From: Muchun Song <songmuchun@bytedance.com>
To: willy@infradead.org, akpm@linux-foundation.org,
hannes@cmpxchg.org, mhocko@kernel.org, vdavydov.dev@gmail.com,
shakeelb@google.com, guro@fb.com, shy828301@gmail.com,
alexs@kernel.org, richard.weiyang@gmail.com, david@fromorbit.com,
trond.myklebust@hammerspace.com, anna.schumaker@netapp.com
Cc: linux-fsdevel@vger.kernel.org, linux-kernel@vger.kernel.org,
linux-mm@kvack.org, linux-nfs@vger.kernel.org,
zhengqi.arch@bytedance.com, duanxiongchun@bytedance.com,
fam.zheng@bytedance.com, Muchun Song <songmuchun@bytedance.com>
Subject: [PATCH v2 07/21] mm: list_lru: optimize the array of per memcg lists memory consumption
Date: Thu, 27 May 2021 14:21:34 +0800 [thread overview]
Message-ID: <20210527062148.9361-8-songmuchun@bytedance.com> (raw)
In-Reply-To: <20210527062148.9361-1-songmuchun@bytedance.com>
The list_lru use an array to store the list_lru_one pointers, which is
per-memcg per-node. What if we run 10k containers in the system? The
size of the array of every list_lru can be 10k * number_of_node *
sizeof(void *). The array size becomes very big, the more numa node
in the system, the more memory we consume. We can convert the array
to per memcg instead of per-memcg per-node. It can save memory
especially when there are many numa nodes in the system. And also
simplify the code.
Signed-off-by: Muchun Song <songmuchun@bytedance.com>
---
include/linux/list_lru.h | 17 +++--
mm/list_lru.c | 191 +++++++++++++++++------------------------------
2 files changed, 79 insertions(+), 129 deletions(-)
diff --git a/include/linux/list_lru.h b/include/linux/list_lru.h
index 9dcaa3e582c9..20a43904001d 100644
--- a/include/linux/list_lru.h
+++ b/include/linux/list_lru.h
@@ -31,10 +31,15 @@ struct list_lru_one {
long nr_items;
};
+struct list_lru_per_memcg {
+ /* array of per cgroup per node lists, indexed by node id */
+ struct list_lru_one nodes[0];
+};
+
struct list_lru_memcg {
- struct rcu_head rcu;
+ struct rcu_head rcu;
/* array of per cgroup lists, indexed by memcg_cache_id */
- struct list_lru_one *lru[];
+ struct list_lru_per_memcg *lrus[];
};
struct list_lru_node {
@@ -42,11 +47,7 @@ struct list_lru_node {
spinlock_t lock;
/* global list, used for the root cgroup in cgroup aware lrus */
struct list_lru_one lru;
-#ifdef CONFIG_MEMCG_KMEM
- /* for cgroup aware lrus points to per cgroup lists, otherwise NULL */
- struct list_lru_memcg __rcu *memcg_lrus;
-#endif
- long nr_items;
+ long nr_items;
} ____cacheline_aligned_in_smp;
struct list_lru {
@@ -55,6 +56,8 @@ struct list_lru {
struct list_head list;
int shrinker_id;
bool memcg_aware;
+ /* for cgroup aware lrus points to per cgroup lists, otherwise NULL */
+ struct list_lru_memcg __rcu *memcg_lrus;
#endif
};
diff --git a/mm/list_lru.c b/mm/list_lru.c
index bed699edabe5..e52f5a91fa0f 100644
--- a/mm/list_lru.c
+++ b/mm/list_lru.c
@@ -49,35 +49,38 @@ static int lru_shrinker_id(struct list_lru *lru)
}
static inline struct list_lru_one *
-list_lru_from_memcg_idx(struct list_lru_node *nlru, int idx)
+list_lru_from_memcg_idx(struct list_lru *lru, int nid, int idx)
{
struct list_lru_memcg *memcg_lrus;
+ struct list_lru_node *nlru = &lru->node[nid];
+
/*
* Either lock or RCU protects the array of per cgroup lists
- * from relocation (see memcg_update_list_lru_node).
+ * from relocation (see memcg_update_list_lru).
