From mboxrd@z Thu Jan 1 00:00:00 1970 From: Takuya Yoshikawa Subject: Re: [RFC][PATCH] srcu: Implement call_srcu() Date: Thu, 2 Feb 2012 00:42:49 +0900 Message-ID: <20120202004249.adb9954c45225383510b6994@gmail.com> References: <1328016724.2446.229.camel@twins> <4F27F0E6.1040309@redhat.com> <1328017807.2446.230.camel@twins> <20120131222447.GH2391@linux.vnet.ibm.com> <1328091749.2760.34.camel@laptop> <4F29178A.1090306@redhat.com> <4F2918D5.4050104@redhat.com> <4F291B56.30600@oss.ntt.co.jp> <4F291B92.8070402@redhat.com> <20120201134347.GA18998@amt.cnet> Mime-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7bit Cc: Avi Kivity , Takuya Yoshikawa , Peter Zijlstra , paulmck@linux.vnet.ibm.com, Oleg Nesterov , linux-kernel , KVM list To: Marcelo Tosatti Return-path: In-Reply-To: <20120201134347.GA18998@amt.cnet> Sender: linux-kernel-owner@vger.kernel.org List-Id: kvm.vger.kernel.org On Wed, 1 Feb 2012 11:43:47 -0200 Marcelo Tosatti wrote: > > > I can show you some performance numbers, this weekend, if you like. > > > > That'll be great, numbers are better than speculation. > > get dirty log: 5634134 ns for 262144 dirty pages > > 5ms (for the entire operation). > I have mixed my personal patch series and Avi's comments, and ... I am now getting really good improvements for every number of dirty pages. (might be a dream, so checking now ... will soon report) Takuya