Re: [PATCH 06/19] perf stat: Add 'needs_sort' argument to cpu_aggr_map__new()

[Ian Rogers]

On Sun, Oct 9, 2022 at 10:36 PM Namhyung Kim <namhyung@xxxxxxxxxx> wrote:
>
> In case of no aggregation, it needs to keep the original (cpu) ordering
> in the aggr_map so that it can be in sync with the cpu map.  This will
> make the code easier to handle AGGR_NONE similar to others.
>

The CPU map is sorted and so sorting the aggr_map should be fine. If
the data is already sorted then it is O(n) to sort. I think this is
preferable to having additional complexity around whether the aggr_map
is sorted.

Thanks,
Ian

> Signed-off-by: Namhyung Kim <namhyung@xxxxxxxxxx>
> ---
>  tools/perf/builtin-stat.c | 7 +++++--
>  tools/perf/util/cpumap.c  | 6 ++++--
>  tools/perf/util/cpumap.h  | 2 +-
>  3 files changed, 10 insertions(+), 5 deletions(-)
>
> diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
> index b00ef20aef5b..e5ddf60ab31d 100644
> --- a/tools/perf/builtin-stat.c
> +++ b/tools/perf/builtin-stat.c
> @@ -1461,8 +1461,9 @@ static int perf_stat_init_aggr_mode(void)
>         aggr_cpu_id_get_t get_id = aggr_mode__get_aggr(stat_config.aggr_mode);
>
>         if (get_id) {
> +               bool needs_sort = stat_config.aggr_mode != AGGR_NONE;
>                 stat_config.aggr_map = cpu_aggr_map__new(evsel_list->core.user_requested_cpus,
> -                                                        get_id, /*data=*/NULL);
> +                                                        get_id, /*data=*/NULL, needs_sort);
>                 if (!stat_config.aggr_map) {
>                         pr_err("cannot build %s map", aggr_mode__string[stat_config.aggr_mode]);
>                         return -1;
> @@ -1677,11 +1678,13 @@ static int perf_stat_init_aggr_mode_file(struct perf_stat *st)
>  {
>         struct perf_env *env = &st->session->header.env;
>         aggr_cpu_id_get_t get_id = aggr_mode__get_aggr_file(stat_config.aggr_mode);
> +       bool needs_sort = stat_config.aggr_mode != AGGR_NONE;
>
>         if (!get_id)
>                 return 0;
>
> -       stat_config.aggr_map = cpu_aggr_map__new(evsel_list->core.user_requested_cpus, get_id, env);
> +       stat_config.aggr_map = cpu_aggr_map__new(evsel_list->core.user_requested_cpus,
> +                                                get_id, env, needs_sort);
>         if (!stat_config.aggr_map) {
>                 pr_err("cannot build %s map", aggr_mode__string[stat_config.aggr_mode]);
>                 return -1;
> diff --git a/tools/perf/util/cpumap.c b/tools/perf/util/cpumap.c
> index 60209fe87456..6e3fcf523de9 100644
> --- a/tools/perf/util/cpumap.c
> +++ b/tools/perf/util/cpumap.c
> @@ -234,7 +234,7 @@ static int aggr_cpu_id__cmp(const void *a_pointer, const void *b_pointer)
>
>  struct cpu_aggr_map *cpu_aggr_map__new(const struct perf_cpu_map *cpus,
>                                        aggr_cpu_id_get_t get_id,
> -                                      void *data)
> +                                      void *data, bool needs_sort)
>  {
>         int idx;
>         struct perf_cpu cpu;
> @@ -270,8 +270,10 @@ struct cpu_aggr_map *cpu_aggr_map__new(const struct perf_cpu_map *cpus,
>                 if (trimmed_c)
>                         c = trimmed_c;
>         }
> +
>         /* ensure we process id in increasing order */
> -       qsort(c->map, c->nr, sizeof(struct aggr_cpu_id), aggr_cpu_id__cmp);
> +       if (needs_sort)
> +               qsort(c->map, c->nr, sizeof(struct aggr_cpu_id), aggr_cpu_id__cmp);
>
>         return c;
>
> diff --git a/tools/perf/util/cpumap.h b/tools/perf/util/cpumap.h
> index b2ff648bc417..da28b3146ef9 100644
> --- a/tools/perf/util/cpumap.h
> +++ b/tools/perf/util/cpumap.h
> @@ -97,7 +97,7 @@ typedef struct aggr_cpu_id (*aggr_cpu_id_get_t)(struct perf_cpu cpu, void *data)
>   */
>  struct cpu_aggr_map *cpu_aggr_map__new(const struct perf_cpu_map *cpus,
>                                        aggr_cpu_id_get_t get_id,
> -                                      void *data);
> +                                      void *data, bool needs_sort);
>
>  bool aggr_cpu_id__equal(const struct aggr_cpu_id *a, const struct aggr_cpu_id *b);
>  bool aggr_cpu_id__is_empty(const struct aggr_cpu_id *a);
> --
> 2.38.0.rc1.362.ged0d419d3c-goog
>