Return-Path: X-Original-To: apmail-hbase-user-archive@www.apache.org Delivered-To: apmail-hbase-user-archive@www.apache.org Received: from mail.apache.org (hermes.apache.org [140.211.11.3]) by minotaur.apache.org (Postfix) with SMTP id 10E8A10F86 for ; Fri, 20 Dec 2013 12:53:49 +0000 (UTC) Received: (qmail 33949 invoked by uid 500); 20 Dec 2013 12:53:44 -0000 Delivered-To: apmail-hbase-user-archive@hbase.apache.org Received: (qmail 33820 invoked by uid 500); 20 Dec 2013 12:53:38 -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 33812 invoked by uid 99); 20 Dec 2013 12:53:36 -0000 Received: from athena.apache.org (HELO athena.apache.org) (140.211.11.136) by apache.org (qpsmtpd/0.29) with ESMTP; Fri, 20 Dec 2013 12:53:36 +0000 X-ASF-Spam-Status: No, hits=1.5 required=5.0 tests=HTML_MESSAGE,RCVD_IN_DNSWL_LOW,SPF_PASS X-Spam-Check-By: apache.org Received-SPF: pass (athena.apache.org: local policy includes SPF record at spf.trusted-forwarder.org) Received: from [209.85.212.41] (HELO mail-vb0-f41.google.com) (209.85.212.41) by apache.org (qpsmtpd/0.29) with ESMTP; Fri, 20 Dec 2013 12:53:32 +0000 Received: by mail-vb0-f41.google.com with SMTP id p14so1433645vbm.0 for ; Fri, 20 Dec 2013 04:53:11 -0800 (PST) X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20130820; h=x-gm-message-state:mime-version:in-reply-to:references:from:date :message-id:subject:to:content-type; bh=d1AP6KX/E17lHU4bwwdQEf0c01BWgvkEXKgy4R5rsck=; b=Rk29Tln4rOvZ9YRHzcs107N52ApH+lpJuUtjPFRkoNz3oB4dSAabLiUUlXsQ35z3p4 C99p3FD7mPzzvBmfXMcsAObBhElW1/2xiFz0xHObFKRL1H6lmuumsDqLfgO3+2okHqgb rEueGoMAZqO22G666tWyx1f3YKIzXZn2GSuxj9jpJdu0cMtgGvMkM0TAmfqxSK9FIYiC npnRnTljhReAF2LpZap5N2tSEESVookrbV6XVHW5pdONEG+Af0ROQJeATfLkZ8Xseq9x NhXdSixL/Fj9ysPkC4BNcd1+Yxfuix2nOvlpT7QXXiVvWTK3TusuckZlA7ybGBDIh7tO jn5w== X-Gm-Message-State: ALoCoQk1SVhHltnDXRl6neNyFpyOmE8yl63aiKWV7PWqR8PKxEMTvpmLaAx8Tc1N8Dt0yiF7OWCV X-Received: by 10.220.88.204 with SMTP id b12mr4691892vcm.3.1387543991276; Fri, 20 Dec 2013 04:53:11 -0800 (PST) MIME-Version: 1.0 Received: by 10.52.24.49 with HTTP; Fri, 20 Dec 2013 04:52:51 -0800 (PST) In-Reply-To: References: From: Jean-Marc Spaggiari Date: Fri, 20 Dec 2013 07:52:51 -0500 Message-ID: Subject: =?UTF-8?B?UmU6IOetlOWkjTog562U5aSNOiBTaG91bGQgd2Ugc2V0IHRoZSBwcm9wZXJ0eSAiaGJhcw==?= =?UTF-8?B?ZS5sb2NhbC5kaXIiIHRvIGEgbGlzdCBvZiBkaXJlY3RvcmllcyBvbiBkaWZmZXJlbnQgZGlza3MgdG8g?= =?UTF-8?B?c3ByZWFkIEkvTz8=?= To: user Content-Type: multipart/alternative; boundary=047d7b3a92eeb5f0bb04edf6c2b1 X-Virus-Checked: Checked by ClamAV on apache.org --047d7b3a92eeb5f0bb04edf6c2b1 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: quoted-printable Barath's respons is a good summary. There almost nothing going into hbase.local.dir. It's like in your local linux box. You don't specify more than one tmp directory. It's the same thing here. There will not be really any benefit of adding that. 2013/12/20 Bharath Vissapragada > Hbase uses HDFS for data storage and region servers just use HDFS API to > write files. So you should be looking at balancing disk IO at datanode > level (dfs.datanode.data.dir as mentioned in other response). The path yo= u > mentioned (hbase.local.dir) is just used for storing temporary files or > CP/dynamic jars etc (not data) by region server and doesn't take much spa= ce > / cause IO. > > > On Fri, Dec 20, 2013 at 2:49 PM, =E8=B0=A2=E8=89=AF = wrote: > > > maybe you have a misunderstanding about "hbase.local.dir", please refer > to > > HBASE-6824 for why it was introduced. > > > > Thanks, > > ________________________________________ > > =E5=8F=91=E4=BB=B6=E4=BA=BA: Tao Xiao [xiaotao.cs.nju@gmail.com] > > =E5=8F=91=E9=80=81=E6=97=B6=E9=97=B4: 2013=E5=B9=B412=E6=9C=8820=E6=97= =A5 16:30 > > =E6=94=B6=E4=BB=B6=E4=BA=BA: user > > =E4=B8=BB=E9=A2=98: Re: =E7=AD=94=E5=A4=8D: Should we set the property = "hbase.local.dir" to a list of > > directories on different disks to spread I/O? > > > > Since "hbase.local.dir" specifes local directory, why doesn't it specif= y > > multiple directories on different disks to spread I/O, just as what > > "dfs.datanode.data.dir" does ? > > > > > > 2013/12/20 =E8=B0=A2=E8=89=AF > > > > > Please take a look at "dfs.datanode.data.dir" in hdfs-site.xml. > > > P.S. "hbase.local.dir" supports one dir only, don't specify it with a > > > list:) > > > > > > Thanks, > > > ________________________________________ > > > =E5=8F=91=E4=BB=B6=E4=BA=BA: Tao Xiao [xiaotao.cs.nju@gmail.com] > > > =E5=8F=91=E9=80=81=E6=97=B6=E9=97=B4: 2013=E5=B9=B412=E6=9C=8820=E6= =97=A5 15:11 > > > =E6=94=B6=E4=BB=B6=E4=BA=BA: user > > > =E4=B8=BB=E9=A2=98: Should we set the property "hbase.local.dir" to a= list of > directories > > > on different disks to spread I/O? > > > > > > Hi, > > > > > > To spread I/O on multiple disks of the HBase cluster, I set the > > > property "hbase.local.dir" in hbase-site.xml to a comma-separated li= st > > of > > > directories on different disks as follows: > > > > > > > > > hbase.local.dir > > > > > > > > > > > > /storage/disk1/hbase.local.dir,/storage/disk2/hbase.local.dir,/sto= rage/disk3/hbase.local.dir > > > > > > > > > is it right ? > > > > > > > > > -- > Bharath Vissapragada > > --047d7b3a92eeb5f0bb04edf6c2b1--