summaryrefslogtreecommitdiffstats
path: root/mm
diff options
context:
space:
mode:
authorRoman Gushchin <guro@fb.com>2018-06-08 02:07:46 +0200
committerLinus Torvalds <torvalds@linux-foundation.org>2018-06-08 02:34:36 +0200
commitbf8d5d52ffe89aac5b46ddb39dd1a4351fae5df4 (patch)
treee0b0457ddf128b0562eb403762b2f2de2292e8b1 /mm
parentmm: move is_pageblock_removable_nolock() to mm/memory_hotplug.c (diff)
downloadlinux-bf8d5d52ffe89aac5b46ddb39dd1a4351fae5df4.tar.xz
linux-bf8d5d52ffe89aac5b46ddb39dd1a4351fae5df4.zip
memcg: introduce memory.min
Memory controller implements the memory.low best-effort memory protection mechanism, which works perfectly in many cases and allows protecting working sets of important workloads from sudden reclaim. But its semantics has a significant limitation: it works only as long as there is a supply of reclaimable memory. This makes it pretty useless against any sort of slow memory leaks or memory usage increases. This is especially true for swapless systems. If swap is enabled, memory soft protection effectively postpones problems, allowing a leaking application to fill all swap area, which makes no sense. The only effective way to guarantee the memory protection in this case is to invoke the OOM killer. It's possible to handle this case in userspace by reacting on MEMCG_LOW events; but there is still a place for a fail-safe in-kernel mechanism to provide stronger guarantees. This patch introduces the memory.min interface for cgroup v2 memory controller. It works very similarly to memory.low (sharing the same hierarchical behavior), except that it's not disabled if there is no more reclaimable memory in the system. If cgroup is not populated, its memory.min is ignored, because otherwise even the OOM killer wouldn't be able to reclaim the protected memory, and the system can stall. [guro@fb.com: s/low/min/ in docs] Link: http://lkml.kernel.org/r/20180510130758.GA9129@castle.DHCP.thefacebook.com Link: http://lkml.kernel.org/r/20180509180734.GA4856@castle.DHCP.thefacebook.com Signed-off-by: Roman Gushchin <guro@fb.com> Reviewed-by: Randy Dunlap <rdunlap@infradead.org> Acked-by: Johannes Weiner <hannes@cmpxchg.org> Cc: Michal Hocko <mhocko@suse.com> Cc: Vladimir Davydov <vdavydov.dev@gmail.com> Cc: Tejun Heo <tj@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Diffstat (limited to 'mm')
-rw-r--r--mm/memcontrol.c118
-rw-r--r--mm/page_counter.c63
-rw-r--r--mm/vmscan.c18
3 files changed, 157 insertions, 42 deletions
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index e6de0d6a3a8d..e3d56927a724 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -4275,6 +4275,7 @@ static void mem_cgroup_css_offline(struct cgroup_subsys_state *css)
}
spin_unlock(&memcg->event_list_lock);
+ page_counter_set_min(&memcg->memory, 0);
page_counter_set_low(&memcg->memory, 0);
memcg_offline_kmem(memcg);
@@ -4329,6 +4330,7 @@ static void mem_cgroup_css_reset(struct cgroup_subsys_state *css)
page_counter_set_max(&memcg->memsw, PAGE_COUNTER_MAX);
page_counter_set_max(&memcg->kmem, PAGE_COUNTER_MAX);
page_counter_set_max(&memcg->tcpmem, PAGE_COUNTER_MAX);
+ page_counter_set_min(&memcg->memory, 0);
page_counter_set_low(&memcg->memory, 0);
memcg->high = PAGE_COUNTER_MAX;
memcg->soft_limit = PAGE_COUNTER_MAX;
@@ -5066,6 +5068,36 @@ static u64 memory_current_read(struct cgroup_subsys_state *css,
return (u64)page_counter_read(&memcg->memory) * PAGE_SIZE;
}
+static int memory_min_show(struct seq_file *m, void *v)
+{
+ struct mem_cgroup *memcg = mem_cgroup_from_css(seq_css(m));
+ unsigned long min = READ_ONCE(memcg->memory.min);
+
+ if (min == PAGE_COUNTER_MAX)
+ seq_puts(m, "max\n");
+ else
+ seq_printf(m, "%llu\n", (u64)min * PAGE_SIZE);
+
+ return 0;
+}
+
+static ssize_t memory_min_write(struct kernfs_open_file *of,
+ char *buf, size_t nbytes, loff_t off)
+{
+ struct mem_cgroup *memcg = mem_cgroup_from_css(of_css(of));
+ unsigned long min;
+ int err;
+
+ buf = strstrip(buf);
+ err = page_counter_memparse(buf, "max", &min);
+ if (err)
+ return err;
+
+ page_counter_set_min(&memcg->memory, min);
+
+ return nbytes;
+}
+
static int memory_low_show(struct seq_file *m, void *v)
{
struct mem_cgroup *memcg = mem_cgroup_from_css(seq_css(m));
@@ -5301,6 +5333,12 @@ static struct cftype memory_files[] = {
.read_u64 = memory_current_read,
},
{
+ .name = "min",
+ .flags = CFTYPE_NOT_ON_ROOT,
+ .seq_show = memory_min_show,
+ .write = memory_min_write,
+ },
+ {
.name = "low",
.flags = CFTYPE_NOT_ON_ROOT,
.seq_show = memory_low_show,
@@ -5349,19 +5387,24 @@ struct cgroup_subsys memory_cgrp_subsys = {
};
/**
- * mem_cgroup_low - check if memory consumption is in the normal range
+ * mem_cgroup_protected - check if memory consumption is in the normal range
* @root: the top ancestor of the sub-tree being checked
* @memcg: the memory cgroup to check
*
* WARNING: This function is not stateless! It can only be used as part
* of a top-down tree iteration, not for isolated queries.
