[PATCH] ocfs2: recheck recovery state after getting lock
* after successfully taking the $RECOVERY lock in EX mode, recheck to make
sure that recovery has not already begun or completed on another node
Signed-off-by: Kurt Hackel <kurt.hackel@oracle.com>
Signed-off-by: Mark Fasheh <mark.fasheh@oracle.com>
diff --git a/fs/ocfs2/dlm/dlmrecovery.c b/fs/ocfs2/dlm/dlmrecovery.c
index 186e9a7..f9ce864 100644
--- a/fs/ocfs2/dlm/dlmrecovery.c
+++ b/fs/ocfs2/dlm/dlmrecovery.c
@@ -2032,6 +2032,30 @@
dlm->reco.new_master);
status = -EEXIST;
} else {
+ status = 0;
+
+ /* see if recovery was already finished elsewhere */
+ spin_lock(&dlm->spinlock);
+ if (dlm->reco.dead_node == O2NM_INVALID_NODE_NUM) {
+ status = -EINVAL;
+ mlog(0, "%s: got reco EX lock, but "
+ "node got recovered already\n", dlm->name);
+ if (dlm->reco.new_master != O2NM_INVALID_NODE_NUM) {
+ mlog(ML_ERROR, "%s: new master is %u "
+ "but no dead node!\n",
+ dlm->name, dlm->reco.new_master);
+ BUG();
+ }
+ }
+ spin_unlock(&dlm->spinlock);
+ }
+
+ /* if this node has actually become the recovery master,
+ * set the master and send the messages to begin recovery */
+ if (!status) {
+ mlog(0, "%s: dead=%u, this=%u, sending "
+ "begin_reco now\n", dlm->name,
+ dlm->reco.dead_node, dlm->node_num);
status = dlm_send_begin_reco_message(dlm,
dlm->reco.dead_node);
/* this always succeeds */