[c-nsp] MTU Question on T1

[Rodney Dunn]

The 75xx dMLPPP implementation does not
do any fragmentation without LFI configured.

Even if it did, by my math the best you
can get is to ship a 1500 byte packet split
in half over the two T1's which is like Gert's
math said about 40msec.

You'd have to send 26+ packets to get the
full data over and that comes up to over
1 sec in total serialization time assuming
infinite processing for reassembly on the endpoints.

Therefore it is impossible to get what you want
unless you had some compression that might could
get the actual data down.

Rodney

On Mon, Jan 24, 2005 at 07:28:00PM +0100, Gert Doering wrote:
> Hi,
> 
> On Mon, Jan 24, 2005 at 10:01:45AM -0800, Richard J. Sears wrote:
> > On the dual T1 issue - correct me if I am wrong please but with ppp
> > multilink interleaving turned on, won't it take that single 40000 byte
> > packet and shove it down one T1 because it came in as a single packet..?
> 
> There is no single 40k packet at the router.  The sending host is
> fragmenting the packet to 1500 byte IP fragments, because a 40k packet
> cannot be sent over Ethernet.
> 
> *If* there were a 40k packet, PPP might fragment it and distribute it
> over the multilink members, but that is a local configuration issue.
> 
> gert
> -- 
> USENET is *not* the non-clickable part of WWW!
>                                                            //www.muc.de/~gert/
> Gert Doering - Munich, Germany                             gert at greenie.muc.de
> fax: +49-89-35655025                        gert at net.informatik.tu-muenchen.de
> _______________________________________________
> cisco-nsp mailing list  cisco-nsp at puck.nether.net
> https://puck.nether.net/mailman/listinfo/cisco-nsp
> archive at http://puck.nether.net/pipermail/cisco-nsp/