[Bloat] Bufferbloat in high resolution + non-stationarity

[Toke Høiland-Jørgensen]

Martin Geddes <mail at martingeddes.com> writes:

> The two critical references are this paper
> <http://www.pnsol.com/public/TP-PNS-2003-09.pdf> and this PhD thesis
> <https://www.cs.kent.ac.uk/pubs/2003/1892/>. The former describes
> "cherish-urgency" multiplexing. The "cherish" is what is different to
> today's scheduling. It is used to create a new class of algorithm
> whose goal is global optimisation, not local optimisation (and global
> pessimisation).

Cool, thanks; I'll add that to my reading list (well, the paper
certainly; not sure I'll get the time to go through the whole 200+ page
thesis anytime soon :/)

> The latter describes a paradigm change from "build it and then reason
> about emergent performance" to "reason about engineered performance
> and then build it". It works in practise
> <http://www.martingeddes.com/how-wales-got-the-first-internet-fast-lane/>,
> so whether it works in theory is left as an exercise to the reader.

I don't suppose there's an open source implementation available to play
with?

-Toke