8e8ae64524
Let the networking stack know when a memcg is under reclaim pressure so that it can clamp its transmit windows accordingly. Whenever the reclaim efficiency of a cgroup's LRU lists drops low enough for a MEDIUM or HIGH vmpressure event to occur, assert a pressure state in the socket and tcp memory code that tells it to curb consumption growth from sockets associated with said control group. Traditionally, vmpressure reports for the entire subtree of a memcg under pressure, which drops useful information on the individual groups reclaimed. However, it's too late to change the userinterface, so add a second reporting mode that reports on the level of reclaim instead of at the level of pressure, and use that report for sockets. vmpressure events are naturally edge triggered, so for hysteresis assert socket pressure for a second to allow for subsequent vmpressure events to occur before letting the socket code return to normal. This will likely need finetuning for a wider variety of workloads, but for now stick to the vmpressure presets and keep hysteresis simple. Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Acked-by: David S. Miller <davem@davemloft.net> Reviewed-by: Vladimir Davydov <vdavydov@virtuozzo.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
51 lines
1.7 KiB
C
51 lines
1.7 KiB
C
#ifndef __LINUX_VMPRESSURE_H
|
|
#define __LINUX_VMPRESSURE_H
|
|
|
|
#include <linux/mutex.h>
|
|
#include <linux/list.h>
|
|
#include <linux/workqueue.h>
|
|
#include <linux/gfp.h>
|
|
#include <linux/types.h>
|
|
#include <linux/cgroup.h>
|
|
#include <linux/eventfd.h>
|
|
|
|
struct vmpressure {
|
|
unsigned long scanned;
|
|
unsigned long reclaimed;
|
|
|
|
unsigned long tree_scanned;
|
|
unsigned long tree_reclaimed;
|
|
/* The lock is used to keep the scanned/reclaimed above in sync. */
|
|
struct spinlock sr_lock;
|
|
|
|
/* The list of vmpressure_event structs. */
|
|
struct list_head events;
|
|
/* Have to grab the lock on events traversal or modifications. */
|
|
struct mutex events_lock;
|
|
|
|
struct work_struct work;
|
|
};
|
|
|
|
struct mem_cgroup;
|
|
|
|
#ifdef CONFIG_MEMCG
|
|
extern void vmpressure(gfp_t gfp, struct mem_cgroup *memcg, bool tree,
|
|
unsigned long scanned, unsigned long reclaimed);
|
|
extern void vmpressure_prio(gfp_t gfp, struct mem_cgroup *memcg, int prio);
|
|
|
|
extern void vmpressure_init(struct vmpressure *vmpr);
|
|
extern void vmpressure_cleanup(struct vmpressure *vmpr);
|
|
extern struct vmpressure *memcg_to_vmpressure(struct mem_cgroup *memcg);
|
|
extern struct cgroup_subsys_state *vmpressure_to_css(struct vmpressure *vmpr);
|
|
extern int vmpressure_register_event(struct mem_cgroup *memcg,
|
|
struct eventfd_ctx *eventfd,
|
|
const char *args);
|
|
extern void vmpressure_unregister_event(struct mem_cgroup *memcg,
|
|
struct eventfd_ctx *eventfd);
|
|
#else
|
|
static inline void vmpressure(gfp_t gfp, struct mem_cgroup *memcg, bool tree,
|
|
unsigned long scanned, unsigned long reclaimed) {}
|
|
static inline void vmpressure_prio(gfp_t gfp, struct mem_cgroup *memcg,
|
|
int prio) {}
|
|
#endif /* CONFIG_MEMCG */
|
|
#endif /* __LINUX_VMPRESSURE_H */
|