Clear joining_node no matter whether it is in the domain map or not.

Currently the process of dlm join contains 2 steps: query join and assert join. After query join, the joined node will set its joining_node. So if the joining node happens to panic before the 2nd step, the joined node will fail to clear its joining_node flag because that node isn't in the domain map. It at least cause 2 problems.
1. All the new join request will fail. So no new node can mount the volume.
2. The joined node can't umount the volume since during the umount process it has to wait for the joining_node to be unknown. So the umount will be hanged.

The solution is to clear the joining_node before we check the domain map.

Signed-off-by Tao Ma <[email protected]>

---
 fs/ocfs2/dlm/dlmrecovery.c |   12 ++++++------
 1 files changed, 6 insertions(+), 6 deletions(-)

fs/ocfs2/dlm/dlmrecovery.c +6 -6

index 2fde7bf..3502bec 100644
@@ -2270,6 +2270,12 @@ static void __dlm_hb_node_down(struct dlm_ctxt *dlm, int idx)
 		}
 	}
 
+	/* Clean up join state on node death. */
+	if (dlm->joining_node == idx) {
+		mlog(0, "Clearing join state for node %u\n", idx);
+		__dlm_set_joining_node(dlm, DLM_LOCK_RES_OWNER_UNKNOWN);
+	}
+
 	/* check to see if the node is already considered dead */
 	if (!test_bit(idx, dlm->live_nodes_map)) {
 		mlog(0, "for domain %s, node %d is already dead. "

@@ -2288,12 +2294,6 @@ static void __dlm_hb_node_down(struct dlm_ctxt *dlm, int idx)
 
 	clear_bit(idx, dlm->live_nodes_map);
 
-	/* Clean up join state on node death. */
-	if (dlm->joining_node == idx) {
-		mlog(0, "Clearing join state for node %u\n", idx);
-		__dlm_set_joining_node(dlm, DLM_LOCK_RES_OWNER_UNKNOWN);
-	}
-
 	/* make sure local cleanup occurs before the heartbeat events */
 	if (!test_bit(idx, dlm->recovery_map))
 		dlm_do_local_recovery_cleanup(dlm, idx);

This looks good. Did you manage to actually test this scenario?

We'll need to apply this both git and 1.2.

Quoted 57 lines · Tao Ma

Currently the process of dlm join contains 2 steps: query join and assert join.
After query join, the joined node will set its joining_node. So if the joining
node happens to panic before the 2nd step, the joined node will fail to clear
its joining_node flag because that node isn't in the domain map. It at least
cause 2 problems.
1. All the new join request will fail. So no new node can mount the volume.
2. The joined node can't umount the volume since during the umount process it
has to wait for the joining_node to be unknown. So the umount will
be hanged.

The solution is to clear the joining_node before we check the domain map.

Signed-off-by Tao Ma <[email protected]>

---
 fs/ocfs2/dlm/dlmrecovery.c |   12 ++++++------
 1 files changed, 6 insertions(+), 6 deletions(-)

fs/ocfs2/dlm/dlmrecovery.c +6 -0

index 2fde7bf..3502bec 100644
@@ -2270,6 +2270,12 @@ static void __dlm_hb_node_down(struct dlm_ctxt 
 *dlm, int idx)
         }
     }
 
+    /* Clean up join state on node death. */
+    if (dlm->joining_node == idx) {
+        mlog(0, "Clearing join state for node %u\n", idx);
+        __dlm_set_joining_node(dlm, DLM_LOCK_RES_OWNER_UNKNOWN);
+    }
+
     /* check to see if the node is already considered dead */
     if (!test_bit(idx, dlm->live_nodes_map)) {

mlog(0, "for domain %s, node %d is already dead. "

fs/ocfs2/dlm/dlmrecovery.c +0 -6

@@ -2288,12 +2294,6 @@ static void __dlm_hb_node_down(struct dlm_ctxt 
 *dlm, int idx)
 
     clear_bit(idx, dlm->live_nodes_map);
 
-    /* Clean up join state on node death. */
-    if (dlm->joining_node == idx) {
-        mlog(0, "Clearing join state for node %u\n", idx);
-        __dlm_set_joining_node(dlm, DLM_LOCK_RES_OWNER_UNKNOWN);
-    }
-
     /* make sure local cleanup occurs before the heartbeat events */
     if (!test_bit(idx, dlm->recovery_map))

         dlm_do_local_recovery_cleanup(dlm, idx);

fs/ocfs2/dlm/dlmrecovery.c +6 -0

index 2fde7bf..3502bec 100644
@@ -2270,6 +2270,12 @@ static void __dlm_hb_node_down(struct dlm_ctxt *dlm, int idx)
 		}
 	}
 
+	/* Clean up join state on node death. */
+	if (dlm->joining_node == idx) {
+		mlog(0, "Clearing join state for node %u\n", idx);
+		__dlm_set_joining_node(dlm, DLM_LOCK_RES_OWNER_UNKNOWN);
+	}
+
 	/* check to see if the node is already considered dead */
 	if (!test_bit(idx, dlm->live_nodes_map)) {
 		mlog(0, "for domain %s, node %d is already dead. "