Commit 8d355a46 authored by Li Nan's avatar Li Nan Committed by Song Liu
Browse files

md/raid10: Do not add spare disk when recovery fails 



In raid10_sync_request(), if data cannot be read from any disk for
recovery, it will go to 'giveup' and let 'chunks_skipped' + 1. After
multiple 'giveup', when 'chunks_skipped >= geo.raid_disks', it will
return 'max_sector', indicating that the recovery has been completed.
However, the recovery is just aborted and the data remains inconsistent.

Fix it by setting mirror->recovery_disabled, which will prevent the spare
disk from being added to this mirror. The same issue also exists during
resync, it will be fixed afterwards.

Signed-off-by: default avatarLi Nan <linan122@huawei.com>
Signed-off-by: default avatarSong Liu <song@kernel.org>
Link: https://lore.kernel.org/r/20230602091839.743798-2-linan666@huaweicloud.com
parent 4d8a5754

drivers/md/raid10.c

+18 −2
Original line number Diff line number Diff line
@@ -3311,6 +3311,7 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr, 
	int chunks_skipped = 0;

	sector_t chunk_mask = conf->geo.chunk_mask;

	int page_idx = 0;

	int error_disk = -1;



	/*

	 * Allow skipping a full rebuild for incremental assembly
@@ -3394,8 +3395,21 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr, 
		return reshape_request(mddev, sector_nr, skipped);



	if (chunks_skipped >= conf->geo.raid_disks) {

		/* if there has been nothing to do on any drive,

		 * then there is nothing to do at all..

		pr_err("md/raid10:%s: %s fails\n", mdname(mddev),

			test_bit(MD_RECOVERY_SYNC, &mddev->recovery) ?  "resync" : "recovery");

		if (error_disk >= 0 &&

		    !test_bit(MD_RECOVERY_SYNC, &mddev->recovery)) {

			/*

			 * recovery fails, set mirrors.recovery_disabled,

			 * device shouldn't be added to there.

			 */

			conf->mirrors[error_disk].recovery_disabled =

						mddev->recovery_disabled;

			return 0;

		}

		/*

		 * if there has been nothing to do on any drive,

		 * then there is nothing to do at all.

		 */

		*skipped = 1;

		return (max_sector - sector_nr) + sectors_skipped;
@@ -3646,6 +3660,8 @@ static sector_t raid10_sync_request(struct mddev *mddev, sector_t sector_nr, 
						       mdname(mddev));

					mirror->recovery_disabled

						= mddev->recovery_disabled;

				} else {

					error_disk = i;

				}

				put_buf(r10_bio);

				if (rb2)