Re: Bug report: tcp staled when send-q != 0, timers == 0.

From: Eugene B. Berdnikov (berd@elf.ihep.su)
Date: Wed Apr 11 2001 - 14:28:36 EST


  Hello.

On Wed, Apr 11, 2001 at 11:04:04PM +0400, kuznet@ms2.inr.ac.ru wrote:
> > In my experiments linux simply sets mss=mtu-40 at the start of ethernet
> > connections. I do not know why, but belive it's ok. How the version of
> > kernel and configuration options can affect mss later?
[...]
> The problem begins f.e. when mss is less and packet arrives on ethernet.
> It eats the same 1.5k of memory, but carries only ~mss bytes of tcp payload.
> See? We do not know this forward, advertise large window, have not enough
> rcvbuf to get it filled and cannot do anything but dropping new packets.

 However, I can't understand the dependency upon the kernel version, etc...

 Let me steak on this question again. In my experiments I found the
 dependency on the keepalive setting for connection on 2.2.17:

   mtu 382 + keepalive yes -> loss
   mtu 382 + keepalive no -> ok

 I made 2 tries for each setting. Does your model of "mss/mtu bug" cover
 such a picture? If the answer is "yes", I am almost satisfied. :-)

 If this behaviour is not deterministic, and is driven by probability,
 does it mean that I can get other results with large number of tests?

-- 
 Eugene Berdnikov
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/



This archive was generated by hypermail 2b29 : Sun Apr 15 2001 - 21:00:17 EST