Re: [tsvwg] L4S DSCP (was: L4S drafts: Next Steps)

[Wesley Eddy <[e-mail]>]

On 3/30/2021 11:19 PM, Steven Blake wrote:
> On Tue, 2021-03-30 at 19:12 -0400, Wesley Eddy wrote:
>> On 3/30/2021 6:41 PM, Jonathan Morton wrote:
>>> Okay, so what mechanism do you propose to contain the L4S
>>> experiment to the participating networks?
>> I think the notion of a strong containment guarantee to
>> participating
>> networks that you mention is a bit extreme in contrast to just
>> reducing
>> the likelihood or severity of issues. There has been a lot of
>> congestion
>> control experimentation on Internet paths that strong containment
>> has
>> not been expected of.
> How many of those experimental congestion control protocols set a RFC
> 3168-defined ECT marking on their packets and then failed to respond to
> a RFC 3168-defined CE congestion signal by triggering multiplicative
> decrease?

The issue is well understood.  The doc talks about detection and 
fallback, and has placeholders for more content in this area.


>> I think the sense of the working group has been to take an approach
>> of
>> collecting and recommending reasonable measures to identify and
>> avoid
>> issues when experimenting with L4S.  This is mainly in Section 4 of
>> the
>> ops draft right now.  I have not understood the general working
>> group
>> direction to be asking for strong containment guarantees though, and
>> I
>> don't think that needs to be a goal.
> The recommended measures in Sec. 5 (not 4) of l4sops-02 are directed at
> the operators deploying RFC 3168 and *not participating in the L4S
> experiment* and consist of either disabling RFC-3168 ECN or of
> instantiating configurations that depend on the capability to classify
> on ECT(1) markings specifically, a configuration feature that doesn't
> appear to be universally available in deployed software. Opinions
> differ on whether these measures are "reasonable" or are directed at
> the appropriate parties.

Section 4 has a number of precautions, as stated, for experimenting with 
L4S.