Received-SPF: pass (google.com: domain of linux-kernel+bounces-34635-linux.lists.archive=gmail.com@vger.kernel.org designates 147.75.199.223 as permitted sender) client-ip=147.75.199.223;
Precedence: bulk
MIME-Version: 1.0
References: <20240121214413.833776-1-tjmercier@google.com>
In-Reply-To: <20240121214413.833776-1-tjmercier@google.com>
From: Yu Zhao <yuzhao@google.com>
Date: Mon, 22 Jan 2024 19:24:56 -0700
Message-ID: <CAOUHufa9BySrKZ5ws9xJoEsdUfbErb4V=2=JSm-dB9B7zMyJbQ@mail.gmail.com>
Subject: Re: [PATCH] Revert "mm:vmscan: fix inaccurate reclaim during
 proactive reclaim"
To: "T.J. Mercier" <tjmercier@google.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>, Michal Hocko <mhocko@kernel.org>, 
	Roman Gushchin <roman.gushchin@linux.dev>, Shakeel Butt <shakeelb@google.com>, 
	Muchun Song <muchun.song@linux.dev>, Andrew Morton <akpm@linux-foundation.org>, android-mm@google.com, 
	yangyifei03@kuaishou.com, cgroups@vger.kernel.org, linux-mm@kvack.org, 
	linux-kernel@vger.kernel.org
Content-Type: text/plain; charset="UTF-8"
Content-Transfer-Encoding: quoted-printable

On Sun, Jan 21, 2024 at 2:44=E2=80=AFPM T.J. Mercier <tjmercier@google.com>=
 wrote:
>
> This reverts commit 0388536ac29104a478c79b3869541524caec28eb.
>
> Proactive reclaim on the root cgroup is 10x slower after this patch when
> MGLRU is enabled, and completion times for proactive reclaim on much
> smaller non-root cgroups take ~30% longer (with or without MGLRU). With
> root reclaim before the patch, I observe average reclaim rates of
> ~70k pages/sec before try_to_free_mem_cgroup_pages starts to fail and
> the nr_retries counter starts to decrement, eventually ending the
> proactive reclaim attempt. After the patch the reclaim rate is
> consistently ~6.6k pages/sec due to the reduced nr_pages value causing
> scan aborts as soon as SWAP_CLUSTER_MAX pages are reclaimed. The
> proactive reclaim doesn't complete after several minutes because
> try_to_free_mem_cgroup_pages is still capable of reclaiming pages in
> tiny SWAP_CLUSTER_MAX page chunks and nr_retries is never decremented.
>
> The docs for memory.reclaim say, "the kernel can over or under reclaim
> from the target cgroup" which this patch was trying to fix. Revert it
> until a less costly solution is found.
>
> Signed-off-by: T.J. Mercier <tjmercier@google.com>

Fixes: 0388536ac291 ("mm:vmscan: fix inaccurate reclaim during
proactive reclaim")
Cc: <stable@vger.kernel.org>