From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1758290AbcBYCrc (ORCPT ); Wed, 24 Feb 2016 21:47:32 -0500 Received: from mx1.redhat.com ([209.132.183.28]:41363 "EHLO mx1.redhat.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751270AbcBYCrb (ORCPT ); Wed, 24 Feb 2016 21:47:31 -0500 Message-ID: <1456368447.25322.23.camel@redhat.com> Subject: Re: [PATCH] mm: limit direct reclaim for higher order allocations From: Rik van Riel To: Joonsoo Kim Cc: David Rientjes , linux-kernel@vger.kernel.org, hannes@cmpxchg.org, akpm@linux-foundation.org, vbabka@suse.cz, mgorman@suse.de Date: Wed, 24 Feb 2016 21:47:27 -0500 In-Reply-To: <20160225003032.GA9723@js1304-P5Q-DELUXE> References: <20160224163850.3d7eb56c@annuminas.surriel.com> <1456352276.25322.7.camel@redhat.com> <20160225003032.GA9723@js1304-P5Q-DELUXE> Content-Type: multipart/signed; micalg="pgp-sha1"; protocol="application/pgp-signature"; boundary="=-bl30VShaIYCHyBwbhTxf" Mime-Version: 1.0 Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org --=-bl30VShaIYCHyBwbhTxf Content-Type: text/plain; charset="UTF-8" Content-Transfer-Encoding: quoted-printable On Thu, 2016-02-25 at 09:30 +0900, Joonsoo Kim wrote: > On Wed, Feb 24, 2016 at 05:17:56PM -0500, Rik van Riel wrote: > > On Wed, 2016-02-24 at 14:15 -0800, David Rientjes wrote: > > > On Wed, 24 Feb 2016, Rik van Riel wrote: > > >=20 > > > > For multi page allocations smaller than > > > > PAGE_ALLOC_COSTLY_ORDER, > > > > the kernel will do direct reclaim if compaction failed for any > > > > reason. This worked fine when Linux systems had 128MB RAM, but > > > > on my 24GB system I frequently see higher order allocations > > > > free up over 3GB of memory, pushing all kinds of things into > > > > swap, and slowing down applications. > > > > =C2=A0 > > >=20 > > > Just curious, are these higher order allocations typically done > > > by > > > the=C2=A0 > > > slub allocator or where are they coming from? > >=20 > > These are slab allocator ones, indeed. > >=20 > > The allocations seem to be order 2 and 3, mostly > > on behalf of the inode cache and alloc_skb. >=20 > Hello, Rik. >=20 > Could you tell me the kernel version you tested? >=20 > Commit 45eb00cd3a03 (mm/slub: don't wait for high-order page > allocation) changes slub allocator's behaviour that high order > allocation request by slub doesn't cause direct reclaim. The system I observed the problem on has a 4.2 based kernel on it. That would explain. Are we sure the problem is limited just to slub, though? --=20 All Rights Reversed. --=-bl30VShaIYCHyBwbhTxf 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 v1 iQEcBAABAgAGBQJWzms/AAoJEM553pKExN6DICoH/A+0uy34pllAdaRRDph1jiAZ xKCJk50zg1Ve7iAVC27h1EJPZF4lloCqExiW5RICJ5R8f8yy5WpnV9YTjvy+0AVG MzimaIs7d116jBMTUsEpyVYeOccdzISFAGSi7bb6Y6r1YOyfdKmgRa8HHuFdSgvT BJmVKP6r6YUNVBmYWskfC3vqrnNruCIKnRxqQfOdoh1l7DiUiAhyLokXqrFwNYVA e/Yxv93xZYJ0EDMQvXJLf+ku8qIKVjQ09jJs9UkIzJFATPB8iL4iwMo+ria64id2 aXjGtw9BLNBir2FHkGQ1AW2VbKBRQ2/Cwm4RCN9Yy4yEH1mmNd0TXuwmDykWLsc= =D5+A -----END PGP SIGNATURE----- --=-bl30VShaIYCHyBwbhTxf--