Re: [PATCH 9/9] perf/x86: add syfs entry to disable HT bug workaround

[Matt Fleming]

On 5 June 2014 11:19, Stephane Eranian <eranian@xxxxxxxxxx> wrote:
> How would you know that you have a uniform workload from inside
> the kernel?

That's what I'm asking you ;-)

>> Does cpu_sibling_map not give you some indication of whether HT is
>> enabled? I think the topology_thread_cpumask() is the topology API for
>> that. But I could most definitely be wrong. Hopefully someone on the
>> Cc list will know.
>>
> Remember trying some of that, but when perf_event is initialized, those
> masks are not yet setup properly.

Oh, bummer.

If there's no way to detect whether we should enable this workaround
at runtime (and it sounds like there isn't a good way), then that's
fair enough.

We should think twice about allowing it to be disabled via sysfs,
however. Because what is guaranteed to happen is that some user will
report getting bogus results from perf for these events and we'll
spend days trying to figure out why, only to discover they disabled
the workaround and didn't tell us or didn't realise that they'd
disabled it.

If the workaround is low overhead, can't we just leave it enabled?
--
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/