DM RAID: Add ability to restore transiently failed devices on resume
DM RAID: Add ability to restore transiently failed devices on resume
This patch adds code to the resume function to check over the devices
in the RAID array. If any are found to be marked as failed and their
superblocks can be read, an attempt is made to reintegrate them into
the array. This allows the user to refresh the array with a simple
suspend and resume of the array - rather than having to load a
completely new table, allocate and initialize all the structures and
throw away the old instantiation.
Signed-off-by: Jonathan Brassow <jbrassow@redhat.com>
Signed-off-by: NeilBrown <neilb@suse.de>
diff --git a/drivers/md/dm-raid.c b/drivers/md/dm-raid.c
index 1d3fe1a..facaf91 100644
--- a/drivers/md/dm-raid.c
+++ b/drivers/md/dm-raid.c
@@ -1574,12 +1574,54 @@
static void raid_resume(struct dm_target *ti)
{
+ int i;
+ uint64_t failed_devices, cleared_failed_devices = 0;
+ unsigned long flags;
+ struct dm_raid_superblock *sb;
struct raid_set *rs = ti->private;
+ struct md_rdev *r;
set_bit(MD_CHANGE_DEVS, &rs->md.flags);
if (!rs->bitmap_loaded) {
bitmap_load(&rs->md);
rs->bitmap_loaded = 1;
+ } else {
+ /*
+ * A secondary resume while the device is active.
+ * Take this opportunity to check whether any failed
+ * devices are reachable again.
+ */
+ for (i = 0; i < rs->md.raid_disks; i++) {
+ r = &rs->dev[i].rdev;
+ if (test_bit(Faulty, &r->flags) && r->sb_page &&
+ sync_page_io(r, 0, r->sb_size,
+ r->sb_page, READ, 1)) {
+ DMINFO("Faulty device #%d has readable super"
+ "block. Attempting to revive it.", i);
+ r->raid_disk = i;
+ r->saved_raid_disk = i;
+ flags = r->flags;
+ clear_bit(Faulty, &r->flags);
+ clear_bit(WriteErrorSeen, &r->flags);
+ clear_bit(In_sync, &r->flags);
+ if (r->mddev->pers->hot_add_disk(r->mddev, r)) {
+ r->raid_disk = -1;
+ r->saved_raid_disk = -1;
+ r->flags = flags;
+ } else {
+ r->recovery_offset = 0;
+ cleared_failed_devices |= 1 << i;
+ }
+ }
+ }
+ if (cleared_failed_devices) {
+ rdev_for_each(r, &rs->md) {
+ sb = page_address(r->sb_page);
+ failed_devices = le64_to_cpu(sb->failed_devices);
+ failed_devices &= ~cleared_failed_devices;
+ sb->failed_devices = cpu_to_le64(failed_devices);
+ }
+ }
}
clear_bit(MD_RECOVERY_FROZEN, &rs->md.recovery);
@@ -1588,7 +1630,7 @@
static struct target_type raid_target = {
.name = "raid",
- .version = {1, 5, 0},
+ .version = {1, 5, 1},
.module = THIS_MODULE,
.ctr = raid_ctr,
.dtr = raid_dtr,
diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index 6e17f818..ec73458 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -1519,8 +1519,9 @@
p = conf->mirrors+mirror;
if (!p->rdev) {
- disk_stack_limits(mddev->gendisk, rdev->bdev,
- rdev->data_offset << 9);
+ if (mddev->gendisk)
+ disk_stack_limits(mddev->gendisk, rdev->bdev,
+ rdev->data_offset << 9);
p->head_position = 0;
rdev->raid_disk = mirror;
@@ -1559,7 +1560,7 @@
clear_bit(Unmerged, &rdev->flags);
}
md_integrity_add_rdev(rdev, mddev);
- if (blk_queue_discard(bdev_get_queue(rdev->bdev)))
+ if (mddev->queue && blk_queue_discard(bdev_get_queue(rdev->bdev)))
queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, mddev->queue);
print_conf(conf);
return err;
diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index 6ddae25..3c6b193 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -1819,15 +1819,17 @@
set_bit(Replacement, &rdev->flags);
rdev->raid_disk = mirror;
err = 0;
- disk_stack_limits(mddev->gendisk, rdev->bdev,
- rdev->data_offset << 9);
+ if (mddev->gendisk)
+ disk_stack_limits(mddev->gendisk, rdev->bdev,
+ rdev->data_offset << 9);
conf->fullsync = 1;
rcu_assign_pointer(p->replacement, rdev);
break;
}
- disk_stack_limits(mddev->gendisk, rdev->bdev,
- rdev->data_offset << 9);
+ if (mddev->gendisk)
+ disk_stack_limits(mddev->gendisk, rdev->bdev,
+ rdev->data_offset << 9);
p->head_position = 0;
p->recovery_disabled = mddev->recovery_disabled - 1;