Received-SPF: pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) client-ip=209.132.180.67;
MIME-Version: 1.0
References: <156431697805.3170.6377599347542228221.stgit@buzz>
 <20190729091738.GF9330@dhcp22.suse.cz> <3d6fc779-2081-ba4b-22cf-be701d617bb4@yandex-team.ru>
 <20190729103307.GG9330@dhcp22.suse.cz> <CAHbLzkrdj-O2uXwM8ujm90OcgjyR4nAiEbFtRGe7SOoY_fs=BA@mail.gmail.com>
 <20190729184850.GH9330@dhcp22.suse.cz> <CAHbLzkp9xFV2sE0TdKfWNRVcAwaYNKwDugRiBBoEKx6A_Hr3Jw@mail.gmail.com>
 <20190802093507.GF6461@dhcp22.suse.cz> <CAHbLzkrjh7KEvdfXackaVy8oW5CU=UaBucERffxcUorgq1vdoA@mail.gmail.com>
 <20190805143239.GS7597@dhcp22.suse.cz>
In-Reply-To: <20190805143239.GS7597@dhcp22.suse.cz>
From:   Shakeel Butt <shakeelb@google.com>
Date:   Mon, 5 Aug 2019 12:24:58 -0700
Message-ID: <CALvZod5upYA2UgUSWJjrL7K=zifhwwvK5M_gUakPhf2fP-3HxA@mail.gmail.com>
Subject: Re: [PATCH RFC] mm/memcontrol: reclaim severe usage over high limit
 in get_user_pages loop
To:     Michal Hocko <mhocko@kernel.org>
Cc:     Yang Shi <shy828301@gmail.com>,
        Konstantin Khlebnikov <khlebnikov@yandex-team.ru>,
        Linux MM <linux-mm@kvack.org>,
        Linux Kernel Mailing List <linux-kernel@vger.kernel.org>,
        Cgroups <cgroups@vger.kernel.org>,
        Vladimir Davydov <vdavydov.dev@gmail.com>,
        Johannes Weiner <hannes@cmpxchg.org>
Content-Type: text/plain; charset="UTF-8"
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

On Mon, Aug 5, 2019 at 7:32 AM Michal Hocko <mhocko@kernel.org> wrote:
>
> On Fri 02-08-19 11:56:28, Yang Shi wrote:
> > On Fri, Aug 2, 2019 at 2:35 AM Michal Hocko <mhocko@kernel.org> wrote:
> > >
> > > On Thu 01-08-19 14:00:51, Yang Shi wrote:
> > > > On Mon, Jul 29, 2019 at 11:48 AM Michal Hocko <mhocko@kernel.org> wrote:
> > > > >
> > > > > On Mon 29-07-19 10:28:43, Yang Shi wrote:
> > > > > [...]
> > > > > > I don't worry too much about scale since the scale issue is not unique
> > > > > > to background reclaim, direct reclaim may run into the same problem.
> > > > >
> > > > > Just to clarify. By scaling problem I mean 1:1 kswapd thread to memcg.
> > > > > You can have thousands of memcgs and I do not think we really do want
> > > > > to create one kswapd for each. Once we have a kswapd thread pool then we
> > > > > get into a tricky land where a determinism/fairness would be non trivial
> > > > > to achieve. Direct reclaim, on the other hand is bound by the workload
> > > > > itself.
> > > >
> > > > Yes, I agree thread pool would introduce more latency than dedicated
> > > > kswapd thread. But, it looks not that bad in our test. When memory
> > > > allocation is fast, even though dedicated kswapd thread can't catch
> > > > up. So, such background reclaim is best effort, not guaranteed.
> > > >
> > > > I don't quite get what you mean about fairness. Do you mean they may
> > > > spend excessive cpu time then cause other processes starvation? I
> > > > think this could be mitigated by properly organizing and setting
> > > > groups. But, I agree this is tricky.
> > >
> > > No, I meant that the cost of reclaiming a unit of charges (e.g.
> > > SWAP_CLUSTER_MAX) is not constant and depends on the state of the memory
> > > on LRUs. Therefore any thread pool mechanism would lead to unfair
> > > reclaim and non-deterministic behavior.
> >
> > Yes, the cost depends on the state of pages, but I still don't quite
> > understand what does "unfair" refer to in this context. Do you mean
> > some cgroups may reclaim much more than others?
>
> > Or the work may take too long so it can't not serve other cgroups in time?
>
> exactly.
>

How about allowing the users to implement their own user space kswapd?
A memcg interface similar to MADV_PAGEOUT. Users can register for
MEMCG_HIGH notification (it needs some modification) and on receiving
the notification, the uswapd (User's kswapd) will trigger reclaim
through memory.pageout (or memory.try_to_free_pages). One can argue
why not just use MADV_PAGEOUT? In real workload, a job can be a
combination of different sub-jobs and most probably may not know the
importance of the memory layout of the tasks of the sub-jobs. So, a
memcg level interface makes more sense there.

Shakeel