's related.
十一月 06, 2019 6:11:35 下午
org.apache.ratis.thirdparty.io.grpc.internal.ManagedChannelOrphanWrapper$ManagedChannelReference
cleanQueue
严重: *~*~*~ Channel ManagedChannelImpl\{logId=32225, target=9.134.51.232:9859}
was not shutdown properly!!! ~*~*~*
Make sure to call shutdown()/shutdownNow() and wait until awaitTermination()
returns true.
java.lang.RuntimeException: ManagedChannel allocation site
at
org.apache.ratis.thirdparty.io.grpc.internal.ManagedChannelOrphanWrapper$ManagedChannelReference.<init>(ManagedChannelOrphanWrapper.java:103)
at
org.apache.ratis.thirdparty.io.grpc.internal.ManagedChannelOrphanWrapper.<init>(ManagedChannelOrphanWrapper.java:53)
at
org.apache.ratis.thirdparty.io.grpc.internal.ManagedChannelOrphanWrapper.<init>(ManagedChannelOrphanWrapper.java:44)
at
org.apache.ratis.thirdparty.io.grpc.internal.AbstractManagedChannelImplBuilder.build(AbstractManagedChannelImplBuilder.java:411)
at
org.apache.hadoop.hdds.scm.XceiverClientGrpc.connectToDatanode(XceiverClientGrpc.java:192)
at
org.apache.hadoop.hdds.scm.XceiverClientGrpc.connect(XceiverClientGrpc.java:139)
at
org.apache.hadoop.hdds.scm.XceiverClientManager$2.call(XceiverClientManager.java:242)
at
org.apache.hadoop.hdds.scm.XceiverClientManager$2.call(XceiverClientManager.java:226)
at
com.google.common.cache.LocalCache$LocalManualCache$1.load(LocalCache.java:4767)
at
com.google.common.cache.LocalCache$LoadingValueReference.loadFuture(LocalCache.java:3568)
at com.google.common.cache.LocalCache$Segment.loadSync(LocalCache.java:2350)
at
com.google.common.cache.LocalCache$Segment.lockedGetOrLoad(LocalCache.java:2313)
at com.google.common.cache.LocalCache$Segment.get(LocalCache.java:2228)
at com.google.common.cache.LocalCache.get(LocalCache.java:3965)
at
com.google.common.cache.LocalCache$LocalManualCache.get(LocalCache.java:4764)
at
org.apache.hadoop.hdds.scm.XceiverClientManager.getClient(XceiverClientManager.java:226)
at
org.apache.hadoop.hdds.scm.XceiverClientManager.acquireClient(XceiverClientManager.java:172)
at
org.apache.hadoop.hdds.scm.XceiverClientManager.acquireClientForReadData(XceiverClientManager.java:162)
at
org.apache.hadoop.hdds.scm.storage.BlockInputStream.getChunkInfos(BlockInputStream.java:154)
at
org.apache.hadoop.hdds.scm.storage.BlockInputStream.initialize(BlockInputStream.java:118)
at
org.apache.hadoop.hdds.scm.storage.BlockInputStream.read(BlockInputStream.java:224)
at
org.apache.hadoop.ozone.client.io.KeyInputStream.read(KeyInputStream.java:173)
at
org.apache.hadoop.ozone.client.io.OzoneInputStream.read(OzoneInputStream.java:47)
at java.io.InputStream.read(InputStream.java:101)
at org.apache.commons.io.IOUtils.copyLarge(IOUtils.java:2146)
at org.apache.commons.io.IOUtils.copy(IOUtils.java:2102)
at org.apache.commons.io.IOUtils.copyLarge(IOUtils.java:2123)
at org.apache.commons.io.IOUtils.copy(IOUtils.java:2078)
at
org.apache.hadoop.ozone.s3.endpoint.ObjectEndpoint.lambda$get$0(ObjectEndpoint.java:252)
at
org.glassfish.jersey.message.internal.StreamingOutputProvider.writeTo(StreamingOutputProvider.java:79)
at
org.glassfish.jersey.message.internal.StreamingOutputProvider.writeTo(StreamingOutputProvider.java:61)
at
org.glassfish.jersey.message.internal.WriterInterceptorExecutor$TerminalWriterInterceptor.invokeWriteTo(WriterInterceptorExecutor.java:266)
at
org.glassfish.jersey.message.internal.WriterInterceptorExecutor$TerminalWriterInterceptor.aroundWriteTo(WriterInterceptorExecutor.java:251)
at
org.glassfish.jersey.message.internal.WriterInterceptorExecutor.proceed(WriterInterceptorExecutor.java:163)
at
org.glassfish.jersey.server.internal.JsonWithPaddingInterceptor.aroundWriteTo(JsonWithPaddingInterceptor.java:109)
