[e2e] Bursty traffic and TCP flows (was: TOEs and related issues)

[Marko Zec]

On Tuesday 09 March 2004 14:36, RJ Atkinson wrote:
> I've trimmed cross-posting a lot in this note.
>
> The thread so far has made numerous assumptions (e.g. small packets
> consume as much buffer space as big packets in real routers) about
> how modern switches/routers are designed.   The validity of many
> of those assumptions is not obvious to me.
>
> So from where I sit, this thread has long since devolved into
> pretty theoretical territory ("if people were silly enough
> to build their routers in a certain way, and the following
> unusual event occurs, then on certain days of the week this
> bad event might happen...").
>
> It might make sense for the folks interested in this thread
> to actually pull back a bit, consider how actual shipping
> switches/routers are built, and restart from there.


I must admit I was silly enough once upon the time when I was employed 
by IBM as a field engineer, until Cisco cashed out IBM to shut down its 
networking business back in autumn 1999. All of the IBM's IP routers at 
that time were built in such a silly way that their buffers were 
measured / limited in terms of number of packets. I guess there are 
still some silly MIT people on this list who designed precisely those 
IBM (ex. Proteon) routers, so perhaps we could hear a comment or two on 
those silly design decisions from the first hand. Furthermore, I guess 
most of the today's Cisco routers are also suffering from the similar 
silly (mis)design problem...

Regarding the other statement that implies on how unusual it must be for 
a TCP flow to build up a queue on a bottleneck link / router, I'd 
rather not comment...


>
> Oh, and the subject line probably needs updating, since how one
> builds a switch/router is farther divorced from the questions
> of whether TOEs make technical/economic sense than some folks
> here might believe.[1]


Agreed,

Marko