From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from mailman by lists.gnu.org with tmda-scanned (Exim 4.43) id 1Ky5AL-0005tl-6D for qemu-devel@nongnu.org; Thu, 06 Nov 2008 08:44:53 -0500 Received: from exim by lists.gnu.org with spam-scanned (Exim 4.43) id 1Ky5AJ-0005tT-Qh for qemu-devel@nongnu.org; Thu, 06 Nov 2008 08:44:52 -0500 Received: from [199.232.76.173] (port=56916 helo=monty-python.gnu.org) by lists.gnu.org with esmtp (Exim 4.43) id 1Ky5AJ-0005tP-HA for qemu-devel@nongnu.org; Thu, 06 Nov 2008 08:44:51 -0500 Received: from mail.codesourcery.com ([65.74.133.4]:51773) by monty-python.gnu.org with esmtps (TLS-1.0:DHE_RSA_AES_256_CBC_SHA1:32) (Exim 4.60) (envelope-from ) id 1Ky5AJ-00045f-3G for qemu-devel@nongnu.org; Thu, 06 Nov 2008 08:44:51 -0500 From: Paul Brook Subject: Re: [Qemu-devel] [RESEND][PATCH 0/3] Fix guest time drift under heavy load. Date: Thu, 6 Nov 2008 14:44:43 +0100 References: <20081029152236.14831.15193.stgit@dhcp-1-237.local> <20081106100821.GF3820@redhat.com> In-Reply-To: <20081106100821.GF3820@redhat.com> MIME-Version: 1.0 Content-Type: text/plain; charset="iso-8859-1" Content-Transfer-Encoding: 7bit Content-Disposition: inline Message-Id: <200811061344.44680.paul@codesourcery.com> Reply-To: qemu-devel@nongnu.org List-Id: qemu-devel.nongnu.org List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , To: qemu-devel@nongnu.org Cc: dlaor@redhat.com, Gleb Natapov > > A guest that counts on having enough CPU for something is > > timing-depenent (buggy). > > Tell this to RT developers who count each CPU cycle. If you want any a realtime illusion you absolutely have to be using -icount. This is still a long way from being cycle accurate and is no use for benchmarking, but it does give some semblance of realistic virtual realtime behavior. Of course this is at the expense of some divergence between host and virtual time. Paul