md/raid10: prioritize adding disk to 'removed' mirror

When add a new disk to raid10, it will traverse conf->mirror from start
and find one of the following mirror to add:
  1. mirror->rdev is set to WantReplacement and it have no replacement,
     set new disk to mirror->replacement.
  2. no mirror->rdev, set new disk to mirror->rdev.

There is a array as below (sda is set to WantReplacement):

    Number   Major   Minor   RaidDevice State
       0       8        0        0      active sync set-A   /dev/sda
       -       0        0        1      removed
       2       8       32        2      active sync set-A   /dev/sdc
       3       8       48        3      active sync set-B   /dev/sdd

Use 'mdadm --add' to add a new disk to this array, the new disk will
become sda's replacement instead of add to removed position, which is
confusing for users. Meanwhile, after new disk recovery success, sda
will be set to Faulty.

Prioritize adding disk to 'removed' mirror is a better choice. In the
above scenario, the behavior is the same as before, except sda will not
be deleted. Before other disks are added, continued use sda is more
reliable.

Signed-off-by: Li Nan <linan122@huawei.com>
Signed-off-by: Song Liu <song@kernel.org>
Link: https://lore.kernel.org/r/20230527092007.3008856-1-linan666@huaweicloud.com

diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index 8eda7993275416666bad647a16283de10c0e13fc..ab0e2485b2b7a2010dd819f4da384ccedf094f3e 100644 (file)
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -2151,9 +2151,10 @@ static int raid10_add_disk(struct mddev *mddev, struct md_rdev *rdev)
 {
        struct r10conf *conf = mddev->private;
        int err = -EEXIST;
-       int mirror;
+       int mirror, repl_slot = -1;
        int first = 0;
        int last = conf->geo.raid_disks - 1;
+       struct raid10_info *p;
 
        if (mddev->recovery_cp < MaxSector)
                /* only hot-add to in-sync arrays, as recovery is
@@ -2176,23 +2177,14 @@ static int raid10_add_disk(struct mddev *mddev, struct md_rdev *rdev)
        else
                mirror = first;
        for ( ; mirror <= last ; mirror++) {
-               struct raid10_info *p = &conf->mirrors[mirror];
+               p = &conf->mirrors[mirror];
                if (p->recovery_disabled == mddev->recovery_disabled)
                        continue;
                if (p->rdev) {
-                       if (!test_bit(WantReplacement, &p->rdev->flags) ||
-                           p->replacement != NULL)
-                               continue;
-                       clear_bit(In_sync, &rdev->flags);
-                       set_bit(Replacement, &rdev->flags);
-                       rdev->raid_disk = mirror;
-                       err = 0;
-                       if (mddev->gendisk)
-                               disk_stack_limits(mddev->gendisk, rdev->bdev,
-                                                 rdev->data_offset << 9);
-                       conf->fullsync = 1;
-                       rcu_assign_pointer(p->replacement, rdev);
-                       break;
+                       if (test_bit(WantReplacement, &p->rdev->flags) &&
+                           p->replacement == NULL && repl_slot < 0)
+                               repl_slot = mirror;
+                       continue;
                }
 
                if (mddev->gendisk)
@@ -2209,6 +2201,19 @@ static int raid10_add_disk(struct mddev *mddev, struct md_rdev *rdev)
                break;
        }
 
+       if (err && repl_slot >= 0) {
+               p = &conf->mirrors[repl_slot];
+               clear_bit(In_sync, &rdev->flags);
+               set_bit(Replacement, &rdev->flags);
+               rdev->raid_disk = repl_slot;
+               err = 0;
+               if (mddev->gendisk)
+                       disk_stack_limits(mddev->gendisk, rdev->bdev,
+                                         rdev->data_offset << 9);
+               conf->fullsync = 1;
+               rcu_assign_pointer(p->replacement, rdev);
+       }
+
        print_conf(conf);
        return err;
 }