From owner-freebsd-questions Thu Jan 4 22:13:44 2001 From owner-freebsd-questions@FreeBSD.ORG Thu Jan 4 22:13:41 2001 Return-Path: Delivered-To: freebsd-questions@freebsd.org Received: from smtppop2pub.verizon.net (smtppop2pub.gte.net [206.46.170.21]) by hub.freebsd.org (Postfix) with ESMTP id 5347937B400 for ; Thu, 4 Jan 2001 22:13:41 -0800 (PST) Received: from next (crtntx1-ar3-098-023.dsl.gtei.net [4.33.98.23]) by smtppop2pub.verizon.net with SMTP ; id AAA71811224 Fri, 5 Jan 2001 00:12:32 -0600 (CST) Message-ID: <001501c076de$9d6a71b0$17622104@next> From: "Jason Halbert" To: "Jeremiah Gowdy" , "Michael Wells" , References: <20010104102301.B13113@imap.cam.zeus.co.uk> <001d01c076dc$94eb38a0$aa240018@vista1.sdca.home.com> Subject: Re: SMP kernel overheats Date: Fri, 5 Jan 2001 06:13:24 -0000 MIME-Version: 1.0 Content-Type: text/plain; charset="iso-8859-1" Content-Transfer-Encoding: 7bit X-Priority: 3 X-MSMail-Priority: Normal X-Mailer: Microsoft Outlook Express 5.00.2919.6700 X-MimeOLE: Produced By Microsoft MimeOLE V5.00.2919.6700 Sender: owner-freebsd-questions@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.ORG In continuing saga of FreeBSD questions "Jeremiah Gowdy" wrote: > > I've been going through a kernel configuration for my SMP machine. It's > > a Gigabyte 6BXD with 2xPIII 550MHz processors. I can provide other > > information if necessary about the hardware, but it's nothing too exotic. > > > > The problem I'm having is that although the kernel seems to work fine, > > and tools like "top" report that the CPUs are idleing, after a few minutes > > the system starts getting really warm, and eventually the BIOS thermal > > alarms are triggered at 65 degrees C. As I say, despite this it is all > > fine in operation, and processes on both CPUs are ok. It is clearly > > running way too hot though. > > > > What I was wondering was is this a known problem? Can it be fixed? Any > > other ideas? Thanks, your help is much appreciated. > > I run an IBM Netfinity 3500, Dual Pentium III 500, which has only heatsinks > on the CPUs and relies on the case fan to suck enough air to keep the CPUs > cool. I run the FreeBSD 4.2 SMP kernel 24/7 on this production server and I > have no issues. Sorry. Is it just me or ... are we looking in the wrong place? Obviously this isn't a kernel issue. If it were lots more people, including me, would be having issues. I think the problem here lies with the externals (fans, case, room temp. etc.). I do agree with FreeBSD not halting a processor. I've seen data and experienced it myself that when temps are regulated properly.. things in general last longer. This phenomina is similar to bending a pieve of metal over and over or turning on and off a light bulb. The kernel isn't the issue. It's the box itself. --- Jason jason@jason-n3xt.org To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-questions" in the body of the message