![Kirill Tkhai](/assets/img/avatar_default.png)
During the reclaiming slab of a memcg, shrink_slab iterates over all registered shrinkers in the system, and tries to count and consume objects related to the cgroup. In case of memory pressure, this behaves bad: I observe high system time and time spent in list_lru_count_one() for many processes on RHEL7 kernel. This patch makes list_lru_node::memcg_lrus rcu protected, that allows to skip taking spinlock in list_lru_count_one(). Shakeel Butt with the patch observes significant perf graph change. He says: ======================================================================== Setup: running a fork-bomb in a memcg of 200MiB on a 8GiB and 4 vcpu VM and recording the trace with 'perf record -g -a'. The trace without the patch: + 34.19% fb.sh [kernel.kallsyms] [k] queued_spin_lock_slowpath + 30.77% fb.sh [kernel.kallsyms] [k] _raw_spin_lock + 3.53% fb.sh [kernel.kallsyms] [k] list_lru_count_one + 2.26% fb.sh [kernel.kallsyms] [k] super_cache_count + 1.68% fb.sh [kernel.kallsyms] [k] shrink_slab + 0.59% fb.sh [kernel.kallsyms] [k] down_read_trylock + 0.48% fb.sh [kernel.kallsyms] [k] _raw_spin_unlock_irqrestore + 0.38% fb.sh [kernel.kallsyms] [k] shrink_node_memcg + 0.32% fb.sh [kernel.kallsyms] [k] queue_work_on + 0.26% fb.sh [kernel.kallsyms] [k] count_shadow_nodes With the patch: + 0.16% swapper [kernel.kallsyms] [k] default_idle + 0.13% oom_reaper [kernel.kallsyms] [k] mutex_spin_on_owner + 0.05% perf [kernel.kallsyms] [k] copy_user_generic_string + 0.05% init.real [kernel.kallsyms] [k] wait_consider_task + 0.05% kworker/0:0 [kernel.kallsyms] [k] finish_task_switch + 0.04% kworker/2:1 [kernel.kallsyms] [k] finish_task_switch + 0.04% kworker/3:1 [kernel.kallsyms] [k] finish_task_switch + 0.04% kworker/1:0 [kernel.kallsyms] [k] finish_task_switch + 0.03% binary [kernel.kallsyms] [k] copy_page ======================================================================== Thanks Shakeel for the testing. [ktkhai@virtuozzo.com: v2] Link: http://lkml.kernel.org/r/151203869520.3915.2587549826865799173.stgit@localhost.localdomain Link: http://lkml.kernel.org/r/150583358557.26700.8490036563698102569.stgit@localhost.localdomain Signed-off-by: Kirill Tkhai <ktkhai@virtuozzo.com> Tested-by: Shakeel Butt <shakeelb@google.com> Acked-by: Vladimir Davydov <vdavydov.dev@gmail.com> Cc: Andrey Ryabinin <aryabinin@virtuozzo.com> Cc: Michal Hocko <mhocko@kernel.org> Cc: Johannes Weiner <hannes@cmpxchg.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
193 lines
6.3 KiB
C
193 lines
6.3 KiB
C
/* SPDX-License-Identifier: GPL-2.0 */
|
|
/*
|
|
* Copyright (c) 2013 Red Hat, Inc. and Parallels Inc. All rights reserved.
