Re: [RFC PATCH v2 07/23] sched/cache: Prioritize preferred NUMA node selection over LLC selection

[Peter Zijlstra]

On Thu, Aug 27, 2026 at 08:28:00PM +0800, Jianyong Wu wrote:

> +	/*
> +	 * Avoid switching sc_stat.cpu too fast. The reason to choose 2X is
> +	 * because:
> +	 * 1. It is better to keep the preferred LLC stable, rather than
> +	 *    changing it frequently and cause migrations
> +	 * 2. 2X means the new preferred LLC has at least 1 more busy CPU than
> +	 *    the old one(200% vs 100%, eg)
> +	 * 3. 2X is chosen based on test results, as it delivers the optimal
> +	 *    performance gain so far.
> +	 *
> +	 * Moving to another node takes precedence over moving inside the
> +	 * current one, as it did when the two updates were applied in that
> +	 * order.
> +	 */

Comments should never refer to old code that no longer exists. Comments
are for the code as it is now. If you want to expand on details of the
transition from one implementation to the next, that's what the
Changelog is for.

> +	if (m_a_n_occ > 2 * curr_m_a_n_occ)
> +		new_cpu = m_a_n_cpu;
> +	else if (pref_llc_cpu >= 0 && pref_llc_occ > 2 * curr_m_a_occ)
> +		new_cpu = pref_llc_cpu;
> +
> +	if (new_cpu >= 0)
> +		WRITE_ONCE(mm->sc_stat.cpu, new_cpu);
>  
>  	update_avg_scale(&mm->sc_stat.nr_running_avg, nr_running);
>  	free_cpumask_var(cpus);
> -- 
> 2.34.1
> 
>