From db0505d320660b6ad92418847e7eca6b61b246ac Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Tue, 17 Oct 2017 16:18:36 +1100 Subject: md: be cautious about using ->curr_resync_completed for ->recovery_offset The ->recovery_offset shows how much of a non-InSync device is actually in sync - how much has been recoveryed. When performing a recovery, ->curr_resync and ->curr_resync_completed follow the device address being recovered and so can be used to update ->recovery_offset. When performing a reshape, ->curr_resync* might follow the device addresses (raid5) or might follow array addresses (raid10), so cannot in general be used to set ->recovery_offset. When reshaping backwards, ->curre_resync* measures from the *end* of the array-or-device, so is particularly unhelpful. So change the common code in md.c to only use ->curr_resync_complete for the simple recovery case, and add code to raid5.c to update ->recovery_offset during a forwards reshape. Signed-off-by: NeilBrown Signed-off-by: Shaohua Li --- drivers/md/md.c | 33 ++++++++++++++++++++++----------- 1 file changed, 22 insertions(+), 11 deletions(-) (limited to 'drivers/md/md.c') diff --git a/drivers/md/md.c b/drivers/md/md.c index 2bf4cc41b4f8..15e4668f594c 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -2454,10 +2454,18 @@ repeat: } } - /* First make sure individual recovery_offsets are correct */ + /* + * First make sure individual recovery_offsets are correct + * curr_resync_completed can only be used during recovery. + * During reshape/resync it might use array-addresses rather + * that device addresses. + */ rdev_for_each(rdev, mddev) { if (rdev->raid_disk >= 0 && mddev->delta_disks >= 0 && + test_bit(MD_RECOVERY_RUNNING, &mddev->recovery) && + test_bit(MD_RECOVERY_RECOVER, &mddev->recovery) && + !test_bit(MD_RECOVERY_RESHAPE, &mddev->recovery) && !test_bit(Journal, &rdev->flags) && !test_bit(In_sync, &rdev->flags) && mddev->curr_resync_completed > rdev->recovery_offset) @@ -8491,16 +8499,19 @@ void md_do_sync(struct md_thread *thread) } else { if (!test_bit(MD_RECOVERY_INTR, &mddev->recovery)) mddev->curr_resync = MaxSector; - rcu_read_lock(); - rdev_for_each_rcu(rdev, mddev) - if (rdev->raid_disk >= 0 && - mddev->delta_disks >= 0 && - !test_bit(Journal, &rdev->flags) && - !test_bit(Faulty, &rdev->flags) && - !test_bit(In_sync, &rdev->flags) && - rdev->recovery_offset < mddev->curr_resync) - rdev->recovery_offset = mddev->curr_resync; - rcu_read_unlock(); + if (!test_bit(MD_RECOVERY_RESHAPE, &mddev->recovery) && + test_bit(MD_RECOVERY_RECOVER, &mddev->recovery)) { + rcu_read_lock(); + rdev_for_each_rcu(rdev, mddev) + if (rdev->raid_disk >= 0 && + mddev->delta_disks >= 0 && + !test_bit(Journal, &rdev->flags) && + !test_bit(Faulty, &rdev->flags) && + !test_bit(In_sync, &rdev->flags) && + rdev->recovery_offset < mddev->curr_resync) + rdev->recovery_offset = mddev->curr_resync; + rcu_read_unlock(); + } } } skip: -- cgit v1.2.3