From owner-freebsd-smp Mon Jul 12 10:38:33 1999 Delivered-To: freebsd-smp@freebsd.org Received: from gatekeeper.imall.com (gatekeeper.imall.com [209.63.195.8]) by hub.freebsd.org (Postfix) with ESMTP id 0001415135 for ; Mon, 12 Jul 1999 10:38:19 -0700 (PDT) (envelope-from rfleming@cc.weber.edu) Received: (from mail@localhost) by gatekeeper.imall.com (8.9.1a/8.9.1) id LAA27905 for ; Mon, 12 Jul 1999 11:38:05 -0600 (MDT) Received: from mail.imall.com(10.0.6.84) by gatekeeper.imall.com via smap (V2.1) id xma027824; Mon, 12 Jul 99 11:37:50 -0600 Received: from cc.weber.edu (spottedcow.imall.com.6.0.10.in-addr.arpa [10.0.6.139] (may be forged)) by mail.imall.com (8.9.1a/8.9.1) with ESMTP id LAA08851 for ; Mon, 12 Jul 1999 11:37:49 -0600 (MDT) Message-ID: <3789D805.6F7CFA06@cc.weber.edu> Date: Mon, 12 Jul 1999 11:56:55 +0000 From: rob X-Mailer: Mozilla 4.6 [en] (X11; I; FreeBSD 2.2.8-RELEASE i386) X-Accept-Language: en MIME-Version: 1.0 To: freebsd-smp@FreeBSD.ORG Subject: Re: 3.2-STABLE up & running on Abit BP6 (dual Celeron socket370) References: <199907111216.OAA02314@dorifer.heim3.tu-clausthal.de> Content-Type: text/plain; charset=iso-8859-1 Content-Transfer-Encoding: 8bit Content-Transfer-Encoding: 8bit Content-Transfer-Encoding: 8bit Sender: owner-freebsd-smp@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org Oliver: I was curious? What do you have in your kernel config file for this machine? I have seen some discussion about similar problems on other threads and have seen it wind up being a kernel issue in one or two cases where load was important. Rob Oliver Fromme wrote: > sthaug@nethelp.no wrote in list.freebsd-smp: > > Yup. Finished the buildworld now, clocked in at 56 minutes. This is > > with only one IBM 10 GB IDE disk. Will try some more as soon as I have > > moved a Cheetah over to the new machine. > > I'd be interested to hear how stable your system is running > under real load (i.e. load > 5 or even > 10, and with serious > hard disk and network activity). > > My dual Celeron-466 system freezes after some random time > (could be a few hours) under heavy load (no panic, keyboard is > dead, so I can't get into DDB). A simple "make world" is > usually not enough to reproduce the problem. The system runs > perfectly fine with a UP kernel (tried it with both CPUs). > > The problem seems to occur less frequently with 4.0-current > (a snapshot from June 22nd); it usually takes 2 or 3 days until > it freezes. But the problem is still there. > > (BTW, I'm running the system overclocked to 2 x 525 MHz, but > the problem is not related to that at all. It occurs at 466 > MHz just the same.) > > Regards > Oliver > > PS: This is an MSI 6120 mainboard with two MSI slot adapters > which have a jumper for dual Celeron support, two Celeron-466 > (PPGA) "in the box", 128 Mb of PC100 ECC memory. > The network interface is an MX (Macronix?) 100Mbps card, and > there's an old NCR810 Fast-SCSI adapter and an even older ISA > VGA card (text mode only, no XFree). Nothing else (well, > floppy drive and PS/2 keyboard). > > PPS: Is there a way I can provide any debug information if > the system just freezes? It looks like a deadlock somewhere > in the kernel. > > PPPS: "make buildworld" is 52 minutes here, with an old (slow) > IBM DCAS connected to the mentioned NCR810 adapter. > > -- > Oliver Fromme, Leibnizstr. 18/61, 38678 Clausthal, Germany > (Info: finger userinfo:olli@dorifer.heim3.tu-clausthal.de) > > "In jedem Stück Kohle wartet ein Diamant auf seine Geburt" > (Terry Pratchett) > > To Unsubscribe: send mail to majordomo@FreeBSD.org > with "unsubscribe freebsd-smp" in the body of the message To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-smp" in the body of the message