From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1752593AbZETEkc (ORCPT ); Wed, 20 May 2009 00:40:32 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1750899AbZETEkY (ORCPT ); Wed, 20 May 2009 00:40:24 -0400 Received: from yw-out-2324.google.com ([74.125.46.31]:1657 "EHLO yw-out-2324.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1750725AbZETEkX convert rfc822-to-8bit (ORCPT ); Wed, 20 May 2009 00:40:23 -0400 DomainKey-Signature: a=rsa-sha1; c=nofws; d=gmail.com; s=gamma; h=mime-version:in-reply-to:references:date:message-id:subject:from:to :cc:content-type:content-transfer-encoding; b=DGi2J93jdIuDt7gNS4IIUpKmpGq0pSoP3EgdxpzfpWCCzhbpXtB8L40rTwctPm3bxo PIoI7dCdAcotihNrNhWHbZ+7aNb1J1QBglYESWnOI9QY5mvZTzmHzWI49iLc/hMNgCTH x2Xy1V5sBAsYHEiIqE+qgvcQdNgKao25pDD5I= MIME-Version: 1.0 In-Reply-To: References: <1242783692.31161.56.camel@centos51> Date: Wed, 20 May 2009 13:40:24 +0900 Message-ID: <49b7c2350905192140nba960d8l7af31c29752a8fcd@mail.gmail.com> Subject: Re: [PATCH 1/1] ftrace: fix typo in ftrace.txt file From: GeunSik Lim To: Steven Rostedt Cc: Ingo Molnar , Peter Zijlstra , linux-rt-users , linux-kernel , tglx , williams Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8BIT Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org 2009/5/20 Steven Rostedt : > > On Wed, 20 May 2009, GeunSik Lim wrote: > >> >> >> commit 43bf3fdddfd6b0ac65ef59bec3c79d9f9064e8bd >> Author: GeunSik,Lim >> Date:   Thu May 14 13:39:18 2009 +0900 >> >>     ftrace: fix typo in ftrace.txt file. >> >>     Fix typo about chart to map the kernel priority to >>     user land priorities. >> >>     About sched_setscheduler(2) >>     Processes scheduled under SCHED_FIFO or SCHED_RR >>     can have a static priority in the range 1 to 99. >> >>         Signed-off-by: GeunSik Lim >> >> diff --git a/Documentation/trace/ftrace.txt b/Documentation/trace/ftrace.txt >> index fd9a3e6..0e17632 100644 >> --- a/Documentation/trace/ftrace.txt >> +++ b/Documentation/trace/ftrace.txt >> @@ -518,9 +518,14 @@ priority with zero (0) being the highest priority and the nice >>  values starting at 100 (nice -20). Below is a quick chart to map >>  the kernel priority to user land priorities. >> >> -  Kernel priority: 0 to 99    ==> user RT priority 99 to 0 >> -  Kernel priority: 100 to 139 ==> user nice -20 to 19 >> -  Kernel priority: 140        ==> idle task priority >> + Kernel priority: 0(high) to 99(low)    ==> user RT priority 99(high) to 1(low) > > Shouldn't that be: > >  Kernel priority: 0(high) to 98(low)    ==> user RT priority 99(high) to 1(low) > Thank you for your opinion. I think about corrected expression for quick chart to map between kernel space and user space in ftrace . > 100 items does not map to 99. Which begs the question, what can have > internal kernel priority 99? > ok. Below example is about kernel (static) priority 99 that you said. please, refer to http://www.kernel.org/doc/man-pages/online/pages/man2/sched_setscheduler.2.html webpage. For processes scheduled under one of the normal scheduling policies (SCHED_OTHER, SCHED_IDLE, SCHED_BATCH), sched_priority is not used in scheduling decisions (it must be specified as 0). int main (int argc, char **argv) { int pidnumber, ret; struct sched_param p; p.sched_priority = 0; <------ Kernel (static) priority. if (argc != 2) { printf("usage: setbatch \n"); exit(-1); } pidnumber = atol(argv[1]); /* 3 = Number of SCHED_BATCH Constant */ ret = sched_setscheduler(pidnumber, 3, &p); if (ret) { printf("could not set pid %d to SCHED_BATCH: err %d.\n", pid, ret); return -1; } printf("pid %d is SCHED_BATCH from now on.\n", pid); return 0; } >> + Kernel priority: 100(high) to 139(low) ==> user nice -20(high) to 19(low) >> + Kernel priority: 140                   ==> idle task priority >> + >> +Processes scheduled with SCHED_OTHER or SCHED_BATCH must be assigned >> +the static priority 0. Processes scheduled under SCHED_FIFO or SCHED_RR > > This line is confusing. "static priorty 0" really has no meaning here. > Those now enter the "nice" priorities, and this statement does not > represent what is shown in the ftrace output. > I agree with your opinion about exact understanding of ftrace output. I will remove this additional description to avoid confusing when we use this document as ftrace how to. >> +can have a static priority in the range 1 to 99. >> + (reference: $> man 2 sched_setscheduler) >> > > -- Steve > > -- Regards, GeunSik Lim -- 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/