[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Date: Sat, 11 Oct 2008 11:27:50 +0300 (EEST)
From: "Ilpo Järvinen" <ilpo.jarvinen@...sinki.fi>
To: "Dâniel Fraga" <fragabr@...il.com>
cc: Thomas Gleixner <tglx@...utronix.de>,
David Miller <davem@...emloft.net>,
Netdev <netdev@...r.kernel.org>
Subject: Re: [PATCH] tcp FRTO: in-order-only "TCP proxy" fragility workaround
(fwd)
On Fri, 10 Oct 2008, Dâniel Fraga wrote:
> On Wed, 8 Oct 2008 23:44:39 +0300 (EEST)
> "Ilpo Järvinen" <ilpo.jarvinen@...sinki.fi> wrote:
>
> > the server (we don't have /proc/net/tcp of that case so I cannot
>
> Ok, now I got a trace that I think is the best one I got so far:
>
> http://www.abusar.org/ftrace/trace-best.txt.bz2
>
> and the requested /proc/net/tcp by the time the Tracer was
> stopped:
>
> http://www.abusar.org/ftrace/trace-tcp.txt
>
> I hope that now it helps.
>
> As always, if you need more information, just ask.
This time there isn't any listening socket with queue to be accepted, not
connections. So it's not exactly the same situation on the server, I'm
sort of thinking that the accept() stuff we found earlier is just
coincidence, I guess it could as well hang somewhere else on other
times.
--
i.
Powered by blists - more mailing lists