[Iccrg] Proposal for ICCRG operations

[Saverio Mascolo]

On Sat, 2006-02-04 at 15:56 -0500, John Leslie wrote:
> Tim Shepard <shep at alum.mit.edu> wrote:
> > To: "S. Keshav" <keshav at uwaterloo.ca>
> > 
> >> What's wrong with TCP's congestion control scheme
> > 
> > The problem with TCP's congestion control scheme is that it builds a
> > standing queue at the point of congestion, which increases the delay.
> 
>    I'd go farther than than: the fundamental problem with TCP's
> congestion control scheme is that it never measures congestion.
> 
>    That said, I agree with Tim that building a queue (of unknown length)
> at the point of congestion is not very smart congestion control.
> 
> > A better congestion control scheme would control the queue length,
> > with a target of zero (or very few) packets, thereby minimizing the
> > impact on delay.

by targetting a queue level of few packets we  have that each flow gets
a constant fraction of the buffer space. In a FIFO queue this translates
in the same fraction of used bandwdith.

what does happen to statistical multiplexing, i.e. to the need of
reshuffling  bandwidth to allocate new flows

saverio

> 
>    That problem looked hard when TCP was invented; and we settled for
> a kind-of brain-dead mechanism (which has worked far better than I would
> have believed).
> 
>    Ideally, we'd move the queuing all the way back to the sender (unless
> someone along the path from the sender can bypass the congestion point).
> 
> --
> John Leslie <john at jlc.net>
> 
> _______________________________________________
> Iccrg mailing list
> Iccrg at cs.ucl.ac.uk
> http://oakham.cs.ucl.ac.uk/mailman/listinfo/iccrg