Commit daaf1e68874c078a15ae6ae827751839c4d81739
Committed by
Linus Torvalds
1 parent
1080d7a303
Exists in
master
and in
7 other branches
memcg: handle panic_on_oom=always case
Presently, if panic_on_oom=2, the whole system panics even if the oom happend in some special situation (as cpuset, mempolicy....). Then, panic_on_oom=2 means painc_on_oom_always. Now, memcg doesn't check panic_on_oom flag. This patch adds a check. BTW, how it's useful ? kdump+panic_on_oom=2 is the last tool to investigate what happens in oom-ed system. When a task is killed, the sysytem recovers and there will be few hint to know what happnes. In mission critical system, oom should never happen. Then, panic_on_oom=2+kdump is useful to avoid next OOM by knowing precise information via snapshot. TODO: - For memcg, it's for isolate system's memory usage, oom-notiifer and freeze_at_oom (or rest_at_oom) should be implemented. Then, management daemon can do similar jobs (as kdump) or taking snapshot per cgroup. Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Balbir Singh <balbir@linux.vnet.ibm.com> Cc: David Rientjes <rientjes@google.com> Cc: Nick Piggin <npiggin@suse.de> Reviewed-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Showing 3 changed files with 10 additions and 2 deletions Side-by-side Diff
Documentation/cgroups/memory.txt
... | ... | @@ -182,6 +182,8 @@ |
182 | 182 | NOTE: Reclaim does not work for the root cgroup, since we cannot set any |
183 | 183 | limits on the root cgroup. |
184 | 184 | |
185 | +Note2: When panic_on_oom is set to "2", the whole system will panic. | |
186 | + | |
185 | 187 | 2. Locking |
186 | 188 | |
187 | 189 | The memory controller uses the following hierarchy |
... | ... | @@ -379,7 +381,8 @@ |
379 | 381 | NOTE1: Enabling/disabling will fail if the cgroup already has other |
380 | 382 | cgroups created below it. |
381 | 383 | |
382 | -NOTE2: This feature can be enabled/disabled per subtree. | |
384 | +NOTE2: When panic_on_oom is set to "2", the whole system will panic in | |
385 | +case of an oom event in any cgroup. | |
383 | 386 | |
384 | 387 | 7. Soft limits |
385 | 388 |
Documentation/sysctl/vm.txt
... | ... | @@ -573,11 +573,14 @@ |
573 | 573 | may be not fatal yet. |
574 | 574 | |
575 | 575 | If this is set to 2, the kernel panics compulsorily even on the |
576 | -above-mentioned. | |
576 | +above-mentioned. Even oom happens under memory cgroup, the whole | |
577 | +system panics. | |
577 | 578 | |
578 | 579 | The default value is 0. |
579 | 580 | 1 and 2 are for failover of clustering. Please select either |
580 | 581 | according to your policy of failover. |
582 | +panic_on_oom=2+kdump gives you very strong tool to investigate | |
583 | +why oom happens. You can get snapshot. | |
581 | 584 | |
582 | 585 | ============================================================= |
583 | 586 |
mm/oom_kill.c