[Iccrg] Proposal for ICCRG operations
kewin at acm.org
Sun Feb 5 02:46:24 GMT 2006
> I don't believe there is one. :^(
Indeed, this is rather tricky.
> To me, congestion is the condition where a packet can't be sent
> "immediately" (meaning perhaps that it can't be queued as the next
> packet to be sent).
See, for me this would not be congestion at all. I understand congestion
as some sort of "sudden interruption"...that means, at one point,
packets are delayed (higher delay than usual/expected), dropped, etc.
However, if the delay = constant (without packet loss), I wouldn't call
this necessarily congestion.
But as you said, it is tricky to find a common definition for congestion.
> It's not quite that bad: if an index of "congestion" doesn't define
> what it's measuring, then that index is meaningless. However, I believe
> we can make use of indices which measure different things.
Maybe we should go away from the single word "congestion" and describe a
type of congestion, which then could be measured. By this I mean that
lets say congestion A describes a behavior where packets are just
delayed, but not dropped, congestion B describes actual packet loss, and
so forth. Coming up with indices for the different types, A, B, etc.,
could the lead to some sort of measurement index for a certain congestion.
Just my few thoughts on a Sunday afternoon with coffee....
> John Leslie <john at jlc.net>
> Iccrg mailing list
> Iccrg at cs.ucl.ac.uk
More information about the Iccrg