David P. Reed
dpreed at reed.com
Tue Apr 2 08:01:45 PST 2002
At 11:21 AM 4/2/2002 +0100, Jon Crowcroft wrote:
>ok - here is a practical proposal
>called ECN++ (or whatever)
I like some of this, but it's way too complicated in a way that doesn't
seem likely to scale well.
The key elements - capturing a "early congestion event" early at the
bottleneck, and then delivering it back to a "congestion manager" - seems
to make sense.
But here's an alternative model. Build a "congestion sampler" overlay
network. This would be a network routers that emit specially labeled
packets into the network, whose destinations are congestion managers, but
which are routed explicitly to cover the interesting paths of the network.
By correlating the statistics of marks, the congestion managers compute
better route structures, and update both the routing tables and the
congestion sampler paths.
More information about the end2end-interest