md: allow last device to be forcibly removed from RAID1/RAID10.

When the 'last' device in a RAID1 or RAID10 reports an error,
we do not mark it as failed.  This would serve little purpose
as there is no risk of losing data beyond that which is obviously
lost (as there is with RAID5), and there could be other sectors
on the device which are readable, and only readable from this device.
This in general this maximises access to data.

However the current implementation also stops an admin from removing
the last device by direct action.  This is rarely useful, but in many
case is not harmful and can make automation easier by removing special
cases.

Also, if an attempt to write metadata fails the device must be marked
as faulty, else an infinite loop will result, attempting to update
the metadata on all non-faulty devices.

So add 'fail_last_dev' member to 'struct mddev', then we can bypasses
the 'last disk' checks for RAID1 and RAID10, and control the behavior
per array by change sysfs node.

Signed-off-by: NeilBrown <[email protected]>
[add sysfs node for fail_last_dev by Guoqing]
Signed-off-by: Guoqing Jiang <[email protected]>
Signed-off-by: Song Liu <[email protected]>

drivers/md/md.c

@@ -5178,6 +5178,34 @@ static struct md_sysfs_entry md_consistency_policy =
 __ATTR(consistency_policy, S_IRUGO | S_IWUSR, consistency_policy_show,
        consistency_policy_store);
 
+static ssize_t fail_last_dev_show(struct mddev *mddev, char *page)
+{
+	return sprintf(page, "%d\n", mddev->fail_last_dev);
+}
+
+/*
+ * Setting fail_last_dev to true to allow last device to be forcibly removed
+ * from RAID1/RAID10.
+ */
+static ssize_t
+fail_last_dev_store(struct mddev *mddev, const char *buf, size_t len)
+{
+	int ret;
+	bool value;
+
+	ret = kstrtobool(buf, &value);
+	if (ret)
+		return ret;
+
+	if (value != mddev->fail_last_dev)
+		mddev->fail_last_dev = value;
+
+	return len;
+}
+static struct md_sysfs_entry md_fail_last_dev =
+__ATTR(fail_last_dev, S_IRUGO | S_IWUSR, fail_last_dev_show,
+       fail_last_dev_store);
+
 static struct attribute *md_default_attrs[] = {
 	&md_level.attr,
 	&md_layout.attr,
@@ -5194,6 +5222,7 @@ static struct attribute *md_default_attrs[] = {
 	&md_array_size.attr,
 	&max_corr_read_errors.attr,
 	&md_consistency_policy.attr,
+	&md_fail_last_dev.attr,
 	NULL,
 };
 

drivers/md/md.h

@@ -487,6 +487,7 @@ struct mddev {
 	unsigned int			good_device_nr;	/* good device num within cluster raid */
 
 	bool	has_superblocks:1;
+	bool	fail_last_dev:1;
 };
 
 enum recovery_flags {

drivers/md/raid1.c

@@ -1617,12 +1617,12 @@ static void raid1_error(struct mddev *mddev, struct md_rdev *rdev)
 
 	/*
 	 * If it is not operational, then we have already marked it as dead
-	 * else if it is the last working disks, ignore the error, let the
-	 * next level up know.
+	 * else if it is the last working disks with "fail_last_dev == false",
+	 * ignore the error, let the next level up know.
 	 * else mark the drive as failed
 	 */
 	spin_lock_irqsave(&conf->device_lock, flags);
-	if (test_bit(In_sync, &rdev->flags)
+	if (test_bit(In_sync, &rdev->flags) && !mddev->fail_last_dev
 	    && (conf->raid_disks - mddev->degraded) == 1) {
 		/*
 		 * Don't fail the drive, act as though we were just a

drivers/md/raid10.c

@@ -1640,12 +1640,12 @@ static void raid10_error(struct mddev *mddev, struct md_rdev *rdev)
 
 	/*
 	 * If it is not operational, then we have already marked it as dead
-	 * else if it is the last working disks, ignore the error, let the
-	 * next level up know.
+	 * else if it is the last working disks with "fail_last_dev == false",
+	 * ignore the error, let the next level up know.
 	 * else mark the drive as failed
 	 */
 	spin_lock_irqsave(&conf->device_lock, flags);
-	if (test_bit(In_sync, &rdev->flags)
+	if (test_bit(In_sync, &rdev->flags) && !mddev->fail_last_dev
 	    && !enough(conf, rdev->raid_disk)) {
 		/*
 		 * Don't fail the drive, just return an IO error.