Re: [PATCHSET 0/6] perf sched timehist: Introduce --idle-hist option (v2)

From: Namhyung Kim
Date: Mon Dec 12 2016 - 12:27:39 EST


Hi David,

On Sat, Dec 10, 2016 at 09:32:54AM -0700, David Ahern wrote:
> On 12/8/16 7:47 AM, Namhyung Kim wrote:
> > Hi,
> >
> > This patchset implements the idle hist feature which analyze reason of system
> > idle. Sometimes I need to investigate what makes CPUs to go idle even though
> > I have jobs to do. It may be due to I/O, waiting on lock or whatever.
> >
>
> ...
>
> > Namhyung Kim (6):
> > perf sched timehist: Split is_idle_sample()
> > perf sched timehist: Introduce struct idle_time_data
> > perf sched timehist: Save callchain when entering idle
> > perf sched timehist: Skip non-idle events when necessary
> > perf sched timehist: Add -I/--idle-hist option
> > perf sched timehist: Show callchains for idle stat
> >
> > tools/perf/Documentation/perf-sched.txt | 4 +
> > tools/perf/builtin-sched.c | 252 +++++++++++++++++++++++++++-----
> > 2 files changed, 222 insertions(+), 34 deletions(-)
> >
>
> LGTM
>
> Acked-by: David Ahern <dsahern@xxxxxxxxx>

Thanks!

>
> Suggested improvement: Add the length of the time window. ie., data collected
> (or analyzed over if --time is used) for N.M seconds. Puts the amount of idle
> time into perspective.

Do you mean adding an elapsed time so that it can see the cpu utilization (or
something similar)? Then we need to expose the elapsed time during record or
maybe just use time difference between first and last sample?

Thanks,
Namhyung