On Tue, Jan 15, 2019 at 10:15:01AM +0000, Patrick Bellasi wrote:
> +#ifdef CONFIG_UCLAMP_TASK
> +struct uclamp_bucket {
> + unsigned long value : bits_per(SCHED_CAPACITY_SCALE);
> + unsigned long tasks : BITS_PER_LONG - bits_per(SCHED_CAPACITY_SCALE);
> +};
> +struct uclamp_cpu {
> + unsigned int value;
/* 4 byte hole */
> + struct uclamp_bucket bucket[UCLAMP_BUCKETS];
> +};
With the default of 5, this UCLAMP_BUCKETS := 6, so struct uclamp_cpu
ends up being 7 'unsigned long's, or 56 bytes on 64bit (with a 4 byte
hole).
> +#endif /* CONFIG_UCLAMP_TASK */
> +
> /*
> * This is the main, per-CPU runqueue data structure.
> *
> @@ -835,6 +879,11 @@ struct rq {
> unsigned long nr_load_updates;
> u64 nr_switches;
>
> +#ifdef CONFIG_UCLAMP_TASK
> + /* Utilization clamp values based on CPU's RUNNABLE tasks */
> + struct uclamp_cpu uclamp[UCLAMP_CNT] ____cacheline_aligned;
Which makes this 112 bytes with 8 bytes in 2 holes, which is short of 2
64 byte cachelines.
Is that the best layout?
> +#endif
> +
> struct cfs_rq cfs;
> struct rt_rq rt;
> struct dl_rq dl;
> --
> 2.19.2
>