*/
- memcg_lrus = rcu_dereference_check(nlru->memcg_lrus,
+ memcg_lrus = rcu_dereference_check(lru->memcg_lrus,
lockdep_is_held(&nlru->lock));
if (memcg_lrus && idx >= 0)
- return memcg_lrus->lru[idx];
+ return &memcg_lrus->lrus[idx]->nodes[nid];
return &nlru->lru;
}
static inline struct list_lru_one *
-list_lru_from_kmem(struct list_lru_node *nlru, void *ptr,
+list_lru_from_kmem(struct list_lru *lru, int nid, void *ptr,
struct mem_cgroup **memcg_ptr)
{
+ struct list_lru_node *nlru = &lru->node[nid];
struct list_lru_one *l = &nlru->lru;
struct mem_cgroup *memcg = NULL;
- if (!nlru->memcg_lrus)
+ if (!lru->memcg_lrus)
goto out;
memcg = mem_cgroup_from_obj(ptr);
if (!memcg)
goto out;
- l = list_lru_from_memcg_idx(nlru, memcg_cache_id(memcg));
+ l = list_lru_from_memcg_idx(lru, nid, memcg_cache_id(memcg));
out:
if (memcg_ptr)
*memcg_ptr = memcg;
@@ -103,18 +106,18 @@ static inline bool list_lru_memcg_aware(struct list_lru *lru)
}
static inline struct list_lru_one *
-list_lru_from_memcg_idx(struct list_lru_node *nlru, int idx)
+list_lru_from_memcg_idx(struct list_lru *lru, int nid, int idx)
{
- return &nlru->lru;
+ return &lru->node[nid].lru;
}
static inline struct list_lru_one *
-list_lru_from_kmem(struct list_lru_node *nlru, void *ptr,
+list_lru_from_kmem(struct list_lru *lru, int nid, void *ptr,
struct mem_cgroup **memcg_ptr)
{
if (memcg_ptr)
*memcg_ptr = NULL;
- return &nlru->lru;
+ return &lru->node[nid].lru;
}
#endif /* CONFIG_MEMCG_KMEM */
@@ -127,7 +130,7 @@ bool list_lru_add(struct list_lru *lru, struct list_head *item)
spin_lock(&nlru->lock);
if (list_empty(item)) {
- l = list_lru_from_kmem(nlru, item, &memcg);
+ l = list_lru_from_kmem(lru, nid, item, &memcg);
list_add_tail(item, &l->list);
/* Set shrinker bit if the first element was added */
if (!l->nr_items++)
@@ -150,7 +153,7 @@ bool list_lru_del(struct list_lru *lru, struct list_head *item)
spin_lock(&nlru->lock);
if (!list_empty(item)) {
- l = list_lru_from_kmem(nlru, item, NULL);
+ l = list_lru_from_kmem(lru, nid, item, NULL);
list_del_init(item);
l->nr_items--;
nlru->nr_items--;
@@ -180,12 +183,11 @@ EXPORT_SYMBOL_GPL(list_lru_isolate_move);
unsigned long list_lru_count_one(struct list_lru *lru,
int nid, struct mem_cgroup *memcg)
{
- struct list_lru_node *nlru = &lru->node[nid];
struct list_lru_one *l;
long count;
rcu_read_lock();
- l = list_lru_from_memcg_idx(nlru, memcg_cache_id(memcg));
+ l = list_lru_from_memcg_idx(lru, nid, memcg_cache_id(memcg));
count = READ_ONCE(l->nr_items);
rcu_read_unlock();
@@ -206,16 +208,16 @@ unsigned long list_lru_count_node(struct list_lru *lru, int nid)
EXPORT_SYMBOL_GPL(list_lru_count_node);
static unsigned long
-__list_lru_walk_one(struct list_lru_node *nlru, int memcg_idx,
+__list_lru_walk_one(struct list_lru *lru, int nid, int memcg_idx,
list_lru_walk_cb isolate, void *cb_arg,
unsigned long *nr_to_walk)
{
-
+ struct list_lru_node *nlru = &lru->node[nid];
struct list_lru_one *l;
struct list_head *item, *n;
unsigned long isolated = 0;
- l = list_lru_from_memcg_idx(nlru, memcg_idx);
+ l = list_lru_from_memcg_idx(lru, nid, memcg_idx);
restart:
list_for_each_safe(item, n, &l->list) {
enum lru_status ret;