|
|
* Authors: David Chinner and Glauber Costa
|
|
*
|
|
* Generic LRU infrastructure
|
|
*/
|
|
#ifndef _LRU_LIST_H
|
|
#define _LRU_LIST_H
|
|
|
|
#include <linux/list.h>
|
|
#include <linux/nodemask.h>
|
|
#include <linux/shrinker.h>
|
|
|
|
struct mem_cgroup;
|
|
|
|
/* list_lru_walk_cb has to always return one of those */
|
|
enum lru_status {
|
|
LRU_REMOVED, /* item removed from list */
|
|
LRU_REMOVED_RETRY, /* item removed, but lock has been
|
|
dropped and reacquired */
|
|
LRU_ROTATE, /* item referenced, give another pass */
|
|
LRU_SKIP, /* item cannot be locked, skip */
|
|
LRU_RETRY, /* item not freeable. May drop the lock
|
|
internally, but has to return locked. */
|
|
};
|
|
|
|
struct list_lru_one {
|
|
struct list_head list;
|
|
/* may become negative during memcg reparenting */
|
|
long nr_items;
|
|
};
|
|
|
|
struct list_lru_memcg {
|
|
struct rcu_head rcu;
|
|
/* array of per cgroup lists, indexed by memcg_cache_id */
|
|
struct list_lru_one *lru[0];
|
|
};
|
|
|
|
struct list_lru_node {
|
|
/* protects all lists on the node, including per cgroup */
|
|
spinlock_t lock;
|
|
/* global list, used for the root cgroup in cgroup aware lrus */
|
|
struct list_lru_one lru;
|
|
#if defined(CONFIG_MEMCG) && !defined(CONFIG_SLOB)
|
|
/* for cgroup aware lrus points to per cgroup lists, otherwise NULL */
|
|
struct list_lru_memcg __rcu *memcg_lrus;
|
|
#endif
|
|
long nr_items;
|
|
} ____cacheline_aligned_in_smp;
|
|
|
|
struct list_lru {
|
|
struct list_lru_node *node;
|
|
#if defined(CONFIG_MEMCG) && !defined(CONFIG_SLOB)
|
|
struct list_head list;
|
|
#endif
|
|
};
|
|
|
|
void list_lru_destroy(struct list_lru *lru);
|
|
int __list_lru_init(struct list_lru *lru, bool memcg_aware,
|
|
struct lock_class_key *key);
|
|
|
|
#define list_lru_init(lru) __list_lru_init((lru), false, NULL)
|
|
#define list_lru_init_key(lru, key) __list_lru_init((lru), false, (key))
|
|
#define list_lru_init_memcg(lru) __list_lru_init((lru), true, NULL)
|
|
|
|
int memcg_update_all_list_lrus(int num_memcgs);
|
|
void memcg_drain_all_list_lrus(int src_idx, int dst_idx);
|
|
|
|
/**
|
|
* list_lru_add: add an element to the lru list's tail
|
|
* @list_lru: the lru pointer
|
|
* @item: the item to be added.
|
|
*
|
|
* If the element is already part of a list, this function returns doing
|
|
* nothing. Therefore the caller does not need to keep state about whether or
|
|
* not the element already belongs in the list and is allowed to lazy update
|
|
* it. Note however that this is valid for *a* list, not *this* list. If
|
|
* the caller organize itself in a way that elements can be in more than
|
|
* one type of list, it is up to the caller to fully remove the item from
|
|
* the previous list (with list_lru_del() for instance) before moving it
|
|
* to @list_lru
|
|
*
|
|
* Return value: true if the list was updated, false otherwise
|
|
*/
|
|
bool list_lru_add(struct list_lru *lru, struct list_head *item);
|
|
|
|
/**
|
|
* list_lru_del: delete an element to the lru list
|
|
* @list_lru: the lru pointer
|
|
* @item: the item to be deleted.
|
|
*
|
|
* This function works analogously as list_lru_add in terms of list
|
|
* manipulation. The comments about an element already pertaining to
|
|
* a list are also valid for list_lru_del.
|
|
*
|
|
* Return value: true if the list was updated, false otherwise
|
|
*/
|
|
bool list_lru_del(struct list_lru *lru, struct list_head *item);
|
|
|
|
/**
|
|
* list_lru_count_one: return the number of objects currently held by @lru
|
|
* @lru: the lru pointer.
|
|
* @nid: the node id to count from.
|
|
* @memcg: the cgroup to count from.
|
|
*
|
|
* Always return a non-negative number, 0 for empty lists. There is no
|
|
* guarantee that the list is not updated while the count is being computed.
