From owner-freebsd-performance@FreeBSD.ORG Tue Apr 25 13:07:40 2006 Return-Path: X-Original-To: freebsd-performance@freebsd.org Delivered-To: freebsd-performance@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 2F12416A404 for ; Tue, 25 Apr 2006 13:07:40 +0000 (UTC) (envelope-from wmoran@collaborativefusion.com) Received: from mx00.pub.collaborativefusion.com (mx00.pub.collaborativefusion.com [206.210.89.199]) by mx1.FreeBSD.org (Postfix) with ESMTP id A820E43D5A for ; Tue, 25 Apr 2006 13:07:39 +0000 (GMT) (envelope-from wmoran@collaborativefusion.com) Received: from vanquish.pgh.priv.collaborativefusion.com (vanquish.pgh.priv.collaborativefusion.com [192.168.2.61]) by wingspan with esmtp; Tue, 25 Apr 2006 09:07:39 -0400 id 00056413.444E1F1B.000090FE Date: Tue, 25 Apr 2006 09:07:39 -0400 From: Bill Moran To: freebsd-performance@freebsd.org Message-Id: <20060425090739.8470143f.wmoran@collaborativefusion.com> Organization: Collaborative Fusion X-Mailer: Sylpheed version 2.2.0 (GTK+ 2.8.12; i386-portbld-freebsd6.0) Mime-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7bit Subject: Dual-core CPU vs. very large cache X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Tue, 25 Apr 2006 13:07:40 -0000 [First off, the list archives for this list don't seem to be searchable. I get the following error: Unable to read document excerpts '/usr/local/mailman/archives/private/freebsd-performance/htdig/db.excerpts' Did you run htdig?] So ... on to the question. We have some database servers that we're looking to replace with beefier hardware, mainly because we're expecting our customer base to grow a lot in the near future. The current hw is Dell 2850 servers. These are dual proc (each proc is hyperthreaded) with Dell PERC controllers driving 4 SCSI-320 disks in a RAID-10. We're doing our best to simulate high-load in the lab, and the database consistently bottlenecks on CPU usage. I'm assuming that the combination of plenty of RAM and high-speed disks has led to the CPU being the slowest part of the system. We're considering two alternatives for the newer hardware: 1) Intel HT CPUs with 8M cache 2) Intel dual-core procs Our current Dells have 2M cache, and I'm trying to determine whether the 8M cache will make a significant difference or not. Can someone recommend a testing procedure for determining whether adding cache is worthwhile or not? I can simulate a test load at any time, but I don't know how to tell whether the cache is the bottleneck of the CPU or not. -- Bill Moran Collaborative Fusion Inc. From owner-freebsd-performance@FreeBSD.ORG Tue Apr 25 17:04:04 2006 Return-Path: X-Original-To: freebsd-performance@freebsd.org Delivered-To: freebsd-performance@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id AE32D16A429 for ; Tue, 25 Apr 2006 17:04:04 +0000 (UTC) (envelope-from Shane@007Marketing.com) Received: from smtp3.adl2.internode.on.net (smtp3.adl2.internode.on.net [203.16.214.203]) by mx1.FreeBSD.org (Postfix) with ESMTP id 9F84A43D5A for ; Tue, 25 Apr 2006 17:03:51 +0000 (GMT) (envelope-from Shane@007Marketing.com) Received: from [192.168.8.50] (ppp247-71.static.internode.on.net [203.122.247.71]) by smtp3.adl2.internode.on.net (8.13.6/8.13.5) with ESMTP id k3PH3jsr058076 for ; Wed, 26 Apr 2006 02:33:50 +0930 (CST) (envelope-from Shane@007Marketing.com) User-Agent: Microsoft-Entourage/10.1.4.030702.0 Date: Wed, 26 Apr 2006 02:33:43 +0930 From: Shane Ambler To: FreeBSD Mailing Lists Message-ID: In-Reply-To: <20060425090739.8470143f.wmoran@collaborativefusion.com> Mime-version: 1.0 Content-type: text/plain; charset="US-ASCII" Content-transfer-encoding: 7bit Subject: Re: Dual-core CPU vs. very large cache X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Tue, 25 Apr 2006 17:04:04 -0000 On 25/4/2006 22:37, "Bill Moran" wrote: > > [First off, the list archives for this list don't seem to be > searchable. I get the following error: > Unable to read document excerpts > '/usr/local/mailman/archives/private/freebsd-performance/htdig/db.excerpts' > Did you run htdig?] > > So ... on to the question. > > We have some database servers that we're looking to replace with > beefier hardware, mainly because we're expecting our customer base > to grow a lot in the near future. > > The current hw is Dell 2850 servers. These are dual proc (each proc > is hyperthreaded) with Dell PERC controllers driving 4 SCSI-320 > disks in a RAID-10. > > We're doing our best to simulate high-load in the lab, and the > database consistently bottlenecks on CPU usage. I'm assuming that > the combination of plenty of RAM and high-speed disks has led to > the CPU being the slowest part of the system. > > We're considering two alternatives for the newer hardware: > 1) Intel HT CPUs with 8M cache > 2) Intel dual-core procs > > Our current Dells have 2M cache, and I'm trying to determine whether > the 8M cache will make a significant difference or not. Can someone > recommend a testing procedure for determining whether adding cache is > worthwhile or not? I can simulate a test load at any time, but I > don't know how to tell whether the cache is the bottleneck of the > CPU or not. Cache helps speed things up by keeping code/data in faster memory - this helps speed things up when the same code/data is used repeatedly. >From the info you have given I am guessing that you have many users who are loading the system up to capacity and that the database is fairly large (a few Gig). On that premise I would recommend the dual core CPU's (two or more dual core xeon's - not P4's) - it sounds like they would be working with more data than would be kept in cache so the extra cache wouldn't increase performance a great deal and with many users loading the system the more cpu's of the dual cores cpu's would allow more requests to be processed at the same time. At the high end of server hardware have you considered Opteron servers? The Tyan Thunder K8QW can run four dual core Opteron's and can take a daughtercard that will allow it to have a total of eight dual core Opteron's. Even the K8QSD Pro can run four dual core Opterons. Start with the two cpu config and if the load gets too high add another two - you then still have the option of adding another four if the need arises. From owner-freebsd-performance@FreeBSD.ORG Tue Apr 25 17:55:20 2006 Return-Path: X-Original-To: freebsd-performance@freebsd.org Delivered-To: freebsd-performance@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 83C0816A44C for ; Tue, 25 Apr 2006 17:55:20 +0000 (UTC) (envelope-from anderson@centtech.com) Received: from mh2.centtech.com (moat3.centtech.com [207.200.51.50]) by mx1.FreeBSD.org (Postfix) with ESMTP id 0714743D53 for ; Tue, 25 Apr 2006 17:55:11 +0000 (GMT) (envelope-from anderson@centtech.com) Received: from [192.168.42.21] (andersonbox1.centtech.com [192.168.42.21]) by mh2.centtech.com (8.13.1/8.13.1) with ESMTP id k3PHt7eF021488; Tue, 25 Apr 2006 12:55:08 -0500 (CDT) (envelope-from anderson@centtech.com) Message-ID: <444E6270.2030805@centtech.com> Date: Tue, 25 Apr 2006 12:54:56 -0500 From: Eric Anderson User-Agent: Thunderbird 1.5 (X11/20060402) MIME-Version: 1.0 To: Shane Ambler References: In-Reply-To: Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit X-Virus-Scanned: ClamAV 0.87.1/1425/Tue Apr 25 07:09:41 2006 on mh2.centtech.com X-Virus-Status: Clean Cc: FreeBSD Mailing Lists Subject: Re: Dual-core CPU vs. very large cache X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Tue, 25 Apr 2006 17:55:20 -0000 Shane Ambler wrote: > On 25/4/2006 22:37, "Bill Moran" wrote: > >> [First off, the list archives for this list don't seem to be >> searchable. I get the following error: >> Unable to read document excerpts >> '/usr/local/mailman/archives/private/freebsd-performance/htdig/db.excerpts' >> Did you run htdig?] >> >> So ... on to the question. >> >> We have some database servers that we're looking to replace with >> beefier hardware, mainly because we're expecting our customer base >> to grow a lot in the near future. >> >> The current hw is Dell 2850 servers. These are dual proc (each proc >> is hyperthreaded) with Dell PERC controllers driving 4 SCSI-320 >> disks in a RAID-10. >> >> We're doing our best to simulate high-load in the lab, and the >> database consistently bottlenecks on CPU usage. I'm assuming that >> the combination of plenty of RAM and high-speed disks has led to >> the CPU being the slowest part of the system. >> >> We're considering two alternatives for the newer hardware: >> 1) Intel HT CPUs with 8M cache >> 2) Intel dual-core procs >> >> Our current Dells have 2M cache, and I'm trying to determine whether >> the 8M cache will make a significant difference or not. Can someone >> recommend a testing procedure for determining whether adding cache is >> worthwhile or not? I can simulate a test load at any time, but I >> don't know how to tell whether the cache is the bottleneck of the >> CPU or not. > > Cache helps speed things up by keeping code/data in faster memory - this > helps speed things up when the same code/data is used repeatedly. > >>From the info you have given I am guessing that you have many users who are > loading the system up to capacity and that the database is fairly large > (a few Gig). > On that premise I would recommend the dual core CPU's (two or more dual core > xeon's - not P4's) - it sounds like they would be working with more data > than would be kept in cache so the extra cache wouldn't increase performance > a great deal and with many users loading the system the more cpu's of the > dual cores cpu's would allow more requests to be processed at the same time. We've done extensive testing of dual-core systems here with different cpu bound processes, and have found out over and over that increasing the cache helps much more for cpu bound processes than dual core. If anything, get two single core processors with the 8M cache on them. Also, make sure that your database is set up with indexes correctly and is pruned (if that needs to be done for your database server). Eric -- ------------------------------------------------------------------------ Eric Anderson Sr. Systems Administrator Centaur Technology Anything that works is better than anything that doesn't. ------------------------------------------------------------------------ From owner-freebsd-performance@FreeBSD.ORG Tue Apr 25 21:00:27 2006 Return-Path: X-Original-To: freebsd-performance@freebsd.org Delivered-To: freebsd-performance@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 71C4F16A402 for ; Tue, 25 Apr 2006 21:00:27 +0000 (UTC) (envelope-from killing@multiplay.co.uk) Received: from multiplay.co.uk (core6.multiplay.co.uk [85.236.96.23]) by mx1.FreeBSD.org (Postfix) with ESMTP id B258B43D4C for ; Tue, 25 Apr 2006 21:00:26 +0000 (GMT) (envelope-from killing@multiplay.co.uk) Received: from vader ([213.116.58.228]) by multiplay.co.uk (multiplay.co.uk [85.236.96.23]) (MDaemon.PRO.v8.1.3.R) with ESMTP id md50002503443.msg for ; Tue, 25 Apr 2006 22:00:27 +0100 Message-ID: <005301c668ab$39c4c150$8b00a8c0@multiplay.co.uk> From: "Steven Hartland" To: "Bill Moran" , References: <20060425090739.8470143f.wmoran@collaborativefusion.com> Date: Tue, 25 Apr 2006 21:53:53 +0100 MIME-Version: 1.0 Content-Type: text/plain; format=flowed; charset="iso-8859-1"; reply-type=original Content-Transfer-Encoding: 7bit X-Priority: 3 X-MSMail-Priority: Normal X-Mailer: Microsoft Outlook Express 6.00.2900.2869 X-MimeOLE: Produced By Microsoft MimeOLE V6.00.2900.2869 X-Spam-Processed: multiplay.co.uk, Tue, 25 Apr 2006 22:00:27 +0100 (not processed: message from valid local sender) X-MDRemoteIP: 213.116.58.228 X-Return-Path: killing@multiplay.co.uk X-MDaemon-Deliver-To: freebsd-performance@freebsd.org X-MDAV-Processed: multiplay.co.uk, Tue, 25 Apr 2006 22:00:27 +0100 Cc: Subject: Re: Dual-core CPU vs. very large cache X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Tue, 25 Apr 2006 21:00:27 -0000 Forget Intel and go for AMD who beat them hands down for DB work: http://www.anandtech.com/IT/showdoc.aspx?i=2745 ----- Original Message ----- From: "Bill Moran" > Our current Dells have 2M cache, and I'm trying to determine whether > the 8M cache will make a significant difference or not. Can someone > recommend a testing procedure for determining whether adding cache is > worthwhile or not? I can simulate a test load at any time, but I > don't know how to tell whether the cache is the bottleneck of the > CPU or not. ================================================ This e.mail is private and confidential between Multiplay (UK) Ltd. and the person or entity to whom it is addressed. In the event of misdirection, the recipient is prohibited from using, copying, printing or otherwise disseminating it or any information contained in it. In the event of misdirection, illegible or incomplete transmission please telephone (023) 8024 3137 or return the E.mail to postmaster@multiplay.co.uk. From owner-freebsd-performance@FreeBSD.ORG Tue Apr 25 21:06:48 2006 Return-Path: X-Original-To: freebsd-performance@freebsd.org Delivered-To: freebsd-performance@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 8417F16A413 for ; Tue, 25 Apr 2006 21:06:48 +0000 (UTC) (envelope-from mikej@rogers.com) Received: from smtp109.rog.mail.re2.yahoo.com (smtp109.rog.mail.re2.yahoo.com [68.142.225.207]) by mx1.FreeBSD.org (Postfix) with SMTP id E737443D48 for ; Tue, 25 Apr 2006 21:06:47 +0000 (GMT) (envelope-from mikej@rogers.com) Received: (qmail 72938 invoked from network); 25 Apr 2006 21:06:47 -0000 DomainKey-Signature: a=rsa-sha1; q=dns; c=nofws; s=s1024; d=rogers.com; h=Received:Message-ID:Date:From:User-Agent:MIME-Version:To:CC:Subject:References:In-Reply-To:Content-Type:Content-Transfer-Encoding; b=m7w4y9leAad9MuLiIj+uYmbx6fUTGzk7THnnkElatH8hHzE7ZaMHZGsKocDOVNk40hjo6swsjXWFnj02x9kLhHMDTJ9NvOpKCYQeiMXxwZ6YcDJ8pH4zwsSrgidmyNEruEi6CP79PC0K2pNHo+hCo2hSOo4/U+XvgcF2DEffYXs= ; Received: from unknown (HELO ?70.31.50.218?) (mikej@rogers.com@70.31.50.218 with plain) by smtp109.rog.mail.re2.yahoo.com with SMTP; 25 Apr 2006 21:06:47 -0000 Message-ID: <444E8F8A.9030409@rogers.com> Date: Tue, 25 Apr 2006 17:07:22 -0400 From: Mike Jakubik User-Agent: Thunderbird 1.5.0.2 (Windows/20060308) MIME-Version: 1.0 To: Steven Hartland References: <20060425090739.8470143f.wmoran@collaborativefusion.com> <005301c668ab$39c4c150$8b00a8c0@multiplay.co.uk> In-Reply-To: <005301c668ab$39c4c150$8b00a8c0@multiplay.co.uk> Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit Cc: freebsd-performance@freebsd.org, Bill Moran Subject: Re: Dual-core CPU vs. very large cache X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Tue, 25 Apr 2006 21:06:48 -0000 Steven Hartland wrote: > Forget Intel and go for AMD who beat them hands down for DB work: > http://www.anandtech.com/IT/showdoc.aspx?i=2745 It will be interesting to see how Intels new CPUs (Conroe, Woodcrest, etc) will perform. From initial gaming benchmarks, they seems to outperform the current AMD offerings. But for current technology i agree, go for an Opteron system. From owner-freebsd-performance@FreeBSD.ORG Wed Apr 26 01:39:28 2006 Return-Path: X-Original-To: freebsd-performance@freebsd.org Delivered-To: freebsd-performance@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 29C1F16A401 for ; Wed, 26 Apr 2006 01:39:28 +0000 (UTC) (envelope-from joseph.koshy@gmail.com) Received: from xproxy.gmail.com (xproxy.gmail.com [66.249.82.195]) by mx1.FreeBSD.org (Postfix) with ESMTP id 84BB143D49 for ; Wed, 26 Apr 2006 01:39:27 +0000 (GMT) (envelope-from joseph.koshy@gmail.com) Received: by xproxy.gmail.com with SMTP id s9so899323wxc for ; Tue, 25 Apr 2006 18:39:26 -0700 (PDT) DomainKey-Signature: a=rsa-sha1; q=dns; c=nofws; s=beta; d=gmail.com; h=received:message-id:date:from:to:subject:cc:in-reply-to:mime-version:content-type:content-transfer-encoding:content-disposition:references; b=uCV9XaIrkCy8wB+ejYxS8TZlHnb+5qnZXZkG1+I17en1MWoiii5RV/rHWef0sMvVNErNi7Z9d1Ua7sODhFfxh769axCj0ubmmfdLzb5Sia0QJuSGgOzSa6krmAHMXtIBR0omfxZ18+s1DwqgoTGLmLpLT0dkS9YnXoIBbEwa4LE= Received: by 10.70.97.7 with SMTP id u7mr4754256wxb; Tue, 25 Apr 2006 18:39:25 -0700 (PDT) Received: by 10.70.116.7 with HTTP; Tue, 25 Apr 2006 18:39:25 -0700 (PDT) Message-ID: <84dead720604251839t3014389dka036b7d7bbd422c@mail.gmail.com> Date: Wed, 26 Apr 2006 07:09:25 +0530 From: "Joseph Koshy" To: "Bill Moran" In-Reply-To: <20060425090739.8470143f.wmoran@collaborativefusion.com> MIME-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: quoted-printable Content-Disposition: inline References: <20060425090739.8470143f.wmoran@collaborativefusion.com> Cc: freebsd-performance@freebsd.org Subject: Re: Dual-core CPU vs. very large cache X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Wed, 26 Apr 2006 01:39:28 -0000 > Our current Dells have 2M cache, and I'm trying to determine > whether the 8M cache will make a significant difference or > not. Can someone recommend a testing procedure for > determining whether adding cache is worthwhile or not? > I can simulate a test load at any time, but I don't know how > to tell whether the cache is the bottleneck of the CPU or not. You didn't say which version of FreeBSD you are running. If this is 6.X, you could run pmcstat(8) in a system-wide counting mode and measure cache behaviour directly. Briefly, # (compile, boot a kernel with options HWPMC_HOOKS) # kldload hwpmc # pmcstat -w 1 -s dc-misses test-load See pmc(3) and the CPU vendor documentation referenced there for the events your CPU can measure. If your application is CPU bound you may want to check for memory bus behaviour, cache behaviour, cycles the processor was stalled and for poor branch prediction. If you notice anything anomalous, you can use the hwpmc's sampling modes to find out what code is causing the anomaly. -- FreeBSD Volunteer, http://people.freebsd.org/~jkoshy From owner-freebsd-performance@FreeBSD.ORG Wed Apr 26 01:56:52 2006 Return-Path: X-Original-To: freebsd-performance@freebsd.org Delivered-To: freebsd-performance@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 8F60616A404 for ; Wed, 26 Apr 2006 01:56:52 +0000 (UTC) (envelope-from mv@thebeastie.org) Received: from p4.roq.com (ns1.ecoms.com [207.44.130.137]) by mx1.FreeBSD.org (Postfix) with ESMTP id 3ECE843D45 for ; Wed, 26 Apr 2006 01:56:49 +0000 (GMT) (envelope-from mv@thebeastie.org) Received: from p4.roq.com (localhost.roq.com [127.0.0.1]) by p4.roq.com (Postfix) with ESMTP id B11BA4D1DC; Wed, 26 Apr 2006 01:58:04 +0000 (GMT) Received: from [192.168.46.102] (ppp166-27.static.internode.on.net [150.101.166.27]) by p4.roq.com (Postfix) with ESMTP id A79054D1D5; Wed, 26 Apr 2006 01:58:03 +0000 (GMT) Message-ID: <444ED35E.5050703@thebeastie.org> Date: Wed, 26 Apr 2006 11:56:46 +1000 From: Michael Vince User-Agent: Mozilla/5.0 (X11; U; FreeBSD amd64; en-US; rv:1.7.12) Gecko/20060404 X-Accept-Language: en-us, en MIME-Version: 1.0 To: Steven Hartland References: <20060425090739.8470143f.wmoran@collaborativefusion.com> <005301c668ab$39c4c150$8b00a8c0@multiplay.co.uk> In-Reply-To: <005301c668ab$39c4c150$8b00a8c0@multiplay.co.uk> Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit X-Virus-Scanned: ClamAV using ClamSMTP Cc: freebsd-performance@freebsd.org, Bill Moran Subject: Re: Dual-core CPU vs. very large cache X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Wed, 26 Apr 2006 01:56:52 -0000 Yes I was going to point out a article from Anandtech as well. Its an older one but someone on Anandtech is a SQL performance article benchmarking different server CPUs on Database performance. It concluded that large CPU cache is very important for Databases. Basically said having a large CPU cache it helped performance more for databases then most things they ever benchmark such as benchmark differences shown in Office apps and multimedia tests. The AMD Opterons are real performance leaders ATM right now no doubt. I also understand why you must get Dell, some of the other hardware suppliers are just to hard to deal with, I tried to get a Opteron server out of HP and after about 1 month of getting excuses about CPU shortages etc I went back to Dell. Off topic here is a kind of cool article I think a lot of people can identify with, http://joyeur.com/2006/03/20/the-sun-doesnt-shine-on-me Mike Steven Hartland wrote: > Forget Intel and go for AMD who beat them hands down for DB work: > http://www.anandtech.com/IT/showdoc.aspx?i=2745 > > ----- Original Message ----- From: "Bill Moran" > > >> Our current Dells have 2M cache, and I'm trying to determine whether >> the 8M cache will make a significant difference or not. Can someone >> recommend a testing procedure for determining whether adding cache is >> worthwhile or not? I can simulate a test load at any time, but I >> don't know how to tell whether the cache is the bottleneck of the >> CPU or not. > From owner-freebsd-performance@FreeBSD.ORG Wed Apr 26 04:01:17 2006 Return-Path: X-Original-To: freebsd-performance@freebsd.org Delivered-To: freebsd-performance@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 4726716A408 for ; Wed, 26 Apr 2006 04:01:17 +0000 (UTC) (envelope-from oceanare@pacific.net.sg) Received: from smtpgate4.pacific.net.sg (smtpgate4.pacific.net.sg [203.81.36.24]) by mx1.FreeBSD.org (Postfix) with SMTP id 606F343D4C for ; Wed, 26 Apr 2006 04:01:15 +0000 (GMT) (envelope-from oceanare@pacific.net.sg) Received: (qmail 32245 invoked from network); 26 Apr 2006 04:01:13 -0000 Received: from maxwell6.pacific.net.sg (203.120.90.212) by smtpgate4.pacific.net.sg with SMTP; 26 Apr 2006 04:01:13 -0000 Received: from [192.168.0.107] ([210.24.122.33]) by maxwell6.pacific.net.sg with ESMTP id <20060426040113.VYC1180.maxwell6.pacific.net.sg@[192.168.0.107]>; Wed, 26 Apr 2006 12:01:13 +0800 Message-ID: <444EF066.1090405@pacific.net.sg> Date: Wed, 26 Apr 2006 12:00:38 +0800 From: Erich Dollansky Organization: oceanare pte ltd User-Agent: Thunderbird 1.5 (X11/20060422) MIME-Version: 1.0 To: Bill Moran References: <20060425090739.8470143f.wmoran@collaborativefusion.com> In-Reply-To: <20060425090739.8470143f.wmoran@collaborativefusion.com> Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit Cc: freebsd-performance@freebsd.org Subject: Re: Dual-core CPU vs. very large cache X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Wed, 26 Apr 2006 04:01:17 -0000 Hi, Bill Moran wrote: > > We have some database servers that we're looking to replace with > beefier hardware, mainly because we're expecting our customer base > to grow a lot in the near future. > > The current hw is Dell 2850 servers. These are dual proc (each proc > is hyperthreaded) with Dell PERC controllers driving 4 SCSI-320 > disks in a RAID-10. SCSI is really the minimum here. > > We're considering two alternatives for the newer hardware: > 1) Intel HT CPUs with 8M cache > 2) Intel dual-core procs Forget both. Opterons have a much better memory interface which helps here a lot. > > Our current Dells have 2M cache, and I'm trying to determine whether > the 8M cache will make a significant difference or not. Can someone You have a simple problem. Even if you have a large cache, it has to be refilled very often. The limited memory band with of Xeons will be of an disadvantage here. Take an Opteron motherboard where every CPU has its own memory slots. Take the CPUs with the larger caches. Dual core plus at least two CPUs help also. > recommend a testing procedure for determining whether adding cache is > worthwhile or not? I can simulate a test load at any time, but I > don't know how to tell whether the cache is the bottleneck of the > CPU or not. > You will never be able to answer this in general. I did some time ago tests with Oracle running on a 24 CPU machine. There are situations where most CPUs are idle because all CPUs work on locked parts off the same table and there are situation where all 24 CPU are working on different parts of the database bringing speed to extremely high levels. As long as you do not know your future scenario and if you have the money, get first the highest number of CPUs possible and add then dual core if possible. Erich From owner-freebsd-performance@FreeBSD.ORG Wed Apr 26 14:35:10 2006 Return-Path: X-Original-To: freebsd-performance@freebsd.org Delivered-To: freebsd-performance@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 6C37416A400 for ; Wed, 26 Apr 2006 14:35:10 +0000 (UTC) (envelope-from dgilbert@daveg.ca) Received: from ox.eicat.ca (ox.eicat.ca [66.96.30.35]) by mx1.FreeBSD.org (Postfix) with ESMTP id 09FE443D45 for ; Wed, 26 Apr 2006 14:35:09 +0000 (GMT) (envelope-from dgilbert@daveg.ca) Received: by ox.eicat.ca (Postfix, from userid 66) id A2C9315A07; Wed, 26 Apr 2006 10:35:08 -0400 (EDT) Received: by canoe.dclg.ca (Postfix, from userid 101) id E73024AC41; Wed, 26 Apr 2006 10:35:06 -0400 (EDT) From: David Gilbert MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Transfer-Encoding: 7bit Message-ID: <17487.34074.833134.823847@canoe.dclg.ca> Date: Wed, 26 Apr 2006 10:35:06 -0400 To: Mike Jakubik In-Reply-To: <444E8F8A.9030409@rogers.com> References: <20060425090739.8470143f.wmoran@collaborativefusion.com> <005301c668ab$39c4c150$8b00a8c0@multiplay.co.uk> <444E8F8A.9030409@rogers.com> X-Mailer: VM 7.17 under 21.4 (patch 19) "Constant Variable" XEmacs Lucid Cc: freebsd-performance@freebsd.org, Steven Hartland , Bill Moran Subject: Re: Dual-core CPU vs. very large cache X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Wed, 26 Apr 2006 14:35:10 -0000 >>>>> "Mike" == Mike Jakubik writes: Mike> Steven Hartland wrote: >> Forget Intel and go for AMD who beat them hands down for DB work: >> http://www.anandtech.com/IT/showdoc.aspx?i=2745 Mike> It will be interesting to see how Intels new CPUs (Conroe, Mike> Woodcrest, etc) will perform. From initial gaming benchmarks, Mike> they seems to outperform the current AMD offerings. But for Mike> current technology i agree, go for an Opteron system. This isn't random. As I understand the issue, the Opteron HT bus handles synchronization much faster. So for a game --- this doesn't matter ... games don't (usually) need sync. Databases, however, live on synchonizaton. If you're a Dell man (and already paying the Dell tax), consider the Sun 1U's. They offer up to 4 cores in a 1U. Dave. -- ============================================================================ |David Gilbert, Independent Contractor. | Two things can be | |Mail: dave@daveg.ca | equal if and only if they | |http://daveg.ca | are precisely opposite. | =========================================================GLO================ From owner-freebsd-performance@FreeBSD.ORG Wed Apr 26 14:42:46 2006 Return-Path: X-Original-To: freebsd-performance@freebsd.org Delivered-To: freebsd-performance@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 8165816A405 for ; Wed, 26 Apr 2006 14:42:46 +0000 (UTC) (envelope-from wmoran@collaborativefusion.com) Received: from mx00.pub.collaborativefusion.com (mx00.pub.collaborativefusion.com [206.210.89.199]) by mx1.FreeBSD.org (Postfix) with ESMTP id 5C93043D70 for ; Wed, 26 Apr 2006 14:42:43 +0000 (GMT) (envelope-from wmoran@collaborativefusion.com) Received: from vanquish.pgh.priv.collaborativefusion.com (vanquish.pgh.priv.collaborativefusion.com [192.168.2.61]) by wingspan with esmtp; Wed, 26 Apr 2006 10:42:42 -0400 id 0005641D.444F86E2.0000996B Date: Wed, 26 Apr 2006 10:42:42 -0400 From: Bill Moran To: David Gilbert Message-Id: <20060426104242.1209c152.wmoran@collaborativefusion.com> In-Reply-To: <17487.34074.833134.823847@canoe.dclg.ca> References: <20060425090739.8470143f.wmoran@collaborativefusion.com> <005301c668ab$39c4c150$8b00a8c0@multiplay.co.uk> <444E8F8A.9030409@rogers.com> <17487.34074.833134.823847@canoe.dclg.ca> Organization: Collaborative Fusion X-Mailer: Sylpheed version 2.2.0 (GTK+ 2.8.12; i386-portbld-freebsd6.0) Mime-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7bit Cc: freebsd-performance@freebsd.org Subject: Re: Dual-core CPU vs. very large cache X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Wed, 26 Apr 2006 14:42:46 -0000 On Wed, 26 Apr 2006 10:35:06 -0400 David Gilbert wrote: > >>>>> "Mike" == Mike Jakubik writes: > > Mike> Steven Hartland wrote: > >> Forget Intel and go for AMD who beat them hands down for DB work: > >> http://www.anandtech.com/IT/showdoc.aspx?i=2745 > > Mike> It will be interesting to see how Intels new CPUs (Conroe, > Mike> Woodcrest, etc) will perform. From initial gaming benchmarks, > Mike> they seems to outperform the current AMD offerings. But for > Mike> current technology i agree, go for an Opteron system. > > This isn't random. As I understand the issue, the Opteron HT bus > handles synchronization much faster. So for a game --- this doesn't > matter ... games don't (usually) need sync. Databases, however, live > on synchonizaton. If you're a Dell man (and already paying the Dell > tax), consider the Sun 1U's. They offer up to 4 cores in a 1U. Lost me here. Are you saying 1U units from Sun? Or does Dell have a 1U called a "Sun"? I am pretty-much locked into Dell - decision made by others. Actually, I've been pretty happy with the Dell HW, but it's a shame they don't offer AMD servers. -- Bill Moran Collaborative Fusion Inc. From owner-freebsd-performance@FreeBSD.ORG Wed Apr 26 14:52:01 2006 Return-Path: X-Original-To: freebsd-performance@freebsd.org Delivered-To: freebsd-performance@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 0CCE516A414 for ; Wed, 26 Apr 2006 14:52:01 +0000 (UTC) (envelope-from mikej@rogers.com) Received: from smtp100.rog.mail.re2.yahoo.com (smtp100.rog.mail.re2.yahoo.com [206.190.36.78]) by mx1.FreeBSD.org (Postfix) with SMTP id D83C643D45 for ; Wed, 26 Apr 2006 14:51:53 +0000 (GMT) (envelope-from mikej@rogers.com) Received: (qmail 5187 invoked from network); 26 Apr 2006 14:51:53 -0000 DomainKey-Signature: a=rsa-sha1; q=dns; c=nofws; s=s1024; d=rogers.com; h=Received:Message-ID:Date:From:User-Agent:MIME-Version:To:CC:Subject:References:In-Reply-To:Content-Type:Content-Transfer-Encoding; b=OwkPWV9WF43TwciBj9YrD3yyJ5FuErmue63hIIB+ZNHU+2Rk+A6gxgQI2AkBkbzWs5HgiBuWPUZUDxDFu3EgXaJvjOmf/ltOkO1F7CC01z0owrklyYuXx5iwYwIhqYbb5qbtn7rOsl3TS7JU4Vjrs8yXdw/lLfZIai0N/nE1YmQ= ; Received: from unknown (HELO ?70.31.50.218?) (mikej@rogers.com@70.31.50.218 with plain) by smtp100.rog.mail.re2.yahoo.com with SMTP; 26 Apr 2006 14:51:52 -0000 Message-ID: <444F8912.4010604@rogers.com> Date: Wed, 26 Apr 2006 10:52:02 -0400 From: Mike Jakubik User-Agent: Thunderbird 1.5.0.2 (Windows/20060308) MIME-Version: 1.0 To: David Gilbert References: <20060425090739.8470143f.wmoran@collaborativefusion.com> <005301c668ab$39c4c150$8b00a8c0@multiplay.co.uk> <444E8F8A.9030409@rogers.com> <17487.34074.833134.823847@canoe.dclg.ca> In-Reply-To: <17487.34074.833134.823847@canoe.dclg.ca> Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit Cc: freebsd-performance@freebsd.org, Steven Hartland , Bill Moran Subject: Re: Dual-core CPU vs. very large cache X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Wed, 26 Apr 2006 14:52:01 -0000 David Gilbert wrote: > This isn't random. As I understand the issue, the Opteron HT bus > handles synchronization much faster. So for a game --- this doesn't > matter ... games don't (usually) need sync. Databases, however, live > on synchonizaton. If you're a Dell man (and already paying the Dell > tax), consider the Sun 1U's. They offer up to 4 cores in a 1U. > Sure, the HTT bus is wonderful. Intel will raise the FSB to 1067, but i still think we will see significant performance improvements on the new Core architecture. The Conroe CPU throughly trashes an AMD Athlon-X2 at a "higher" frequency. For those interested: http://www.anandtech.com/tradeshows/showdoc.aspx?i=2713 As much as i love AMDs cpus, the availability of good server motherboards and chipsets stinks, hopefully that will change when socket AM2 comes out. From owner-freebsd-performance@FreeBSD.ORG Wed Apr 26 14:55:44 2006 Return-Path: X-Original-To: freebsd-performance@freebsd.org Delivered-To: freebsd-performance@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 94A0D16A417 for ; Wed, 26 Apr 2006 14:55:44 +0000 (UTC) (envelope-from mikej@rogers.com) Received: from smtp108.rog.mail.re2.yahoo.com (smtp108.rog.mail.re2.yahoo.com [68.142.225.206]) by mx1.FreeBSD.org (Postfix) with SMTP id F0F0043D45 for ; Wed, 26 Apr 2006 14:55:43 +0000 (GMT) (envelope-from mikej@rogers.com) Received: (qmail 52805 invoked from network); 26 Apr 2006 14:55:43 -0000 DomainKey-Signature: