Received-SPF: pass (google.com: domain of linux-kernel+bounces-50497-linux.lists.archive=gmail.com@vger.kernel.org designates 147.75.80.249 as permitted sender) client-ip=147.75.80.249;
Date: Fri, 2 Feb 2024 20:46:56 +0100
From: Michal =?utf-8?Q?Koutn=C3=BD?= <mkoutny@suse.com>
To: "T.J. Mercier" <tjmercier@google.com>
Cc: Efly Young <yangyifei03@kuaishou.com>, hannes@cmpxchg.org, 
	akpm@linux-foundation.org, android-mm@google.com, cgroups@vger.kernel.org, 
	linux-kernel@vger.kernel.org, linux-mm@kvack.org, mhocko@kernel.org, muchun.song@linux.dev, 
	roman.gushchin@linux.dev, shakeelb@google.com, yuzhao@google.com
Subject: Re: Re: Re: [PATCH] mm: memcg: Use larger chunks for proactive
 reclaim
Message-ID: <bycpbzvo2fpd2qrrl7ipnzrsyun7hg5tjlqouafuosxxlxfml5@vpbl6kl74hx5>
References: <20240201153428.GA307226@cmpxchg.org>
 <20240202050247.45167-1-yangyifei03@kuaishou.com>
 <vofidz4pzybyxoozjrmuqhycm2aji6inp6lkgd3fakyv5jqsjr@pleoj7ljsxhi>
 <CABdmKX2KsxVExVWzysc_fQagGkYWhqRF00KxNxjpVWovHHip+Q@mail.gmail.com>
Precedence: bulk
MIME-Version: 1.0
Content-Type: multipart/signed; micalg=pgp-sha512;
	protocol="application/pgp-signature"; boundary="gwdtcq3kwf5cetlv"
Content-Disposition: inline
In-Reply-To: <CABdmKX2KsxVExVWzysc_fQagGkYWhqRF00KxNxjpVWovHHip+Q@mail.gmail.com>


--gwdtcq3kwf5cetlv
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
Content-Transfer-Encoding: quoted-printable

On Fri, Feb 02, 2024 at 10:22:34AM -0800, "T.J. Mercier" <tjmercier@google.=
com> wrote:
> So all of these should be more or less equivalent:
> delta <=3D SWAP_CLUSTER_MAX ? delta : (delta + 3*SWAP_CLUSTER_MAX) / 4
> max((nr_to_reclaim - nr_reclaimed) / 4, (nr_to_reclaim - nr_reclaimed) % =
4)
> (nr_to_reclaim - nr_reclaimed) / 4 + 4
> (nr_to_reclaim - nr_reclaimed) / 4
>=20
> I was just trying to avoid putting in a 0 for the request size with the m=
od.

The third variant would be simpler then. Modulo looks weird.

Oh, and I just realized that try_to_free_mem_cgroup_pages() does
max(nr_pages, SWAP_CLUSTER_MAX). Then I'd vote for the fourth variant +
possible comment about harmless 0.
(I'm sorry if this was discussed before.)

Michal

--gwdtcq3kwf5cetlv
Content-Type: application/pgp-signature; name="signature.asc"

-----BEGIN PGP SIGNATURE-----

iHUEABYKAB0WIQQpEWyjXuwGT2dDBqAGvrMr/1gcjgUCZb1GrgAKCRAGvrMr/1gc
jpaqAP9PQEKb5U00/7EvIWgO4mSe3xgJFzSEakWK6ZzZcedHxQD7Br+GIkc1yt7s
uBEhvGPzYvygslFDhyZVTQXlOueoaAs=
=ArmI
-----END PGP SIGNATURE-----

--gwdtcq3kwf5cetlv--