From owner-freebsd-questions@FreeBSD.ORG Thu Feb 16 22:46:30 2006 Return-Path: X-Original-To: freebsd-questions@freebsd.org Delivered-To: freebsd-questions@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id DB09016A420 for ; Thu, 16 Feb 2006 22:46:30 +0000 (GMT) (envelope-from freebsd-01@jeremykister.com) Received: from qmail-01.nntx.net (qmail-01.nntx.net [204.9.96.15]) by mx1.FreeBSD.org (Postfix) with SMTP id 43A1D43D48 for ; Thu, 16 Feb 2006 22:46:30 +0000 (GMT) (envelope-from freebsd-01@jeremykister.com) Received: (qmail 28485 invoked by uid 1010); 16 Feb 2006 17:46:29 -0500 Received: by simscan 1.2.0 ppid: 28457, pid: 28484, t: 0.0793s scanners:none Received: from unknown (HELO ?64.115.0.169?) (smtpauth-01@jeremykister.com@64.115.0.169) by qmail-01.nntx.net with SMTP; 16 Feb 2006 17:46:29 -0500 Message-ID: <43F500BE.3070903@jeremykister.com> Date: Thu, 16 Feb 2006 17:46:22 -0500 From: Jeremy Kister User-Agent: Mozilla Thunderbird 1.0.6 (Windows/20050716) X-Accept-Language: en-us, en MIME-Version: 1.0 To: freebsd-questions@freebsd.org Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit Subject: Crashing with FreeBSD 6.0R X-BeenThere: freebsd-questions@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: User questions List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Thu, 16 Feb 2006 22:46:31 -0000 I've got four brand new identical HP DL360 systems, each with Dual Xeon 2.8ghz (with Hyperthreading on). All four of them are randomly crashing in the same manner. Each server is running FreeBSD 6.0-RELEASE, running identical software and is set up in an identical manner (besides hostname, ip, etc). The only difference is that one of the four acts as a NFS server for /usr/ports, while the other three use AMD to access the volume, on rare occasion. Each of the four servers primary purpose is to deal with incoming mail. Each runs an identical flavor of daemontools, ucspi-tcp, and qmail. each kernel dump says that "tcpserver" was the process running during a page fault, but I would bet that the problem has nothing to do with tcpserver. I've tried disabling hyperthreading in the operating system (via removing /boot/loader.conf:machdep.hyperthreading_allowed=1)... No changes. I could try disabling hyperthreading in the BIOS to see if the crashing stops. I could also upgrade to 6.1beta if there was any reason to. for the output of "kgdb kernel.debug /var/crash/vmcore.2", see: http://jeremy.kister.net./tmp/freebsd-crash.txt Any suggestions on where to go from here? -- Jeremy Kister http://jeremy.kister.net./