From: NeilBrown <neilb@cse.unsw.edu.au>
Two problems are fixed here.
1/ if the array is known to require a resync (parity update),
but there are too many failed devices, the resync cannot complete
but will be retried indefinitely.
2/ if the array has too many failed drives to be usable and a spare is
available, reconstruction will be attempted, but cannot work. This
also is retried indefinitely.
Signed-off-by: Neil Brown <neilb@cse.unsw.edu.au>
Signed-off-by: Andrew Morton <akpm@osdl.org>
---
25-akpm/drivers/md/md.c | 12 ++++++------
25-akpm/drivers/md/raid5.c | 13 +++++++++++++
25-akpm/drivers/md/raid6main.c | 12 ++++++++++++
3 files changed, 31 insertions(+), 6 deletions(-)
diff -puN drivers/md/md.c~md-make-raid5-and-raid6-robust-against-failure-during-recovery drivers/md/md.c
--- 25/drivers/md/md.c~md-make-raid5-and-raid6-robust-against-failure-during-recovery 2005-02-17 18:00:51.000000000 -0800
+++ 25-akpm/drivers/md/md.c 2005-02-17 18:00:51.000000000 -0800
@@ -3655,18 +3655,18 @@ void md_check_recovery(mddev_t *mddev)
/* no recovery is running.
* remove any failed drives, then
- * add spares if possible
+ * add spares if possible.
+ * Spare are also removed and re-added, to allow
+ * the personality to fail the re-add.
*/
- ITERATE_RDEV(mddev,rdev,rtmp) {
+ ITERATE_RDEV(mddev,rdev,rtmp)
if (rdev->raid_disk >= 0 &&
- rdev->faulty &&
+ (rdev->faulty || ! rdev->in_sync) &&
atomic_read(&rdev->nr_pending)==0) {
if (mddev->pers->hot_remove_disk(mddev, rdev->raid_disk)==0)
rdev->raid_disk = -1;
}
- if (!rdev->faulty && rdev->raid_disk >= 0 && !rdev->in_sync)
- spares++;
- }
+
if (mddev->degraded) {
ITERATE_RDEV(mddev,rdev,rtmp)
if (rdev->raid_disk < 0
diff -puN drivers/md/raid5.c~md-make-raid5-and-raid6-robust-against-failure-during-recovery drivers/md/raid5.c
--- 25/drivers/md/raid5.c~md-make-raid5-and-raid6-robust-against-failure-during-recovery 2005-02-17 18:00:51.000000000 -0800
+++ 25-akpm/drivers/md/raid5.c 2005-02-17 18:00:51.000000000 -0800
@@ -1493,6 +1493,15 @@ static int sync_request (mddev_t *mddev,
unplug_slaves(mddev);
return 0;
}
+ /* if there is 1 or more failed drives and we are trying
+ * to resync, then assert that we are finished, because there is
+ * nothing we can do.
+ */
+ if (mddev->degraded >= 1 && test_bit(MD_RECOVERY_SYNC, &mddev->recovery)) {
+ int rv = (mddev->size << 1) - sector_nr;
+ md_done_sync(mddev, rv, 1);
+ return rv;
+ }
x = sector_nr;
chunk_offset = sector_div(x, sectors_per_chunk);
@@ -1884,6 +1893,10 @@ static int raid5_add_disk(mddev_t *mddev
int disk;
struct disk_info *p;
+ if (mddev->degraded > 1)
+ /* no point adding a device */
+ return 0;
+
/*
* find the disk ...
*/
diff -puN drivers/md/raid6main.c~md-make-raid5-and-raid6-robust-against-failure-during-recovery drivers/md/raid6main.c
--- 25/drivers/md/raid6main.c~md-make-raid5-and-raid6-robust-against-failure-during-recovery 2005-02-17 18:00:51.000000000 -0800
+++ 25-akpm/drivers/md/raid6main.c 2005-02-17 18:00:51.000000000 -0800
@@ -1652,6 +1652,15 @@ static int sync_request (mddev_t *mddev,
unplug_slaves(mddev);
return 0;
}
+ /* if there are 2 or more failed drives and we are trying
+ * to resync, then assert that we are finished, because there is
+ * nothing we can do.
+ */
+ if (mddev->degraded >= 2 && test_bit(MD_RECOVERY_SYNC, &mddev->recovery)) {
+ int rv = (mddev->size << 1) - sector_nr;
+ md_done_sync(mddev, rv, 1);
+ return rv;
+ }
x = sector_nr;
chunk_offset = sector_div(x, sectors_per_chunk);
@@ -2050,6 +2059,9 @@ static int raid6_add_disk(mddev_t *mddev
int disk;
struct disk_info *p;
+ if (mddev->degraded > 2)
+ /* no point adding a device */
+ return 0;
/*
* find the disk ...
*/
_