packet reordering at exchange points

Sat Apr 13 08:39:50 UTC 2002

> Gotta go with the old head scratch on that one...
>
> Imagine the packet zipping down a wire.  It hits a router. It slows
> down. Why? Because (until very recently) wire-speed != processing
> speed != backplane speed... This is called 'blocking'.  The packet
> has to wait somewhere while the prior packet is being processed
> and fed through the backplane.
>
> Very recently vendors started offloading tasks from a single processor
> to sub-processors and ASICs in a more distributed manner. This has led
> to routers that are faster than the wire (in contrast to the above
> stated routers that were slower than the wire).  In this situation,
> buffering allows a greater port density: that is to say, more
> channels at a slower speed (the speed of the wire) rather than
> less channels at a higher speed (faster than the wire).

Apart from the fact that I have been building these (PC/Sparc based) routers
since the early '90s is neither here nor there. My point in general was to
actualy try to make people explain why there is a 'marketing' relationship
between the size of buffers and a magical bandwidth x delay product of
(normally) line rate x one second.

I fully understand (in case it appeared otherwise) the issues of interface
contention when aggregating traffic and also the need for buffering in QoS
implementations, but the perceived wisdom of 'you must have at least one
seconds buffer on each *interface*' still seems very shoddy and marketing
driven.

Still haven't heard it (a good reason), but then again I haven't gone to
read Van Jacobson's paper that was referenced in an earlier reply. And that
paper probably makes too good a point and bears no relation to the marketing
drivel we have been getting for many years.

BTW The faster than line rate / slower than line rate forwarding engine
stuff is an ongoing and iterative thing that has been the simple result of
capacity growth and in turn a has spurred the development of each new
generation of router - just like any growth industry - and this will
continue until we run out of electrons and photons and god-knows-what-else
to move around.

Peter