Messages in this thread | | | Date | Thu, 11 Sep 2014 15:37:11 +0200 | From | Jiri Olsa <> | Subject | Re: [PATCH V5 2/3] perf tools: parse the pmu event prefix and surfix |
| |
On Thu, Sep 11, 2014 at 01:31:48PM +0000, Liang, Kan wrote: > > > > SNIP > > > > > return 0; > > > } > > > > > > +static int > > > +comp_pmu(const void *p1, const void *p2) { > > > + struct perf_pmu_event_symbol *pmu1 = > > > + (struct perf_pmu_event_symbol *) p1; > > > + struct perf_pmu_event_symbol *pmu2 = > > > + (struct perf_pmu_event_symbol *) p2; > > > + > > > + return strcmp(pmu1->symbol, pmu2->symbol); } > > > + > > > +/* > > > + * Read the pmu events list from sysfs > > > + * Save it into perf_pmu_events_list > > > + */ > > > +static void perf_pmu__parse_init(void) { > > > + > > > + struct perf_pmu *pmu = NULL; > > > + struct perf_pmu_alias *alias; > > > + int len = 0; > > > + > > > > missing my previous comment being addressed: > > > > I just found it in Junk E-mail. I have no idea why. :( > > > --- > > Why do we need to call scan here? Looks like: > > pmu = pmu_lookup("cpu") > > > > should be enough.. and could be used below as well > > --- > > > > Could we use "perf_pmu__find" here? > pmu_lookup is a static function. > Also, it looks we don't need to lookup all the time if the PMU is loaded.
right, perf_pmu__find seems better
thanks, jirka
| |