[Iccrg] Proposal for ICCRG operations

[John Leslie]

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.

   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>