memcg: move memcg reclaimable page into tail of inactive list

The rotate_reclaimable_page function moves just written out pages, which
the VM wanted to reclaim, to the end of the inactive list.  That way the
VM will find those pages first next time it needs to free memory.

This patch applies the rule in memcg.  It can help to prevent unnecessary
working page eviction of memcg.

Signed-off-by: Minchan Kim <minchan.kim@gmail.com>
Acked-by: Balbir Singh <balbir@linux.vnet.ibm.com>
Acked-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Reviewed-by: Rik van Riel <riel@redhat.com>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index a1a1e5384f6e426c143ad6b3374de23e5c30e02a..5bb7be2628cab2743d45c5d1283d0bc4e0f76fbb 100644 (file)
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -62,6 +62,7 @@ extern int mem_cgroup_cache_charge(struct page *page, struct mm_struct *mm,
                                        gfp_t gfp_mask);
 extern void mem_cgroup_add_lru_list(struct page *page, enum lru_list lru);
 extern void mem_cgroup_del_lru_list(struct page *page, enum lru_list lru);
+extern void mem_cgroup_rotate_reclaimable_page(struct page *page);
 extern void mem_cgroup_rotate_lru_list(struct page *page, enum lru_list lru);
 extern void mem_cgroup_del_lru(struct page *page);
 extern void mem_cgroup_move_lists(struct page *page,
@@ -211,6 +212,11 @@ static inline void mem_cgroup_del_lru_list(struct page *page, int lru)
        return ;
 }
 
+static inline inline void mem_cgroup_rotate_reclaimable_page(struct page *page)
+{
+       return ;
+}
+
 static inline void mem_cgroup_rotate_lru_list(struct page *page, int lru)
 {
        return ;

diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 6ef5c53dffcb30a42d76789f7c409f2a35dd5a5a..9e0f05efd114617add605e2dd27d60f0d2376b4c 100644 (file)
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -829,6 +829,32 @@ void mem_cgroup_del_lru(struct page *page)
        mem_cgroup_del_lru_list(page, page_lru(page));
 }
 
+/*
+ * Writeback is about to end against a page which has been marked for immediate
+ * reclaim.  If it still appears to be reclaimable, move it to the tail of the
+ * inactive list.
+ */
+void mem_cgroup_rotate_reclaimable_page(struct page *page)
+{
+       struct mem_cgroup_per_zone *mz;
+       struct page_cgroup *pc;
+       enum lru_list lru = page_lru(page);
+
+       if (mem_cgroup_disabled())
+               return;
+
+       pc = lookup_page_cgroup(page);
+       /* unused or root page is not rotated. */
+       if (!PageCgroupUsed(pc))
+               return;
+       /* Ensure pc->mem_cgroup is visible after reading PCG_USED. */
+       smp_rmb();
+       if (mem_cgroup_is_root(pc->mem_cgroup))
+               return;
+       mz = page_cgroup_zoneinfo(pc);
+       list_move_tail(&pc->lru, &mz->lists[lru]);
+}
+
 void mem_cgroup_rotate_lru_list(struct page *page, enum lru_list lru)
 {
        struct mem_cgroup_per_zone *mz;

diff --git a/mm/swap.c b/mm/swap.c
index 4aea806d0d441c7d58d4bc8be83103ff743e5289..1b9e4ebaffc80f07b94300619682a271bdf5511d 100644 (file)
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -200,8 +200,9 @@ static void pagevec_move_tail(struct pagevec *pvec)
                        spin_lock(&zone->lru_lock);
                }
                if (PageLRU(page) && !PageActive(page) && !PageUnevictable(page)) {
-                       int lru = page_lru_base_type(page);
+                       enum lru_list lru = page_lru_base_type(page);
                        list_move_tail(&page->lru, &zone->lru[lru].list);
+                       mem_cgroup_rotate_reclaimable_page(page);
                        pgmoved++;
                }
        }