On Tue, 17 Aug 2010 20:43:10 -0700 (PDT)
David Rientjes <rientjes@xxxxxxxxxx> wrote:
> On Wed, 18 Aug 2010, KAMEZAWA Hiroyuki wrote:
>
> > > I was thinking about adding an "unsinged long oom_kill_disable_count" to
> > > struct mm_struct that would atomically increment anytime a task attached
> > > to it had a signal->oom_score_adj of OOM_SCORE_ADJ_MIN.
> > >
> > > The proc handler when changing /proc/pid/oom_score_adj would inc or dec
> > > the counter depending on the new value, and exit_mm() would dec the
> > > counter if current->signal->oom_score_adj is OOM_SCORE_ADJ_MIN.
> > >
> > > What do you think?
> > >
> >
> > Hmm. I want to make hooks to "exit" small.
> >
>
>
> Is it worth adding
>
> if (unlikely(current->signal->oom_score_adj == OOM_SCORE_ADJ_MIN))
> atomic_dec(¤t->mm->oom_disable_count);
>
> to exit_mm() under task_lock() to avoid the O(n^2) select_bad_process() on
> oom? Or do you think that's too expensive?
>
Hmm, if this coutner is changed only under down_write(mmap_sem),
simple 'int' counter is enough quick.
> > One idea is.
> >
> > add a new member
> > mm->unkiilable_by_oom_jiffies.
> >
> > And add
> > > +static bool is_mm_unfreeable(struct mm_struct *mm)
> > > +{
> > > + struct task_struct *p;
> > > +
> > if (mm->unkillable_by_oom_jiffies < jiffies)
> > return true;
> >
> > > + for_each_process(p)
> > > + if (p->mm == mm && !(p->flags & PF_KTHREAD) &&
> > > + p->signal->oom_score_adj == OOM_SCORE_ADJ_MIN)
> >
> > mm->unkillable_by_oom_jiffies = jiffies + HZ;
> >
> > > + return true;
> > > + return false;
> > > +}+static bool is_mm_unfreeable(struct mm_struct *mm)
> >
>
> This probably isn't fast enough for the common case, which is when no
> tasks for "mm" have an oom_score_adj of OOM_SCORE_ADJ_MIN, since it still
> iterates through every task.
>
you're right.
Thanks,
-Kame
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@xxxxxxxxxx For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@xxxxxxxxx";> email@xxxxxxxxx </a>