From owner-freebsd-amd64@FreeBSD.ORG Mon Jul 11 14:52:40 2005 Return-Path: X-Original-To: freebsd-amd64@freebsd.org Delivered-To: freebsd-amd64@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id AF96316A41C for ; Mon, 11 Jul 2005 14:52:40 +0000 (GMT) (envelope-from rob@hudson-trading.com) Received: from daemon.mistermishap.net (167-49.nyc.dsl.access.net [166.84.167.49]) by mx1.FreeBSD.org (Postfix) with ESMTP id 3354543D45 for ; Mon, 11 Jul 2005 14:52:39 +0000 (GMT) (envelope-from rob@hudson-trading.com) Received: from daemon.mistermishap.net (localhost.mistermishap.net [127.0.0.1]) by daemon.mistermishap.net (8.12.9/8.12.9) with ESMTP id j6BEqbmU008498; Mon, 11 Jul 2005 10:52:37 -0400 (EDT) (envelope-from rob@hudson-trading.com) Received: from localhost (rob@localhost) by daemon.mistermishap.net (8.12.9/8.12.9/Submit) with ESMTP id j6BEqV5a008495; Mon, 11 Jul 2005 10:52:35 -0400 (EDT) X-Authentication-Warning: daemon.mistermishap.net: rob owned process doing -bs Date: Mon, 11 Jul 2005 10:52:31 -0400 (EDT) From: Rob Watt X-X-Sender: rob@daemon.mistermishap.net To: Mykel In-Reply-To: <42D06471.6080105@mWare.ca> Message-ID: <20050711102832.V8006@daemon.mistermishap.net> References: <20050630160225.D38285@daemon.mistermishap.net> <42D06471.6080105@mWare.ca> MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII Cc: freebsd-amd64@freebsd.org, David Gilbert Subject: Re: fatal trap 12 in pagedaemon on dual-core opteron machine X-BeenThere: freebsd-amd64@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Porting FreeBSD to the AMD64 platform List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Mon, 11 Jul 2005 14:52:40 -0000 On Sat, 9 Jul 2005, Mykel wrote: > I've got 4 Tyan S2882s. The units I use the GigE (bge) on crash all the > time while syncing or running ggated... Not particularly heavily loaded > either (avg of .5 maybe?) > > The other one that doesn't use GigE (www.UserFriendly.org) has never > crashed. > > It's NICs I'm pretty sure. We've used various stages of 5.3 and 5.4 to > no avail. I'm about to start RMA'ing them... but when all 3 die the same > way... I'm not encouraged. > > Presently we're running ggates across the fxp cards and they've been > solid (so far... we only started yesterday) > Are you using the onboard bge or PCI em? I've been able to reproduce the problem with PCI em copper and fiber cards. The copper cards were gigabit, but were set to 100Mbits. I have not tested with the onboard bge nics or the intel fxp cards. Since you've experienced the problem with bge I won't even bother testing them. We thought initially that the problem might be with the card. But since it's appeard with nics from 2 different vendors, 3 different cards and 2 drivers, then the cards seem less likely to be the primary culprit. We did have another problem with the tyan K8SR board that was related to the bios. When the machine was cold booted, memory performance was 25-50% of the performance when warm booted. This was fixed by a bios update (2.05v). maybe there is some other bios related memory bug that is the cause of the panics. It seems that other people have had this happen with single core machines, but I haven't been able to reproduce it on our single core machines, only on the dual-core. - Rob Watt