Re: [PATCH v2] sched/fair: reduce long-tail newly idle balance cost

On Tue, Mar 23, 2021 at 02:44:57PM +0100, Vincent Guittot wrote: > Hi Aurey, > > On Tue, 16 Mar 2021 at 05:27, Li, Aubrey wrote: > > > > On 2021/2/24 16:15, Aubrey Li wrote: > > > A long-tail load balance cost is observed on the newly idle path, > > > this is caused by a race window between the f

Re: [PATCH v2] sched/fair: reduce long-tail newly idle balance cost

Hi Aurey, On Tue, 16 Mar 2021 at 05:27, Li, Aubrey wrote: > > On 2021/2/24 16:15, Aubrey Li wrote: > > A long-tail load balance cost is observed on the newly idle path, > > this is caused by a race window between the first nr_running check > > of the busiest runqueue and its nr_running recheck in

Re: [PATCH v2] sched/fair: reduce long-tail newly idle balance cost

On 2021/2/24 16:15, Aubrey Li wrote: > A long-tail load balance cost is observed on the newly idle path, > this is caused by a race window between the first nr_running check > of the busiest runqueue and its nr_running recheck in detach_tasks. > > Before the busiest runqueue is locked, the tasks o