iv/linux
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

md: fix problem when adding device to read-only array with bitmap.

Browse Source 
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: d70ed2e4fa
Cc: stable@vger.kernel.org (3.2+)
Signed-off-by: NeilBrown <neilb@suse.de>
This commit is contained in:
NeilBrown 2013-12-12 10:13:33 +11:00
parent e8b8491585
commit 8313b8e57f
2 changed files with 18 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

18
drivers/md/md.c
View File

@ -1087,6 +1087,7 @@ 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) {
@ -1165,6 +1166,8 @@ 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 */
@ -1573,6 +1576,7 @@ 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) {
@ -1655,6 +1659,8 @@ 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 */
@ -2798,6 +2804,7 @@ 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) {
@ -5770,6 +5777,7 @@ 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
@ -7716,7 +7724,8 @@ 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;
@ -7797,9 +7806,12 @@ 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;
}

3
drivers/md/md.h
View File

@ -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