[PATCH] tracing: hwlat: update old comment

[PATCH] tracing: hwlat: update old comment

[Luiz Capitulino]

The ftrace hwlat does support a cpumask.

Signed-off-by: Luiz Capitulino <lcapitulino@redhat.com>
---
 kernel/trace/trace_hwlat.c | 5 +----
 1 file changed, 1 insertion(+), 4 deletions(-)

diff --git a/kernel/trace/trace_hwlat.c b/kernel/trace/trace_hwlat.c
index af344a1b..1199fe1 100644
--- a/kernel/trace/trace_hwlat.c
+++ b/kernel/trace/trace_hwlat.c
@@ -322,10 +322,7 @@ static void move_to_next_cpu(bool initmask)
  * need to ensure nothing else might be running (and thus preempting).
  * Obviously this should never be used in production environments.
  *
- * Currently this runs on which ever CPU it was scheduled on, but most
- * real-world hardware latency situations occur across several CPUs,
- * but we might later generalize this if we find there are any actualy
- * systems with alternate SMI delivery or other hardware latencies.
+ * Executes one loop interaction on each CPU in tracing_cpumask sysfs file.
  */
 static int kthread_fn(void *data)
 {
-- 
2.5.5

Re: [PATCH] tracing: hwlat: update old comment

[Steven Rostedt]

On Mon, 13 Feb 2017 12:25:17 -0500
Luiz Capitulino <lcapitulino@redhat.com> wrote:

> The ftrace hwlat does support a cpumask.
> 
> Signed-off-by: Luiz Capitulino <lcapitulino@redhat.com>

Thanks! Applied.

-- Steve

> ---
>  kernel/trace/trace_hwlat.c | 5 +----
>  1 file changed, 1 insertion(+), 4 deletions(-)
> 
> diff --git a/kernel/trace/trace_hwlat.c b/kernel/trace/trace_hwlat.c
> index af344a1b..1199fe1 100644
> --- a/kernel/trace/trace_hwlat.c
> +++ b/kernel/trace/trace_hwlat.c
> @@ -322,10 +322,7 @@ static void move_to_next_cpu(bool initmask)
>   * need to ensure nothing else might be running (and thus preempting).
>   * Obviously this should never be used in production environments.
>   *
> - * Currently this runs on which ever CPU it was scheduled on, but most
> - * real-world hardware latency situations occur across several CPUs,
> - * but we might later generalize this if we find there are any actualy
> - * systems with alternate SMI delivery or other hardware latencies.
> + * Executes one loop interaction on each CPU in tracing_cpumask sysfs file.
>   */
>  static int kthread_fn(void *data)
>  {