at
org.glassfish.jersey.message.internal.WriterInterceptorExecutor.proceed(WriterInterceptorExecutor.java:163)
at
org.glassfish.jersey.server.internal.MappableExceptionWrapperInterceptor.aroundWriteTo(MappableExceptionWrapperInterceptor.java:85)
at
org.glassfish.jersey.message.internal.WriterInterceptorExecutor.proceed(WriterInterceptorExecutor.java:163)
at
org.glassfish.jersey.message.internal.MessageBodyFactory.writeTo(MessageBodyFactory.java:1135)
at
org.glassfish.jersey.server.ServerRuntime$Responder.writeResponse(ServerRuntime.java:662)
at
org.glassfish.jersey.server.ServerRuntime$Responder.processResponse(ServerRuntime.java:395)
at
org.glassfish.jersey.server.ServerRuntime$Responder.process(ServerRuntime.java:385)
at org.glassfish.jersey.server.ServerRuntime$1.run(ServerRuntime.java:280)
at org.glassfish.jersey.internal.Errors$1.call(Errors.java:272)
at org.glassfish.jersey.internal.Errors$1.call(Errors.java:268)
at org.glassfish.jersey.internal.Errors.process(Errors.java:316)
at org.glassfish.jersey.internal.Errors.process(Errors.java:298)
at org.glassfish.jersey.internal.Errors.process(Errors.java:268)
at
org.glassfish.jersey.process.internal.RequestScope.runInScope(RequestScope.java:289)
at org.glassfish.jersey.server.ServerRuntime.process(ServerRuntime.java:256)
at
org.glassfish.jersey.server.ApplicationHandler.handle(ApplicationHandler.java:703)
at org.glassfish.jersey.servlet.WebComponent.serviceImpl(WebComponent.java:416)
at org.glassfish.jersey.servlet.WebComponent.service(WebComponent.java:370)
at
org.glassfish.jersey.servlet.ServletContainer.service(ServletContainer.java:389)
at
org.glassfish.jersey.servlet.ServletContainer.service(ServletContainer.java:342)
at
org.glassfish.jersey.servlet.ServletContainer.service(ServletContainer.java:229)
at org.eclipse.jetty.servlet.ServletHolder.handle(ServletHolder.java:840)
at
org.eclipse.jetty.servlet.ServletHandler$CachedChain.doFilter(ServletHandler.java:1780)
at
org.apache.hadoop.http.HttpServer2$QuotingInputFilter.doFilter(HttpServer2.java:1609)
at
org.eclipse.jetty.servlet.ServletHandler$CachedChain.doFilter(ServletHandler.java:1767)
at org.apache.hadoop.http.NoCacheFilter.doFilter(NoCacheFilter.java:45)
at
org.eclipse.jetty.servlet.ServletHandler$CachedChain.doFilter(ServletHandler.java:1767)
at org.eclipse.jetty.servlet.ServletHandler.doHandle(ServletHandler.java:583)
at
org.eclipse.jetty.server.handler.ScopedHandler.handle(ScopedHandler.java:143)
at org.eclipse.jetty.security.SecurityHandler.handle(SecurityHandler.java:548)
at
org.eclipse.jetty.server.session.SessionHandler.doHandle(SessionHandler.java:226)
at
org.eclipse.jetty.server.handler.ContextHandler.doHandle(ContextHandler.java:1180)
at org.eclipse.jetty.servlet.ServletHandler.doScope(ServletHandler.java:513)
at
org.eclipse.jetty.server.session.SessionHandler.doScope(SessionHandler.java:185)
at
org.eclipse.jetty.server.handler.ContextHandler.doScope(ContextHandler.java:1112)
at
org.eclipse.jetty.server.handler.ScopedHandler.handle(ScopedHandler.java:141)
at
org.eclipse.jetty.server.handler.HandlerCollection.handle(HandlerCollection.java:119)
at
org.eclipse.jetty.server.handler.HandlerWrapper.handle(HandlerWrapper.java:134)
at org.eclipse.jetty.server.Server.handle(Server.java:539)
at org.eclipse.jetty.server.HttpChannel.handle(HttpChannel.java:333)
at org.eclipse.jetty.server.HttpConnection.onFillable(HttpConnection.java:251)
at
org.eclipse.jetty.io.AbstractConnection$ReadCallback.succeeded(AbstractConnection.java:283)
at org.eclipse.jetty.io.FillInterest.fillable(FillInterest.java:108)
at
org.eclipse.jetty.io.SelectChannelEndPoint$2.run(SelectChannelEndPoint.java:93)
at
