From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from eggs.gnu.org ([208.118.235.92]:40649) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1UK51r-0007eG-7C for qemu-devel@nongnu.org; Mon, 25 Mar 2013 06:53:28 -0400 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1UK51p-0003Ke-UN for qemu-devel@nongnu.org; Mon, 25 Mar 2013 06:53:27 -0400 Received: from mx4-phx2.redhat.com ([209.132.183.25]:56245) by eggs.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1UK51p-0003KX-LL for qemu-devel@nongnu.org; Mon, 25 Mar 2013 06:53:25 -0400 Date: Mon, 25 Mar 2013 06:53:19 -0400 (EDT) From: Paolo Bonzini Message-ID: <1328150503.13028038.1364208799172.JavaMail.root@redhat.com> In-Reply-To: <5150242B.4090605@kamp.de> MIME-Version: 1.0 Content-Type: text/plain; charset=utf-8 Content-Transfer-Encoding: 7bit Subject: Re: [Qemu-devel] [PATCHv4 0/9] buffer_is_zero / migration optimizations List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , To: Peter Lieven Cc: Orit Wasserman , quintela@redhat.com, qemu-devel@nongnu.org, Stefan Hajnoczi > ubuntu 12.04 LTS 64-bit desktop with 1G memory shortly after boot: > histogram: 31.7% 32.9% [...] 36.4% 100.0% > > --- > > opensuse 11.1 64-bit with 24GB ram (busy server) > histogram: 97.5% 97.9% [...] 99.5% 100.0% > > --- > > windows server 2008 R2 with 8G ram running for 3 days: > histogram: 20.9% 21.3% [...] 22.5% 100.0% > > --- > > windows XP guest with 1G Ram running for approx. 1 hours > histogram: 25.6% [...] 35.8% 100.0% Doesn't this suggest checking the first _and the last_ word, and using the vectorized loop if none is zero? Paolo