From mboxrd@z Thu Jan 1 00:00:00 1970 From: Jeremy Fitzhardinge Subject: Re: Re: [PATCH] x86: unconditionally mark TSC unstable under Xen Date: Thu, 15 Jul 2010 11:05:51 -0700 Message-ID: <4C3F4DFF.3070607@goop.org> References: <51C8308F-F413-47AF-8845-C92BD36CA35C@linode.com> <4C3E2DCC.1010201@goop.org> <4C3F3B0F.1040107@goop.org> <70bac91d-227c-452f-bf20-a03a86d02255@default 4C3F45B0.305@goop.org> Mime-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: 7bit Return-path: In-Reply-To: List-Unsubscribe: , List-Post: List-Help: List-Subscribe: , Sender: xen-devel-bounces@lists.xensource.com Errors-To: xen-devel-bounces@lists.xensource.com To: Dan Magenheimer Cc: xen-devel@lists.xensource.com, Jed Smith , Jan Beulich , Stefano Stabellini List-Id: xen-devel@lists.xenproject.org On 07/15/2010 10:48 AM, Dan Magenheimer wrote: > Maybe the xen_sched_clock code should be entirely removed > rather than ifdef'd since it is no longer used and > "(somewhat, in theory)" led to a strange bug? Or if > you are confident that it will be useful in the future > by some linux scheduler, maybe add some comments about > how enabling it may cause the effects Jed saw. Yes, I can probably remove it altogether, though it isn't actually selectable without manually editing the Kconfig file. > And maybe an even better answer is to submit a patch upstream > so that the scheduler doesn't use the same timebase for > measuring both, since the kernel is making a bad assumption > about real vs virtual time. I'd imagine KVM users might benefit > from that also. Its unclear how useful it is anyway. I've discussed it with Peter Zijlstra from time to time, but making the scheduler use two timebases is non-trivial I think. Or perhaps more accurate to say that I don't want to be getting into the scheduler, since it is not only a technical minefield. J