Date: Thu, 17 Mar 2016 08:06:29 -0400
From: Steven Rostedt <rostedt@goodmis.org>
To: Thomas Gleixner <tglx@linutronix.de>
Cc: Peter Zijlstra <peterz@infradead.org>,
        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: <20160317080629.1af8f733@grimm.local.home>
In-Reply-To: <alpine.DEB.2.11.1603171214530.3978@nanos>
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>
MIME-Version: 1.0
Content-Type: text/plain; charset=US-ASCII
Content-Transfer-Encoding: 7bit
Sender: linux-kernel-owner@vger.kernel.org
Content-Length: 901
Lines: 22

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?

-- Steve