From mboxrd@z Thu Jan 1 00:00:00 1970 From: Ryan Harper Subject: Re: [PATCH 0/2] RFC use dirty bit for page dirty tracking (v2) Date: Mon, 6 Jul 2009 22:32:02 -0500 Message-ID: <20090707033202.GN11590@us.ibm.com> References: <1244651005-18322-1-git-send-email-ieidus@redhat.com> <20090615145836.GI28278@us.ibm.com> <4A366679.9020604@redhat.com> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Cc: Ryan Harper , Izik Eidus , kvm@vger.kernel.org To: Avi Kivity Return-path: Received: from e3.ny.us.ibm.com ([32.97.182.143]:33241 "EHLO e3.ny.us.ibm.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1756348AbZGGDcA (ORCPT ); Mon, 6 Jul 2009 23:32:00 -0400 Received: from d01relay02.pok.ibm.com (d01relay02.pok.ibm.com [9.56.227.234]) by e3.ny.us.ibm.com (8.13.1/8.13.1) with ESMTP id n673QYNV032580 for ; Mon, 6 Jul 2009 23:26:34 -0400 Received: from d01av01.pok.ibm.com (d01av01.pok.ibm.com [9.56.224.215]) by d01relay02.pok.ibm.com (8.13.8/8.13.8/NCO v9.2) with ESMTP id n673W3ZP236684 for ; Mon, 6 Jul 2009 23:32:03 -0400 Received: from d01av01.pok.ibm.com (loopback [127.0.0.1]) by d01av01.pok.ibm.com (8.12.11.20060308/8.13.3) with ESMTP id n673W3ng016663 for ; Mon, 6 Jul 2009 23:32:03 -0400 Content-Disposition: inline In-Reply-To: <4A366679.9020604@redhat.com> Sender: kvm-owner@vger.kernel.org List-ID: * Avi Kivity [2009-06-15 10:19]: > On 06/15/2009 05:58 PM, Ryan Harper wrote: > >* Izik Eidus [2009-06-10 11:25]: > > > >>RFC move to dirty bit tracking using the page table dirty bit (v2) > >> > >> > > > >Where is this series at? Did you want me to test one of the ept dirty > >tracking patches for that hugepage+ept+local migration bug? > > > > The first patch (which might cure your oops) is already in qemu-kvm.git, > please test it out. Sorry for taking forever on this... current upstream kvm modules from kvm-kmod.git are working fine for this. I believe the final patch that was committed: commit e244584fe3a5c20deddeca246548ac86dbc6e1d1 Author: Izik Eidus Date: Wed Jun 10 19:23:24 2009 +0300 KVM: Fix dirty bit tracking for slots with large pages did the trick. Should this get pulled back into any of the stable trees? -- Ryan Harper Software Engineer; Linux Technology Center IBM Corp., Austin, Tx ryanh@us.ibm.com