mm/memcg: prepare for swap over-high accounting and penalty calculation

Patch series "memcg: Slow down swap allocation as the available space
gets depleted", v6.

Tejun describes the problem as follows:

When swap runs out, there's an abrupt change in system behavior - the
anonymous memory suddenly becomes unmanageable which readily breaks any
sort of memory isolation and can bring down the whole system.  To avoid
that, oomd [1] monitors free swap space and triggers kills when it drops
below the specific threshold (e.g.  15%).

While this works, it's far from ideal:

 - Depending on IO performance and total swap size, a given
   headroom might not be enough or too much.

 - oomd has to monitor swap depletion in addition to the usual
   pressure metrics and it currently doesn't consider memory.swap.max.

Solve this by adapting parts of the approach that memory.high uses -
slow down allocation as the resource gets depleted turning the depletion
behavior from abrupt cliff one to gradual degradation observable through
memory pressure metric.

[1] https://github.com/facebookincubator/oomd

This patch (of 4):

Slice the memory overage calculation logic a little bit so we can reuse
it to apply a similar penalty to the swap.  The logic which accesses the
memory-specific fields (use and high values) has to be taken out of
calculate_high_delay().

Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Shakeel Butt <shakeelb@google.com>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Cc: Hugh Dickins <hughd@google.com>
Cc: Chris Down <chris@chrisdown.name>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Tejun Heo <tj@kernel.org>
Link: http://lkml.kernel.org/r/20200527195846.102707-1-kuba@kernel.org
Link: http://lkml.kernel.org/r/20200527195846.102707-2-kuba@kernel.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index d5bbd920398e3fdf774cf2a3562286933b0411a3..b0ac90dc3bb027b543cec288ed505a471354ad99 100644 (file)
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -2321,41 +2321,48 @@ static void high_work_func(struct work_struct *work)
  #define MEMCG_DELAY_PRECISION_SHIFT 20
  #define MEMCG_DELAY_SCALING_SHIFT 14
 
-/*
- * Get the number of jiffies that we should penalise a mischievous cgroup which
- * is exceeding its memory.high by checking both it and its ancestors.
- */
-static unsigned long calculate_high_delay(struct mem_cgroup *memcg,
-                                         unsigned int nr_pages)
+static u64 calculate_overage(unsigned long usage, unsigned long high)
 {
-       unsigned long penalty_jiffies;
-       u64 max_overage = 0;
-
-       do {
-               unsigned long usage, high;
-               u64 overage;
+       u64 overage;
 
-               usage = page_counter_read(&memcg->memory);
-               high = READ_ONCE(memcg->high);
+       if (usage <= high)
+               return 0;
 
-               if (usage <= high)
-                       continue;
+       /*
+        * Prevent division by 0 in overage calculation by acting as if
+        * it was a threshold of 1 page
+        */
+       high = max(high, 1UL);
 
-               /*
-                * Prevent division by 0 in overage calculation by acting as if
-                * it was a threshold of 1 page
-                */
-               high = max(high, 1UL);
+       overage = usage - high;
+       overage <<= MEMCG_DELAY_PRECISION_SHIFT;
+       return div64_u64(overage, high);
+}
 
-               overage = usage - high;
-               overage <<= MEMCG_DELAY_PRECISION_SHIFT;
-               overage = div64_u64(overage, high);
+static u64 mem_find_max_overage(struct mem_cgroup *memcg)
+{
+       u64 overage, max_overage = 0;
 
-               if (overage > max_overage)
-                       max_overage = overage;
+       do {
+               overage = calculate_overage(page_counter_read(&memcg->memory),
+                                           READ_ONCE(memcg->high));
+               max_overage = max(overage, max_overage);
        } while ((memcg = parent_mem_cgroup(memcg)) &&
                 !mem_cgroup_is_root(memcg));
 
+       return max_overage;
+}
+
+/*
+ * Get the number of jiffies that we should penalise a mischievous cgroup which
+ * is exceeding its memory.high by checking both it and its ancestors.
+ */
+static unsigned long calculate_high_delay(struct mem_cgroup *memcg,
+                                         unsigned int nr_pages,
+                                         u64 max_overage)
+{
+       unsigned long penalty_jiffies;
+
        if (!max_overage)
                return 0;
 
@@ -2411,7 +2418,8 @@ void mem_cgroup_handle_over_high(void)
         * memory.high is breached and reclaim is unable to keep up. Throttle
         * allocators proactively to slow down excessive growth.
         */
-       penalty_jiffies = calculate_high_delay(memcg, nr_pages);
+       penalty_jiffies = calculate_high_delay(memcg, nr_pages,
+                                              mem_find_max_overage(memcg));
 
        /*
         * Don't sleep if the amount of jiffies this memcg owes us is so low