Re: [Starlink] [Rpm] RFC: bufferbloat observability project

[Robert McMahon <rjmcmahon@rjmcmahon.com>]

[-- Attachment #1: Type: text/plain, Size: 1309 bytes --]

Hi Dave,

Thanks for the mention of iperf 2. I want to clarify that the tooling over the last many years has a focus on ultra low latency both in metrics and mechanisms. Bufferbloat is supported mostly as a rating through the use of synthetic traffic and Little's Law. David Reed had pointed out that synthetic traffic does not match real world traffic, which comes from chaotic distributions and might be infinite in the possibilities (though maybe less than infinity squared.)


Bob



On Mar 12, 2023, 5:52 AM, at 5:52 AM, Dave Taht via Rpm <rpm@lists.bufferbloat.net> wrote:
>I just put together a list of common tools developers use every day,
>that would benefit from observing and managing network latency better.
>Things like git, and so on. Could some folk out there please pitch in
>with additional suggestions?
>
>https://docs.google.com/document/d/1SPuDhjMggexUuIGV8lUziQ3r8JjyLSwpZPoHieVLiaE/edit#heading=h.fyd7g5rbur4a
>
>Also it increasingly bothers me to see unbounded queues in so many new
>language libraries.
>
>--
>Roy Beatty (from Blade Runner) and I:
>https://www.understandinglatency.com/
>Dave Täht CEO, TekLibre, LLC
>_______________________________________________
>Rpm mailing list
>Rpm@lists.bufferbloat.net
>https://lists.bufferbloat.net/listinfo/rpm

[-- Attachment #2: Type: text/html, Size: 1567 bytes --]