On Fri, 2019-02-22 at 14:06 +0100, Toke Høiland-Jørgensen wrote: > Johannes Berg <johannes@xxxxxxxxxxxxxxxx> writes: > > > Toke Høiland-Jørgensen wrote: > > > > > When we did the original tests for the optimal value of sk_pacing_shift, we > > > came up with 6 ms of buffering as the default. Sadly, 6 is not a power of > > > two, so when picking the shift value I erred on the size of less buffering > > > and picked 4 ms instead of 8. This was probably wrong; those 2 ms of extra > > > buffering makes a larger difference than I thought. > > > > > > So, change the default pacing shift to 7, which corresponds to 8 ms of > > > buffering. The point of diminishing returns really kicks in after 8 ms, and > > > so having this as a default should cut down on the need for extensive > > > per-device testing and overrides needed in the drivers. > > > > > > Signed-off-by: Toke Høiland-Jørgensen <toke@xxxxxxxxxx> > > > > Patch applied to wireless.git, thanks. > > > > a41f56b9a17a (HEAD -> mac80211) mac80211: Change default > > tx_sk_pacing_shift to 7 This mess came from Kalle's tool btw, so I can't really use it yet :-) > Cool, thanks! What's the easiest way to backport this? I figure it's > easier to just update sk_pacing_shift_update() in tx.c for 4.19 (which > predates the addition of the driver override hook); shall I just send a > separate patch to stable for that? Or do we need to backport the driver > override hook as well? Just update the value, no need to backport the hook. johannes
