From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1751874AbbCIRFM (ORCPT ); Mon, 9 Mar 2015 13:05:12 -0400 Received: from prod-mail-xrelay07.akamai.com ([72.246.2.115]:24542 "EHLO prod-mail-xrelay07.akamai.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1750741AbbCIRFG (ORCPT ); Mon, 9 Mar 2015 13:05:06 -0400 Date: Mon, 9 Mar 2015 13:05:05 -0400 From: Eric B Munson To: David Rientjes Cc: Andrew Morton , Vlastimil Babka , Thomas Gleixner , Christoph Lameter , Peter Zijlstra , Mel Gorman , linux-mm@kvack.org, linux-kernel@vger.kernel.org Subject: Re: [PATCH] Allow compaction of unevictable pages Message-ID: <20150309170505.GA2290@akamai.com> References: <1425667287-30841-1-git-send-email-emunson@akamai.com> MIME-Version: 1.0 Content-Type: multipart/signed; micalg=pgp-sha1; protocol="application/pgp-signature"; boundary="OXfL5xGRrasGEqWY" Content-Disposition: inline In-Reply-To: User-Agent: Mutt/1.5.21 (2010-09-15) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org --OXfL5xGRrasGEqWY Content-Type: text/plain; charset=us-ascii Content-Disposition: inline Content-Transfer-Encoding: quoted-printable On Fri, 06 Mar 2015, David Rientjes wrote: > On Fri, 6 Mar 2015, Eric B Munson wrote: >=20 > > diff --git a/mm/compaction.c b/mm/compaction.c > > index 8c0d945..33c81e1 100644 > > --- a/mm/compaction.c > > +++ b/mm/compaction.c > > @@ -1056,7 +1056,7 @@ static isolate_migrate_t isolate_migratepages(str= uct zone *zone, > > { > > unsigned long low_pfn, end_pfn; > > struct page *page; > > - const isolate_mode_t isolate_mode =3D > > + const isolate_mode_t isolate_mode =3D ISOLATE_UNEVICTABLE | > > (cc->mode =3D=3D MIGRATE_ASYNC ? ISOLATE_ASYNC_MIGRATE : 0); > > =20 > > /* >=20 > I agree that memory compaction should be isolating and migrating=20 > unevictable memory for better results, and we have been running with a=20 > similar patch internally for about a year for the same purpose as you,=20 > higher probability of allocating hugepages. >=20 > This would be better off removing the notion of ISOLATE_UNEVICTABLE=20 > entirely, however, since CMA and now memory compaction would be using it,= =20 > so the check in __isolate_lru_page() is no longer necessary. Has the=20 > added bonus of removing about 10 lines of soure code. Thanks for having a look, I will send out a V2 that removes ISOLATE_UNEVICTABLE and the check in __isolate_lru_page(). Eric --OXfL5xGRrasGEqWY Content-Type: application/pgp-signature; name="signature.asc" Content-Description: Digital signature -----BEGIN PGP SIGNATURE----- Version: GnuPG v1 iQIcBAEBAgAGBQJU/dLBAAoJELbVsDOpoOa9xfIP/R4oju4qqvlAS4eczr2ajl0Y ufjDDgBxT/NuKufYKtmMztrSHOItFhIHYnx9zjavYq0C/FL1ajoR9DvjghA/Im78 pNEL8tk5OzdkPB75bOvNjmTNuNCGZOElGLy50wqBDhO+EHELX3ZycEuuTs8q9kfl QmGYxKPEj1X4P1THG4m/823CelitvYgTbyOWr5Jk5qsuAz5K3d1sVFR1nFUyhtGJ XirKnwplBMyAEi+FnffWUmmm3qEB/tHOf1dtyzQf5q0pB2luoz72m+Jv/PdgDDmH 3sFISFUQjjrvPqDC5RGL7GAFpzkj+d2ZGLGUP9i2HhBlU7imPuaEJx6V3N9y545I FK+Kao71L3wWEygcE/C5Ldu62lV+RJTAxxkqXY0veel/KmmxfH4ggLPDZq+B4Oym g+HahZWMB4+qZDrwXoe9t4zytCZ8u59wKgedtBDBhJq2iZ8dB0M/SVzMaIlZ6d+5 1qTZU/LGqLX8q63awQ6yGQIkKP9XoOBmJGzuTFDWvGjH6k6xAL5zblbpyNwODoNq ZqPv0WZY09zSCaAasncbB/5DrFqPaJlSw75jObdkIJMQ7RY+yhkgnH7aPnPSseYp s7+esvkC4wbHOOtA7ayDJGxBLd6sFeaIX4mpFJAlAbJ4NmSp6mowtDNspaataX5e HlqGCxo8cAGonbXEFJ4a =5YZm -----END PGP SIGNATURE----- --OXfL5xGRrasGEqWY--