I am curious as to the cpu and thruput difference between pfifo, htb + fqcodel v cake at these insane speeds. On Fri, Jul 6, 2018, 3:27 AM Toke Høiland-Jørgensen wrote: > Jonathan Morton writes: > > >> On 6 Jul, 2018, at 4:21 pm, Toke Høiland-Jørgensen > wrote: > >> > >>> I'm handling it without using any extra permanent state, just making > >>> use of what's already there. Take a look at latest commit. > >> > >> Yup, that also fixes the infinite loop issue. I'm fine with doing it > >> this way; however, it doesn't handle the other places where we check > >> whether sch->q.qlen is nonzero. Are you sure that is not going to give > >> us more problems down the road? :) > > > > The other places are checking whether the queue is empty for the > > purposes of updating the shaper state. They are therefore much less > > critical, and I think self-correcting. > > Right, cool. In that case I think we are good to go for another upstream > submission; I'll get that done later today :) > > -Toke > _______________________________________________ > Cake mailing list > Cake@lists.bufferbloat.net > https://lists.bufferbloat.net/listinfo/cake >