Return-Path: Delivered-To: apmail-hbase-user-archive@www.apache.org Received: (qmail 61245 invoked from network); 24 Jan 2011 13:42:46 -0000 Received: from hermes.apache.org (HELO mail.apache.org) (140.211.11.3) by minotaur.apache.org with SMTP; 24 Jan 2011 13:42:46 -0000 Received: (qmail 21991 invoked by uid 500); 24 Jan 2011 13:42:45 -0000 Delivered-To: apmail-hbase-user-archive@hbase.apache.org Received: (qmail 21619 invoked by uid 500); 24 Jan 2011 13:42:42 -0000 Mailing-List: contact user-help@hbase.apache.org; run by ezmlm Precedence: bulk List-Help: List-Unsubscribe: List-Post: List-Id: Reply-To: user@hbase.apache.org Delivered-To: mailing list user@hbase.apache.org Received: (qmail 21611 invoked by uid 99); 24 Jan 2011 13:42:41 -0000 Received: from nike.apache.org (HELO nike.apache.org) (192.87.106.230) by apache.org (qpsmtpd/0.29) with ESMTP; Mon, 24 Jan 2011 13:42:41 +0000 X-ASF-Spam-Status: No, hits=0.7 required=10.0 tests=RCVD_IN_DNSWL_NONE,SPF_NEUTRAL X-Spam-Check-By: apache.org Received-SPF: neutral (nike.apache.org: local policy) Received: from [98.139.52.243] (HELO nm26-vm1.bullet.mail.ac4.yahoo.com) (98.139.52.243) by apache.org (qpsmtpd/0.29) with SMTP; Mon, 24 Jan 2011 13:42:31 +0000 Received: from [98.139.52.193] by nm26.bullet.mail.ac4.yahoo.com with NNFMP; 24 Jan 2011 13:42:10 -0000 Received: from [98.139.52.146] by tm6.bullet.mail.ac4.yahoo.com with NNFMP; 24 Jan 2011 13:42:10 -0000 Received: from [127.0.0.1] by omp1029.mail.ac4.yahoo.com with NNFMP; 24 Jan 2011 13:42:10 -0000 X-Yahoo-Newman-Property: ymail-5 X-Yahoo-Newman-Id: 72816.44175.bm@omp1029.mail.ac4.yahoo.com Received: (qmail 78114 invoked by uid 60001); 24 Jan 2011 13:42:10 -0000 DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=yahoo.com; s=s1024; t=1295876529; bh=o9QQYtTJsvx3flAKyYBo/QziFCqMtIIiNkihcL5G45A=; h=Message-ID:X-YMail-OSG:Received:X-RocketYMMF:X-Mailer:Date:From:Reply-To:Subject:To:In-Reply-To:MIME-Version:Content-Type; b=jNbbU/eUE1fSeqYygSfjy/4qek9skkXzEuE3+OLc7Q7i+4Zb2QJsw0BPT8Zmp91Z+fsstERv1JoAunPCoZxsaqGk3oCKjJBhd399On1QcemuL2dswHbGMtUkOFfGFl8G17bAUCW6+0VOtBpetlY2BMEZ345nDjP+WgwPiwJyTLU= Message-ID: <874849.77774.qm@web65514.mail.ac4.yahoo.com> X-YMail-OSG: Jl.jxQkVM1nm7jTOHgsi1_gHKxVUG5sdGa9.9wAlifVrqE5 ZWY_CSKhnVc.GtVmG1Tq4U6voLJnJ5Kg0e1BafMgdBnFiu.VgNibnGJdJwuL A6LjXU.jGZGiFzNIN9we10nGix9H36anxARDpSraC4bza6s7_gC8JoHnbxxT 6PHB.XNk3H77MJ3S66qCS9R8okuHQgf9vJmIv3YUN8QiiBB2A8iw.wzNjthr FY11qCcjChT_WS6VsPo9XtQOZMwOTtjzpgj._ldogesksYfX2mrdJ4cZ9SI2 bKwiy4yQoQoUz_7flzeemkDNMNjVNE5oSxC_V9lin8fV9WFA40Rf9eiCq3L7 J8dsLc_xa_vqWee7a3jkPBYIgzfM0v7Q41dmAlymYpCkAyqK.I0A0azQqxft AjA6uzJceX1o- Received: from [60.251.45.163] by web65514.mail.ac4.yahoo.com via HTTP; Mon, 24 Jan 2011 05:42:09 PST X-RocketYMMF: apurtell X-Mailer: YahooMailClassic/11.4.20 YahooMailWebService/0.8.107.285259 Date: Mon, 24 Jan 2011 05:42:09 -0800 (PST) From: Andrew Purtell Reply-To: apurtell@apache.org Subject: Re: DFS rebalancing with running HBase To: user@hbase.apache.org In-Reply-To: <4D3D6EBF.8010302@gmail.com> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii X-Virus-Checked: Checked by ClamAV on apache.org Martin, The trouble was due to a defect in how HDFS managed partitioning deletion work among the datanodes. Especially when under high write load, HBase can post a lot of deletes due to compactions. Running the balancer just makes it worse -- additional replications into the face of uneven deletion just brings the end faster when a datanode fills. This is fixed in CDH3 via HDFS-630: https://issues.apache.org/jira/browse/HDFS-630 This is fixed in HDFS 0.21 + via HADOOP-5124: https://issues.apache.org/jira/browse/HADOOP-5124 All, It might be a good idea to apply one of these fixes to the ASF 0.20-append branch. Best regards, - Andy Problems worthy of attack prove their worth by hitting back. - Piet Hein (via Tom White) --- On Mon, 1/24/11, Martin Fiala wrote: > From: Martin Fiala > Subject: DFS rebalancing with running HBase > To: user@hbase.apache.org > Date: Monday, January 24, 2011, 4:21 AM > Hello, > > in one old thread regarding hadoop/hbase 0.19.x Andrew > Purtell wrote, that running DFS balancer while HBase is > running, is not recommended. I didn't find any remarks about > this in Hadoop or HBase documentation. > > http://mail-archives.apache.org/mod_mbox/hbase-user/200905.mbox/%3c812604.43615.qm@web65510.mail.ac4.yahoo.com%3e > > Is it still the case? What bad things can happen? > > It is quite clear, that with writing heavily to HBase and > running balancer simultaneously, the cluster is not going to > be balanced. It can become even more unbalanced. > What about running balancer when we are only reading from > HBase or writing small amounts of records? > > Regards, > Martin Fiala >