a=rsa-sha1; q=dns; c=nofws; s=s1024; d=rogers.com; h=Received:Message-ID:Date:From:User-Agent:MIME-Version:To:CC:Subject:References:In-Reply-To:Content-Type:Content-Transfer-Encoding; b=m0s6x1zG3SU0VP4vwoqlI/GaTShQlPYWTpC6uNep+5a9e9/02macTMU5qOo5u0hSyQmqv5J+uWL1qcba/8zx7SiW8HkMgSNBQsjLNTeoe+obDNRgJNCZfOFg0Da7LI+dBrUPpPcc6Dq9rAYSDUZ30KiKe4Rry6Efb/AteEqwtUY= ; Received: from unknown (HELO ?70.31.50.218?) (mikej@rogers.com@70.31.50.218 with plain) by smtp108.rog.mail.re2.yahoo.com with SMTP; 26 Apr 2006 14:55:42 -0000 Message-ID: <444F89F8.2090405@rogers.com> Date: Wed, 26 Apr 2006 10:55:52 -0400 From: Mike Jakubik User-Agent: Thunderbird 1.5.0.2 (Windows/20060308) MIME-Version: 1.0 To: Bill Moran References: <20060425090739.8470143f.wmoran@collaborativefusion.com> <005301c668ab$39c4c150$8b00a8c0@multiplay.co.uk> <444E8F8A.9030409@rogers.com> <17487.34074.833134.823847@canoe.dclg.ca> <20060426104242.1209c152.wmoran@collaborativefusion.com> In-Reply-To: <20060426104242.1209c152.wmoran@collaborativefusion.com> Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit Cc: freebsd-performance@freebsd.org, David Gilbert Subject: Re: Dual-core CPU vs. very large cache X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Wed, 26 Apr 2006 14:55:45 -0000 Bill Moran wrote: > Lost me here. > > Are you saying 1U units from Sun? Or does Dell have a 1U called a > "Sun"? > > I am pretty-much locked into Dell - decision made by others. Actually, > I've been pretty happy with the Dell HW, but it's a shame they don't > offer AMD servers. > I'm quite sure he was referring to the x64 servers from SUN, tell your boss that Dell does not sell what you need. http://www.sun.com/servers/index.jsp?cat=Sun%20Fire%20x64%20Servers&tab=3 From owner-freebsd-performance@FreeBSD.ORG Wed Apr 26 15:31:37 2006 Return-Path: X-Original-To: freebsd-performance@freebsd.org Delivered-To: freebsd-performance@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 9AC1216A403 for ; Wed, 26 Apr 2006 15:31:37 +0000 (UTC) (envelope-from killing@multiplay.co.uk) Received: from multiplay.co.uk (core6.multiplay.co.uk [85.236.96.23]) by mx1.FreeBSD.org (Postfix) with ESMTP id ECF8D43D46 for ; Wed, 26 Apr 2006 15:31:36 +0000 (GMT) (envelope-from killing@multiplay.co.uk) Received: from vader ([212.135.219.181]) by multiplay.co.uk (multiplay.co.uk [85.236.96.23]) (MDaemon.PRO.v8.1.3.R) with ESMTP id md50002505954.msg for ; Wed, 26 Apr 2006 16:31:20 +0100 Message-ID: <00bd01c66946$6ce6f3a0$b5db87d4@multiplay.co.uk> From: "Steven Hartland" To: "Mike Jakubik" , "David Gilbert" References: <20060425090739.8470143f.wmoran@collaborativefusion.com> <005301c668ab$39c4c150$8b00a8c0@multiplay.co.uk> <444E8F8A.9030409@rogers.com> <17487.34074.833134.823847@canoe.dclg.ca> <444F8912.4010604@rogers.com> Date: Wed, 26 Apr 2006 16:30:55 +0100 MIME-Version: 1.0 Content-Type: text/plain; format=flowed; charset="iso-8859-1"; reply-type=response Content-Transfer-Encoding: 7bit X-Priority: 3 X-MSMail-Priority: Normal X-Mailer: Microsoft Outlook Express 6.00.2900.2869 X-MimeOLE: Produced By Microsoft MimeOLE V6.00.2900.2869 X-Spam-Processed: multiplay.co.uk, Wed, 26 Apr 2006 16:31:20 +0100 (not processed: message from valid local sender) X-MDRemoteIP: 212.135.219.181 X-Return-Path: killing@multiplay.co.uk X-MDaemon-Deliver-To: freebsd-performance@freebsd.org X-MDAV-Processed: multiplay.co.uk, Wed, 26 Apr 2006 16:31:22 +0100 Cc: freebsd-performance@freebsd.org, Bill Moran Subject: Re: Dual-core CPU vs. very large cache X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Wed, 26 Apr 2006 15:31:37 -0000 ----- Original Message ----- From: "Mike Jakubik" > David Gilbert wrote: >> This isn't random. As I understand the issue, the Opteron HT bus >> handles synchronization much faster. So for a game --- this doesn't >> matter ... games don't (usually) need sync. Databases, however, live >> on synchonizaton. If you're a Dell man (and already paying the Dell >> tax), consider the Sun 1U's. They offer up to 4 cores in a 1U. Not sure what your on about regard sync? If your infering that intel kit works better for DB's for some strange reason then I think you've been very much missinformed. > Sure, the HTT bus is wonderful. Intel will raise the FSB to 1067, but i > still think we will see significant performance improvements on the new > Core architecture. The Conroe CPU throughly trashes an AMD Athlon-X2 at > a "higher" frequency. For those interested: > > http://www.anandtech.com/tradeshows/showdoc.aspx?i=2713 > > > As much as i love AMDs cpus, the availability of good server > motherboards and chipsets stinks, hopefully that will change when socket > AM2 comes out. Unfortunately of no use atm as they wont be available for quite some time. IIRC AM2 is not a server solution just a client one the new server socket is significantly different. We would love to be able to deal with Dell but as they restrict themselves to the much lower performing Intel chips its not an option. Anyone who gets trapped into that side of things really need to consider their position seriously and tell whoever that Dell simply cannot supply that you need. Steve ================================================ This e.mail is private and confidential between Multiplay (UK) Ltd. and the person or entity to whom it is addressed. In the event of misdirection, the recipient is prohibited from using, copying, printing or otherwise disseminating it or any information contained in it. In the event of misdirection, illegible or incomplete transmission please telephone (023) 8024 3137 or return the E.mail to postmaster@multiplay.co.uk. From owner-freebsd-performance@FreeBSD.ORG Wed Apr 26 16:43:19 2006 Return-Path: X-Original-To: freebsd-performance@freebsd.org Delivered-To: freebsd-performance@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 854D516A400 for ; Wed, 26 Apr 2006 16:43:19 +0000 (UTC) (envelope-from mikej@rogers.com) Received: from smtp108.rog.mail.re2.yahoo.com (smtp108.rog.mail.re2.yahoo.com [68.142.225.206]) by mx1.FreeBSD.org (Postfix) with SMTP id D9D8543D55 for ; Wed, 26 Apr 2006 16:43:17 +0000 (GMT) (envelope-from mikej@rogers.com) Received: (qmail 55969 invoked from network); 26 Apr 2006 16:43:17 -0000 DomainKey-Signature: a=rsa-sha1; q=dns; c=nofws; s=s1024; d=rogers.com; h=Received:Message-ID:Date:From:User-Agent:MIME-Version:To:CC:Subject:References:In-Reply-To:Content-Type:Content-Transfer-Encoding; b=5fqMSRSUYhwQnsDPc1EyqlhrES8x1iK/lyu88SzLBT+vMvysE74Tdgy9avLR5WWVJ2sfYqA6U3spJxGX3IUQ/AZhKPW0MQtTy1SMkjE0nO57aXTfGzVR5AKbF6TFMn1RYnrfF+Y3gHarn1ChDSfdi1vZePZ+RgiEjujp0xtnrxw= ; Received: from unknown (HELO ?70.31.50.218?) (mikej@rogers.com@70.31.50.218 with plain) by smtp108.rog.mail.re2.yahoo.com with SMTP; 26 Apr 2006 16:43:17 -0000 Message-ID: <444FA32F.2060209@rogers.com> Date: Wed, 26 Apr 2006 12:43:27 -0400 From: Mike Jakubik User-Agent: Thunderbird 1.5.0.2 (Windows/20060308) MIME-Version: 1.0 To: Steven Hartland References: <20060425090739.8470143f.wmoran@collaborativefusion.com> <005301c668ab$39c4c150$8b00a8c0@multiplay.co.uk> <444E8F8A.9030409@rogers.com> <17487.34074.833134.823847@canoe.dclg.ca> <444F8912.4010604@rogers.com> <00bd01c66946$6ce6f3a0$b5db87d4@multiplay.co.uk> In-Reply-To: <00bd01c66946$6ce6f3a0$b5db87d4@multiplay.co.uk> Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit Cc: freebsd-performance@freebsd.org, Bill Moran , David Gilbert Subject: Re: Dual-core CPU vs. very large cache X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Wed, 26 Apr 2006 16:43:19 -0000 Steven Hartland wrote: > IIRC AM2 is not a server solution just a client one the new server > socket is significantly different. Its not a server/desktop thing, its a new socket that will allow AMD to use DDR2 memory. It applies to both Athlons and Opterons. From owner-freebsd-performance@FreeBSD.ORG Wed Apr 26 17:16:43 2006 Return-Path: X-Original-To: freebsd-performance@freebsd.org Delivered-To: freebsd-performance@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 7BF6916A400 for ; Wed, 26 Apr 2006 17:16:43 +0000 (UTC) (envelope-from killing@multiplay.co.uk) Received: from multiplay.co.uk (core6.multiplay.co.uk [85.236.96.23]) by mx1.FreeBSD.org (Postfix) with ESMTP id D163843D5A for ; Wed, 26 Apr 2006 17:16:42 +0000 (GMT) (envelope-from killing@multiplay.co.uk) Received: from vader ([212.135.219.181]) by multiplay.co.uk (multiplay.co.uk [85.236.96.23]) (MDaemon.PRO.v8.1.3.R) with ESMTP id md50002506339.msg for ; Wed, 26 Apr 2006 18:16:05 +0100 Message-ID: <014f01c66955$0ee2f790$b5db87d4@multiplay.co.uk> From: "Steven Hartland" To: "Mike Jakubik" References: <20060425090739.8470143f.wmoran@collaborativefusion.com> <005301c668ab$39c4c150$8b00a8c0@multiplay.co.uk> <444E8F8A.9030409@rogers.com> <17487.34074.833134.823847@canoe.dclg.ca> <444F8912.4010604@rogers.com> <00bd01c66946$6ce6f3a0$b5db87d4@multiplay.co.uk> <444FA32F.2060209@rogers.com> Date: Wed, 26 Apr 2006 18:15:40 +0100 MIME-Version: 1.0 Content-Type: text/plain; format=flowed; charset="iso-8859-1"; reply-type=response Content-Transfer-Encoding: 7bit X-Priority: 3 X-MSMail-Priority: Normal X-Mailer: Microsoft Outlook Express 6.00.2900.2869 X-MimeOLE: Produced By Microsoft MimeOLE V6.00.2900.2869 X-Spam-Processed: multiplay.co.uk, Wed, 26 Apr 2006 18:16:05 +0100 (not processed: message from valid local sender) X-MDRemoteIP: 212.135.219.181 X-Return-Path: killing@multiplay.co.uk X-MDaemon-Deliver-To: freebsd-performance@freebsd.org X-MDAV-Processed: multiplay.co.uk, Wed, 26 Apr 2006 18:16:07 +0100 Cc: freebsd-performance@freebsd.org, Bill Moran , David Gilbert Subject: Re: Dual-core CPU vs. very large cache X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Wed, 26 Apr 2006 17:16:43 -0000 ----- Original Message ----- From: "Mike Jakubik" > Steven Hartland wrote: >> IIRC AM2 is not a server solution just a client one the new server >> socket is significantly different. > > Its not a server/desktop thing, its a new socket that will allow AMD to > use DDR2 memory. It applies to both Athlons and Opterons. Checked back and I still get the impression this is not the case. Socket-AM2: Desktop DDR2 => http://www.anandtech.com/tradeshows/showdoc.aspx?i=2710&p=2 Socket-F: LGA and DDR2 for Servers => http://www.anandtech.com/tradeshows/showdoc.aspx?i=2710&p=3 ================================================ This e.mail is private and confidential between Multiplay (UK) Ltd. and the person or entity to whom it is addressed. In the event of misdirection, the recipient is prohibited from using, copying, printing or otherwise disseminating it or any information contained in it. In the event of misdirection, illegible or incomplete transmission please telephone (023) 8024 3137 or return the E.mail to postmaster@multiplay.co.uk. From owner-freebsd-performance@FreeBSD.ORG Thu Apr 27 03:21:00 2006 Return-Path: X-Original-To: freebsd-performance@freebsd.org Delivered-To: freebsd-performance@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id E695216A406 for ; Thu, 27 Apr 2006 03:21:00 +0000 (UTC) (envelope-from obrien@NUXI.com) Received: