Messages in this thread | | | Date | Wed, 2 Dec 2015 15:10:03 +0100 | From | Frederic Weisbecker <> | Subject | Re: [PATCH 2/7] nohz: New tick dependency mask |
| |
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.
| |