Re: [PATCH 2/7] nohz: New tick dependency mask

[Frederic Weisbecker <fweisbec@gmail.com>]

On Wed, Dec 02, 2015 at 01:45:31PM +0100, Peter Zijlstra wrote:
> On Tue, Dec 01, 2015 at 11:20:28PM +0100, Frederic Weisbecker wrote:
> 
> > > > +static void trace_tick_dependency(unsigned long dep)
> > > > +{
> > > > +	if (dep & TICK_POSIX_TIMER_MASK) {
> > > > +		trace_tick_stop(0, "posix timers running\n");
> > > > +		return;
> > > > +	}
> > > > +
> > > > +	if (dep & TICK_PERF_EVENTS_MASK) {
> > > > +		trace_tick_stop(0, "perf events running\n");
> > > > +		return;
> > > > +	}
> > > > +
> > > > +	if (dep & TICK_SCHED_MASK) {
> > > > +		trace_tick_stop(0, "more than 1 task in runqueue\n");
> > > > +		return;
> > > > +	}
> > > > +
> > > > +	if (dep & TICK_CLOCK_UNSTABLE_MASK)
> > > > +		trace_tick_stop(0, "unstable sched clock\n");
> > > > +}
> > > 
> > > I would suggest ditching the strings and using the
> > 
> > Using a code value instead?
> 
> Duh, it seems I forgot to finish that sentence :/
> 
> I meant to say use the ftrace enum stuff. So yes, you encode a value and
> the ftrace printing muck will generate a string if and when required.

Right I first wanted to avoid that because it makes parsing more complicated for
tools but probably it works fine now with libtraceevents.