summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorChris Down <chris@chrisdown.name>2019-10-06 17:58:38 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2019-10-07 15:47:20 -0700
commit1bc63fb1272be0773e925f78c0fbd06c89701d55 (patch)
tree0de9348aa1004008b4440c8f7831200e461954e8
parent9de7ca46ad2688bd51e80f7119fefa301ad7f3fa (diff)
mm, memcg: make scan aggression always exclude protection
This patch is an incremental improvement on the existing memory.{low,min} relative reclaim work to base its scan pressure calculations on how much protection is available compared to the current usage, rather than how much the current usage is over some protection threshold. This change doesn't change the experience for the user in the normal case too much. One benefit is that it replaces the (somewhat arbitrary) 100% cutoff with an indefinite slope, which makes it easier to ballpark a memory.low value. As well as this, the old methodology doesn't quite apply generically to machines with varying amounts of physical memory. Let's say we have a top level cgroup, workload.slice, and another top level cgroup, system-management.slice. We want to roughly give 12G to system-management.slice, so on a 32GB machine we set memory.low to 20GB in workload.slice, and on a 64GB machine we set memory.low to 52GB. However, because these are relative amounts to the total machine size, while the amount of memory we want to generally be willing to yield to system.slice is absolute (12G), we end up putting more pressure on system.slice just because we have a larger machine and a larger workload to fill it, which seems fairly unintuitive. With this new behaviour, we don't end up with this unintended side effect. Previously the way that memory.low protection works is that if you are 50% over a certain baseline, you get 50% of your normal scan pressure. This is certainly better than the previous cliff-edge behaviour, but it can be improved even further by always considering memory under the currently enforced protection threshold to be out of bounds. This means that we can set relatively low memory.low thresholds for variable or bursty workloads while still getting a reasonable level of protection, whereas with the previous version we may still trivially hit the 100% clamp. The previous 100% clamp is also somewhat arbitrary, whereas this one is more concretely based on the currently enforced protection threshold, which is likely easier to reason about. There is also a subtle issue with the way that proportional reclaim worked previously -- it promotes having no memory.low, since it makes pressure higher during low reclaim. This happens because we base our scan pressure modulation on how far memory.current is between memory.min and memory.low, but if memory.low is unset, we only use the overage method. In most cromulent configurations, this then means that we end up with *more* pressure than with no memory.low at all when we're in low reclaim, which is not really very usable or expected. With this patch, memory.low and memory.min affect reclaim pressure in a more understandable and composable way. For example, from a user standpoint, "protected" memory now remains untouchable from a reclaim aggression standpoint, and users can also have more confidence that bursty workloads will still receive some amount of guaranteed protection. Link: http://lkml.kernel.org/r/20190322160307.GA3316@chrisdown.name Signed-off-by: Chris Down <chris@chrisdown.name> Reviewed-by: Roman Gushchin <guro@fb.com> Acked-by: Johannes Weiner <hannes@cmpxchg.org> Acked-by: Michal Hocko <mhocko@kernel.org> Cc: Tejun Heo <tj@kernel.org> Cc: Dennis Zhou <dennis@kernel.org> Cc: Vladimir Davydov <vdavydov.dev@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
-rw-r--r--include/linux/memcontrol.h25
-rw-r--r--mm/vmscan.c61
2 files changed, 32 insertions, 54 deletions
diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 1cbad1248e5a..ae703ea3ef48 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -356,17 +356,17 @@ static inline bool mem_cgroup_disabled(void)
return !cgroup_subsys_enabled(memory_cgrp_subsys);
}
-static inline void mem_cgroup_protection(struct mem_cgroup *memcg,
