Re: [PATCH] perf_events: fix time tracking in samples

[Stephane Eranian]

On Tue, Oct 19, 2010 at 6:52 PM, Peter Zijlstra <peterz@xxxxxxxxxxxxx> wrote:
> On Tue, 2010-10-19 at 18:47 +0200, Stephane Eranian wrote:
>> This patch corrects time tracking in samples. Without this patch
>> both time_enabled and time_running may be reported as zero when
>> user asks for PERF_SAMPLE_READ.
>>
>> You use PERF_SAMPLE_READ when you want to sample the values of
>> other counters in each sample. Because of multiplexing, it is
>> necessary to know both time_enable, time_running to be able
>> to scale counts correctly.
>>
>> We defer updating timing until we know it is really needed, i.e.,
>> only when we have PERF_SAMPLE_READ.
>>
>> With this patch, the libpfm4 example task_smpl now reports
>> correct counts (shown on 2.4GHz Core 2):
>>
>> $ task_smpl -p 2400000000 -e unhalted_core_cycles:u,instructions_retired:u,baclears Ânoploop 5
>> noploop for 5 seconds
>> IIP:0x000000004006d6 PID:5596 TID:5596 TIME:466,210,211,430 STREAM_ID:33 PERIOD:2,400,000,000 ENA=1,010,157,814 RUN=1,010,157,814 NR=3
>> Â Â Â 2,400,000,254 unhalted_core_cycles:u (33)
>> Â Â Â 2,399,273,744 instructions_retired:u (34)
>> Â Â Â 53,340 baclears (35)
>>
>> Signed-off-by: Stephane Eranian <eranian@xxxxxxxxxx>
>>
>> ---
>>
>> diff --git a/kernel/perf_event.c b/kernel/perf_event.c
>> index f309e80..04611dd 100644
>> --- a/kernel/perf_event.c
>> +++ b/kernel/perf_event.c
>> @@ -3494,6 +3494,9 @@ static void perf_output_read_group(struct perf_output_handle *handle,
>> Âstatic void perf_output_read(struct perf_output_handle *handle,
>> Â Â Â Â Â Â Â Â Â Â Â Â Â Âstruct perf_event *event)
>> Â{
>> + Â Â update_context_time(event->ctx);
>> + Â Â update_event_times(event);
>> +
>> Â Â Â if (event->attr.read_format & PERF_FORMAT_GROUP)
>> Â Â Â Â Â Â Â perf_output_read_group(handle, event);
>> Â Â Â else
>
>
> Right, except that this can actually corrupt the time measurements... :/
>
> Usually context times are updated under ctx->lock, and this is called
> from NMI context, which can interrupt ctx->lock..
>
Ok, I missed that. But I don't understand why you need the lock to
udpate the time. The lower-level clock is lockless if I recall. Can't you
use an atomic ops in update_context_time()?

> I was thinking about updating a local copy of the times, in that case
> you can only get funny times from samples, but it won't corrupt the
> actual running data.
>
You want time to be correct in every sample How would you detect
bogus timing?
--
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/