mm/memcontrol: export memcg.swap watermark via sysfs for v2 memcg

This patch is similar to commit 8e20d4b ("mm/memcontrol: export memcg->watermark via sysfs for v2 memcg"), but exports the swap counter's watermark. We allocate jobs to our compute farm using heuristics determined by memory and swap usage from previous jobs. Tracking the peak swap usage for new jobs is important for determining when jobs are exceeding their expected bounds, or when our baseline metrics are getting outdated. Our toolset was written to use the "memory.memsw.max_usage_in_bytes" file in cgroups v1, and altering it to poll cgroups v2's "memory.swap.current" would give less accurate results as well as add complication to the code. Having this watermark exposed in sysfs is much preferred. Link: https://lkml.kernel.org/r/[email protected] Signed-off-by: Lars R. Damerow <[email protected]> Acked-by: Johannes Weiner <[email protected]> Cc: Jonathan Corbet <[email protected]> Cc: Michal Hocko <[email protected]> Cc: Muchun Song <[email protected]> Cc: Roman Gushchin <[email protected]> Cc: Shakeel Butt <[email protected]> Cc: Tejun Heo <[email protected]> Cc: Zefan Li <[email protected]> Signed-off-by: Andrew Morton <[email protected]>
torvalds · Jun 9, 2023 · e0e0b41 · e0e0b41
1 parent 283ebde
commit e0e0b41
Show file tree

Hide file tree

Showing 2 changed files with 20 additions and 0 deletions.
diff --git a/Documentation/admin-guide/cgroup-v2.rst b/Documentation/admin-guide/cgroup-v2.rst
@@ -1582,6 +1582,13 @@ PAGE_SIZE multiple when read back.
 
 	Healthy workloads are not expected to reach this limit.
 
+  memory.swap.peak
+	A read-only single value file which exists on non-root
+	cgroups.
+
+	The max swap usage recorded for the cgroup and its
+	descendants since the creation of the cgroup.
+
   memory.swap.max
 	A read-write single value file which exists on non-root
 	cgroups.  The default is "max".

diff --git a/mm/memcontrol.c b/mm/memcontrol.c
@@ -7622,6 +7622,14 @@ static u64 swap_current_read(struct cgroup_subsys_state *css,
 	return (u64)page_counter_read(&memcg->swap) * PAGE_SIZE;
 }
 
+static u64 swap_peak_read(struct cgroup_subsys_state *css,
+			  struct cftype *cft)
+{
+	struct mem_cgroup *memcg = mem_cgroup_from_css(css);
+
+	return (u64)memcg->swap.watermark * PAGE_SIZE;
+}
+
 static int swap_high_show(struct seq_file *m, void *v)
 {
 	return seq_puts_memcg_tunable(m,
@@ -7700,6 +7708,11 @@ static struct cftype swap_files[] = {
 		.seq_show = swap_max_show,
 		.write = swap_max_write,
 	},
+	{
+		.name = "swap.peak",
+		.flags = CFTYPE_NOT_ON_ROOT,
+		.read_u64 = swap_peak_read,
+	},
 	{
 		.name = "swap.events",
 		.flags = CFTYPE_NOT_ON_ROOT,