Hello, Michal. On Mon, Jun 17, 2013 at 03:27:44PM +0200, Michal Hocko wrote: > Thanks for your results! Yes the boost can be really high. I will try to > measure some memcg workloads as soon as I have some spare cycles. I do > not expect a big win but I also do not think this would regress. With the just committed RCU-sched conversion, the slowdown even on single CPU configuration w/ CONFIG_PREEMPT should be in the range of a few percent points in the worst cases and will mostly be in the noise in any realistic scenarios. So, yeah, looks pretty good to me. :) Thanks. -- tejun _______________________________________________ Containers mailing list Containers@xxxxxxxxxxxxxxxxxxxxxxxxxx https://lists.linuxfoundation.org/mailman/listinfo/containers
