On 12/8/25 09:27, K Prateek Nayak wrote:
> Pushing tasks can fail for multitude of reasons - task affinity, the
> unavailability of an idle CPUs by the time balance callback is executed,
> etc.
>
> Maintain a CPU local counter in sched_domain to rate limit push attempts
> if the failures build up. This counter is reset at the time of periodic
> balance to the value in "nr_idle_scan".
>
> Since "nr_idle_scan" is only computed for SIS_UTIL, rate limiting has
> been guarded behind the same sched_feat().
>
> Signed-off-by: K Prateek Nayak <kprateek.nayak@amd.com>
> ---
> include/linux/sched/topology.h | 4 ++++
> kernel/sched/fair.c | 23 +++++++++++++++++++++--
> 2 files changed, 25 insertions(+), 2 deletions(-)
>
> diff --git a/include/linux/sched/topology.h b/include/linux/sched/topology.h
> index 074ee2980cdf..ebe26ce82c1a 100644
> --- a/include/linux/sched/topology.h
> +++ b/include/linux/sched/topology.h
> @@ -122,6 +122,10 @@ struct sched_domain {
> unsigned int alb_failed;
> unsigned int alb_pushed;
>
> + /* Push load balancing */
> + unsigned long last_nr_push_update;
> + int nr_push_attempt;
> +
> /* SD_BALANCE_EXEC stats */
> unsigned int sbe_count;
> unsigned int sbe_balanced;
> diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
> index 34aeb8e58e0b..46d33ab63336 100644
> --- a/kernel/sched/fair.c
> +++ b/kernel/sched/fair.c
> @@ -12356,6 +12356,16 @@ static void sched_balance_domains(struct rq *rq, enum cpu_idle_type idle)
> rq->max_idle_balance_cost =
> max((u64)sysctl_sched_migration_cost, max_cost);
> }
> + if (sched_feat(SIS_UTIL)) {
> + sd = rcu_dereference(per_cpu(sd_llc, cpu));
> +
> + if (sd && sd->shared &&
> + time_after_eq(jiffies, sd->last_nr_push_update + sd->min_interval)) {
> + sd->nr_push_attempt = READ_ONCE(sd->shared->nr_idle_scan);
> + sd->last_nr_push_update = jiffies;
> + }
> + }
> +
> rcu_read_unlock();
>
> /*
> @@ -13110,8 +13120,6 @@ static inline bool should_push_tasks(struct rq *rq)
> struct sched_domain *sd;
> int cpu = cpu_of(rq);
>
> - /* TODO: Add a CPU local failure counter. */
> -
> /* CPU doesn't have any fair task to push. */
> if (!has_pushable_tasks(rq))
> return false;
> @@ -13126,6 +13134,10 @@ static inline bool should_push_tasks(struct rq *rq)
> if (!sd)
> return false;
>
> + /* We've failed to push task too many times. */
> + if (sched_feat(SIS_UTIL) && sd->nr_push_attempt <= 0)
> + return false;
> +
> /*
> * We may not be able to find a push target.
> * Skip for this tick and depend on the periodic
> @@ -13176,6 +13188,13 @@ static bool push_fair_task(struct rq *rq)
> return true;
> }
>
> + /*
> + * If the push failed after a full search, decrement the
> + * attempt counter to dicourage further attempts. Periodic
> + * balancer will reset the "nr_push_attempt" after a while.
> + */
> + sd->nr_push_attempt--;
> +
> return false;
> }
>
Just to confirm, but this patch is included when the cover letter mentions "push" for the
benchmarks?
Did this help the regressions then?