From hdfs-issues-return-246854-archive-asf-public=cust-asf.ponee.io@hadoop.apache.org Fri Dec 28 17:20:06 2018 Return-Path: X-Original-To: archive-asf-public@cust-asf.ponee.io Delivered-To: archive-asf-public@cust-asf.ponee.io Received: from mail.apache.org (hermes.apache.org [140.211.11.3]) by mx-eu-01.ponee.io (Postfix) with SMTP id 10548180677 for ; Fri, 28 Dec 2018 17:20:05 +0100 (CET) Received: (qmail 28844 invoked by uid 500); 28 Dec 2018 16:20:05 -0000 Mailing-List: contact hdfs-issues-help@hadoop.apache.org; run by ezmlm Precedence: bulk List-Help: List-Unsubscribe: List-Post: List-Id: Delivered-To: mailing list hdfs-issues@hadoop.apache.org Received: (qmail 28769 invoked by uid 99); 28 Dec 2018 16:20:05 -0000 Received: from pnap-us-west-generic-nat.apache.org (HELO spamd4-us-west.apache.org) (209.188.14.142) by apache.org (qpsmtpd/0.29) with ESMTP; Fri, 28 Dec 2018 16:20:05 +0000 Received: from localhost (localhost [127.0.0.1]) by spamd4-us-west.apache.org (ASF Mail Server at spamd4-us-west.apache.org) with ESMTP id A0F4AC250D for ; Fri, 28 Dec 2018 16:20:04 +0000 (UTC) X-Virus-Scanned: Debian amavisd-new at spamd4-us-west.apache.org X-Spam-Flag: NO X-Spam-Score: -110.301 X-Spam-Level: X-Spam-Status: No, score=-110.301 tagged_above=-999 required=6.31 tests=[ENV_AND_HDR_SPF_MATCH=-0.5, RCVD_IN_DNSWL_MED=-2.3, SPF_PASS=-0.001, USER_IN_DEF_SPF_WL=-7.5, USER_IN_WHITELIST=-100] autolearn=disabled Received: from mx1-lw-us.apache.org ([10.40.0.8]) by localhost (spamd4-us-west.apache.org [10.40.0.11]) (amavisd-new, port 10024) with ESMTP id DhJ_5GEKgpds for ; Fri, 28 Dec 2018 16:20:02 +0000 (UTC) Received: from mailrelay1-us-west.apache.org (mailrelay1-us-west.apache.org [209.188.14.139]) by mx1-lw-us.apache.org (ASF Mail Server at mx1-lw-us.apache.org) with ESMTP id 170425FC16 for ; Fri, 28 Dec 2018 16:20:02 +0000 (UTC) Received: from jira-lw-us.apache.org (unknown [207.244.88.139]) by mailrelay1-us-west.apache.org (ASF Mail Server at mailrelay1-us-west.apache.org) with ESMTP id 2E3C6E261D for ; Fri, 28 Dec 2018 16:20:01 +0000 (UTC) Received: from jira-lw-us.apache.org (localhost [127.0.0.1]) by jira-lw-us.apache.org (ASF Mail Server at jira-lw-us.apache.org) with ESMTP id 5839925376 for ; Fri, 28 Dec 2018 16:20:00 +0000 (UTC) Date: Fri, 28 Dec 2018 16:20:00 +0000 (UTC) From: "Kenneth Yang (JIRA)" To: hdfs-issues@hadoop.apache.org Message-ID: In-Reply-To: References: Subject: [jira] [Updated] (HDFS-14171) Performance improvement in Tailing EditLog MIME-Version: 1.0 Content-Type: text/plain; charset=utf-8 Content-Transfer-Encoding: quoted-printable X-JIRA-FingerPrint: 30527f35849b9dde25b450d4833f0394 [ https://issues.apache.org/jira/browse/HDFS-14171?page=3Dcom.atlassia= n.jira.plugin.system.issuetabpanels:all-tabpanel ] Kenneth Yang updated HDFS-14171: -------------------------------- Attachment: HDFS-14171.003.patch > Performance improvement in Tailing EditLog > ------------------------------------------ > > Key: HDFS-14171 > URL: https://issues.apache.org/jira/browse/HDFS-14171 > Project: Hadoop HDFS > Issue Type: Improvement > Components: namenode > Affects Versions: 2.9.0, 3.0.0-alpha1 > Reporter: Kenneth Yang > Priority: Minor > Attachments: HDFS-14171.000.patch, HDFS-14171.001.patch, HDFS-141= 