md/raid5: write errors should be recorded as bad blocks if possible.
When a write error is detected, don't mark the device as failed
immediately but rather record the fact for handle_stripe to deal with.
Handle_stripe then attempts to record a bad block. Only if that fails
does the device get marked as faulty.
Signed-off-by: NeilBrown <neilb@suse.de>
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 5fc6216..9768a7d 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -1658,8 +1658,10 @@
return;
}
- if (!uptodate)
- md_error(conf->mddev, conf->disks[i].rdev);
+ if (!uptodate) {
+ set_bit(WriteErrorSeen, &conf->disks[i].rdev->flags);
+ set_bit(R5_WriteError, &sh->dev[i].flags);
+ }
rdev_dec_pending(conf->disks[i].rdev, conf->mddev);
@@ -3038,6 +3040,14 @@
if (sh->sector + STRIPE_SECTORS <= rdev->recovery_offset)
set_bit(R5_Insync, &dev->flags);
}
+ if (test_bit(R5_WriteError, &dev->flags)) {
+ clear_bit(R5_Insync, &dev->flags);
+ if (!test_bit(Faulty, &rdev->flags)) {
+ s->handle_bad_blocks = 1;
+ atomic_inc(&rdev->nr_pending);
+ } else
+ clear_bit(R5_WriteError, &dev->flags);
+ }
if (!test_bit(R5_Insync, &dev->flags)) {
/* The ReadError flag will just be confusing now */
clear_bit(R5_ReadError, &dev->flags);
@@ -3086,6 +3096,11 @@
analyse_stripe(sh, &s);
+ if (s.handle_bad_blocks) {
+ set_bit(STRIPE_HANDLE, &sh->state);
+ goto finish;
+ }
+
if (unlikely(s.blocked_rdev)) {
if (s.syncing || s.expanding || s.expanded ||
s.to_write || s.written) {
@@ -3283,6 +3298,20 @@
if (unlikely(s.blocked_rdev))
md_wait_for_blocked_rdev(s.blocked_rdev, conf->mddev);
+ if (s.handle_bad_blocks)
+ for (i = disks; i--; ) {
+ mdk_rdev_t *rdev;
+ struct r5dev *dev = &sh->dev[i];
+ if (test_and_clear_bit(R5_WriteError, &dev->flags)) {
+ /* We own a safe reference to the rdev */
+ rdev = conf->disks[i].rdev;
+ if (!rdev_set_badblocks(rdev, sh->sector,
+ STRIPE_SECTORS, 0))
+ md_error(conf->mddev, rdev);
+ rdev_dec_pending(rdev, conf->mddev);
+ }
+ }
+
if (s.ops_request)
raid_run_ops(sh, s.ops_request);