[2/2] mm, memcg: Throttle allocators based on ancestral memory.high
diff mbox series

Message ID 8cd132f84bd7e16cdb8fde3378cdbf05ba00d387.1584036142.git.chris@chrisdown.name
State Accepted
Commit e26733e0d0ec6798eca93daa300bc3f43616127f
Headers show
Series
  • [1/2] mm, memcg: Fix corruption on 64-bit divisor in memory.high throttling
Related show

Commit Message

Chris Down March 12, 2020, 6:03 p.m. UTC
Prior to this commit, we only directly check the affected cgroup's
memory.high against its usage. However, it's possible that we are being
reclaimed as a result of hitting an ancestor memory.high and should be
penalised based on that, instead.

This patch changes memory.high overage throttling to use the largest
overage in its ancestors when considering how many penalty jiffies to
charge. This makes sure that we penalise poorly behaving cgroups in the
same way regardless of at what level of the hierarchy memory.high was
breached.

Fixes: 0e4b01df8659 ("mm, memcg: throttle allocators when failing reclaim over memory.high")
Reported-by: Johannes Weiner <hannes@cmpxchg.org>
Signed-off-by: Chris Down <chris@chrisdown.name>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Tejun Heo <tj@kernel.org>
Cc: linux-mm@kvack.org
Cc: cgroups@vger.kernel.org
Cc: linux-kernel@vger.kernel.org
Cc: kernel-team@fb.com
Cc: stable@vger.kernel.org # 5.4.x
---
 mm/memcontrol.c | 93 ++++++++++++++++++++++++++++++-------------------
 1 file changed, 58 insertions(+), 35 deletions(-)

Comments

Johannes Weiner March 16, 2020, 4:21 p.m. UTC | #1
On Thu, Mar 12, 2020 at 06:03:04PM +0000, Chris Down wrote:
> Prior to this commit, we only directly check the affected cgroup's
> memory.high against its usage. However, it's possible that we are being
> reclaimed as a result of hitting an ancestor memory.high and should be
> penalised based on that, instead.
> 
> This patch changes memory.high overage throttling to use the largest
> overage in its ancestors when considering how many penalty jiffies to
> charge. This makes sure that we penalise poorly behaving cgroups in the
> same way regardless of at what level of the hierarchy memory.high was
> breached.
> 
> Fixes: 0e4b01df8659 ("mm, memcg: throttle allocators when failing reclaim over memory.high")
> Reported-by: Johannes Weiner <hannes@cmpxchg.org>
> Signed-off-by: Chris Down <chris@chrisdown.name>
> Cc: Andrew Morton <akpm@linux-foundation.org>
> Cc: Tejun Heo <tj@kernel.org>
> Cc: linux-mm@kvack.org
> Cc: cgroups@vger.kernel.org
> Cc: linux-kernel@vger.kernel.org
> Cc: kernel-team@fb.com
> Cc: stable@vger.kernel.org # 5.4.x

Acked-by: Johannes Weiner <hannes@cmpxchg.org>

Patch
diff mbox series

diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index a70206e516fe..46d649241a21 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -2297,28 +2297,41 @@  static void high_work_func(struct work_struct *work)
  #define MEMCG_DELAY_SCALING_SHIFT 14
 
 /*
- * Scheduled by try_charge() to be executed from the userland return path
- * and reclaims memory over the high limit.
+ * 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.
  */
-void mem_cgroup_handle_over_high(void)
+static unsigned long calculate_high_delay(struct mem_cgroup *memcg,
+					  unsigned int nr_pages)
 {
-	unsigned long usage, high, clamped_high;
-	unsigned long pflags;
-	unsigned long penalty_jiffies, overage;
-	unsigned int nr_pages = current->memcg_nr_pages_over_high;
-	struct mem_cgroup *memcg;
+	unsigned long penalty_jiffies;
+	u64 max_overage = 0;
 
-	if (likely(!nr_pages))
-		return;
+	do {
+		unsigned long usage, high;
+		u64 overage;
 
-	memcg = get_mem_cgroup_from_mm(current->mm);
-	reclaim_high(memcg, nr_pages, GFP_KERNEL);
-	current->memcg_nr_pages_over_high = 0;
+		usage = page_counter_read(&memcg->memory);
+		high = READ_ONCE(memcg->high);
+
+		/*
+		 * 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;
+		overage = div64_u64(overage, high);
+
+		if (overage > max_overage)
+			max_overage = overage;
+	} while ((memcg = parent_mem_cgroup(memcg)) &&
+		 !mem_cgroup_is_root(memcg));
+
+	if (!max_overage)
+		return 0;
 
 	/*
-	 * memory.high is breached and reclaim is unable to keep up. Throttle
-	 * allocators proactively to slow down excessive growth.
-	 *
 	 * We use overage compared to memory.high to calculate the number of
 	 * jiffies to sleep (penalty_jiffies). Ideally this value should be
 	 * fairly lenient on small overages, and increasingly harsh when the
@@ -2326,24 +2339,9 @@  void mem_cgroup_handle_over_high(void)
 	 * its crazy behaviour, so we exponentially increase the delay based on
 	 * overage amount.
 	 */
-
-	usage = page_counter_read(&memcg->memory);
-	high = READ_ONCE(memcg->high);
-
-	if (usage <= high)
-		goto out;
-
-	/*
-	 * Prevent division by 0 in overage calculation by acting as if it was a
-	 * threshold of 1 page
-	 */
-	clamped_high = max(high, 1UL);
-
-	overage = div64_u64((u64)(usage - high) << MEMCG_DELAY_PRECISION_SHIFT,
-			  clamped_high);
-
-	penalty_jiffies = ((u64)overage * overage * HZ)
-		>> (MEMCG_DELAY_PRECISION_SHIFT + MEMCG_DELAY_SCALING_SHIFT);
+	penalty_jiffies = max_overage * max_overage * HZ;
+	penalty_jiffies >>= MEMCG_DELAY_PRECISION_SHIFT;
+	penalty_jiffies >>= MEMCG_DELAY_SCALING_SHIFT;
 
 	/*
 	 * Factor in the task's own contribution to the overage, such that four
@@ -2360,7 +2358,32 @@  void mem_cgroup_handle_over_high(void)
 	 * application moving forwards and also permit diagnostics, albeit
 	 * extremely slowly.
 	 */
-	penalty_jiffies = min(penalty_jiffies, MEMCG_MAX_HIGH_DELAY_JIFFIES);
+	return min(penalty_jiffies, MEMCG_MAX_HIGH_DELAY_JIFFIES);
+}
+
+/*
+ * Scheduled by try_charge() to be executed from the userland return path
+ * and reclaims memory over the high limit.
+ */
+void mem_cgroup_handle_over_high(void)
+{
+	unsigned long penalty_jiffies;
+	unsigned long pflags;
+	unsigned int nr_pages = current->memcg_nr_pages_over_high;
+	struct mem_cgroup *memcg;
+
+	if (likely(!nr_pages))
+		return;
+
+	memcg = get_mem_cgroup_from_mm(current->mm);
+	reclaim_high(memcg, nr_pages, GFP_KERNEL);
+	current->memcg_nr_pages_over_high = 0;
+
+	/*
+	 * 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);
 
 	/*
 	 * Don't sleep if the amount of jiffies this memcg owes us is so low