mm: vmscan: detect file thrashing at the reclaim root

We use refault information to determine whether the cache workingset is
stable or transitioning, and dynamically adjust the inactive:active file
LRU ratio so as to maximize protection from one-off cache during stable
periods, and minimize IO during transitions.

With cgroups and their nested LRU lists, we currently don't do this
correctly.  While recursive cgroup reclaim establishes a relative LRU
order among the pages of all involved cgroups, refaults only affect the
local LRU order in the cgroup in which they are occuring.  As a result,
cache transitions can take longer in a cgrouped system as the active pages
of sibling cgroups aren't challenged when they should be.

[ Right now, this is somewhat theoretical, because the siblings, under
  continued regular reclaim pressure, should eventually run out of
  inactive pages - and since inactive:active *size* balancing is also
  done on a cgroup-local level, we will challenge the active pages
  eventually in most cases. But the next patch will move that relative
  size enforcement to the reclaim root as well, and then this patch
  here will be necessary to propagate refault pressure to siblings. ]

This patch moves refault detection to the root of reclaim.  Instead of
remembering the cgroup owner of an evicted page, remember the cgroup that
caused the reclaim to happen.  When refaults later occur, they'll
correctly influence the cross-cgroup LRU order that reclaim follows.

I.e.  if global reclaim kicked out pages in some subgroup A/B/C, the
refault of those pages will challenge the global LRU order, and not just
the local order down inside C.

[hannes@cmpxchg.org:  use page_memcg() instead of another lookup]
  Link: http://lkml.kernel.org/r/20191115160722.GA309754@cmpxchg.org
Link: http://lkml.kernel.org/r/20191107205334.158354-3-hannes@cmpxchg.org
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Reviewed-by: Suren Baghdasaryan <surenb@google.com>
Cc: Andrey Ryabinin <aryabinin@virtuozzo.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Rik van Riel <riel@surriel.com>
Cc: Shakeel Butt <shakeelb@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

1 files changed, 15 insertions, 17 deletions

diff --git a/mm/vmscan.c b/mm/vmscan.c
index 725b5d4784f7..39657012e2d8 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -853,7 +853,7 @@ static pageout_t pageout(struct page *page, struct address_space *mapping)
  * gets returned with a refcount of 0.
  */
 static int __remove_mapping(struct address_space *mapping, struct page *page,
-			    bool reclaimed)
+			    bool reclaimed, struct mem_cgroup *target_memcg)
 {
 	unsigned long flags;
 	int refcount;
@@ -925,7 +925,7 @@ static int __remove_mapping(struct address_space *mapping, struct page *page,
 		 */
 		if (reclaimed && page_is_file_cache(page) &&
 		    !mapping_exiting(mapping) && !dax_mapping(mapping))
-			shadow = workingset_eviction(page);
+			shadow = workingset_eviction(page, target_memcg);
 		__delete_from_page_cache(page, shadow);
 		xa_unlock_irqrestore(&mapping->i_pages, flags);
 
@@ -948,7 +948,7 @@ cannot_free:
  */
 int remove_mapping(struct address_space *mapping, struct page *page)
 {
-	if (__remove_mapping(mapping, page, false)) {
+	if (__remove_mapping(mapping, page, false, NULL)) {
 		/*
 		 * Unfreezing the refcount with 1 rather than 2 effectively
 		 * drops the pagecache ref for us without requiring another
@@ -1426,7 +1426,8 @@ static unsigned long shrink_page_list(struct list_head *page_list,
 
 			count_vm_event(PGLAZYFREED);
 			count_memcg_page_event(page, PGLAZYFREED);
-		} else if (!mapping || !__remove_mapping(mapping, page, true))
+		} else if (!mapping || !__remove_mapping(mapping, page, true,
+							 sc->target_mem_cgroup))
 			goto keep_locked;
 
 		unlock_page(page);
@@ -2189,6 +2190,7 @@ static bool inactive_list_is_low(struct lruvec *lruvec, bool file,
 	enum lru_list inactive_lru = file * LRU_FILE;
 	unsigned long inactive, active;
 	unsigned long inactive_ratio;
+	struct lruvec *target_lruvec;
 	unsigned long refaults;
 	unsigned long gb;
 
@@ -2200,8 +2202,9 @@ static bool inactive_list_is_low(struct lruvec *lruvec, bool file,
 	 * is being established. Disable active list protection to get
 	 * rid of the stale workingset quickly.
 	 */
-	refaults = lruvec_page_state_local(lruvec, WORKINGSET_ACTIVATE);
-	if (file && lruvec->refaults != refaults) {
+	target_lruvec = mem_cgroup_lruvec(sc->target_mem_cgroup, pgdat);
+	refaults = lruvec_page_state(target_lruvec, WORKINGSET_ACTIVATE);
+	if (file && target_lruvec->refaults != refaults) {
 		inactive_ratio = 0;
 	} else {
 		gb = (inactive + active) >> (30 - PAGE_SHIFT);
@@ -2973,19 +2976,14 @@ static void shrink_zones(struct zonelist *zonelist, struct scan_control *sc)
 	sc->gfp_mask = orig_mask;
 }
 
-static void snapshot_refaults(struct mem_cgroup *root_memcg, pg_data_t *pgdat)
+static void snapshot_refaults(struct mem_cgroup *target_memcg, pg_data_t *pgdat)
 {
-	struct mem_cgroup *memcg;
-
-	memcg = mem_cgroup_iter(root_memcg, NULL, NULL);
-	do {
-		unsigned long refaults;
-		struct lruvec *lruvec;
+	struct lruvec *target_lruvec;
+	unsigned long refaults;
 
-		lruvec = mem_cgroup_lruvec(memcg, pgdat);
-		refaults = lruvec_page_state_local(lruvec, WORKINGSET_ACTIVATE);
-		lruvec->refaults = refaults;
-	} while ((memcg = mem_cgroup_iter(root_memcg, memcg, NULL)));
+	target_lruvec = mem_cgroup_lruvec(target_memcg, pgdat);
+	refaults = lruvec_page_state(target_lruvec, WORKINGSET_ACTIVATE);
+	target_lruvec->refaults = refaults;
 }
 
 /*