diff --git a/Documentation/cgroups/memory.txt b/Documentation/cgroups/memory.txt index 4937e6fff9b4..b3429aec444c 100644 --- a/Documentation/cgroups/memory.txt +++ b/Documentation/cgroups/memory.txt @@ -540,14 +540,13 @@ Note: 5.3 swappiness -Similar to /proc/sys/vm/swappiness, but only affecting reclaim that is -triggered by this cgroup's hard limit. The tunable in the root cgroup -corresponds to the global swappiness setting. +Overrides /proc/sys/vm/swappiness for the particular group. The tunable +in the root cgroup corresponds to the global swappiness setting. -Please note that unlike the global swappiness, memcg knob set to 0 -really prevents from any swapping even if there is a swap storage -available. This might lead to memcg OOM killer if there are no file -pages to reclaim. +Please note that unlike during the global reclaim, limit reclaim +enforces that 0 swappiness really prevents from any swapping even if +there is a swap storage available. This might lead to memcg OOM killer +if there are no file pages to reclaim. 5.4 failcnt diff --git a/mm/memcontrol.c b/mm/memcontrol.c index a500cb0594c4..9bf8a84bcaae 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -1550,7 +1550,7 @@ static unsigned long mem_cgroup_margin(struct mem_cgroup *memcg) int mem_cgroup_swappiness(struct mem_cgroup *memcg) { /* root ? */ - if (!css_parent(&memcg->css)) + if (mem_cgroup_disabled() || !css_parent(&memcg->css)) return vm_swappiness; return memcg->swappiness; diff --git a/mm/vmscan.c b/mm/vmscan.c index 05d41c0d7f6c..f44476a41544 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -83,6 +83,9 @@ struct scan_control { /* Scan (total_size >> priority) pages at once */ int priority; + /* anon vs. file LRUs scanning "ratio" */ + int swappiness; + /* * The memory cgroup that hit its limit and as a result is the * primary target of this reclaim invocation. @@ -1845,13 +1848,6 @@ static unsigned long shrink_list(enum lru_list lru, unsigned long nr_to_scan, return shrink_inactive_list(nr_to_scan, lruvec, sc, lru); } -static int vmscan_swappiness(struct scan_control *sc) -{ - if (global_reclaim(sc)) - return vm_swappiness; - return mem_cgroup_swappiness(sc->target_mem_cgroup); -} - enum scan_balance { SCAN_EQUAL, SCAN_FRACT, @@ -1912,7 +1908,7 @@ static void get_scan_count(struct lruvec *lruvec, struct scan_control *sc, * using the memory controller's swap limit feature would be * too expensive. */ - if (!global_reclaim(sc) && !vmscan_swappiness(sc)) { + if (!global_reclaim(sc) && !sc->swappiness) { scan_balance = SCAN_FILE; goto out; } @@ -1922,7 +1918,7 @@ static void get_scan_count(struct lruvec *lruvec, struct scan_control *sc, * system is close to OOM, scan both anon and file equally * (unless the swappiness setting disagrees with swapping). */ - if (!sc->priority && vmscan_swappiness(sc)) { + if (!sc->priority && sc->swappiness) { scan_balance = SCAN_EQUAL; goto out; } @@ -1965,7 +1961,7 @@ static void get_scan_count(struct lruvec *lruvec, struct scan_control *sc, * With swappiness at 100, anonymous and file have the same priority. * This scanning priority is essentially the inverse of IO cost. */ - anon_prio = vmscan_swappiness(sc); + anon_prio = sc->swappiness; file_prio = 200 - anon_prio; /* @@ -2265,6 +2261,7 @@ static void shrink_zone(struct zone *zone, struct scan_control *sc) lruvec = mem_cgroup_zone_lruvec(zone, memcg); + sc->swappiness = mem_cgroup_swappiness(memcg); shrink_lruvec(lruvec, sc); /* @@ -2731,6 +2728,7 @@ unsigned long mem_cgroup_shrink_node_zone(struct mem_cgroup *memcg, .may_swap = !noswap, .order = 0, .priority = 0, + .swappiness = mem_cgroup_swappiness(memcg), .target_mem_cgroup = memcg, }; struct lruvec *lruvec = mem_cgroup_zone_lruvec(zone, memcg);