Something that may interest folks here is that we compared Sprout-over-unlimited-buffer with TCP-Cubic-over-CoDel on these cellular-type links. That is, a scenario where the network operators implemented CoDel inside the LTE/UMTS/1xEV-DO base station (for the downlink) and the phone manufacturers implemented CoDel inside the "baseband" chip for the uplink.

Bottom line results is that for the case where a cellular user can control all their own flows, it's roughly a wash. To a first approximation, you can fix bufferbloat on a cellular network *either* by putting CoDel inside the base station and baseband chip (and otherwise running the same endpoint TCP), *or* by changing the endpoints but leaving the base station and baseband chip unmodified.

Obviously we benefit dramatically from the per-user queues of the cellular network. By contrast, in a typical house with a bufferbloated cable modem where one user can cause big delays for everybody else, you can't fix bufferbloat by fixing just one endpoint. We will have some results soon on whether you can fix it by fixing all the endpoints (but still leaving the "bloated" gateway intact).

On Wed, Jul 10, 2013 at 3:30 PM, Dave Taht <dave.taht@gmail.com> wrote:

I haven't been paying a lot of attention to rmcat and webrtc until
recently, although I'd had a nice discussion with keith on it a while
back..

this particular thread sums up some interesting issues on that front.

http://www.ietf.org/mail-archive/web/rmcat/current/msg00390.html

--
Dave Täht

Fixing bufferbloat with cerowrt: http://www.teklibre.com/cerowrt/subscribe.html