On 5/23/19 11:51 PM, Hillf Danton wrote:
On Thu, 23 May 2019 10:27:38 +0800 Yang Shi wrote:
@ -1642,14 +1650,14 @@ static unsigned long isolate_lru_pages(unsigned long
nr_to_scan,
unsigned long nr_zone_taken[MAX_NR_ZONES] = { 0 };
unsigned long nr_skipped[MAX_NR_ZONES] = {
On 5/23/19 8:52 PM, Huang, Ying wrote:
Yang Shi writes:
Since commit bd4c82c22c36 ("mm, THP, swap: delay splitting THP after
swapped out"), THP can be swapped out in a whole. But, nr_reclaimed
and some other vm counters still get inc'ed by one even though a whole
THP (512 pages) gets
Yang Shi writes:
> Since commit bd4c82c22c36 ("mm, THP, swap: delay splitting THP after
> swapped out"), THP can be swapped out in a whole. But, nr_reclaimed
> and some other vm counters still get inc'ed by one even though a whole
> THP (512 pages) gets swapped out.
>
> This doesn't make too
Since commit bd4c82c22c36 ("mm, THP, swap: delay splitting THP after
swapped out"), THP can be swapped out in a whole. But, nr_reclaimed
and some other vm counters still get inc'ed by one even though a whole
THP (512 pages) gets swapped out.
This doesn't make too much sense to memory reclaim.
4 matches
Mail list logo
