Re: [PATCH v3 4/4] perf,x86: add RAPL hrtimer support

2013-10-28 Thread Stephane Eranian
On Sat, Oct 26, 2013 at 7:53 PM, Jiri Olsa wrote: > On Sat, Oct 26, 2013 at 07:07:06PM +0200, Stephane Eranian wrote: >> On Fri, Oct 25, 2013 at 7:44 PM, Jiri Olsa wrote: >> > On Wed, Oct 23, 2013 at 02:58:05PM +0200, Stephane Eranian wrote: > > SNIP > >> >> + list_for_each_entry(event, &pmu-

Re: [PATCH v3 4/4] perf,x86: add RAPL hrtimer support

2013-10-26 Thread Jiri Olsa
On Sat, Oct 26, 2013 at 07:07:06PM +0200, Stephane Eranian wrote: > On Fri, Oct 25, 2013 at 7:44 PM, Jiri Olsa wrote: > > On Wed, Oct 23, 2013 at 02:58:05PM +0200, Stephane Eranian wrote: SNIP > >> + list_for_each_entry(event, &pmu->active_list, active_entry) { > >> + rapl_event_

Re: [PATCH v3 4/4] perf,x86: add RAPL hrtimer support

2013-10-26 Thread Stephane Eranian
On Fri, Oct 25, 2013 at 7:44 PM, Jiri Olsa wrote: > On Wed, Oct 23, 2013 at 02:58:05PM +0200, Stephane Eranian wrote: >> The RAPL PMU counters do not interrupt on overflow. >> Therefore, the kernel needs to poll the counters >> to avoid missing an overflow. This patch adds >> the hrtimer code to d

Re: [PATCH v3 4/4] perf,x86: add RAPL hrtimer support

2013-10-25 Thread Jiri Olsa
On Wed, Oct 23, 2013 at 02:58:05PM +0200, Stephane Eranian wrote: > The RAPL PMU counters do not interrupt on overflow. > Therefore, the kernel needs to poll the counters > to avoid missing an overflow. This patch adds > the hrtimer code to do this. > > The timer internval is calculated at boot ti

[PATCH v3 4/4] perf,x86: add RAPL hrtimer support

2013-10-23 Thread Stephane Eranian
The RAPL PMU counters do not interrupt on overflow. Therefore, the kernel needs to poll the counters to avoid missing an overflow. This patch adds the hrtimer code to do this. The timer internval is calculated at boot time based on the power unit used by the HW. Signed-off-by: Stephane Eranian -