[Cerowrt-devel] [Make-wifi-fast] wifi airtime fairness patches could use eyeballs and testing
toke at toke.dk
Wed Aug 10 11:04:08 EDT 2016
Noah Causin <n0manletter at gmail.com> writes:
> I am aware that a performance regression with using fq in mac80211 with multiple tcp streams has been reported, and this patch in lede disables it.
> Has that been resolved?
Just did a test of this and can reproduce with a wndr3800 as the access
point. I see about a 25% reduction in aggregate throughput with two
streams as opposed to one.
Packet captures and time sequence graphs are here:
https://kau.toke.dk/experiments/softq-debug/ - the onestream* and
More information about the Cerowrt-devel