Re: [PATCH 07/10] sched, fair: Optimize find_busiest_queue()

[Paul Turner]

On Mon, Aug 19, 2013 at 9:01 AM, Peter Zijlstra <peterz@xxxxxxxxxxxxx> wrote:
> Use for_each_cpu_and() and thereby avoid computing the capacity for
> CPUs we know we're not interested in.
>
> Signed-off-by: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
> ---
>  kernel/sched/fair.c |    5 +----
>  1 file changed, 1 insertion(+), 4 deletions(-)
>
> --- a/kernel/sched/fair.c
> +++ b/kernel/sched/fair.c
> @@ -4977,7 +4977,7 @@ static struct rq *find_busiest_queue(str
>         unsigned long busiest_load = 0, busiest_power = SCHED_POWER_SCALE;
>         int i;
>
> -       for_each_cpu(i, sched_group_cpus(group)) {
> +       for_each_cpu_and(i, sched_group_cpus(group), env->cpus) {
>                 unsigned long power = power_of(i);
>                 unsigned long capacity = DIV_ROUND_CLOSEST(power,
>                                                            SCHED_POWER_SCALE);
> @@ -4986,9 +4986,6 @@ static struct rq *find_busiest_queue(str
>                 if (!capacity)
>                         capacity = fix_small_capacity(env->sd, group);
>
> -               if (!cpumask_test_cpu(i, env->cpus))
> -                       continue;
> -
>                 rq = cpu_rq(i);
>                 wl = weighted_cpuload(i);

There's no need to actually do the divisions immediately below this also.

e.g.
  unsigned long max_load_power = SCHED_POWER_SCALE;
  ...
  if (wl * max_load_power > max_load * power) {
   max_load = wl;
   max_load_power = power;
   ...

This would actually end up being a little more accurate even.

[ Alternatively without caching max_load_power we could compare wl *
power vs max_load * SCHED_POWER_SCALE. ]

Reviewed-by: Paul Turner <pjt@xxxxxxxxxx>
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/