md-cluster: remove capabilities
This adds "remove" capabilities for the clustered environment.
When a user initiates removal of a device from the array, a
REMOVE message with disk number in the array is sent to all
the nodes which kick the respective device in their own array.
This facilitates the removal of failed devices.
Signed-off-by: Goldwyn Rodrigues <rgoldwyn@suse.com>
Signed-off-by: NeilBrown <neilb@suse.de>
diff --git a/drivers/md/md-cluster.c b/drivers/md/md-cluster.c
index 10c44a3..30b41b7 100644
--- a/drivers/md/md-cluster.c
+++ b/drivers/md/md-cluster.c
@@ -72,6 +72,7 @@
METADATA_UPDATED = 0,
RESYNCING,
NEWDISK,
+ REMOVE,
};
struct cluster_msg {
@@ -401,6 +402,16 @@
dlm_lock_sync(cinfo->no_new_dev_lockres, DLM_LOCK_CR);
}
+static void process_remove_disk(struct mddev *mddev, struct cluster_msg *msg)
+{
+ struct md_rdev *rdev = md_find_rdev_nr_rcu(mddev, msg->raid_slot);
+
+ if (rdev)
+ md_kick_rdev_from_array(rdev);
+ else
+ pr_warn("%s: %d Could not find disk(%d) to REMOVE\n", __func__, __LINE__, msg->raid_slot);
+}
+
static void process_recvd_msg(struct mddev *mddev, struct cluster_msg *msg)
{
switch (msg->type) {
@@ -419,6 +430,15 @@
pr_info("%s: %d Received message: NEWDISK from %d\n",
__func__, __LINE__, msg->slot);
process_add_new_disk(mddev, msg);
+ break;
+ case REMOVE:
+ pr_info("%s: %d Received REMOVE from %d\n",
+ __func__, __LINE__, msg->slot);
+ process_remove_disk(mddev, msg);
+ break;
+ default:
+ pr_warn("%s:%d Received unknown message from %d\n",
+ __func__, __LINE__, msg->slot);
}
}
@@ -854,6 +874,15 @@
return 0;
}
+static int remove_disk(struct mddev *mddev, struct md_rdev *rdev)
+{
+ struct cluster_msg cmsg;
+ struct md_cluster_info *cinfo = mddev->cluster_info;
+ cmsg.type = REMOVE;
+ cmsg.raid_slot = rdev->desc_nr;
+ return __sendmsg(cinfo, &cmsg);
+}
+
static struct md_cluster_operations cluster_ops = {
.join = join,
.leave = leave,
@@ -868,6 +897,7 @@
.add_new_disk_start = add_new_disk_start,
.add_new_disk_finish = add_new_disk_finish,
.new_disk_ack = new_disk_ack,
+ .remove_disk = remove_disk,
};
static int __init cluster_init(void)
diff --git a/drivers/md/md-cluster.h b/drivers/md/md-cluster.h
index 7417133..71e5143 100644
--- a/drivers/md/md-cluster.h
+++ b/drivers/md/md-cluster.h
@@ -22,6 +22,7 @@
int (*add_new_disk_start)(struct mddev *mddev, struct md_rdev *rdev);
int (*add_new_disk_finish)(struct mddev *mddev);
int (*new_disk_ack)(struct mddev *mddev, bool ack);
+ int (*remove_disk)(struct mddev *mddev, struct md_rdev *rdev);
};
#endif /* _MD_CLUSTER_H */
diff --git a/drivers/md/md.c b/drivers/md/md.c
index d406a79..ca011d1 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -2477,8 +2477,10 @@
else {
struct mddev *mddev = rdev->mddev;
if (mddev_is_clustered(mddev))
- md_cluster_ops->metadata_update_start(mddev);
+ md_cluster_ops->remove_disk(mddev, rdev);
md_kick_rdev_from_array(rdev);
+ if (mddev_is_clustered(mddev))
+ md_cluster_ops->metadata_update_start(mddev);
if (mddev->pers)
md_update_sb(mddev, 1);
md_new_event(mddev);
@@ -5968,6 +5970,9 @@
if (rdev->raid_disk >= 0)
goto busy;
+ if (mddev_is_clustered(mddev))
+ md_cluster_ops->remove_disk(mddev, rdev);
+
md_kick_rdev_from_array(rdev);
md_update_sb(mddev, 1);
md_new_event(mddev);