mm: list_lru: allocate list_lru_one only when needed

In our server, we found a suspected memory leak problem.  The kmalloc-32
consumes more than 6GB of memory.  Other kmem_caches consume less than
2GB memory.

After our in-depth analysis, the memory consumption of kmalloc-32 slab
cache is the cause of list_lru_one allocation.

  crash> p memcg_nr_cache_ids
  memcg_nr_cache_ids = $2 = 24574

memcg_nr_cache_ids is very large and memory consumption of each list_lru
can be calculated with the following formula.

  num_numa_node * memcg_nr_cache_ids * 32 (kmalloc-32)

There are 4 numa nodes in our system, so each list_lru consumes ~3MB.

  crash> list super_blocks | wc -l
  952

Every mount will register 2 list lrus, one is for inode, another is for
dentry.  There are 952 super_blocks.  So the total memory is 952 * 2 * 3
MB (~5.6GB).  But the number of memory cgroup is less than 500.  So I
guess more than 12286 containers have been deployed on this machine (I do
not know why there are so many containers, it may be a user's bug or the
user really want to do that).  And memcg_nr_cache_ids has not been reduced
to a suitable value.  This can waste a lot of memory.

Now the infrastructure for dynamic list_lru_one allocation is ready, so
remove statically allocated memory code to save memory.

Link: https://lkml.kernel.org/r/20220228122126.37293-11-songmuchun@bytedance.com
Signed-off-by: Muchun Song <songmuchun@bytedance.com>
Cc: Alex Shi <alexs@kernel.org>
Cc: Anna Schumaker <Anna.Schumaker@Netapp.com>
Cc: Chao Yu <chao@kernel.org>
Cc: Dave Chinner <david@fromorbit.com>
Cc: Fam Zheng <fam.zheng@bytedance.com>
Cc: Jaegeuk Kim <jaegeuk@kernel.org>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Kari Argillander <kari.argillander@gmail.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Qi Zheng <zhengqi.arch@bytedance.com>
Cc: Roman Gushchin <roman.gushchin@linux.dev>
Cc: Shakeel Butt <shakeelb@google.com>
Cc: Theodore Ts'o <tytso@mit.edu>
Cc: Trond Myklebust <trond.myklebust@hammerspace.com>
Cc: Vladimir Davydov <vdavydov.dev@gmail.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Wei Yang <richard.weiyang@gmail.com>
Cc: Xiongchun Duan <duanxiongchun@bytedance.com>
Cc: Yang Shi <shy828301@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
This commit is contained in:
Muchun Song 2022-03-22 14:41:19 -07:00 коммит произвёл Linus Torvalds
Родитель da0efe3094
Коммит 5abc1e37af
3 изменённых файлов: 77 добавлений и 57 удалений

Просмотреть файл

@ -32,14 +32,15 @@ struct list_lru_one {
};
struct list_lru_per_memcg {
struct rcu_head rcu;
/* array of per cgroup per node lists, indexed by node id */
struct list_lru_one node[0];
struct list_lru_one node[];
};
struct list_lru_memcg {
struct rcu_head rcu;
/* array of per cgroup lists, indexed by memcg_cache_id */
struct list_lru_per_memcg *mlru[];
struct list_lru_per_memcg __rcu *mlru[];
};
struct list_lru_node {
@ -77,7 +78,7 @@ int __list_lru_init(struct list_lru *lru, bool memcg_aware,
int memcg_list_lru_alloc(struct mem_cgroup *memcg, struct list_lru *lru,
gfp_t gfp);
int memcg_update_all_list_lrus(int num_memcgs);
void memcg_drain_all_list_lrus(int src_idx, struct mem_cgroup *dst_memcg);
void memcg_drain_all_list_lrus(struct mem_cgroup *src, struct mem_cgroup *dst);
/**
* list_lru_add: add an element to the lru list's tail

