vmstat: update comment regarding stat_threshold
authorChristoph Lameter <cl@linux.com>
Thu, 14 Apr 2011 22:21:58 +0000 (15:21 -0700)
committerLinus Torvalds <torvalds@linux-foundation.org>
Thu, 14 Apr 2011 23:06:54 +0000 (16:06 -0700)
Signed-off-by: Christoph Lameter <cl@linux.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
mm/vmstat.c

index 772b39b87d955078b4f0d7a1b7114751e0ef9a74..8cb0f0a703e59f62c8987c482fc829ab251206a5 100644 (file)
@@ -321,9 +321,12 @@ static inline void mod_state(struct zone *zone,
                /*
                 * The fetching of the stat_threshold is racy. We may apply
                 * a counter threshold to the wrong the cpu if we get
-                * rescheduled while executing here. However, the following
-                * will apply the threshold again and therefore bring the
-                * counter under the threshold.
+                * rescheduled while executing here. However, the next
+                * counter update will apply the threshold again and
+                * therefore bring the counter under the threshold again.
+                *
+                * Most of the time the thresholds are the same anyways
+                * for all cpus in a zone.
                 */
                t = this_cpu_read(pcp->stat_threshold);