From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Date: Mon, 15 Nov 2010 16:55:21 +0100 From: Martin Schwidefsky Subject: Re: [RFC][PATCH v2 5/7] taskstats: Improve cumulative CPU time accounting Message-ID: <20101115165521.21baac60@mschwide.boeblingen.de.ibm.com> In-Reply-To: <20101113183810.GA9021@redhat.com> References: <20101111170352.732381138@linux.vnet.ibm.com> <20101111170815.404670062@linux.vnet.ibm.com> <20101113183810.GA9021@redhat.com> Mime-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7bit Sender: linux-kernel-owner@vger.kernel.org List-Archive: List-Post: To: Oleg Nesterov Cc: Michael Holzheu , Shailabh Nagar , Andrew Morton , Venkatesh Pallipadi , Suresh Siddha , Peter Zijlstra , Ingo Molnar , John stultz , Thomas Gleixner , Balbir Singh , Heiko Carstens , Roland McGrath , linux-kernel@vger.kernel.org, linux-s390@vger.kernel.org List-ID: On Sat, 13 Nov 2010 19:38:10 +0100 Oleg Nesterov wrote: > First of all, let me repeat, I am not going to discuss whether we need > these changes or not, I do not know even if I understand your motivation. Hmm, is the motivation of whole patch series unclear or just the details in this one? What we want is a low-overhead tool that precisely shows where the cpu spent its time (or didn't because of steal time). The granularity target is tenths of microseconds, something that should be possible with decent hardware. What makes life hard is the corner case of a task that has been reparented to init. That is reason for this complicated secondary accounting structure. > My only concern is correctness, but You review effort to improve correctness is very much appreciated. We'll try to split the patches to make review easier. -- blue skies, Martin. "Reality continues to ruin my life." - Calvin.