Re: [iccrg] Musings on the future of Internet Congestion Control

Hi Christian!

I definitely think that work like this is the way to go - as capacities become less and less utilized, we should probably make congestion controls a bit more “daring”.

As a side note, your email made me check if RFC 9040 is cited  ;-)   and it is… but the way the reference is written in section 3.4 gives the impression that RFC 9040 only discusses the case of concurrent connections, which it doesn’t (it’s one half of the RFC, called “ensemble sharing" - the other half is “temporal sharing”). I think it would make sense to update this text a little.

Generally, for anyone who think that something in particular should have been referenced in our paper, please note that IEEE Communications Magazine only allows 15 references.  We DID want to cite, and talk about much more. We’re also in the order of 10 words or so below the word limit.

Cheers,
Michael

> On Jun 16, 2022, at 5:57 AM, Christian Huitema <huitema@huitema.net> wrote:
> 
> Michael,
> 
> Your paper mentions the issue of "not being able to ramp up capacity quickly enough". There has been quite a bit of attention to that in the context of satellite networks, leading for example to https://datatracker.ietf.org/doc/html/draft-kuhn-quic-careful-resume-01.html -- basically, remember network conditions from previous connections and use them cautiously to ramp up congestion control faster. Maybe worth mentioning in follow-up papers.
> 
> -- Christian Huitema
> 
> On 6/15/2022 1:02 AM, Michael Welzl wrote:
>> Dear ICCRGers,
>> 
>> We just got a paper accepted that I wanted to share:
>> Michael Welzl, Peyman Teymoori, Safiqul Islam, David Hutchison, Stein Gjessing: "Future Internet Congestion Control: The Diminishing Feedback Problem", accepted for publication in IEEE Communications Magazine, 2022.
>> 
>> The preprint is available at:
>> https://arxiv.org/abs/2206.06642 <https://arxiv.org/abs/2206.06642>
>> I thought that it could provoke an interesting discussion in this group.
>> 
>> Figures 4 and 5 in this paper show that, across the world, network links do not just become "faster”: the range between the low end and the high end grows too.
>> This, I think, is problematic for a global end-to-end standard - e.g., it means that we cannot simply keep scaling IW along forever (or, if we do, utilization will decline more and more).
>> 
>> So, we ask: what is the way ahead?  Should congestion control really stay end-to-end?
>> 
>> Cheers,
>> Michael
>> 
>> 
>> 
>> _______________________________________________
>> iccrg mailing list
>> iccrg@irtf.org
>> https://www.irtf.org/mailman/listinfo/iccrg