>
> diff --git a/kernel/sched/core.c b/kernel/sched/core.c
> index e8b3350..da2cb3e 100644
> --- a/kernel/sched/core.c
> +++ b/kernel/sched/core.c
> @@ -1348,6 +1348,8 @@ ttwu_do_wakeup(struct rq *rq, struct task_struct *p,
> int wake_flags)
> else
> update_avg(&rq->avg_idle, delta);
> rq->idle_stamp = 0;
> +
> + rq->idle_duration = (rq->idle_duration + delta) / 2;
Cant we just use avg_idle instead of introducing idle_duration?
> }
> #endif
> }
> @@ -7027,6 +7029,7 @@ void __init sched_init(void)
> rq->online = 0;
> rq->idle_stamp = 0;
> rq->avg_idle = 2*sysctl_sched_migration_cost;
> + rq->idle_duration = 0;
>
> INIT_LIST_HEAD(&rq->cfs_tasks);
>
> diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
> index 75024a6..a3f062c 100644
> --- a/kernel/sched/debug.c
> +++ b/kernel/sched/debug.c
> @@ -307,6 +307,7 @@ do {
> \
> P(sched_goidle);
> #ifdef CONFIG_SMP
> P64(avg_idle);
> + P64(idle_duration);
> #endif
>
> P(ttwu_count);
> diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
> index c61a614..da7ddd6 100644
> --- a/kernel/sched/fair.c
> +++ b/kernel/sched/fair.c
> @@ -5240,6 +5240,8 @@ void idle_balance(int this_cpu, struct rq *this_rq)
> struct sched_domain *sd;
> int pulled_task = 0;
> unsigned long next_balance = jiffies + HZ;
> + u64 cost = 0;
> + u64 idle_duration = this_rq->idle_duration;
>
> this_rq->idle_stamp = this_rq->clock;
>
> @@ -5256,14 +5258,31 @@ void idle_balance(int this_cpu, struct rq *this_rq)
> for_each_domain(this_cpu, sd) {
> unsigned long interval;
> int balance = 1;
> + u64 this_domain_balance_cost = 0;
> + u64 start_time;
>
> if (!(sd->flags & SD_LOAD_BALANCE))
> continue;
>
> + /*
> + * If the time which this_cpu remains is not lot higher than
> the cost
> + * of attempt idle balancing within this domain, then stop
> searching.
> + */
> + if (idle_duration / 10 < (sd->avg_idle_balance_cost + cost))
> + break;
> +
> if (sd->flags & SD_BALANCE_NEWIDLE) {
> + start_time = sched_clock_cpu(smp_processor_id());
> +
> /* If we've pulled tasks over stop searching: */
> pulled_task = load_balance(this_cpu, this_rq,
> sd, CPU_NEWLY_IDLE,
> &balance);
> +
> + this_domain_balance_cost =
> sched_clock_cpu(smp_processor_id()) - start_time;
Should we take the consideration of whether a idle_balance was
successful or not?
How about having a per-sched_domain counter.
For every nth unsuccessful load balance, skip the n+1th idle
balance and reset the counter. Also reset the counter on every
successful idle load balance.
I am not sure whats a reasonable value for n can be, but may be we could
try with n=3.
Also have we checked the performance after adjusting the
sched_migration_cost tunable?
I guess, if we increase the sched_migration_cost, we should have lesser
newly idle balance requests.
--
Thanks and Regards
Srikar Dronamraju
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majord...@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
