From owner-freebsd-sparc64@FreeBSD.ORG Tue Nov 13 21:03:17 2007 Return-Path: Delivered-To: sparc64@FreeBSD.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id C5DD716A417; Tue, 13 Nov 2007 21:03:17 +0000 (UTC) (envelope-from xcllnt@mac.com) Received: from smtpoutm.mac.com (smtpoutm.mac.com [17.148.16.80]) by mx1.freebsd.org (Postfix) with ESMTP id 94F5513C4CC; Tue, 13 Nov 2007 21:03:17 +0000 (UTC) (envelope-from xcllnt@mac.com) Received: from mac.com (asmtp008-s [10.150.69.71]) by smtpoutm.mac.com (Xserve/smtpout017/MantshX 4.0) with ESMTP id lADKmbHl014948; Tue, 13 Nov 2007 12:48:37 -0800 (PST) Received: from mini-g4.jnpr.net (natint3.juniper.net [66.129.224.36]) (authenticated bits=0) by mac.com (Xserve/asmtp008/MantshX 4.0) with ESMTP id lADKmYvJ003063 (version=TLSv1/SSLv3 cipher=AES128-SHA bits=128 verify=NO); Tue, 13 Nov 2007 12:48:35 -0800 (PST) Message-Id: From: Marcel Moolenaar To: Hiroki Sato In-Reply-To: <20071114.052521.135026097.hrs@allbsd.org> Content-Type: text/plain; charset=US-ASCII; format=flowed Content-Transfer-Encoding: 7bit Mime-Version: 1.0 (Apple Message framework v912) Date: Tue, 13 Nov 2007 12:48:29 -0800 References: <472DAFBE.9070603@FreeBSD.org> <472E4B8D.2020902@alaska.net> <47348106.8080001@alaska.net> <20071114.052521.135026097.hrs@allbsd.org> X-Mailer: Apple Mail (2.912) Cc: kris@FreeBSD.org, sparc64@FreeBSD.org Subject: Re: hardware and package builds X-BeenThere: freebsd-sparc64@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Porting FreeBSD to the Sparc List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Tue, 13 Nov 2007 21:03:17 -0000 On Nov 13, 2007, at 12:25 PM, Hiroki Sato wrote: > Well, let me explain the current situation of my e4500s first. I > have three e4500s with 10-14 CPUs online for experiment and package > building now, but some of them are often down probably because some > hardware failure. JFYI: pluto2.freebsd.org (ia64) has been running reliably for a long time with FreeBSD 6.x. Now that the machine has been upgraded to FreeBSD -CURRENT do I experience machine check aborts. These MCAs have been observed on pluto1.freebsd.org for a while when it was running FreeBSD 7.x and it was attributed to the hardware and Kris stopped package builds on that machine. Now I'm actually thinking that it's a FreeBSD problem, because it now all of a sudden is a problem on pluto2 and both machines are reliable otherwise -- that is, only when doing a 4-way parallel package build do these MCAs happen. An 8-way parallel buildworld is fine. This does not mean that it's a hardware problem in your case of course, but keep in mind that it may also be a kernel bug... -- Marcel Moolenaar xcllnt@mac.com