Re:Beyond bufferbloat: End-to-end congestion control cannot ...
by nsteel on Wednesday July 10, 2024 @09:32AM
(#40926717)
Did you read the linked paper which talks a lot about TCP pacing?
Re:Beyond bufferbloat: End-to-end congestion control cannot ...
by sambazi on Thursday July 11, 2024 @07:41AM
(#40935577)
i did not read that paper with a focus on adaptive bitrate selection for video streaming services that came out 8 years after the pacing implementation hit the kernel. thx thou
Re:Beyond bufferbloat: End-to-end congestion control cannot ...
by nsteel on Tuesday July 23, 2024 @10:09AM
(#41046188)
It uses that implementation, so yes, it came out afterwards. Section 2 and 3 might help.
Re:Beyond bufferbloat: End-to-end congestion control cannot ...
by flapjack on Thursday July 11, 2024 @01:36PM
(#40938858)
I would definitely not say that we re-invented pacing! One version of the question we looked at was: how low a pace rate can you pick for an ABR algorithm, without reducing video QoE? The part which takes work is this "without reducing video QoE" requirement. If you're interested, check out the paper!
Re:Beyond bufferbloat: End-to-end congestion control cannot ...
by sambazi on Friday July 12, 2024 @05:20AM
(#40943973)
> One version of the question we looked at was: how low a pace rate can you pick for an ABR algorithm, without reducing video QoE?
that is certainly an interesting economical optimization problem to reason about, though imho somewhat beyond technical merit, as simply letting the client choose quality and sending the data full speed works well enough.
addition:
i totally agree that things have to look economical in order to work and that there are technical edge-cases that need to be handled for good ux, but i dont't quite see how client-side buffer occupancy in the seconds range is in the users interest.
was slightly at a loss in what exactly needed to be shown here until i clicked the link and came to the conclusion that you re-invented(?) pacing.
https://man7.org/linux/man-pages/man8/tc-fq.8.html