From mboxrd@z Thu Jan 1 00:00:00 1970 From: Daniel Bareiro Subject: Re: Memory usage with qemu-kvm-0.12.1.1 Date: Thu, 31 Dec 2009 12:05:27 -0300 Message-ID: <20091231150527.GA16528@defiant.freesoftware> References: <20091227155107.GK7104@defiant.freesoftware> <4B378546.6070104@redhat.com> <4B378C25.4070206@redhat.com> <4B378D6D.40505@redhat.com> <4B378F32.1050307@redhat.com> <4B379562.8060007@redhat.com> <4B37978F.5030009@redhat.com> Reply-To: dbareiro@gmx.net Mime-Version: 1.0 Content-Type: multipart/signed; micalg=pgp-sha1; protocol="application/pgp-signature"; boundary="Kj7319i9nmIyA2yE" Cc: Rik van Riel , Avi Kivity , KVM General To: Hugh Dickins Return-path: Received: from mail.gmx.net ([213.165.64.20]:42253 "HELO mail.gmx.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with SMTP id S1752470AbZLaPFd (ORCPT ); Thu, 31 Dec 2009 10:05:33 -0500 Content-Disposition: inline In-Reply-To: Sender: kvm-owner@vger.kernel.org List-ID: --Kj7319i9nmIyA2yE Content-Type: text/plain; charset=us-ascii Content-Disposition: inline Content-Transfer-Encoding: quoted-printable Hi, Hugh. On Wednesday, 30 December 2009 18:14:30 +0000, Hugh Dickins wrote: > On Sun, 27 Dec 2009, Rik van Riel wrote: > > On 12/27/2009 12:12 PM, Avi Kivity wrote: > > > On 12/27/2009 06:45 PM, Rik van Riel wrote: > > > >=20 > > > > > If so, it doesn't copy stable@kernel.org. Is it queued for -stabl= e? > > > >=20 > > > > I do not believe that it is queued for -stable. > > > >=20 > > > > Do performance fixes fit with -stable policy? > > >=20 > > > If it is a serious regression, I believe it fits. > >=20 > > It's probably been there since 2.6.28, though it might have been > > introduced later with a cleanup patch. It seems to go back at > > least as far as March... =20 > It does look as if it would have got worse in 2.6.31 and 2.6.32 > - though I am reluctant to predict how these scans work out in > practice from just glancing at the code! >=20 > I agree with Avi (or with Avi's implication), that it would be > worth sending the fix to -stable - but it would be nice to hear > if the patch (inline below) actually does fix Daniel's problem. > It applies and builds correctly on 2.6.31.9 and 2.6.32.3. >=20 > We have certainly sent much more specialized performance fixes > to -stable (I'm thinking of Lee's anon_vma locking), and I see > this as more of a straightforward bugfix anyway - people get > worried by going into swap without understanding why. >=20 > I forget which patch of mine Avi was thinking of, > but I'm pretty sure Rik's will prove much the more relevant. I shutdown the virtual machines yesterday and I boot them again and the swap usage did not exceed the 9 MB / 486 MB with /proc/sys/vm/swappiness set to 0. Now I tried restarting the host with the same running VM and, at the moment, the use of swap is zero with /proc/sys/vm/swappiness by default (60). root@ubuntu:~# free total used free shared buffers cached Mem: 4060340 2299556 1760784 0 837668 133292 -/+ buffers/cache: 1328596 2731744 Swap: 497972 0 497972 What tests would be recommendable to make to reproduce the problem? You say that the patch applies and builds correctly on 2.6.31.9 and 2.6.32.3. I would like to test it with 2.6.32.3, but I didn't find the source code of it in [1]. It would have to be in another path? Thanks for your reply and the patch. Regards, Daniel [1] http://www.kernel.org/pub/linux/kernel/v2.6/ --=20 Fingerprint: BFB3 08D6 B4D1 31B2 72B9 29CE 6696 BF1B 14E6 1D37 Powered by Debian GNU/Linux Lenny - Linux user #188.598 --Kj7319i9nmIyA2yE Content-Type: application/pgp-signature; name="signature.asc" Content-Description: Digital signature Content-Disposition: inline -----BEGIN PGP SIGNATURE----- Version: GnuPG v1.4.9 (GNU/Linux) iEYEARECAAYFAks8vbcACgkQZpa/GxTmHTeHUACdEKZUv+uRdRhnAeoRxec4yNVI b+oAoIIO+vnTpQrtDmw8EpVeph402p8I =Fg55 -----END PGP SIGNATURE----- --Kj7319i9nmIyA2yE--