from dragon.NUXI.org (trang.nuxi.com [66.93.134.19]) by mx1.FreeBSD.org (Postfix) with ESMTP id 690FD43D4C for ; Thu, 27 Apr 2006 03:21:00 +0000 (GMT) (envelope-from obrien@NUXI.com) Received: from dragon.NUXI.org (obrien@localhost [127.0.0.1]) by dragon.NUXI.org (8.13.4/8.13.4) with ESMTP id k3R3Kexo086802; Wed, 26 Apr 2006 20:20:40 -0700 (PDT) (envelope-from obrien@dragon.NUXI.org) Received: (from obrien@localhost) by dragon.NUXI.org (8.13.4/8.13.1/Submit) id k3R3KcB5086801; Wed, 26 Apr 2006 20:20:38 -0700 (PDT) (envelope-from obrien) Date: Wed, 26 Apr 2006 20:20:38 -0700 From: "David O'Brien" To: Mike Jakubik Message-ID: <20060427032037.GA86693@dragon.NUXI.org> References: <20060425090739.8470143f.wmoran@collaborativefusion.com> <005301c668ab$39c4c150$8b00a8c0@multiplay.co.uk> <444E8F8A.9030409@rogers.com> <17487.34074.833134.823847@canoe.dclg.ca> <444F8912.4010604@rogers.com> <00bd01c66946$6ce6f3a0$b5db87d4@multiplay.co.uk> <444FA32F.2060209@rogers.com> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <444FA32F.2060209@rogers.com> X-Operating-System: FreeBSD 7.0-CURRENT Organization: The NUXI BSD Group X-Pgp-Rsa-Fingerprint: B7 4D 3E E9 11 39 5F A3 90 76 5D 69 58 D9 98 7A X-Pgp-Rsa-Keyid: 1024/34F9F9D5 User-Agent: Mutt/1.5.11 Cc: freebsd-performance@freebsd.org, Steven Hartland , Bill Moran , David Gilbert Subject: Re: Dual-core CPU vs. very large cache X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list Reply-To: obrien@freebsd.org List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Thu, 27 Apr 2006 03:21:01 -0000 On Wed, Apr 26, 2006 at 12:43:27PM -0400, Mike Jakubik wrote: > Steven Hartland wrote: > >IIRC AM2 is not a server solution just a client one the new server > >socket is significantly different. > > Its not a server/desktop thing, its a new socket that will allow AMD to > use DDR2 memory. It applies to both Athlons and Opterons. No! Socket AM2 is the DDR2 939-pin Athlon64 desktop replacement. Socket F(1207) is DDR2 the 940-pin Opteron server replacement. -- -- David (obrien@FreeBSD.org) From owner-freebsd-performance@FreeBSD.ORG Thu Apr 27 03:30:17 2006 Return-Path: X-Original-To: freebsd-performance@freebsd.org Delivered-To: freebsd-performance@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 0F04C16A408 for ; Thu, 27 Apr 2006 03:30:16 +0000 (UTC) (envelope-from mikej@rogers.com) Received: from smtp101.rog.mail.re2.yahoo.com (smtp101.rog.mail.re2.yahoo.com [206.190.36.79]) by mx1.FreeBSD.org (Postfix) with SMTP id 0CA0A43D4C for ; Thu, 27 Apr 2006 03:30:14 +0000 (GMT) (envelope-from mikej@rogers.com) Received: (qmail 20022 invoked from network); 27 Apr 2006 03:30:14 -0000 DomainKey-Signature: a=rsa-sha1; q=dns; c=nofws; s=s1024; d=rogers.com; h=Received:Message-ID:Date:From:User-Agent:MIME-Version:To:CC:Subject:References:In-Reply-To:Content-Type:Content-Transfer-Encoding; b=MG2V9KqfiKUFXLJQfCQvBW+NQIkwthWipAFiuqyq7C9ktvhX1+qvk6uMHJKGKVs+EUOfiVL09IP0vWdLNyCSGjwrMBZ38hg5hptSFYS+te9tZ99IzE1iAL9B7ggoCRVSQ3kJR41jeCaI6QTb4XJvvXfe1dyAOgXFdStXQr/0wgw= ; Received: from unknown (HELO ?70.31.50.218?) (mikej@rogers.com@70.31.50.218 with plain) by smtp101.rog.mail.re2.yahoo.com with SMTP; 27 Apr 2006 03:30:14 -0000 Message-ID: <44503AC6.3060609@rogers.com> Date: Wed, 26 Apr 2006 23:30:14 -0400 From: Mike Jakubik User-Agent: Thunderbird 1.5.0.2 (Windows/20060308) MIME-Version: 1.0 To: obrien@freebsd.org References: <20060425090739.8470143f.wmoran@collaborativefusion.com> <005301c668ab$39c4c150$8b00a8c0@multiplay.co.uk> <444E8F8A.9030409@rogers.com> <17487.34074.833134.823847@canoe.dclg.ca> <444F8912.4010604@rogers.com> <00bd01c66946$6ce6f3a0$b5db87d4@multiplay.co.uk> <444FA32F.2060209@rogers.com> <20060427032037.GA86693@dragon.NUXI.org> In-Reply-To: <20060427032037.GA86693@dragon.NUXI.org> Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit Cc: freebsd-performance@freebsd.org, Steven Hartland , Bill Moran , David Gilbert Subject: Re: Dual-core CPU vs. very large cache X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Thu, 27 Apr 2006 03:30:17 -0000 David O'Brien wrote: > On Wed, Apr 26, 2006 at 12:43:27PM -0400, Mike Jakubik wrote: > >> Steven Hartland wrote: >> >>> IIRC AM2 is not a server solution just a client one the new server >>> socket is significantly different. >>> >> Its not a server/desktop thing, its a new socket that will allow AMD to >> use DDR2 memory. It applies to both Athlons and Opterons. >> > > No! Socket AM2 is the DDR2 939-pin Athlon64 desktop replacement. > Socket F(1207) is DDR2 the 940-pin Opteron server replacement. > > Same crap, different pins. The change simply allows AMD cpus to use DDR2 memory, nothing more. From owner-freebsd-performance@FreeBSD.ORG Thu Apr 27 05:32:56 2006 Return-Path: X-Original-To: freebsd-performance@freebsd.org Delivered-To: freebsd-performance@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 92EC816A400 for ; Thu, 27 Apr 2006 05:32:56 +0000 (UTC) (envelope-from martin@gneto.com) Received: from mxfep01.bredband.com (mxfep01.bredband.com [195.54.107.70]) by mx1.FreeBSD.org (Postfix) with ESMTP id 8C03E43D49 for ; Thu, 27 Apr 2006 05:32:54 +0000 (GMT) (envelope-from martin@gneto.com) Received: from ua-83-227-181-30.cust.bredbandsbolaget.se ([83.227.181.30] [83.227.181.30]) by mxfep01.bredband.com with ESMTP id <20060427053253.EIIQ16061.mxfep01.bredband.com@ua-83-227-181-30.cust.bredbandsbolaget.se>; Thu, 27 Apr 2006 07:32:53 +0200 Received: from [192.168.10.11] (euklides.gneto.com [192.168.10.11]) by ua-83-227-181-30.cust.bredbandsbolaget.se (Postfix) with ESMTP id 3B62B67922; Thu, 27 Apr 2006 07:32:52 +0200 (CEST) Message-ID: <44505784.2030806@gneto.com> Date: Thu, 27 Apr 2006 07:32:52 +0200 From: Martin Nilsson User-Agent: Thunderbird 1.5.0.2 (X11/20060423) MIME-Version: 1.0 To: freebsd-performance@freebsd.org References: <20060425090739.8470143f.wmoran@collaborativefusion.com> <005301c668ab$39c4c150$8b00a8c0@multiplay.co.uk> <444E8F8A.9030409@rogers.com> <17487.34074.833134.823847@canoe.dclg.ca> <444F8912.4010604@rogers.com> In-Reply-To: <444F8912.4010604@rogers.com> Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit Cc: Mike Jakubik Subject: Re: Dual-core CPU vs. very large cache X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Thu, 27 Apr 2006 05:32:56 -0000 Mike Jakubik wrote: > As much as i love AMDs cpus, the availability of good server > motherboards and chipsets stinks, hopefully that will change when socket > AM2 comes out. That is an old myth: http://www.supermicro.com/Aplus/ From owner-freebsd-performance@FreeBSD.ORG Thu Apr 27 11:11:36 2006 Return-Path: X-Original-To: freebsd-performance@freebsd.org Delivered-To: freebsd-performance@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 77D2416A400; Thu, 27 Apr 2006 11:11:36 +0000 (UTC) (envelope-from killing@multiplay.co.uk) Received: from multiplay.co.uk (core6.multiplay.co.uk [85.236.96.23]) by mx1.FreeBSD.org (Postfix) with ESMTP id AA32943D46; Thu, 27 Apr 2006 11:11:35 +0000 (GMT) (envelope-from killing@multiplay.co.uk) Received: from vader ([212.135.219.179]) by multiplay.co.uk (multiplay.co.uk [85.236.96.23]) (MDaemon.PRO.v8.1.3.R) with ESMTP id md50002508629.msg; Thu, 27 Apr 2006 12:11:15 +0100 Message-ID: <007901c669eb$4a28d9a0$b3db87d4@multiplay.co.uk> From: "Steven Hartland" To: "Mike Jakubik" , References: <20060425090739.8470143f.wmoran@collaborativefusion.com><005301c668ab$39c4c150$8b00a8c0@multiplay.co.uk><444E8F8A.9030409@rogers.com><17487.34074.833134.823847@canoe.dclg.ca><444F8912.4010604@rogers.com><00bd01c66946$6ce6f3a0$b5db87d4@multiplay.co.uk><444FA32F.2060209@rogers.com><20060427032037.GA86693@dragon.NUXI.org> <44503AC6.3060609@rogers.com> Date: Thu, 27 Apr 2006 12:11:05 +0100 MIME-Version: 1.0 Content-Type: text/plain; format=flowed; charset="iso-8859-1"; reply-type=response Content-Transfer-Encoding: 7bit X-Priority: 3 X-MSMail-Priority: Normal X-Mailer: Microsoft Outlook Express 6.00.2900.2869 X-MimeOLE: Produced By Microsoft MimeOLE V6.00.2900.2869 X-Spam-Processed: multiplay.co.uk, Thu, 27 Apr 2006 12:11:15 +0100 (not processed: message from valid local sender) X-MDRemoteIP: 212.135.219.179 X-Return-Path: killing@multiplay.co.uk X-MDAV-Processed: multiplay.co.uk, Thu, 27 Apr 2006 12:11:17 +0100 Cc: freebsd-performance@freebsd.org, Bill Moran , David Gilbert Subject: Re: Dual-core CPU vs. very large cache X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Thu, 27 Apr 2006 11:11:36 -0000 ----- Original Message ----- From: "Mike Jakubik" >> No! Socket AM2 is the DDR2 939-pin Athlon64 desktop replacement. >> Socket F(1207) is DDR2 the 940-pin Opteron server replacement. >> > > Same crap, different pins. The change simply allows AMD cpus to use DDR2 > memory, nothing more. > Getting off topic now but I'd submit to you that a 1207 pin vs 940 pin is setting up for the access requirements of quad core something that AM2 is not going to be capable of hence quite different indeed. Steve ================================================ This e.mail is private and confidential between Multiplay (UK) Ltd. and the person or entity to whom it is addressed. In the event of misdirection, the recipient is prohibited from using, copying, printing or otherwise disseminating it or any information contained in it. In the event of misdirection, illegible or incomplete transmission please telephone (023) 8024 3137 or return the E.mail to postmaster@multiplay.co.uk. From owner-freebsd-performance@FreeBSD.ORG Thu Apr 27 16:08:55 2006 Return-Path: X-Original-To: freebsd-performance@freebsd.org Delivered-To: freebsd-performance@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id F32B016A400 for ; Thu, 27 Apr 2006 16:08:54 +0000 (UTC) (envelope-from mikej@rogers.com) Received: from smtp103.rog.mail.re2.yahoo.com (smtp103.rog.mail.re2.yahoo.com [206.190.36.81]) by mx1.FreeBSD.org (Postfix) with SMTP id 5AAAE43D48 for ; Thu, 27 Apr 2006 16:08:54 +0000 (GMT) (envelope-from mikej@rogers.com) Received: (qmail 35195 invoked from network); 27 Apr 2006 16:08:53 -0000 DomainKey-Signature: a=rsa-sha1; q=dns; c=nofws; s=s1024; d=rogers.com; h=Received:Message-ID:Date:From:User-Agent:MIME-Version:To:CC:Subject:References:In-Reply-To:Content-Type:Content-Transfer-Encoding; b=PiumsKUt6cVvPFlzWDOnDOW63vT3zLnq+vBFKA+Hl/JBls22fGxhrBmT2fypiL+MpNicoh/Q/KaZ+dDoYpAxUwsLftqnsXFaYAgvemXQ/CpcN9CNlxfUEoRxdZnteaMQ6Ql8q3d31lrPMS6+w8e1xVT7SO2j1tNKHJbcyxvr4hI= ; Received: from unknown (HELO ?70.31.50.218?) (mikej@rogers.com@70.31.50.218 with plain) by smtp103.rog.mail.re2.yahoo.com with SMTP; 27 Apr 2006 16:08:53 -0000 Message-ID: <4450EC9B.1050101@rogers.com> Date: Thu, 27 Apr 2006 12:08:59 -0400 From: Mike Jakubik User-Agent: Thunderbird 1.5.0.2 (Windows/20060308) MIME-Version: 1.0 To: Martin Nilsson References: <20060425090739.8470143f.wmoran@collaborativefusion.com> <005301c668ab$39c4c150$8b00a8c0@multiplay.co.uk> <444E8F8A.9030409@rogers.com> <17487.34074.833134.823847@canoe.dclg.ca> <444F8912.4010604@rogers.com> <44505784.2030806@gneto.com> In-Reply-To: <44505784.2030806@gneto.com> Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit Cc: freebsd-performance@freebsd.org Subject: Re: Dual-core CPU vs. very large cache X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Thu, 27 Apr 2006 16:08:55 -0000 Martin Nilsson wrote: > Mike Jakubik wrote: >> As much as i love AMDs cpus, the availability of good server >> motherboards and chipsets stinks, hopefully that will change when >> socket AM2 comes out. > > That is an old myth: http://www.supermicro.com/Aplus/ Its not an old myth. Find me a single cpu opteron board, with dual Intel network cards (bge and nve suck ass) connected to a PCIe bus. Sorry, it doesn't exist. You have your pick of the old AMD chipset, the crappy Nvidia, or the unsupported ServerWorks, which still doesn't have PCIe. From owner-freebsd-performance@FreeBSD.ORG Thu Apr 27 16:21:42 2006 Return-Path: X-Original-To: freebsd-performance@freebsd.org Delivered-To: freebsd-performance@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 396D316A413 for ; Thu, 27 Apr 2006 16:21:42 +0000 (UTC) (envelope-from killing@multiplay.co.uk) Received: from multiplay.co.uk (core6.multiplay.co.uk [85.236.96.23]) by mx1.FreeBSD.org (Postfix) with ESMTP id 6F73743D4C for ; Thu, 27 Apr 2006 16:21:41 +0000 (GMT) (envelope-from killing@multiplay.co.uk) Received: from vader ([212.135.219.179]) by multiplay.co.uk (multiplay.co.uk [85.236.96.23]) (MDaemon.PRO.v8.1.3.R) with ESMTP id md50002509758.msg for ; Thu, 27 Apr 2006 17:21:36 +0100 Message-ID: <029201c66a16$a3c7e890$b3db87d4@multiplay.co.uk> From: "Steven Hartland" To: "Mike Jakubik" , "Martin Nilsson" References: <20060425090739.8470143f.wmoran@collaborativefusion.com> <005301c668ab$39c4c150$8b00a8c0@multiplay.co.uk> <444E8F8A.9030409@rogers.com> <17487.34074.833134.823847@canoe.dclg.ca><444F8912.4010604@rogers.com> <44505784.2030806@gneto.com> <4450EC9B.1050101@rogers.com> Date: Thu, 27 Apr 2006 17:21:22 +0100 MIME-Version: 1.0 Content-Type: text/plain; format=flowed; charset="iso-8859-1"; reply-type=response Content-Transfer-Encoding: 7bit X-Priority: 3 X-MSMail-Priority: Normal X-Mailer: Microsoft Outlook Express 6.00.2900.2869 X-MimeOLE: Produced By Microsoft MimeOLE V6.00.2900.2869 X-Spam-Processed: multiplay.co.uk, Thu, 27 Apr 2006 17:21:36 +0100 (not processed: message from valid local sender) X-MDRemoteIP: 212.135.219.179 X-Return-Path: killing@multiplay.co.uk X-MDaemon-Deliver-To: freebsd-performance@freebsd.org X-MDAV-Processed: multiplay.co.uk, Thu, 27 Apr 2006 17:21:37 +0100 Cc: freebsd-performance@freebsd.org Subject: Re: Dual-core CPU vs. very large cache X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Thu, 27 Apr 2006 16:21:42 -0000 ----- Original Message ----- From: "Mike Jakubik" > Martin Nilsson wrote: >> Mike Jakubik wrote: >>> As much as i love AMDs cpus, the availability of good server >>> motherboards and chipsets stinks, hopefully that will change when >>> socket AM2 comes out. >> >> That is an old myth: http://www.supermicro.com/Aplus/ > > Its not an old myth. Find me a single cpu opteron board, with dual Intel > network cards (bge and nve suck ass) connected to a PCIe bus. Sorry, it > doesn't exist. You have your pick of the old AMD chipset, the crappy > Nvidia, or the unsupported ServerWorks, which still doesn't have PCIe. I suspect it doesn't exist because there's no market for single cpu opteron boards, that's a desktop requirement not really server. If you want server boards look for dual proc boards, there is a good selection out there with a myriad of options. Not sure why you think bge sucks not had any problems with them here, fairly good performance and reliable. Steve ================================================ This e.mail is private and confidential between Multiplay (UK) Ltd. and the person or entity to whom it is addressed. In the event of misdirection, the recipient is prohibited from using, copying, printing or otherwise disseminating it or any information contained in it. In the event of misdirection, illegible or incomplete transmission please telephone (023) 8024 3137 or return the E.mail to postmaster@multiplay.co.uk. From owner-freebsd-performance@FreeBSD.ORG Thu Apr 27 16:27:26 2006 Return-Path: X-Original-To: freebsd-performance@freebsd.org Delivered-To: freebsd-performance@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 5208816A403 for ; Thu, 27 Apr 2006 16:27:26 +0000 (UTC) (envelope-from mikej@rogers.com) Received: from smtp108.rog.mail.re2.yahoo.com (smtp108.rog.mail.re2.yahoo.com [68.142.225.206]) by mx1.FreeBSD.org (Postfix) with SMTP id 912E843D46 for ; Thu, 27 Apr 2006 16:27:25 +0000 (GMT) (envelope-from mikej@rogers.com) Received: (qmail 29245 invoked from network); 27 Apr 2006 16:27:24 -0000 DomainKey-Signature: a=rsa-sha1; q=dns; c=nofws; s=s1024; d=rogers.com; h=Received:Message-ID:Date:From:User-Agent:MIME-Version:To:CC:Subject:References:In-Reply-To:Content-Type:Content-Transfer-Encoding; b=kDdZiAVFhcfaRSLI9ZAgn4QNKiKz0oJma+JMu3QHn5/PwosI7B1y1HGcxF5Bp5Mpe7uTeZv0wts34ZHZqxWF8A5OW60uY9iTaqT/ZSnmnY8SQb28XCFUrLUcz/BQ83XjsdDj8Whb+hR4NgOTyweQCRaHI49N+2J18suB5f4sRpI= ; Received: from unknown (HELO ?70.31.50.218?) (mikej@rogers.com@70.31.50.218 with plain) by smtp108.rog.mail.re2.yahoo.com with SMTP; 27 Apr 2006 16:27:24 -0000 Message-ID: <4450F0F2.9040102@rogers.com> Date: Thu, 27 Apr 2006 12:27:30 -0400 From: Mike Jakubik User-Agent: Thunderbird 1.5.0.2 (Windows/20060308) MIME-Version: 1.0 To: Steven Hartland References: <20060425090739.8470143f.wmoran@collaborativefusion.com> <005301c668ab$39c4c150$8b00a8c0@multiplay.co.uk> <444E8F8A.9030409@rogers.com> <17487.34074.833134.823847@canoe.dclg.ca><444F8912.4010604@rogers.com> <44505784.2030806@gneto.com> <4450EC9B.1050101@rogers.com> <029201c66a16$a3c7e890$b3db87d4@multiplay.co.uk> In-Reply-To: <029201c66a16$a3c7e890$b3db87d4@multiplay.co.uk> Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit Cc: freebsd-performance@freebsd.org, Martin Nilsson Subject: Re: Dual-core CPU vs. very large cache X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Thu, 27 Apr 2006 16:27:26 -0000 Steven Hartland wrote: > ----- Original Message ----- From: "Mike Jakubik" > > >> Martin Nilsson wrote: >>> Mike Jakubik wrote: >>>> As much as i love AMDs cpus, the availability of good server >>>> motherboards and chipsets stinks, hopefully that will change when >>>> socket AM2 comes out. >>> >>> That is an old myth: http://www.supermicro.com/Aplus/ >> >> Its not an old myth. Find me a single cpu opteron board, with dual >> Intel network cards (bge and nve suck ass) connected to a PCIe bus. >> Sorry, it doesn't exist. You have your pick of the old AMD chipset, >> the crappy Nvidia, or the unsupported ServerWorks, which still >> doesn't have PCIe. > > I suspect it doesn't exist because there's no market for single > cpu opteron boards, that's a desktop requirement not really server. > Yes, there is. Just not with the chipset/network card i want. Its the same story for dual cpu boards. Intel may not have the performance crown right now, but their products are reliable and well supported. (Does nvidia provide source code to their chipset/network card for freebsd? No. Does Broadcom... No. Does Intel? Yes.) > If you want server boards look for dual proc boards, there is a > good selection out there with a myriad of options. > > Not sure why you think bge sucks not had any problems with them > here, fairly good performance and reliable. Just look around the list on the continuous problems people have with that and the nve card. I would never feel safe putting these in production. From owner-freebsd-performance@FreeBSD.ORG Thu Apr 27 16:35:47 2006 Return-Path: X-Original-To: freebsd-performance@freebsd.org Delivered-To: freebsd-performance@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 4093716A405 for ; Thu, 27 Apr 2006 16:35:47 +0000 (UTC) (envelope-from killing@multiplay.co.uk) Received: from multiplay.co.uk (core6.multiplay.co.uk [85.236.96.23]) by mx1.FreeBSD.org (Postfix) with ESMTP id 7DFF943D46 for ; Thu, 27 Apr 2006 16:35:45 +0000 (GMT) (envelope-from killing@multiplay.co.uk) Received: from vader ([212.135.219.179]) by multiplay.co.uk (multiplay.co.uk [85.236.96.23]) (MDaemon.PRO.v8.1.3.R) with ESMTP id md50002509836.msg for ; Thu, 27 Apr 2006 17:34:55 +0100 Message-ID: <02b401c66a18$8058f230$b3db87d4@multiplay.co.uk> From: "Steven Hartland" To: "Mike Jakubik" References: <20060425090739.8470143f.wmoran@collaborativefusion.com> <005301c668ab$39c4c150$8b00a8c0@multiplay.co.uk> <444E8F8A.9030409@rogers.com> <17487.34074.833134.823847@canoe.dclg.ca><444F8912.4010604@rogers.com><44505784.2030806@gneto.com> <4450EC9B.1050101@rogers.com><029201c66a16$a3c7e890$b3db87d4@multiplay.co.uk> <4450F0F2.9040102@rogers.com> Date: Thu, 27 Apr 2006 17:34:42 +0100 MIME-Version: 1.0 Content-Type: text/plain; format=flowed; charset="iso-8859-1"; reply-type=response Content-Transfer-Encoding: 7bit X-Priority: 3 X-MSMail-Priority: Normal X-Mailer: Microsoft Outlook Express 6.00.2900.2869 X-MimeOLE: Produced By Microsoft MimeOLE V6.00.2900.2869 X-Spam-Processed: multiplay.co.uk, Thu, 27 Apr 2006 17:34:55 +0100 (not processed: message from valid local sender) X-MDRemoteIP: 212.135.219.179 X-Return-Path: killing@multiplay.co.uk X-MDaemon-Deliver-To: freebsd-performance@freebsd.org X-MDAV-Processed: multiplay.co.uk, Thu, 27 Apr 2006 17:34:57 +0100 Cc: freebsd-performance@freebsd.org, Martin Nilsson Subject: Re: Dual-core CPU vs. very large cache X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Thu, 27 Apr 2006 16:35:49 -0000 ----- Original Message ----- From: "Mike Jakubik" > > Just look around the list on the continuous problems people have with > that and the nve card. I would never feel safe putting these in production. I would agree with nve but not had any problems with bge here and we put them under quite a bit of load as busy DB, Web, FTP and Samba servers not to mention metric tone of game servers. If you want a specific netcard nothing to stop you putting in a PCI-X card which is what we do when we want Fibre, you dont tend to find many MB netcards are fibre :) Steve ================================================ This e.mail is private and confidential between Multiplay (UK) Ltd. and the person or entity to whom it is addressed. In the event of misdirection, the recipient is prohibited from using, copying, printing or otherwise disseminating it or any information contained in it. In the event of misdirection, illegible or incomplete transmission please telephone (023) 8024 3137 or return the E.mail to postmaster@multiplay.co.uk. From owner-freebsd-performance@FreeBSD.ORG Thu Apr 27 16:41:56 2006 Return-Path: X-Original-To: freebsd-performance@freebsd.org Delivered-To: freebsd-performance@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 