Commit 88bcfef7 authored by Goldwyn Rodrigues's avatar Goldwyn Rodrigues Committed by NeilBrown

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: default avatarGoldwyn Rodrigues <rgoldwyn@suse.com>
Signed-off-by: default avatarNeilBrown <neilb@suse.de>
parent 57d051dc
...@@ -72,6 +72,7 @@ enum msg_type { ...@@ -72,6 +72,7 @@ enum msg_type {
METADATA_UPDATED = 0, METADATA_UPDATED = 0,
RESYNCING, RESYNCING,
NEWDISK, NEWDISK,
REMOVE,
}; };
struct cluster_msg { struct cluster_msg {
...@@ -401,6 +402,16 @@ static void process_metadata_update(struct mddev *mddev, struct cluster_msg *msg ...@@ -401,6 +402,16 @@ static void process_metadata_update(struct mddev *mddev, struct cluster_msg *msg
dlm_lock_sync(cinfo->no_new_dev_lockres, DLM_LOCK_CR); 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) static void process_recvd_msg(struct mddev *mddev, struct cluster_msg *msg)
{ {
switch (msg->type) { switch (msg->type) {
...@@ -419,6 +430,15 @@ static void process_recvd_msg(struct mddev *mddev, struct cluster_msg *msg) ...@@ -419,6 +430,15 @@ static void process_recvd_msg(struct mddev *mddev, struct cluster_msg *msg)
pr_info("%s: %d Received message: NEWDISK from %d\n", pr_info("%s: %d Received message: NEWDISK from %d\n",
__func__, __LINE__, msg->slot); __func__, __LINE__, msg->slot);
process_add_new_disk(mddev, msg); 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 @@ static int new_disk_ack(struct mddev *mddev, bool ack) ...@@ -854,6 +874,15 @@ static int new_disk_ack(struct mddev *mddev, bool ack)
return 0; 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 = { static struct md_cluster_operations cluster_ops = {
.join = join, .join = join,
.leave = leave, .leave = leave,
...@@ -868,6 +897,7 @@ static struct md_cluster_operations cluster_ops = { ...@@ -868,6 +897,7 @@ static struct md_cluster_operations cluster_ops = {
.add_new_disk_start = add_new_disk_start, .add_new_disk_start = add_new_disk_start,
.add_new_disk_finish = add_new_disk_finish, .add_new_disk_finish = add_new_disk_finish,
.new_disk_ack = new_disk_ack, .new_disk_ack = new_disk_ack,
.remove_disk = remove_disk,
}; };
static int __init cluster_init(void) static int __init cluster_init(void)
......
...@@ -22,6 +22,7 @@ struct md_cluster_operations { ...@@ -22,6 +22,7 @@ struct md_cluster_operations {
int (*add_new_disk_start)(struct mddev *mddev, struct md_rdev *rdev); int (*add_new_disk_start)(struct mddev *mddev, struct md_rdev *rdev);
int (*add_new_disk_finish)(struct mddev *mddev); int (*add_new_disk_finish)(struct mddev *mddev);
int (*new_disk_ack)(struct mddev *mddev, bool ack); int (*new_disk_ack)(struct mddev *mddev, bool ack);
int (*remove_disk)(struct mddev *mddev, struct md_rdev *rdev);
}; };
#endif /* _MD_CLUSTER_H */ #endif /* _MD_CLUSTER_H */
...@@ -2477,8 +2477,10 @@ state_store(struct md_rdev *rdev, const char *buf, size_t len) ...@@ -2477,8 +2477,10 @@ state_store(struct md_rdev *rdev, const char *buf, size_t len)
else { else {
struct mddev *mddev = rdev->mddev; struct mddev *mddev = rdev->mddev;
if (mddev_is_clustered(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); md_kick_rdev_from_array(rdev);
if (mddev_is_clustered(mddev))
md_cluster_ops->metadata_update_start(mddev);
if (mddev->pers) if (mddev->pers)
md_update_sb(mddev, 1); md_update_sb(mddev, 1);
md_new_event(mddev); md_new_event(mddev);
...@@ -5968,6 +5970,9 @@ static int hot_remove_disk(struct mddev *mddev, dev_t dev) ...@@ -5968,6 +5970,9 @@ static int hot_remove_disk(struct mddev *mddev, dev_t dev)
if (rdev->raid_disk >= 0) if (rdev->raid_disk >= 0)
goto busy; goto busy;
if (mddev_is_clustered(mddev))
md_cluster_ops->remove_disk(mddev, rdev);
md_kick_rdev_from_array(rdev); md_kick_rdev_from_array(rdev);
md_update_sb(mddev, 1); md_update_sb(mddev, 1);
md_new_event(mddev); md_new_event(mddev);
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment