[Ecn-sane] A brick wall threshold for SCE_threshold

Dave Taht dave.taht at gmail.com
Tue Mar 9 14:20:22 EST 2021


On Tue, Mar 9, 2021 at 10:58 AM Jonathan Morton <chromatix99 at gmail.com> wrote:
>
> > On 9 Mar, 2021, at 8:48 pm, Dave Taht <dave.taht at gmail.com> wrote:
> >
> > I do not think anything other than a brick wall can be implemented in high speed hardware.
>
> We've spoken to a Cisco guy who says they can already do Approximate Fairness at 100Gbps per port.  That's our benchmark.

I have long wondered how much of AFD they were selling.

>
> > I really wish you'd try a brick wall
>
> We did.  We didn't like the results.

But you did not try a bbr-like approach. Observe a mark, and the rtt inflation.

bbrv2 works pretty decently with CE_threshold already. making it work
with a brick wall
SCE made some sense.

>
>  - Jonathan Morton



-- 
"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


More information about the Ecn-sane mailing list