Messages in this thread | | | Date | Sun, 11 Dec 2011 09:01:38 +0100 | From | Ingo Molnar <> | Subject | Re: [PATCH 2/4] perf_event: add PERF_COUNT_HW_REF_CPU_CYCLES generic PMU event |
| |
* Stephane Eranian <eranian@google.com> wrote:
> This event counts the number of reference core cpu cycles. > Reference means that the event increments at a constant rate > which is not subject to core CPU frequency adjustments. The > event may not count when the processor is in halted (low > power) state. As such, it may not be equivalent to wall clock > time. However, when the processor is not halted state, the > event keeps a constant correlation with wall clock time. > > Signed-off-by: Stephane Eranian <eranian@google.com> > --- > include/linux/perf_event.h | 1 + > 1 files changed, 1 insertions(+), 0 deletions(-) > > diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h > index 564769c..0885561 100644 > --- a/include/linux/perf_event.h > +++ b/include/linux/perf_event.h > @@ -54,6 +54,7 @@ enum perf_hw_id { > PERF_COUNT_HW_BUS_CYCLES = 6, > PERF_COUNT_HW_STALLED_CYCLES_FRONTEND = 7, > PERF_COUNT_HW_STALLED_CYCLES_BACKEND = 8, > + PERF_COUNT_HW_REF_CPU_CYCLES = 9,
Btw., that was what 'bus cycles' tried to do a long time ago: the constant, non-variable baseline heartbeat of the system.
We could simply rename that, fix the event tables where needed, and keep the ABI.
Just a small detail: how about naming it 'constant [frequency] CPU cycles'? That's a concept that might be present on other platforms as well.
CONST_FREQ_CYCLES or so. The 'CPU' can be dropped as well because it's not really the CPU's frequency anymore.
Thanks,
Ingo
| |