From owner-freebsd-current@FreeBSD.ORG Sat Jan 28 15:15:52 2006 Return-Path: X-Original-To: freebsd-current@freebsd.org Delivered-To: freebsd-current@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 4571C16A420 for ; Sat, 28 Jan 2006 15:15:52 +0000 (GMT) (envelope-from Thomas.Sparrevohn@btinternet.com) Received: from smtp810.mail.ukl.yahoo.com (smtp810.mail.ukl.yahoo.com [217.12.12.200]) by mx1.FreeBSD.org (Postfix) with SMTP id 83C4343D49 for ; Sat, 28 Jan 2006 15:15:50 +0000 (GMT) (envelope-from Thomas.Sparrevohn@btinternet.com) Received: (qmail 63116 invoked from network); 28 Jan 2006 15:15:49 -0000 Received: from unknown (HELO w2fzz0vc01.aah-go-on.com) (thomas.sparrevohn@btinternet.com@86.133.244.63 with plain) by smtp810.mail.ukl.yahoo.com with SMTP; 28 Jan 2006 15:15:49 -0000 From: Thomas Sparrevohn To: freebsd-current@freebsd.org Date: Sat, 28 Jan 2006 15:15:46 +0000 User-Agent: KMail/1.9.1 References: <29245.1138186687@critter.freebsd.dk> <43DA871F.8020707@samsco.org> <20060127211609.GD20549@odin.ac.hmc.edu> In-Reply-To: <20060127211609.GD20549@odin.ac.hmc.edu> MIME-Version: 1.0 Content-Type: text/plain; charset="iso-8859-1" Content-Transfer-Encoding: 7bit Content-Disposition: inline Message-Id: <200601281515.47570.Thomas.Sparrevohn@btinternet.com> Subject: Re: [TEST/REVIEW] CPU accounting patches X-BeenThere: freebsd-current@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list Reply-To: Thomas.Sparrevohn@btinternet.com List-Id: Discussions about the use of FreeBSD-current List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sat, 28 Jan 2006 15:15:52 -0000 On Friday 27 January 2006 21:16, Brooks Davis wrote: [snip] > I agree as well. Certainly if we were charging for use of our cluster, > this is what we'd want. While I probably wouldn't run powerd on the > cluster, I and thinking about seeing if I can step down the CPU speed > when there aren't any queued jobs on the machine. That could save > significant power some of the time (I'm in the process of upgrading the > cluster portion of our server room to install 300KVA (~KW) of power and > plan to use it all within a year or two). > > Once we have the infrastructure to deal with this correctly, an > intresting test for someone to run would be to look at disk and memory > bound applications at different CPU speeds. I suspect you'd find that > while wallclock increased at lower CPU speeds, cpu cycles would decrease > for many workloads because the relative bandwidth of storage and maybe > memory would increase. > > -- Brooks Just to give the discussion a different angle - Across most very large midrange estates - the expectated maximum use of systems when measured over a full year averages is app. 8% - The % being sligthly tricky because it includes name servers, NIS etc. If one refines the data you find that the best case looks like a maximum use of around 16% - 20% - The measurements made over the entire estate of a couple of ITO's and hardware vendors - e.g. based upon 50,000+ servers - I that view the ability to account effectively for Use/Speed etc. are somewhat more interessting