[PATCH] perf stat: Do not allow --for-each-cgroup without cpu

[PATCH] perf stat: Do not allow --for-each-cgroup without cpu

[Namhyung Kim]

The cgroup mode should work with cpu events.  Warn if --for-each-cgroup
option is used with a task target like existing -G option.

  # perf stat --for-each-cgroup . sleep 1
  both cgroup and no-aggregation modes only available in system-wide mode

   Usage: perf stat [<options>] [<command>]

      -G, --cgroup <name>   monitor event in cgroup name only
      -A, --no-aggr         disable CPU count aggregation
      -a, --all-cpus        system-wide collection from all CPUs
          --for-each-cgroup <name>
                            expand events for each cgroup

Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
 tools/perf/builtin-stat.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 84de61795e67..1a64aebc0d2f 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -2386,7 +2386,8 @@ int cmd_stat(int argc, const char **argv)
 	 * --per-thread is aggregated per thread, we dont mix it with cpu mode
 	 */
 	if (((stat_config.aggr_mode != AGGR_GLOBAL &&
-	      stat_config.aggr_mode != AGGR_THREAD) || nr_cgroups) &&
+	      stat_config.aggr_mode != AGGR_THREAD) ||
+	     (nr_cgroups || stat_config.cgroup_list)) &&
 	    !target__has_cpu(&target)) {
 		fprintf(stderr, "both cgroup and no-aggregation "
 			"modes only available in system-wide mode\n");
@@ -2394,6 +2395,7 @@ int cmd_stat(int argc, const char **argv)
 		parse_options_usage(stat_usage, stat_options, "G", 1);
 		parse_options_usage(NULL, stat_options, "A", 1);
 		parse_options_usage(NULL, stat_options, "a", 1);
+		parse_options_usage(NULL, stat_options, "for-each-cgroup", 0);
 		goto out;
 	}
 
-- 
2.33.0.259.gc128427fd7-goog

Re: [PATCH] perf stat: Do not allow --for-each-cgroup without cpu

[Arnaldo Carvalho de Melo]

Em Mon, Aug 30, 2021 at 10:02:00AM -0700, Namhyung Kim escreveu:
> The cgroup mode should work with cpu events.  Warn if --for-each-cgroup
> option is used with a task target like existing -G option.
> 
>   # perf stat --for-each-cgroup . sleep 1
>   both cgroup and no-aggregation modes only available in system-wide mode
> 
>    Usage: perf stat [<options>] [<command>]
> 
>       -G, --cgroup <name>   monitor event in cgroup name only
>       -A, --no-aggr         disable CPU count aggregation
>       -a, --all-cpus        system-wide collection from all CPUs
>           --for-each-cgroup <name>
>                             expand events for each cgroup

Thanks, applied.

- Arnaldo

 
> Signed-off-by: Namhyung Kim <namhyung@kernel.org>
> ---
>  tools/perf/builtin-stat.c | 4 +++-
>  1 file changed, 3 insertions(+), 1 deletion(-)
> 
> diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
> index 84de61795e67..1a64aebc0d2f 100644
> --- a/tools/perf/builtin-stat.c
> +++ b/tools/perf/builtin-stat.c
> @@ -2386,7 +2386,8 @@ int cmd_stat(int argc, const char **argv)
>  	 * --per-thread is aggregated per thread, we dont mix it with cpu mode
>  	 */
>  	if (((stat_config.aggr_mode != AGGR_GLOBAL &&
> -	      stat_config.aggr_mode != AGGR_THREAD) || nr_cgroups) &&
> +	      stat_config.aggr_mode != AGGR_THREAD) ||
> +	     (nr_cgroups || stat_config.cgroup_list)) &&
>  	    !target__has_cpu(&target)) {
>  		fprintf(stderr, "both cgroup and no-aggregation "
>  			"modes only available in system-wide mode\n");
> @@ -2394,6 +2395,7 @@ int cmd_stat(int argc, const char **argv)
>  		parse_options_usage(stat_usage, stat_options, "G", 1);
>  		parse_options_usage(NULL, stat_options, "A", 1);
>  		parse_options_usage(NULL, stat_options, "a", 1);
> +		parse_options_usage(NULL, stat_options, "for-each-cgroup", 0);
>  		goto out;
>  	}
>  
> -- 
> 2.33.0.259.gc128427fd7-goog