*
- * Returns %true if memory consumption of @memcg is in the normal range.
+ * Returns one of the following:
+ * MEMCG_PROT_NONE: cgroup memory is not protected
+ * MEMCG_PROT_LOW: cgroup memory is protected as long there is
+ * an unprotected supply of reclaimable memory from other cgroups.
+ * MEMCG_PROT_MIN: cgroup memory is protected
*
- * @root is exclusive; it is never low when looked at directly
+ * @root is exclusive; it is never protected when looked at directly
*
- * To provide a proper hierarchical behavior, effective memory.low value
- * is used.
+ * To provide a proper hierarchical behavior, effective memory.min/low values
+ * are used. Below is the description of how effective memory.low is calculated.
+ * Effective memory.min values is calculated in the same way.
*
* Effective memory.low is always equal or less than the original memory.low.
* If there is no memory.low overcommittment (which is always true for
@@ -5406,51 +5449,78 @@ struct cgroup_subsys memory_cgrp_subsys = {
* E/memory.current = 0
*
* These calculations require constant tracking of the actual low usages
- * (see propagate_low_usage()), as well as recursive calculation of
- * effective memory.low values. But as we do call mem_cgroup_low()
+ * (see propagate_protected_usage()), as well as recursive calculation of
+ * effective memory.low values. But as we do call mem_cgroup_protected()
* path for each memory cgroup top-down from the reclaim,
* it's possible to optimize this part, and save calculated elow
* for next usage. This part is intentionally racy, but it's ok,
* as memory.low is a best-effort mechanism.
*/
-bool mem_cgroup_low(struct mem_cgroup *root, struct mem_cgroup *memcg)
+enum mem_cgroup_protection mem_cgroup_protected(struct mem_cgroup *root,
+ struct mem_cgroup *memcg)
{
- unsigned long usage, low_usage, siblings_low_usage;
- unsigned long elow, parent_elow;
struct mem_cgroup *parent;
+ unsigned long emin, parent_emin;
+ unsigned long elow, parent_elow;
+ unsigned long usage;
if (mem_cgroup_disabled())
- return false;
+ return MEMCG_PROT_NONE;
if (!root)
root = root_mem_cgroup;
if (memcg == root)
- return false;
+ return MEMCG_PROT_NONE;
- elow = memcg->memory.low;
usage = page_counter_read(&memcg->memory);
- parent = parent_mem_cgroup(memcg);
+ if (!usage)
+ return MEMCG_PROT_NONE;
+
+ emin = memcg->memory.min;
+ elow = memcg->memory.low;
+ parent = parent_mem_cgroup(memcg);
if (parent == root)
goto exit;
+ parent_emin = READ_ONCE(parent->memory.emin);
+ emin = min(emin, parent_emin);
+ if (emin && parent_emin) {
+ unsigned long min_usage, siblings_min_usage;
+
+ min_usage = min(usage, memcg->memory.min);
+ siblings_min_usage = atomic_long_read(
+ &parent->memory.children_min_usage);
+
+ if (min_usage && siblings_min_usage)
+ emin = min(emin, parent_emin * min_usage /
+ siblings_min_usage);
+ }
+
parent_elow = READ_ONCE(parent->memory.elow);
elow = min(elow, parent_elow);
+ if (elow && parent_elow) {
+ unsigned long low_usage, siblings_low_usage;
- if (!elow || !parent_elow)
- goto exit;
+ low_usage = min(usage, memcg->memory.low);
+ siblings_low_usage = atomic_long_read(
+ &parent->memory.children_low_usage);
- low_usage = min(usage, memcg->memory.low);
- siblings_low_usage = atomic_long_read(
- &parent->memory.children_low_usage);
-
- if (!low_usage || !siblings_low_usage)
- goto exit;
+ if (low_usage && siblings_low_usage)
+ elow = min(elow, parent_elow * low_usage /
+ siblings_low_usage);
+ }
- elow = min(elow, parent_elow * low_usage / siblings_low_usage);
exit:
+ memcg->memory.emin = emin;
memcg->memory.elow = elow;
- return usage && usage <= elow;
+
+ if (usage <= emin)
+ return MEMCG_PROT_MIN;
+ else if (usage <= elow)
+ return MEMCG_PROT_LOW;
+ else
+ return MEMCG_PROT_NONE;
}
/**
diff --git a/mm/page_counter.c b/mm/page_counter.c
index a5ff4cbc355a..de31470655f6 100644
--- a/mm/page_counter.c
+++ b/mm/page_counter.c
@@ -13,26 +13,38 @@
#include <linux/bug.h>
#include <asm/page.h>
-static void propagate_low_usage(struct page_counter *c, unsigned long usage)
