Received: from makus.postgresql.org (makus.postgresql.org [98.129.198.125]) by mail.postgresql.org (Postfix) with ESMTP id 6495D171224A for ; Tue, 6 Mar 2012 05:34:56 -0400 (AST) Received: from mail-ey0-f174.google.com ([209.85.215.174]) by makus.postgresql.org with esmtp (Exim 4.72) (envelope-from ) id 1S4qnG-0005Vw-NM for pgsql-performance@postgresql.org; Tue, 06 Mar 2012 09:34:55 +0000 Received: by eaaq12 with SMTP id q12so1742136eaa.19 for ; Tue, 06 Mar 2012 01:34:41 -0800 (PST) Received-SPF: pass (google.com: domain of yebhavinga@gmail.com designates 10.14.207.200 as permitted sender) client-ip=10.14.207.200; Authentication-Results: mr.google.com; spf=pass (google.com: domain of yebhavinga@gmail.com designates 10.14.207.200 as permitted sender) smtp.mail=yebhavinga@gmail.com; dkim=pass header.i=yebhavinga@gmail.com Received: from mr.google.com ([10.14.207.200]) by 10.14.207.200 with SMTP id n48mr13135858eeo.71.1331026481771 (num_hops = 1); Tue, 06 Mar 2012 01:34:41 -0800 (PST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20120113; h=message-id:date:from:user-agent:mime-version:to:cc:subject :references:in-reply-to:content-type:content-transfer-encoding; bh=R7k70yrf9LljmXFCOjscxuNTLpLMlCBcV3Kcqy4BiAQ=; b=e97m5DGeSmDMpgG7rjsgf+JGQg/RuLSQRPR+r8O6fxOZpBd1HcOlynDq4zAVmqL44l jcYZj2Pv8Qg8T2zlu2ssKbWOv/huxDC1nYLBmfJB+3KqWGTH34/08WQW6CXgN+zJUI2K r6hJTwf60VdJiP6sWoo1RWTo4O70MGxKTX4DTXWrOvb+8YzsdTwFi3FT7OL1Zj7sTxBl lBriSAArgFFHT3g4u7BHCH7ULGGR0EB8L2BagQDV/zKQnsQpMHFi6ncXw5g9YQniJ191 v4WRwkwtY4E/7XBJF9ibmyI/KGUndoP8fv545vlySthCUF7gM+Ik/k13Z8FsCXkdqT5t Tx8w== Received: by 10.14.207.200 with SMTP id n48mr9941269eeo.71.1331026481651; Tue, 06 Mar 2012 01:34:41 -0800 (PST) Received: from [192.168.73.63] (5357DA75.cm-6-8d.dynamic.ziggo.nl. [83.87.218.117]) by mx.google.com with ESMTPS id n55sm32378007eef.6.2012.03.06.01.34.40 (version=TLSv1/SSLv3 cipher=OTHER); Tue, 06 Mar 2012 01:34:40 -0800 (PST) Message-ID: <4F55DA38.90701@gmail.com> Date: Tue, 06 Mar 2012 10:34:48 +0100 From: Yeb Havinga User-Agent: Mozilla/5.0 (Windows NT 5.1; rv:9.0) Gecko/20111222 Thunderbird/9.0.1 MIME-Version: 1.0 To: Andrea Suisani CC: Mark Kirkwood , pgsql-performance@postgresql.org Subject: Re: SSD and RAID References: <4F554025.9040101@catalyst.net.nz> <4F55C802.8040401@gmail.com> <4F55CC07.6020307@opinioni.net> In-Reply-To: <4F55CC07.6020307@opinioni.net> Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit X-Pg-Spam-Score: -2.6 (--) X-Archive-Number: 201203/64 X-Sequence-Number: 46514 On 2012-03-06 09:34, Andrea Suisani wrote: > On 03/06/2012 09:17 AM, Yeb Havinga wrote: >> >> PS: we applied the same philosophy (different brands) also to >> motherboards, io controllers and memory, but after testing, we liked >> one IO controllers software so much more than the other so we chose >> to have only one. Also stream memory performance of one motherboard >> showed a significant performance >> regression in the higher thread counts that we decided to go for the >> other brand for all servers. >> > > care to share motherboard winning model? > > thanks > Andrea > On http://i.imgur.com/vfmvu.png is a graph of three systems, made with the multi stream scaling (average of 10 tests if I remember correctly) test. The red and blue are 2 X 12 core opteron 6168 systems with 64 GB DDR3 1333MHz in 8GB dimms Red is a Tyan S8230 Blue is a Supermicro H8DGI-G We tried a lot of things to rule out motherboards, such as swap memory of both systems, ensure BIOS settings are similar (e.g. ECC mode), update to latest BIOS where possible, but none of those settings improved the memory performance drop. Both systems were installed with kickstarted Centos 6.2, so also no kernel setting differences there.. regards, Yeb -- Yeb Havinga http://www.mgrid.net/ Mastering Medical Data