From: Li Nan <linan122@xxxxxxxxxx>
When a new disk is added during running recovery, the kernel may
restart recovery from the beginning of the device and submit write
io to ranges that have already been synchronized.
Reproduce:
mdadm -CR /dev/md0 -l1 -n3 /dev/sda missing missing
mdadm --add /dev/md0 /dev/sdb
sleep 10
cat /proc/mdstat # partially synchronized
mdadm --add /dev/md0 /dev/sdc
cat /proc/mdstat # start from 0
iostat 1 sdb sdc # sdb has io, too
If 'rdev->recovery_offset' is ahead of the current recovery sector,
read from that device instead of issuing a write. It prevents
unnecessary writes while still preserving the chance to back up data
if it is the last copy.
Signed-off-by: Li Nan <linan122@xxxxxxxxxx>
---
drivers/md/raid1.c | 6 +++++-
1 file changed, 5 insertions(+), 1 deletion(-)
diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index 3e422854cafb..ac5a9b73157a 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -2894,7 +2894,8 @@ static sector_t raid1_sync_request(struct mddev *mddev, sector_t sector_nr,
test_bit(Faulty, &rdev->flags)) {
if (i < conf->raid_disks)
still_degraded = true;
- } else if (!test_bit(In_sync, &rdev->flags)) {
+ } else if (!test_bit(In_sync, &rdev->flags) &&
+ rdev->recovery_offset <= sector_nr) {
bio->bi_opf = REQ_OP_WRITE;
bio->bi_end_io = end_sync_write;
write_targets ++;
@@ -2903,6 +2904,9 @@ static sector_t raid1_sync_request(struct mddev *mddev, sector_t sector_nr,
sector_t first_bad = MaxSector;
sector_t bad_sectors;
+ if (!test_bit(In_sync, &rdev->flags))
+ good_sectors = min(rdev->recovery_offset - sector_nr,
+ (u64)good_sectors);
if (is_badblock(rdev, sector_nr, good_sectors,
&first_bad, &bad_sectors)) {
if (first_bad > sector_nr)
--
2.39.2
