Received: from localhost (unknown [200.46.204.183]) by postgresql.org (Postfix) with ESMTP id 39F619FA436 for ; Thu, 1 Nov 2007 21:27:35 -0300 (ADT) Received: from postgresql.org ([200.46.204.71]) by localhost (mx1.hub.org [200.46.204.183]) (amavisd-maia, port 10024) with ESMTP id 72001-06 for ; Thu, 1 Nov 2007 21:27:31 -0300 (ADT) X-Greylist: from auto-whitelisted by SQLgrey-1.7.5 Received: from wdscexfe02.sc.wdc.com (wdscexfe02.sc.wdc.com [129.253.170.52]) by postgresql.org (Postfix) with ESMTP id 15C559FA419 for ; Thu, 1 Nov 2007 21:27:30 -0300 (ADT) Received: from wdmyexbe03.my.asia.wdc.com ([129.253.105.55]) by wdscexfe02.sc.wdc.com with Microsoft SMTPSVC(6.0.3790.1830); Thu, 1 Nov 2007 17:27:13 -0700 Received: from 129.253.107.232 ([129.253.107.232]) by wdmyexbe03.my.asia.wdc.com ([129.253.105.55]) with Microsoft Exchange Server HTTP-DAV ; Fri, 2 Nov 2007 00:27:09 +0000 Received: from neuromancer by 129.253.105.55; 02 Nov 2007 08:26:54 +0800 Subject: Re: Hardware for PostgreSQL From: Ow Mun Heng To: Steve Crawford Cc: Magnus Hagander , Tomas Vondra , Ketema , pgsql-performance@postgresql.org In-Reply-To: <472A17ED.1070008@pinpointresearch.com> References: <1193849108.591961.103570@22g2000hsm.googlegroups.com> <4728FAA1.7060905@fuzzy.cz> <1193889182.7999.71.camel@neuromancer.home.net> <4729783A.2030201@hagander.net> <1193903161.9148.27.camel@neuromancer.home.net> <472985B5.6010701@hagander.net> <472A17ED.1070008@pinpointresearch.com> Content-Type: text/plain Content-Transfer-Encoding: 7bit Date: Fri, 02 Nov 2007 08:26:54 +0800 Message-Id: <1193963214.9625.3.camel@neuromancer.home.net> Mime-Version: 1.0 X-Mailer: Evolution 2.12.0 X-OriginalArrivalTime: 02 Nov 2007 00:27:13.0434 (UTC) FILETIME=[1D47FFA0:01C81CE7] X-Virus-Scanned: Maia Mailguard 1.0.1 X-Spam-Status: No, hits=0.948 tagged_above=0 required=5 tests=AWL=-0.379, BAYES_20=-0.74, RCVD_NUMERIC_HELO=2.067 X-Spam-Level: X-Archive-Number: 200711/26 X-Sequence-Number: 27441 On Thu, 2007-11-01 at 11:16 -0700, Steve Crawford wrote: > Magnus Hagander wrote: > > Ow Mun Heng wrote: > >>> You're likely better off (performance-wise) putting it on the same disk > >>> as the database itself if that one has better RAID, for example. > >> I'm thinking along the lines of since nothing much writes to the OS > >> Disk, I should(keyword) be safe. > > > > Unless it's *always* in the cache (not so likely), reads will also move > > the heads... > > And if you aren't mounted noatime, reads will also cause a write. /dev/VolGroup00/LogVol01 / ext3 defaults,noatime 1 1 /dev/md0 /raid1_array ext3 noatime,data=writeback 1 1 Yep..yep..