Просмотреть файл

@ -60,8 +60,12 @@ list_lru_from_memcg_idx(struct list_lru *lru, int nid, int idx)
* from relocation (see memcg_update_list_lru).
*/
mlrus = rcu_dereference_check(lru->mlrus, lockdep_is_held(&nlru->lock));
if (mlrus && idx >= 0)
return &mlrus->mlru[idx]->node[nid];
if (mlrus && idx >= 0) {
struct list_lru_per_memcg *mlru;
mlru = rcu_dereference_check(mlrus->mlru[idx], true);
return mlru ? &mlru->node[nid] : NULL;
}
return &nlru->lru;
}
@ -188,7 +192,7 @@ unsigned long list_lru_count_one(struct list_lru *lru,
rcu_read_lock();
l = list_lru_from_memcg_idx(lru, nid, memcg_cache_id(memcg));
count = READ_ONCE(l->nr_items);
count = l ? READ_ONCE(l->nr_items) : 0;
rcu_read_unlock();
if (unlikely(count < 0))
@ -217,8 +221,11 @@ __list_lru_walk_one(struct list_lru *lru, int nid, int memcg_idx,
struct list_head *item, *n;
unsigned long isolated = 0;
l = list_lru_from_memcg_idx(lru, nid, memcg_idx);
restart:
l = list_lru_from_memcg_idx(lru, nid, memcg_idx);
if (!l)
goto out;
list_for_each_safe(item, n, &l->list) {
enum lru_status ret;
@ -262,6 +269,7 @@ restart:
BUG();
}
}
out:
return isolated;
}
@ -354,20 +362,25 @@ static struct list_lru_per_memcg *memcg_init_list_lru_one(gfp_t gfp)
return mlru;
}
static int memcg_init_list_lru_range(struct list_lru_memcg *mlrus,
int begin, int end)
static void memcg_list_lru_free(struct list_lru *lru, int src_idx)
{
int i;
struct list_lru_memcg *mlrus;
struct list_lru_per_memcg *mlru;
for (i = begin; i < end; i++) {
mlrus->mlru[i] = memcg_init_list_lru_one(GFP_KERNEL);
if (!mlrus->mlru[i])
goto fail;
}
return 0;
fail:
memcg_destroy_list_lru_range(mlrus, begin, i);
return -ENOMEM;
spin_lock_irq(&lru->lock);
mlrus = rcu_dereference_protected(lru->mlrus, true);
mlru = rcu_dereference_protected(mlrus->mlru[src_idx], true);
rcu_assign_pointer(mlrus->mlru[src_idx], NULL);
spin_unlock_irq(&lru->lock);
/*
* The __list_lru_walk_one() can walk the list of this node.
* We need kvfree_rcu() here. And the walking of the list
* is under lru->node[nid]->lock, which can serve as a RCU
* read-side critical section.
*/
if (mlru)
kvfree_rcu(mlru, rcu);
}
static int memcg_init_list_lru(struct list_lru *lru, bool memcg_aware)
@ -381,14 +394,10 @@ static int memcg_init_list_lru(struct list_lru *lru, bool memcg_aware)
spin_lock_init(&lru->lock);
mlrus = kvmalloc(struct_size(mlrus, mlru, size), GFP_KERNEL);
mlrus = kvzalloc(struct_size(mlrus, mlru, size), GFP_KERNEL);
if (!mlrus)
return -ENOMEM;
if (memcg_init_list_lru_range(mlrus, 0, size)) {
kvfree(mlrus);
return -ENOMEM;
}
RCU_INIT_POINTER(lru->mlrus, mlrus);
return 0;
@ -422,13 +431,9 @@ static int memcg_update_list_lru(struct list_lru *lru, int old_size, int new_siz
if (!new)
return -ENOMEM;
if (memcg_init_list_lru_range(new, old_size, new_size)) {
kvfree(new);
return -ENOMEM;
}
spin_lock_irq(&lru->lock);
memcpy(&new->mlru, &old->mlru, flex_array_size(new, mlru, old_size));
memset(&new->mlru[old_size], 0, flex_array_size(new, mlru, new_size - old_size));
rcu_assign_pointer(lru->mlrus, new);
spin_unlock_irq(&lru->lock);
@ -436,20 +441,6 @@ static int memcg_update_list_lru(struct list_lru *lru, int old_size, int new_siz
return 0;
}
static void memcg_cancel_update_list_lru(struct list_lru *lru,
int old_size, int new_size)
{
struct list_lru_memcg *mlrus;
mlrus = rcu_dereference_protected(lru->mlrus,
lockdep_is_held(&list_lrus_mutex));
/*
* Do not bother shrinking the array back to the old size, because we
* cannot handle allocation failures here.
*/
memcg_destroy_list_lru_range(mlrus, old_size, new_size);
}
int memcg_update_all_list_lrus(int new_size)
{
