On Thu, Mar 15, 2007 at 12:33:03PM -0600, unit3 wrote:
> Dave Hall wrote:
> > It wouldn't, it would be up to the sending and receiving hosts to figure
> > that out through path MTU discovery.
> >
> > If the switch isn't able to deal with jumbo frames, there are only two
> > things it might do, drop the frame or truncate the frame.
> >
> Ok, but given any of those scenarios, is a 2.6.x Linux system's path MTU
> discovery smart enough to figure out what's going on and correct? Or
> will it just send data out to get mangled and not detect it?
In my quick test here, it did not work. I have 2 Linux hosts, Ubuntu
Edgy and CentOS 4.4 both connected to my switch. I set the MTU to
4500 and attempted to send some ICMP PINGs of 2k or so. It appears
that this switch is dropping them. The originator did not start to
fragment the packets.
-- Jason
Received on Thu Mar 15 12:42:56 2007
This archive was generated by hypermail 2.1.8 : Thu Mar 15 2007 - 12:43:01 CST