@@ -272,8 +274,8 @@ list_lru_walk_one(struct list_lru *lru, int nid, struct mem_cgroup *memcg,
unsigned long ret;
spin_lock(&nlru->lock);
- ret = __list_lru_walk_one(nlru, memcg_cache_id(memcg), isolate, cb_arg,
- nr_to_walk);
+ ret = __list_lru_walk_one(lru, nid, memcg_cache_id(memcg), isolate,
+ cb_arg, nr_to_walk);
spin_unlock(&nlru->lock);
return ret;
}
@@ -288,8 +290,8 @@ list_lru_walk_one_irq(struct list_lru *lru, int nid, struct mem_cgroup *memcg,
unsigned long ret;
spin_lock_irq(&nlru->lock);
- ret = __list_lru_walk_one(nlru, memcg_cache_id(memcg), isolate, cb_arg,
- nr_to_walk);
+ ret = __list_lru_walk_one(lru, nid, memcg_cache_id(memcg), isolate,
+ cb_arg, nr_to_walk);
spin_unlock_irq(&nlru->lock);
return ret;
}
@@ -308,7 +310,7 @@ unsigned long list_lru_walk_node(struct list_lru *lru, int nid,
struct list_lru_node *nlru = &lru->node[nid];
spin_lock(&nlru->lock);
- isolated += __list_lru_walk_one(nlru, memcg_idx,
+ isolated += __list_lru_walk_one(lru, nid, memcg_idx,
isolate, cb_arg,
nr_to_walk);
spin_unlock(&nlru->lock);
@@ -328,169 +330,114 @@ static void init_one_lru(struct list_lru_one *l)
}
#ifdef CONFIG_MEMCG_KMEM
-static void __memcg_destroy_list_lru_node(struct list_lru_memcg *memcg_lrus,
- int begin, int end)
+static void memcg_destroy_list_lru_range(struct list_lru_memcg *memcg_lrus,
+ int begin, int end)
{
int i;
for (i = begin; i < end; i++)
- kfree(memcg_lrus->lru[i]);
+ kfree(memcg_lrus->lrus[i]);
}
-static int __memcg_init_list_lru_node(struct list_lru_memcg *memcg_lrus,
- int begin, int end)
+static int memcg_init_list_lru_range(struct list_lru_memcg *memcg_lrus,
+ int begin, int end)
{
int i;
for (i = begin; i < end; i++) {
- struct list_lru_one *l;
+ int nid;
+ struct list_lru_per_memcg *lru;
- l = kmalloc(sizeof(struct list_lru_one), GFP_KERNEL);
- if (!l)
+ lru = kmalloc(struct_size(lru, nodes, nr_node_ids), GFP_KERNEL);
+ if (!lru)
goto fail;
- init_one_lru(l);
- memcg_lrus->lru[i] = l;
+ for_each_node(nid)
+ init_one_lru(&lru->nodes[nid]);
+ memcg_lrus->lrus[i] = lru;
}
return 0;
fail:
- __memcg_destroy_list_lru_node(memcg_lrus, begin, i);
+ memcg_destroy_list_lru_range(memcg_lrus, begin, i);
return -ENOMEM;
}
-static int memcg_init_list_lru_node(struct list_lru_node *nlru)
+static int memcg_init_list_lru(struct list_lru *lru, bool memcg_aware)
{
struct list_lru_memcg *memcg_lrus;
int size = memcg_nr_cache_ids;
+ lru->memcg_aware = memcg_aware;
+ if (!memcg_aware)
+ return 0;
+
memcg_lrus = kvmalloc(sizeof(*memcg_lrus) +
- size * sizeof(void *), GFP_KERNEL);
+ size * sizeof(memcg_lrus->lrus[0]), GFP_KERNEL);
if (!memcg_lrus)
return -ENOMEM;
- if (__memcg_init_list_lru_node(memcg_lrus, 0, size)) {
+ if (memcg_init_list_lru_range(memcg_lrus, 0, size)) {
kvfree(memcg_lrus);
return -ENOMEM;
}
- RCU_INIT_POINTER(nlru->memcg_lrus, memcg_lrus);
+ RCU_INIT_POINTER(lru->memcg_lrus, memcg_lrus);
return 0;
}
-static void memcg_destroy_list_lru_node(struct list_lru_node *nlru)
+static void memcg_destroy_list_lru(struct list_lru *lru)
{
struct list_lru_memcg *memcg_lrus;
+
+ if (!list_lru_memcg_aware(lru))
+ return;
+
/*
* This is called when shrinker has already been unregistered,
* and nobody can use it. So, there is no need to use kvfree_rcu().
