Re: [PATCH] tracing: print function names instead of just address

From: Changbin Du
Date: Mon Feb 11 2019 - 21:58:25 EST


On Mon, Feb 11, 2019 at 02:55:32PM -0500, Steven Rostedt wrote:
> On Sun, 10 Feb 2019 00:19:19 +0800
> Changbin Du <changbin.du@xxxxxxxxx> wrote:
>
> > Here is an example for this change.
> >
> > $ sudo perf record -e 'ftrace:function' --filter='ip==schedule'
> > $ sudo perf report
>
> I took this but changed the subject as it only affects perf (the kernel
> doesn't use the format field for output, and trace-cmd has an internal
> plugin that overrides it too).
>
Thanks. You explained why I can't find the usage for the other entries.
I was looking for it before... :)

> -- Steve
>
> >
> > The output of perf before this patch:
> >
> > \# Samples: 100 of event 'ftrace:function'
> > \# Event count (approx.): 100
> > \#
> > \# Overhead Trace output
> > \# ........ ......................................
> > \#
> > 51.00% ffffffff81f6aaa0 <-- ffffffff81158e8d
> > 29.00% ffffffff81f6aaa0 <-- ffffffff8116ccb2
> > 8.00% ffffffff81f6aaa0 <-- ffffffff81f6f2ed
> > 4.00% ffffffff81f6aaa0 <-- ffffffff811628db
> > 4.00% ffffffff81f6aaa0 <-- ffffffff81f6ec5b
> > 2.00% ffffffff81f6aaa0 <-- ffffffff81f6f21a
> > 1.00% ffffffff81f6aaa0 <-- ffffffff811b04af
> > 1.00% ffffffff81f6aaa0 <-- ffffffff8143ce17
> >
> > After this patch:
> >
> > \# Samples: 36 of event 'ftrace:function'
> > \# Event count (approx.): 36
> > \#
> > \# Overhead Trace output
> > \# ........ ............................................
> > \#
> > 38.89% schedule <-- schedule_hrtimeout_range_clock
> > 27.78% schedule <-- worker_thread
> > 13.89% schedule <-- schedule_timeout
> > 11.11% schedule <-- smpboot_thread_fn
> > 5.56% schedule <-- rcu_gp_kthread
> > 2.78% schedule <-- exit_to_usermode_loop
> >
> > Signed-off-by: Changbin Du <changbin.du@xxxxxxxxx>
> > ---
> > kernel/trace/trace_entries.h | 41 +++++++++++++++++-------------------
> > 1 file changed, 19 insertions(+), 22 deletions(-)
> >
> >

--
Cheers,
Changbin Du