Re: [GIT PULL 0/8] Annotation weekly ponies delivery

[Namhyung Kim]

Hi,

On Tue, 15 May 2012 00:06:25 +0900, Namhyung Kim wrote:
> 2012-05-14 (ì), 13:55 +0200, Ingo Molnar:
>> Another detail seems to be that the bug takes per-task-inherited 
>> profiling. Doing:
>> 
>>    perf record -a -e cycles:pp make -j64 bzImage
>> 
>> produces the expected number of events. Without the '-a' the bug 
>> Linus found triggers.
>> 
>> Similarly, 'perf top' does not trigger the bug - because it's 
>> using per CPU, not per task (inherited) profiling.
>> 
>
> perf_evlist__config_attrs() has this:
>
> 	if (evlist->cpus->map[0] < 0)
> 		opts->no_inherit = true;
>
> meaning that per task profiling won't enable event inheritance. I don't
> know why it's needed though.

I found this on commit 5d2cd90922c7 ("perf evsel: Fix use of inherit"):

-               /*
-                * Don't allow mmap() of inherited per-task counters. This
-                * would create a performance issue due to all children writing
-                * to the same buffer.
-                *
-                * FIXME:
-                * Proper fix is not to pass 'inherit' to perf_evsel__open*,
-                * but a 'flags' parameter, with 'group' folded there as well,
-                * then introduce a PERF_O_{MMAP,GROUP,INHERIT} enum, and if
-                * O_MMAP is set, emit a warning if cpu < 0 and O_INHERIT is
-                * set. Lets go for the minimal fix first tho.
-                */
-               evsel->attr.inherit = (cpus->map[cpu] >= 0) && inherit;

Hmm.. still don't know what to do then.

Thanks,
Namhyung
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/