linux-kernel - Re: [PATCH] mm, vmscan: do not loop on too_many

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <20170710170933.GE7071@dhcp22.suse.cz>
Date:   Mon, 10 Jul 2017 19:09:34 +0200
From:   Michal Hocko <mhocko@...nel.org>
To:     Johannes Weiner <hannes@...xchg.org>
Cc:     Rik van Riel <riel@...hat.com>,
        Andrew Morton <akpm@...ux-foundation.org>,
        Mel Gorman <mgorman@...e.de>,
        Tetsuo Handa <penguin-kernel@...ove.SAKURA.ne.jp>,
        Vlastimil Babka <vbabka@...e.cz>, linux-mm@...ck.org,
        LKML <linux-kernel@...r.kernel.org>
Subject: Re: [PATCH] mm, vmscan: do not loop on too_many_isolated for ever

On Mon 10-07-17 12:58:59, Johannes Weiner wrote:
> On Mon, Jul 10, 2017 at 09:58:03AM -0400, Rik van Riel wrote:
> > On Mon, 2017-07-10 at 09:48 +0200, Michal Hocko wrote:
> > 
> > > Johannes and Rik had some concerns that this could lead to premature
> > > OOM kills. I agree with them that we need a better throttling
> > > mechanism. Until now we didn't give the issue described above a high
> > > priority because it usually required a really insane workload to
> > > trigger. But it seems that the issue can be reproduced also without
> > > having an insane number of competing threads [3].
> > 
> > My worries stand, but lets fix the real observed bug, and not worry
> > too much about the theoretical bug for now.
> > 
> > Acked-by: Rik van Riel <riel@...hat.com>
> 
> I agree with this.
> 
> Acked-by: Johannes Weiner <hannes@...xchg.org>

Thanks to both of you. Just to make it clear. I really do want to
address the throttling problem longterm properly. I do not have any
great ideas to be honest.  I am busy with other things so it might be
quite some time before I come up with something.

-- 
Michal Hocko
SUSE Labs