Messages in this thread | | | Date | Fri, 10 May 2013 11:53:45 +0200 | From | Peter Zijlstra <> | Subject | Re: [PATCH 0/9] perf: Adding better precise_ip field handling |
| |
On Fri, May 10, 2013 at 11:40:53AM +0200, Jiri Olsa wrote: > nope, but I need a automated way to find out if PEBS > is supported in system
Create an event, see what happens ;-) But I suppose you want to know if it should have worked vs does it actually work? Yeah, I suppose what you did is the right thing there.
I was just completely missing the rationale earlier.
> > > having maximum precise enabled with just single 'p' seemed > > > like good idea > > > > Doesn't seem like to me; that takes away the possibility to use less. > > hm, we could have another modifier to get system precise value > 'P' maybe.. and keep the 'p' logic
That might be a possibility indeed.
> > Also, you really don't need the max_precise for that either. At worst you'll > > have a number of unsuccessful event creations. > > so you mean just detect that by opening events with increasing > precise and see how far we could get.. could be I guess, though > the 'precise' sysfs attribute seems more fit to me
The other way around, start at ppp end at !p, then use the one that worked.
| |