[RFC PATCH 6/8] memcg: Introduce additional memory control slowdown if needed

[Waiman Long]

For fast cpus on slow disks, yielding the cpus repeatedly with
PR_MEMACT_SLOWDOWN may not be able to slow down memory allocation enough
for memory reclaim to catch up. In case a large memory block is mmap'ed
and the pages are faulted in one-by-one, the syscall delays won't be
activated during this process.

To be safe, an additional variable delay of 20-5000 us will be added
to __mem_cgroup_over_high_action() if the excess memory used is more
than 1/256 of the memory limit.

Signed-off-by: Waiman Long <longman@xxxxxxxxxx>
---
 mm/memcontrol.c | 22 ++++++++++++++++------
 1 file changed, 16 insertions(+), 6 deletions(-)

diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 6488f8a10d66..bddf3e659469 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -2643,11 +2643,10 @@ get_rss_counter(struct mm_struct *mm, int mm_bit, u16 flags, int rss_bit)
 static bool __mem_cgroup_over_high_action(struct mem_cgroup *memcg, u8 action,
 					  u16 flags)
 {
-	unsigned long mem = 0;
+	unsigned long mem = 0, limit = 0, excess = 0;
 	bool ret = false;
 	struct mm_struct *mm = get_task_mm(current);
 	u8  signal = READ_ONCE(current->memcg_over_high_signal);
-	u32 limit;
 
 	if (!mm)
 		return true;	/* No more check is needed */
@@ -2657,9 +2656,10 @@ static bool __mem_cgroup_over_high_action(struct mem_cgroup *memcg, u8 action,
 
 	if (memcg) {
 		mem = page_counter_read(&memcg->memory);
-		limit = READ_ONCE(current->memcg_over_high_climit);
-		if (mem <= memcg->memory.high + limit)
+		limit = READ_ONCE(current->memcg_over_high_climit) + memcg->memory.high;
+		if (mem <= limit)
 			goto out;
+		excess = mem - limit;
 	}
 
 	/*
@@ -2676,6 +2676,7 @@ static bool __mem_cgroup_over_high_action(struct mem_cgroup *memcg, u8 action,
 		limit = READ_ONCE(current->memcg_over_high_plimit);
 		if (mem <= limit)
 			goto out;
+		excess = mem - limit;
 	}
 
 	ret = true;
@@ -2685,10 +2686,19 @@ static bool __mem_cgroup_over_high_action(struct mem_cgroup *memcg, u8 action,
 		break;
 	case PR_MEMACT_SLOWDOWN:
 		/*
-		 * Slow down by yielding the cpu & adding delay to
-		 * memory allocation syscalls.
+		 * Slow down by yielding the cpu & adding delay to memory
+		 * allocation syscalls.
+		 *
+		 * An additional 20-5000 us of delay is added in case the
+		 * excess memory is more than 1/256 of the limit.
 		 */
 		WRITE_ONCE(current->memcg_over_limit, true);
+		limit >>= 8;
+		if (limit && (excess > limit)) {
+			int delay = min(5000UL, excess/limit * 20UL);
+
+			udelay(delay);
+		}
 		set_tsk_need_resched(current);
 		set_preempt_need_resched();
 		break;
-- 
2.18.1