summaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
authorFrederic Weisbecker <fweisbec@gmail.com>2009-04-06 01:49:33 +0200
committerIngo Molnar <mingo@elte.hu>2009-04-10 12:50:56 +0200
commit2062501ae6505dbc5bff3a792246c2661d114050 (patch)
tree59792987c9e9fd1ae657c2e4a5cdb14545523e24
parent1cad1252ed279ea59f3f8d3d3a5817eeb2f7a4d3 (diff)
downloadop-kernel-dev-2062501ae6505dbc5bff3a792246c2661d114050.zip
op-kernel-dev-2062501ae6505dbc5bff3a792246c2661d114050.tar.gz
tracing/lockdep: report the time waited for a lock
While trying to optimize the new lock on reiserfs to replace the bkl, I find the lock tracing very useful though it lacks something important for performance (and latency) instrumentation: the time a task waits for a lock. That's what this patch implements: bash-4816 [000] 202.652815: lock_contended: lock_contended: &sb->s_type->i_mutex_key bash-4816 [000] 202.652819: lock_acquired: &rq->lock (0.000 us) <...>-4787 [000] 202.652825: lock_acquired: &rq->lock (0.000 us) <...>-4787 [000] 202.652829: lock_acquired: &rq->lock (0.000 us) bash-4816 [000] 202.652833: lock_acquired: &sb->s_type->i_mutex_key (16.005 us) As shown above, the "lock acquired" field is followed by the time it has been waiting for the lock. Usually, a lock contended entry is followed by a near lock_acquired entry with a non-zero time waited. Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Acked-by: Peter Zijlstra <peterz@infradead.org> Cc: Steven Rostedt <rostedt@goodmis.org> LKML-Reference: <1238975373-15739-1-git-send-email-fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
-rw-r--r--include/trace/lockdep_event_types.h23
-rw-r--r--kernel/lockdep.c8
2 files changed, 22 insertions, 9 deletions
diff --git a/include/trace/lockdep_event_types.h b/include/trace/lockdep_event_types.h
index adccfcd..863f1e4 100644
--- a/include/trace/lockdep_event_types.h
+++ b/include/trace/lockdep_event_types.h
@@ -32,11 +32,24 @@ TRACE_FORMAT(lock_contended,
TP_FMT("%s", lock->name)
);
-TRACE_FORMAT(lock_acquired,
- TP_PROTO(struct lockdep_map *lock, unsigned long ip),
- TP_ARGS(lock, ip),
- TP_FMT("%s", lock->name)
- );
+TRACE_EVENT(lock_acquired,
+ TP_PROTO(struct lockdep_map *lock, unsigned long ip, s64 waittime),
+
+ TP_ARGS(lock, ip, waittime),
+
+ TP_STRUCT__entry(
+ __field(const char *, name)
+ __field(unsigned long, wait_usec)
+ __field(unsigned long, wait_nsec_rem)
+ ),
+ TP_fast_assign(
+ __entry->name = lock->name;
+ __entry->wait_nsec_rem = do_div(waittime, NSEC_PER_USEC);
+ __entry->wait_usec = (unsigned long) waittime;
+ ),
+ TP_printk("%s (%lu.%03lu us)", __entry->name, __entry->wait_usec,
+ __entry->wait_nsec_rem)
+);
#endif
#endif
diff --git a/kernel/lockdep.c b/kernel/lockdep.c
index b0f0118..c4582a6 100644
--- a/kernel/lockdep.c
+++ b/kernel/lockdep.c
@@ -3061,6 +3061,8 @@ found_it:
put_lock_stats(stats);
}
+DEFINE_TRACE(lock_acquired);
+
static void
__lock_acquired(struct lockdep_map *lock, unsigned long ip)
{
@@ -3099,6 +3101,8 @@ found_it:
hlock->holdtime_stamp = now;
}
+ trace_lock_acquired(lock, ip, waittime);
+
stats = get_lock_stats(hlock_class(hlock));
if (waittime) {
if (hlock->read)
@@ -3137,14 +3141,10 @@ void lock_contended(struct lockdep_map *lock, unsigned long ip)
}
EXPORT_SYMBOL_GPL(lock_contended);
-DEFINE_TRACE(lock_acquired);
-
void lock_acquired(struct lockdep_map *lock, unsigned long ip)
{
unsigned long flags;
- trace_lock_acquired(lock, ip);
-
if (unlikely(!lock_stat))
return;
OpenPOWER on IntegriCloud