[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-Id: <20220609055652.938821-4-namhyung@kernel.org>
Date: Wed, 8 Jun 2022 22:56:48 -0700
From: Namhyung Kim <namhyung@...nel.org>
To: Arnaldo Carvalho de Melo <acme@...nel.org>,
Jiri Olsa <jolsa@...nel.org>
Cc: Ingo Molnar <mingo@...nel.org>,
Peter Zijlstra <peterz@...radead.org>,
LKML <linux-kernel@...r.kernel.org>,
Ian Rogers <irogers@...gle.com>,
linux-perf-users@...r.kernel.org, Will Deacon <will@...nel.org>,
Waiman Long <longman@...hat.com>,
Boqun Feng <boqun.feng@...il.com>,
Davidlohr Bueso <dave@...olabs.net>
Subject: [PATCH 3/7] perf lock: Skip print_bad_events() if nothing bad
The debug output is meaningful when there are bad lock sequences.
Skip it unless there's one or -v option is given.
Signed-off-by: Namhyung Kim <namhyung@...nel.org>
---
tools/perf/builtin-lock.c | 7 +++++++
1 file changed, 7 insertions(+)
diff --git a/tools/perf/builtin-lock.c b/tools/perf/builtin-lock.c
index 118a036a81fb..2337b09dd2cd 100644
--- a/tools/perf/builtin-lock.c
+++ b/tools/perf/builtin-lock.c
@@ -858,9 +858,16 @@ static void print_bad_events(int bad, int total)
{
/* Output for debug, this have to be removed */
int i;
+ int broken = 0;
const char *name[4] =
{ "acquire", "acquired", "contended", "release" };
+ for (i = 0; i < BROKEN_MAX; i++)
+ broken += bad_hist[i];
+
+ if (broken == 0 && !verbose)
+ return;
+
pr_info("\n=== output for debug===\n\n");
pr_info("bad: %d, total: %d\n", bad, total);
pr_info("bad rate: %.2f %%\n", (double)bad / (double)total * 100);
--
2.36.1.255.ge46751e96f-goog
Powered by blists - more mailing lists