From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1752121AbcFGBL0 (ORCPT ); Mon, 6 Jun 2016 21:11:26 -0400 Received: from mx1.redhat.com ([209.132.183.28]:53625 "EHLO mx1.redhat.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751894AbcFGBLX (ORCPT ); Mon, 6 Jun 2016 21:11:23 -0400 Message-ID: <1465261878.16365.149.camel@redhat.com> Subject: Re: [PATCH 05/10] mm: remove LRU balancing effect of temporary page isolation From: Rik van Riel To: Johannes Weiner Cc: linux-mm@kvack.org, linux-kernel@vger.kernel.org, Andrew Morton , Mel Gorman , Andrea Arcangeli , Andi Kleen , Michal Hocko , Tim Chen , kernel-team@fb.com Date: Mon, 06 Jun 2016 21:11:18 -0400 In-Reply-To: <20160606221550.GA6665@cmpxchg.org> References: <20160606194836.3624-1-hannes@cmpxchg.org> <20160606194836.3624-6-hannes@cmpxchg.org> <1465250169.16365.147.camel@redhat.com> <20160606221550.GA6665@cmpxchg.org> Content-Type: multipart/signed; micalg="pgp-sha256"; protocol="application/pgp-signature"; boundary="=-DEsm4J3ppzrMGOLVNmll" Mime-Version: 1.0 X-Greylist: Sender IP whitelisted, not delayed by milter-greylist-4.5.16 (mx1.redhat.com [10.5.110.26]); Tue, 07 Jun 2016 01:11:22 +0000 (UTC) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org --=-DEsm4J3ppzrMGOLVNmll Content-Type: text/plain; charset="UTF-8" Content-Transfer-Encoding: quoted-printable On Mon, 2016-06-06 at 18:15 -0400, Johannes Weiner wrote: > On Mon, Jun 06, 2016 at 05:56:09PM -0400, Rik van Riel wrote: > >=20 > > On Mon, 2016-06-06 at 15:48 -0400, Johannes Weiner wrote: > > >=20 > > > =C2=A0 > > > +void lru_cache_putback(struct page *page) > > > +{ > > > + struct pagevec *pvec =3D &get_cpu_var(lru_putback_pvec); > > > + > > > + get_page(page); > > > + if (!pagevec_space(pvec)) > > > + __pagevec_lru_add(pvec, false); > > > + pagevec_add(pvec, page); > > > + put_cpu_var(lru_putback_pvec); > > > +} > > >=20 > > Wait a moment. > >=20 > > So now we have a putback_lru_page, which does adjust > > the statistics, and an lru_cache_putback which does > > not? > >=20 > > This function could use a name that is not as similar > > to its counterpart :) > lru_cache_add() and lru_cache_putback() are the two sibling > functions, > where the first influences the LRU balance and the second one > doesn't. >=20 > The last hunk in the patch (obscured by showing the label instead of > the function name as context) updates putback_lru_page() from using > lru_cache_add() to using lru_cache_putback(). >=20 > Does that make sense? That means the page reclaim does not update the "rotated" statistics. That seems undesirable, no? Am I overlooking something? --=20 All Rights Reversed. --=-DEsm4J3ppzrMGOLVNmll Content-Type: application/pgp-signature; name="signature.asc" Content-Description: This is a digitally signed message part Content-Transfer-Encoding: 7bit -----BEGIN PGP SIGNATURE----- Version: GnuPG v2 iQEcBAABCAAGBQJXVh82AAoJEM553pKExN6DCCMIAI7IV8X195ET31hixsf9c4pW I7xGVhc4UAyZYAn5wnPGZqU2Gi8wnuv0Z+JTOYNRKL88cNR4EzNQynotdxqVsQXd Hn82qO3QQ1ylyB9RugZVyVYKJDOhKhxVRXjTSo66gNK5DzURQtvQUcNZjIzqYLHK VeCfr4YGMMXKN6/A66ESqvhkISKQ9LW8ZYTr/6L8Upwt873U+RNmvDwd1M+DkQEa c5iBQReJeJBarwcBcAfjhtqmWAn0C+TLcL9m4e2FvpGllIMMIXOzreIEsG7g1Ung w7rI5A/mHiHYBP+Pm6lHZdtdJho9m20KC1Bos3snYyFpQFMJxYbPVCVfiAp47Dw= =G57z -----END PGP SIGNATURE----- --=-DEsm4J3ppzrMGOLVNmll--