Re: [PATCH 5/6] mm/page_alloc: Limit the number of pages on PCP lists when reclaim is active

[Dave Hansen]

On 5/21/21 3:28 AM, Mel Gorman wrote:
> +static int nr_pcp_high(struct per_cpu_pages *pcp, struct zone *zone)
> +{
> +	int high = READ_ONCE(pcp->high);
> +
> +	if (unlikely(!high))
> +		return 0;
> +
> +	if (!test_bit(ZONE_RECLAIM_ACTIVE, &zone->flags))
> +		return high;
> +
> +	/*
> +	 * If reclaim is active, limit the number of pages that can be
> +	 * stored on pcp lists
> +	 */
> +	return READ_ONCE(pcp->batch) << 2;
> +}

Should there be a sanity check on this?  Let's say we had one of those
weirdo zones with tons of CPUs and a small low_wmark_pages().  Could we
have a case where:

	pcp->high < pcp->batch<<2

and this effectively *raises* nr_pcp_high()?

It's not possible with the current pcp->high calculation, but does
anything prevent it now?