Date: Fri, 20 Dec 2013 12:57:29 +0100 From: Michael Tuexen <Michael.Tuexen@lurchi.franken.de> To: Adrian Chadd <adrian@freebsd.org> Cc: FreeBSD Net <freebsd-net@freebsd.org>, FreeBSD Stable Mailing List <freebsd-stable@freebsd.org>, Mark Felder <feld@freebsd.org> Subject: Re: 10.0-RC1: bad mbuf leak? Message-ID: <C88BC646-2DD9-4A89-98F3-926C91953DDA@lurchi.franken.de> In-Reply-To: <CAJ-Vmo=D%2BTq4SNJsEK5a4Aw9as34m31hutU%2BwQ1GqqaD2a3zVg@mail.gmail.com> References: <1387204500.12061.60192349.19EAE1B4@webmail.messagingengine.com> <CAJ-VmonGE2=vmFOnCtLVLyNp0=F%2BNUd6OdU6=rROH_PWkyXSDA@mail.gmail.com> <FB1A916C-7ABA-4FFD-A79A-CF757E83F6E8@lurchi.franken.de> <CAJ-Vmo=D%2BTq4SNJsEK5a4Aw9as34m31hutU%2BwQ1GqqaD2a3zVg@mail.gmail.com>
next in thread | previous in thread | raw e-mail | index | archive | help
On Dec 19, 2013, at 9:02 PM, Adrian Chadd <adrian@freebsd.org> wrote: > On 19 December 2013 01:09, Michael Tuexen > <Michael.Tuexen@lurchi.franken.de> wrote: >> On Dec 19, 2013, at 9:41 AM, Adrian Chadd <adrian@freebsd.org> wrote: >> >>> Hm, try reverting just the em code to that from a 10.0-BETA? Just in >>> case something changed there? >> I saw a similar behaviour without the patches we are discussing (regarding >> ignoring the error). > > Hm. Why was that? I don't know. I have some igb devices nailed down to 100MBit, but I haven't tested. Since this problem also triggered a problem in SCTP, I looked at that first and came up with a patch for the drivers to have correctly in case of drops. However, with my fixes, the mbuf problems went away... I can revert my patches and try to figure you what is going on... The mbufs denied counter was already large after a reboot of the system, without any traffic (SCTP or anything else). Best regards Michael > > > -a >
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?C88BC646-2DD9-4A89-98F3-926C91953DDA>