Re: [PATCH v3 04/10] sched/fair: Let low-priority cores help high-priority busy SMT cores

[Vincent Guittot]

On Tue, 7 Feb 2023 at 05:50, Ricardo Neri
<ricardo.neri-calderon@xxxxxxxxxxxxxxx> wrote:
>
> Using asym_packing priorities within an SMT core is straightforward. Just
> follow the priorities that hardware indicates.
>
> When balancing load from an SMT core, also consider the idle of its
> siblings. Priorities do not reflect that an SMT core divides its throughput
> among all its busy siblings. They only makes sense when exactly one sibling
> is busy.
>
> Indicate that active balance is needed if the destination CPU has lower
> priority than the source CPU but the latter has busy SMT siblings.
>
> Make find_busiest_queue() not skip higher-priority SMT cores with more than
> busy sibling.
>
> Cc: Ben Segall <bsegall@xxxxxxxxxx>
> Cc: Daniel Bristot de Oliveira <bristot@xxxxxxxxxx>
> Cc: Dietmar Eggemann <dietmar.eggemann@xxxxxxx>
> Cc: Len Brown <len.brown@xxxxxxxxx>
> Cc: Mel Gorman <mgorman@xxxxxxx>
> Cc: Rafael J. Wysocki <rafael.j.wysocki@xxxxxxxxx>
> Cc: Srinivas Pandruvada <srinivas.pandruvada@xxxxxxxxxxxxxxx>
> Cc: Steven Rostedt <rostedt@xxxxxxxxxxx>
> Cc: Tim C. Chen <tim.c.chen@xxxxxxxxx>
> Cc: Valentin Schneider <vschneid@xxxxxxxxxx>
> Cc: x86@xxxxxxxxxx
> Cc: linux-kernel@xxxxxxxxxxxxxxx
> Suggested-by: Valentin Schneider <vschneid@xxxxxxxxxx>
> Signed-off-by: Ricardo Neri <ricardo.neri-calderon@xxxxxxxxxxxxxxx>
> ---
> Changes since v2:
>  * Introduced this patch.
>
> Changes since v1:
>  * N/A
> ---
>  kernel/sched/fair.c | 31 ++++++++++++++++++++++++++-----
>  1 file changed, 26 insertions(+), 5 deletions(-)
>
> diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
> index 80c86462c6f6..c9d0ddfd11f2 100644
> --- a/kernel/sched/fair.c
> +++ b/kernel/sched/fair.c
> @@ -10436,11 +10436,20 @@ static struct rq *find_busiest_queue(struct lb_env *env,
>                     nr_running == 1)
>                         continue;
>
> -               /* Make sure we only pull tasks from a CPU of lower priority */
> +               /*
> +                * Make sure we only pull tasks from a CPU of lower priority
> +                * when balancing between SMT siblings.
> +                *
> +                * If balancing between cores, let lower priority CPUs help
> +                * SMT cores with more than one busy sibling.
> +                */
>                 if ((env->sd->flags & SD_ASYM_PACKING) &&
>                     sched_asym_prefer(i, env->dst_cpu) &&
> -                   nr_running == 1)
> -                       continue;
> +                   nr_running == 1) {
> +                       if (env->sd->flags & SD_SHARE_CPUCAPACITY ||
> +                           (!(env->sd->flags & SD_SHARE_CPUCAPACITY) && is_core_idle(i)))

This 2nd if could be merged with the upper one
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -10518,11 +10518,10 @@ static struct rq *find_busiest_queue(struct
lb_env *env,
                 */
                if ((env->sd->flags & SD_ASYM_PACKING) &&
                    sched_asym_prefer(i, env->dst_cpu) &&
-                   nr_running == 1) {
-                       if (env->sd->flags & SD_SHARE_CPUCAPACITY ||
-                           (!(env->sd->flags & SD_SHARE_CPUCAPACITY)
&& is_core_idle(i)))
+                   (nr_running == 1) &&
+                   (env->sd->flags & SD_SHARE_CPUCAPACITY ||
+                           (!(env->sd->flags & SD_SHARE_CPUCAPACITY)
&& is_core_idle(i))))
                                continue;
-               }

                switch (env->migration_type) {
                case migrate_load:
---

AFAICT, you can even remove one env->sd->flags & SD_SHARE_CPUCAPACITY
test with the below but this make the condition far less obvious

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index a6021af9de11..7dfa30c45327 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -10518,11 +10518,10 @@ static struct rq *find_busiest_queue(struct
lb_env *env,
                 */
                if ((env->sd->flags & SD_ASYM_PACKING) &&
                    sched_asym_prefer(i, env->dst_cpu) &&
-                   nr_running == 1) {
-                       if (env->sd->flags & SD_SHARE_CPUCAPACITY ||
-                           (!(env->sd->flags & SD_SHARE_CPUCAPACITY)
&& is_core_idle(i)))
+                   (nr_running == 1) &&
+                   !(!(env->sd->flags & SD_SHARE_CPUCAPACITY) &&
+                       !is_core_idle(i)))
                                continue;
-               }

> +                               continue;
> +               }
>
>                 switch (env->migration_type) {
>                 case migrate_load:
> @@ -10530,8 +10539,20 @@ asym_active_balance(struct lb_env *env)
>          * lower priority CPUs in order to pack all tasks in the
>          * highest priority CPUs.
>          */
> -       return env->idle != CPU_NOT_IDLE && (env->sd->flags & SD_ASYM_PACKING) &&
> -              sched_asym_prefer(env->dst_cpu, env->src_cpu);
> +       if (env->idle != CPU_NOT_IDLE && (env->sd->flags & SD_ASYM_PACKING)) {
> +               /* Always obey priorities between SMT siblings. */
> +               if (env->sd->flags & SD_SHARE_CPUCAPACITY)
> +                       return sched_asym_prefer(env->dst_cpu, env->src_cpu);
> +
> +               /*
> +                * A lower priority CPU can help an SMT core with more than one
> +                * busy sibling.
> +                */
> +               return sched_asym_prefer(env->dst_cpu, env->src_cpu) ||
> +                      !is_core_idle(env->src_cpu);
> +       }
> +
> +       return false;
>  }
>
>  static inline bool
> --
> 2.25.1
>