Messages in this thread | | | Subject | Re: Improving OOM killer | From | Minchan Kim <> | Date | Thu, 04 Feb 2010 01:06:18 +0900 |
| |
On Thu, 2010-02-04 at 00:00 +0900, Minchan Kim wrote: > On Wed, 2010-02-03 at 17:55 +0530, Balbir Singh wrote: > > * Lubos Lunak <l.lunak@suse.cz> [2010-02-03 13:10:27]: > >> > I don't understand how this matters. Overcommit is memory for which address > > > space has been allocated but not actual memory, right? Then that's exactly > > > what I'm claiming is wrong and am trying to reverse. Currently OOM killer > > > takes this into account because it uses VmSize, but IMO it shouldn't - if a > > > process does malloc(400M) but then it uses only a tiny fraction of that, in > > > the case of memory shortage killing that process does not solve anything in > > > practice. > > > > We have a way of tracking commmitted address space, which is more > > sensible than just allocating memory and is used for tracking > > overcommit. I was suggesting that, that might be a better approach. > > Yes. It does make sense. At least total_vm doesn't care about > MAP_NORESERVE case. But unfortunately, it's a per CPU not per Process.
Sorry for confusing. It was opposite. I slept :) The commited as doesn't care about MAP_NORESERVE case. But it definitely charges memory. so I think total_vm is better than committed as if we really have to use vmsize heuristic continuously.
But I am not sure that i understand your point about overcommit policy.
-- Kind regards, Minchan Kim
| |