From owner-freebsd-questions@FreeBSD.ORG Fri Feb 16 19:30:28 2007 Return-Path: X-Original-To: freebsd-questions@freebsd.org Delivered-To: freebsd-questions@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [69.147.83.52]) by hub.freebsd.org (Postfix) with ESMTP id 9B37716A406 for ; Fri, 16 Feb 2007 19:30:28 +0000 (UTC) (envelope-from nagylzs@freemail.hu) Received: from smtp.enternet.hu (smtp.enternet.hu [62.112.192.21]) by mx1.freebsd.org (Postfix) with ESMTP id 5003113C4A8 for ; Fri, 16 Feb 2007 19:30:28 +0000 (UTC) (envelope-from nagylzs@freemail.hu) Received: from [62.68.191.191] (helo=[172.16.0.43]) by smtp.enternet.hu with esmtpa (Exim 4) id 1HI8mo-0007Gz-SC; Fri, 16 Feb 2007 20:30:26 +0100 Message-ID: <45D6064E.7010601@freemail.hu> Date: Fri, 16 Feb 2007 20:30:22 +0100 From: =?ISO-8859-1?Q?Nagy_L=E1szl=F3_Zsolt?= User-Agent: Thunderbird 1.5.0.9 (Windows/20061207) MIME-Version: 1.0 To: Chuck Swiger , freebsd-questions@freebsd.org References: <45D5D042.4000202@designaproduct.biz> <45D5F9A9.7090601@freemail.hu> <45D5FAFB.2080801@joeholden.co.uk> <45D5FDED.6090807@freemail.hu> <968D90FD-3F47-4743-8653-87BC3CB029C8@mac.com> In-Reply-To: <968D90FD-3F47-4743-8653-87BC3CB029C8@mac.com> Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit Cc: Subject: Re: Invisible process killing the CPU X-BeenThere: freebsd-questions@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: User questions List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 16 Feb 2007 19:30:28 -0000 > > One possibility is that your CPU fan has failed, in which case newer > machines would downclock itself extremely in order to avoid burning > out-- that might be an explanation for why your performance has > decreased so much. The cpu fan is not failed. This was the first thing I checked before I wrote to this list. The fan is spinning. In my understanding, if the freq goes down then each program will use more of the total CPU time because of the less computing capacity. So, having two processes, instead of 10% + 10% (total 20%) it would be 50% + 50% (total 100%). But this is not the case. On this computer, everything is at 0% but the total CPU is at 100%. > Otherwise, try using "ps auxw" to show all of the processes which are > running and see whether there are surprising things, I do not know enough about FreeBSD to tell what is surprising. :-( Would it help to send the output here? > or perhaps try "top -o time" to sort by accumulated CPU time and look > at what's consuming the most... Most CPU time is for the ppp daemon: PID USERNAME THR PRI NICE SIZE RES STATE TIME WCPU COMMAND 244 root 1 96 0 3404K 2084K select 1:40 0.00% ppp but I don't think that ppp is causing the problem, since it is at WCPU 0%. Best, Laszlo