diff options
| author | Frederic Weisbecker <fweisbec@gmail.com> | 2010-05-07 02:33:42 +0200 |
|---|---|---|
| committer | Frederic Weisbecker <fweisbec@gmail.com> | 2010-05-09 13:45:30 +0200 |
| commit | 90c0e5fc7b73d2575c7367e1da70ff9521718e5e (patch) | |
| tree | 555df001b47f27ae0a4339725e9ba06175e94ff1 /tools/perf/builtin-lock.c | |
| parent | perf: Fix perf lock bad rate (diff) | |
| download | linux-90c0e5fc7b73d2575c7367e1da70ff9521718e5e.tar.xz linux-90c0e5fc7b73d2575c7367e1da70ff9521718e5e.zip | |
perf lock: Always check min AND max wait time
When a lock is acquired after beeing contended, we update the
wait time statistics for the given lock.
But if the min wait time is updated, we don't check the max wait
time. This is wrong because the first time we update the wait time,
we want to update both min and max wait time.
Before:
Name acquired contended total wait (ns) max wait (ns) min wait (ns)
key 8 1 21656 0 21656
After:
Name acquired contended total wait (ns) max wait (ns) min wait (ns)
key 8 1 21656 21656 21656
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Hitoshi Mitake <mitake@dcl.info.waseda.ac.jp>
Diffstat (limited to 'tools/perf/builtin-lock.c')
| -rw-r--r-- | tools/perf/builtin-lock.c | 2 |
1 files changed, 1 insertions, 1 deletions
diff --git a/tools/perf/builtin-lock.c b/tools/perf/builtin-lock.c index d7dde9cbbdf4..e549f4547b98 100644 --- a/tools/perf/builtin-lock.c +++ b/tools/perf/builtin-lock.c @@ -496,7 +496,7 @@ report_lock_acquired_event(struct trace_acquired_event *acquired_event, ls->wait_time_total += contended_term; if (contended_term < ls->wait_time_min) ls->wait_time_min = contended_term; - else if (ls->wait_time_max < contended_term) + if (ls->wait_time_max < contended_term) ls->wait_time_max = contended_term; break; case SEQ_STATE_RELEASED: |