Re: [tsvwg] L4S vs SCE

[Jonathan Morton <[e-mail]>]

NB: most of the questions below don't seem to be directly relevant to the coexistence question this thread is supposed to be exploring.

>>> Would an SCE router likely preserve or change the queueing of ECT(1) L4S traffic? - is this behvaiour different to any existing ECN-marking router?
>> 
>> SCE middleboxes don't queue or handle ECN(1)-marked or CE-marked traffic any differently from ECT(0) traffic.  The a-priori ECT(1) marking merely removes the option of applying an SCE mark.
> 
> Will a SCE middlebox keep a rolling update of the incoming fraction of
> ECT(1) vs. the fraction it would want to (re-)mark with ECT(1)? Or is
> "ships-in-the-night" behavior between two fractionally congested SCE
> middleboxes sufficient with an overall remarking probability of
> 1-((1-p1)*(1-p2))
> 
> With regular RED, ships-in-the-night was acepted, but the typical
> marking ratios for 3168-TCP would be an order of magnitude lower,
> limiting the deviation compared to "correct" max(p1, p2) marking.

This question is not important.  SCE admits the possibility of a wide variety of marking strategies, some of which may choose to take this factor into account.  The reference AQMs do not.

> As SCE has a target marking probability (ect0 -> ect1) from close to 50%
> under steady state, such couplings between consecutive bottlenecks would
> be much more prononounced.

You are again looking at old, long-superseded information.  The target marking probability is typically below 50% at steady state.  It would be as high as 50% in the case of a cwnd of about 4 segments.

>>> And would SCE traffic arriving at the L4S queue meet L4S expectations in terms of responsiveness?
>> 
>> Yes, since the MD response to CE is actually more severe/conservative than what L4S expects.
> 
> Well, SCE would be starved out due to the high p of CE marks in a L4S
> queue, even if not sharing the Q.

Remember that SCE-marked packets exist due to upstream congestion at an SCE-aware bottleneck.  As soon as the affected flow reacts to CE, it will back off sufficiently to ensure the upstream queue is drained, and SCE marking will generally then cease, ensuring that the flow is now entirely ECT(0) marked.  This dynamic behaviour is important to understand when considering the system as a whole.

>> Is that sufficient, or does a more detailed analysis need to be organised?
> 
> A good analytical model of the sce cc response function would be good to
> have always.

Sure, but that's not relevant to the coexistence question.  Let's keep it to its own thread.

 - Jonathan Morton