summaryrefslogtreecommitdiffstats
path: root/mm/vmscan.c
diff options
context:
space:
mode:
authorJohannes Weiner <hannes@cmpxchg.org>2014-04-03 14:47:51 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2014-04-03 16:21:01 -0700
commita528910e12ec7ee203095eb1711468a66b9b60b0 (patch)
treec9ceed84994f015e991161c91b87d47d93cd6491 /mm/vmscan.c
parent91b0abe36a7b2b3b02d7500925a5f8455334f0e5 (diff)
downloadlinux-a528910e12ec7ee203095eb1711468a66b9b60b0.tar.bz2
mm: thrash detection-based file cache sizing
The VM maintains cached filesystem pages on two types of lists. One list holds the pages recently faulted into the cache, the other list holds pages that have been referenced repeatedly on that first list. The idea is to prefer reclaiming young pages over those that have shown to benefit from caching in the past. We call the recently usedbut ultimately was not significantly better than a FIFO policy and still thrashed cache based on eviction speed, rather than actual demand for cache. This patch solves one half of the problem by decoupling the ability to detect working set changes from the inactive list size. By maintaining a history of recently evicted file pages it can detect frequently used pages with an arbitrarily small inactive list size, and subsequently apply pressure on the active list based on actual demand for cache, not just overall eviction speed. Every zone maintains a counter that tracks inactive list aging speed. When a page is evicted, a snapshot of this counter is stored in the now-empty page cache radix tree slot. On refault, the minimum access distance of the page can be assessed, to evaluate whether the page should be part of the active list or not. This fixes the VM's blindness towards working set changes in excess of the inactive list. And it's the foundation to further improve the protection ability and reduce the minimum inactive list size of 50%. Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Reviewed-by: Rik van Riel <riel@redhat.com> Reviewed-by: Minchan Kim <minchan@kernel.org> Reviewed-by: Bob Liu <bob.liu@oracle.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Christoph Hellwig <hch@infradead.org> Cc: Dave Chinner <david@fromorbit.com> Cc: Greg Thelen <gthelen@google.com> Cc: Hugh Dickins <hughd@google.com> Cc: Jan Kara <jack@suse.cz> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Luigi Semenzato <semenzato@google.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Metin Doslu <metin@citusdata.com> Cc: Michel Lespinasse <walken@google.com> Cc: Ozgun Erdogan <ozgun@citusdata.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Roman Gushchin <klamm@yandex-team.ru> Cc: Ryan Mallon <rmallon@gmail.com> Cc: Tejun Heo <tj@kernel.org> Cc: Vlastimil Babka <vbabka@suse.cz> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Diffstat (limited to 'mm/vmscan.c')
-rw-r--r--mm/vmscan.c24
1 files changed, 19 insertions, 5 deletions
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 2a0bb8fdb259..1f56a80a7c41 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -523,7 +523,8 @@ static pageout_t pageout(struct page *page, struct address_space *mapping,
* Same as remove_mapping, but if the page is removed from the mapping, it
* gets returned with a refcount of 0.
*/
-static int __remove_mapping(struct address_space *mapping, struct page *page)
+static int __remove_mapping(struct address_space *mapping, struct page *page,
+ bool reclaimed)
{
BUG_ON(!PageLocked(page));
BUG_ON(mapping != page_mapping(page));
@@ -569,10 +570,23 @@ static int __remove_mapping(struct address_space *mapping, struct page *page)
swapcache_free(swap, page);
} else {
void (*freepage)(struct page *);
+ void *shadow = NULL;
freepage = mapping->a_ops->freepage;
-
- __delete_from_page_cache(page, NULL);
+ /*
+ * Remember a shadow entry for reclaimed file cache in
+ * order to detect refaults, thus thrashing, later on.
+ *
+ * But don't store shadows in an address space that is
+ * already exiting. This is not just an optizimation,
+ * inode reclaim needs to empty out the radix tree or
+ * the nodes are lost. Don't plant shadows behind its
+ * back.
+ */
+ if (reclaimed && page_is_file_cache(page) &&
+ !mapping_exiting(mapping))
+ shadow = workingset_eviction(mapping, page);
+ __delete_from_page_cache(page, shadow);
spin_unlock_irq(&mapping->tree_lock);
mem_cgroup_uncharge_cache_page(page);
@@ -595,7 +609,7 @@ cannot_free:
*/
int remove_mapping(struct address_space *mapping, struct page *page)
{
- if (__remove_mapping(mapping, page)) {
+ if (__remove_mapping(mapping, page, false)) {
/*
* Unfreezing the refcount with 1 rather than 2 effectively
* drops the pagecache ref for us without requiring another
@@ -1065,7 +1079,7 @@ static unsigned long shrink_page_list(struct list_head *page_list,
}
}
- if (!mapping || !__remove_mapping(mapping, page))
+ if (!mapping || !__remove_mapping(mapping, page, true))
goto keep_locked;
/*