Fix read-balancing during node failure

During a node failure, We need to suspend read balancing so that the
reads are directed to the first device and stale data is not read.
Suspending writes is not required because these would be recorded and
synced eventually.

A new flag MD_CLUSTER_SUSPEND_READ_BALANCING is set in recover_prep().
area_resyncing() will respond true for the entire devices if this
flag is set and the request type is READ. The flag is cleared
in recover_done().

Signed-off-by: Goldwyn Rodrigues <rgoldwyn@suse.com>
Reported-By: David Teigland <teigland@redhat.com>
Signed-off-by: NeilBrown <neilb@suse.com>

1 files changed, 4 insertions, 3 deletions

diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index 50cf0c893b16..94f5b55069e0 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -541,7 +541,7 @@ static int read_balance(struct r1conf *conf, struct r1bio *r1_bio, int *max_sect
 
         if ((conf->mddev->recovery_cp < this_sector + sectors) ||
             (mddev_is_clustered(conf->mddev) &&
-            md_cluster_ops->area_resyncing(conf->mddev, this_sector,
+            md_cluster_ops->area_resyncing(conf->mddev, READ, this_sector,
                     this_sector + sectors)))
                 choose_first = 1;
         else
@@ -1111,7 +1111,8 @@ static void make_request(struct mddev *mddev, struct bio * bio)
             ((bio_end_sector(bio) > mddev->suspend_lo &&
             bio->bi_iter.bi_sector < mddev->suspend_hi) ||
             (mddev_is_clustered(mddev) &&
-             md_cluster_ops->area_resyncing(mddev, bio->bi_iter.bi_sector, bio_end_sector(bio))))) {
+             md_cluster_ops->area_resyncing(mddev, WRITE,
+                     bio->bi_iter.bi_sector, bio_end_sector(bio))))) {
                 /* As the suspend_* range is controlled by
                  * userspace, we want an interruptible
                  * wait.
@@ -1124,7 +1125,7 @@ static void make_request(struct mddev *mddev, struct bio * bio)
                         if (bio_end_sector(bio) <= mddev->suspend_lo ||
                             bio->bi_iter.bi_sector >= mddev->suspend_hi ||
                             (mddev_is_clustered(mddev) &&
-                             !md_cluster_ops->area_resyncing(mddev,
+                             !md_cluster_ops->area_resyncing(mddev, WRITE,
                                      bio->bi_iter.bi_sector, bio_end_sector(bio))))
                                 break;
                         schedule();