Messages in this thread | | | Subject | Re: sched_clock - microblaze | From | Steven Rostedt <> | Date | Thu, 15 Apr 2010 11:04:48 -0400 |
| |
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() { > >
| |