org.eclipse.jetty.util.thread.strategy.ExecuteProduceConsume.executeProduceConsume(ExecuteProduceConsume.java:303)
at
org.eclipse.jetty.util.thread.strategy.ExecuteProduceConsume.produceConsume(ExecuteProduceConsume.java:148)
at
org.eclipse.jetty.util.thread.strategy.ExecuteProduceConsume.run(ExecuteProduceConsume.java:136)
at
org.eclipse.jetty.util.thread.QueuedThreadPool.runJob(QueuedThreadPool.java:671)
at
org.eclipse.jetty.util.thread.QueuedThreadPool$2.run(QueuedThreadPool.java:589)
at java.lang.Thread.run(Thread.java:745)
> Multipart upload report errors while writing to ozone Ratis pipeline
> --------------------------------------------------------------------
>
> Key: HDDS-2356
> URL: https://issues.apache.org/jira/browse/HDDS-2356
> Project: Hadoop Distributed Data Store
> Issue Type: Bug
> Components: Ozone Manager
> Affects Versions: 0.4.1
> Environment: Env: 4 VMs in total: 3 Datanodes on 3 VMs, 1 OM & 1 SCM
> on a separate VM
> Reporter: Li Cheng
> Assignee: Bharat Viswanadham
> Priority: Blocker
> Fix For: 0.5.0
>
> Attachments: hs_err_pid9340.log, image-2019-10-31-18-56-56-177.png
>
>
> Env: 4 VMs in total: 3 Datanodes on 3 VMs, 1 OM & 1 SCM on a separate VM, say
> it's VM0.
> I use goofys as a fuse and enable ozone S3 gateway to mount ozone to a path
> on VM0, while reading data from VM0 local disk and write to mount path. The
> dataset has various sizes of files from 0 byte to GB-level and it has a
> number of ~50,000 files.
> The writing is slow (1GB for ~10 mins) and it stops after around 4GB. As I
> look at hadoop-root-om-VM_50_210_centos.out log, I see OM throwing errors
> related with Multipart upload. This error eventually causes the writing to
> terminate and OM to be closed.
>
> Updated on 11/06/2019:
> See new multipart upload error NO_SUCH_MULTIPART_UPLOAD_ERROR and full logs
> are in the attachment.
> 2019-11-05 18:12:37,766 ERROR
> org.apache.hadoop.ozone.om.request.s3.multipart.S3MultipartUploadCommitPartRequest:
> MultipartUpload Commit is failed for Key:./2
> 0191012/plc_1570863541668_9278 in Volume/Bucket
> s325d55ad283aa400af464c76d713c07ad/ozone-test
> NO_SUCH_MULTIPART_UPLOAD_ERROR
> org.apache.hadoop.ozone.om.exceptions.OMException: No such Multipart upload
> is with specified uploadId fcda8608-b431-48b7-8386-
> 0a332f1a709a-103084683261641950
> at
> org.apache.hadoop.ozone.om.request.s3.multipart.S3MultipartUploadCommitPartRequest.validateAndUpdateCache(S3MultipartUploadCommitPartRequest.java:1
> 56)
> at
> org.apache.hadoop.ozone.protocolPB.OzoneManagerProtocolServerSideTranslatorPB.submitRequestDirectlyToOM(OzoneManagerProtocolServerSideTranslatorPB.
> java:217)
> at
> org.apache.hadoop.ozone.protocolPB.OzoneManagerProtocolServerSideTranslatorPB.processRequest(OzoneManagerProtocolServerSideTranslatorPB.java:132)
> at
> org.apache.hadoop.hdds.server.OzoneProtocolMessageDispatcher.processRequest(OzoneProtocolMessageDispatcher.java:72)
> at
> org.apache.hadoop.ozone.protocolPB.OzoneManagerProtocolServerSideTranslatorPB.submitRequest(OzoneManagerProtocolServerSideTranslatorPB.java:100)
> at
> org.apache.hadoop.ozone.protocol.proto.OzoneManagerProtocolProtos$OzoneManagerService$2.callBlockingMethod(OzoneManagerProtocolProtos.java)
> at
> org.apache.hadoop.ipc.ProtobufRpcEngine$Server$ProtoBufRpcInvoker.call(ProtobufRpcEngine.java:524)
> at org.apache.hadoop.ipc.RPC$Server.call(RPC.java:1025)
> at org.apache.hadoop.ipc.Server$RpcCall.run(Server.java:876)
> at org.apache.hadoop.ipc.Server$RpcCall.run(Server.java:822)
> 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:1730)
> at org.apache.hadoop.ipc.Server$Handler.run(Server.java:2682)
>
> Updated on 10/28/2019:
> See MISMATCH_MULTIPART_LIST error.
