Re: [PATCH 1/2] perf sched: Introduce timehist command - v2

[Namhyung Kim <namhyung@kernel.org>]

On Sun,  1 Dec 2013 17:23:14 -0700, David Ahern wrote:
> 'perf sched timehist' provides an analysis of scheduling events.
>
> Example usage:
>     perf sched record -- sleep 1
>     perf sched timehist
>
> By default it shows the individual schedule events, including the time between
> sched-in events for the task, the task scheduling delay (time between wakeup
> and actually running) and run time for the task:
>
>            time cpu  task name[tid/pid]    b/n time sch delay  run time
>   ------------- ---- -------------------- --------- --------- ---------
>    79371.874569 [11] gcc[31949]               0.014     0.000     1.148
>    79371.874591 [10] gcc[31951]               0.000     0.000     0.024
>    79371.874603 [10] migration/10[59]         3.350     0.004     0.011
>    79371.874604 [11] <idle>                   1.148     0.000     0.035
>    79371.874723 [05] <idle>                   0.016     0.000     1.383
>    79371.874746 [05] gcc[31949]               0.153     0.078     0.022
> ...
>
> Times are in msec.usec.

Hmm.. I'm not sure this is right.  It probably confuse users since
timehist_time_str() still uses "sec.usec" format and it looks not
natural for me to use "msec".

Yeah, I see perf stat uses "msec.usec" for result of clock events but
AFAICT it also shows the unit explicitly.  And perf stat -I uses
"sec.nsec" format and perf script also uses "sec.usec" format so there's
a little consistency here.

I think this "msec.usec" format fits well for the scheduling events but
in general "sec.usec" format looks better IMHO.

Thanks,
Namhyung