From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from mailman by lists.gnu.org with tmda-scanned (Exim 4.43) id 1KzDJG-0003SW-BJ for qemu-devel@nongnu.org; Sun, 09 Nov 2008 11:38:46 -0500 Received: from exim by lists.gnu.org with spam-scanned (Exim 4.43) id 1KzDJE-0003S8-EM for qemu-devel@nongnu.org; Sun, 09 Nov 2008 11:38:45 -0500 Received: from [199.232.76.173] (port=48927 helo=monty-python.gnu.org) by lists.gnu.org with esmtp (Exim 4.43) id 1KzDJE-0003S5-8Z for qemu-devel@nongnu.org; Sun, 09 Nov 2008 11:38:44 -0500 Received: from an-out-0708.google.com ([209.85.132.240]:20417) by monty-python.gnu.org with esmtp (Exim 4.60) (envelope-from ) id 1KzDJE-0002hG-2y for qemu-devel@nongnu.org; Sun, 09 Nov 2008 11:38:44 -0500 Received: by an-out-0708.google.com with SMTP id c38so169748ana.37 for ; Sun, 09 Nov 2008 08:38:43 -0800 (PST) Message-ID: <4917120F.4080000@codemonkey.ws> Date: Sun, 09 Nov 2008 10:38:39 -0600 From: Anthony Liguori MIME-Version: 1.0 Subject: Re: [Qemu-devel] [RESEND][PATCH 0/3] Fix guest time drift under heavy load. References: <20081029152236.14831.15193.stgit@dhcp-1-237.local> <20081106081206.GD3820@redhat.com> <4912FAE5.9010100@codemonkey.ws> <200811061424.43689.paul@codesourcery.com> <491301C9.40506@codemonkey.ws> <20081106145142.GA29861@redhat.com> <49130F54.4060907@codemonkey.ws> <20081108083620.GB19381@redhat.com> <20081109074037.GA32281@redhat.com> In-Reply-To: <20081109074037.GA32281@redhat.com> Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit Reply-To: qemu-devel@nongnu.org List-Id: qemu-devel.nongnu.org List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , To: Gleb Natapov Cc: Paul Brook , qemu-devel@nongnu.org Gleb Natapov wrote: > On Sat, Nov 08, 2008 at 10:36:20AM +0200, Gleb Natapov wrote: > >>> I think the best ones are going to be intense host workload (and let's >>> see how much is needed before we start drifting badly) and high guest >>> frequencies with hosts that lack high resolution timers. I think with a >>> high resolution guest and no host overcommit, it should be very >>> difficult to produce drift regardless of what the guest is doing. >>> >>> >> Later I'll try to generate load on a host an see how this affects >> guest's time drift. >> >> > Just did that. Run qemu process bound to CPU 1 (taskset 1 qemu ...). > Run busy loop on the same CPU (taskset 1 bash -c "while true; do x='x'; done") > Run disk test utility as before inside a guest. After 40 minutes time > drift is almost 1 minute, but the drift was not gradual i.e I observed > gradual drift of 1 second per ~6 minutest, but sometimes there were jumps > of ~10 seconds. > Yeah, this is what I would expect. This is why we'll probably have to do some sort of interrupt catch-up. But I'd like to make sure we have the idle host stuff figured out because I don't see a reason why we should lose ticks. I don't want to mask other problems with something like TDF. Regards, Anthony Liguori > -- > Gleb. >