Re: [RFC PATCH 2/4] mm: kpromoted: Hot page info collection and promotion daemon

[Davidlohr Bueso]

On Thu, 06 Mar 2025, Bharata B Rao wrote:

> +static int page_should_be_promoted(struct page_hotness_info *phi)
> +{
> +	struct page *page = pfn_to_online_page(phi->pfn);
> +	unsigned long now = jiffies;
> +	struct folio *folio;
> +
> +	if (!page || is_zone_device_page(page))
> +		return false;
> +
> +	folio = page_folio(page);
> +	if (!folio_test_lru(folio)) {
> +		count_vm_event(KPROMOTED_MIG_NON_LRU);
> +		return false;
> +	}
> +	if (folio_nid(folio) == phi->hot_node) {
> +		count_vm_event(KPROMOTED_MIG_RIGHT_NODE);
> +		return false;
> +	}

How about using the LRU age itself:

if (folio_test_active())
   return true;

> +
> +	/* If the page was hot a while ago, don't promote */
> +	if ((now - phi->last_update) > 2 * msecs_to_jiffies(KPROMOTED_FREQ_WINDOW)) {
> +		count_vm_event(KPROMOTED_MIG_COLD_OLD);
> +		return false;
> +	}
> +
> +	/* If the page hasn't been accessed enough number of times, don't promote */
> +	if (phi->frequency < KPRMOTED_FREQ_THRESHOLD) {
> +		count_vm_event(KPROMOTED_MIG_COLD_NOT_ACCESSED);
> +		return false;
> +	}
> +	return true;
> +}

...

> +static int kpromoted(void *p)
> +{
> +	pg_data_t *pgdat = (pg_data_t *)p;
> +	struct task_struct *tsk = current;
> +	long timeout = msecs_to_jiffies(KPROMOTE_DELAY);
> +
> +	const struct cpumask *cpumask = cpumask_of_node(pgdat->node_id);
> +
> +	if (!cpumask_empty(cpumask))
> +		set_cpus_allowed_ptr(tsk, cpumask);

Explicit cpumasks are not needed if you use kthread_create_on_node().

See https://web.git.kernel.org/pub/scm/linux/kernel/git/next/linux-next.git/commit/?id=c6a566f6c1b4d5dff659acd221f95a72923f4085

> +
> +	while (!kthread_should_stop()) {
> +		wait_event_timeout(pgdat->kpromoted_wait,
> +				   kpromoted_work_requested(pgdat), timeout);
> +		kpromoted_do_work(pgdat);
> +	}
> +	return 0;
> +}
> +
> +static void kpromoted_run(int nid)
> +{
> +	pg_data_t *pgdat = NODE_DATA(nid);
> +
> +	if (pgdat->kpromoted)
> +		return;
> +
> +	pgdat->kpromoted = kthread_run(kpromoted, pgdat, "kpromoted%d", nid);
> +	if (IS_ERR(pgdat->kpromoted)) {
> +		pr_err("Failed to start kpromoted on node %d\n", nid);
> +		pgdat->kpromoted = NULL;
> +	}
> +}
> +