lkml.org 
[lkml]   [2010]   [Dec]   [3]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
/
Date
From
SubjectRe: [RFC][PATCH 0/2 v2] tracing: Add conditional to tracepoints
On Thu, Dec 02, 2010 at 11:03:58PM -0500, Steven Rostedt wrote:
> This is an RFC that adds the TP_CONDITION() to the TRACE_EVENT()
> code.
>
> There are certain cases that a tracepoint only makes sense if
> a specific condition is met. But because we do not want to dirty
> the fast path (the non tracing case) with if statements that are
> there only to avoid tracing, we just pass the condition variables
> to the tracepoint, and let the user filter them out if needed.
>
> A perfect example is the tracepoint sched_wakeup. It traces all
> calls to try_to_wake_up() even if it fails to wake up. But if we add:
>
> if (success)
> trace_sched_wakeup(p);
>
> We have that "if (success)" tested for every time we call try_to_wake_up().
> Even when tracing is not (or never will be) enabled.
>
> This patch set adds a variant TRACE_EVENT_CONDITIONAL()
> (and DEFINE_EVENT_CONDITIONAL()) that has a "cond" argument.
> This argument is encapsulated with "TP_CONDITIONAL()" which turns into:
>
> if (!cond)
> return;
>
> What's new with this version?
>
> This version adds this if statement to __DO_TRACE(). As it is
> in a static inline function, the return still applies.
>
> Also, since the shortcut is made before the callbacks, the test
> is at the call site. This means that you can have a DECLARE_EVENT_CLASS()
> where one of its DEFINE_EVENTS() is normal and the other is a
> DEFINE_EVENT_CONDITION().
>
> The following patches are in:
>
> git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-2.6-trace.git
>
> branch: rfc/trace-conditional-v2
>
>
> Steven Rostedt (2):
> tracing: Add TRACE_EVENT_CONDITIONAL()
> tracing: Only trace sched_wakeup if it actually work something up
>
> ----
> include/linux/tracepoint.h | 29 +++++++++++++++++++++++------
> include/trace/define_trace.h | 15 +++++++++++++++
> include/trace/events/sched.h | 16 ++++++++--------
> 3 files changed, 46 insertions(+), 14 deletions(-)


Looks good

Acked-by: Frederic Weisbecker <fweisbec@gmail.com>

I suspect we'll need to fix some scripts/subperf commands in perf. Those that do:

if (success)

tests after reading a trace from a wakeup event.


\
 
 \ /
  Last update: 2010-12-03 15:49    [W:0.266 / U:0.408 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site