aboutsummaryrefslogtreecommitdiff
path: root/fs/ocfs2/dlm
diff options
context:
space:
mode:
authorTao Ma <tao.ma@oracle.com>2008-01-10 15:20:55 +0800
committerMark Fasheh <mark.fasheh@oracle.com>2008-01-25 15:05:46 -0800
commit2d4b1cbb44f5557727c35895a83f82d023573fa9 (patch)
treedfd6da78d6c18b9261b3c1cb572986ac5c495f66 /fs/ocfs2/dlm
parent4092d49f705aa19750c39758fa1be767e162c48d (diff)
ocfs2/dlm: Clear joining_node on hearbeat node down
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 <tao.ma@oracle.com> Signed-off-by: Mark Fasheh <mark.fasheh@oracle.com>
Diffstat (limited to 'fs/ocfs2/dlm')
-rw-r--r--fs/ocfs2/dlm/dlmrecovery.c12
1 files changed, 6 insertions, 6 deletions
diff --git a/fs/ocfs2/dlm/dlmrecovery.c b/fs/ocfs2/dlm/dlmrecovery.c
index b10f3e313fb..91f747b8a53 100644
--- a/fs/ocfs2/dlm/dlmrecovery.c
+++ b/fs/ocfs2/dlm/dlmrecovery.c
@@ -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);