[PATCH] ocfs2/dlm: fixes
* fix a hang which can occur during shutdown migration
* do not allow nodes to join during recovery
* when restarting lock mastery, do not ignore nodes which come up
* more than one node could become recovery master, fix this
* sleep to allow some time for heartbeat state to catch up to network
* extra debug info for bad recovery state problems
* make DLM_RECO_NODE_DATA_DONE a valid state for non-master recovery nodes
* prune all locks from dead nodes on $RECOVERY lock resources
* do NOT automatically add new nodes to mle nodemaps until they have properly
joined the domain
* make sure dlm_pick_recovery_master only exits when all nodes have synced
* properly handle dlmunlock errors in dlm_pick_recovery_master
* do not propagate network errors in dlm_send_begin_reco_message
* dead nodes were not being put in the recovery map sometimes, fix this
* dlmunlock was failing to clear the unlock actions on DLM_DENIED
Signed-off-by: Kurt Hackel <kurt.hackel@oracle.com>
Signed-off-by: Mark Fasheh <mark.fasheh@oracle.com>
diff --git a/fs/ocfs2/dlm/dlmmaster.c b/fs/ocfs2/dlm/dlmmaster.c
index 27e984f..a3194fe 100644
--- a/fs/ocfs2/dlm/dlmmaster.c
+++ b/fs/ocfs2/dlm/dlmmaster.c
@@ -1050,17 +1050,10 @@
node = dlm_bitmap_diff_iter_next(&bdi, &sc);
while (node >= 0) {
if (sc == NODE_UP) {
- /* a node came up. easy. might not even need
- * to talk to it if its node number is higher
- * or if we are already blocked. */
- mlog(0, "node up! %d\n", node);
- if (blocked)
- goto next;
-
- if (node > dlm->node_num) {
- mlog(0, "node > this node. skipping.\n");
- goto next;
- }
+ /* a node came up. clear any old vote from
+ * the response map and set it in the vote map
+ * then restart the mastery. */
+ mlog(ML_NOTICE, "node %d up while restarting\n", node);
/* redo the master request, but only for the new node */
mlog(0, "sending request to new node\n");
@@ -2005,6 +1998,15 @@
break;
mlog(0, "timed out during migration\n");
+ /* avoid hang during shutdown when migrating lockres
+ * to a node which also goes down */
+ if (dlm_is_node_dead(dlm, target)) {
+ mlog(0, "%s:%.*s: expected migration target %u "
+ "is no longer up. restarting.\n",
+ dlm->name, res->lockname.len,
+ res->lockname.name, target);
+ ret = -ERESTARTSYS;
+ }
}
if (ret == -ERESTARTSYS) {
/* migration failed, detach and clean up mle */