Re: [RFC PATCH 6/8] sched/fair: Increase probability of lb stats being reused

["Chen, Yu C" <yu.c.chen@intel.com>]

On 3/13/2025 5:37 PM, K Prateek Nayak wrote:
> The load balancer will start caching the sg_lb_stats during load
> balancing and propagate it up the sched domain hierarchy in the
> subsequent commits.
> 
> Increase the probability of load balancing intervals across domains to
> be aligned to improve the reuse efficiency of the propagated stats.
> Go one step further and proactively explore balancing at a higher domain
> if the next update time for a higher domain in before the next update
> time for its children.
> 
> Signed-off-by: K Prateek Nayak <kprateek.nayak@amd.com>
> ---
>   kernel/sched/fair.c | 18 +++++++-----------
>   1 file changed, 7 insertions(+), 11 deletions(-)
> 
> diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
> index 3b1ed14e4b5e..60517a732c10 100644
> --- a/kernel/sched/fair.c
> +++ b/kernel/sched/fair.c
> @@ -11956,15 +11956,6 @@ get_sd_balance_interval(struct sched_domain *sd, int cpu_busy)
>   
>   	/* scale ms to jiffies */
>   	interval = msecs_to_jiffies(interval);
> -
> -	/*
> -	 * Reduce likelihood of busy balancing at higher domains racing with
> -	 * balancing at lower domains by preventing their balancing periods
> -	 * from being multiples of each other.
> -	 */
> -	if (cpu_busy)
> -		interval -= 1;
> -
>   	interval = clamp(interval, 1UL, max_load_balance_interval);
>   
>   	return interval;
> @@ -12126,7 +12117,7 @@ static void sched_balance_domains(struct rq *rq, enum cpu_idle_type idle)
>   	int continue_balancing = 1;
>   	int cpu = rq->cpu;
>   	int busy = idle != CPU_IDLE && !sched_idle_cpu(cpu);
> -	unsigned long interval;
> +	unsigned long interval, prev_sd_next_balance = 0;
>   	struct sched_domain *sd;
>   	/* Earliest time when we have to do rebalance again */
>   	unsigned long next_balance = jiffies + 60*HZ;
> @@ -12136,6 +12127,8 @@ static void sched_balance_domains(struct rq *rq, enum cpu_idle_type idle)
>   
>   	rcu_read_lock();
>   	for_each_domain(cpu, sd) {
> +		unsigned long next_interval;
> +
>   		/*
>   		 * Decay the newidle max times here because this is a regular
>   		 * visit to all the domains.
> @@ -12162,7 +12155,9 @@ static void sched_balance_domains(struct rq *rq, enum cpu_idle_type idle)
>   				goto out;
>   		}
>   
> -		if (time_after_eq(jiffies, sd->last_balance + interval)) {
> +		next_interval = sd->last_balance + interval;
> +		if (time_after_eq(jiffies, next_interval) ||
> +		    (prev_sd_next_balance && time_after(prev_sd_next_balance, next_interval))) {

(prev_sd_next_balance && time_after(jiffies, prev_sd_next_balance))?

thanks,
Chenyu

>   			if (sched_balance_rq(cpu, rq, sd, idle, &continue_balancing)) {
>   				/*
>   				 * The LBF_DST_PINNED logic could have changed
> @@ -12174,6 +12169,7 @@ static void sched_balance_domains(struct rq *rq, enum cpu_idle_type idle)
>   			}
>   			sd->last_balance = jiffies;
>   			interval = get_sd_balance_interval(sd, busy);
> +			prev_sd_next_balance = sd->last_balance + interval;
>   		}
>   		if (need_serialize)
>   			atomic_set_release(&sched_balance_running, 0);