From: Zheng Qixing <zhengqixing@xxxxxxxxxx>
During raid resync, if a disk becomes faulty, the operation is
briefly interrupted. The MD_RECOVERY_RECOVER flag triggered by
the disk failure causes sync_action to incorrectly show "recover"
instead of "resync". The same issue affects reshape operations.
Reproduction steps:
mdadm -Cv /dev/md1 -l1 -n4 -e1.2 /dev/sd{a..d} // -> resync happended
mdadm -f /dev/md1 /dev/sda // -> resync interrupted
cat sync_action
-> recover
Add progress checks in md_sync_action() for resync/recover/reshape
to ensure the interface correctly reports the actual operation type.
Fixes: 4b10a3bc67c1 ("md: ensure resync is prioritized over recovery")
Signed-off-by: Zheng Qixing <zhengqixing@xxxxxxxxxx>
---
drivers/md/md.c | 38 ++++++++++++++++++++++++++++++++++++--
1 file changed, 36 insertions(+), 2 deletions(-)
diff --git a/drivers/md/md.c b/drivers/md/md.c
index 4ea956a80343..798428d0870b 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -4845,9 +4845,34 @@ static bool rdev_needs_recovery(struct md_rdev *rdev, sector_t sectors)
return false;
}
+static enum sync_action md_get_active_sync_action(struct mddev *mddev)
+{
+ struct md_rdev *rdev;
+ bool is_recover = false;
+
+ if (mddev->resync_offset < MaxSector)
+ return ACTION_RESYNC;
+
+ if (mddev->reshape_position != MaxSector)
+ return ACTION_RESHAPE;
+
+ rcu_read_lock();
+ rdev_for_each_rcu(rdev, mddev) {
+ if (rdev->raid_disk >= 0 &&
+ rdev_needs_recovery(rdev, MaxSector)) {
+ is_recover = true;
+ break;
+ }
+ }
+ rcu_read_unlock();
+
+ return is_recover ? ACTION_RECOVER : ACTION_IDLE;
+}
+
enum sync_action md_sync_action(struct mddev *mddev)
{
unsigned long recovery = mddev->recovery;
+ enum sync_action active_action;
/*
* frozen has the highest priority, means running sync_thread will be
@@ -4871,8 +4896,17 @@ enum sync_action md_sync_action(struct mddev *mddev)
!test_bit(MD_RECOVERY_NEEDED, &recovery))
return ACTION_IDLE;
- if (test_bit(MD_RECOVERY_RESHAPE, &recovery) ||
- mddev->reshape_position != MaxSector)
+ /*
+ * Check if any sync operation (resync/recover/reshape) is
+ * currently active. This ensures that only one sync operation
+ * can run at a time. Returns the type of active operation, or
+ * ACTION_IDLE if none are active.
+ */
+ active_action = md_get_active_sync_action(mddev);
+ if (active_action != ACTION_IDLE)
+ return active_action;
+
+ if (test_bit(MD_RECOVERY_RESHAPE, &recovery))
return ACTION_RESHAPE;
if (test_bit(MD_RECOVERY_RECOVER, &recovery))
--
2.39.2
