Received: from maia.hub.org (maia-3.hub.org [200.46.204.243]) by mail.postgresql.org (Postfix) with ESMTP id CCC28133616B for ; Mon, 7 Feb 2011 04:32:06 -0400 (AST) 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 08981-03 for ; Mon, 7 Feb 2011 08:31:55 +0000 (UTC) X-Greylist: from auto-whitelisted by SQLgrey-1.7.6 Received: from moutng.kundenserver.de (moutng.kundenserver.de [212.227.17.10]) by mail.postgresql.org (Postfix) with ESMTP id 3B3F91337BB7 for ; Mon, 7 Feb 2011 04:31:55 -0400 (AST) Received: from [192.168.1.6] (mail.highperformancepostgresql.com [71.179.240.8]) by mrelayeu.kundenserver.de (node=mrbap2) with ESMTP (Nemesis) id 0LcFAj-1QSo3z0TLR-00k56T; Mon, 07 Feb 2011 09:31:54 +0100 Message-ID: <4D4FADF8.4020705@2ndquadrant.com> Date: Mon, 07 Feb 2011 03:31:52 -0500 From: Greg Smith User-Agent: Thunderbird 2.0.0.24 (X11/20100317) MIME-Version: 1.0 To: Michael Kohl CC: pgsql-performance@postgresql.org Subject: Re: High load, References: In-Reply-To: Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit X-Provags-ID: V02:K0:9UfMEJOp3iWPBmJScO3gTbZewFj+MFNF1xnu2EZFTWl GobaMK57ucm0veQkgQAw9GC7ycbbcsCyKLYUgwKeVKApkOyzRU jF79DG4qYUBb2NoBbzQJTse9Sq31mrcajy0T4vmR2Ivj/00nS9 lssmR+WaxFplgk0NnxwTmYHGewXu1bNJs5W3G9s3+wwGpsFGhB AOdkXK71nvppDqlKT4nX3xj5q89VJhw36wPqrKebuM= X-Virus-Scanned: Maia Mailguard 1.0.1 X-Spam-Status: No, hits=-1.9 tagged_above=-10 required=5 tests=BAYES_00=-1.9, RCVD_IN_DNSWL_NONE=-0.0001 X-Spam-Level: X-Archive-Number: 201102/282 X-Sequence-Number: 42420 Michael Kohl wrote: > HDD: 2x 120 GB OCZ Vertex 2 SSD; RAID 1 > As a general warning here, as far as I know the regular Vertex 2 SSD doesn't cache writes properly for database use. It's possible to have a crash that leaves the database corrupted, if the drive has writes queued up in its cache. The Vertex 2 Pro resolves this issue with a supercap, you may have a model with concerns here. See http://wiki.postgresql.org/wiki/Reliable_Writes for more information. In addition to the log_checkpoints suggestion already made, I'd also recommend turning on log_lock_waits and log_temp_files on your server. All three of those--checkpoints, locks, and unexpected temp file use--can cause the sort of issue you're seeing. Well, not locks so much given you're seeing heavy disk I/O, but it's good to start logging those issues before they get bad, too. -- Greg Smith 2ndQuadrant US greg@2ndQuadrant.com Baltimore, MD PostgreSQL Training, Services, and 24x7 Support www.2ndQuadrant.us "PostgreSQL 9.0 High Performance": http://www.2ndQuadrant.com/books