Re: [PATCH 2/5] Revert "oom: give the dying task a higher priority"

["Luis Claudio R. Goncalves" <lclaudio@uudg.org>]

On Wed, Mar 23, 2011 at 04:42:29PM +0900, KAMEZAWA Hiroyuki wrote:
| On Tue, 22 Mar 2011 20:06:48 +0900 (JST)
| KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> wrote:
| 
| > This reverts commit 93b43fa55088fe977503a156d1097cc2055449a2.
| > 
| > The commit dramatically improve oom killer logic when fork-bomb
| > occur. But, I've found it has nasty corner case. Now cpu cgroup
| > has strange default RT runtime. It's 0! That said, if a process
| > under cpu cgroup promote RT scheduling class, the process never
| > run at all.
| > 
| > Eventually, kernel may hang up when oom kill occur.
| > 
| > The author need to resubmit it as adding knob and disabled
| > by default if he really need this feature.
| > 
| > Cc: Luis Claudio R. Goncalves <lclaudio@uudg.org>
| > Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
| 
| Acked-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>

The original patch was written to fix an issue observed in 2.6.24.7-rt.
As the logic sounded useful, I ported it to upstream. Anyway,I am trying
a few ideas to rework that patch. In the meantime, I'm pretty fine with
reverting the commit.

Acked-by: Luis Claudio R. Gonçalves <lgoncalv@uudg.org>

-- 
[ Luis Claudio R. Goncalves                    Bass - Gospel - RT ]
[ Fingerprint: 4FDD B8C4 3C59 34BD 8BE9  2696 7203 D980 A448 C8F8 ]