[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, 5 insertions, 0 deletions

diff --git a/fs/ocfs2/dlm/dlmconvert.c b/fs/ocfs2/dlm/dlmconvert.c
index f5c2f1979ad3..f66e2d818ccd 100644
--- a/fs/ocfs2/dlm/dlmconvert.c
+++ b/fs/ocfs2/dlm/dlmconvert.c
@@ -392,6 +392,11 @@ static enum dlm_status dlm_send_remote_convert_request(struct dlm_ctxt *dlm,
         } else {
                 mlog_errno(tmpret);
                 if (dlm_is_host_down(tmpret)) {
+                        /* instead of logging the same network error over
+                         * and over, sleep here and wait for the heartbeat
+                         * to notice the node is dead.  times out after 5s. */
+                        dlm_wait_for_node_death(dlm, res->owner, 
+                                                DLM_NODE_DEATH_WAIT_MAX);
                         ret = DLM_RECOVERING;
                         mlog(0, "node %u died so returning DLM_RECOVERING "
                              "from convert message!\n", res->owner);