[Panic] Dummynet/IPFW related recurring crash.

Brandon Gooch jamesbrandongooch at gmail.com
Mon Jan 24 17:11:14 UTC 2011


On Sun, Jan 23, 2011 at 7:08 PM, Pawel Tyll <ptyll at nitronet.pl> wrote:
> On Fri, Jan 7, 2011, Brandon Gooch <jamesbrandongooch at gmail.com> wrote:
>> It's likely that the mbuf handling problem (in em_refresh_mbufs()) is
>> triggered by the processing you're doing with ipfw (or elsewhere for
>> that matter), so, yes, I think it's a bug fixed in the revision
>> discussed.
>
>> When you update and test, please let us know. Also, don't forget to
>> submit a follow-up to your PR.
>
> Unfortunately bad news:
>
> Machine fell after 14 days, 22:31:42 for the same reason according to
> what was left of panic screen. It didn't do a dump, nor reboot as is
> customary since some time on S3420GP boards (and other Intel server
> boards, since colleague has dual-cpu board from same epoch).
>
> What can I try next?

I'm not sure. Perhaps there is another code path in the em(4) driver
that leads to the same, bad-pointer state. I'll have to defer to Jack
Vogel or Luigi Rizzo for potential insight into the issue.

Please provide as much information as possible (even if it comes down
to taking a photo of the console, or transcribing the backtrace).

FYI, I haven't been able to test this on any of my setups yet...

-Brandon


More information about the freebsd-net mailing list