[Iccrg] Why don't we stop treating ECN and loss similarly?
David.Ros@telecom-bretagne.eu (David Ros) Mon, 29 October 2012 14:08 UTC
From: David.Ros@telecom-bretagne.eu
Date: Mon, 29 Oct 2012 14:08:35 +0000
Subject: [Iccrg] Why don't we stop treating ECN and loss similarly?
In-Reply-To: <920D98EE-EFEB-47E2-879C-84999F258771@ifi.uio.no>
References: <920D98EE-EFEB-47E2-879C-84999F258771@ifi.uio.no>
Message-ID: <2349C56A-EB82-4F6D-AF8E-A92B1AF02088@telecom-bretagne.eu>
X-Date: Mon Oct 29 14:08:35 2012
On 27 oct. 2012, at 11:26, Michael Welzl wrote: > Hi, > > Here's an idea, inspired by something Bob Briscoe posted to the TSVWG list recently in a discussion of draft-carlberg-tsvwg-ecn-reactions. However, this possibly stupid idea is my own responsibility alone :-) > > > According to RFC 3168, senders must react to ECN just as if packets had been dropped. > This is to maintain fairness between ECN-compatible and non-compatible flows. > Because of this requirement, AQMs cannot ECN-mark packets more aggressively than it drops packets from non-ECN-capable flows - else ECN-marked flows would be at a disadvantage. > > We have seen various non-standard congestion control behaviors can co-exist reasonably well with standard TCP in practice. If it was possible to have a milder congestion reaction to ECN-based reaction, it would also be possible to ECN-mark packets earlier, leading to a bigger advantage for everyone using ECN. And none of this is possible when we have the "treat an ECN mark just like loss" rule in place. > > Hence, my question: to incentivize ECN usage and enable better behavior when it's used, shouldn't we remove this rule? > Hi, (jumping late into this thread) Likely I am missing something, but I don't see a fundamental difference between, say, having CUBIC compete with non-CUBIC flows and having RFC3168-compliant, ECN-enabled flows compete with "non-standard" ones (non-standard as in, reduce cwnd by less than half). I don't know if we should *remove* the halve-cwnd-if-ECN-mark rule, but it looks like an interesting experiment to do. Thanks, David. PS: by the way, what does a CUBIC sender do in the face of incoming ECN marks? > Note that this is not even about a more fine-grain interpretation of ECN feedback - it's more like an intermediate step. > > I'm curious what everyone thinks... am I missing something? > > Cheers, > Michael > > > _______________________________________________ > Iccrg mailing list > Iccrg@cs.ucl.ac.uk > http://oakham.cs.ucl.ac.uk/mailman/listinfo/iccrg ================================================================= David ROS http://www.rennes.enst-bretagne.fr/~dros/ "It would seem that you have no useful skill or talent whatsoever," he said. "Have you thought of going into teaching?" -- Terry Pratchett
- [Iccrg] Why don't we stop treating ECN and loss s… Mayutan A.
- [Iccrg] Why don't we stop treating ECN and loss s… Mikael Abrahamsson
- [Iccrg] Why don't we stop treating ECN and loss s… David Ros
- [Iccrg] Why don't we stop treating ECN and loss s… Michael Welzl
- [Iccrg] Why don't we stop treating ECN and loss s… ken carlberg
- [Iccrg] Why don't we stop treating ECN and loss s… Mikael Abrahamsson
- [Iccrg] Why don't we stop treating ECN and loss s… ken carlberg
- [Iccrg] Why don't we stop treating ECN and loss s… Mikael Abrahamsson
- [Iccrg] Why don't we stop treating ECN and loss s… Michael Welzl
- [Iccrg] Why don't we stop treating ECN and loss s… João Taveira Araújo
- [Iccrg] Why don't we stop treating ECN and loss s… João Taveira Araújo
- [Iccrg] Why don't we stop treating ECN and loss s… Lachlan Andrew
- [Iccrg] Why don't we stop treating ECN and loss s… Michael Welzl