Re: sched_clock - microblaze

[Steven Rostedt <rostedt@goodmis.org>]

On Thu, 2010-04-15 at 16:55 +0200, Michal Simek wrote:
> Hi Thomas and Steven,
> 
> I would like to improve time measuring for ftrace (Log below)
> 
> I looked at http://lkml.org/lkml/2009/11/16/181
> where Thomas suggested to create sched_clock() function.
> I used the same solution as Wu proposed but it is not nice.
> 
> Is unimplemented sched_clock the reason why ftrace not show fine grain time?

Yeah, sched_clock is used by ftrace for timings, so if it only returns
jiffies, then that will, unfortunately, be the resolution of the tracer.

I've been told that if you make a higher resolution timer for sched
clock, it will improve the scheduling in CFS.

-- Steve

> 
> Or is there any other thing which is wrong?
> 
> Thanks,
> Michal
> 
> 
> 
> Dumping ftrace buffer:
> ---------------------------------
>   0) ! 10000.00 us |                                }
>   0)   <========== |
>   0) ! 10000.00 us |                            }
>   0) ! 10000.00 us |                          }
>   0)   0.000 us    |                          get_seconds();
>   0)   0.000 us    |                          tcp_rcv_rtt_update();
>   0)   0.000 us    |                          tcp_ack();
>   0)   0.000 us    |                          tcp_rcv_rtt_update();
>   0)   0.000 us    |                          tcp_urg();
>   0)               |                          tcp_data_queue() {
>   0)   0.000 us    |                            __sk_mem_schedule();
>   0)   0.000 us    |                            tcp_event_data_recv();
>   0)   0.000 us    |                            sock_def_readable();
>   0)   0.000 us    |                          }
>   0)   0.000 us    |                          tcp_check_space();
>   0)               |                          __tcp_ack_snd_check() {
> 
>