From owner-freebsd-smp@FreeBSD.ORG Wed Feb 11 14:50:27 2009 Return-Path: Delivered-To: freebsd-smp@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id C5A7D1065677 for ; Wed, 11 Feb 2009 14:50:27 +0000 (UTC) (envelope-from jhb@freebsd.org) Received: from cyrus.watson.org (cyrus.watson.org [65.122.17.42]) by mx1.freebsd.org (Postfix) with ESMTP id 96F358FC13 for ; Wed, 11 Feb 2009 14:50:27 +0000 (UTC) (envelope-from jhb@freebsd.org) Received: from server.baldwin.cx (pool-98-109-39-197.nwrknj.fios.verizon.net [98.109.39.197]) by cyrus.watson.org (Postfix) with ESMTPSA id 4362446B4C; Wed, 11 Feb 2009 09:50:27 -0500 (EST) Received: from localhost (john@localhost [127.0.0.1]) (authenticated bits=0) by server.baldwin.cx (8.14.3/8.14.3) with ESMTP id n1BEo9FB025248; Wed, 11 Feb 2009 09:50:21 -0500 (EST) (envelope-from jhb@freebsd.org) From: John Baldwin To: freebsd-smp@freebsd.org Date: Wed, 11 Feb 2009 09:31:32 -0500 User-Agent: KMail/1.9.7 References: <4991950C.6020006@biglist.com> In-Reply-To: <4991950C.6020006@biglist.com> MIME-Version: 1.0 Content-Type: text/plain; charset="iso-8859-1" Content-Transfer-Encoding: 7bit Content-Disposition: inline Message-Id: <200902110931.33023.jhb@freebsd.org> X-Greylist: Sender succeeded SMTP AUTH authentication, not delayed by milter-greylist-2.0.2 (server.baldwin.cx [127.0.0.1]); Wed, 11 Feb 2009 09:50:21 -0500 (EST) X-Virus-Scanned: ClamAV 0.94.2/8979/Wed Feb 11 07:23:15 2009 on server.baldwin.cx X-Virus-Status: Clean X-Spam-Status: No, score=-4.4 required=4.2 tests=ALL_TRUSTED,AWL,BAYES_00 autolearn=ham version=3.1.3 X-Spam-Checker-Version: SpamAssassin 3.1.3 (2006-06-01) on server.baldwin.cx Cc: Matt Hempel Subject: Re: Running with APIC enabled crashes a Supermicro server running 7.0/7.1 X-BeenThere: freebsd-smp@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: FreeBSD SMP implementation group List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Wed, 11 Feb 2009 14:50:28 -0000 On Tuesday 10 February 2009 9:54:04 am Matt Hempel wrote: > > Dual Xeon 1.8 GHz with hyperthreading. 2 Gigs of Memory. Server ran > 4.11 successfully in production for 5+ years. > > http://www.supermicro.com/products/system/1U/6013/SYS-6013P-8+.cfm > > Boot fails more than 50% of the time running 7.0/7.1. Either it panics > after failing during the APIC check (at the beginning of boot) or at > "Trying to mount root from ufs:/dev/mirror/gm0s1a". > > Panic'ced boots report failures on two different AP#s (2 and 3) and two > different PHY#s (6 and 7). See below. Look for a BIOS update. The last time I saw this, some weird interaction with SMM was interfering with the delivery of the INIT and/or STARTUP IPIs. A BIOS update that included newer microcode for the CPUs in question fixed the issue. For the boxes I was testing, if I disabled USB legacy compat (which would result in fewer SMM traps during boot), then the machines would fail to boot every time. With USB legacy compat enabled, they would fail occasionally. -- John Baldwin