On Tue, 14 Jan 2025 10:12:02 -0500
Steven Rostedt [off-list ref] wrote:

From: Steven Rostedt <rostedt@goodmis.org>

The function graph tracer now calculates the calltime internally and for
each instance. If there are two instances that are running function graph
tracer and are tracing the same functions, the timings of the length of
those functions may be slightly different:

 # trace-cmd record -B foo -p function_graph -B bar -p function_graph sleep 5
 # trace-cmd report
[..]
bar:            sleep-981   [000] ...1.  1101.109027: funcgraph_entry:        0.764 us   |          mutex_unlock(); (ret=0xffff8abcc256c300)
foo:            sleep-981   [000] ...1.  1101.109028: funcgraph_entry:        0.748 us   |          mutex_unlock(); (ret=0xffff8abcc256c300)
bar:            sleep-981   [000] .....  1101.109029: funcgraph_exit:         2.456 us   |        } (ret=0xffff8abcc256c300)
foo:            sleep-981   [000] .....  1101.109029: funcgraph_exit:         2.403 us   |        } (ret=0xffff8abcc256c300)
bar:            sleep-981   [000] d..1.  1101.109031: funcgraph_entry:        0.844 us   |  fpregs_assert_state_consistent(); (ret=0x0)
foo:            sleep-981   [000] d..1.  1101.109032: funcgraph_entry:        0.803 us   |  fpregs_assert_state_consistent(); (ret=0x0)

I added:

  Link: https://lore.kernel.org/all/20250114101806.b2778cb01f34f5be9d23ad98@kernel.org/ (local)
 
  Suggested-by: Masami Hiramatsu [off-list ref]

To this as well.

-- Steve

Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 Documentation/trace/ftrace.rst | 6 ++++++
 1 file changed, 6 insertions(+)