Messages in this thread | | | Date | Wed, 28 May 2014 10:09:10 -0400 | From | Steven Rostedt <> | Subject | Re: [PATCH v2] tracing: Don't account for cpu idle time with irqsoff tracers |
| |
On Wed, 28 May 2014 09:28:52 +0200 Peter Zijlstra <peterz@infradead.org> wrote:
> On Tue, May 27, 2014 at 07:30:50PM -0400, Steven Rostedt wrote: > > Paul, Peter, see anything wrong with this? > > You mean, aside from that it won't actually apply due to that code > having been massively overhauled? > > I suppose the same thing Arnd mentioned, the cpuidle_enter() thing can > be huge, but is we're going to have to push this down into all cpuidle > drivers we're not going to be happy. >
I believe that the stop/start_critical_timings() can nest. If not, I can make them do so. Thus, we could start adding them in the depths of the cpuidle drivers. If we miss one, we may not notice until someone reports a large latency due to it. And that is only if the driver itself calls local_irq_save/restore().
-- Steve
| |