From: Vladimir Davydov <vdavydov@virtuozzo.com>
To: Michal Hocko <mhocko@kernel.org>
Cc: <linux-mm@kvack.org>,
Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>,
David Rientjes <rientjes@google.com>,
Oleg Nesterov <oleg@redhat.com>,
"Andrew Morton" <akpm@linux-foundation.org>,
LKML <linux-kernel@vger.kernel.org>
Subject: Re: [PATCH 3/6] mm, oom_adj: make sure processes sharing mm have same view of oom_score_adj
Date: Mon, 30 May 2016 11:47:53 +0300 [thread overview]
Message-ID: <20160530084753.GH26059@esperanza> (raw)
In-Reply-To: <20160530070705.GD22928@dhcp22.suse.cz>
On Mon, May 30, 2016 at 09:07:05AM +0200, Michal Hocko wrote:
> On Fri 27-05-16 19:18:21, Vladimir Davydov wrote:
> > On Fri, May 27, 2016 at 01:18:03PM +0200, Michal Hocko wrote:
> > ...
> > > @@ -1087,7 +1105,25 @@ static int __set_oom_adj(struct file *file, int oom_adj, bool legacy)
> > > unlock_task_sighand(task, &flags);
> > > err_put_task:
> > > put_task_struct(task);
> > > +
> > > + if (mm) {
> > > + struct task_struct *p;
> > > +
> > > + rcu_read_lock();
> > > + for_each_process(p) {
> > > + task_lock(p);
> > > + if (!p->vfork_done && process_shares_mm(p, mm)) {
> > > + p->signal->oom_score_adj = oom_adj;
> > > + if (!legacy && has_capability_noaudit(current, CAP_SYS_RESOURCE))
> > > + p->signal->oom_score_adj_min = (short)oom_adj;
> > > + }
> > > + task_unlock(p);
> >
> > I.e. you write to /proc/pid1/oom_score_adj and get
> > /proc/pid2/oom_score_adj updated if pid1 and pid2 share mm?
> > IMO that looks unexpected from userspace pov.
>
> How much different it is from threads in the same thread group?
> Processes sharing the mm without signals is a rather weird threading
> model isn't it?
I think so too. I wouldn't be surprised if it turned out that nobody had
ever used it. But may be there's someone out there who does.
> Currently we just lie to users about their oom_score_adj
> in this weird corner case.
Hmm, looks like a bug, but nobody has ever complained about it.
> The only exception was OOM_SCORE_ADJ_MIN
> where we really didn't kill the task but all other values are simply
> ignored in practice.
>
> > May be, we'd better add mm->oom_score_adj and set it to the min
> > signal->oom_score_adj over all processes sharing it? This would
> > require iterating over all processes every time oom_score_adj gets
> > updated, but that's a slow path.
>
> Not sure I understand. So you would prefer that mm->oom_score_adj might
> disagree with p->signal->oom_score_adj?
No, I wouldn't. I'd rather agree that oom_score_adj should be per mm,
because we choose the victim basing solely on mm stats.
What I mean is we don't touch p->signal->oom_score_adj of other tasks
sharing mm, but instead store minimal oom_score_adj over all tasks
sharing mm in the mm_struct whenever a task's oom_score_adj is modified.
And use mm->oom_score_adj instead of signal->oom_score_adj in oom killer
code. This would save us from any accusations of user API modifications
and it would also make the oom code a bit easier to follow IMHO.
next prev parent reply other threads:[~2016-05-30 9:21 UTC|newest]
Thread overview: 38+ messages / expand[flat|nested] mbox.gz Atom feed top
2016-05-26 12:40 [PATCH 0/5] Handle oom bypass more gracefully Michal Hocko
2016-05-26 12:40 ` [PATCH 1/6] mm, oom: do not loop over all tasks if there are no external tasks sharing mm Michal Hocko
2016-05-26 14:30 ` Tetsuo Handa
2016-05-26 14:59 ` Michal Hocko
2016-05-26 15:25 ` [PATCH 1/6] mm, oom: do not loop over all tasks if there are noexternal " Tetsuo Handa
2016-05-26 15:35 ` Michal Hocko
2016-05-26 16:14 ` [PATCH 1/6] mm, oom: do not loop over all tasks if there are no external " Tetsuo Handa
2016-05-27 6:45 ` Michal Hocko
2016-05-27 7:15 ` Michal Hocko
2016-05-27 8:03 ` Michal Hocko
2016-05-26 12:40 ` [PATCH 2/6] proc, oom_adj: extract oom_score_adj setting into a helper Michal Hocko
2016-05-26 12:40 ` [PATCH 3/6] mm, oom_adj: make sure processes sharing mm have same view of oom_score_adj Michal Hocko
2016-05-27 11:18 ` Michal Hocko
2016-05-27 16:18 ` Vladimir Davydov
2016-05-30 7:07 ` Michal Hocko
2016-05-30 8:47 ` Vladimir Davydov [this message]
2016-05-30 9:39 ` Michal Hocko
2016-05-30 10:26 ` Vladimir Davydov
2016-05-30 11:11 ` Michal Hocko
2016-05-30 12:19 ` Vladimir Davydov
2016-05-30 12:28 ` Michal Hocko
2016-05-26 12:40 ` [PATCH 4/6] mm, oom: skip over vforked tasks Michal Hocko
2016-05-27 16:48 ` Vladimir Davydov
2016-05-30 7:13 ` Michal Hocko
2016-05-30 9:52 ` Michal Hocko
2016-05-30 10:40 ` Vladimir Davydov
2016-05-30 10:53 ` Michal Hocko
2016-05-30 12:03 ` Michal Hocko
2016-05-26 12:40 ` [PATCH 5/6] mm, oom: kill all tasks sharing the mm Michal Hocko
2016-05-26 12:40 ` [PATCH 6/6] mm, oom: fortify task_will_free_mem Michal Hocko
2016-05-26 14:11 ` Tetsuo Handa
2016-05-26 14:23 ` Michal Hocko
2016-05-26 14:41 ` Tetsuo Handa
2016-05-26 14:56 ` Michal Hocko
2016-05-27 11:07 ` Michal Hocko
2016-05-27 16:00 ` [PATCH 0/5] Handle oom bypass more gracefully Michal Hocko
2016-05-30 13:05 [PATCH 0/6 -v2] " Michal Hocko
2016-05-30 13:05 ` [PATCH 3/6] mm, oom_adj: make sure processes sharing mm have same view of oom_score_adj Michal Hocko
2016-05-31 7:41 ` Michal Hocko
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20160530084753.GH26059@esperanza \
--to=vdavydov@virtuozzo.com \
--cc=akpm@linux-foundation.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=mhocko@kernel.org \
--cc=oleg@redhat.com \
--cc=penguin-kernel@I-love.SAKURA.ne.jp \
--cc=rientjes@google.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).