Return-Path: Delivered-To: apmail-hadoop-hbase-dev-archive@minotaur.apache.org Received: (qmail 64240 invoked from network); 20 May 2009 15:34:55 -0000 Received: from hermes.apache.org (HELO mail.apache.org) (140.211.11.3) by minotaur.apache.org with SMTP; 20 May 2009 15:34:55 -0000 Received: (qmail 7846 invoked by uid 500); 20 May 2009 15:35:08 -0000 Delivered-To: apmail-hadoop-hbase-dev-archive@hadoop.apache.org Received: (qmail 7804 invoked by uid 500); 20 May 2009 15:35:08 -0000 Mailing-List: contact hbase-dev-help@hadoop.apache.org; run by ezmlm Precedence: bulk List-Help: List-Unsubscribe: List-Post: List-Id: Reply-To: hbase-dev@hadoop.apache.org Delivered-To: mailing list hbase-dev@hadoop.apache.org Received: (qmail 7664 invoked by uid 99); 20 May 2009 15:35:07 -0000 Received: from athena.apache.org (HELO athena.apache.org) (140.211.11.136) by apache.org (qpsmtpd/0.29) with ESMTP; Wed, 20 May 2009 15:35:07 +0000 X-ASF-Spam-Status: No, hits=-2000.0 required=10.0 tests=ALL_TRUSTED X-Spam-Check-By: apache.org Received: from [140.211.11.140] (HELO brutus.apache.org) (140.211.11.140) by apache.org (qpsmtpd/0.29) with ESMTP; Wed, 20 May 2009 15:35:05 +0000 Received: from brutus (localhost [127.0.0.1]) by brutus.apache.org (Postfix) with ESMTP id ACF4A234C052 for ; Wed, 20 May 2009 08:34:45 -0700 (PDT) Message-ID: <1881008833.1242833685707.JavaMail.jira@brutus> Date: Wed, 20 May 2009 08:34:45 -0700 (PDT) From: "Evgeny Ryabitskiy (JIRA)" To: hbase-dev@hadoop.apache.org Subject: [jira] Updated: (HBASE-1017) Region balancing does not bring newly added node within acceptable range In-Reply-To: <1929845832.1227323564259.JavaMail.jira@brutus> MIME-Version: 1.0 Content-Type: text/plain; charset=utf-8 Content-Transfer-Encoding: quoted-printable X-JIRA-FingerPrint: 30527f35849b9dde25b450d4833f0394 X-Virus-Checked: Checked by ClamAV on apache.org [ https://issues.apache.org/jira/browse/HBASE-1017?page=3Dcom.atlassia= n.jira.plugin.system.issuetabpanels:all-tabpanel ] Evgeny Ryabitskiy updated HBASE-1017: ------------------------------------- Attachment: HBASE-1017_v12_FINAL.patch > Region balancing does not bring newly added node within acceptable range > ------------------------------------------------------------------------ > > Key: HBASE-1017 > URL: https://issues.apache.org/jira/browse/HBASE-1017 > Project: Hadoop HBase > Issue Type: Improvement > Affects Versions: 0.19.0 > Reporter: Jonathan Gray > Assignee: Evgeny Ryabitskiy > Priority: Minor > Fix For: 0.20.0 > > Attachments: HBASE-1017_v1.patch, HBASE-1017_v10.patch, HBASE-101= 7_v11_FINAL.patch, HBASE-1017_v12_FINAL.patch, HBASE-1017_v2.patch, HBASE-1= 017_v4.patch, HBASE-1017_v5.patch, HBASE-1017_v6.patch, HBASE-1017_v7.patch= , HBASE-1017_v8.patch, HBASE-1017_v9.patch, loadbalance2.0.patch > > > With a 10 node cluster, there were only 9 online nodes. With about 215 t= otal regions, each of the 9 had around 24 regions (average load is 24). Sl= op is 10% so 22 to 26 is the acceptable range. > Starting up the 10th node, master log showed: > {code} > 2008-11-21 15:57:51,521 INFO org.apache.hadoop.hbase.master.ServerManager= : Received start message from: 72.34.249.210:60020 > 2008-11-21 15:57:53,351 DEBUG org.apache.hadoop.hbase.master.RegionManage= r: Server 72.34.249.219:60020 is overloaded. Server load: 25 avg: 22.0, slo= p: 0.1 > 2008-11-21 15:57:53,351 DEBUG org.apache.hadoop.hbase.master.RegionManage= r: Choosing to reassign 3 regions. mostLoadedRegions has 10 regions in it. > 2008-11-21 15:57:53,351 DEBUG org.apache.hadoop.hbase.master.RegionManage= r: Going to close region streamitems,^@^@^@^@^AH=C3=AF=C2=BF=C2=BD;,1225411= 051632 > 2008-11-21 15:57:53,351 DEBUG org.apache.hadoop.hbase.master.RegionManage= r: Going to close region streamitems,^@^@^@^@^@=C3=AF=C2=BF=C2=BD=C3=9D,122= 5411056686 > 2008-11-21 15:57:53,351 DEBUG org.apache.hadoop.hbase.master.RegionManage= r: Going to close region groups,,1222913580957 > 2008-11-21 15:57:53,975 DEBUG org.apache.hadoop.hbase.master.RegionManage= r: Server 72.34.249.213:60020 is overloaded. Server load: 25 avg: 22.0, slo= p: 0.1 > 2008-11-21 15:57:53,975 DEBUG org.apache.hadoop.hbase.master.RegionManage= r: Choosing to reassign 3 regions. mostLoadedRegions has 10 regions in it. > 2008-11-21 15:57:53,976 DEBUG org.apache.hadoop.hbase.master.RegionManage= r: Going to close region upgrade,,1226892014784 > 2008-11-21 15:57:53,976 DEBUG org.apache.hadoop.hbase.master.RegionManage= r: Going to close region streamitems,^@^@^@^@^@3^Z=C3=AF=C2=BF=C2=BD,122541= 1056701 > 2008-11-21 15:57:53,976 DEBUG org.apache.hadoop.hbase.master.RegionManage= r: Going to close region streamitems,^@^@^@^@^@ ^L,1225411049042 > {code} > The new regionserver received only 6 regions. This happened because when= the 10th came in, average load dropped to 22. This caused two servers wit= h 25 regions (acceptable when avg was 24 but not now) to reassign 3 of thei= r regions each to bring them back down to the average. Unfortunately all o= ther regions remained within the 10% slop (20 to 24) so they were not overl= oaded and thus did not reassign off any regions. It was only chance that m= ade even 6 of the regions get reassigned as there could have been exactly 2= 4 on each server, in which case none would have been assigned to the new no= de. > This will behave worse on larger clusters when adding a new node has litt= le impact on the avg load/server. --=20 This message is automatically generated by JIRA. - You can reply to this email to add a comment to the issue online.