Date: Tue, 13 Nov 2007 12:48:29 -0800 From: Marcel Moolenaar <xcllnt@mac.com> To: Hiroki Sato <hrs@FreeBSD.org> Cc: kris@FreeBSD.org, sparc64@FreeBSD.org Subject: Re: hardware and package builds Message-ID: <FE618411-8C88-4BCF-A172-D17E24321E05@mac.com> In-Reply-To: <20071114.052521.135026097.hrs@allbsd.org> References: <472DAFBE.9070603@FreeBSD.org> <472E4B8D.2020902@alaska.net> <47348106.8080001@alaska.net> <20071114.052521.135026097.hrs@allbsd.org>
next in thread | previous in thread | raw e-mail | index | archive | help
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
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?FE618411-8C88-4BCF-A172-D17E24321E05>