[LibreQoS] mice and elephants visualizations

[LibreQoS] mice and elephants visualizations

[Dave Taht]

All of us, including me! have a tendency to do things like measure a
ton of flent or iperf sessions and consider the end result "good".

Actual traffic looks nothing like that, with the vast majority of
flows in slow start, and ending quickly. This old paper came to mind
yesterday, in light of seeing bracket's qoe stuff land:

http://www.cs.unc.edu/Research/dirt/proj/marron/MiceElephants/

One of fq_codel's and cakes hidden advantages is in the fq portion,
where, for the first 3-5 round trips on a tcp connection,
go out first, and that is in part why it runs circles around everything else.




-- 
This song goes out to all the folk that thought Stadia would work:
https://www.linkedin.com/posts/dtaht_the-mushroom-song-activity-6981366665607352320-FXtz
Dave Täht CEO, TekLibre, LLC