[patch] mm: vmscan: treat memcg low limit as hard guarantee

[Johannes Weiner]

Don't hide low limit configuration problems behind weak semantics and
quietly breach the set-up guarantees.

Make it simple: memcg guarantees are equivalent to mlocked memory,
anonymous memory without swap, kernel memory, pinned memory etc. -
unreclaimable.  If no memory can be reclaimed without otherwise
breaching guarantees, it's a real problem, so let the machine OOM and
dump the memory state in that situation.

Signed-off-by: Johannes Weiner <hannes@xxxxxxxxxxx>
---
 include/linux/memcontrol.h |  5 -----
 mm/memcontrol.c            | 15 ---------------
 mm/vmscan.c                | 41 +++++------------------------------------
 3 files changed, 5 insertions(+), 56 deletions(-)

diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index a5cf853129ec..c3a53cbb88eb 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -94,7 +94,6 @@ bool task_in_mem_cgroup(struct task_struct *task,
 
 extern bool mem_cgroup_within_guarantee(struct mem_cgroup *memcg,
 		struct mem_cgroup *root);
-extern bool mem_cgroup_all_within_guarantee(struct mem_cgroup *root);
 
 extern struct mem_cgroup *try_get_mem_cgroup_from_page(struct page *page);
 extern struct mem_cgroup *mem_cgroup_from_task(struct task_struct *p);
@@ -297,10 +296,6 @@ static inline bool mem_cgroup_within_guarantee(struct mem_cgroup *memcg,
 {
 	return false;
 }
-static inline bool mem_cgroup_all_within_guarantee(struct mem_cgroup *root)
-{
-	return false;
-}
 
 static inline struct mem_cgroup *try_get_mem_cgroup_from_page(struct page *page)
 {
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 4df733e13727..85fdef53fcf1 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -2788,7 +2788,6 @@ static struct mem_cgroup *mem_cgroup_lookup(unsigned short id)
  *
  * The given group is within its reclaim gurantee if it is below its low limit
  * or the same applies for any parent up the hierarchy until root (including).
- * Such a group might be excluded from the reclaim.
  */
 bool mem_cgroup_within_guarantee(struct mem_cgroup *memcg,
 		struct mem_cgroup *root)
@@ -2801,25 +2800,11 @@ bool mem_cgroup_within_guarantee(struct mem_cgroup *memcg,
 			return true;
 		if (memcg == root)
 			break;
-
 	} while ((memcg = parent_mem_cgroup(memcg)));
 
 	return false;
 }
 
-bool mem_cgroup_all_within_guarantee(struct mem_cgroup *root)
-{
-	struct mem_cgroup *iter;
-
-	for_each_mem_cgroup_tree(iter, root)
-		if (!mem_cgroup_within_guarantee(iter, root)) {
-			mem_cgroup_iter_break(root, iter);
-			return false;
-		}
-
-	return true;
-}
-
 struct mem_cgroup *try_get_mem_cgroup_from_page(struct page *page)
 {
 	struct mem_cgroup *memcg = NULL;
diff --git a/mm/vmscan.c b/mm/vmscan.c
index a8ffe4e616fe..c72493e8fb53 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -2244,20 +2244,14 @@ static inline bool should_continue_reclaim(struct zone *zone,
 }
 
 /**
- * __shrink_zone - shrinks a given zone
+ * shrink_zone - shrinks a given zone
  *
  * @zone: zone to shrink
  * @sc: scan control with additional reclaim parameters
- * @honor_memcg_guarantee: do not reclaim memcgs which are within their memory
- * guarantee
- *
- * Returns the number of reclaimed memcgs.
  */
-static unsigned __shrink_zone(struct zone *zone, struct scan_control *sc,
-		bool honor_memcg_guarantee)
+static void shrink_zone(struct zone *zone, struct scan_control *sc)
 {
 	unsigned long nr_reclaimed, nr_scanned;
-	unsigned nr_scanned_groups = 0;
 
 	do {
 		struct mem_cgroup *root = sc->target_mem_cgroup;
@@ -2274,20 +2268,16 @@ static unsigned __shrink_zone(struct zone *zone, struct scan_control *sc,
 		do {
 			struct lruvec *lruvec;
 
-			/* Memcg might be protected from the reclaim */
-			if (honor_memcg_guarantee &&
-					mem_cgroup_within_guarantee(memcg, root)) {
+			/* Don't reclaim guaranteed memory */
+			if (mem_cgroup_within_guarantee(memcg, root)) {
 				/*
-				 * It would be more optimal to skip the memcg
-				 * subtree now but we do not have a memcg iter
-				 * helper for that. Anyone?
+				 * XXX: skip the entire subtree here
 				 */
 				memcg = mem_cgroup_iter(root, memcg, &reclaim);
 				continue;
 			}
 
 			lruvec = mem_cgroup_zone_lruvec(zone, memcg);
-			nr_scanned_groups++;
 
 			sc->swappiness = mem_cgroup_swappiness(memcg);
 			shrink_lruvec(lruvec, sc);
@@ -2316,27 +2306,6 @@ static unsigned __shrink_zone(struct zone *zone, struct scan_control *sc,
 
 	} while (should_continue_reclaim(zone, sc->nr_reclaimed - nr_reclaimed,
 					 sc->nr_scanned - nr_scanned, sc));
-
-	return nr_scanned_groups;
-}
-
-static void shrink_zone(struct zone *zone, struct scan_control *sc)
-{
-	bool honor_guarantee = true;
-
-	while (!__shrink_zone(zone, sc, honor_guarantee)) {
-		/*
-		 * The previous round of reclaim didn't find anything to scan
-		 * because
-		 * a) the whole reclaimed hierarchy is within guarantee so
-		 *    we fallback to ignore the guarantee because other option
-		 *    would be the OOM
-		 * b) multiple reclaimers are racing and so the first round
-		 *    should be retried
-		 */
-		if (mem_cgroup_all_within_guarantee(sc->target_mem_cgroup))
-			honor_guarantee = false;
-	}
 }
 
 /* Returns true if compaction should go ahead for a high-order request */
-- 
1.9.3

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/