MD: Allow restarting an interrupted incremental recovery.

If an incremental recovery was interrupted, a subsequent
re-add will result in a full recovery, even though an
incremental should be possible (seen with raid1).

Solve this problem by not updating the superblock on the
recovering device until array is not degraded any longer.

Cc: Neil Brown <neilb@suse.de>
Signed-off-by: Andrei Warkentin <andreiw@vmware.com>
Signed-off-by: NeilBrown <neilb@suse.de>

diff --git a/drivers/md/md.c b/drivers/md/md.c
index 0ea3485..e8d198d 100644 (file)
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -2449,7 +2449,8 @@ repeat:
                if (rdev->sb_loaded != 1)
                        continue; /* no noise on spare devices */
 
-               if (!test_bit(Faulty, &rdev->flags)) {
+               if (!test_bit(Faulty, &rdev->flags) &&
+                   rdev->saved_raid_disk == -1) {
                        md_super_write(mddev,rdev,
                                       rdev->sb_start, rdev->sb_size,
                                       rdev->sb_page);
@@ -2465,9 +2466,12 @@ repeat:
                                rdev->badblocks.size = 0;
                        }
 
-               } else
+               } else if (test_bit(Faulty, &rdev->flags))
                        pr_debug("md: %s (skipping faulty)\n",
                                 bdevname(rdev->bdev, b));
+               else
+                       pr_debug("(skipping incremental s/r ");
+
                if (mddev->level == LEVEL_MULTIPATH)
                        /* only need to write one superblock... */
                        break;
@@ -7366,15 +7370,19 @@ static void reap_sync_thread(struct mddev *mddev)
        if (test_bit(MD_RECOVERY_RESHAPE, &mddev->recovery) &&
            mddev->pers->finish_reshape)
                mddev->pers->finish_reshape(mddev);
-       md_update_sb(mddev, 1);
 
-       /* if array is no-longer degraded, then any saved_raid_disk
-        * information must be scrapped
+       /* If array is no-longer degraded, then any saved_raid_disk
+        * information must be scrapped.  Also if any device is now
+        * In_sync we must scrape the saved_raid_disk for that device
+        * do the superblock for an incrementally recovered device
+        * written out.
         */
-       if (!mddev->degraded)
-               list_for_each_entry(rdev, &mddev->disks, same_set)
+       list_for_each_entry(rdev, &mddev->disks, same_set)
+               if (!mddev->degraded ||
+                   test_bit(In_sync, &rdev->flags))
                        rdev->saved_raid_disk = -1;
 
+       md_update_sb(mddev, 1);
        clear_bit(MD_RECOVERY_RUNNING, &mddev->recovery);
        clear_bit(MD_RECOVERY_SYNC, &mddev->recovery);
        clear_bit(MD_RECOVERY_RESHAPE, &mddev->recovery);