diff options
author | NeilBrown <neilb@suse.de> | 2013-12-11 23:13:33 (GMT) |
---|---|---|
committer | Greg Kroah-Hartman <gregkh@linuxfoundation.org> | 2014-01-25 16:49:29 (GMT) |
commit | 871b7cf844174a54c11de4a7e847dac6ef3c5c23 (patch) | |
tree | f4e5441b9a15a0c180a63361f24851b39118cbf6 | |
parent | 5191a696c8eb656f0bd3b6bcd780be29f8680168 (diff) | |
download | linux-fsl-qoriq-871b7cf844174a54c11de4a7e847dac6ef3c5c23.tar.xz |
md: fix problem when adding device to read-only array with bitmap.
commit 8313b8e57f55b15e5b7f7fc5d1630bbf686a9a97 upstream.
If an array is started degraded, and then the missing device
is found it can be re-added and a minimal bitmap-based recovery
will bring it fully up-to-date.
If the array is read-only a recovery would not be allowed.
But also if the array is read-only and the missing device was
present very recently, then there could be no need for any
recovery at all, so we simply include the device in the read-only
array without any recovery.
However... if the missing device was removed a little longer ago
it could be missing some updates, but if a bitmap is present it will
be conditionally accepted pending a bitmap-based update. We don't
currently detect this case properly and will include that old
device into the read-only array with no recovery even though it really
needs a recovery.
This patch keeps track of whether a bitmap-based-recovery is really
needed or not in the new Bitmap_sync rdev flag. If that is set,
then the device will not be added to a read-only array.
Cc: Andrei Warkentin <andreiw@vmware.com>
Fixes: d70ed2e4fafdbef0800e73942482bb075c21578b
Signed-off-by: NeilBrown <neilb@suse.de>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
-rw-r--r-- | drivers/md/md.c | 18 | ||||
-rw-r--r-- | drivers/md/md.h | 3 |
2 files changed, 18 insertions, 3 deletions
diff --git a/drivers/md/md.c b/drivers/md/md.c index ba46d97..015bc45 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -1119,6 +1119,7 @@ static int super_90_validate(struct mddev *mddev, struct md_rdev *rdev) rdev->raid_disk = -1; clear_bit(Faulty, &rdev->flags); clear_bit(In_sync, &rdev->flags); + clear_bit(Bitmap_sync, &rdev->flags); clear_bit(WriteMostly, &rdev->flags); if (mddev->raid_disks == 0) { @@ -1197,6 +1198,8 @@ static int super_90_validate(struct mddev *mddev, struct md_rdev *rdev) */ if (ev1 < mddev->bitmap->events_cleared) return 0; + if (ev1 < mddev->events) + set_bit(Bitmap_sync, &rdev->flags); } else { if (ev1 < mddev->events) /* just a hot-add of a new device, leave raid_disk at -1 */ @@ -1605,6 +1608,7 @@ static int super_1_validate(struct mddev *mddev, struct md_rdev *rdev) rdev->raid_disk = -1; clear_bit(Faulty, &rdev->flags); clear_bit(In_sync, &rdev->flags); + clear_bit(Bitmap_sync, &rdev->flags); clear_bit(WriteMostly, &rdev->flags); if (mddev->raid_disks == 0) { @@ -1687,6 +1691,8 @@ static int super_1_validate(struct mddev *mddev, struct md_rdev *rdev) */ if (ev1 < mddev->bitmap->events_cleared) return 0; + if (ev1 < mddev->events) + set_bit(Bitmap_sync, &rdev->flags); } else { if (ev1 < mddev->events) /* just a hot-add of a new device, leave raid_disk at -1 */ @@ -2830,6 +2836,7 @@ slot_store(struct md_rdev *rdev, const char *buf, size_t len) else rdev->saved_raid_disk = -1; clear_bit(In_sync, &rdev->flags); + clear_bit(Bitmap_sync, &rdev->flags); err = rdev->mddev->pers-> hot_add_disk(rdev->mddev, rdev); if (err) { @@ -5773,6 +5780,7 @@ static int add_new_disk(struct mddev * mddev, mdu_disk_info_t *info) info->raid_disk < mddev->raid_disks) { rdev->raid_disk = info->raid_disk; set_bit(In_sync, &rdev->flags); + clear_bit(Bitmap_sync, &rdev->flags); } else rdev->raid_disk = -1; } else @@ -7731,7 +7739,8 @@ static int remove_and_add_spares(struct mddev *mddev, if (test_bit(Faulty, &rdev->flags)) continue; if (mddev->ro && - rdev->saved_raid_disk < 0) + ! (rdev->saved_raid_disk >= 0 && + !test_bit(Bitmap_sync, &rdev->flags))) continue; rdev->recovery_offset = 0; @@ -7812,9 +7821,12 @@ void md_check_recovery(struct mddev *mddev) * As we only add devices that are already in-sync, * we can activate the spares immediately. */ - clear_bit(MD_RECOVERY_NEEDED, &mddev->recovery); remove_and_add_spares(mddev, NULL); - mddev->pers->spare_active(mddev); + /* There is no thread, but we need to call + * ->spare_active and clear saved_raid_disk + */ + md_reap_sync_thread(mddev); + clear_bit(MD_RECOVERY_NEEDED, &mddev->recovery); goto unlock; } diff --git a/drivers/md/md.h b/drivers/md/md.h index 608050c..6367564 100644 --- a/drivers/md/md.h +++ b/drivers/md/md.h @@ -129,6 +129,9 @@ struct md_rdev { enum flag_bits { Faulty, /* device is known to have a fault */ In_sync, /* device is in_sync with rest of array */ + Bitmap_sync, /* ..actually, not quite In_sync. Need a + * bitmap-based recovery to get fully in sync + */ Unmerged, /* device is being added to array and should * be considerred for bvec_merge_fn but not * yet for actual IO |