Re: [PATCH RFC 18/21] libperf evlist: Allow mixing per-thread and per-cpu mmaps

[Adrian Hunter]

On 3/05/22 23:29, Namhyung Kim wrote:
> On Fri, Apr 22, 2022 at 9:25 AM Adrian Hunter <adrian.hunter@xxxxxxxxx> wrote:
>>
>> mmap_per_evsel() will skip events that do not match the CPU, so all CPUs
>> can be iterated in any case.
>>
>> Signed-off-by: Adrian Hunter <adrian.hunter@xxxxxxxxx>
>> ---
> [...]
>> @@ -561,9 +538,12 @@ static int perf_evlist__nr_mmaps(struct perf_evlist *evlist)
>>  {
>>         int nr_mmaps;
>>
>> +       /* One for each CPU */
>>         nr_mmaps = perf_cpu_map__nr(evlist->all_cpus);
>> -       if (perf_cpu_map__empty(evlist->all_cpus))
>> -               nr_mmaps = perf_thread_map__nr(evlist->threads);
>> +       /* One for each thread */
>> +       nr_mmaps += perf_thread_map__nr(evlist->threads);
>> +       /* Minus the dummy CPU or dummy thread */
>> +       nr_mmaps -= 1;
> 
> I'm not sure it'd work for per-task events with default-per-cpu mode.

Thanks for noticing that. It ends up being too high which doesn't fail
immediately.  I need to add a check that nr_mmaps matches the number
of mmaps actually made.

> 
> Thanks,
> Namhyung
> 
>>
>>         return nr_mmaps;
>>  }