理解和配置 Linux 下的 OOM Killer

...
Out of memory: Kill proc
4000
ess 9682 (mysqld) score 9 or sacrifice child
Killed process 9682, UID 27, (mysqld) total-vm:47388kB, anon-rss:3744kB, file-rss:80kB
httpd invoked oom-killer: gfp_mask=0x201da, order=0, oom_adj=0, oom_score_adj=0
httpd cpuset=/ mems_allowed=0
Pid: 8911, comm: httpd Not tainted 2.6.32-279.1.1.el6.i686 #1
...
21556 total pagecache pages
21049 pages in swap cache
Swap cache stats: add 12819103, delete 12798054, find 3188096/4634617
Free swap  = 0kB
Total swap = 524280kB
131071 pages RAM
0 pages HighMem
3673 pages reserved
67960 pages shared
124940 pages non-shared

/**
* oom_badness - heuristic function to determine which candidate task to kill
* @p: task struct of which task we should calculate
* @totalpages: total present RAM allowed for page allocation
*
* The heuristic for determining which task to kill is made to be as simple and
* predictable as possible.  The goal is to return the highest value for the
* task consuming the most memory to avoid subsequent oom failures.
*/
unsigned long oom_badness(struct task_struct *p, struct mem_cgroup *memcg,
const nodemask_t *nodemask, unsigned long totalpages)
{
long points;
long adj;

if (oom_unkillable_task(p, memcg, nodemask))
return 0;

p = find_lock_task_mm(p);
if (!p)
return 0;

adj = (long)p->signal->oom_score_adj;
if (adj == OOM_SCORE_ADJ_MIN) {
task_unlock(p);
return 0;
}

/*
* The baseline for the badness score is the proportion of RAM that each
* task's rss, pagetable and swap space use.
*/
points = get_mm_rss(p->mm) + p->mm->nr_ptes +
get_mm_counter(p->mm, MM_SWAPENTS);
task_unlock(p);

/*
* Root processes get 3% bonus, just like the __vm_enough_memory()
* implementation used by LSMs.
*/
if (has_capability_noaudit(p, CAP_SYS_ADMIN))
adj -= 30;

/* Normalize to oom_score_adj units */
adj *= totalpages / 1000;
points += adj;

/*
* Never return 0 for an eligible task regardless of the root bonus and
* oom_score_adj (oom_score_adj can't be OOM_SCORE_ADJ_MIN here).
*/
return points > 0 ? points : 1;
}

# ps aux | grep mysqld
mysql    2196  1.6  2.1 623800 44876 ?        Ssl  09:42   0:00 /usr/sbin/mysqld

# cat /proc/2196/oom_score_adj
0
# echo -15 > /proc/2196/oom_score_adj

# sysctl -w vm.overcommit_memory=2

# echo "vm.overcommit_memory=2" >> /etc/sysctl.conf

# cat /proc/981/oom_score
18

# echo -15 > /proc/981/oom_score_adj
# cat /proc/981/oom_score
3

# vi oomscore.sh
#!/bin/bash
for proc in $(find /proc -maxdepth 1 -regex '/proc/[0-9]+'); do
printf "%2d %5d %s\n" \
"$(cat $proc/oom_score)" \
"$(basename $proc)" \
"$(cat $proc/cmdline | tr '\0' ' ' | head -c 50)"
done 2>/dev/null | sort -nr | head -n 10

# chmod +x oomscore.sh
# ./oomscore.sh
18   981 /usr/sbin/mysqld
4 31359 -bash
4 31056 -bash
1 31358 sshd: root@pts/6
1 31244 sshd: vpsee [priv]
1 31159 -bash
1 31158 sudo -i
1 31055 sshd: root@pts/3
1 30912 sshd: vpsee [priv]
1 29547 /usr/sbin/sshd -D