summaryrefslogtreecommitdiffstats
path: root/fs/super.c
diff options
context:
space:
mode:
authorVladimir Davydov <vdavydov@parallels.com>2015-02-12 14:58:47 -0800
committerLinus Torvalds <torvalds@linux-foundation.org>2015-02-12 18:54:08 -0800
commit503c358cf1925853195ee39ec437e51138bbb7df (patch)
tree14aebe291975ec4353f21068990ebfec503ed63f /fs/super.c
parent10c1045f28e86ac90589a188f0be2d7a4347efdf (diff)
downloadlinux-503c358cf1925853195ee39ec437e51138bbb7df.tar.bz2
list_lru: introduce list_lru_shrink_{count,walk}
Kmem accounting of memcg is unusable now, because it lacks slab shrinker support. That means when we hit the limit we will get ENOMEM w/o any chance to recover. What we should do then is to call shrink_slab, which would reclaim old inode/dentry caches from this cgroup. This is what this patch set is intended to do. Basically, it does two things. First, it introduces the notion of per-memcg slab shrinker. A shrinker that wants to reclaim objects per cgroup should mark itself as SHRINKER_MEMCG_AWARE. Then it will be passed the memory cgroup to scan from in shrink_control->memcg. For such shrinkers shrink_slab iterates over the whole cgroup subtree under the target cgroup and calls the shrinker for each kmem-active memory cgroup. Secondly, this patch set makes the list_lru structure per-memcg. It's done transparently to list_lru users - everything they have to do is to tell list_lru_init that they want memcg-aware list_lru. Then the list_lru will automatically distribute objects among per-memcg lists basing on which cgroup the object is accounted to. This way to make FS shrinkers (icache, dcache) memcg-aware we only need to make them use memcg-aware list_lru, and this is what this patch set does. As before, this patch set only enables per-memcg kmem reclaim when the pressure goes from memory.limit, not from memory.kmem.limit. Handling memory.kmem.limit is going to be tricky due to GFP_NOFS allocations, and it is still unclear whether we will have this knob in the unified hierarchy. This patch (of 9): NUMA aware slab shrinkers use the list_lru structure to distribute objects coming from different NUMA nodes to different lists. Whenever such a shrinker needs to count or scan objects from a particular node, it issues commands like this: count = list_lru_count_node(lru, sc->nid); freed = list_lru_walk_node(lru, sc->nid, isolate_func, isolate_arg, &sc->nr_to_scan); where sc is an instance of the shrink_control structure passed to it from vmscan. To simplify this, let's add special list_lru functions to be used by shrinkers, list_lru_shrink_count() and list_lru_shrink_walk(), which consolidate the nid and nr_to_scan arguments in the shrink_control structure. This will also allow us to avoid patching shrinkers that use list_lru when we make shrink_slab() per-memcg - all we will have to do is extend the shrink_control structure to include the target memcg and make list_lru_shrink_{count,walk} handle this appropriately. Signed-off-by: Vladimir Davydov <vdavydov@parallels.com> Suggested-by: Dave Chinner <david@fromorbit.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Michal Hocko <mhocko@suse.cz> Cc: Greg Thelen <gthelen@google.com> Cc: Glauber Costa <glommer@gmail.com> Cc: Alexander Viro <viro@zeniv.linux.org.uk> Cc: Christoph Lameter <cl@linux.com> Cc: Pekka Enberg <penberg@kernel.org> Cc: David Rientjes <rientjes@google.com> Cc: Joonsoo Kim <iamjoonsoo.kim@lge.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 'fs/super.c')
-rw-r--r--fs/super.c24
1 files changed, 11 insertions, 13 deletions
diff --git a/fs/super.c b/fs/super.c
index eae088f6aaae..4554ac257647 100644
--- a/fs/super.c
+++ b/fs/super.c
@@ -77,8 +77,8 @@ static unsigned long super_cache_scan(struct shrinker *shrink,
if (sb->s_op->nr_cached_objects)
fs_objects = sb->s_op->nr_cached_objects(sb, sc->nid);
- inodes = list_lru_count_node(&sb->s_inode_lru, sc->nid);
- dentries = list_lru_count_node(&sb->s_dentry_lru, sc->nid);
+ inodes = list_lru_shrink_count(&sb->s_inode_lru, sc);
+ dentries = list_lru_shrink_count(&sb->s_dentry_lru, sc);
total_objects = dentries + inodes + fs_objects + 1;
if (!total_objects)
total_objects = 1;
@@ -86,20 +86,20 @@ static unsigned long super_cache_scan(struct shrinker *shrink,
/* proportion the scan between the caches */
dentries = mult_frac(sc->nr_to_scan, dentries, total_objects);
inodes = mult_frac(sc->nr_to_scan, inodes, total_objects);
+ fs_objects = mult_frac(sc->nr_to_scan, fs_objects, total_objects);
/*
* prune the dcache first as the icache is pinned by it, then
* prune the icache, followed by the filesystem specific caches
*/
- freed = prune_dcache_sb(sb, dentries, sc->nid);
- freed += prune_icache_sb(sb, inodes, sc->nid);
+ sc->nr_to_scan = dentries;
+ freed = prune_dcache_sb(sb, sc);
+ sc->nr_to_scan = inodes;
+ freed += prune_icache_sb(sb, sc);
- if (fs_objects) {
- fs_objects = mult_frac(sc->nr_to_scan, fs_objects,
- total_objects);
+ if (fs_objects)
freed += sb->s_op->free_cached_objects(sb, fs_objects,
sc->nid);
- }
drop_super(sb);
return freed;
@@ -118,17 +118,15 @@ static unsigned long super_cache_count(struct shrinker *shrink,
* scalability bottleneck. The counts could get updated
* between super_cache_count and super_cache_scan anyway.
* Call to super_cache_count with shrinker_rwsem held
- * ensures the safety of call to list_lru_count_node() and
+ * ensures the safety of call to list_lru_shrink_count() and
* s_op->nr_cached_objects().
*/
if (sb->s_op && sb->s_op->nr_cached_objects)
total_objects = sb->s_op->nr_cached_objects(sb,
sc->nid);
- total_objects += list_lru_count_node(&sb->s_dentry_lru,
- sc->nid);
- total_objects += list_lru_count_node(&sb->s_inode_lru,
- sc->nid);
+ total_objects += list_lru_shrink_count(&sb->s_dentry_lru, sc);
+ total_objects += list_lru_shrink_count(&sb->s_inode_lru, sc);
total_objects = vfs_pressure_ratio(total_objects);
return total_objects;