md: support blocking writes to an array on device failure
Allows a userspace metadata handler to take action upon detecting a device
failure.
Based on an original patch by Neil Brown.
Changes:
-added blocked_wait waitqueue to rdev
-don't qualify Blocked with Faulty always let userspace block writes
-added md_wait_for_blocked_rdev to wait for the block device to be clear, if
userspace misses the notification another one is sent every 5 seconds
-set MD_RECOVERY_NEEDED after clearing "blocked"
-kill DoBlock flag, just test mddev->external
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: Neil Brown <neilb@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 968daca..087eee0 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -2607,6 +2607,7 @@
}
}
+
/*
* handle_stripe - do things to a stripe.
*
@@ -2632,6 +2633,7 @@
struct stripe_head_state s;
struct r5dev *dev;
unsigned long pending = 0;
+ mdk_rdev_t *blocked_rdev = NULL;
memset(&s, 0, sizeof(s));
pr_debug("handling stripe %llu, state=%#lx cnt=%d, pd_idx=%d "
@@ -2691,6 +2693,11 @@
if (dev->written)
s.written++;
rdev = rcu_dereference(conf->disks[i].rdev);
+ if (rdev && unlikely(test_bit(Blocked, &rdev->flags))) {
+ blocked_rdev = rdev;
+ atomic_inc(&rdev->nr_pending);
+ break;
+ }
if (!rdev || !test_bit(In_sync, &rdev->flags)) {
/* The ReadError flag will just be confusing now */
clear_bit(R5_ReadError, &dev->flags);
@@ -2705,6 +2712,11 @@
}
rcu_read_unlock();
+ if (unlikely(blocked_rdev)) {
+ set_bit(STRIPE_HANDLE, &sh->state);
+ goto unlock;
+ }
+
if (s.to_fill && !test_and_set_bit(STRIPE_OP_BIOFILL, &sh->ops.pending))
sh->ops.count++;
@@ -2894,8 +2906,13 @@
if (sh->ops.count)
pending = get_stripe_work(sh);
+ unlock:
spin_unlock(&sh->lock);
+ /* wait for this device to become unblocked */
+ if (unlikely(blocked_rdev))
+ md_wait_for_blocked_rdev(blocked_rdev, conf->mddev);
+
if (pending)
raid5_run_ops(sh, pending);
@@ -2912,6 +2929,7 @@
struct stripe_head_state s;
struct r6_state r6s;
struct r5dev *dev, *pdev, *qdev;
+ mdk_rdev_t *blocked_rdev = NULL;
r6s.qd_idx = raid6_next_disk(pd_idx, disks);
pr_debug("handling stripe %llu, state=%#lx cnt=%d, "
@@ -2975,6 +2993,11 @@
if (dev->written)
s.written++;
rdev = rcu_dereference(conf->disks[i].rdev);
+ if (rdev && unlikely(test_bit(Blocked, &rdev->flags))) {
+ blocked_rdev = rdev;
+ atomic_inc(&rdev->nr_pending);
+ break;
+ }
if (!rdev || !test_bit(In_sync, &rdev->flags)) {
/* The ReadError flag will just be confusing now */
clear_bit(R5_ReadError, &dev->flags);
@@ -2989,6 +3012,11 @@
set_bit(R5_Insync, &dev->flags);
}
rcu_read_unlock();
+
+ if (unlikely(blocked_rdev)) {
+ set_bit(STRIPE_HANDLE, &sh->state);
+ goto unlock;
+ }
pr_debug("locked=%d uptodate=%d to_read=%d"
" to_write=%d failed=%d failed_num=%d,%d\n",
s.locked, s.uptodate, s.to_read, s.to_write, s.failed,
@@ -3094,8 +3122,13 @@
!test_bit(STRIPE_OP_COMPUTE_BLK, &sh->ops.pending))
handle_stripe_expansion(conf, sh, &r6s);
+ unlock:
spin_unlock(&sh->lock);
+ /* wait for this device to become unblocked */
+ if (unlikely(blocked_rdev))
+ md_wait_for_blocked_rdev(blocked_rdev, conf->mddev);
+
return_io(return_bi);
for (i=disks; i-- ;) {