Messages in this thread | | | Date | Fri, 8 Jun 2012 09:57:09 +0300 | Subject | Re: [PATCH 0/5] Some vmevent fixes... | From | Pekka Enberg <> |
| |
On Fri, Jun 8, 2012 at 6:45 AM, KOSAKI Motohiro <kosaki.motohiro@gmail.com> wrote: > So, big design choice here. 1) vmevent is a just notification. it can't > guarantee to prevent oom. or 2) to implement some trick (e.g. reserved > memory for vmevent processes, kernel activity blocking until finish > memory returing, etc)
Yes, vmevent is only for notification and will not *guarantee* OOM prevention. It simply tries to provide hints early enough to the userspace to so that OOM can be avoided if possible.
| |