Received: from maia.hub.org (maia-3.hub.org [200.46.204.243]) by mail.postgresql.org (Postfix) with ESMTP id A3C54133798F for ; Mon, 27 Sep 2010 13:53:40 -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 14450-03 for ; Mon, 27 Sep 2010 16:53:32 +0000 (UTC) X-Greylist: from auto-whitelisted by SQLgrey-1.7.6 Received: from moutng.kundenserver.de (moutng.kundenserver.de [212.227.126.187]) by mail.postgresql.org (Postfix) with ESMTP id 303B6133729E for ; Mon, 27 Sep 2010 13:53:32 -0300 (ADT) Received: from [192.168.1.6] (static-71-179-240-8.bltmmd.fios.verizon.net [71.179.240.8]) by mrelayeu.kundenserver.de (node=mreu2) with ESMTP (Nemesis) id 0Lu05i-1ObLp63hDi-010vAL; Mon, 27 Sep 2010 18:53:31 +0200 Message-ID: <4CA0CC06.4040809@2ndquadrant.com> Date: Mon, 27 Sep 2010 12:53:26 -0400 From: Greg Smith User-Agent: Thunderbird 2.0.0.24 (X11/20100317) MIME-Version: 1.0 To: "pgsql-performance@postgresql.org" Subject: Re: Memory speed testing References: <4C983297.8010301@2ndquadrant.com> In-Reply-To: <4C983297.8010301@2ndquadrant.com> Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit X-Provags-ID: V02:K0:LTOiIZEt73IzEFxmxGhfhs7Qjzrx9gaxUHnC4ENkoiV C2ZmQU1uSgC1TisXrWKfq/WQ/3nb681zdzoOBROvDeN2ClDl/E ffafe8HtxR/UcnCjpMHpz3rossN8HKZbKGscE1hnkDlxZbR/Fu wtilcq2hjw/y32GDC/f9sjp+wuhxsR29tuJZZG47tNBIdMPO9x h7Ayub6yHugwYBTX4d5Opur0wzmo9wtriCbD38IKaE= 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: 201009/188 X-Sequence-Number: 40391 Last bit of promotion here for this project: http://github.com/gregs1104/stream-scaling has been updated with a few more results anonymously submitted by list members here. The updated chart really fleshes out how the RAM scaling works on the older multi-socket AMD servers now. That's something that's been described on this list for years, but never really measured this clearly before to my knowledge. I have 4 and 8 socket examples in there now, showing DDR2/667 and DDR2/800. Also have some initial numbers on the DDR-3 based Phenom II processors too, which fit right in the middle of the Intel samples. They look like another round of good bang for the buck midrange desktop parts typical for AMD. -- Greg Smith, 2ndQuadrant US greg@2ndQuadrant.com Baltimore, MD PostgreSQL Training, Services and Support www.2ndQuadrant.us Author, "PostgreSQL 9.0 High Performance" Pre-ordering at: https://www.packtpub.com/postgresql-9-0-high-performance/book