Re: [RFC PATCH 0/4] perf: Custom contexts

[Frederic Weisbecker]

On Mon, Mar 14, 2011 at 06:03:15PM -0300, Arnaldo Carvalho de Melo wrote:
> Em Mon, Mar 14, 2011 at 09:51:02PM +0100, Frederic Weisbecker escreveu:
> > On Mon, Mar 14, 2011 at 05:43:41PM -0300, Arnaldo Carvalho de Melo wrote:
> > > > - Count instructions inside softirqs, outside softirqs and everywhere:
> 
> > > > 	$ perf stat -e irq:softirq_entry -e irq:softirq_exit \
> > > > 		-e instructions --starter 0 --stopper 1 --enable-on-starter \
> > > > 		-e instructions --starter 1 --stopper 0 \
> > > > 		-e instructions ./perf bench sched messaging
> 
> > > $ perf record -e instructions@irq:softirq_entry..irq:softirq_exit \
> > > 	      -e instructions@irq:softirq_exit..irq:softirq_entry \
> > > 	      -e instructions \
> > > 	perf bench sched messaging
> 
> > Agreed that's nice but may be more as a shortcut than a full replacement?
> > Otherwise it becomes hard or unreadable to define a filter on a starter. Or
> > a starter on a starter.
> 
> Sure, multiple ways to express ranges probably is ok, with more complex
> ones for more complex cases, like the way you did, that first defines an
> evlist that is the set of starters/stoppers and then evsel->evidx to add
> starters/stoppers to later events.

Yep.

> But starter on a starter? Couldn't grok, could you provide an example?

I have no strong example in mind.

But one may want to count instructions when we are in an interrupt and
lock A is held.

Or count instruction when A and B are held. Or count instruction in
page faults happening in read() syscall.

Event range define a state, and anytime you need to profile/trace a
desired stacked state, starters on starters can be a good solution,
thus even a common practice.
 
> But I could think of this as a way to express filters:
> 
> $ perf record -e instructions@irq:irq:irq_handler_entry(irq=eth0)..irq:irq_handler_exit(\1) \
> 	      -e instructions \
> 	netperf
> 
> looks quite natural for someone used to git and sed, i.e. developers :)

Yeah indeed, I like filters defined in parenthesis after the event!
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/