From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from mailman by lists.gnu.org with tmda-scanned (Exim 4.43) id 1IMfpq-0000We-6t for qemu-devel@nongnu.org; Sun, 19 Aug 2007 04:08:34 -0400 Received: from exim by lists.gnu.org with spam-scanned (Exim 4.43) id 1IMfpo-0000Vy-AI for qemu-devel@nongnu.org; Sun, 19 Aug 2007 04:08:33 -0400 Received: from [199.232.76.173] (helo=monty-python.gnu.org) by lists.gnu.org with esmtp (Exim 4.43) id 1IMfpo-0000Vg-3M for qemu-devel@nongnu.org; Sun, 19 Aug 2007 04:08:32 -0400 Received: from il.qumranet.com ([82.166.9.18]) by monty-python.gnu.org with esmtp (Exim 4.60) (envelope-from ) id 1IMfpn-0003nP-Nl for qemu-devel@nongnu.org; Sun, 19 Aug 2007 04:08:31 -0400 Message-ID: <46C7FA8A.2090900@qumranet.com> Date: Sun, 19 Aug 2007 11:08:42 +0300 From: Avi Kivity MIME-Version: 1.0 References: <11872968773449-git-send-email-kronos.it@gmail.com> <11872968771257-git-send-email-kronos.it@gmail.com> <11872968773155-git-send-email-kronos.it@gmail.com> <11872968773524-git-send-email-kronos.it@gmail.com> <1187296877557-git-send-email-kronos.it@gmail.com> <42755.207.81.93.54.1187334969.squirrel@mail.voxel.net> In-Reply-To: <42755.207.81.93.54.1187334969.squirrel@mail.voxel.net> Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit Subject: [Qemu-devel] Re: [kvm-devel] [PATCH/RFC 4/4] Add support for dynamic ticks. Reply-To: qemu-devel@nongnu.org List-Id: qemu-devel.nongnu.org List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , To: Matthew Kent Cc: kvm-devel@lists.sourceforge.net, Dan Kenigsberg , Luca Tettamanti , qemu-devel@nongnu.org Matthew Kent wrote: >> If DYNAMIC_TICKS is defined qemu does not attepmt to generate SIGALRM at a >> constant rate. Rather, the system timer is set to generate SIGALRM only >> when it is needed. DYNAMIC_TICKS reduces the number of SIGALRMs sent to >> idle dynamic-ticked guests. >> Original patch from Dan Kenigsberg >> >> Signed-off-by: Luca Tettamanti >> > > Wow, this patch sure made a difference for some timings I've been doing > with kvm-35 and hackbench. All tests using 2.6.23-rc3+hrtimers patch for > x86_64/i386 tickless and a quad core intel: > > [mkent@localhost ~]$ time ./hackbench 50 > x86_64 host : real 0m10.845s > x86_64 host, bound to 1 cpu : real 0m21.884s > i386 guest+unix clock : real 0m49.206s > i386 guest+hpet clock : real 0m48.292s > i386 guest+dynticks clock : real 0m28.835s > > Results are repeatable and verfied with a stopwatch because I didn't > believe them at first :) > > Great stuff. > I'm not sure what these results mean... -- error compiling committee.c: too many arguments to function