[Ecn-sane] ect(1) queue selector question

[Dave Taht]

Thx for the clarifications. What I meant by X-G was 3G, 4G, 5G.

On Sun, Feb 21, 2021 at 9:14 AM Rodney W. Grimes
<4bone at gndrsh.dnsmgr.net> wrote:
>
> Hello Dave, and Sebastian,
>
> > Hi Dave,
> >
> >
> > > On Feb 20, 2021, at 20:27, Dave Taht <dave.taht at gmail.com> wrote:
> > >
> > > I note that I have done my best to stay out of this for a while, so
> > > long that I (thankfully) mis-remember various aspects of the debate.
> > > Today I have a question about l4s vs SCE as it's come up again.
> > >
> > > l4s uses both a dscp codepoint AND ect(1) to indicate dctcp style
> > > congestion control
> > > is in use, and also can dump other protocols into that queue lacking
> > > any ecn markings.
> >
> >       Mmmh, according to the L4S internet drafts, L4S does not want to use a DSCP at all. Interestingly enough, Greg White is proposing a related internet draft about the NQB PHB and DSCP that sounds awfully like the missing DSCP in the L4S drafts. IMHO if the whole thing would be guarded behind a DSCP I would be less annoyed by the design and process of L4S....
>
> That is correct, the L4S proponents absolutely do not want anything to do with a DSCP and L4S.
> If they would of simply agreed that this was actually a good idea they could propbably be at deployment state now.... but they insist it is pointless to take this route due to the traveral problem.
>
> >
> > >
> > > SCE proposes to use ect(1) as an indicator of some congestion and does
> > > not explictly
> > > require a dscp codepoint in a FQ'd implementation.
> >
> >       Pretty much. I do think that a demonstration using an additional DSCP to create a similar HOV lane for SCE would have gone miles in convincing people in the WG that L4S might really not be as swell as its proponents argue, IMHO it won the day more with its attractive promise of low latency for all instead of what it delivers.
>
> The original SCE design was without any mention of DSCP.  Since that pretty much stahled us in the battle with L4S there actually *IS* an SCE design that uses one or more DSCP.  This technically allows SCE to proceed forward on its own without any blessing from IETF so that we may gain some additional experience and data.  This *IS NOT* the ideal design, but I feel by taking this road we might gain ground.
>
> > > Do I have that right? Now, my question was, simply, in MPLS or X-G are
> > > they out of bits, and
> > > that's why they want to use up this one in L4S?
> >
> >       I do not think that MPLS folks are a driver in all of this, no? No idea what X-G is.
>
> We do not know fully all of there motivations for being so very insistant on doing it this way, only this way, and with no changes of any kind.  But they do seem very stuck on there design and unflexiable in any and all suggestions of change.
>
> > > --
> > > "For a successful technology, reality must take precedence over public
> > > relations, for Mother Nature cannot be fooled" - Richard Feynman
> > >
> > > dave at taht.net <Dave T?ht> CTO, TekLibre, LLC Tel: 1-831-435-0729
>
> Regards,
> --
> Rod Grimes                                                 rgrimes at freebsd.org



-- 
"For a successful technology, reality must take precedence over public
relations, for Mother Nature cannot be fooled" - Richard Feynman

dave at taht.net <Dave Täht> CTO, TekLibre, LLC Tel: 1-831-435-0729