From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from mailman by lists.gnu.org with tmda-scanned (Exim 4.43) id 1ILw43-0002rz-BV for qemu-devel@nongnu.org; Fri, 17 Aug 2007 03:16:11 -0400 Received: from exim by lists.gnu.org with spam-scanned (Exim 4.43) id 1ILw3y-0002qI-OU for qemu-devel@nongnu.org; Fri, 17 Aug 2007 03:16:10 -0400 Received: from [199.232.76.173] (helo=monty-python.gnu.org) by lists.gnu.org with esmtp (Exim 4.43) id 1ILw3y-0002q8-Kq for qemu-devel@nongnu.org; Fri, 17 Aug 2007 03:16:06 -0400 Received: from zero.voxel.net ([69.9.191.6]) by monty-python.gnu.org with esmtp (Exim 4.60) (envelope-from ) id 1ILw3y-0005Bk-CZ for qemu-devel@nongnu.org; Fri, 17 Aug 2007 03:16:06 -0400 Message-ID: <42755.207.81.93.54.1187334969.squirrel@mail.voxel.net> In-Reply-To: <1187296877557-git-send-email-kronos.it@gmail.com> 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> Date: Fri, 17 Aug 2007 00:16:09 -0700 (PDT) From: "Matthew Kent" MIME-Version: 1.0 Content-Type: text/plain;charset=iso-8859-1 Content-Transfer-Encoding: quoted-printable 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: Luca Tettamanti Cc: kvm-devel@lists.sourceforge.net, Dan Kenigsberg , qemu-devel@nongnu.org > If DYNAMIC_TICKS is defined qemu does not attepmt to generate SIGALRM a= t 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. --=20 Matthew Kent http://magoazul.com