Operations like MADV_FREE, FADV_DONTNEED etc. currently move any affected active pages to the inactive list to accelerate their reclaim (good) but also steer page reclaim toward that LRU type, or away from the other (bad). The reason why this is undesirable is that such operations are not part of the regular page aging cycle, and rather a fluke that doesn't say much about the remaining pages on that list; they might all be in heavy use, and once the chunk of easy victims has been purged, the VM continues to apply elevated pressure on those remaining hot pages. The other LRU, meanwhile, might have easily reclaimable pages, and there was never a need to steer away from it in the first place. As the previous patch outlined, we should focus on recording actually observed cost to steer the balance rather than speculating about the potential value of one LRU list over the other. In that spirit, leave explicitely deactivated pages to the LRU algorithm to pick up, and let rotations decide which list is the easiest to reclaim. [cai@lca.pw: fix set-but-not-used warning] Link: http://lkml.kernel.org/r/20200522133335.GA624@Qians-MacBook-Air.local Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Acked-by: Minchan Kim <minchan@kernel.org> Acked-by: Michal Hocko <mhocko@suse.com> Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com> Cc: Rik van Riel <riel@surriel.com> Cc: Qian Cai <cai@lca.pw> Link: http://lkml.kernel.org/r/20200520232525.798933-10-hannes@cmpxchg.org Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Unified · Split
| @@ -498,7 +498,7 @@ void lru_cache_add_active_or_unevictable(struct page *page, · 497 unmodified lines | |||
| 498 | static void lru_deactivate_file_fn(struct page *page, struct lruvec *lruvec, | 498 | static void lru_deactivate_file_fn(struct page *page, struct lruvec *lruvec, |
| 499 | void *arg) | 499 | void *arg) |
| 500 | { | 500 | { |
| 501 | int lru, file; | 501 | int lru; |
| 502 | bool active; | 502 | bool active; |
| 503 | 503 | ||
| 504 | if (!PageLRU(page)) | 504 | if (!PageLRU(page)) |
| @@ -512,7 +512,6 @@ static void lru_deactivate_file_fn(struct page *page, struct lruvec *lruvec, · 7 unmodified lines | |||
| 512 | return; | 512 | return; |
| 513 | 513 | ||
| 514 | active = PageActive(page); | 514 | active = PageActive(page); |
| 515 | file = page_is_file_lru(page); | ||
| 516 | lru = page_lru_base_type(page); | 515 | lru = page_lru_base_type(page); |
| 517 | 516 | ||
| 518 | del_page_from_lru_list(page, lruvec, lru + active); | 517 | del_page_from_lru_list(page, lruvec, lru + active); |
| @@ -538,14 +537,12 @@ static void lru_deactivate_file_fn(struct page *page, struct lruvec *lruvec, · 19 unmodified lines | |||
| 538 | 537 | ||
| 539 | if (active) | 538 | if (active) |
| 540 | __count_vm_event(PGDEACTIVATE); | 539 | __count_vm_event(PGDEACTIVATE); |
| 541 | lru_note_cost(lruvec, !file, hpage_nr_pages(page)); | ||
| 542 | } | 540 | } |
| 543 | 541 | ||
| 544 | static void lru_deactivate_fn(struct page *page, struct lruvec *lruvec, | 542 | static void lru_deactivate_fn(struct page *page, struct lruvec *lruvec, |
| 545 | void *arg) | 543 | void *arg) |
| 546 | { | 544 | { |
| 547 | if (PageLRU(page) && PageActive(page) && !PageUnevictable(page)) { | 545 | if (PageLRU(page) && PageActive(page) && !PageUnevictable(page)) { |
| 548 | int file = page_is_file_lru(page); | ||
| 549 | int lru = page_lru_base_type(page); | 546 | int lru = page_lru_base_type(page); |
| 550 | 547 | ||
| 551 | del_page_from_lru_list(page, lruvec, lru + LRU_ACTIVE); | 548 | del_page_from_lru_list(page, lruvec, lru + LRU_ACTIVE); |
| @@ -554,7 +551,6 @@ static void lru_deactivate_fn(struct page *page, struct lruvec *lruvec, · 2 unmodified lines | |||
| 554 | add_page_to_lru_list(page, lruvec, lru); | 551 | add_page_to_lru_list(page, lruvec, lru); |
| 555 | 552 | ||
| 556 | __count_vm_events(PGDEACTIVATE, hpage_nr_pages(page)); | 553 | __count_vm_events(PGDEACTIVATE, hpage_nr_pages(page)); |
| 557 | lru_note_cost(lruvec, !file, hpage_nr_pages(page)); | ||
| 558 | } | 554 | } |
| 559 | } | 555 | } |
| 560 | 556 | ||
| @@ -579,7 +575,6 @@ static void lru_lazyfree_fn(struct page *page, struct lruvec *lruvec, · 18 unmodified lines | |||
| 579 | 575 | ||
| 580 | __count_vm_events(PGLAZYFREE, hpage_nr_pages(page)); | 576 | __count_vm_events(PGLAZYFREE, hpage_nr_pages(page)); |
| 581 | count_memcg_page_event(page, PGLAZYFREE); | 577 | count_memcg_page_event(page, PGLAZYFREE); |
| 582 | lru_note_cost(lruvec, 0, hpage_nr_pages(page)); | ||
| 583 | } | 578 | } |
| 584 | } | 579 | } |
| 585 | 580 | ||