[DLM] abort recovery more quickly

When we abort one recovery to do another, break out of the ping_members()
routine more quickly, and wake up the dlm_recoverd thread more quickly
instead of waiting for it to time out.

Signed-off-by: David Teigland <teigland@redhat.com>
Signed-off-by: Steven Whitehouse <swhiteho@redhat.com>

2 files changed, 20 insertions, 5 deletions

diff --git a/fs/dlm/member.c b/fs/dlm/member.c
index cd0c51e..ebb33c3 100644
--- a/fs/dlm/member.c
+++ b/fs/dlm/member.c
@@ -162,11 +162,22 @@ static void make_member_array(struct dlm_ls *ls)
 
 /* send a status request to all members just to establish comms connections */
 
-static void ping_members(struct dlm_ls *ls)
+static int ping_members(struct dlm_ls *ls)
 {
 	struct dlm_member *memb;
-	list_for_each_entry(memb, &ls->ls_nodes, list)
-		dlm_rcom_status(ls, memb->nodeid);
+	int error = 0;
+
+	list_for_each_entry(memb, &ls->ls_nodes, list) {
+		error = dlm_recovery_stopped(ls);
+		if (error)
+			break;
+		error = dlm_rcom_status(ls, memb->nodeid);
+		if (error)
+			break;
+	}
+	if (error)
+		log_debug(ls, "ping_members aborted %d", error);
+	return error;
 }
 
 int dlm_recover_members(struct dlm_ls *ls, struct dlm_recover *rv, int *neg_out)
@@ -212,10 +223,13 @@ int dlm_recover_members(struct dlm_ls *ls, struct dlm_recover *rv, int *neg_out)
 	dlm_set_recover_status(ls, DLM_RS_NODES);
 	*neg_out = neg;
 
-	ping_members(ls);
+	error = ping_members(ls);
+	if (error)
+		goto out;
 
 	error = dlm_recover_members_wait(ls);
-	log_debug(ls, "total members %d", ls->ls_num_nodes);
+ out:
+	log_debug(ls, "total members %d error %d", ls->ls_num_nodes, error);
 	return error;
 }
 
diff --git a/fs/dlm/recoverd.c b/fs/dlm/recoverd.c
index 7010353..eac8e9f 100644
--- a/fs/dlm/recoverd.c
+++ b/fs/dlm/recoverd.c
@@ -275,6 +275,7 @@ void dlm_recoverd_stop(struct dlm_ls *ls)
 
 void dlm_recoverd_suspend(struct dlm_ls *ls)
 {
+	wake_up(&ls->ls_wait_general);
 	mutex_lock(&ls->ls_recoverd_active);
 }