Messages in this thread | | | Date | Fri, 18 May 2012 13:03:57 +0200 | From | Borislav Petkov <> | Subject | Re: [PATCH 1/2] perf: Add persistent event facilities |
| |
On Fri, May 18, 2012 at 12:14:00PM +0200, Peter Zijlstra wrote: > On Wed, 2012-03-21 at 15:34 +0100, Borislav Petkov wrote: > > +int perf_add_persistent_on_cpu(int cpu, struct pers_event_desc *desc, > > + struct dentry *dir, unsigned nr_pages) > > OK, so this creates an even and registers it somewhere in debugfs.
(debugfs)/mce/
> - you allow an arbitrary place in debugfs; this might make finding > them 'interesting'. Should we put them all in the same place?
My take on this is that we want to be able to make the same events we have now, persistent. Basically not trace for the duration of a child process but in a process-agnostic way, system-wide.
In that case, we probably want to be able to mark events as persistent, maybe add another node in debugfs:
(debugfs)/tracing/events/mce/mce_record/attr
which can be used for flags or whatever, or something to that effect...
> - persistent events created from userspace don't seem to get a debugfs > entry and will be lost forever?
Yeah, see above.
> In general I think a little more exploring of the semantics and > ramifications might be in order.
Absolutely!
Thanks.
-- Regards/Gruss, Boris.
Advanced Micro Devices GmbH Einsteinring 24, 85609 Dornach GM: Alberto Bozzo Reg: Dornach, Landkreis Muenchen HRB Nr. 43632 WEEE Registernr: 129 19551
| |