Messages in this thread | | | Date | Mon, 30 Nov 2015 11:23:22 +0100 | From | Peter Zijlstra <> | Subject | Re: [PATCH 2/3] sched/fair: Move hot load_avg into its own cacheline |
| |
On Wed, Nov 25, 2015 at 02:09:39PM -0500, Waiman Long wrote: > +++ b/kernel/sched/sched.h > @@ -248,7 +248,12 @@ struct task_group { > unsigned long shares; > > #ifdef CONFIG_SMP > - atomic_long_t load_avg; > + /* > + * load_avg can be heavily contended at clock tick time, so put > + * it in its own cacheline separated from the fields above which > + * will also be accessed at each tick. > + */ > + atomic_long_t load_avg ____cacheline_aligned;
Same as with the other patch; this only works if the structure itself is cacheline aligned, which I don't think it is.
> #endif > #endif > > -- > 1.7.1 >
| |