From: Michal Hocko <mhocko@kernel.org>
To: Johannes Weiner <hannes@cmpxchg.org>
Cc: Greg Thelen <gthelen@google.com>,
Shakeel Butt <shakeelb@google.com>,
Alexander Viro <viro@zeniv.linux.org.uk>,
Vladimir Davydov <vdavydov.dev@gmail.com>,
Andrew Morton <akpm@linux-foundation.org>,
Linux MM <linux-mm@kvack.org>,
linux-fsdevel@vger.kernel.org,
LKML <linux-kernel@vger.kernel.org>
Subject: Re: [PATCH] fs, mm: account filp and names caches to kmemcg
Date: Tue, 24 Oct 2017 18:22:13 +0200 [thread overview]
Message-ID: <20171024162213.n6jrpz3t5pldkgxy@dhcp22.suse.cz> (raw)
In-Reply-To: <20171024160637.GB32340@cmpxchg.org>
On Tue 24-10-17 12:06:37, Johannes Weiner wrote:
> On Fri, Oct 13, 2017 at 05:24:21PM +0200, Michal Hocko wrote:
> > Well, it actually occured to me that this would trigger the global oom
> > killer in case no memcg specific victim can be found which is definitely
> > not something we would like to do. This should work better. I am not
> > sure we can trigger this corner case but we should cover it and it
> > actually doesn't make the code much worse.
> > ---
> > diff --git a/mm/memcontrol.c b/mm/memcontrol.c
> > index d5f3a62887cf..7b370f070b82 100644
> > --- a/mm/memcontrol.c
> > +++ b/mm/memcontrol.c
> > @@ -1528,26 +1528,40 @@ static void memcg_oom_recover(struct mem_cgroup *memcg)
> >
> > static void mem_cgroup_oom(struct mem_cgroup *memcg, gfp_t mask, int order)
> > {
> > - if (!current->memcg_may_oom)
> > - return;
> > /*
> > * We are in the middle of the charge context here, so we
> > * don't want to block when potentially sitting on a callstack
> > * that holds all kinds of filesystem and mm locks.
> > *
> > - * Also, the caller may handle a failed allocation gracefully
> > - * (like optional page cache readahead) and so an OOM killer
> > - * invocation might not even be necessary.
> > + * cgroup v1 allowes sync users space handling so we cannot afford
> > + * to get stuck here for that configuration. That's why we don't do
> > + * anything here except remember the OOM context and then deal with
> > + * it at the end of the page fault when the stack is unwound, the
> > + * locks are released, and when we know whether the fault was overall
> > + * successful.
>
> How about
>
> "cgroup1 allows disabling the OOM killer and waiting for outside
> handling until the charge can succeed; remember the context and put
> the task to sleep at the end of the page fault when all locks are
> released."
OK
> and then follow it directly with the branch that handles this:
>
> if (memcg->oom_kill_disable) {
> css_get(&memcg->css);
> current->memcg_in_oom = memcg;
> ...
> return false;
> }
>
> return mem_cgroup_out_of_memory(memcg, mask, order);
>
> > + * On the other hand, in-kernel OOM killer allows for an async victim
> > + * memory reclaim (oom_reaper) and that means that we are not solely
> > + * relying on the oom victim to make a forward progress so we can stay
> > + * in the the try_charge context and keep retrying as long as there
> > + * are oom victims to select.
>
> I would put that part into try_charge, where that decision is made.
OK
> > *
> > - * That's why we don't do anything here except remember the
> > - * OOM context and then deal with it at the end of the page
> > - * fault when the stack is unwound, the locks are released,
> > - * and when we know whether the fault was overall successful.
> > + * Please note that mem_cgroup_oom_synchronize might fail to find a
> > + * victim and then we have rely on mem_cgroup_oom_synchronize otherwise
> > + * we would fall back to the global oom killer in pagefault_out_of_memory
>
> Ah, that's why... Ugh, that's really duct-tapey.
As you know, I really hate the #PF OOM path. We should get rid of it.
