From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from eggs.gnu.org ([2001:4830:134:3::10]:37641) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1X1fCZ-00046n-BO for qemu-devel@nongnu.org; Mon, 30 Jun 2014 13:17:16 -0400 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1X1fCU-0005Vu-GK for qemu-devel@nongnu.org; Mon, 30 Jun 2014 13:17:11 -0400 Received: from mx1.redhat.com ([209.132.183.28]:25736) by eggs.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1X1fCU-0005Vn-6Z for qemu-devel@nongnu.org; Mon, 30 Jun 2014 13:17:06 -0400 Message-ID: <53B19B80.5060000@redhat.com> Date: Mon, 30 Jun 2014 19:16:48 +0200 From: Paolo Bonzini MIME-Version: 1.0 References: <1404136749-523-1-git-send-email-sebastian.tanase@openwide.fr> In-Reply-To: <1404136749-523-1-git-send-email-sebastian.tanase@openwide.fr> Content-Type: text/plain; charset=UTF-8; format=flowed Content-Transfer-Encoding: 7bit Subject: Re: [Qemu-devel] [RFC PATCH V3 0/6] icount: Implement delay algorithm between guest and host clocks List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , To: Sebastian Tanase , qemu-devel@nongnu.org Cc: kwolf@redhat.com, peter.maydell@linaro.org, aliguori@amazon.com, wenchaoqemu@gmail.com, quintela@redhat.com, mjt@tls.msk.ru, mst@redhat.com, stefanha@redhat.com, armbru@redhat.com, lcapitulino@redhat.com, michael@walle.cc, alex@alex.org.uk, crobinso@redhat.com, afaerber@suse.de, rth@twiddle.net Il 30/06/2014 15:59, Sebastian Tanase ha scritto: > The icount option already implemented in QEMU allows the guest to run at a theoretical > frequency of 1/(2^N) GHz (N is the icount parameter). The goal of this patch is to have a > real guest frequency close to the one imposed by using the icount option. > > The main idea behind the algorithm is that we compare the virtual monotonic clock and the > host monotonic clock. For big icounts (on our test machine, an i5 CPU @ 3.10GHz, icounts > starting at 6) the guest clock will be ahead of the host clock. In this case, we try to > sleep QEMU for the difference between the 2 clocks. Therefore, the guest would have > executed for a period almost equally to the one imposed by icount. We should point out > that the algorithm works only for those icounts that allow the guest clock to be in front > of the host clock. > > The first patch adds support for QemuOpts for the 'icount' parameter. It also adds a > suboption called 'shift' that will hold the value for 'icount'. Therefore we now have > -icount shift=N|auto or -icount N|auto. > > The second patch adds the 'align' suboption for icount. > > The third patch exports 'icount_time_shift' so that it can be used in places other than > cpus.c; we need it in cpu-exec.c for calculating for how long we want QEMU to sleep. > > The forth patch implements the algorithm used for calculating the delay we want to sleep. > It uses the number of instructions executed by the virtual cpu and also the icount_time_shift. > > The fifth patch prints to the console whenever the guest clock runs behind the host > clock. The fastest printing speed is every 2 seconds, and we only print if the align option > is enabled. We also have a limit to 100 printed messages. > > The sixth patch adds information about the difference between the host and guest clocks > (taking into account the offset) in the 'info jit' command. We also print the maximum > delay and advance of the guest clock compared to the host clock. I think the changes I made are too big to get this in 2.1, but we can certainly get this very early in 2.2 instead. I'll shortly push my changes to an "icount" branch at github.com/bonzini/qemu.git. Can you look at it and rebase patches 5 and 6 on top (plus the small change I asked for in my review of patch 2)? Thanks, Paolo