Hi Ying, On Sun, Nov 26, 2023 at 6:36 PM Huang, Ying <ying.huang@xxxxxxxxx> wrote: > > Michal Hocko <mhocko@xxxxxxxx> writes: > > > On Thu 23-11-23 14:15:59, Huang, Ying wrote: > >> Michal Hocko <mhocko@xxxxxxxx> writes: > > [...] > >> > Yes swapcache pages are indeed more complicated but most of the time > >> > they just go away as well, no? > >> > >> When we swapin a page, we will put it in swapcache too. And the page > >> can be in that state for long time if there is more than 50% free space > >> in the swap device. > > > > True, but why is that a problem? If you encounter such a swapped in page > > on the file LRU then the page should be referened and as such should be > > activated, no? > > This just means that anonymous pages in file LRU aren't temporary or > short-term. So we need to consider that. For example, the original > method to balance between anonymous pages and file pages need to be > re-designed. The anonymous pages are considered hotter than file pages > in general. I agree with Ying that anonymous pages typically have different page access patterns than file pages, so we might want to treat them differently to reclaim them effectively. One random idea: How about we put the anonymous page in a swap cache in a different LRU than the rest of the anonymous pages. Then shrinking against those pages in the swap cache would be more effective.Instead of having [anon, file] LRU, now we have [anon not in swap cache, anon in swap cache, file] LRU Chris