+static void propagate_protected_usage(struct page_counter *c,
+ unsigned long usage)
{
- unsigned long low_usage, old;
+ unsigned long protected, old_protected;
long delta;
if (!c->parent)
return;
- if (!c->low && !atomic_long_read(&c->low_usage))
- return;
+ if (c->min || atomic_long_read(&c->min_usage)) {
+ if (usage <= c->min)
+ protected = usage;
+ else
+ protected = 0;
+
+ old_protected = atomic_long_xchg(&c->min_usage, protected);
+ delta = protected - old_protected;
+ if (delta)
+ atomic_long_add(delta, &c->parent->children_min_usage);
+ }
- if (usage <= c->low)
- low_usage = usage;
- else
- low_usage = 0;
+ if (c->low || atomic_long_read(&c->low_usage)) {
+ if (usage <= c->low)
+ protected = usage;
+ else
+ protected = 0;
- old = atomic_long_xchg(&c->low_usage, low_usage);
- delta = low_usage - old;
- if (delta)
- atomic_long_add(delta, &c->parent->children_low_usage);
+ old_protected = atomic_long_xchg(&c->low_usage, protected);
+ delta = protected - old_protected;
+ if (delta)
+ atomic_long_add(delta, &c->parent->children_low_usage);
+ }
}
/**
@@ -45,7 +57,7 @@ void page_counter_cancel(struct page_counter *counter, unsigned long nr_pages)
long new;
new = atomic_long_sub_return(nr_pages, &counter->usage);
- propagate_low_usage(counter, new);
+ propagate_protected_usage(counter, new);
/* More uncharges than charges? */
WARN_ON_ONCE(new < 0);
}
@@ -65,7 +77,7 @@ void page_counter_charge(struct page_counter *counter, unsigned long nr_pages)
long new;
new = atomic_long_add_return(nr_pages, &c->usage);
- propagate_low_usage(counter, new);
+ propagate_protected_usage(counter, new);
/*
* This is indeed racy, but we can live with some
* inaccuracy in the watermark.
@@ -109,7 +121,7 @@ bool page_counter_try_charge(struct page_counter *counter,
new = atomic_long_add_return(nr_pages, &c->usage);
if (new > c->max) {
atomic_long_sub(nr_pages, &c->usage);
- propagate_low_usage(counter, new);
+ propagate_protected_usage(counter, new);
/*
* This is racy, but we can live with some
* inaccuracy in the failcnt.
@@ -118,7 +130,7 @@ bool page_counter_try_charge(struct page_counter *counter,
*fail = c;
goto failed;
}
- propagate_low_usage(counter, new);
+ propagate_protected_usage(counter, new);
/*
* Just like with failcnt, we can live with some
* inaccuracy in the watermark.
@@ -191,6 +203,23 @@ int page_counter_set_max(struct page_counter *counter, unsigned long nr_pages)
}
/**
+ * page_counter_set_min - set the amount of protected memory
+ * @counter: counter
+ * @nr_pages: value to set
+ *
+ * The caller must serialize invocations on the same counter.
+ */
+void page_counter_set_min(struct page_counter *counter, unsigned long nr_pages)
+{
+ struct page_counter *c;
+
+ counter->min = nr_pages;
+
+ for (c = counter; c; c = c->parent)
+ propagate_protected_usage(c, atomic_long_read(&c->usage));
+}
+
+/**
* page_counter_set_low - set the amount of protected memory
* @counter: counter
* @nr_pages: value to set
@@ -204,7 +233,7 @@ void page_counter_set_low(struct page_counter *counter, unsigned long nr_pages)
counter->low = nr_pages;
for (c = counter; c; c = c->parent)
- propagate_low_usage(c, atomic_long_read(&c->usage));
+ propagate_protected_usage(c, atomic_long_read(&c->usage));
}
/**
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 0e67b477ecef..03822f86f288 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -2544,12 +2544,28 @@ static bool shrink_node(pg_data_t *pgdat, struct scan_control *sc)
unsigned long reclaimed;
unsigned long scanned;
- if (mem_cgroup_low(root, memcg)) {
+ switch (mem_cgroup_protected(root, memcg)) {
+ case MEMCG_PROT_MIN:
+ /*
+ * Hard protection.
+ * If there is no reclaimable memory, OOM.
+ */
+ continue;
+ case MEMCG_PROT_LOW:
+ /*
+ * Soft protection.
+ * Respect the protection only as long as
+ * there is an unprotected supply
+ * of reclaimable memory from other cgroups.
+ */
if (!sc->memcg_low_reclaim) {
sc->memcg_low_skipped = 1;
continue;
}
memcg_memory_event(memcg, MEMCG_LOW);
+ break;
+ case MEMCG_PROT_NONE:
+ break;
}
reclaimed = sc->nr_reclaimed;