5E59C16A40A for ; Thu, 27 Apr 2006 16:41:56 +0000 (UTC) (envelope-from mikej@rogers.com) Received: from smtp106.rog.mail.re2.yahoo.com (smtp106.rog.mail.re2.yahoo.com [68.142.225.204]) by mx1.FreeBSD.org (Postfix) with SMTP id C546B43D5C for ; Thu, 27 Apr 2006 16:41:55 +0000 (GMT) (envelope-from mikej@rogers.com) Received: (qmail 4842 invoked from network); 27 Apr 2006 16:41:55 -0000 DomainKey-Signature: a=rsa-sha1; q=dns; c=nofws; s=s1024; d=rogers.com; h=Received:Message-ID:Date:From:User-Agent:MIME-Version:To:CC:Subject:References:In-Reply-To:Content-Type:Content-Transfer-Encoding; b=DhiUtigBDQf70Q0EhSbjoAajwJnid5MdQa3BClnN6PSncG2N5BZMMTBGcm/YcZHUBdqPyENILJxg00U+QeLFpdUd6SCxe3rDtaLSR8y82kyU8CTbUbfK1+SvYV4eXdjY8iRAaAKxDKBmOXK1vkOkiIPdYydcZLZ/aJ4iLFd0IIg= ; Received: from unknown (HELO ?70.31.50.218?) (mikej@rogers.com@70.31.50.218 with plain) by smtp106.rog.mail.re2.yahoo.com with SMTP; 27 Apr 2006 16:41:55 -0000 Message-ID: <4450F459.60505@rogers.com> Date: Thu, 27 Apr 2006 12:42:01 -0400 From: Mike Jakubik User-Agent: Thunderbird 1.5.0.2 (Windows/20060308) MIME-Version: 1.0 To: Steven Hartland References: <20060425090739.8470143f.wmoran@collaborativefusion.com> <005301c668ab$39c4c150$8b00a8c0@multiplay.co.uk> <444E8F8A.9030409@rogers.com> <17487.34074.833134.823847@canoe.dclg.ca><444F8912.4010604@rogers.com><44505784.2030806@gneto.com> <4450EC9B.1050101@rogers.com><029201c66a16$a3c7e890$b3db87d4@multiplay.co.uk> <4450F0F2.9040102@rogers.com> <02b401c66a18$8058f230$b3db87d4@multiplay.co.uk> In-Reply-To: <02b401c66a18$8058f230$b3db87d4@multiplay.co.uk> Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit Cc: freebsd-performance@freebsd.org, Martin Nilsson Subject: Re: Dual-core CPU vs. very large cache X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Thu, 27 Apr 2006 16:41:56 -0000 Steven Hartland wrote: > ----- Original Message ----- From: "Mike Jakubik" >> >> Just look around the list on the continuous problems people have with >> that and the nve card. I would never feel safe putting these in >> production. > > I would agree with nve but not had any problems with bge > here and we put them under quite a bit of load as busy > DB, Web, FTP and Samba servers not to mention metric tone > of game servers. > Sure, not to say they are all broken, but many do have problems, so it becomes a gamble. > If you want a specific netcard nothing to stop you putting > in a PCI-X card which is what we do when we want Fibre, you > dont tend to find many MB netcards are fibre :) Yes there is, i need a 1U single Opteron board, with 2 integrated cards. I guess the current AMD offerings do not meet my requirements. I am working on a commercial product, which is an all in one 1U appliance (running fbsd of course), and i had to go with Intel just for reasons of availability, stability, and support. From owner-freebsd-performance@FreeBSD.ORG Thu Apr 27 18:57:28 2006 Return-Path: X-Original-To: freebsd-performance@freebsd.org Delivered-To: freebsd-performance@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id E6C9D16A402 for ; Thu, 27 Apr 2006 18:57:28 +0000 (UTC) (envelope-from obrien@NUXI.com) Received: from dragon.NUXI.org (trang.nuxi.com [66.93.134.19]) by mx1.FreeBSD.org (Postfix) with ESMTP id 85A1743D46 for ; Thu, 27 Apr 2006 18:57:28 +0000 (GMT) (envelope-from obrien@NUXI.com) Received: from dragon.NUXI.org (obrien@localhost [127.0.0.1]) by dragon.NUXI.org (8.13.4/8.13.4) with ESMTP id k3RIvNm4002783; Thu, 27 Apr 2006 11:57:23 -0700 (PDT) (envelope-from obrien@dragon.NUXI.org) Received: (from obrien@localhost) by dragon.NUXI.org (8.13.4/8.13.1/Submit) id k3RIvMNI002782; Thu, 27 Apr 2006 11:57:22 -0700 (PDT) (envelope-from obrien) Date: Thu, 27 Apr 2006 11:57:22 -0700 From: "David O'Brien" To: Mike Jakubik Message-ID: <20060427185722.GA2741@dragon.NUXI.org> References: <20060425090739.8470143f.wmoran@collaborativefusion.com> <005301c668ab$39c4c150$8b00a8c0@multiplay.co.uk> <444E8F8A.9030409@rogers.com> <17487.34074.833134.823847@canoe.dclg.ca> <444F8912.4010604@rogers.com> <00bd01c66946$6ce6f3a0$b5db87d4@multiplay.co.uk> <444FA32F.2060209@rogers.com> <20060427032037.GA86693@dragon.NUXI.org> <44503AC6.3060609@rogers.com> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <44503AC6.3060609@rogers.com> X-Operating-System: FreeBSD 7.0-CURRENT Organization: The NUXI BSD Group X-Pgp-Rsa-Fingerprint: B7 4D 3E E9 11 39 5F A3 90 76 5D 69 58 D9 98 7A X-Pgp-Rsa-Keyid: 1024/34F9F9D5 User-Agent: Mutt/1.5.11 Cc: freebsd-performance@freebsd.org, Steven Hartland , Bill Moran , David Gilbert Subject: Re: Dual-core CPU vs. very large cache X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list Reply-To: obrien@freebsd.org List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Thu, 27 Apr 2006 18:57:29 -0000 On Wed, Apr 26, 2006 at 11:30:14PM -0400, Mike Jakubik wrote: > David O'Brien wrote: > >On Wed, Apr 26, 2006 at 12:43:27PM -0400, Mike Jakubik wrote: > > > >>Steven Hartland wrote: > >> > >>>IIRC AM2 is not a server solution just a client one the new server > >>>socket is significantly different. > >>> > >>Its not a server/desktop thing, its a new socket that will allow AMD to > >>use DDR2 memory. It applies to both Athlons and Opterons. > > > >No! Socket AM2 is the DDR2 939-pin Athlon64 desktop replacement. > >Socket F(1207) is DDR2 the 940-pin Opteron server replacement. > > Same crap, different pins. The change simply allows AMD cpus to use DDR2 > memory, nothing more. What does that mean? "Same Crap"? I was giving accurate and correct names of the sockets and that there are two different Opteron rev.F sockets. -- -- David (obrien@FreeBSD.org) Q: Because it reverses the logical flow of conversation. A: Why is top-posting (putting a reply at the top of the message) frowned upon? From owner-freebsd-performance@FreeBSD.ORG Thu Apr 27 19:03:19 2006 Return-Path: X-Original-To: freebsd-performance@freebsd.org Delivered-To: freebsd-performance@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 0523E16A402 for ; Thu, 27 Apr 2006 19:03:19 +0000 (UTC) (envelope-from obrien@NUXI.com) Received: from dragon.NUXI.org (trang.nuxi.com [66.93.134.19]) by mx1.FreeBSD.org (Postfix) with ESMTP id 9BF2243D67 for ; Thu, 27 Apr 2006 19:03:18 +0000 (GMT) (envelope-from obrien@NUXI.com) Received: from dragon.NUXI.org (obrien@localhost [127.0.0.1]) by dragon.NUXI.org (8.13.4/8.13.4) with ESMTP id k3RJ3E3r002894; Thu, 27 Apr 2006 12:03:14 -0700 (PDT) (envelope-from obrien@dragon.NUXI.org) Received: (from obrien@localhost) by dragon.NUXI.org (8.13.4/8.13.1/Submit) id k3RJ3D9k002893; Thu, 27 Apr 2006 12:03:13 -0700 (PDT) (envelope-from obrien) Date: Thu, 27 Apr 2006 12:03:13 -0700 From: "David O'Brien" To: Steven Hartland Message-ID: <20060427190313.GB2741@dragon.NUXI.org> References: <44503AC6.3060609@rogers.com> <007901c669eb$4a28d9a0$b3db87d4@multiplay.co.uk> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <007901c669eb$4a28d9a0$b3db87d4@multiplay.co.uk> X-Operating-System: FreeBSD 7.0-CURRENT Organization: The NUXI BSD Group X-Pgp-Rsa-Fingerprint: B7 4D 3E E9 11 39 5F A3 90 76 5D 69 58 D9 98 7A X-Pgp-Rsa-Keyid: 1024/34F9F9D5 User-Agent: Mutt/1.5.11 Cc: Mike Jakubik , freebsd-performance@freebsd.org, Bill Moran , David Gilbert Subject: Re: Dual-core CPU vs. very large cache X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list Reply-To: obrien@freebsd.org List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Thu, 27 Apr 2006 19:03:19 -0000 On Thu, Apr 27, 2006 at 12:11:05PM +0100, Steven Hartland wrote: > ----- Original Message ----- > From: "Mike Jakubik" > > >>No! Socket AM2 is the DDR2 939-pin Athlon64 desktop replacement. > >>Socket F(1207) is DDR2 the 940-pin Opteron server replacement. > >> > > > >Same crap, different pins. The change simply allows AMD cpus to use DDR2 > >memory, nothing more. > > Getting off topic now but I'd submit to you that a 1207 pin vs 940 pin > is setting up for the access requirements of quad core something that > AM2 is not going to be capable of hence quite different indeed. Nope. Quad core is internal connections between cores - not external. So you don't need extra pins to support quad-core vs. dual-core. -- -- David (obrien@FreeBSD.org) Q: Because it reverses the logical flow of conversation. A: Why is top-posting (putting a reply at the top of the message) frowned upon? From owner-freebsd-performance@FreeBSD.ORG Thu Apr 27 19:04:15 2006 Return-Path: X-Original-To: freebsd-performance@freebsd.org Delivered-To: freebsd-performance@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 6630116A474 for ; Thu, 27 Apr 2006 19:04:15 +0000 (UTC) (envelope-from mikej@rogers.com) Received: from smtp103.rog.mail.re2.yahoo.com (smtp103.rog.mail.re2.yahoo.com [206.190.36.81]) by mx1.FreeBSD.org (Postfix) with SMTP id E30D643D46 for ; Thu, 27 Apr 2006 19:04:11 +0000 (GMT) (envelope-from mikej@rogers.com) Received: (qmail 99748 invoked from network); 27 Apr 2006 19:04:11 -0000 DomainKey-Signature: a=rsa-sha1; q=dns; c=nofws; s=s1024; d=rogers.com; h=Received:Message-ID:Date:From:User-Agent:MIME-Version:To:CC:Subject:References:In-Reply-To:Content-Type:Content-Transfer-Encoding; b=FA9m8gbm9Jucl5v2ZWgcCTsXk/gftekMILeUdqor9V2xGceUw5/TIEyP4nsmji0rf7z6F7MRfr2TcX9dC8aAYWXvM4RUM47w1je7R5nk33Jo+towDORJQqzw+S4REMuV7tXjqFuX00ikt/32B0Rz05Lys6vitRVtaQ+JPjx+7oQ= ; Received: from unknown (HELO ?70.31.50.218?) (mikej@rogers.com@70.31.50.218 with plain) by smtp103.rog.mail.re2.yahoo.com with SMTP; 27 Apr 2006 19:04:11 -0000 Message-ID: <445115B0.3080900@rogers.com> Date: Thu, 27 Apr 2006 15:04:16 -0400 From: Mike Jakubik User-Agent: Thunderbird 1.5.0.2 (Windows/20060308) MIME-Version: 1.0 To: obrien@freebsd.org References: <20060425090739.8470143f.wmoran@collaborativefusion.com> <005301c668ab$39c4c150$8b00a8c0@multiplay.co.uk> <444E8F8A.9030409@rogers.com> <17487.34074.833134.823847@canoe.dclg.ca> <444F8912.4010604@rogers.com> <00bd01c66946$6ce6f3a0$b5db87d4@multiplay.co.uk> <444FA32F.2060209@rogers.com> <20060427032037.GA86693@dragon.NUXI.org> <44503AC6.3060609@rogers.com> <20060427185722.GA2741@dragon.NUXI.org> In-Reply-To: <20060427185722.GA2741@dragon.NUXI.org> Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit Cc: freebsd-performance@freebsd.org, Steven Hartland , Bill Moran , David Gilbert Subject: Re: Dual-core CPU vs. very large cache X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Thu, 27 Apr 2006 19:04:15 -0000 David O'Brien wrote: > On Wed, Apr 26, 2006 at 11:30:14PM -0400, Mike Jakubik wrote: > >> David O'Brien wrote: >> >>> On Wed, Apr 26, 2006 at 12:43:27PM -0400, Mike Jakubik wrote: >>> >>> >>>> Steven Hartland wrote: >>>> >>>> >>>>> IIRC AM2 is not a server solution just a client one the new server >>>>> socket is significantly different. >>>>> >>>>> >>>> Its not a server/desktop thing, its a new socket that will allow AMD to >>>> use DDR2 memory. It applies to both Athlons and