Date: Sat, 23 Aug 2008 23:12:39 -0400 From: Mike Tancsa <mike@sentex.net> To: "Kip Macy" <kmacy@freebsd.org> Cc: "Bjoern A. Zeeb" <bzeeb-lists@lists.zabbadoz.net>, freebsd-net@freebsd.org Subject: Re: strange TCP issue on RELENG_7 Message-ID: <200808240312.m7O3CZS0098145@lava.sentex.ca> In-Reply-To: <3c1674c90808231916l2c92a8e4sae0f191af31b5870@mail.gmail.co m> References: <200808221719.m7MHJY25090566@lava.sentex.ca> <20080822191146.T66593@maildrop.int.zabbadoz.net> <200808221922.m7MJMcUN091064@lava.sentex.ca> <3c1674c90808231916l2c92a8e4sae0f191af31b5870@mail.gmail.com>
next in thread | previous in thread | raw e-mail | index | archive | help
At 10:16 PM 8/23/2008, Kip Macy wrote:
>Can you help me out a bit with your workload?
>
>tcp_offload_connect(...) needs to determine which interface an address
>corresponds to see if that interface supports TCP offload. The code
>does the exact same thing as ip_output does except it doesn't have the
>inpcb locked (which isn't used as part of the route lookup).
This is the only RELENG_7 box that I have where it routes tcp packets
asymmetrically, so that sounds like it might be the portion that is
badly interacting. The server has just one default gateway, which is
out em0, but clients all over the net will connect to IP addresses
aliased on lo0 and to the one IP on em1. But all connections exit
out em0 other than connected routes of course.
---Mike
>Julian has worked in this code most recently, maybe he has some idea
>what is going on.
>
>-Kip
>
>
>On Fri, Aug 22, 2008 at 12:22 PM, Mike Tancsa <mike@sentex.net> wrote:
> > At 03:12 PM 8/22/2008, Bjoern A. Zeeb wrote:
> >
> >> can you make sure you have this?
> >>
> >> http://svn.freebsd.org/changeset/base/181596
> >
> > Hi,
> > I do. I am running a GENERIC kernel but with inet6 disabled from yesterday
> >
> > 7.0-STABLE #0: Thu Aug 21 10:27:04 EDT 2008
> >
> > and with the patch below as TOE seems to be broken for my workload
> >
> >
> > # diff -u sys/netinet/tcp_offload.c sys/netinet/tcp_offload.c.disable
> > --- sys/netinet/tcp_offload.c 2008-08-01 13:47:27.000000000 -0400
> > +++ sys/netinet/tcp_offload.c.disable 2008-08-22 15:16:50.000000000 -0400
> > @@ -58,6 +58,8 @@
> > struct rtentry *rt;
> > int error;
> >
> > + return (EINVAL);
> > +
> > /*
> > * Look up the route used for the connection to
> > * determine if it uses an interface capable of
> >
> > I can try changing to ipfw and see if that makes a difference ? But the RST
> > doesnt sound like a pf issue no ? I would have thought it would just
> > blackhole the packet.
> >
> > ---Mike
> > _______________________________________________
> > freebsd-net@freebsd.org mailing list
> > http://lists.freebsd.org/mailman/listinfo/freebsd-net
> > To unsubscribe, send any mail to "freebsd-net-unsubscribe@freebsd.org"
> >
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?200808240312.m7O3CZS0098145>