[ https://issues.apache.org/jira/browse/HDFS-12749?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16364280#comment-16364280 ]
He Xiaoqiao commented on HDFS-12749: ------------------------------------ ping [~xkrogen] I also had seen this problems in our big production cluster, and I think this is a blocked issue. The issue was original reported by my colleague [~tanyuxin] and we applied this patch to our production cluster based branch-2.7, the problems as mentioned above disappears. I think the description of this ticket may lead to little ambiguity. I would like to offer more information, a) {{BPServiceActor#register}} only catch exception {{EOFException}} and {{SocketTimeoutException}} (both are subclass of IOException) when register to NameNode. b) when the request pass to under {{RPC}} layer, {{Client#call}} (line 1448) may throw many type exceptions, such as {{InterruptedIOException}}, {{IOException}}, etc. of course for different exception reasons. c) Load of NameNode may very high during restarting process, especially in big cluster. when datanode reregister to namenode at this time, {{RPC#Client}} may throw IOException (not subclass of IOException) to {{BPServiceActor#register}} as [~tanyuxin] describe above. d) The IOException will be catch by {{BPServiceActor#processCommand}} and print warn log {{`WARN org.apache.hadoop.hdfs.server.datanode.DataNode: Error processing datanode Command`}} but not reinit context of {{BlockPool}} when reregister and continue run, so {{BlockReport}} will not be scheduled immediately (when DataNode send {{BlockReport}} to restarting NameNode based on the last {{BlockReport}} time.) e) Actually, There are other subsequent problems besides NOT schedule {{BlockReport}} immediately. Such as block token secret keys not update correctly and client can not read {{Blocks}} from this DataNode even if hold the correct BlockToken. I have reviewed patch and one minor suggestion, a) please rebase an active branch (such as branch-2.7) and offer new patch; b) it will be better if add new UnitTest for this fix. If I am wrong please correct me. [~tanyuxin] > DN may not send block report to NN after NN restart > --------------------------------------------------- > > Key: HDFS-12749 > URL: https://issues.apache.org/jira/browse/HDFS-12749 > Project: Hadoop HDFS > Issue Type: Bug > Affects Versions: 2.7.1 > Reporter: TanYuxin > Priority: Major > Attachments: HDFS-12749.001.patch > > > Now our cluster have thousands of DN, millions of files and blocks. When NN > restart, NN's load is very high. > After NN restart,DN will call BPServiceActor#reRegister method to register. > But register RPC will get a IOException since NN is busy dealing with Block > Report. The exception is caught at BPServiceActor#processCommand. > Next is the caught IOException: > {code:java} > WARN org.apache.hadoop.hdfs.server.datanode.DataNode: Error processing > datanode Command > java.io.IOException: Failed on local exception: java.io.IOException: > java.net.SocketTimeoutException: 60000 millis timeout while waiting for > channel to be ready for read. ch : java.nio.channels.SocketChannel[connected > local=/DataNode_IP:Port remote=NameNode_Host/IP:Port]; Host Details : local > host is: "DataNode_Host/Datanode_IP"; destination host is: > "NameNode_Host":Port; > at org.apache.hadoop.net.NetUtils.wrapException(NetUtils.java:773) > at org.apache.hadoop.ipc.Client.call(Client.java:1474) > at org.apache.hadoop.ipc.Client.call(Client.java:1407) > at > org.apache.hadoop.ipc.ProtobufRpcEngine$Invoker.invoke(ProtobufRpcEngine.java:229) > at com.sun.proxy.$Proxy13.registerDatanode(Unknown Source) > at > org.apache.hadoop.hdfs.protocolPB.DatanodeProtocolClientSideTranslatorPB.registerDatanode(DatanodeProtocolClientSideTranslatorPB.java:126) > at > org.apache.hadoop.hdfs.server.datanode.BPServiceActor.register(BPServiceActor.java:793) > at > org.apache.hadoop.hdfs.server.datanode.BPServiceActor.reRegister(BPServiceActor.java:926) > at > org.apache.hadoop.hdfs.server.datanode.BPOfferService.processCommandFromActor(BPOfferService.java:604) > at > org.apache.hadoop.hdfs.server.datanode.BPServiceActor.processCommand(BPServiceActor.java:898) > at > org.apache.hadoop.hdfs.server.datanode.BPServiceActor.offerService(BPServiceActor.java:711) > at > org.apache.hadoop.hdfs.server.datanode.BPServiceActor.run(BPServiceActor.java:864) > at java.lang.Thread.run(Thread.java:745) > {code} > The un-catched IOException breaks BPServiceActor#register, and the Block > Report can not be sent immediately. > {code} > /** > * Register one bp with the corresponding NameNode > * <p> > * The bpDatanode needs to register with the namenode on startup in order > * 1) to report which storage it is serving now and > * 2) to receive a registrationID > * > * issued by the namenode to recognize registered datanodes. > * > * @param nsInfo current NamespaceInfo > * @see FSNamesystem#registerDatanode(DatanodeRegistration) > * @throws IOException > */ > void register(NamespaceInfo nsInfo) throws IOException { > // The handshake() phase loaded the block pool storage > // off disk - so update the bpRegistration object from that info > DatanodeRegistration newBpRegistration = bpos.createRegistration(); > LOG.info(this + " beginning handshake with NN"); > while (shouldRun()) { > try { > // Use returned registration from namenode with updated fields > newBpRegistration = bpNamenode.registerDatanode(newBpRegistration); > newBpRegistration.setNamespaceInfo(nsInfo); > bpRegistration = newBpRegistration; > break; > } catch(EOFException e) { // namenode might have just restarted > LOG.info("Problem connecting to server: " + nnAddr + " :" > + e.getLocalizedMessage()); > sleepAndLogInterrupts(1000, "connecting to server"); > } catch(SocketTimeoutException e) { // namenode is busy > LOG.info("Problem connecting to server: " + nnAddr); > sleepAndLogInterrupts(1000, "connecting to server"); > } > } > > LOG.info("Block pool " + this + " successfully registered with NN"); > bpos.registrationSucceeded(this, bpRegistration); > // random short delay - helps scatter the BR from all DNs > scheduler.scheduleBlockReport(dnConf.initialBlockReportDelay); > } > {code} > But NameNode has processed registerDatanode successfully, so it won't ask DN > to re-register again -- This message was sent by Atlassian JIRA (v7.6.3#76005) --------------------------------------------------------------------- To unsubscribe, e-mail: hdfs-issues-unsubscr...@hadoop.apache.org For additional commands, e-mail: hdfs-issues-h...@hadoop.apache.org