Re: [RFC PATCH v5 01/16] perf stat: Add new field in stat_config to enable hardware aware grouping.

[Ian Rogers]

On Fri, Apr 12, 2024 at 2:08 PM <weilin.wang@xxxxxxxxx> wrote:
>
> From: Weilin Wang <weilin.wang@xxxxxxxxx>
>
> Hardware counter and event information could be used to help creating event
> groups that better utilize hardware counters and improve multiplexing.
>
> Reviewed-by: Ian Rogers <irogers@xxxxxxxxxx>
> Signed-off-by: Weilin Wang <weilin.wang@xxxxxxxxx>
> ---
>  tools/perf/builtin-stat.c     | 5 +++++
>  tools/perf/util/metricgroup.c | 5 +++++
>  tools/perf/util/metricgroup.h | 1 +
>  tools/perf/util/stat.h        | 1 +
>  4 files changed, 12 insertions(+)
>
> diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
> index 6bba1a89d030..c4a5f0984295 100644
> --- a/tools/perf/builtin-stat.c
> +++ b/tools/perf/builtin-stat.c
> @@ -2106,6 +2106,7 @@ static int add_default_attributes(void)
>                                                 stat_config.metric_no_threshold,
>                                                 stat_config.user_requested_cpu_list,
>                                                 stat_config.system_wide,
> +                                               stat_config.hardware_aware_grouping,
>                                                 &stat_config.metric_events);
>         }
>
> @@ -2139,6 +2140,7 @@ static int add_default_attributes(void)
>                                                 stat_config.metric_no_threshold,
>                                                 stat_config.user_requested_cpu_list,
>                                                 stat_config.system_wide,
> +                                               stat_config.hardware_aware_grouping,
>                                                 &stat_config.metric_events);
>         }
>
> @@ -2173,6 +2175,7 @@ static int add_default_attributes(void)
>                                                 /*metric_no_threshold=*/true,
>                                                 stat_config.user_requested_cpu_list,
>                                                 stat_config.system_wide,
> +                                               stat_config.hardware_aware_grouping,
>                                                 &stat_config.metric_events) < 0)
>                         return -1;
>         }
> @@ -2214,6 +2217,7 @@ static int add_default_attributes(void)
>                                                         /*metric_no_threshold=*/true,
>                                                         stat_config.user_requested_cpu_list,
>                                                         stat_config.system_wide,
> +                                                       stat_config.hardware_aware_grouping,
>                                                         &stat_config.metric_events) < 0)
>                                 return -1;
>
> @@ -2748,6 +2752,7 @@ int cmd_stat(int argc, const char **argv)
>                                                 stat_config.metric_no_threshold,
>                                                 stat_config.user_requested_cpu_list,
>                                                 stat_config.system_wide,
> +                                               stat_config.hardware_aware_grouping,
>                                                 &stat_config.metric_events);
>
>                 zfree(&metrics);
> diff --git a/tools/perf/util/metricgroup.c b/tools/perf/util/metricgroup.c
> index 79ef6095ab28..11613450725a 100644
> --- a/tools/perf/util/metricgroup.c
> +++ b/tools/perf/util/metricgroup.c
> @@ -1690,12 +1690,17 @@ int metricgroup__parse_groups(struct evlist *perf_evlist,
>                               bool metric_no_threshold,
>                               const char *user_requested_cpu_list,
>                               bool system_wide,
> +                             bool hardware_aware_grouping,
>                               struct rblist *metric_events)
>  {
>         const struct pmu_metrics_table *table = pmu_metrics_table__find();
>
>         if (!table)
>                 return -EINVAL;
> +       if (hardware_aware_grouping) {
> +               pr_debug("Use hardware aware grouping instead of traditional metric grouping method\n");
> +       }

nit: single line if statements shouldn't have curlies:
https://www.kernel.org/doc/html/v6.8/process/coding-style.html#placing-braces-and-spaces

Thanks,
Ian

> +
>
>         return parse_groups(perf_evlist, pmu, str, metric_no_group, metric_no_merge,
>                             metric_no_threshold, user_requested_cpu_list, system_wide,
> diff --git a/tools/perf/util/metricgroup.h b/tools/perf/util/metricgroup.h
> index d5325c6ec8e1..779f6ede1b51 100644
> --- a/tools/perf/util/metricgroup.h
> +++ b/tools/perf/util/metricgroup.h
> @@ -77,6 +77,7 @@ int metricgroup__parse_groups(struct evlist *perf_evlist,
>                               bool metric_no_threshold,
>                               const char *user_requested_cpu_list,
>                               bool system_wide,
> +                             bool hardware_aware_grouping,
>                               struct rblist *metric_events);
>  int metricgroup__parse_groups_test(struct evlist *evlist,
>                                    const struct pmu_metrics_table *table,
> diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h
> index d6e5c8787ba2..fd7a187551bd 100644
> --- a/tools/perf/util/stat.h
> +++ b/tools/perf/util/stat.h
> @@ -87,6 +87,7 @@ struct perf_stat_config {
>         bool                     metric_no_group;
>         bool                     metric_no_merge;
>         bool                     metric_no_threshold;
> +       bool                     hardware_aware_grouping;
>         bool                     stop_read_counter;
>         bool                     iostat_run;
>         char                     *user_requested_cpu_list;
> --
> 2.42.0
>