[Bloat] still trying to find hardware for the next generation worth hacking on

[Dave Taht]

I figure everyone has already seen this:

http://burntchrome.blogspot.com/2014/05/fixing-bufferbloat-on-comcasts-blast.html

But this is the best we can do. Above 50mbit, cero's current hardware
(cpu designed in 1989)
peaks out. We've done some testing on the slightly higher end
edgerouter lite, and it
can't keep up, either, above about 70mbit. The edgerouter pro does
considerably better but costs considerably more. ivy bridge x86 boxes
"just work" up to well past 300mbits...

As cerowrt 3.10 is basically baked, it's time (finally!) to find a new
chipset that everyone can work with, and move on to higher gateway
bandwidths, and 802.11ac.

For 2+ years now, we've been looking for better hardware than this...
and I'd like to at
least find something sooner that could run the SQM system at 105Mbit...

I know we could just switch future development to intel hardware, and
there are some promising arm based designs now out, and there have
been a few suggestions here and on cerowrt-devel...

At the moment, I'm thinking that instead of searching for a chipset,
and board, that merely issuing an RFP with the requirements of this
project and others associated with it, might find us a vendor willing
to help, with something new coming off the line... would anyone be
interested in helping write that?

-- 
Dave Täht