md-cluster: gather resync infos and enable recv_thread after bitmap is ready
The in-memory bitmap is not ready when node joins cluster, so it doesn't make sense to make gather_all_resync_info() called so earlier, we need to call it after the node's bitmap is setup. Also, recv_thread could be wake up after node joins cluster, but it could cause problem if node receives RESYNCING message without persionality since mddev->pers->quiesce is called in process_suspend_info. This commit introduces a new cluster interface load_bitmaps to fix above problems, load_bitmaps is called in bitmap_load where bitmap and persionality are ready, and load_bitmaps does the following tasks: 1. call gather_all_resync_info to load all the node's bitmap info. 2. set MD_CLUSTER_ALREADY_IN_CLUSTER bit to recv_thread could be wake up, and wake up recv_thread if there is pending recv event. Then ack_bast only wakes up recv_thread after IN_CLUSTER bit is ready otherwise MD_CLUSTER_PENDING_RESYNC_EVENT is set. Reviewed-by: NeilBrown <neilb@suse.com> Signed-off-by: Guoqing Jiang <gqjiang@suse.com> Signed-off-by: Shaohua Li <shli@fb.com>
This commit is contained in:
parent
85ad1d13ee
commit
51e453aecb
|
@ -1848,6 +1848,9 @@ int bitmap_load(struct mddev *mddev)
|
|||
if (!bitmap)
|
||||
goto out;
|
||||
|
||||
if (mddev_is_clustered(mddev))
|
||||
md_cluster_ops->load_bitmaps(mddev, mddev->bitmap_info.nodes);
|
||||
|
||||
/* Clear out old bitmap info first: Either there is none, or we
|
||||
* are resuming after someone else has possibly changed things,
|
||||
* so we should forget old cached info.
|
||||
|
|
|
@ -61,6 +61,10 @@ struct resync_info {
|
|||
* the lock.
|
||||
*/
|
||||
#define MD_CLUSTER_SEND_LOCKED_ALREADY 5
|
||||
/* We should receive message after node joined cluster and
|
||||
* set up all the related infos such as bitmap and personality */
|
||||
#define MD_CLUSTER_ALREADY_IN_CLUSTER 6
|
||||
#define MD_CLUSTER_PENDING_RECV_EVENT 7
|
||||
|
||||
|
||||
struct md_cluster_info {
|
||||
|
@ -376,8 +380,12 @@ static void ack_bast(void *arg, int mode)
|
|||
struct dlm_lock_resource *res = arg;
|
||||
struct md_cluster_info *cinfo = res->mddev->cluster_info;
|
||||
|
||||
if (mode == DLM_LOCK_EX)
|
||||
md_wakeup_thread(cinfo->recv_thread);
|
||||
if (mode == DLM_LOCK_EX) {
|
||||
if (test_bit(MD_CLUSTER_ALREADY_IN_CLUSTER, &cinfo->state))
|
||||
md_wakeup_thread(cinfo->recv_thread);
|
||||
else
|
||||
set_bit(MD_CLUSTER_PENDING_RECV_EVENT, &cinfo->state);
|
||||
}
|
||||
}
|
||||
|
||||
static void __remove_suspend_info(struct md_cluster_info *cinfo, int slot)
|
||||
|
@ -846,10 +854,6 @@ static int join(struct mddev *mddev, int nodes)
|
|||
if (!cinfo->resync_lockres)
|
||||
goto err;
|
||||
|
||||
ret = gather_all_resync_info(mddev, nodes);
|
||||
if (ret)
|
||||
goto err;
|
||||
|
||||
return 0;
|
||||
err:
|
||||
md_unregister_thread(&cinfo->recovery_thread);
|
||||
|
@ -867,6 +871,19 @@ err:
|
|||
return ret;
|
||||
}
|
||||
|
||||
static void load_bitmaps(struct mddev *mddev, int total_slots)
|
||||
{
|
||||
struct md_cluster_info *cinfo = mddev->cluster_info;
|
||||
|
||||
/* load all the node's bitmap info for resync */
|
||||
if (gather_all_resync_info(mddev, total_slots))
|
||||
pr_err("md-cluster: failed to gather all resyn infos\n");
|
||||
set_bit(MD_CLUSTER_ALREADY_IN_CLUSTER, &cinfo->state);
|
||||
/* wake up recv thread in case something need to be handled */
|
||||
if (test_and_clear_bit(MD_CLUSTER_PENDING_RECV_EVENT, &cinfo->state))
|
||||
md_wakeup_thread(cinfo->recv_thread);
|
||||
}
|
||||
|
||||
static void resync_bitmap(struct mddev *mddev)
|
||||
{
|
||||
struct md_cluster_info *cinfo = mddev->cluster_info;
|
||||
|
@ -1208,6 +1225,7 @@ static struct md_cluster_operations cluster_ops = {
|
|||
.add_new_disk_cancel = add_new_disk_cancel,
|
||||
.new_disk_ack = new_disk_ack,
|
||||
.remove_disk = remove_disk,
|
||||
.load_bitmaps = load_bitmaps,
|
||||
.gather_bitmaps = gather_bitmaps,
|
||||
.lock_all_bitmaps = lock_all_bitmaps,
|
||||
.unlock_all_bitmaps = unlock_all_bitmaps,
|
||||
|
|
|
@ -23,6 +23,7 @@ struct md_cluster_operations {
|
|||
void (*add_new_disk_cancel)(struct mddev *mddev);
|
||||
int (*new_disk_ack)(struct mddev *mddev, bool ack);
|
||||
int (*remove_disk)(struct mddev *mddev, struct md_rdev *rdev);
|
||||
void (*load_bitmaps)(struct mddev *mddev, int total_slots);
|
||||
int (*gather_bitmaps)(struct md_rdev *rdev);
|
||||
int (*lock_all_bitmaps)(struct mddev *mddev);
|
||||
void (*unlock_all_bitmaps)(struct mddev *mddev);
|
||||
|
|
Loading…
Reference in New Issue