Explorar el Código

md: perform async updates for metadata where possible.

When adding devices to, or removing device from, an array we need to
update the metadata.  However we don't need to do it synchronously as
data integrity doesn't depend on these changes being recorded
instantly.  So avoid the synchronous call to md_update_sb and just set
a flag so that the thread will do it.

This can reduce the number of updates performed when lots of devices
are being added or removed.

Signed-off-by: NeilBrown <neilb@suse.com>
Signed-off-by: Shaohua Li <shli@fb.com>
NeilBrown hace 8 años
padre
commit
060b0689f5
Se han modificado 1 ficheros con 12 adiciones y 4 borrados
  1. 12 4
      drivers/md/md.c

+ 12 - 4
drivers/md/md.c

@@ -2599,8 +2599,10 @@ state_store(struct md_rdev *rdev, const char *buf, size_t len)
 
 			if (err == 0) {
 				md_kick_rdev_from_array(rdev);
-				if (mddev->pers)
-					md_update_sb(mddev, 1);
+				if (mddev->pers) {
+					set_bit(MD_CHANGE_DEVS, &mddev->flags);
+					md_wakeup_thread(mddev->thread);
+				}
 				md_new_event(mddev);
 			}
 		}
@@ -6175,7 +6177,11 @@ kick_rdev:
 		md_cluster_ops->remove_disk(mddev, rdev);
 
 	md_kick_rdev_from_array(rdev);
-	md_update_sb(mddev, 1);
+	set_bit(MD_CHANGE_DEVS, &mddev->flags);
+	if (mddev->thread)
+		md_wakeup_thread(mddev->thread);
+	else
+		md_update_sb(mddev, 1);
 	md_new_event(mddev);
 
 	return 0;
@@ -6240,7 +6246,9 @@ static int hot_add_disk(struct mddev *mddev, dev_t dev)
 
 	rdev->raid_disk = -1;
 
-	md_update_sb(mddev, 1);
+	set_bit(MD_CHANGE_DEVS, &mddev->flags);
+	if (!mddev->thread)
+		md_update_sb(mddev, 1);
 	/*
 	 * Kick recovery, maybe this spare has to be added to the
 	 * array immediately.