RE: [PATCH V8 7/8] perf, x86: introduce PERF_RECORD_LOST_SAMPLES

[Liang, Kan]

> 
> 
> So I changed it slightly to the below; changes are:
> 
>  - record 'lost' events to all set bits; after all we really do not
>    know which event this sample belonged to, only logging to the first
>    set bit seems 'wrong'.

If so, the same dropped sample will be count multiple times. It's hard to know
the exact number of dropped samples.

> 
>  - dropped the @id field from the record, it is already included in the
>    @sample_id values.
> ---
> Subject: perf, x86: introduce PERF_RECORD_LOST_SAMPLES
> From: Kan Liang <kan.liang@xxxxxxxxx>
> Date: Wed, 6 May 2015 15:33:53 -0400
> 
> After enlarging the PEBS interrupt threshold, there may be some mixed up
> PEBS samples which are discarded by kernel. This patch drives the kernel to
> emit a PERF_RECORD_LOST_SAMPLES record with the number of possible
> discards when it is impossible to demux the samples. It makes sure the
> user is not left in the dark about such discards.
> 
> Cc: acme@xxxxxxxxxxxxx
> Cc: eranian@xxxxxxxxxx
> Cc: andi@xxxxxxxxxxxxxx
> Cc: mingo@xxxxxxxxxx
> Signed-off-by: Kan Liang <kan.liang@xxxxxxxxx>
> Signed-off-by: Peter Zijlstra (Intel) <peterz@xxxxxxxxxxxxx>
> Link: http://lkml.kernel.org/r/1430940834-8964-8-git-send-email-
> kan.liang@xxxxxxxxx
> ---
>  arch/x86/kernel/cpu/perf_event_intel_ds.c |   22 ++++++++++++++++----
>  include/linux/perf_event.h                |    3 ++
>  include/uapi/linux/perf_event.h           |   12 ++++++++++
>  kernel/events/core.c                      |   33
> ++++++++++++++++++++++++++++++
>  4 files changed, 66 insertions(+), 4 deletions(-)
> 
> --- a/arch/x86/kernel/cpu/perf_event_intel_ds.c
> +++ b/arch/x86/kernel/cpu/perf_event_intel_ds.c
> @@ -1124,8 +1124,9 @@ static void intel_pmu_drain_pebs_nhm(str
>  	struct debug_store *ds = cpuc->ds;
>  	struct perf_event *event;
>  	void *base, *at, *top;
> -	int bit;
>  	short counts[MAX_PEBS_EVENTS] = {};
> +	short error[MAX_PEBS_EVENTS] = {};
> +	int bit, i;
> 
>  	if (!x86_pmu.pebs_active)
>  		return;
> @@ -1169,20 +1170,33 @@ static void intel_pmu_drain_pebs_nhm(str
>  			/* slow path */
>  			pebs_status = p->status & cpuc->pebs_enabled;
>  			pebs_status &= (1ULL << MAX_PEBS_EVENTS) - 1;
> -			if (pebs_status != (1 << bit))
> +			if (pebs_status != (1 << bit)) {
> +				for (i = 0; 1 < MAX_PEBS_EVENTS; i++) {
> +					if (pebs_status & (1 << i))
> +						error[i]++;
> +				}
>  				continue;
> +			}
>  		}
>  		counts[bit]++;
>  	}
> 
>  	for (bit = 0; bit < x86_pmu.max_pebs_events; bit++) {
> -		if (counts[bit] == 0)
> +		if ((counts[bit] == 0) && (error[bit] == 0))
>  			continue;
> +
>  		event = cpuc->events[bit];
>  		WARN_ON_ONCE(!event);
>  		WARN_ON_ONCE(!event->attr.precise_ip);
> 
> -		__intel_pmu_pebs_event(event, iregs, base, top, bit,
> counts[bit]);
> +		/* log dropped samples number */
> +		if (error[bit])
> +			perf_log_lost_samples(event, error[bit]);
> +
> +		if (counts[bit]) {
> +			__intel_pmu_pebs_event(event, iregs, base,
> +					       top, bit, counts[bit]);
> +		}
>  	}
>  }
> 
> --- a/include/linux/perf_event.h
> +++ b/include/linux/perf_event.h
> @@ -747,6 +747,9 @@ perf_event__output_id_sample(struct perf
>  			     struct perf_output_handle *handle,
>  			     struct perf_sample_data *sample);
> 
> +extern void
> +perf_log_lost_samples(struct perf_event *event, u64 lost);
> +
>  static inline bool is_sampling_event(struct perf_event *event)  {
>  	return event->attr.sample_period != 0;
> --- a/include/uapi/linux/perf_event.h
> +++ b/include/uapi/linux/perf_event.h
> @@ -800,6 +800,18 @@ enum perf_event_type {
>  	 */
>  	PERF_RECORD_ITRACE_START		= 12,
> 
> +	/*
> +	 * Records the dropped/lost sample number.
> +	 *
> +	 * struct {
> +	 *	struct perf_event_header	header;
> +	 *
> +	 *	u64				lost;
> +	 *	struct sample_id		sample_id;
> +	 * };
> +	 */
> +	PERF_RECORD_LOST_SAMPLES		= 13,
> +
>  	PERF_RECORD_MAX,			/* non-ABI */
>  };
> 
> --- a/kernel/events/core.c
> +++ b/kernel/events/core.c
> @@ -5947,6 +5947,39 @@ void perf_event_aux_event(struct perf_ev  }
> 
>  /*
> + * Lost/dropped samples logging
> + */
> +void perf_log_lost_samples(struct perf_event *event, u64 lost) {
> +	struct perf_output_handle handle;
> +	struct perf_sample_data sample;
> +	int ret;
> +
> +	struct {
> +		struct perf_event_header	header;
> +		u64				lost;
> +	} lost_samples_event = {
> +		.header = {
> +			.type = PERF_RECORD_LOST_SAMPLES,
> +			.misc = 0,
> +			.size = sizeof(lost_samples_event),
> +		},
> +		.lost		= lost,
> +	};
> +
> +	perf_event_header__init_id(&lost_samples_event.header,
> &sample,
> +event);
> +
> +	ret = perf_output_begin(&handle, event,
> +				lost_samples_event.header.size);
> +	if (ret)
> +		return;
> +
> +	perf_output_put(&handle, lost_samples_event);
> +	perf_event__output_id_sample(event, &handle, &sample);
> +	perf_output_end(&handle);
> +}
> +
> +/*
>   * IRQ throttle logging
>   */
> 
> --
> 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/
--
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/