>
> 2019-10-28 11:44:34,079 [qtp1383524016-70] ERROR - Error in Complete
> Multipart Upload Request for bucket: ozone-test, key:
> 20191012/plc_1570863541668_927
> 8
> MISMATCH_MULTIPART_LIST org.apache.hadoop.ozone.om.exceptions.OMException:
> Complete Multipart Upload Failed: volume:
> s3c89e813c80ffcea9543004d57b2a1239bucket:
> ozone-testkey: 20191012/plc_1570863541668_9278
> at
> org.apache.hadoop.ozone.om.protocolPB.OzoneManagerProtocolClientSideTranslatorPB.handleError(OzoneManagerProtocolClientSideTranslatorPB.java:732)
> at
> org.apache.hadoop.ozone.om.protocolPB.OzoneManagerProtocolClientSideTranslatorPB.completeMultipartUpload(OzoneManagerProtocolClientSideTranslatorPB
> .java:1104)
> at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
> at
> sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
> at
> sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
> at java.lang.reflect.Method.invoke(Method.java:497)
> at
> org.apache.hadoop.hdds.tracing.TraceAllMethod.invoke(TraceAllMethod.java:66)
> at com.sun.proxy.$Proxy82.completeMultipartUpload(Unknown Source)
> at
> org.apache.hadoop.ozone.client.rpc.RpcClient.completeMultipartUpload(RpcClient.java:883)
> at
> org.apache.hadoop.ozone.client.OzoneBucket.completeMultipartUpload(OzoneBucket.java:445)
> at
> org.apache.hadoop.ozone.s3.endpoint.ObjectEndpoint.completeMultipartUpload(ObjectEndpoint.java:498)
> 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.glassfish.jersey.server.model.internal.ResourceMethodInvocationHandlerFactory.lambda$static$0(ResourceMethodInvocationHandlerFactory.java:76)
> at
> org.glassfish.jersey.server.model.internal.AbstractJavaResourceMethodDispatcher$1.run(AbstractJavaResourceMethodDispatcher.java:148)
> at
> org.glassfish.jersey.server.model.internal.AbstractJavaResourceMethodDispatcher.invoke(AbstractJavaResourceMethodDispatcher.java:191)
> at
> org.glassfish.jersey.server.model.internal.JavaResourceMethodDispatcherProvider$ResponseOutInvoker.doDispatch(JavaResourceMethodDispatcherProvider.java:200)
> at
> org.glassfish.jersey.server.model.internal.AbstractJavaResourceMethodDispatcher.dispatch(AbstractJavaResourceMethodDispatcher.java:103)
> at
> org.glassfish.jersey.server.model.ResourceMethodInvoker.invoke(ResourceMethodInvoker.java:493)
>
> The following errors has been resolved in
> https://issues.apache.org/jira/browse/HDDS-2322.
> 2019-10-24 16:01:59,527 [OMDoubleBufferFlushThread] ERROR - Terminating with
> exit status 2: OMDoubleBuffer flush
> threadOMDoubleBufferFlushThreadencountered Throwable error
> java.util.ConcurrentModificationException
> at java.util.TreeMap.forEach(TreeMap.java:1004)
> at
> org.apache.hadoop.ozone.om.helpers.OmMultipartKeyInfo.getProto(OmMultipartKeyInfo.java:111)
> at
> org.apache.hadoop.ozone.om.codec.OmMultipartKeyInfoCodec.toPersistedFormat(OmMultipartKeyInfoCodec.java:38)
> at
> org.apache.hadoop.ozone.om.codec.OmMultipartKeyInfoCodec.toPersistedFormat(OmMultipartKeyInfoCodec.java:31)
> at
> org.apache.hadoop.hdds.utils.db.CodecRegistry.asRawData(CodecRegistry.java:68)
> at
> org.apache.hadoop.hdds.utils.db.TypedTable.putWithBatch(TypedTable.java:125)
> at
> org.apache.hadoop.ozone.om.response.s3.multipart.S3MultipartUploadCommitPartResponse.addToDBBatch(S3MultipartUploadCommitPartResponse.java:112)
> at
> org.apache.hadoop.ozone.om.ratis.OzoneManagerDoubleBuffer.lambda$flushTransactions$0(OzoneManagerDoubleBuffer.java:137)
> at java.util.Iterator.forEachRemaining(Iterator.java:116)
> at
> org.apache.hadoop.ozone.om.ratis.OzoneManagerDoubleBuffer.flushTransactions(OzoneManagerDoubleBuffer.java:135)
> at java.lang.Thread.run(Thread.java:745)
> 2019-10-24 16:01:59,629 [shutdown-hook-0] INFO - SHUTDOWN_MSG:
--
This message was sent by Atlassian Jira
(v8.3.4#803005)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
