summaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
authorVladimir Davydov <vdavydov@virtuozzo.com>2016-03-17 22:18:27 +0100
committerLinus Torvalds <torvalds@linux-foundation.org>2016-03-17 23:09:34 +0100
commitb313aeee25098bf361c808fe45ba2d3af398ec46 (patch)
treef63800bcaf471414988f6c6cfbb577c7c4180861
parentinclude/linux/page-flags.h: force inlining of selected page flag modifications (diff)
downloadlinux-b313aeee25098bf361c808fe45ba2d3af398ec46.tar.xz
linux-b313aeee25098bf361c808fe45ba2d3af398ec46.zip
mm: memcontrol: enable kmem accounting for all cgroups in the legacy hierarchy
Workingset code was recently made memcg aware, but shadow node shrinker is still global. As a result, one small cgroup can consume all memory available for shadow nodes, possibly hurting other cgroups by reclaiming their shadow nodes, even though reclaim distances stored in its shadow nodes have no effect. To avoid this, we need to make shadow node shrinker memcg aware. The actual work is done in patch 6 of the series. Patches 1 and 2 prepare memcg/shrinker infrastructure for the change. Patch 3 is just a collateral cleanup. Patch 4 makes radix_tree_node accounted, which is necessary for making shadow node shrinker memcg aware. Patch 5 reduces shadow nodes overhead in case workload mostly uses anonymous pages. This patch: Currently, in the legacy hierarchy kmem accounting is off for all cgroups by default and must be enabled explicitly by writing something to memory.kmem.limit_in_bytes. Since we don't support reclaim on hitting kmem limit, nor do we have any plans to implement it, this is likely to be -1, just to enable kmem accounting and limit kernel memory consumption by the memory.limit_in_bytes along with user memory. This user API was introduced when the implementation of kmem accounting lacked slab shrinker support and hence was useless in practice. Things have changed since then - slab shrinkers were made memcg aware, the accounting overhead seems to be negligible, and a failure to charge a kmem allocation should not have critical consequences, because we only account those kernel objects that should be safe to fail. That's why kmem accounting is enabled by default for all cgroups in the default hierarchy, which will eventually replace the legacy one. The ability to enable kmem accounting for some cgroups while keeping it disabled for others is getting difficult to maintain. E.g. to make shadow node shrinker memcg aware (see mm/workingset.c), we need to know the relationship between the number of shadow nodes allocated for a cgroup and the size of its lru list. If kmem accounting is enabled for all cgroups there is no problem, but what should we do if kmem accounting is enabled only for half of cgroups? We've no other choice but use global lru stats while scanning root cgroup's shadow nodes, but that would be wrong if kmem accounting was enabled for all cgroups (which is the case if the unified hierarchy is used), in which case we should use lru stats of the root cgroup's lruvec. That being said, let's enable kmem accounting for all memory cgroups by default. If one finds it unstable or too costly, it can always be disabled system-wide by passing cgroup.memory=nokmem to the kernel at boot time. Signed-off-by: Vladimir Davydov <vdavydov@virtuozzo.com> Acked-by: Johannes Weiner <hannes@cmpxchg.org> Cc: Michal Hocko <mhocko@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Diffstat (limited to '')
-rw-r--r--mm/memcontrol.c41
1 files changed, 5 insertions, 36 deletions
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 4b7dda7c2e74..28d1b1e9d4fb 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -2824,6 +2824,9 @@ static int memcg_online_kmem(struct mem_cgroup *memcg)
{
int memcg_id;
+ if (cgroup_memory_nokmem)
+ return 0;
+
BUG_ON(memcg->kmemcg_id >= 0);
BUG_ON(memcg->kmem_state);
@@ -2844,24 +2847,6 @@ static int memcg_online_kmem(struct mem_cgroup *memcg)
return 0;
}
-static int memcg_propagate_kmem(struct mem_cgroup *parent,
- struct mem_cgroup *memcg)
-{
- int ret = 0;
-
- mutex_lock(&memcg_limit_mutex);
- /*
- * If the parent cgroup is not kmem-online now, it cannot be
- * onlined after this point, because it has at least one child
- * already.
- */
- if (memcg_kmem_online(parent) ||
- (cgroup_subsys_on_dfl(memory_cgrp_subsys) && !cgroup_memory_nokmem))
- ret = memcg_online_kmem(memcg);
- mutex_unlock(&memcg_limit_mutex);
- return ret;
-}
-
static void memcg_offline_kmem(struct mem_cgroup *memcg)
{
struct cgroup_subsys_state *css;
@@ -2920,10 +2905,6 @@ static void memcg_free_kmem(struct mem_cgroup *memcg)
}
}
#else
-static int memcg_propagate_kmem(struct mem_cgroup *parent, struct mem_cgroup *memcg)
-{
- return 0;
-}
static int memcg_online_kmem(struct mem_cgroup *memcg)
{
return 0;
@@ -2939,22 +2920,10 @@ static void memcg_free_kmem(struct mem_cgroup *memcg)
static int memcg_update_kmem_limit(struct mem_cgroup *memcg,
unsigned long limit)
{
- int ret = 0;
+ int ret;
mutex_lock(&memcg_limit_mutex);
- /* Top-level cgroup doesn't propagate from root */
- if (!memcg_kmem_online(memcg)) {
- if (cgroup_is_populated(memcg->css.cgroup) ||
- (memcg->use_hierarchy && memcg_has_children(memcg)))
- ret = -EBUSY;
- if (ret)
- goto out;
- ret = memcg_online_kmem(memcg);
- if (ret)
- goto out;
- }
ret = page_counter_limit(&memcg->kmem, limit);
-out:
mutex_unlock(&memcg_limit_mutex);
return ret;
}
@@ -4205,7 +4174,7 @@ mem_cgroup_css_alloc(struct cgroup_subsys_state *parent_css)
return &memcg->css;
}
- error = memcg_propagate_kmem(parent, memcg);
+ error = memcg_online_kmem(memcg);
if (error)
goto fail;