From owner-freebsd-amd64@FreeBSD.ORG Fri Apr 1 16:18:50 2005 Return-Path: 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 2953616A4CE for ; Fri, 1 Apr 2005 16:18:50 +0000 (GMT) Received: from yertle.kcilink.com (yertle.kcilink.com [65.205.34.180]) by mx1.FreeBSD.org (Postfix) with ESMTP id E5D0243D39 for ; Fri, 1 Apr 2005 16:18:49 +0000 (GMT) (envelope-from vivek@khera.org) Received: from [192.168.7.149] (host-149.int.kcilink.com [192.168.7.149]) by yertle.kcilink.com (Postfix) with ESMTP id 7C0DFB80C for ; Fri, 1 Apr 2005 11:18:49 -0500 (EST) Mime-Version: 1.0 (Apple Message framework v619.2) In-Reply-To: <424D58F7.1010005@infotechfl.com> References: <3f9aa5aef19c41837cce1563e2c97a21@khera.org> <424C215E.5080201@infotechfl.com> <424C4EED.5070601@infotechfl.com> <1112312243.6323.10.camel@lanshark.dmv.com> <424D58F7.1010005@infotechfl.com> Content-Type: text/plain; charset=US-ASCII; format=flowed Message-Id: Content-Transfer-Encoding: 7bit From: Vivek Khera Date: Fri, 1 Apr 2005 11:18:47 -0500 To: freebsd-amd64@freebsd.org X-Mailer: Apple Mail (2.619.2) Subject: Re: Tyan k8sr lockups X-BeenThere: freebsd-amd64@freebsd.org X-Mailman-Version: 2.1.1 Precedence: list List-Id: Porting FreeBSD to the AMD64 platform List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 01 Apr 2005 16:18:50 -0000 On Apr 1, 2005, at 9:21 AM, Gary Mu1der wrote: > Is there a way to force a crash dump? I heard mention of a key combo > on the console to force a crash dump, but I suspect the console > keyboard is totally hung as well. > > Does anyone have a doc on how to run the kernel under gdb or something > and log what is happening to a serial console? > when I get my lockups (had another this A.M.) the serial console line is non-responsive as well. I cannot break into the kernel debugger at all. There is no evidence of *anything* going bad other than the machine is totally unresponsive to network and console. nothing is logged anywhere, including the BIOS. when it happens it is during time of heavy I/O + network load. I'm now running with debug.mpsafenet=0 to see if i'm tickling a bug in the network stack, given that I saw some bge0 timeouts earlier.