*/
- memcg_lrus = rcu_dereference_protected(nlru->memcg_lrus, true);
- __memcg_destroy_list_lru_node(memcg_lrus, 0, memcg_nr_cache_ids);
+ memcg_lrus = rcu_dereference_protected(lru->memcg_lrus, true);
+ memcg_destroy_list_lru_range(memcg_lrus, 0, memcg_nr_cache_ids);
kvfree(memcg_lrus);
}
-static int memcg_update_list_lru_node(struct list_lru_node *nlru,
- int old_size, int new_size)
+static int memcg_update_list_lru(struct list_lru *lru, int old_size, int new_size)
{
struct list_lru_memcg *old, *new;
BUG_ON(old_size > new_size);
- old = rcu_dereference_protected(nlru->memcg_lrus,
+ old = rcu_dereference_protected(lru->memcg_lrus,
lockdep_is_held(&list_lrus_mutex));
- new = kvmalloc(sizeof(*new) + new_size * sizeof(void *), GFP_KERNEL);
+ new = kvmalloc(sizeof(*new) + new_size * sizeof(new->lrus[0]), GFP_KERNEL);
if (!new)
return -ENOMEM;
- if (__memcg_init_list_lru_node(new, old_size, new_size)) {
+ if (memcg_init_list_lru_range(new, old_size, new_size)) {
kvfree(new);
return -ENOMEM;
}
- memcpy(&new->lru, &old->lru, old_size * sizeof(void *));
+ memcpy(&new->lrus, &old->lrus, old_size * sizeof(new->lrus[0]));
- rcu_assign_pointer(nlru->memcg_lrus, new);
+ rcu_assign_pointer(lru->memcg_lrus, new);
kvfree_rcu(old, rcu);
return 0;
}
-static void memcg_cancel_update_list_lru_node(struct list_lru_node *nlru,
- int old_size, int new_size)
-{
- struct list_lru_memcg *memcg_lrus;
-
- memcg_lrus = rcu_dereference_protected(nlru->memcg_lrus,
- 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_node(memcg_lrus, old_size, new_size);
-}
-
-static int memcg_init_list_lru(struct list_lru *lru, bool memcg_aware)
-{
- int i;
-
- lru->memcg_aware = memcg_aware;
-
- if (!memcg_aware)
- return 0;
-
- for_each_node(i) {
- if (memcg_init_list_lru_node(&lru->node[i]))
- goto fail;
- }
- return 0;
-fail:
- for (i = i - 1; i >= 0; i--) {
- if (!lru->node[i].memcg_lrus)
- continue;
- memcg_destroy_list_lru_node(&lru->node[i]);
- }
- return -ENOMEM;
-}
-
-static void memcg_destroy_list_lru(struct list_lru *lru)
-{
- int i;
-
- if (!list_lru_memcg_aware(lru))
- return;
-
- for_each_node(i)
- memcg_destroy_list_lru_node(&lru->node[i]);
-}
-
-static int memcg_update_list_lru(struct list_lru *lru,
- int old_size, int new_size)
-{
- int i;
-
- for_each_node(i) {
- if (memcg_update_list_lru_node(&lru->node[i],
- old_size, new_size))
- goto fail;
- }
- return 0;
-fail:
- for (i = i - 1; i >= 0; i--) {
- if (!lru->node[i].memcg_lrus)
- continue;
-
- memcg_cancel_update_list_lru_node(&lru->node[i],
- old_size, new_size);
- }
- return -ENOMEM;
-}
-
static void memcg_cancel_update_list_lru(struct list_lru *lru,
int old_size, int new_size)
{
- int i;
+ struct list_lru_memcg *memcg_lrus;
- for_each_node(i)
- memcg_cancel_update_list_lru_node(&lru->node[i],
- old_size, new_size);
+ memcg_lrus = rcu_dereference_protected(lru->memcg_lrus,
+ 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(memcg_lrus, old_size, new_size);
}
int memcg_update_all_list_lrus(int new_size)
@@ -527,8 +474,8 @@ static void memcg_drain_list_lru_node(struct list_lru *lru, int nid,
*/
spin_lock_irq(&nlru->lock);
- src = list_lru_from_memcg_idx(nlru, src_idx);
- dst = list_lru_from_memcg_idx(nlru, dst_idx);
+ src = list_lru_from_memcg_idx(lru, nid, src_idx);
+ dst = list_lru_from_memcg_idx(lru, nid, dst_idx);
