Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
MIME-Version: 1.0
References: <20220623000530.1194226-1-yosryahmed@google.com> <20220622171624.fc7de8d0ab18a5cf663f8ab8@linux-foundation.org>
In-Reply-To: <20220622171624.fc7de8d0ab18a5cf663f8ab8@linux-foundation.org>
From:   Yosry Ahmed <yosryahmed@google.com>
Date:   Wed, 22 Jun 2022 17:24:55 -0700
Message-ID: <CAJD7tkag2sj86FXnMb+v4GhDJWOZ_tNpMMCde8faEgqdQ9=uEg@mail.gmail.com>
Subject: Re: [PATCH] mm: vmpressure: don't count userspace-induced reclaim as
 memory pressure
To:     Andrew Morton <akpm@linux-foundation.org>
Cc:     Johannes Weiner <hannes@cmpxchg.org>,
        Michal Hocko <mhocko@kernel.org>,
        Roman Gushchin <roman.gushchin@linux.dev>,
        Shakeel Butt <shakeelb@google.com>,
        Muchun Song <songmuchun@bytedance.com>,
        Matthew Wilcox <willy@infradead.org>,
        Vlastimil Babka <vbabka@suse.cz>,
        David Hildenbrand <david@redhat.com>,
        Miaohe Lin <linmiaohe@huawei.com>, NeilBrown <neilb@suse.de>,
        Alistair Popple <apopple@nvidia.com>,
        Suren Baghdasaryan <surenb@google.com>,
        Peter Xu <peterx@redhat.com>,
        Linux Kernel Mailing List <linux-kernel@vger.kernel.org>,
        Cgroups <cgroups@vger.kernel.org>, Linux-MM <linux-mm@kvack.org>
Content-Type: text/plain; charset="UTF-8"
Precedence: bulk

On Wed, Jun 22, 2022 at 5:16 PM Andrew Morton <akpm@linux-foundation.org> wrote:
>
> On Thu, 23 Jun 2022 00:05:30 +0000 Yosry Ahmed <yosryahmed@google.com> wrote:
>
> > Commit e22c6ed90aa9 ("mm: memcontrol: don't count limit-setting reclaim
> > as memory pressure") made sure that memory reclaim that is induced by
> > userspace (limit-setting, proactive reclaim, ..) is not counted as
> > memory pressure for the purposes of psi.
> >
> > Instead of counting psi inside try_to_free_mem_cgroup_pages(), callers
> > from try_charge() and reclaim_high() wrap the call to
> > try_to_free_mem_cgroup_pages() with psi handlers.
> >
> > However, vmpressure is still counted in these cases where reclaim is
> > directly induced by userspace. This patch makes sure vmpressure is not
> > counted in those operations, in the same way as psi. Since vmpressure
> > calls need to happen deeper within the reclaim path, the same approach
> > could not be followed. Hence, a new "controlled" flag is added to struct
> > scan_control to flag a reclaim operation that is controlled by
> > userspace. This flag is set by limit-setting and proactive reclaim
> > operations, and is used to count vmpressure correctly.
> >
> > To prevent future divergence of psi and vmpressure, commit e22c6ed90aa9
> > ("mm: memcontrol: don't count limit-setting reclaim as memory pressure")
> > is effectively reverted and the same flag is used to control psi as
> > well.
>
> I'll await reviewer input on this, but I can always do trivia!

Thanks for taking a look so quickly, will address and send v2 soon!

>
> > @@ -3502,6 +3497,8 @@ unsigned long mem_cgroup_soft_limit_reclaim(pg_data_t *pgdat, int order,
> >  static int mem_cgroup_force_empty(struct mem_cgroup *memcg)
> >  {
> >       int nr_retries = MAX_RECLAIM_RETRIES;
> > +     unsigned int reclaim_options = MEMCG_RECLAIM_CONTROLLED |
> > +             MEMCG_RECLAIM_MAY_SWAP;
>
> If it doesn't fit, it's nicer to do
>
>         unsigned int reclaim_options;
>         ...
>
>         reclaim_options = MEMCG_RECLAIM_CONTROLLED | MEMCG_RECLAIM_MAY_SWAP;
>
> (several places)
>
> > @@ -3751,6 +3757,7 @@ unsigned long try_to_free_pages(struct zonelist *zonelist, int order,
> >               .may_writepage = !laptop_mode,
> >               .may_unmap = 1,
> >               .may_swap = 1,
> > +             .controlled = 0,
> >       };
>
> Let's just skip all these initializations to zero, let the compiler take
> care of it.
>
> > @@ -4095,6 +4112,7 @@ static int balance_pgdat(pg_data_t *pgdat, int order, int highest_zoneidx)
> >               .gfp_mask = GFP_KERNEL,
> >               .order = order,
> >               .may_unmap = 1,
> > +             .controlled = 0,
> >       };
> >
> >       set_task_reclaim_state(current, &sc.reclaim_state);
> > @@ -4555,6 +4573,7 @@ unsigned long shrink_all_memory(unsigned long nr_to_reclaim)
> >               .may_unmap = 1,
> >               .may_swap = 1,
> >               .hibernation_mode = 1,
> > +             .controlled = 0,
> >       };
> >       struct zonelist *zonelist = node_zonelist(numa_node_id(), sc.gfp_mask);
> >       unsigned long nr_reclaimed;
> > @@ -4707,6 +4726,7 @@ static int __node_reclaim(struct pglist_data *pgdat, gfp_t gfp_mask, unsigned in
> >               .may_unmap = !!(node_reclaim_mode & RECLAIM_UNMAP),
> >               .may_swap = 1,
> >               .reclaim_idx = gfp_zone(gfp_mask),
> > +             .controlled = 0,
> >       };
> >       unsigned long pflags;
>
>