Date: Thu, 17 Mar 2016 13:13:33 +0100
From: Peter Zijlstra <peterz@infradead.org>
To: Steven Rostedt <rostedt@goodmis.org>
Cc: Thomas Gleixner <tglx@linutronix.de>, Nicholas Mc Guire <der.herr@hofr.at>,
        Joel Fernandes <agnel.joel@gmail.com>,
        Greg Kroah-Hartman <greg@kroah.com>, linux-rt-users@vger.kernel.org,
        Linux Kernel Mailing List <linux-kernel@vger.kernel.org>,
        kernelnewbies <kernelnewbies@nl.linux.org>,
        Ingo Molnar <mingo@redhat.com>
Subject: Re: RFC on fixing mutex spinning on owner
Message-ID: <20160317121333.GU6344@twins.programming.kicks-ass.net>
References: <CAD=GYpbHjcsuQSnNPL4SCv-r=Me6oiH7dJ98a64udbakWLaUjQ@mail.gmail.com>
 <20160316233530.GA8731@kroah.com>
 <CAD=GYpZVGwfk8Y8WTQpdgdm5qgxjsi_gVrnOswuWitEbhaWPbw@mail.gmail.com>
 <20160316221751.71816309@grimm.local.home>
 <20160317073605.GM6344@twins.programming.kicks-ass.net>
 <20160317080526.GB6679@osadl.at>
 <20160317101823.GQ6344@twins.programming.kicks-ass.net>
 <alpine.DEB.2.11.1603171214530.3978@nanos>
 <20160317080629.1af8f733@grimm.local.home>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <20160317080629.1af8f733@grimm.local.home>
User-Agent: Mutt/1.5.21 (2012-12-30)
Sender: linux-kernel-owner@vger.kernel.org
Content-Length: 1074
Lines: 24

On Thu, Mar 17, 2016 at 08:06:29AM -0400, Steven Rostedt wrote:
> On Thu, 17 Mar 2016 12:16:11 +0100 (CET)
> Thomas Gleixner <tglx@linutronix.de> wrote:
> 
> > On Thu, 17 Mar 2016, Peter Zijlstra wrote:
> > > Also, maybe the tracer should measure the time from need_resched()
> > > getting true until the next preemption point, instead of the entire time
> > > preemption was disabled. Which would avoid the entire issue altogether.  
> > 
> > Well, that only gives you the information on a actual preemption, but not
> > information about long preempt disabled regions which can cause a problem
> > eventually.
> > 
> 
> Actually, I was thinking the reverse. If need_resched() is called and
> is false, then do a reset of the preemption time. But if need_resched()
> is true, then do nothing, as that would measure the total time preempt
> disable was set and a task could not schedule.
> 
> Question is, should this be a hook and each location audited, or add
> this to need_resched() itself?

Is anybody calling need_resched() and then not doing anything with the
value?