int ret = 0;
@ -460,15 +451,10 @@ int memcg_update_all_list_lrus(int new_size)
list_for_each_entry(lru, &memcg_list_lrus, list) {
ret = memcg_update_list_lru(lru, old_size, new_size);
if (ret)
goto fail;
break;
}
out:
mutex_unlock(&list_lrus_mutex);
return ret;
fail:
list_for_each_entry_continue_reverse(lru, &memcg_list_lrus, list)
memcg_cancel_update_list_lru(lru, old_size, new_size);
goto out;
}
static void memcg_drain_list_lru_node(struct list_lru *lru, int nid,
@ -485,6 +471,8 @@ static void memcg_drain_list_lru_node(struct list_lru *lru, int nid,
spin_lock_irq(&nlru->lock);
src = list_lru_from_memcg_idx(lru, nid, src_idx);
if (!src)
goto out;
dst = list_lru_from_memcg_idx(lru, nid, dst_idx);
list_splice_init(&src->list, &dst->list);
@ -494,7 +482,7 @@ static void memcg_drain_list_lru_node(struct list_lru *lru, int nid,
set_shrinker_bit(dst_memcg, nid, lru_shrinker_id(lru));
src->nr_items = 0;
}
out:
spin_unlock_irq(&nlru->lock);
}
@ -505,15 +493,41 @@ static void memcg_drain_list_lru(struct list_lru *lru,
for_each_node(i)
memcg_drain_list_lru_node(lru, i, src_idx, dst_memcg);
memcg_list_lru_free(lru, src_idx);
}
void memcg_drain_all_list_lrus(int src_idx, struct mem_cgroup *dst_memcg)
void memcg_drain_all_list_lrus(struct mem_cgroup *src, struct mem_cgroup *dst)
{
struct cgroup_subsys_state *css;
struct list_lru *lru;
int src_idx = src->kmemcg_id;
/*
* Change kmemcg_id of this cgroup and all its descendants to the
* parent's id, and then move all entries from this cgroup's list_lrus
* to ones of the parent.
*
* After we have finished, all list_lrus corresponding to this cgroup
* are guaranteed to remain empty. So we can safely free this cgroup's
* list lrus in memcg_list_lru_free().
*
* Changing ->kmemcg_id to the parent can prevent memcg_list_lru_alloc()
* from allocating list lrus for this cgroup after memcg_list_lru_free()
* call.
*/
rcu_read_lock();
css_for_each_descendant_pre(css, &src->css) {
struct mem_cgroup *memcg;
memcg = mem_cgroup_from_css(css);
memcg->kmemcg_id = dst->kmemcg_id;
}
rcu_read_unlock();
mutex_lock(&list_lrus_mutex);
list_for_each_entry(lru, &memcg_list_lrus, list)
memcg_drain_list_lru(lru, src_idx, dst_memcg);
memcg_drain_list_lru(lru, src_idx, dst);
mutex_unlock(&list_lrus_mutex);
}
@ -528,7 +542,7 @@ static bool memcg_list_lru_allocated(struct mem_cgroup *memcg,
return true;
rcu_read_lock();
allocated = !!rcu_dereference(lru->mlrus)->mlru[idx];
allocated = !!rcu_access_pointer(rcu_dereference(lru->mlrus)->mlru[idx]);
rcu_read_unlock();
return allocated;
@ -576,11 +590,12 @@ int memcg_list_lru_alloc(struct mem_cgroup *memcg, struct list_lru *lru,
mlrus = rcu_dereference_protected(lru->mlrus, true);
while (i--) {
int index = table[i].memcg->kmemcg_id;
struct list_lru_per_memcg *mlru = table[i].mlru;
if (mlrus->mlru[index])
kfree(table[i].mlru);
if (index < 0 || rcu_dereference_protected(mlrus->mlru[index], true))
kfree(mlru);
else
mlrus->mlru[index] = table[i].mlru;
rcu_assign_pointer(mlrus->mlru[index], mlru);
}
spin_unlock_irqrestore(&lru->lock, flags);

Просмотреть файл

@ -3709,6 +3709,10 @@ static void memcg_offline_kmem(struct mem_cgroup *memcg)
memcg_reparent_objcgs(memcg, parent);
/*
* memcg_drain_all_list_lrus() can change memcg->kmemcg_id.
* Cache it to local @kmemcg_id.
*/
kmemcg_id = memcg->kmemcg_id;
/*
@ -3717,7 +3721,7 @@ static void memcg_offline_kmem(struct mem_cgroup *memcg)
* The ordering is imposed by list_lru_node->lock taken by
* memcg_drain_all_list_lrus().
*/
memcg_drain_all_list_lrus(kmemcg_id, parent);
memcg_drain_all_list_lrus(memcg, parent);
memcg_free_cache_id(kmemcg_id);
}