Re: oomkillers gone wild.

[Dave Jones]

On Sat, Jun 09, 2012 at 11:21:47PM -0400, KOSAKI Motohiro wrote:
 > (6/9/12 10:21 PM), David Rientjes wrote:
 > > On Fri, 8 Jun 2012, Dave Jones wrote:
 > >
 > >>   >  On a system not under oom conditions, i.e. before you start trinity, can
 > >>   >  you send the output of
 > >>   >
 > >>   >  	cat /proc/$(pidof dbus-daemon)/oom_score{_adj,}
 > >>   >  	grep RSS /proc/$(pidof dbus-daemon)/status
 > >>
 > >> # cat /proc/$(pidof dbus-daemon)/oom_score{_adj,}
 > >> -900
 > >> 7441500919753
 > >> # grep RSS /proc/$(pidof dbus-daemon)/status
 > >> VmRSS:	    1660 kB
 > >
 > > I'm suspecting you don't have my patch that changes the type of the
 > > automatic variable in oom_badness() to signed.  Could you retry this with
 > > that patch or pull 3.5-rc2 which already includes it?

that was with the unsigned long -> long patch.

 > Yes. Dave (Jones), As far as parsed your log, you are using x86_64, right?

yes.

 > As far as my testing, current linus tree works fine at least normal case.
 > please respin.

To double check, here it is in rc2 (which has that patch)..

$ uname -r
3.5.0-rc2+
$ cat /proc/$(pidof dbus-daemon)/oom_score{_adj,}
-900
7441500919753
$ grep RSS /proc/$(pidof dbus-daemon)/status
VmRSS:	    1604 kB

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/