Messages in this thread |  | | Date | Thu, 12 May 2011 09:13:54 +0900 | | Subject | Re: OOM Killer don't works at all if the system have >gigabytes memory (was Re: [PATCH] mm: check zone->all_unreclaimable in all_unreclaimable()) | | From | Minchan Kim <> |
| |
On Thu, May 12, 2011 at 5:34 AM, David Rientjes <rientjes@google.com> wrote: > On Tue, 10 May 2011, CAI Qian wrote: > >> Sure, I saw there were some discussion going on between you and David >> about your patches. Does it make more sense for me to test those after >> you have settled down technical arguments? >> > > Something like the following (untested) patch should fix the issue by > simply increasing the range of a task's badness from 0-1000 to 0-10000. > > There are other things to fix like the tasklist dump output and > documentation, but this shows how easy it is to increase the resolution of > the scoring. (This patch also includes a change to only give root
It does make sense. I think raising resolution should be a easy way to fix the problem.
> processes a 1% bonus for every 30% of memory they use as proposed > earlier.)
I didn't follow earlier your suggestion. But it's not formal patch so I expect if you send formal patch to merge, you would write down the rationale.
> > > diff --git a/mm/oom_kill.c b/mm/oom_kill.c > --- a/mm/oom_kill.c > +++ b/mm/oom_kill.c > @@ -160,7 +160,7 @@ unsigned int oom_badness(struct task_struct *p, struct mem_cgroup *mem, > */ > if (p->flags & PF_OOM_ORIGIN) { > task_unlock(p); > - return 1000; > + return 10000; > } > > /* > @@ -177,32 +177,32 @@ unsigned int oom_badness(struct task_struct *p, struct mem_cgroup *mem, > points = get_mm_rss(p->mm) + p->mm->nr_ptes; > points += get_mm_counter(p->mm, MM_SWAPENTS); > > - points *= 1000; > + points *= 10000; > points /= totalpages; > task_unlock(p); > > /* > - * Root processes get 3% bonus, just like the __vm_enough_memory() > - * implementation used by LSMs. > + * Root processes get 1% bonus per 30% memory used for a total of 3% > + * possible just like LSMs. > */ > if (has_capability_noaudit(p, CAP_SYS_ADMIN)) > - points -= 30; > + points -= 100 * (points / 3000); > > /* > * /proc/pid/oom_score_adj ranges from -1000 to +1000 such that it may > * either completely disable oom killing or always prefer a certain > * task. > */ > - points += p->signal->oom_score_adj; > + points += p->signal->oom_score_adj * 10; > > /* > * Never return 0 for an eligible task that may be killed since it's > - * possible that no single user task uses more than 0.1% of memory and > + * possible that no single user task uses more than 0.01% of memory and > * no single admin tasks uses more than 3.0%. > */ > if (points <= 0) > return 1; > - return (points < 1000) ? points : 1000; > + return (points < 10000) ? points : 10000; > } > > /* > @@ -314,7 +314,7 @@ static struct task_struct *select_bad_process(unsigned int *ppoints, > */ > if (p == current) { > chosen = p; > - *ppoints = 1000; > + *ppoints = 10000;
Scattering constant value isn't good. You are proving it now. I think you did it since this is not a formal patch. I expect you will define new value (ex, OOM_INTERNAL_MAX_SCORE or whatever)
-- Kind regards, Minchan Kim -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
|  |