Received: from maia.hub.org (maia-3.hub.org [200.46.204.243]) by mail.postgresql.org (Postfix) with ESMTP id B42A71337BDC for ; Fri, 22 Apr 2011 18:53:32 -0300 (ADT) Received: from mail.postgresql.org ([200.46.204.86]) by maia.hub.org (mx1.hub.org [200.46.204.243]) (amavisd-maia, port 10024) with ESMTP id 83350-03 for ; Fri, 22 Apr 2011 21:53:25 +0000 (UTC) X-Greylist: delayed 00:09:16.335152 by SQLgrey-1.7.6 Received: from morework.geizhals.at (morework.geizhals.at [78.142.138.3]) by mail.postgresql.org (Postfix) with ESMTP id 495461337B82 for ; Fri, 22 Apr 2011 18:53:25 -0300 (ADT) Received: from localhost (morework [127.0.0.1]) by morework.geizhals.at (Postfix) with ESMTP id CD9C9168E5C7 for ; Fri, 22 Apr 2011 23:44:06 +0200 (CEST) X-Virus-Scanned: amavisd-new at geizhals.at Received: from morework.geizhals.at ([127.0.0.1]) by localhost (morework.geizhals.at [127.0.0.1]) (amavisd-new, port 10024) with ESMTP id hQ9NmaJoK-rn for ; Fri, 22 Apr 2011 23:44:01 +0200 (CEST) Received: from [172.16.43.138] (unknown [172.16.43.138]) (using TLSv1 with cipher AES256-SHA (256/256 bits)) (No client certificate requested) (Authenticated sender: mjy) by morework.geizhals.at (Postfix) with ESMTPSA for ; Fri, 22 Apr 2011 23:44:01 +0200 (CEST) Message-ID: <4DB1F69E.1000305@geizhals.at> Date: Fri, 22 Apr 2011 23:43:58 +0200 From: Marinos Yannikos User-Agent: Mozilla/5.0 (Windows; U; Windows NT 5.1; de; rv:1.9.2.15) Gecko/20110303 Lightning/1.0b2 Thunderbird/3.1.9 MIME-Version: 1.0 To: pgsql-performance@postgresql.org Subject: Re: postgresql random io test with 2 SSD Kingston V+100 500GB in (software) Raid1 References: In-Reply-To: Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit X-Virus-Scanned: Maia Mailguard 1.0.1 X-Spam-Status: No, hits=-1.91 tagged_above=-10 required=5 tests=BAYES_00=-1.9, T_RP_MATCHES_RCVD=-0.01 X-Spam-Level: X-Archive-Number: 201104/327 X-Sequence-Number: 43389 Am 19.04.2011 11:15, schrieb Laurent Laborde: > Soft RAID1 (md) > ext3 We have experimented a bit with Postgres and ext3 (with and without Linux software RAID1) and have found that since somewhere after 2.6.18, it has been prohibitively slow and causing high latencies during buffer flushes. You will probably see a significant improvement with ext4 (mkfs.ext4, not just remount as ext4, which is also possible). Also, you need to make sure that your blocks are properly aligned with SSDs, that might explain low random I/O performance. See http://www.nuclex.org/blog/personal/80-aligning-an-ssd-on-linux and http://www.ocztechnologyforum.com/forum/showthread.php?54379-Linux-Tips-tweaks-and-alignment&p=373226&viewfull=1#post373226 for example. Regards, Marinos