Em Tue, Aug 20, 2019 at 04:02:19PM +0200, Jiri Olsa escreveu:
> There's wrong bitmap considered when checking
> for cpu count of specific node.
>
> We do the needed computation for 'set' variable,
> but at the end we use the 'c2c_he->cpuset' weight,
> which shows misleading numbers.
>
> Reported-by: Joe Mario <jma...@redhat.com>
You forgot to add this:
Fixes: 1e181b92a2da ("perf c2c report: Add 'node' sort key")
Can you please confirm that that is the cset being fixed? This helps
with backporters, stable@, etc.
- Arnaldo
> Link: https://lkml.kernel.org/n/tip-9wvrv74n7d4nbgztr74is...@git.kernel.org
> Signed-off-by: Jiri Olsa <jo...@kernel.org>
> ---
> tools/perf/builtin-c2c.c | 2 +-
> 1 file changed, 1 insertion(+), 1 deletion(-)
>
> diff --git a/tools/perf/builtin-c2c.c b/tools/perf/builtin-c2c.c
> index f0aae6e13a33..9240c6bf70f5 100644
> --- a/tools/perf/builtin-c2c.c
> +++ b/tools/perf/builtin-c2c.c
> @@ -1106,7 +1106,7 @@ node_entry(struct perf_hpp_fmt *fmt __maybe_unused,
> struct perf_hpp *hpp,
> break;
> case 1:
> {
> - int num = bitmap_weight(c2c_he->cpuset, c2c.cpus_cnt);
> + int num = bitmap_weight(set, c2c.cpus_cnt);
> struct c2c_stats *stats = &c2c_he->node_stats[node];
>
> ret = scnprintf(hpp->buf, hpp->size, "%2d{%2d ", node,
> num);
> --
> 2.21.0
--
- Arnaldo