Opterons. >>>> >>> No! Socket AM2 is the DDR2 939-pin Athlon64 desktop replacement. >>> Socket F(1207) is DDR2 the 940-pin Opteron server replacement. >>> >> Same crap, different pins. The change simply allows AMD cpus to use DDR2 >> memory, nothing more. >> > > What does that mean? "Same Crap"? I was giving accurate and correct > names of the sockets and that there are two different Opteron rev.F > sockets. > > Correct, however in the original discussion i stated that i hope some new chipsets will appear when the new socket is introduced, which adds DDR2 support. Then someone started nit picking about the naming of the sockets. From owner-freebsd-performance@FreeBSD.ORG Thu Apr 27 19:29:07 2006 Return-Path: X-Original-To: freebsd-performance@freebsd.org Delivered-To: freebsd-performance@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 13AC716A401; Thu, 27 Apr 2006 19:29:07 +0000 (UTC) (envelope-from killing@multiplay.co.uk) Received: from multiplay.co.uk (core6.multiplay.co.uk [85.236.96.23]) by mx1.FreeBSD.org (Postfix) with ESMTP id 0CC0243D48; Thu, 27 Apr 2006 19:29:05 +0000 (GMT) (envelope-from killing@multiplay.co.uk) Received: from vader ([212.135.219.179]) by multiplay.co.uk (multiplay.co.uk [85.236.96.23]) (MDaemon.PRO.v8.1.3.R) with ESMTP id md50002510428.msg; Thu, 27 Apr 2006 20:28:53 +0100 Message-ID: <00b101c66a30$ceb32820$b3db87d4@multiplay.co.uk> From: "Steven Hartland" To: References: <44503AC6.3060609@rogers.com> <007901c669eb$4a28d9a0$b3db87d4@multiplay.co.uk> <20060427190313.GB2741@dragon.NUXI.org> Date: Thu, 27 Apr 2006 20:28:42 +0100 MIME-Version: 1.0 Content-Type: text/plain; format=flowed; charset="iso-8859-1"; reply-type=original Content-Transfer-Encoding: 7bit X-Priority: 3 X-MSMail-Priority: Normal X-Mailer: Microsoft Outlook Express 6.00.2900.2869 X-MimeOLE: Produced By Microsoft MimeOLE V6.00.2900.2869 X-Spam-Processed: multiplay.co.uk, Thu, 27 Apr 2006 20:28:53 +0100 (not processed: message from valid local sender) X-MDRemoteIP: 212.135.219.179 X-Return-Path: killing@multiplay.co.uk X-MDAV-Processed: multiplay.co.uk, Thu, 27 Apr 2006 20:28:55 +0100 Cc: Mike Jakubik , freebsd-performance@freebsd.org, Bill Moran , David Gilbert Subject: Re: Dual-core CPU vs. very large cache X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Thu, 27 Apr 2006 19:29:07 -0000 ----- Original Message ----- From: "David O'Brien" > On Thu, Apr 27, 2006 at 12:11:05PM +0100, Steven Hartland wrote: >> Getting off topic now but I'd submit to you that a 1207 pin vs 940 pin >> is setting up for the access requirements of quad core something that >> AM2 is not going to be capable of hence quite different indeed. > > Nope. Quad core is internal connections between cores - not external. > So you don't need extra pins to support quad-core vs. dual-core. There was talk that there would be an enhanced memory controller or possibly dual memory controllers in quad core cpus which would be supported by the extra pins in Socket-F. Either way I suspect that the additional pins will be used to provide additional external bandwidth to successfully supply the upcoming multi core CPU's with enough data so they aren't starved. All hearsay though as I've not see any real specs :) Steve ================================================ This e.mail is private and confidential between Multiplay (UK) Ltd. and the person or entity to whom it is addressed. In the event of misdirection, the recipient is prohibited from using, copying, printing or otherwise disseminating it or any information contained in it. In the event of misdirection, illegible or incomplete transmission please telephone (023) 8024 3137 or return the E.mail to postmaster@multiplay.co.uk. From owner-freebsd-performance@FreeBSD.ORG Fri Apr 28 10:29:13 2006 Return-Path: X-Original-To: freebsd-performance@freebsd.org Delivered-To: freebsd-performance@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id B1DCE16A403 for ; Fri, 28 Apr 2006 10:29:13 +0000 (UTC) (envelope-from Shane@007Marketing.com) Received: from ash25e.internode.on.net (ash25e.internode.on.net [203.16.214.182]) by mx1.FreeBSD.org (Postfix) with ESMTP id 1D28D43D6A for ; Fri, 28 Apr 2006 10:29:07 +0000 (GMT) (envelope-from Shane@007Marketing.com) Received: from [192.168.8.50] (ppp247-71.static.internode.on.net [203.122.247.71]) by ash25e.internode.on.net (8.13.6/8.13.5) with ESMTP id k3SAT5le002281 for ; Fri, 28 Apr 2006 19:59:06 +0930 (CST) (envelope-from Shane@007Marketing.com) User-Agent: Microsoft-Entourage/10.1.4.030702.0 Date: Fri, 28 Apr 2006 19:59:03 +0930 From: Shane Ambler To: FreeBSD Mailing Lists Message-ID: In-Reply-To: <4450EC9B.1050101@rogers.com> Mime-version: 1.0 Content-type: text/plain; charset="US-ASCII" Content-transfer-encoding: 7bit Subject: Re: Dual-core CPU vs. very large cache X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 28 Apr 2006 10:29:13 -0000 On 28/4/2006 1:38, "Mike Jakubik" wrote: > Martin Nilsson wrote: >> Mike Jakubik wrote: >>> As much as i love AMDs cpus, the availability of good server >>> motherboards and chipsets stinks, hopefully that will change when >>> socket AM2 comes out. >> >> That is an old myth: http://www.supermicro.com/Aplus/ > > Its not an old myth. Find me a single cpu opteron board, with dual Intel > network cards (bge and nve suck ass) connected to a PCIe bus. Sorry, it > doesn't exist. You have your pick of the old AMD chipset, the crappy > Nvidia, or the unsupported ServerWorks, which still doesn't have PCIe. I haven't dug real deep for data but a casual look through the Intel's dual Xeon board specs shows they don't say where their network controllers are connected but some of their boards have an Intel ethernet controller as well as "one Marvell* Yukon* -EC 88E8050 PCI Express*" Sounds to me like Intel doesn't have ethernet controllers that run on PCIe regardless of the cpu From owner-freebsd-performance@FreeBSD.ORG Fri Apr 28 14:47:24 2006 Return-Path: X-Original-To: freebsd-performance@freebsd.org Delivered-To: freebsd-performance@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 1DC6116A401 for ; Fri, 28 Apr 2006 14:47:24 +0000 (UTC) (envelope-from eddy+public+spam@noc.everquick.net) Received: from a.mx.ict1.everquick.net (a.mx.ict1.everquick.net [204.10.191.21]) by mx1.FreeBSD.org (Postfix) with ESMTP id 6D3C643D46 for ; Fri, 28 Apr 2006 14:47:23 +0000 (GMT) (envelope-from eddy+public+spam@noc.everquick.net) Received: from pop.ict1.everquick.net (localhost [127.0.0.1]) by a.mx.ict1.everquick.net (8.12.10/8.12.10) with ESMTP id k3SElK4F006275 for ; Fri, 28 Apr 2006 14:47:21 GMT X-Everquick-No-Abuse-1: Report any email abuse to or X-Everquick-No-Abuse-2: call +1 (785) 865-5885. Please be sure to reference X-Everquick-No-Abuse-3: the Message-Id and include GMT timestamps. Received: from localhost (eddy@localhost) by pop.ict1.everquick.net (8.13.3/8.13.3/Submit) with ESMTP id k3SElKX1006272 for ; Fri, 28 Apr 2006 14:47:20 GMT X-Authentication-Warning: pop.ict1.everquick.net: eddy owned process doing -bs Date: Fri, 28 Apr 2006 14:47:20 +0000 (GMT) From: "Edward B. DREGER" X-X-Sender: eddy@pop.ict1.everquick.net To: FreeBSD Mailing Lists In-Reply-To: Message-ID: References: MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII Subject: Re: Dual-core CPU vs. very large cache X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 28 Apr 2006 14:47:24 -0000 SA> Date: Fri, 28 Apr 2006 19:59:03 +0930 SA> From: Shane Ambler SA> I haven't dug real deep for data but a casual look through the SA> Intel's dual Xeon board specs shows they don't say where their SA> network controllers are connected but some of their boards have an SA> Intel ethernet controller as well as "one Marvell* Yukon* -EC SA> 88E8050 PCI Express*" Search for "CSA bus" or "communications streaming architecture" for Intel's perspective. Eddy -- Everquick Internet - http://www.everquick.net/ A division of Brotsman & Dreger, Inc. - http://www.brotsman.com/ Bandwidth, consulting, e-commerce, hosting, and network building Phone: +1 785 865 5885 Lawrence and [inter]national Phone: +1 316 794 8922 Wichita ________________________________________________________________________ DO NOT send mail to the following addresses: davidc@brics.com -*- jfconmaapaq@intc.net -*- sam@everquick.net Sending mail to spambait addresses is a great way to get blocked. Ditto for broken OOO autoresponders and foolish AV software backscatter. From owner-freebsd-performance@FreeBSD.ORG Fri Apr 28 15:11:46 2006 Return-Path: X-Original-To: freebsd-performance@freebsd.org Delivered-To: freebsd-performance@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 0F7CA16A400 for ; Fri, 28 Apr 2006 15:11:46 +0000 (UTC) (envelope-from eddy+public+spam@noc.everquick.net) Received: from a.mx.ict1.everquick.net (a.mx.ict1.everquick.net [204.10.191.21]) by mx1.FreeBSD.org (Postfix) with ESMTP id CD25B43D46 for ; Fri, 28 Apr 2006 15:11:44 +0000 (GMT) (envelope-from eddy+public+spam@noc.everquick.net) Received: from pop.ict1.everquick.net (localhost [127.0.0.1]) by a.mx.ict1.everquick.net (8.12.10/8.12.10) with ESMTP id k3SFBg4F009785 for ; Fri, 28 Apr 2006 15:11:42 GMT X-Everquick-No-Abuse-1: Report any email abuse to or X-Everquick-No-Abuse-2: call +1 (785) 865-5885. Please be sure to reference X-Everquick-No-Abuse-3: the Message-Id and include GMT timestamps. Received: from localhost (eddy@localhost) by pop.ict1.everquick.net (8.13.3/8.13.3/Submit) with ESMTP id k3SFBgSP009782 for ; Fri, 28 Apr 2006 15:11:42 GMT X-Authentication-Warning: pop.ict1.everquick.net: eddy owned process doing -bs Date: Fri, 28 Apr 2006 15:11:42 +0000 (GMT) From: "Edward B. DREGER" X-X-Sender: eddy@pop.ict1.everquick.net To: freebsd-performance@freebsd.org In-Reply-To: <4450F459.60505@rogers.com> Message-ID: References: <20060425090739.8470143f.wmoran@collaborativefusion.com> <005301c668ab$39c4c150$8b00a8c0@multiplay.co.uk> <444E8F8A.9030409@rogers.com> <17487.34074.833134.823847@canoe.dclg.ca><444F8912.4010604@rogers.com><44505784.2030806@gneto.com> <4450EC9B.1050101@rogers.com><029201c66a16$a3c7e890$b3db87d4@multiplay.co.uk> <4450F0F2.9040102@rogers.com> <02b401c66a18$8058f230$b3db87d4@multiplay.co.uk> <4450F459.60505@rogers.com> MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII Subject: Re: Dual-core CPU vs. very large cache X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 28 Apr 2006 15:11:46 -0000 MJ> Date: Thu, 27 Apr 2006 12:42:01 -0400 MJ> From: Mike Jakubik MJ> Yes there is, i need a 1U single Opteron board, with 2 integrated MJ> cards. I guess the current AMD offerings do not meet my MJ> requirements. The IWill QK8S intrigues me. Has anyone tried one? Eddy -- Everquick Internet - http://www.everquick.net/ A division of Brotsman & Dreger, Inc. - http://www.brotsman.com/ Bandwidth, consulting, e-commerce, hosting, and network building Phone: +1 785 865 5885 Lawrence and [inter]national Phone: +1 316 794 8922 Wichita