attr inherit vs inherit_stat

attr inherit vs inherit_stat

[Vince Weaver]

Hello

I'm trying to figure out the difference between the "inherit" and
"inherit_stat" bitfields in the perf_event_attr structure.

Both seem to have similar functionality, and the code in core.c
is hard to follow.

Does anyone have any idea?

Thanks,

Vince
vweaver1@eecs.utk.edu

Re: attr inherit vs inherit_stat

[Namhyung Kim]

On Tue, 7 Aug 2012 15:47:32 -0400, Vince Weaver wrote:
> Hello

Hello Vince,

>
> I'm trying to figure out the difference between the "inherit" and
> "inherit_stat" bitfields in the perf_event_attr structure.
>
> Both seem to have similar functionality, and the code in core.c
> is hard to follow.
>
> Does anyone have any idea?

AFAIK the "inherit" field determines whether the event is inherited to a
child process/thread.  The "inherit_stat" is only meaningful when the
"inherit" field is also set and it'll preserve (saved) event counts
between context switch of the inherited processes/threads.

Thanks,
Namhyung

Re: attr inherit vs inherit_stat

[Vince Weaver]

On Tue, 4 Sep 2012, Namhyung Kim wrote:
> 
> AFAIK the "inherit" field determines whether the event is inherited to a
> child process/thread.  The "inherit_stat" is only meaningful when the
> "inherit" field is also set and it'll preserve (saved) event counts
> between context switch of the inherited processes/threads.

Thank you for taking the time to answer!

I'm still trying to construct a test case that shows the difference but 
I'm failing.

Aren't the stats *always* saved on context switch?

Does this affect what happens when you read the perf_event fd in the 
inherited threads, or only from the master thread?

What is the expected behavior if you set inherit_thread but do not set 
inherit?

Thanks for any clarifications you can provide,

Vince

Re: attr inherit vs inherit_stat

[Namhyung Kim]

(Adding peterz in case he has a time to answer)

On Thu, 6 Sep 2012 11:19:21 -0400, Vince Weaver wrote:
> On Tue, 4 Sep 2012, Namhyung Kim wrote:
>> 
>> AFAIK the "inherit" field determines whether the event is inherited to a
>> child process/thread.  The "inherit_stat" is only meaningful when the
>> "inherit" field is also set and it'll preserve (saved) event counts
>> between context switch of the inherited processes/threads.
>
> Thank you for taking the time to answer!
>
> I'm still trying to construct a test case that shows the difference but 
> I'm failing.

Please note that my understanding of perf core code is not firm enough
so there might be some mistakes. ;-)


>
> Aren't the stats *always* saved on context switch?

If both of them are cloned from the same parent event context and
there's no event added in the meantime.

Please see perf_event_context_sched_out() calling perf_event_sync_stat.


>
> Does this affect what happens when you read the perf_event fd in the 
> inherited threads, or only from the master thread?

It might.  But I guess the master thread doesn't get affected from that.


>
> What is the expected behavior if you set inherit_thread but do not set 
> inherit?

You meant inherit_stat, right?  If so, it looks it'd be a nop since
there's no inherited events.  Maybe the perf tools can be changed to
warn about that.

Thanks,
Namhyung

Re: attr inherit vs inherit_stat

[Peter Zijlstra]

On Fri, 2012-09-07 at 10:20 +0900, Namhyung Kim wrote:
> (Adding peterz in case he has a time to answer)
> 
> On Thu, 6 Sep 2012 11:19:21 -0400, Vince Weaver wrote:
> > On Tue, 4 Sep 2012, Namhyung Kim wrote:
> >> 
> >> AFAIK the "inherit" field determines whether the event is inherited to a
> >> child process/thread.  The "inherit_stat" is only meaningful when the
> >> "inherit" field is also set and it'll preserve (saved) event counts
> >> between context switch of the inherited processes/threads.
> >
> > Thank you for taking the time to answer!
> >
> > I'm still trying to construct a test case that shows the difference but 
> > I'm failing.

inherit && inherit_stat preserves the counts per-task and issues a
PERF_RECORD_READ when a task dies. This allows a per-task stat on an
inherited process hierarchy.

> > Aren't the stats *always* saved on context switch?

No, they're normally swizzled around, the only thing we care about is
the total event count for the entire task-set, not the count of the
individual tasks.

> > Does this affect what happens when you read the perf_event fd in the 
> > inherited threads, or only from the master thread?

read() on an inherited event gives the total count of the entire
hierarchy.

> > What is the expected behavior if you set inherit_thread but do not set 
> > inherit?
> 
> You meant inherit_stat, right?  If so, it looks it'd be a nop since
> there's no inherited events.  Maybe the perf tools can be changed to
> warn about that.

Right that would be a pointless configuration.