X-Original-To: pgsql-performance-postgresql.org@localhost.postgresql.org Received: from localhost (av.hub.org [200.46.204.144]) by postgresql.org (Postfix) with ESMTP id 3EBA29DC85F for ; Thu, 5 Jan 2006 12:44:13 -0400 (AST) Received: from postgresql.org ([200.46.204.71]) by localhost (av.hub.org [200.46.204.144]) (amavisd-new, port 10024) with ESMTP id 28643-09 for ; Thu, 5 Jan 2006 12:44:09 -0400 (AST) X-Greylist: from auto-whitelisted by SQLgrey- Received: from mail.logix-tt.com (serval.logix-tt.com [213.239.221.42]) by postgresql.org (Postfix) with ESMTP id BB9449DC817 for ; Thu, 5 Jan 2006 12:44:08 -0400 (AST) Received: from kingfisher.intern.logix-tt.com (Mea6f.m.pppool.de [89.49.234.111]) (using TLSv1 with cipher DHE-RSA-AES256-SHA (256/256 bits)) (No client certificate requested) by mail.logix-tt.com (Postfix) with ESMTP id 8D3EC24400F; Thu, 5 Jan 2006 17:50:25 +0100 (CET) Received: from [127.0.0.1] (localhost [127.0.0.1]) by kingfisher.intern.logix-tt.com (Postfix) with ESMTP id D904D184B9036; Thu, 5 Jan 2006 17:44:05 +0100 (CET) Message-ID: <43BD4CD5.8080207@logix-tt.com> Date: Thu, 05 Jan 2006 17:44:05 +0100 From: Markus Schaber Organization: Logical Tracking and Tracing International AG, Switzerland User-Agent: Debian Thunderbird 1.0.7 (X11/20051017) X-Accept-Language: en-us, en MIME-Version: 1.0 To: pgsql-performance@postgresql.org Subject: Re: What's the best hardver for PostgreSQL 8.1? References: <43A84D03.7090002@ritek.hu> <200512212209.50234.caseroj@comcast.net> <200512212231.55100.caseroj@comcast.net> <20051224135042.484c6e32.frank@wiles.org> <6.2.5.6.0.20051224161551.01dc5d98@earthlink.net> In-Reply-To: X-Enigmail-Version: 0.93.0.0 Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: 7bit X-Virus-Scanned: by amavisd-new at hub.org X-Spam-Status: No, score=0.12 required=5 tests=[AWL=0.120] X-Spam-Score: 0.12 X-Spam-Level: X-Archive-Number: 200601/22 X-Sequence-Number: 16500 Hi, William, William Yu wrote: > Random write performance (small block that only writes to 1 drive): > 1 write requires N-1 reads + N writes --> 1/2N-1 % This is not true. Most Raid-5 engines use XOR or similar checksum methods. As opposed to cryptographic checksums, those can be updated and corrected incrementally. check_new = check_old xor data_old xor data_new So 2 reads and 2 writes are enough: read data and checksum, then adjust the checksum via the data difference, and write data and new checksum. And often, the old data block still is in cache, accounting to 1 read and two writes. HTH, Markus -- Markus Schaber | Logical Tracking&Tracing International AG Dipl. Inf. | Software Development GIS Fight against software patents in EU! www.ffii.org www.nosoftwarepatents.org