From 6c3b7eb38700ff6bfcc5cc4b18125c57d792b7b4 Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Wed, 3 Jun 2020 16:03:09 -0700 Subject: [PATCH 2372/2944] mm: vmscan: reclaim writepage is IO cost task #31256938 commit 96f8bf4fb1dd2656ae3e92326be9ebf003bbfd45 upstream The VM tries to balance reclaim pressure between anon and file so as to reduce the amount of IO incurred due to the memory shortage. It already counts refaults and swapins, but in addition it should also count writepage calls during reclaim. For swap, this is obvious: it's IO that wouldn't have occurred if the anonymous memory hadn't been under memory pressure. From a relative balancing point of view this makes sense as well: even if anon is cold and reclaimable, a cache that isn't thrashing may have equally cold pages that don't require IO to reclaim. For file writeback, it's trickier: some of the reclaim writepage IO would have likely occurred anyway due to dirty expiration. But not all of it - premature writeback reduces batching and generates additional writes. Since the flushers are already woken up by the time the VM starts writing cache pages one by one, let's assume that we'e likely causing writes that wouldn't have happened without memory pressure. In addition, the per-page cost of IO would have probably been much cheaper if written in larger batches from the flusher thread rather than the single-page-writes from kswapd. For our purposes - getting the trend right to accelerate convergence on a stable state that doesn't require paging at all - this is sufficiently accurate. If we later wanted to optimize for sustained thrashing, we can still refine the measurements. Count all writepage calls from kswapd as IO cost toward the LRU that the page belongs to. Why do this dynamically? Don't we know in advance that anon pages require IO to reclaim, and so could build in a static bias? First, scanning is not the same as reclaiming. If all the anon pages are referenced, we may not swap for a while just because we're scanning the anon list. During this time, however, it's important that we age anonymous memory and the page cache at the same rate so that their hot-cold gradients are comparable. Everything else being equal, we still want to reclaim the coldest memory overall. Second, we keep copies in swap unless the page changes. If there is swap-backed data that's mostly read (tmpfs file) and has been swapped out before, we can reclaim it without incurring additional IO. Signed-off-by: Johannes Weiner Signed-off-by: Andrew Morton Cc: Joonsoo Kim Cc: Michal Hocko Cc: Minchan Kim Cc: Rik van Riel Link: http://lkml.kernel.org/r/20200520232525.798933-14-hannes@cmpxchg.org Signed-off-by: Linus Torvalds Signed-off-by: zhongjiang-ali Reviewed-by: Xunlei Pang --- include/linux/swap.h | 4 +++- include/linux/vmstat.h | 1 + mm/swap.c | 16 ++++++++++------ mm/swap_state.c | 2 +- mm/vmscan.c | 3 +++ mm/workingset.c | 2 +- 6 files changed, 19 insertions(+), 9 deletions(-) diff --git a/include/linux/swap.h b/include/linux/swap.h index 87d1c03..8a8986e 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -332,7 +332,9 @@ struct vma_swap_readahead { /* linux/mm/swap.c */ -extern void lru_note_cost(struct page *); +extern void lru_note_cost(struct lruvec *lruvec, bool file, + unsigned int nr_pages); +extern void lru_note_cost_page(struct page *); extern void lru_cache_add(struct page *); extern void lru_add_page_tail(struct page *page, struct page *page_tail, struct lruvec *lruvec, struct list_head *head); diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h index f25cef8..a014fb7f 100644 --- a/include/linux/vmstat.h +++ b/include/linux/vmstat.h @@ -26,6 +26,7 @@ struct reclaim_stat { unsigned nr_congested; unsigned nr_writeback; unsigned nr_immediate; + unsigned nr_pageout; unsigned nr_activate; unsigned nr_ref_keep; unsigned nr_unmap_fail; diff --git a/mm/swap.c b/mm/swap.c index 4294115..8367dc7 100644 --- a/mm/swap.c +++ b/mm/swap.c @@ -262,18 +262,16 @@ void rotate_reclaimable_page(struct page *page) } } -void lru_note_cost(struct page *page) +void lru_note_cost(struct lruvec *lruvec, bool file, unsigned int nr_pages) { - struct lruvec *lruvec = mem_cgroup_page_lruvec(page, page_pgdat(page)); - do { unsigned long lrusize; /* Record cost event */ - if (page_is_file_cache(page)) - lruvec->file_cost++; + if (file) + lruvec->file_cost += nr_pages; else - lruvec->anon_cost++; + lruvec->anon_cost += nr_pages; /* * Decay previous events @@ -295,6 +293,12 @@ void lru_note_cost(struct page *page) } while ((lruvec = parent_lruvec(lruvec))); } +void lru_note_cost_page(struct page *page) +{ + lru_note_cost(mem_cgroup_page_lruvec(page, page_pgdat(page)), + page_is_file_cache(page), hpage_nr_pages(page)); +} + static void __activate_page(struct page *page, struct lruvec *lruvec, void *arg) { diff --git a/mm/swap_state.c b/mm/swap_state.c index e15a929..6bed727 100644 --- a/mm/swap_state.c +++ b/mm/swap_state.c @@ -472,7 +472,7 @@ struct page *__read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask, /* XXX: Move to lru_cache_add() when it supports new vs putback */ spin_lock_irq(&page_pgdat(page)->lru_lock); - lru_note_cost(page); + lru_note_cost_page(page); spin_unlock_irq(&page_pgdat(page)->lru_lock); /* Caller will initiate read into locked page */ diff --git a/mm/vmscan.c b/mm/vmscan.c index 03048b5..3ed820a 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -1357,6 +1357,8 @@ static unsigned long shrink_page_list(struct list_head *page_list, case PAGE_ACTIVATE: goto activate_locked; case PAGE_SUCCESS: + stat->nr_pageout += hpage_nr_pages(page); + if (PageWriteback(page)) goto keep; if (PageDirty(page)) @@ -1935,6 +1937,7 @@ static int current_may_throttle(void) putback_inactive_pages(lruvec, &page_list); __mod_node_page_state(pgdat, NR_ISOLATED_ANON + file, -nr_taken); + lru_note_cost(lruvec, file, stat.nr_pageout); if (current_is_kswapd()) { if (!cgroup_reclaim(sc)) __count_vm_events(PGSTEAL_KSWAPD, nr_reclaimed); diff --git a/mm/workingset.c b/mm/workingset.c index c0a4e82..961e464 100644 --- a/mm/workingset.c +++ b/mm/workingset.c @@ -368,7 +368,7 @@ void workingset_refault(struct page *page, void *shadow) SetPageWorkingset(page); /* XXX: Move to lru_cache_add() when it supports new vs putback */ spin_lock_irq(&page_pgdat(page)->lru_lock); - lru_note_cost(page); + lru_note_cost_page(page); spin_unlock_irq(&page_pgdat(page)->lru_lock); inc_lruvec_state(lruvec, WORKINGSET_RESTORE); } -- 1.8.3.1