Date: Sat, 6 Aug 2005 11:54:33 +0100 (BST) From: Robert Watson <rwatson@FreeBSD.org> To: "Alexander S. Usov" <A.S.Usov@kvi.nl> Cc: freebsd-stable@freebsd.org Subject: Re: panic: sbflush_locked on 5.4-p5/i386 Message-ID: <20050806115232.B46767@fledge.watson.org> In-Reply-To: <20050729125525.D74149@fledge.watson.org> References: <6eb82e0507241001615f7490@mail.gmail.com> <dc0m7k$enm$1@sea.gmane.org> <20050729002138.X60522@fledge.watson.org> <dcd588$tkf$1@sea.gmane.org> <20050729125525.D74149@fledge.watson.org>
next in thread | previous in thread | raw e-mail | index | archive | help
On Fri, 29 Jul 2005, Robert Watson wrote: > On Fri, 29 Jul 2005, Alexander S. Usov wrote: > >>>> I got a few similar panics. >>>> It looks that I managet to get rid of them by setting mpsafenet=0, but I >>>> am not sure -- I have to monitor it for a bit longer. >>>> I have managed to get a few dumps, so the traces are: >> >> Unfortunately I don't have these dumps anymore, I will try to switch >> mpsafenet back on and wait for a new ones. They were quite reproducable for >> me. > > Thanks. I will be away this weekend, but hope to have a chance to look > into this early next week. If you could send me the dmesg of the box > also, and the output of "sysctl -a", that would be helpful. Probably > out of band rather than via the list (or if you could put it on a web > page I could reach). Two quetions: - Is there substantial IPv6 traffic on this system? I've had at least one report that this panic happens on a system only in the context of IPv6. - Is it possible for you to try running with a latest 5-STABLE kernel? Mohan at Yahoo!, who did the TCP SACK work, has been investigating the problem but has been unable to reproduce it either. Fortunately, it sounds like Geore Neville-Neil is able to reprodeuce it in a test environment, albeit only with IPv6, so we'll see what we can do. Mohan may shortly have a diagnostic patch to run with. Thanks, Robert N M Watson
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?20050806115232.B46767>