lockstat: human readability tweaks
Present all this fancy new lock statistics information:
*warning, _wide_ output ahead*
(output edited for purpose of brevity)
# cat /proc/lock_stat
lock_stat version 0.1
-----------------------------------------------------------------------------------------------------------------------------------------------------------------
class name contentions waittime-min waittime-max waittime-total acquisitions holdtime-min holdtime-max holdtime-total
-----------------------------------------------------------------------------------------------------------------------------------------------------------------
&inode->i_mutex: 14458 6.57 398832.75 2469412.23 6768876 0.34 11398383.65 339410830.89
---------------
&inode->i_mutex 4486 [<ffffffff802a08f9>] pipe_wait+0x86/0x8d
&inode->i_mutex 0 [<ffffffff802a01e8>] pipe_write_fasync+0x29/0x5d
&inode->i_mutex 0 [<ffffffff802a0e18>] pipe_read+0x74/0x3a5
&inode->i_mutex 0 [<ffffffff802a1a6a>] do_lookup+0x81/0x1ae
.................................................................................................................................................................
&inode->i_data.tree_lock-W: 491 0.27 62.47 493.89 2477833 0.39 468.89 1146584.25
&inode->i_data.tree_lock-R: 65 0.44 4.27 48.78 26288792 0.36 184.62 10197458.24
--------------------------
&inode->i_data.tree_lock 46 [<ffffffff80277095>] __do_page_cache_readahead+0x69/0x24f
&inode->i_data.tree_lock 31 [<ffffffff8026f9fb>] add_to_page_cache+0x31/0xba
&inode->i_data.tree_lock 0 [<ffffffff802770ee>] __do_page_cache_readahead+0xc2/0x24f
&inode->i_data.tree_lock 0 [<ffffffff8026f6e4>] find_get_page+0x1a/0x58
.................................................................................................................................................................
proc_inum_idr.lock: 0 0.00 0.00 0.00 36 0.00 65.60 148.26
proc_subdir_lock: 0 0.00 0.00 0.00 3049859 0.00 106.81 1563212.42
shrinker_rwsem-W: 0 0.00 0.00 0.00 5 0.00 1.73 3.68
shrinker_rwsem-R: 0 0.00 0.00 0.00 633 2.57 246.57 10909.76
'contentions' and 'acquisitions' are the number of such events measured (since
the last reset). The waittime- and holdtime- (min, max, total) numbers are
presented in microseconds.
If there are any contention points, the lock class is presented in the block
format (as i_mutex and tree_lock above), otherwise a single line of output is
presented.
The output is sorted on absolute number of contentions (read + write), this
should get the worst offenders presented first, so that:
# grep : /proc/lock_stat | head
will quickly show who's bad.
The stats can be reset using:
# echo 0 > /proc/lock_stat
[bunk@stusta.de: make 2 functions static]
[akpm@linux-foundation.org: fix printk warning]
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Acked-by: Ingo Molnar <mingo@elte.hu>
Acked-by: Jason Baron <jbaron@redhat.com>
Signed-off-by: Adrian Bunk <bunk@stusta.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
diff --git a/kernel/lockdep.c b/kernel/lockdep.c
index 70ca4db..a8dc99d 100644
--- a/kernel/lockdep.c
+++ b/kernel/lockdep.c
@@ -149,6 +149,50 @@
lt->nr++;
}
+static inline void lock_time_add(struct lock_time *src, struct lock_time *dst)
+{
+ dst->min += src->min;
+ dst->max += src->max;
+ dst->total += src->total;
+ dst->nr += src->nr;
+}
+
+struct lock_class_stats lock_stats(struct lock_class *class)
+{
+ struct lock_class_stats stats;
+ int cpu, i;
+
+ memset(&stats, 0, sizeof(struct lock_class_stats));
+ for_each_possible_cpu(cpu) {
+ struct lock_class_stats *pcs =
+ &per_cpu(lock_stats, cpu)[class - lock_classes];
+
+ for (i = 0; i < ARRAY_SIZE(stats.contention_point); i++)
+ stats.contention_point[i] += pcs->contention_point[i];
+
+ lock_time_add(&pcs->read_waittime, &stats.read_waittime);
+ lock_time_add(&pcs->write_waittime, &stats.write_waittime);
+
+ lock_time_add(&pcs->read_holdtime, &stats.read_holdtime);
+ lock_time_add(&pcs->write_holdtime, &stats.write_holdtime);
+ }
+
+ return stats;
+}
+
+void clear_lock_stats(struct lock_class *class)
+{
+ int cpu;
+
+ for_each_possible_cpu(cpu) {
+ struct lock_class_stats *cpu_stats =
+ &per_cpu(lock_stats, cpu)[class - lock_classes];
+
+ memset(cpu_stats, 0, sizeof(struct lock_class_stats));
+ }
+ memset(class->contention_point, 0, sizeof(class->contention_point));
+}
+
static struct lock_class_stats *get_lock_stats(struct lock_class *class)
{
return &get_cpu_var(lock_stats)[class - lock_classes];