[67257] in North American Network Operators' Group
Re: Are SW upgrades needed in MPLS core networks?
daemon@ATHENA.MIT.EDU (Rubens Kuhl Jr.)
Fri Feb 6 14:34:37 2004
Reply-To: "Rubens Kuhl Jr." <rubens@email.com>
From: "Rubens Kuhl Jr." <rubens@email.com>
To: "Petri Helenius" <pete@he.iki.fi>
Cc: <nanog@nanog.org>
Date: Fri, 6 Feb 2004 17:32:57 -0200
Errors-To: owner-nanog-outgoing@merit.edu
> There is another factor at play here which is memory bandwidth at the
> lookup engine. If you have to look deeper into the packet than you can
> accomplish by using single spin trough the thing that fetches x bit wide
> words from the packet, you´ll effectively half your packet rate.
Yes, that might explain the performance halving in some architetures (may be
it's what happens with Sup 720, may be not), instead of longer lookup cycle.
> Doing 8+1+1+1+1+... would seem wasteful for IPv6 with the current
> address allocation scheme, are you sure that´s what´s used for IPv6 too?
I'm not. Juniper isn't very open about this matter, and I only got
confirmation of that for IPv4.
Rubens