> > */
> > + if (!memcg->oom_kill_disable &&
> > + mem_cgroup_out_of_memory(memcg, mask, order))
> > + return true;
> > +
> > + if (!current->memcg_may_oom)
> > + return false;
> > css_get(&memcg->css);
> > current->memcg_in_oom = memcg;
> > current->memcg_oom_gfp_mask = mask;
> > current->memcg_oom_order = order;
> > +
> > + return false;
> > }
> >
> > /**
> > @@ -2007,8 +2021,11 @@ static int try_charge(struct mem_cgroup *memcg, gfp_t gfp_mask,
> >
> > mem_cgroup_event(mem_over_limit, MEMCG_OOM);
> >
> > - mem_cgroup_oom(mem_over_limit, gfp_mask,
> > - get_order(nr_pages * PAGE_SIZE));
> > + if (mem_cgroup_oom(mem_over_limit, gfp_mask,
> > + get_order(nr_pages * PAGE_SIZE))) {
> > + nr_retries = MEM_CGROUP_RECLAIM_RETRIES;
> > + goto retry;
> > + }
>
> As per the previous email, this has to goto force, otherwise we return
> -ENOMEM from syscalls once in a blue moon, which makes verification an
> absolute nightmare. The behavior should be reliable, without weird p99
> corner cases.
>
> I think what we should be doing here is: if a charge fails, set up an
> oom context and force the charge; add mem_cgroup_oom_synchronize() to
> the end of syscalls and kernel-context faults.
What would prevent a runaway in case the only process in the memcg is
oom unkillable then?
--
Michal Hocko
SUSE Labs
next prev parent reply other threads:[~2017-10-24 16:22 UTC|newest]
Thread overview: 52+ messages / expand[flat|nested] mbox.gz Atom feed top
2017-10-05 22:21 [PATCH] fs, mm: account filp and names caches to kmemcg Shakeel Butt
2017-10-06 7:59 ` Michal Hocko
2017-10-06 19:33 ` Shakeel Butt
2017-10-09 6:24 ` Michal Hocko
2017-10-09 17:52 ` Greg Thelen
2017-10-09 18:04 ` Michal Hocko
2017-10-09 18:17 ` Michal Hocko
2017-10-10 9:10 ` Michal Hocko
2017-10-10 22:21 ` Shakeel Butt
2017-10-11 9:09 ` Michal Hocko
2017-10-09 20:26 ` Johannes Weiner
2017-10-10 9:14 ` Michal Hocko
2017-10-10 14:17 ` Johannes Weiner
2017-10-10 14:24 ` Michal Hocko
2017-10-12 19:03 ` Johannes Weiner
2017-10-12 23:57 ` Greg Thelen
2017-10-13 6:51 ` Michal Hocko
2017-10-13 6:35 ` Michal Hocko
2017-10-13 7:00 ` Michal Hocko
2017-10-13 15:24 ` Michal Hocko
2017-10-24 12:18 ` Michal Hocko
2017-10-24 17:54 ` Johannes Weiner
2017-10-24 16:06 ` Johannes Weiner
2017-10-24 16:22 ` Michal Hocko [this message]
2017-10-24 17:23 ` Johannes Weiner
2017-10-24 17:55 ` Michal Hocko
2017-10-24 18:58 ` Johannes Weiner
2017-10-24 20:15 ` Michal Hocko
2017-10-25 6:51 ` Greg Thelen
2017-10-25 7:15 ` Michal Hocko
2017-10-25 13:11 ` Johannes Weiner
2017-10-25 14:12 ` Michal Hocko
2017-10-25 16:44 ` Johannes Weiner
2017-10-25 17:29 ` Michal Hocko
2017-10-25 18:11 ` Johannes Weiner
2017-10-25 19:00 ` Michal Hocko
2017-10-25 21:13 ` Johannes Weiner
2017-10-25 22:49 ` Greg Thelen
2017-10-26 7:49 ` Michal Hocko
2017-10-26 12:45 ` Tetsuo Handa
2017-10-26 14:31 ` Johannes Weiner
2017-10-26 19:56 ` Greg Thelen
2017-10-27 8:20 ` Michal Hocko
2017-10-27 20:50 ` Shakeel Butt
2017-10-30 8:29 ` Michal Hocko
2017-10-30 19:28 ` Shakeel Butt
2017-10-31 8:00 ` Michal Hocko
2017-10-31 16:49 ` Johannes Weiner
2017-10-31 18:50 ` Michal Hocko
2017-10-24 15:45 ` Johannes Weiner
2017-10-24 16:30 ` Michal Hocko
2017-10-10 23:32 ` Al Viro
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=20171024162213.n6jrpz3t5pldkgxy@dhcp22.suse.cz \
--to=mhocko@kernel.org \
--cc=akpm@linux-foundation.org \
--cc=gthelen@google.com \
--cc=hannes@cmpxchg.org \
--cc=linux-fsdevel@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=shakeelb@google.com \
--cc=vdavydov.dev@gmail.com \
--cc=viro@zeniv.linux.org.uk \
/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).