Commit cb731d6c authored by Vladimir Davydov's avatar Vladimir Davydov Committed by Linus Torvalds

vmscan: per memory cgroup slab shrinkers

This patch adds SHRINKER_MEMCG_AWARE flag.  If a shrinker has this flag
set, it will be called per memory cgroup.  The memory cgroup to scan
objects from is passed in shrink_control->memcg.  If the memory cgroup
is NULL, a memcg aware shrinker is supposed to scan objects from the
global list.  Unaware shrinkers are only called on global pressure with
memcg=NULL.
Signed-off-by: default avatarVladimir Davydov <vdavydov@parallels.com>
Cc: 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: default avatarAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: default avatarLinus Torvalds <torvalds@linux-foundation.org>
parent 4101b624
......@@ -37,20 +37,6 @@ static void drop_pagecache_sb(struct super_block *sb, void *unused)
iput(toput_inode);
}
static void drop_slab(void)
{
int nr_objects;
do {
int nid;
nr_objects = 0;
for_each_online_node(nid)
nr_objects += shrink_node_slabs(GFP_KERNEL, nid,
1000, 1000);
} while (nr_objects > 10);
}
int drop_caches_sysctl_handler(struct ctl_table *table, int write,
void __user *buffer, size_t *length, loff_t *ppos)
{
......
......@@ -413,6 +413,8 @@ static inline bool memcg_kmem_enabled(void)
return static_key_false(&memcg_kmem_enabled_key);
}
bool memcg_kmem_is_active(struct mem_cgroup *memcg);
/*
* In general, we'll do everything in our power to not incur in any overhead
* for non-memcg users for the kmem functions. Not even a function call, if we
......@@ -542,6 +544,11 @@ static inline bool memcg_kmem_enabled(void)
return false;
}
static inline bool memcg_kmem_is_active(struct mem_cgroup *memcg)
{
return false;
}
static inline bool
memcg_kmem_newpage_charge(gfp_t gfp, struct mem_cgroup **memcg, int order)
{
......
......@@ -2168,9 +2168,8 @@ int drop_caches_sysctl_handler(struct ctl_table *, int,
void __user *, size_t *, loff_t *);
#endif
unsigned long shrink_node_slabs(gfp_t gfp_mask, int nid,
unsigned long nr_scanned,
unsigned long nr_eligible);
void drop_slab(void);
void drop_slab_node(int nid);
#ifndef CONFIG_MMU
#define randomize_va_space 0
......
......@@ -20,6 +20,9 @@ struct shrink_control {
/* current node being shrunk (for NUMA aware shrinkers) */
int nid;
/* current memcg being shrunk (for memcg aware shrinkers) */
struct mem_cgroup *memcg;
};
#define SHRINK_STOP (~0UL)
......@@ -62,6 +65,7 @@ struct shrinker {
/* Flags */
#define SHRINKER_NUMA_AWARE (1 << 0)
#define SHRINKER_MEMCG_AWARE (1 << 1)
extern int register_shrinker(struct shrinker *);
extern void unregister_shrinker(struct shrinker *);
......
......@@ -352,7 +352,7 @@ struct mem_cgroup {
};
#ifdef CONFIG_MEMCG_KMEM
static bool memcg_kmem_is_active(struct mem_cgroup *memcg)
bool memcg_kmem_is_active(struct mem_cgroup *memcg)
{
return memcg->kmemcg_id >= 0;
}
......
......@@ -242,15 +242,8 @@ void shake_page(struct page *p, int access)
* Only call shrink_node_slabs here (which would also shrink
* other caches) if access is not potentially fatal.
*/
if (access) {
int nr;
int nid = page_to_nid(p);
do {
nr = shrink_node_slabs(GFP_KERNEL, nid, 1000, 1000);
if (page_count(p) == 1)
break;
} while (nr > 10);
}
if (access)
drop_slab_node(page_to_nid(p));
}
EXPORT_SYMBOL_GPL(shake_page);
......
......@@ -232,7 +232,7 @@ EXPORT_SYMBOL(unregister_shrinker);
#define SHRINK_BATCH 128
static unsigned long shrink_slabs(struct shrink_control *shrinkctl,
static unsigned long do_shrink_slab(struct shrink_control *shrinkctl,
struct shrinker *shrinker,
unsigned long nr_scanned,
unsigned long nr_eligible)
......@@ -344,9 +344,10 @@ static unsigned long shrink_slabs(struct shrink_control *shrinkctl,
}
/**
* shrink_node_slabs - shrink slab caches of a given node
* shrink_slab - shrink slab caches
* @gfp_mask: allocation context
* @nid: node whose slab caches to target
* @memcg: memory cgroup whose slab caches to target
* @nr_scanned: pressure numerator
* @nr_eligible: pressure denominator
*
......@@ -355,6 +356,12 @@ static unsigned long shrink_slabs(struct shrink_control *shrinkctl,
* @nid is passed along to shrinkers with SHRINKER_NUMA_AWARE set,
* unaware shrinkers will receive a node id of 0 instead.
