10g residential CPE
Mikael Abrahamsson
swmike at swm.pp.se
Sat Dec 26 18:28:18 UTC 2020
On Sat, 26 Dec 2020, Baldur Norddahl wrote:
> I demonstrated that it is about buffers by showing the same download
> from a server that paces the traffic indeed gets the full 930 Mbps with
> exactly the same settings, including starting window size, and the same
> path (Copenhagen to Stockholm).
You demonstrated that it's about which TCP algorithm they use, probably.
They all respond very differently to increase in RTT vs loss.
https://arxiv.org/pdf/1903.03852.pdf
Generally the Internet doesn't need more buffers, it needs less. If you
have only FIFO available, configure it to tail-drop at 10ms or so, to help
your customers with what they really care about, interactive performance.
I debloat my 1000/1000 with bidir 900/900 FQ_CODEL to avoid my downloads
affecting my interactive performance.
--
Mikael Abrahamsson email: swmike at swm.pp.se
More information about the NANOG
mailing list