71.002.patch, HDFS-14171.003.patch, HDFS-14171_Call-Tree.png > > > Stack: > {code:java} > Thread 456 (Edit log tailer): > State: RUNNABLE > Blocked count: 1139 > Waited count: 12 > Stack: > org.apache.hadoop.hdfs.server.blockmanagement.DatanodeManager.getNumLiveD= ataNodes(DatanodeManager.java:1259) > org.apache.hadoop.hdfs.server.blockmanagement.BlockManagerSafeMode.areThr= esholdsMet(BlockManagerSafeMode.java:570) > org.apache.hadoop.hdfs.server.blockmanagement.BlockManagerSafeMode.checkS= afeMode(BlockManagerSafeMode.java:213) > org.apache.hadoop.hdfs.server.blockmanagement.BlockManagerSafeMode.adjust= BlockTotals(BlockManagerSafeMode.java:265) > org.apache.hadoop.hdfs.server.blockmanagement.BlockManager.completeBlock(= BlockManager.java:1087) > org.apache.hadoop.hdfs.server.blockmanagement.BlockManager.forceCompleteB= lock(BlockManager.java:1118) > org.apache.hadoop.hdfs.server.namenode.FSEditLogLoader.updateBlocks(FSEdi= tLogLoader.java:1126) > org.apache.hadoop.hdfs.server.namenode.FSEditLogLoader.applyEditLogOp(FSE= ditLogLoader.java:468) > org.apache.hadoop.hdfs.server.namenode.FSEditLogLoader.loadEditRecords(FS= EditLogLoader.java:258) > org.apache.hadoop.hdfs.server.namenode.FSEditLogLoader.loadFSEdits(FSEdit= LogLoader.java:161) > org.apache.hadoop.hdfs.server.namenode.FSImage.loadEdits(FSImage.java:892= ) > org.apache.hadoop.hdfs.server.namenode.ha.EditLogTailer.doTailEdits(EditL= ogTailer.java:321) > org.apache.hadoop.hdfs.server.namenode.ha.EditLogTailer$EditLogTailerThre= ad.doWork(EditLogTailer.java:460) > org.apache.hadoop.hdfs.server.namenode.ha.EditLogTailer$EditLogTailerThre= ad.access$400(EditLogTailer.java:410) > org.apache.hadoop.hdfs.server.namenode.ha.EditLogTailer$EditLogTailerThre= ad$1.run(EditLogTailer.java:427) > org.apache.hadoop.security.SecurityUtil.doAsLoginUserOrFatal(SecurityUtil= .java:414) > org.apache.hadoop.hdfs.server.namenode.ha.EditLogTailer$EditLogTailerThre= ad.run(EditLogTailer.java:423) > Thread 455 (pool-16-thread-1): > {code} > code: > {code:java} > private boolean areThresholdsMet() { > assert namesystem.hasWriteLock(); > int datanodeNum =3D blockManager.getDatanodeManager().getNumLiveDataNod= es(); > synchronized (this) { > return blockSafe >=3D blockThreshold && datanodeNum >=3D datanodeThre= shold; > } > } > {code} > According to the code, each time the method areThresholdsMet() is called,= the value of {color:#ff0000}datanodeNum{color} is need to be calculated.= =C2=A0 However, in the scenario of {color:#ff0000}datanodeThreshold{color} = is equal to 0=EF=BC=880 is the default value of the configuration=EF=BC=89,= This expression datanodeNum >=3D datanodeThreshold always returns true. > Calling the method {color:#ff0000}getNumLiveDataNodes(){color} is time co= nsuming at a scale of 10,000 datanode clusters. Therefore, we add the judgm= ent condition, and only when the datanodeThreshold is greater than 0, the d= atanodeNum is calculated, which improves the perfomance greatly. > The Call Tree=C2=A0graph=C2=A0is shown in the attached file. > =C2=A0 -- This message was sent by Atlassian JIRA (v7.6.3#76005) --------------------------------------------------------------------- To unsubscribe, e-mail: hdfs-issues-unsubscribe@hadoop.apache.org For additional commands, e-mail: hdfs-issues-help@hadoop.apache.org