diff options
authorJohannes Weiner <>2020-06-03 16:03:09 -0700
committerLinus Torvalds <>2020-06-03 20:09:49 -0700
commit96f8bf4fb1dd2656ae3e92326be9ebf003bbfd45 (patch)
parent7cf111bc39f6792abedcdfbc4e6291a5603b0ef0 (diff)
mm: vmscan: reclaim writepage is IO cost
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: Signed-off-by: Linus Torvalds <>
6 files changed, 19 insertions, 9 deletions
diff --git a/include/linux/swap.h b/include/linux/swap.h
index 0b71bf75fb67..4c5974bb9ba9 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -334,7 +334,9 @@ extern unsigned long nr_free_pagecache_pages(void);
/* 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 10cc932e209a..3d12c34cd42a 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[2];
unsigned nr_ref_keep;
unsigned nr_unmap_fail;
diff --git a/mm/swap.c b/mm/swap.c
index 4dff2123f695..343675d629ae 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -278,18 +278,16 @@ 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_lru(page))
- lruvec->file_cost++;
+ if (file)
+ lruvec->file_cost += nr_pages;
- lruvec->anon_cost++;
+ lruvec->anon_cost += nr_pages;
* Decay previous events
@@ -311,6 +309,12 @@ 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_lru(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 1cd0b345ff7e..9d20b00627af 100644
--- a/mm/swap_state.c
+++ b/mm/swap_state.c
@@ -442,7 +442,7 @@ 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 */
- lru_note_cost(page);
+ lru_note_cost_page(page);
/* Caller will initiate read into locked page */
diff --git a/mm/vmscan.c b/mm/vmscan.c
index d08640f0235c..14ffe9ccf7ef 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -1359,6 +1359,8 @@ static unsigned int shrink_page_list(struct list_head *page_list,
goto activate_locked;
+ stat->nr_pageout += hpage_nr_pages(page);
if (PageWriteback(page))
goto keep;
if (PageDirty(page))
@@ -1964,6 +1966,7 @@ shrink_inactive_list(unsigned long nr_to_scan, struct lruvec *lruvec,
move_pages_to_lru(lruvec, &page_list);
__mod_node_page_state(pgdat, NR_ISOLATED_ANON + file, -nr_taken);
+ lru_note_cost(lruvec, file, stat.nr_pageout);
item = current_is_kswapd() ? PGSTEAL_KSWAPD : PGSTEAL_DIRECT;
if (!cgroup_reclaim(sc))
__count_vm_events(item, nr_reclaimed);
diff --git a/mm/workingset.c b/mm/workingset.c
index a6a2a740ed0b..d481ea452eeb 100644
--- a/mm/workingset.c
+++ b/mm/workingset.c
@@ -367,7 +367,7 @@ void workingset_refault(struct page *page, void *shadow)
/* XXX: Move to lru_cache_add() when it supports new vs putback */
- lru_note_cost(page);
+ lru_note_cost_page(page);
inc_lruvec_state(lruvec, WORKINGSET_RESTORE);