*
* @memcg specifies the memory cgroup to target. If it is not NULL,
* only shrinkers with SHRINKER_MEMCG_AWARE set will be called to scan
* objects from the memory cgroup specified. Otherwise all shrinkers
* are called, and memcg aware shrinkers are supposed to scan the
* global list then.
*
* @nr_scanned and @nr_eligible form a ratio that indicate how much of
* the available objects should be scanned. Page reclaim for example
* passes the number of pages scanned and the number of pages on the
......@@ -365,13 +372,17 @@ static unsigned long shrink_slabs(struct shrink_control *shrinkctl,
*
* Returns the number of reclaimed slab objects.
*/
unsigned long shrink_node_slabs(gfp_t gfp_mask, int nid,
static unsigned long shrink_slab(gfp_t gfp_mask, int nid,
struct mem_cgroup *memcg,
unsigned long nr_scanned,
unsigned long nr_eligible)
{
struct shrinker *shrinker;
unsigned long freed = 0;
if (memcg && !memcg_kmem_is_active(memcg))
return 0;
if (nr_scanned == 0)
nr_scanned = SWAP_CLUSTER_MAX;
......@@ -390,12 +401,16 @@ unsigned long shrink_node_slabs(gfp_t gfp_mask, int nid,
struct shrink_control sc = {
.gfp_mask = gfp_mask,
.nid = nid,
.memcg = memcg,
};
if (memcg && !(shrinker->flags & SHRINKER_MEMCG_AWARE))
continue;
if (!(shrinker->flags & SHRINKER_NUMA_AWARE))
sc.nid = 0;
freed += shrink_slabs(&sc, shrinker, nr_scanned, nr_eligible);
freed += do_shrink_slab(&sc, shrinker, nr_scanned, nr_eligible);
}
up_read(&shrinker_rwsem);
......@@ -404,6 +419,29 @@ unsigned long shrink_node_slabs(gfp_t gfp_mask, int nid,
return freed;
}
void drop_slab_node(int nid)
{
unsigned long freed;
do {
struct mem_cgroup *memcg = NULL;
freed = 0;
do {
freed += shrink_slab(GFP_KERNEL, nid, memcg,
1000, 1000);
} while ((memcg = mem_cgroup_iter(NULL, memcg, NULL)) != NULL);
} while (freed > 10);
}
void drop_slab(void)
{
int nid;
for_each_online_node(nid)
drop_slab_node(nid);
}
static inline int is_page_cache_freeable(struct page *page)
{
/*
......@@ -2276,6 +2314,7 @@ static inline bool should_continue_reclaim(struct zone *zone,
static bool shrink_zone(struct zone *zone, struct scan_control *sc,
bool is_classzone)
{
struct reclaim_state *reclaim_state = current->reclaim_state;
unsigned long nr_reclaimed, nr_scanned;
bool reclaimable = false;
......@@ -2294,6 +2333,7 @@ static bool shrink_zone(struct zone *zone, struct scan_control *sc,
memcg = mem_cgroup_iter(root, NULL, &reclaim);
do {
unsigned long lru_pages;
unsigned long scanned;
struct lruvec *lruvec;
int swappiness;
......@@ -2305,10 +2345,16 @@ static bool shrink_zone(struct zone *zone, struct scan_control *sc,
lruvec = mem_cgroup_zone_lruvec(zone, memcg);
swappiness = mem_cgroup_swappiness(memcg);
scanned = sc->nr_scanned;
shrink_lruvec(lruvec, swappiness, sc, &lru_pages);
zone_lru_pages += lru_pages;
if (memcg && is_classzone)
shrink_slab(sc->gfp_mask, zone_to_nid(zone),
memcg, sc->nr_scanned - scanned,
lru_pages);
/*
* Direct reclaim and kswapd have to scan all memory
* cgroups to fulfill the overall scan target for the
......@@ -2330,20 +2376,15 @@ static bool shrink_zone(struct zone *zone, struct scan_control *sc,
* Shrink the slab caches in the same proportion that
* the eligible LRU pages were scanned.
*/
if (global_reclaim(sc) && is_classzone) {
struct reclaim_state *reclaim_state;
shrink_node_slabs(sc->gfp_mask, zone_to_nid(zone),
if (global_reclaim(sc) && is_classzone)
shrink_slab(sc->gfp_mask, zone_to_nid(zone), NULL,
sc->nr_scanned - nr_scanned,
zone_lru_pages);
reclaim_state = current->reclaim_state;
if (reclaim_state) {
sc->nr_reclaimed +=
reclaim_state->reclaimed_slab;
sc->nr_reclaimed += reclaim_state->reclaimed_slab;
reclaim_state->reclaimed_slab = 0;
}
}
vmpressure(sc->gfp_mask, sc->target_mem_cgroup,
sc->nr_scanned - nr_scanned,
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment