Hi,
I was just wondering the process of the patch "oom reaper: handle
mlocked pages".
links:
https://lore.kernel.org/linux-mm/1454505240-23446-3-git-send-email-mhocko@xxxxxxxxxx/
https://lore.kernel.org/linux-mm/20160223132157.GD14178@xxxxxxxxxxxxxx/
In linux master, we found that when we start a process and alloc large
memory with MAP_LOCKED, the oom will triggered and kill some system
process such as sshd ,rsyslog etc.
...
[ 45.110665] Out of memory: Killed process 2551 (oom)
total-vm:1035324kB, anon-rss:1028196kB, file-rss:704kB, shmem-rss:0kB,
UID:0 pgtables:2056kB oom_score_adj:1000
[ 45.115303] Out of memory: Killed process 2554 (oom)
total-vm:1025084kB, anon-rss:1015596kB, file-rss:388kB, shmem-rss:0kB,
UID:0 pgtables:2032kB oom_score_adj:1000
[ 45.115685] Out of memory: Killed process 2553 (oom)
total-vm:953404kB, anon-rss:947748kB, file-rss:388kB, shmem-rss:0kB,
UID:0 pgtables:1896kB oom_score_adj:1000
[ 45.116031] Out of memory: Killed process 2552 (oom)
total-vm:789564kB, anon-rss:783272kB, file-rss:388kB, shmem-rss:0kB,
UID:0 pgtables:1576kB oom_score_adj:1000
[ 45.117199] Out of memory: Killed process 2523 (sshd)
total-vm:77052kB, anon-rss:804kB, file-rss:4672kB, shmem-rss:4kB, UID:0
pgtables:196kB oom_score_adj:0
[ 45.120936] Out of memory: Killed process 2526 (bash)
total-vm:17792kB, anon-rss:1180kB, file-rss:2868kB, shmem-rss:0kB, UID:0
pgtables:76kB oom_score_adj:0
...
the process demo is:
...
#define ALLOC_SIZE (10 * 1024 * 1024)
while (1) {
addr = mmap(NULL, ALLOC_SIZE, PROT_READ | PROT_WRITE, MAP_PRIVATE |
MAP_ANONYMOUS | MAP_LOCKED, -1, 0);
if (addr != MAP_FAILED)
memset(addr, 1, ALLOC_SIZE);
}
...
And we found that when the oom_reaper is done but the memory is still high:
[ 45.115685] Out of memory: Killed process 2553 (oom)
total-vm:953404kB, anon-rss:947748kB, file-rss:388kB, shmem-rss:0kB,
UID:0 pgtables:1896kB oom_score_adj:1000
[ 45.115739] oom_reaper: reaped process 2553 (oom), now
anon-rss:947708kB, file-rss:0kB, shmem-rss:0kB
This is because the bad proccess which recieved SIGKILL is unlocking the
mem to exit which needs more time. And the next oom is triggered to kill
the other system process.
Kind regards,
Yongqiang Liu
