On Tue, 19 November 2013 14:14:00 +0100, Michal Hocko wrote: > > We have basically ended up with 3 options AFAIR: > 1) allow memcg approach (memcg.oom_control) on the root level > for both OOM notification and blocking OOM killer and handle > the situation from the userspace same as we can for other > memcgs. > 2) allow modules to hook into OOM killer path and take the > appropriate action. > 3) create a generic filtering mechanism which could be > controlled from the userspace by a set of rules (e.g. > something analogous to packet filtering). One ancient option I sometime miss was this: - Kill the biggest process. Doesn't always make the optimal choice, but neither did any of the refinements. But it had the nice advantage that even I could predict which bad choice it would make and why. Every bit of sophistication means that you still get it wrong sometimes, but in less obvious and more annoying ways. Then again, an alternative I actually use in production is to reboot the machine on OOM. Again, very simple, very blunt and very predictable. Jörn -- No art, however minor, demands less than total dedication if you want to excel in it. -- Leon Battista Alberti -- To unsubscribe, send a message with 'unsubscribe linux-mm' in the body to majordomo@xxxxxxxxx. For more info on Linux MM, see: http://www.linux-mm.org/ . Don't email: <a href=mailto:"dont@xxxxxxxxx";> email@xxxxxxxxx </a>