From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1754158AbYDETPg (ORCPT ); Sat, 5 Apr 2008 15:15:36 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1753262AbYDETP0 (ORCPT ); Sat, 5 Apr 2008 15:15:26 -0400 Received: from wf-out-1314.google.com ([209.85.200.174]:45768 "EHLO wf-out-1314.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752871AbYDETPU (ORCPT ); Sat, 5 Apr 2008 15:15:20 -0400 DomainKey-Signature: a=rsa-sha1; c=nofws; d=gmail.com; s=gamma; h=from:organization:to:subject:date:user-agent:cc:references:in-reply-to:mime-version:content-type:content-transfer-encoding:content-disposition:message-id; b=oE9aJbYBHTju2patO0k2avN+MHg4HfYMIosy/qcapCWudM3pDpCex0jXTZpzglj0LKfWyDbcAfpD37GAE58fXutowzz1cczexNOURME2EApy+/RLYS/AICn+dzSClZ+tt+q+PbMHFmzQIfCQiWVobEHXhs3DBSwY7kfxEFBO20c= From: Balaji Rao Organization: National Institute of Technology Karnataka To: Dhaval Giani Subject: Re: [RFC][-mm] [1/2] Simple stats for cpu resource controller Date: Sun, 6 Apr 2008 00:39:02 +0530 User-Agent: KMail/1.9.6 (enterprise 0.20071012.724442) Cc: linux-kernel@vger.kernel.org, containers@lists.osdl.org, menage@google.com, a.p.zijlstra@chello.nl, balbir@in.ibm.com, Ingo Molnar , Srivatsa Vaddagiri References: <200804052339.46632.balajirrao@gmail.com> <20080405185616.GA21279@linux.vnet.ibm.com> In-Reply-To: <20080405185616.GA21279@linux.vnet.ibm.com> MIME-Version: 1.0 Content-Type: text/plain; charset="iso-8859-1" Content-Transfer-Encoding: 7bit Content-Disposition: inline Message-Id: <200804060039.03083.balajirrao@gmail.com> Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Sunday 06 April 2008 12:26:16 am Dhaval Giani wrote: > On Sat, Apr 05, 2008 at 11:39:46PM +0530, Balaji Rao wrote: > > This patch implements some trivial statistics for the CPU controller. > > > > As per our current requirements, we have decided to keep the stats tick based as opposed to using CFS precise accounting. > > > > A quick question? Why? Everywhere in the CFS we use precise accounting, > (even within the CPU controller). Doesn't make sense using ticks here > then. > Using CFS precise accounting has a cost (see task_utime and task_stime). Currently our requirements don't call for precise statistics. -- regards, Balaji Rao Dept. of Mechanical Engineering, National Institute of Technology Karnataka, India