Date: Thu, 29 Mar 2001 12:46:28 +0200 (CEST) From: "Hartmann, O." <ohartman@klima.physik.uni-mainz.de> To: "Chad R. Larson" <chad@DCFinc.com> Cc: <freebsd-stable@FreeBSD.ORG> Subject: Re: Overheated PIII in SMP system Message-ID: <Pine.BSF.4.33.0103291238430.3932-100000@klima.physik.uni-mainz.de> In-Reply-To: <200103290112.SAA00301@freeway.dcfinc.com>
next in thread | previous in thread | raw e-mail | index | archive | help
On Wed, 28 Mar 2001, Chad R. Larson wrote: Dear Sirs. I do not think FreeBSD's behaviour is the cause for "overheating" the CPU, and I do not care about what FreeBSD is doing while in an idle loop. If the system is stable, it is all right. In my case, something seems to be very wrong. I monitored now for about two days all parameters I can obtain by the "HEALTHD" daemon and I I did several changes, e.g. swapping both CPUs. Now the system runs "stable" (but how long?). I swapped the CPUs again and I realized, that my first observation, that heat follows one specific CPU, was an err. Heat is located in SLOT 1 for CPU #0. Obviously is the othe CPU not that sensitive to heat than the other one, but a measuremnt of 52 degrees Celsius on the heat sink is really to much! "Healthd" gives a lot of warnings to me due the fact that SLOT 1 delivers a core voltage of 2.06 to 2.08 and not 2.05 as the other, second slot. I think this is like an evidence to accuse the mainboard. This will getting changed today (ASUS P2B-D against ASUS CUV4X-D with two new boxed 733B-Coppermines). Coppermines seems to be much "cooler" than old KATMAI - and the risk of a dying system due old hardware is to high ... :>As I recall, Hartmann, O. wrote: :>> One of our SMP servers, a FreeBSD 4.-RC box, is not willing :>> to compile a world. It faults with SIG 11. :>> :>> The problem is caused by a overheated Intel Pentium III/600MHz :>> with KATMAI core. :> :>Your core problem (heh) is caused by the fact that the idle behavior :>of the uniprocessor kernel is to halt, waiting for an interrupt. :>The idle behavior of the SMP kernel is to loop, looking for work to :>dispatch. This means the SMP never halts, and therefore runs :>hotter. :> :>That doesn't give you a cure, however... :-( :> :> -crl :>-- :>Chad R. Larson (CRL15) 602-953-1392 Brother, can you paradigm? :>chad@dcfinc.com chad@larsons.org larson1@home.com :>DCF, Inc. - 14623 North 49th Place, Scottsdale, Arizona 85254-2207 :> -- MfG O. Hartmann ohartman@klima.physik.uni-mainz.de ---------------------------------------------------------------- IT-Administration des Institut fuer Physik der Atmosphaere (IPA) ---------------------------------------------------------------- Johannes Gutenberg Universitaet Mainz Becherweg 21 55099 Mainz Tel: +496131/3924662 (Maschinensaal) Tel: +496131/3924144 FAX: +496131/3923532 To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-stable" in the body of the message
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?Pine.BSF.4.33.0103291238430.3932-100000>