[46764] in North American Network Operators' Group
Re: packet reordering at exchange points
daemon@ATHENA.MIT.EDU (Neil J. McRae)
Wed Apr 10 10:56:21 2002
In-Reply-To: <016501c1e09e$cf233450$2028a8c0@carpenter> from Peter Galbavy at "Apr 10, 2002 03:48:36 pm"
To: peter.galbavy@knowtion.net (Peter Galbavy)
Date: Wed, 10 Apr 2002 15:51:36 +0100 (BST)
Cc: ras@e-gerbil.net (Richard A Steenbergen),
eddy+public+spam@noc.everquick.net (E.B. Dreger),
paul@vix.com (Paul Vixie), nanog@merit.edu
MIME-Version: 1.0
Content-Type: text/plain; charset=US-ASCII
Content-Transfer-Encoding: 7bit
Message-Id: <20020410145137.291D13F06B@equinox.DOMINO.ORG>
From: neil@DOMINO.ORG (Neil J. McRae)
Errors-To: owner-nanog-outgoing@merit.edu
Peter,
For basic Internet style routeing you are probably
correct [and possibly even more true for MPLS style
switching/routeing], but these days customers
demand different classes of service and managed data and bandwidth
services over IP. These requires lots of packet hacking and for
that you need bufferss. If you need any type of filtering done
thats remotely intelligent you need somewhere to process those
packets especially when you are running 10G interfaces.
Regards,
Neil.
--
Neil J. McRae - Alive and Kicking
neil@DOMINO.ORG
