Re: [PATCH 46/49] perf stat: Filter out unmatched aggregation for hybrid event

[Arnaldo Carvalho de Melo <acme@kernel.org>]

Em Mon, Feb 08, 2021 at 07:25:43AM -0800, kan.liang@linux.intel.com escreveu:
> From: Jin Yao <yao.jin@linux.intel.com>
> 
> perf-stat has supported some aggregation modes, such as --per-core,
> --per-socket and etc. While for hybrid event, it may only available
> on part of cpus. So for --per-core, we need to filter out the
> unavailable cores, for --per-socket, filter out the unavailable
> sockets, and so on.
> 
> Before:
> 
> root@otcpl-adl-s-2:~# ./perf stat --per-core -e cpu_core/cycles/ -a -- sleep 1
> 
>  Performance counter stats for 'system wide':
> 
> S0-D0-C0           2            311,114      cycles [cpu_core]

Why not use the pmu style event name, i.e.:

S0-D0-C0           2            311,114        cpu_core/cycles/

?

> S0-D0-C4           2             59,784      cycles [cpu_core]
> S0-D0-C8           2            121,287      cycles [cpu_core]
> S0-D0-C12          2          2,690,245      cycles [cpu_core]
> S0-D0-C16          2          2,060,545      cycles [cpu_core]
> S0-D0-C20          2          3,632,251      cycles [cpu_core]
> S0-D0-C24          2            775,736      cycles [cpu_core]
> S0-D0-C28          2            742,020      cycles [cpu_core]
> S0-D0-C32          0      <not counted>      cycles [cpu_core]
> S0-D0-C33          0      <not counted>      cycles [cpu_core]
> S0-D0-C34          0      <not counted>      cycles [cpu_core]
> S0-D0-C35          0      <not counted>      cycles [cpu_core]
> S0-D0-C36          0      <not counted>      cycles [cpu_core]
> S0-D0-C37          0      <not counted>      cycles [cpu_core]
> S0-D0-C38          0      <not counted>      cycles [cpu_core]
> S0-D0-C39          0      <not counted>      cycles [cpu_core]
> 
>        1.001779842 seconds time elapsed
> 
> After:
> 
> root@otcpl-adl-s-2:~# ./perf stat --per-core -e cpu_core/cycles/ -a -- sleep 1
> 
>  Performance counter stats for 'system wide':
> 
> S0-D0-C0           2          1,088,230      cycles [cpu_core]
> S0-D0-C4           2             57,228      cycles [cpu_core]
> S0-D0-C8           2             98,327      cycles [cpu_core]
> S0-D0-C12          2          2,741,955      cycles [cpu_core]
> S0-D0-C16          2          2,090,432      cycles [cpu_core]
> S0-D0-C20          2          3,192,108      cycles [cpu_core]
> S0-D0-C24          2          2,910,752      cycles [cpu_core]
> S0-D0-C28          2            388,696      cycles [cpu_core]
> 
> Reviewed-by: Andi Kleen <ak@linux.intel.com>
> Signed-off-by: Jin Yao <yao.jin@linux.intel.com>
> ---
>  tools/perf/util/stat-display.c | 20 ++++++++++++++++++++
>  1 file changed, 20 insertions(+)
> 
> diff --git a/tools/perf/util/stat-display.c b/tools/perf/util/stat-display.c
> index 21a3f80..fa11572 100644
> --- a/tools/perf/util/stat-display.c
> +++ b/tools/perf/util/stat-display.c
> @@ -630,6 +630,20 @@ static void aggr_cb(struct perf_stat_config *config,
>  	}
>  }
>  
> +static bool aggr_id_hybrid_matched(struct perf_stat_config *config,
> +				   struct evsel *counter, struct aggr_cpu_id id)
> +{
> +	struct aggr_cpu_id s;
> +
> +	for (int i = 0; i < evsel__nr_cpus(counter); i++) {
> +		s = config->aggr_get_id(config, evsel__cpus(counter), i);
> +		if (cpu_map__compare_aggr_cpu_id(s, id))
> +			return true;
> +	}
> +
> +	return false;
> +}
> +
>  static void print_counter_aggrdata(struct perf_stat_config *config,
>  				   struct evsel *counter, int s,
>  				   char *prefix, bool metric_only,
> @@ -643,6 +657,12 @@ static void print_counter_aggrdata(struct perf_stat_config *config,
>  	double uval;
>  
>  	ad.id = id = config->aggr_map->map[s];
> +
> +	if (perf_pmu__hybrid_exist() &&
> +	    !aggr_id_hybrid_matched(config, counter, id)) {
> +		return;
> +	}
> +
>  	ad.val = ad.ena = ad.run = 0;
>  	ad.nr = 0;
>  	if (!collect_data(config, counter, aggr_cb, &ad))
> -- 
> 2.7.4
> 

-- 

- Arnaldo