md: change managed of recovery_disabled.

If we hit a read error while recovering a mirror, we want to abort the
recovery without necessarily failing the disk - as having a disk this
a read error is better than not having an array at all.

Currently this is managed with a per-array flag "recovery_disabled"
and is only implemented for RAID1.  For RAID10 we will need finer
grained control as we might want to disable recovery for individual
devices separately.

So push more of the decision making into the personality.
'recovery_disabled' is now a 'cookie' which is copied when the
personality want to disable recovery and is changed when a device is
added to the array as this is used as a trigger to 'try recovery
again'.

This will allow RAID10 to get the control that it needs.

Signed-off-by: NeilBrown <neilb@suse.de>
This commit is contained in:
NeilBrown 2011-07-27 11:00:36 +10:00
parent a478a069b6
commit 5389042ffa
4 changed files with 19 additions and 7 deletions

View File

@ -1922,7 +1922,7 @@ static int bind_rdev_to_array(mdk_rdev_t * rdev, mddev_t * mddev)
bd_link_disk_holder(rdev->bdev, mddev->gendisk);
/* May as well allow recovery to be retried once */
mddev->recovery_disabled = 0;
mddev->recovery_disabled++;
return 0;
@ -7070,7 +7070,7 @@ static int remove_and_add_spares(mddev_t *mddev)
}
}
if (mddev->degraded && !mddev->recovery_disabled) {
if (mddev->degraded) {
list_for_each_entry(rdev, &mddev->disks, same_set) {
if (rdev->raid_disk >= 0 &&
!test_bit(In_sync, &rdev->flags) &&

View File

@ -239,9 +239,12 @@ struct mddev_s
#define MD_RECOVERY_FROZEN 9
unsigned long recovery;
int recovery_disabled; /* if we detect that recovery
* will always fail, set this
* so we don't loop trying */
/* If a RAID personality determines that recovery (of a particular
* device) will fail due to a read error on the source device, it
* takes a copy of this number and does not attempt recovery again
* until this number changes.
*/
int recovery_disabled;
int in_sync; /* know to not need resync */
/* 'open_mutex' avoids races between 'md_open' and 'do_md_stop', so

View File

@ -956,7 +956,7 @@ static void error(mddev_t *mddev, mdk_rdev_t *rdev)
* However don't try a recovery from this drive as
* it is very likely to fail.
*/
mddev->recovery_disabled = 1;
conf->recovery_disabled = mddev->recovery_disabled;
return;
}
if (test_and_clear_bit(In_sync, &rdev->flags)) {
@ -1052,6 +1052,9 @@ static int raid1_add_disk(mddev_t *mddev, mdk_rdev_t *rdev)
int first = 0;
int last = mddev->raid_disks - 1;
if (mddev->recovery_disabled == conf->recovery_disabled)
return -EBUSY;
if (rdev->raid_disk >= 0)
first = last = rdev->raid_disk;
@ -1107,7 +1110,7 @@ static int raid1_remove_disk(mddev_t *mddev, int number)
* is not possible.
*/
if (!test_bit(Faulty, &rdev->flags) &&
!mddev->recovery_disabled &&
mddev->recovery_disabled != conf->recovery_disabled &&
mddev->degraded < conf->raid_disks) {
err = -EBUSY;
goto abort;

View File

@ -48,6 +48,12 @@ struct r1_private_data_s {
* (fresh device added).
* Cleared when a sync completes.
*/
int recovery_disabled; /* when the same as
* mddev->recovery_disabled
* we don't allow recovery
* to be attempted as we
* expect a read error
*/
wait_queue_head_t wait_barrier;