[Iccrg] Explicit feedback

[Tony Li]

> >    I doubt we can make much of a change at the backbone in the short
> > term. But research into what sorts of congestion 
> information might be
> > carried in routing updates seems quite useful.
> 
> I never stumbled upon a paper on such a thing - does anyone
> know if this has already been proposed? Any pointers?


IGRP has carried loading information since the early 80's.  Similarly,
one of the early Arpanet routing algorithms (SPREAD, I think) carried
load information.  Both were used in routing decisions and resulted in
oscillation.

The control loop time constant for routing protocols is simply too long
to be useful at conveying high frequency congestion event notification.
However, very low frequency utilization information might be possible.
I would tend to consider this first for IGPs, given their more limited
scope than BGP.

Tony