Re: [PATCH v1 3/4] mm/compaction: optimize >0 order folio compaction with free page split.

[Zi Yan <ziy@nvidia.com>]

[-- Attachment #1: Type: text/plain, Size: 3430 bytes --]

On 22 Nov 2023, at 5:26, Ryan Roberts wrote:

> On 13/11/2023 17:01, Zi Yan wrote:
>> From: Zi Yan <ziy@nvidia.com>
>>
>> During migration in a memory compaction, free pages are placed in an array
>> of page lists based on their order. But the desired free page order (i.e.,
>> the order of a source page) might not be always present, thus leading to
>> migration failures. Split a high order free pages when source migration
>> page has a lower order to increase migration successful rate.
>>
>> Note: merging free pages when a migration fails and a lower order free
>> page is returned via compaction_free() is possible, but there is too much
>> work. Since the free pages are not buddy pages, it is hard to identify
>> these free pages using existing PFN-based page merging algorithm.
>>
>> Signed-off-by: Zi Yan <ziy@nvidia.com>
>> ---
>>  mm/compaction.c | 40 +++++++++++++++++++++++++++++++++++++++-
>>  1 file changed, 39 insertions(+), 1 deletion(-)
>>
>> diff --git a/mm/compaction.c b/mm/compaction.c
>> index ec6b5cc7e907..9c083e6b399a 100644
>> --- a/mm/compaction.c
>> +++ b/mm/compaction.c
>> @@ -1806,9 +1806,46 @@ static struct folio *compaction_alloc(struct folio *src, unsigned long data)
>>  	struct compact_control *cc = (struct compact_control *)data;
>>  	struct folio *dst;
>>  	int order = folio_order(src);
>> +	bool has_isolated_pages = false;
>>
>> +again:
>>  	if (!cc->freepages[order].nr_pages) {
>> -		isolate_freepages(cc);
>> +		int i;
>> +
>> +		for (i = order + 1; i <= MAX_ORDER; i++) {
>> +			if (cc->freepages[i].nr_pages) {
>> +				struct page *freepage =
>> +					list_first_entry(&cc->freepages[i].pages,
>> +							 struct page, lru);
>> +
>> +				int start_order = i;
>> +				unsigned long size = 1 << start_order;
>> +
>> +				list_del(&freepage->lru);
>> +				cc->freepages[i].nr_pages--;
>> +
>> +				while (start_order > order) {
>> +					start_order--;
>> +					size >>= 1;
>> +
>> +					list_add(&freepage[size].lru,
>> +						&cc->freepages[start_order].pages);
>> +					cc->freepages[start_order].nr_pages++;
>> +					set_page_private(&freepage[size], start_order);
>> +				}
>> +				post_alloc_hook(freepage, order, __GFP_MOVABLE);
>> +				if (order)
>> +					prep_compound_page(freepage, order);
>> +				dst = page_folio(freepage);
>> +				goto done;
>
> Perhaps just do:
>
> dst = (struct folio *)freepage;
> goto done;
>
> then move done: up a couple of statements below, so that post_alloc_hook() and
> prep_compound_page() are always done below in common path? Although perhaps the

Sure. Thanks for the suggestion.

> cast is frowned upon, you're already making the assumption that page and folio
> are interchangable the way you call list_first_entry().

To save the _compound_head() in page_folio()? OK.

>
>> +			}
>> +		}
>> +		if (!has_isolated_pages) {
>> +			isolate_freepages(cc);
>> +			has_isolated_pages = true;
>> +			goto again;
>> +		}
>> +
>>  		if (!cc->freepages[order].nr_pages)
>>  			return NULL;
>>  	}
>> @@ -1819,6 +1856,7 @@ static struct folio *compaction_alloc(struct folio *src, unsigned long data)
>>  	post_alloc_hook(&dst->page, order, __GFP_MOVABLE);
>>  	if (order)
>>  		prep_compound_page(&dst->page, order);
>> +done:
>>  	cc->nr_freepages -= 1 << order;
>>  	return page_rmappable_folio(&dst->page);
>>  }


--
Best Regards,
Yan, Zi

[-- Attachment #2: OpenPGP digital signature --]
[-- Type: application/pgp-signature, Size: 854 bytes --]