Date: Fri, 1 Apr 2005 11:18:47 -0500 From: Vivek Khera <vivek@khera.org> To: freebsd-amd64@freebsd.org Subject: Re: Tyan k8sr lockups Message-ID: <cab069d57aee4d9ba99d5ed9ef6b94c1@khera.org> In-Reply-To: <424D58F7.1010005@infotechfl.com> References: <f0111a98c01333b3c306c81d10294de4@khera.org> <Pine.SOC.4.61.0503300229560.3181@tea.blinkenlights.nl> <3f9aa5aef19c41837cce1563e2c97a21@khera.org> <424C215E.5080201@infotechfl.com> <b6c7cfb181756fdfa3593f64223cb08a@khera.org> <424C4EED.5070601@infotechfl.com> <1112312243.6323.10.camel@lanshark.dmv.com> <424D58F7.1010005@infotechfl.com>
next in thread | previous in thread | raw e-mail | index | archive | help
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.
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?cab069d57aee4d9ba99d5ed9ef6b94c1>