[PATCH] ocfs2: add dlm_wait_for_node_death

* add dlm_wait_for_node_death function to be used after receiving a network
  error.  this will wait for the given timeout to allow the heartbeat
  callbacks to update the domain map.  without this, some paths may spin
  and consume enough cpu that the heartbeat gets starved and never updates.

Signed-off-by: Kurt Hackel <kurt.hackel@oracle.com>
Signed-off-by: Mark Fasheh <mark.fasheh@oracle.com>

1 files changed, 18 insertions, 0 deletions

diff --git a/fs/ocfs2/dlm/dlmrecovery.c b/fs/ocfs2/dlm/dlmrecovery.c
index f9ce864966ec..ed76bda1a534 100644
--- a/fs/ocfs2/dlm/dlmrecovery.c
+++ b/fs/ocfs2/dlm/dlmrecovery.c
@@ -278,6 +278,24 @@ int dlm_is_node_dead(struct dlm_ctxt *dlm, u8 node)
         return dead;
 }
 
+int dlm_wait_for_node_death(struct dlm_ctxt *dlm, u8 node, int timeout)
+{
+        if (timeout) {
+                mlog(ML_NOTICE, "%s: waiting %dms for notification of "
+                     "death of node %u\n", dlm->name, timeout, node);
+                wait_event_timeout(dlm->dlm_reco_thread_wq,
+                           dlm_is_node_dead(dlm, node),
+                           msecs_to_jiffies(timeout));
+        } else {
+                mlog(ML_NOTICE, "%s: waiting indefinitely for notification "
+                     "of death of node %u\n", dlm->name, node);
+                wait_event(dlm->dlm_reco_thread_wq,
+                           dlm_is_node_dead(dlm, node));
+        }
+        /* for now, return 0 */
+        return 0;
+}
+
 /* callers of the top-level api calls (dlmlock/dlmunlock) should
  * block on the dlm->reco.event when recovery is in progress.
  * the dlm recovery thread will set this state when it begins