|
|
* Callers that want such a guarantee need to provide an outer lock.
|
|
*/
|
|
unsigned long list_lru_count_one(struct list_lru *lru,
|
|
int nid, struct mem_cgroup *memcg);
|
|
unsigned long list_lru_count_node(struct list_lru *lru, int nid);
|
|
|
|
static inline unsigned long list_lru_shrink_count(struct list_lru *lru,
|
|
struct shrink_control *sc)
|
|
{
|
|
return list_lru_count_one(lru, sc->nid, sc->memcg);
|
|
}
|
|
|
|
static inline unsigned long list_lru_count(struct list_lru *lru)
|
|
{
|
|
long count = 0;
|
|
int nid;
|
|
|
|
for_each_node_state(nid, N_NORMAL_MEMORY)
|
|
count += list_lru_count_node(lru, nid);
|
|
|
|
return count;
|
|
}
|
|
|
|
void list_lru_isolate(struct list_lru_one *list, struct list_head *item);
|
|
void list_lru_isolate_move(struct list_lru_one *list, struct list_head *item,
|
|
struct list_head *head);
|
|
|
|
typedef enum lru_status (*list_lru_walk_cb)(struct list_head *item,
|
|
struct list_lru_one *list, spinlock_t *lock, void *cb_arg);
|
|
|
|
/**
|
|
* list_lru_walk_one: walk a list_lru, isolating and disposing freeable items.
|
|
* @lru: the lru pointer.
|
|
* @nid: the node id to scan from.
|
|
* @memcg: the cgroup to scan from.
|
|
* @isolate: callback function that is resposible for deciding what to do with
|
|
* the item currently being scanned
|
|
* @cb_arg: opaque type that will be passed to @isolate
|
|
* @nr_to_walk: how many items to scan.
|
|
*
|
|
* This function will scan all elements in a particular list_lru, calling the
|
|
* @isolate callback for each of those items, along with the current list
|
|
* spinlock and a caller-provided opaque. The @isolate callback can choose to
|
|
* drop the lock internally, but *must* return with the lock held. The callback
|
|
* will return an enum lru_status telling the list_lru infrastructure what to
|
|
* do with the object being scanned.
|
|
*
|
|
* Please note that nr_to_walk does not mean how many objects will be freed,
|
|
* just how many objects will be scanned.
|
|
*
|
|
* Return value: the number of objects effectively removed from the LRU.
|
|
*/
|
|
unsigned long list_lru_walk_one(struct list_lru *lru,
|
|
int nid, struct mem_cgroup *memcg,
|
|
list_lru_walk_cb isolate, void *cb_arg,
|
|
unsigned long *nr_to_walk);
|
|
unsigned long list_lru_walk_node(struct list_lru *lru, int nid,
|
|
list_lru_walk_cb isolate, void *cb_arg,
|
|
unsigned long *nr_to_walk);
|
|
|
|
static inline unsigned long
|
|
list_lru_shrink_walk(struct list_lru *lru, struct shrink_control *sc,
|
|
list_lru_walk_cb isolate, void *cb_arg)
|
|
{
|
|
return list_lru_walk_one(lru, sc->nid, sc->memcg, isolate, cb_arg,
|
|
&sc->nr_to_scan);
|
|
}
|
|
|
|
static inline unsigned long
|
|
list_lru_walk(struct list_lru *lru, list_lru_walk_cb isolate,
|
|
void *cb_arg, unsigned long nr_to_walk)
|
|
{
|
|
long isolated = 0;
|
|
int nid;
|
|
|
|
for_each_node_state(nid, N_NORMAL_MEMORY) {
|
|
isolated += list_lru_walk_node(lru, nid, isolate,
|
|
cb_arg, &nr_to_walk);
|
|
if (nr_to_walk <= 0)
|
|
break;
|
|
}
|
|
return isolated;
|
|
}
|
|
#endif /* _LRU_LIST_H */
|