list_splice_init(&src->list, &dst->list);
--
2.11.0
next prev parent reply other threads:[~2021-05-27 6:25 UTC|newest]
Thread overview: 26+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-05-27 6:21 [PATCH v2 00/21] Optimize list lru memory consumption Muchun Song
2021-05-27 6:21 ` [PATCH v2 01/21] mm: list_lru: fix list_lru_count_one() return value Muchun Song
2021-05-27 6:21 ` [PATCH v2 02/21] mm: memcontrol: remove kmemcg_id reparenting Muchun Song
2021-05-27 6:21 ` [PATCH v2 03/21] mm: memcontrol: remove the kmem states Muchun Song
2021-05-27 6:21 ` [PATCH v2 04/21] mm: memcontrol: do it in mem_cgroup_css_online to make the kmem online Muchun Song
2021-05-27 6:21 ` [PATCH v2 05/21] mm: list_lru: remove lru node locking from memcg_update_list_lru_node Muchun Song
2021-05-27 6:21 ` [PATCH v2 06/21] mm: list_lru: only add the memcg aware lrus to the list_lrus Muchun Song
2021-05-27 6:21 ` Muchun Song [this message]
2021-05-27 6:21 ` [PATCH v2 08/21] mm: list_lru: remove memcg_aware field from struct list_lru Muchun Song
2021-05-27 6:21 ` [PATCH v2 09/21] mm: introduce kmem_cache_alloc_lru Muchun Song
2021-05-27 6:21 ` [PATCH v2 10/21] fs: introduce alloc_inode_sb() to allocate filesystems specific inode Muchun Song
2021-05-27 6:21 ` [PATCH v2 11/21] mm: dcache: use kmem_cache_alloc_lru() to allocate dentry Muchun Song
2021-05-27 6:21 ` [PATCH v2 12/21] xarray: use kmem_cache_alloc_lru to allocate xa_node Muchun Song
2021-05-27 6:21 ` [PATCH v2 13/21] mm: workingset: use xas_set_lru() to pass shadow_nodes Muchun Song
2021-05-27 6:21 ` [PATCH v2 14/21] nfs42: use a specific kmem_cache to allocate nfs4_xattr_entry Muchun Song
2021-05-27 6:21 ` [PATCH v2 15/21] mm: list_lru: allocate list_lru_one only when needed Muchun Song
2021-05-27 6:21 ` [PATCH v2 16/21] mm: list_lru: rename memcg_drain_all_list_lrus to memcg_reparent_list_lrus Muchun Song
2021-05-27 6:21 ` [PATCH v2 17/21] mm: list_lru: replace linear array with xarray Muchun Song
2021-05-27 12:07 ` Matthew Wilcox
2021-05-28 3:43 ` [External] " Muchun Song
2021-05-28 8:04 ` Muchun Song
2021-05-27 6:21 ` [PATCH v2 18/21] mm: memcontrol: reuse memory cgroup ID for kmem ID Muchun Song
2021-05-27 6:21 ` [PATCH v2 19/21] mm: memcontrol: fix cannot alloc the maximum memcg ID Muchun Song
2021-05-27 6:21 ` [PATCH v2 20/21] mm: list_lru: rename list_lru_per_memcg to list_lru_memcg Muchun Song
2021-05-27 6:21 ` [PATCH v2 21/21] mm: memcontrol: rename memcg_cache_id to memcg_kmem_id Muchun Song
2021-06-16 10:53 ` [PATCH v2 00/21] Optimize list lru memory consumption Muchun Song
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20210527062148.9361-8-songmuchun@bytedance.com \
--to=songmuchun@bytedance.com \
--cc=akpm@linux-foundation.org \
--cc=alexs@kernel.org \
--cc=anna.schumaker@netapp.com \
--cc=david@fromorbit.com \
--cc=duanxiongchun@bytedance.com \
--cc=fam.zheng@bytedance.com \
--cc=guro@fb.com \
--cc=hannes@cmpxchg.org \
--cc=linux-fsdevel@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=linux-nfs@vger.kernel.org \
--cc=mhocko@kernel.org \
--cc=richard.weiyang@gmail.com \
--cc=shakeelb@google.com \
--cc=shy828301@gmail.com \
--cc=trond.myklebust@hammerspace.com \
--cc=vdavydov.dev@gmail.com \
--cc=willy@infradead.org \
--cc=zhengqi.arch@bytedance.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).