Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1752928Ab0LVOSE (ORCPT ); Wed, 22 Dec 2010 09:18:04 -0500 Received: from smtp-out.google.com ([74.125.121.67]:4754 "EHLO smtp-out.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751681Ab0LVOSC (ORCPT ); Wed, 22 Dec 2010 09:18:02 -0500 DomainKey-Signature: a=rsa-sha1; c=nofws; d=google.com; s=beta; h=mime-version:in-reply-to:references:date:message-id:subject:from:to :cc:content-type; b=mpXUt5e84oWQ7SK2/YyGot7n3BmiF05spLkdKsbHLI0HQygsMWO1d3i3p3pDPZMcW0 Qa6YDagdmbsNnqNUlG6w== MIME-Version: 1.0 In-Reply-To: <1293026724.2170.137.camel@laptop> References: <1292980144-28796-1-git-send-email-venki@google.com> <1292980144-28796-6-git-send-email-venki@google.com> <1293009621.2170.72.camel@laptop> <1293026724.2170.137.camel@laptop> Date: Wed, 22 Dec 2010 06:17:57 -0800 Message-ID: Subject: Re: [PATCH 5/5] Account ksoftirqd time as cpustat softirq -v2 From: Venkatesh Pallipadi To: Peter Zijlstra Cc: Ingo Molnar , "H. Peter Anvin" , Thomas Gleixner , Balbir Singh , Martin Schwidefsky , linux-kernel@vger.kernel.org, Paul Turner , Eric Dumazet , Shaun Ruffell Content-Type: text/plain; charset=ISO-8859-1 X-System-Of-Record: true Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 1673 Lines: 37 On Wed, Dec 22, 2010 at 6:05 AM, Peter Zijlstra wrote: > On Wed, 2010-12-22 at 05:59 -0800, Venkatesh Pallipadi wrote: >> > So you add the ksoftirqd runtime as softirq time in the /proc/stat >> > output? >> > >> > That seems dubious... >> > >> >> Yes. Thats similar to what we do today. As long as we are in softirq, >> whether bottomhalf or ksoftirqd, we account the tick as softirq time >> in /proc/stat. >> I thought it also makes sense from user perspective. They want to know >> how much time are we currently spending serving softirqs and hardirqs. >> It is better to get that information at one place, instead of say look >> at /proc/stat and add percpu ksoftirqd time to it. I mean, >> user/administrator does not have to care whether ksoftirqd is involved >> or not to know how much time was spend serving softirqs. >> > But ksoftirqd time is also counted as sys time, so somewhere this won't > add up to 100%. > It won't get added into cpu kstat system time. It will get added into task stime, so looking into ksoftirqd task time, this will be seen as system time. So, per cpu kstat should be consistent when added up. The problem will be, with ksoftirqd, cpu stats will say the time as softirq and task stats will account the time to ksoftirqd task as stime, which is different from what we do with other tasks. I guess that should be OK as ksoftirqd are special in some sense. Thanks, Venki -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/