From mboxrd@z Thu Jan 1 00:00:00 1970 From: Zachary Amsden Subject: Re: [PATCH 04/17] Fix deep C-state TSC desynchronization Date: Wed, 16 Jun 2010 08:43:43 -1000 Message-ID: <4C191B5F.7080109@redhat.com> References: <1276587259-32319-1-git-send-email-zamsden@redhat.com> <1276587259-32319-5-git-send-email-zamsden@redhat.com> <4C18870C.9070707@redhat.com> Mime-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit Cc: avi@redhat.com, mtosatti@redhat.com, glommer@redhat.com, kvm@vger.kernel.org, linux-kernel@vger.kernel.org To: Jason Wang Return-path: Received: from mx1.redhat.com ([209.132.183.28]:59020 "EHLO mx1.redhat.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1759027Ab0FPSnq (ORCPT ); Wed, 16 Jun 2010 14:43:46 -0400 In-Reply-To: <4C18870C.9070707@redhat.com> Sender: kvm-owner@vger.kernel.org List-ID: On 06/15/2010 10:10 PM, Jason Wang wrote: > Zachary Amsden wrote: > >> When CPUs with unstable TSCs enter deep C-state, TSC may stop >> running. This causes us to require resynchronization. Since >> we can't tell when this may potentially happen, we assume the >> worst by forcing re-compensation for it at every point the VCPU >> task is descheduled. >> >> >> > Is there any method to do the compensation on host TSC when recovering > from C-state? It should be simpler than do it on guest TSC. > Actually, yes, we could re-calibrate from HPET. Considering this patch is already broken, maybe that's a better idea.