From owner-freebsd-hackers Fri Nov 23 14:45:14 2001 Delivered-To: freebsd-hackers@freebsd.org Received: from mailbeast.ahaza.com (mailbeast.ahaza.com [209.180.221.132]) by hub.freebsd.org (Postfix) with ESMTP id BED6937B405 for ; Fri, 23 Nov 2001 14:45:11 -0800 (PST) Received: from akira.ahaza.com (akira.ahaza.com [172.16.30.230]) by mailbeast.ahaza.com (8.11.1/8.11.1) with ESMTP id fANMjBX12197 for ; Fri, 23 Nov 2001 14:45:11 -0800 (PST) (envelope-from quark@akira.ahaza.com) Received: (from quark@localhost) by akira.ahaza.com (8.11.6/8.11.6) id fANMjTe05701 for hackers@freebsd.org; Fri, 23 Nov 2001 14:45:29 -0800 (PST) (envelope-from quark) Date: Fri, 23 Nov 2001 14:45:29 -0800 From: Tim Wiess To: hackers@freebsd.org Subject: Problems with Dual Athlons Message-ID: <20011123144529.A5628@ahaza.com> Mail-Followup-To: hackers@freebsd.org Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline Sender: owner-freebsd-hackers@FreeBSD.ORG Precedence: bulk List-ID: List-Archive: (Web Archive) List-Help: (List Instructions) List-Subscribe: List-Unsubscribe: X-Loop: FreeBSD.ORG Hello all, I've recently put together a dual Athlon system, and unfortunately so far I have had nothing but problems running FreeBSD on it. I have gone through many of the archives in the hackers, bugs, and smp lists, and while most indicate that they have had much success running FreeBSD on dual Athlons, there have been a few cases which were similar to mine. Basically, I am unable to run the system for more than 30 minutes without getting a panic. Fatal trap 12: page fault while in kernel mode mp_lock = 01000002; cpuid = 1; lapic.id = 00000000 fault virtual address = 0xa0a fault code = supervisor read, page not present instruction pointer = 0x8:0xc02218e8 stack pointer = 0x10:0xff80fbc0 frame pointer = 0x10:0xff80fbc0 code segment = base 0x0, limit 0xfffff, type 0x1b = DPL 0, pres 1, def32 1, gran 1 processor eflags = interrupt enabled, resume, IOPL = 0 current process = Idle interrupt mask = bio <- SMP: XXX The instruction pointer points to the worklist_insert routine in the soft updates code. Although I don't think that it's the file system that's really the source of the problem, since I believe I've seen different instruction pointers listed for the same type of panic. In the other cases I was reading about, their panics were also caused by a page fault. Unfortunately it didn't seem like the source of the problem was ever really located. So I thought I would run this by you all and see if anyone had any additional thoughts or suggestions. For the record, I'm running the 1.2Ghz Athlons on a Tyan S2460 board with 256MB of 266Mhz DDR-SDRAM. thanks tim To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-hackers" in the body of the message