[nsp] ip load-sharing per-packet - cef accelerated ?

[Charles Sprickman]

On Mon, 10 Mar 2003, Alex Rubenstein wrote:

> > We found the opposite. per-packet CEF on links where it is supported
> > result in tremendous performance increase and smoother utilization of the
> > links.
>
> Probably because you (and like many others) have had it fortunate enough
> that packets aren't going out of order.

I've got a situation where I have to per-packet, and it's pretty ugly, but
we get more traffic through than we did without it.

How ugly?

Two 1.5 SDSL lines (bridge mode tied to a bvi) and one T1 line, and at
least 6Mb of traffic wanting to get through.  BVI was the only thing I
could come up with (and it was there already) to let me run ospf over the
sdsl links, since the dsl routers do not grok ospf, and I wanted
everything to at least look like it was terminating at the router (there's
a vlan for each sdsl line).

Anyone have any clever ideas for a situation where MLPPP is not possible?
MLPPPoE? :)

C

>
>
> -- Alex Rubenstein, AR97, K2AHR, alex at nac.net, latency, Al Reuben --
> --    Net Access Corporation, 800-NET-ME-36, http://www.nac.net   --
>
>
> _______________________________________________
> cisco-nsp mailing list  cisco-nsp at puck.nether.net
> http://puck.nether.net/mailman/listinfo/cisco-nsp
> archive at http://puck.nether.net/pipermail/cisco-nsp/
>