perf trace: Allow selecting use the use of the ordered_events code

I was trigger happy on this one, as using ordered_events as implemented
by Jiri for use with the --block code under discussion on lkml incurs
in delaying processing to form batches that then get ordered and then
printed.

With 'perf trace' we want to process the events as they go, without that
delay, and doing it that way works well for the common case which is to
trace a thread or a workload started by 'perf trace'.

So revert back to not using ordered_events but add an option to select
that mode so that users can experiment with their particular use case to
see if works better, i.e. if the added delay is not a problem and the
ordering helps.

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: https://lkml.kernel.org/n/tip-8ki7sld6rusnjhhtaly26i5o@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

1 files changed, 6 insertions, 0 deletions

diff --git a/tools/perf/Documentation/perf-trace.txt b/tools/perf/Documentation/perf-trace.txt
index e113450503d2..631e687be4eb 100644
--- a/tools/perf/Documentation/perf-trace.txt
+++ b/tools/perf/Documentation/perf-trace.txt
@@ -205,6 +205,12 @@ the thread executes on the designated CPUs. Default is to monitor all CPUs.
 	because the file may be huge. A time out is needed in such cases.
 	This option sets the time out limit. The default value is 500 ms.
 
+--sort-events::
+	Do sorting on batches of events, use when noticing out of order events that
+	may happen, for instance, when a thread gets migrated to a different CPU
+	while processing a syscall.
+
+
 PAGEFAULTS
 ----------