md: When RAID5 is dirty, force reconstruct-write instead of read-modify-write.

Signed-off-by: Alex Lyakas <alex@zadarastorage.com>
Suggested-by: Yair Hershko <yair@zadarastorage.com>
Signed-off-by: NeilBrown <neilb@suse.de>

diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index d11012604e2801c899dd8fbb78966fe702e2b41b..9de8221f64ec99da99e34c41a6354faf39b667c4 100644 (file)
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -2806,12 +2806,25 @@ static void handle_stripe_dirtying(struct r5conf *conf,
                                   int disks)
 {
        int rmw = 0, rcw = 0, i;
-       if (conf->max_degraded == 2) {
-               /* RAID6 requires 'rcw' in current implementation
-                * Calculate the real rcw later - for now fake it
+       sector_t recovery_cp = conf->mddev->recovery_cp;
+
+       /* RAID6 requires 'rcw' in current implementation.
+        * Otherwise, check whether resync is now happening or should start.
+        * If yes, then the array is dirty (after unclean shutdown or
+        * initial creation), so parity in some stripes might be inconsistent.
+        * In this case, we need to always do reconstruct-write, to ensure
+        * that in case of drive failure or read-error correction, we
+        * generate correct data from the parity.
+        */
+       if (conf->max_degraded == 2 ||
+           (recovery_cp < MaxSector && sh->sector >= recovery_cp)) {
+               /* Calculate the real rcw later - for now make it
                 * look like rcw is cheaper
                 */
                rcw = 1; rmw = 2;
+               pr_debug("force RCW max_degraded=%u, recovery_cp=%llu sh->sector=%llu\n",
+                        conf->max_degraded, (unsigned long long)recovery_cp,
+                        (unsigned long long)sh->sector);
        } else for (i = disks; i--; ) {
                /* would I have to read this buffer for read_modify_write */
                struct r5dev *dev = &sh->dev[i];