linux_dsm_epyc7002/include/linux/oom.h
David Rientjes a7f638f999 mm, oom: normalize oom scores to oom_score_adj scale only for userspace
The oom_score_adj scale ranges from -1000 to 1000 and represents the
proportion of memory available to the process at allocation time.  This
means an oom_score_adj value of 300, for example, will bias a process as
though it was using an extra 30.0% of available memory and a value of
-350 will discount 35.0% of available memory from its usage.

The oom killer badness heuristic also uses this scale to report the oom
score for each eligible process in determining the "best" process to
kill.  Thus, it can only differentiate each process's memory usage by
0.1% of system RAM.

On large systems, this can end up being a large amount of memory: 256MB
on 256GB systems, for example.

This can be fixed by having the badness heuristic to use the actual
memory usage in scoring threads and then normalizing it to the
oom_score_adj scale for userspace.  This results in better comparison
between eligible threads for kill and no change from the userspace
perspective.

Suggested-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Tested-by: Dave Jones <davej@redhat.com>
Signed-off-by: David Rientjes <rientjes@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-05-29 16:22:24 -07:00

77 lines
1.9 KiB
C

#ifndef __INCLUDE_LINUX_OOM_H
#define __INCLUDE_LINUX_OOM_H
/*
* /proc/<pid>/oom_adj is deprecated, see
* Documentation/feature-removal-schedule.txt.
*
* /proc/<pid>/oom_adj set to -17 protects from the oom-killer
*/
#define OOM_DISABLE (-17)
/* inclusive */
#define OOM_ADJUST_MIN (-16)
#define OOM_ADJUST_MAX 15
/*
* /proc/<pid>/oom_score_adj set to OOM_SCORE_ADJ_MIN disables oom killing for
* pid.
*/
#define OOM_SCORE_ADJ_MIN (-1000)
#define OOM_SCORE_ADJ_MAX 1000
#ifdef __KERNEL__
#include <linux/sched.h>
#include <linux/types.h>
#include <linux/nodemask.h>
struct zonelist;
struct notifier_block;
struct mem_cgroup;
struct task_struct;
/*
* Types of limitations to the nodes from which allocations may occur
*/
enum oom_constraint {
CONSTRAINT_NONE,
CONSTRAINT_CPUSET,
CONSTRAINT_MEMORY_POLICY,
CONSTRAINT_MEMCG,
};
extern void compare_swap_oom_score_adj(int old_val, int new_val);
extern int test_set_oom_score_adj(int new_val);
extern unsigned long oom_badness(struct task_struct *p,
struct mem_cgroup *memcg, const nodemask_t *nodemask,
unsigned long totalpages);
extern int try_set_zonelist_oom(struct zonelist *zonelist, gfp_t gfp_flags);
extern void clear_zonelist_oom(struct zonelist *zonelist, gfp_t gfp_flags);
extern void out_of_memory(struct zonelist *zonelist, gfp_t gfp_mask,
int order, nodemask_t *mask, bool force_kill);
extern int register_oom_notifier(struct notifier_block *nb);
extern int unregister_oom_notifier(struct notifier_block *nb);
extern bool oom_killer_disabled;
static inline void oom_killer_disable(void)
{
oom_killer_disabled = true;
}
static inline void oom_killer_enable(void)
{
oom_killer_disabled = false;
}
extern struct task_struct *find_lock_task_mm(struct task_struct *p);
/* sysctls */
extern int sysctl_oom_dump_tasks;
extern int sysctl_oom_kill_allocating_task;
extern int sysctl_panic_on_oom;
#endif /* __KERNEL__*/
#endif /* _INCLUDE_LINUX_OOM_H */