perf stat: Make all displayed event names parseable as well
authorIngo Molnar <mingo@elte.hu>
Wed, 27 Apr 2011 02:24:57 +0000 (04:24 +0200)
committerIngo Molnar <mingo@elte.hu>
Tue, 26 Apr 2011 18:04:55 +0000 (20:04 +0200)
Right now we display this by default:

          0.202204 task-clock-msecs         #      0.282 CPUs
                 0 context-switches         #      0.000 M/sec
                 0 CPU-migrations           #      0.000 M/sec
                85 page-faults              #      0.420 M/sec

The task-clock-msecs event cannot actually be passed back as an
event name, the event name we recognize is 'task-clock'.

So change the output of the cpu-clock and task-clock events
to be idempotent.

( Units should be printed out in the right-side column, if needed. )

Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Acked-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Link: http://lkml.kernel.org/n/tip-lexrnbzy09asscgd4f7oac4i@git.kernel.org
Signed-off-by: Ingo Molnar <mingo@elte.hu>
tools/perf/util/parse-events.c

index b686269..b5bfef1 100644 (file)
@@ -70,8 +70,8 @@ static const char *hw_event_names[] = {
 };
 
 static const char *sw_event_names[] = {
-       "cpu-clock-msecs",
-       "task-clock-msecs",
+       "cpu-clock",
+       "task-clock",
        "page-faults",
        "context-switches",
        "CPU-migrations",