Re: Removal of events for unsupported architectures or processor models
Aaro Koskinen <[email protected]>
| Newsgroups | gmane.linux.oprofile |
|---|---|
| Message-ID | <[email protected]> |
On Wed, Jul 23, 2014 at 09:17:43AM -0500, Maynard Johnson wrote: > Not a stupid question at all. Right now, timer mode is > supported only with the "legacy" opcontrol-based profiler. > The operf profiler could, theoretically, support a timer-like option > (e.g., configuring perf_events with PERF_COUNT_SW_CPU_CLOCK). I've not > been motivated to add this myself, but would certainly review patches > if anyone would like to contribute such support (after 1.0 is released). > But that may not help for your OMAP case anyway if perf_events is not > supported at all for that processor type. Ok, thanks, I will try look into this at some point. I'm not yet too familiar with the perf world, but I think OMAP should support perf_events in general, but it's just some chip revisions where the HW counters could not be used / did not work. > So, as I mentioned already, for those architectures or specific > processor types that are not supported by perf_events, users should use > opcontrol with oprofile release 0.9.9. Right, but I would also like to stick with a single SW version / source tree for all my platforms. :) A. ------------------------------------------------------------------------------ Want fast and easy access to all the code in your enterprise? Index and search up to 200,000 lines of code with a free copy of Black Duck Code Sight - the same software that powers the world's largest code search on Ohloh, the Black Duck Open Hub! Try it now. http://p.sf.net/sfu/bds