- unsigned long *min, unsigned long *low)
+static inline unsigned long mem_cgroup_protection(struct mem_cgroup *memcg,
+ bool in_low_reclaim)
{
- if (mem_cgroup_disabled()) {
- *min = 0;
- *low = 0;
- return;
- }
+ if (mem_cgroup_disabled())
+ return 0;
+
+ if (in_low_reclaim)
+ return READ_ONCE(memcg->memory.emin);
- *min = READ_ONCE(memcg->memory.emin);
- *low = READ_ONCE(memcg->memory.elow);
+ return max(READ_ONCE(memcg->memory.emin),
+ READ_ONCE(memcg->memory.elow));
}
enum mem_cgroup_protection mem_cgroup_protected(struct mem_cgroup *root,
@@ -844,11 +844,10 @@ static inline void memcg_memory_event_mm(struct mm_struct *mm,
{
}
-static inline void mem_cgroup_protection(struct mem_cgroup *memcg,
- unsigned long *min, unsigned long *low)
+static inline unsigned long mem_cgroup_protection(struct mem_cgroup *memcg,
+ bool in_low_reclaim)
{
- *min = 0;
- *low = 0;
+ return 0;
}
static inline enum mem_cgroup_protection mem_cgroup_protected(
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 70347d626fb3..c6659bb758a4 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -2461,12 +2461,13 @@ out:
int file = is_file_lru(lru);
unsigned long lruvec_size;
unsigned long scan;
- unsigned long min, low;
+ unsigned long protection;
lruvec_size = lruvec_lru_size(lruvec, lru, sc->reclaim_idx);
- mem_cgroup_protection(memcg, &min, &low);
+ protection = mem_cgroup_protection(memcg,
+ sc->memcg_low_reclaim);
- if (min || low) {
+ if (protection) {
/*
* Scale a cgroup's reclaim pressure by proportioning
* its current usage to its memory.low or memory.min
@@ -2479,13 +2480,10 @@ out:
* setting extremely liberal protection thresholds. It
* also means we simply get no protection at all if we
* set it too low, which is not ideal.
- */
- unsigned long cgroup_size = mem_cgroup_size(memcg);
-
- /*
- * If there is any protection in place, we adjust scan
- * pressure in proportion to how much a group's current
- * usage exceeds that, in percent.
+ *
+ * If there is any protection in place, we reduce scan
+ * pressure by how much of the total memory used is
+ * within protection thresholds.
*
* There is one special case: in the first reclaim pass,
* we skip over all groups that are within their low
@@ -2495,43 +2493,24 @@ out:
* ideally want to honor how well-behaved groups are in
* that case instead of simply punishing them all
* equally. As such, we reclaim them based on how much
- * of their best-effort protection they are using. Usage
- * below memory.min is excluded from consideration when
- * calculating utilisation, as it isn't ever
- * reclaimable, so it might as well not exist for our
- * purposes.
+ * memory they are using, reducing the scan pressure
+ * again by how much of the total memory used is under
+ * hard protection.
*/
- if (sc->memcg_low_reclaim && low > min) {
- /*
- * Reclaim according to utilisation between min
- * and low
- */
- scan = lruvec_size * (cgroup_size - min) /
- (low - min);
- } else {
- /* Reclaim according to protection overage */
- scan = lruvec_size * cgroup_size /
- max(min, low) - lruvec_size;
- }
+ unsigned long cgroup_size = mem_cgroup_size(memcg);
+
+ /* Avoid TOCTOU with earlier protection check */
+ cgroup_size = max(cgroup_size, protection);
+
+ scan = lruvec_size - lruvec_size * protection /
+ cgroup_size;
/*
- * Don't allow the scan target to exceed the lruvec
- * size, which otherwise could happen if we have >200%
- * overage in the normal case, or >100% overage when
- * sc->memcg_low_reclaim is set.
- *
- * This is important because other cgroups without
- * memory.low have their scan target initially set to
- * their lruvec size, so allowing values >100% of the
- * lruvec size here could result in penalising cgroups
- * with memory.low set even *more* than their peers in
- * some cases in the case of large overages.
- *
- * Also, minimally target SWAP_CLUSTER_MAX pages to keep
+ * Minimally target SWAP_CLUSTER_MAX pages to keep
* reclaim moving forwards, avoiding decremeting
* sc->priority further than desirable.
*/
- scan = clamp(scan, SWAP_CLUSTER_MAX, lruvec_size);
+ scan = max(scan, SWAP_CLUSTER_MAX);
} else {
scan = lruvec_size;
}