aboutsummaryrefslogtreecommitdiff
path: root/drivers/md
diff options
context:
space:
mode:
authorNeilBrown2014-07-31 10:16:29 +1000
committerNeilBrown2014-07-31 10:16:52 +1000
commit2446dba03f9dabe0b477a126cbeb377854785b47 (patch)
tree15bf004ae35cc4e8e6000f0f0883dcb09fe062eb /drivers/md
parent64aa90f26c06e1cb2aacfb98a7d0eccfbd6c1a91 (diff)
md/raid1,raid10: always abort recover on write error.
Currently we don't abort recovery on a write error if the write error to the recovering device was triggerd by normal IO (as opposed to recovery IO). This means that for one bitmap region, the recovery might write to the recovering device for a few sectors, then not bother for subsequent sectors (as it never writes to failed devices). In this case the bitmap bit will be cleared, but it really shouldn't. The result is that if the recovering device fails and is then re-added (after fixing whatever hardware problem triggerred the failure), the second recovery won't redo the region it was in the middle of, so some of the device will not be recovered properly. If we abort the recovery, the region being processes will be cancelled (bit not cleared) and the whole region will be retried. As the bug can result in data corruption the patch is suitable for -stable. For kernels prior to 3.11 there is a conflict in raid10.c which will require care. Original-from: jiao hui <jiaohui@bwstor.com.cn> Reported-and-tested-by: jiao hui <jiaohui@bwstor.com.cn> Signed-off-by: NeilBrown <neilb@suse.de> Cc: stable@vger.kernel.org
Diffstat (limited to 'drivers/md')
-rw-r--r--drivers/md/raid1.c8
-rw-r--r--drivers/md/raid10.c11
2 files changed, 9 insertions, 10 deletions
diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index 56e24c072b62..d7690f86fdb9 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -1501,12 +1501,12 @@ static void error(struct mddev *mddev, struct md_rdev *rdev)
mddev->degraded++;
set_bit(Faulty, &rdev->flags);
spin_unlock_irqrestore(&conf->device_lock, flags);
- /*
- * if recovery is running, make sure it aborts.
- */
- set_bit(MD_RECOVERY_INTR, &mddev->recovery);
} else
set_bit(Faulty, &rdev->flags);
+ /*
+ * if recovery is running, make sure it aborts.
+ */
+ set_bit(MD_RECOVERY_INTR, &mddev->recovery);
set_bit(MD_CHANGE_DEVS, &mddev->flags);
printk(KERN_ALERT
"md/raid1:%s: Disk failure on %s, disabling device.\n"
diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index cb882aae9e20..b08c18871323 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -1684,13 +1684,12 @@ static void error(struct mddev *mddev, struct md_rdev *rdev)
spin_unlock_irqrestore(&conf->device_lock, flags);
return;
}
- if (test_and_clear_bit(In_sync, &rdev->flags)) {
+ if (test_and_clear_bit(In_sync, &rdev->flags))
mddev->degraded++;
- /*
- * if recovery is running, make sure it aborts.
- */
- set_bit(MD_RECOVERY_INTR, &mddev->recovery);
- }
+ /*
+ * If recovery is running, make sure it aborts.
+ */
+ set_bit(MD_RECOVERY_INTR, &mddev->recovery);
set_bit(Blocked, &rdev->flags);
set_bit(Faulty, &rdev->flags);
set_bit(MD_CHANGE_DEVS, &mddev->flags);