mds: initiate monitor reconnect if beacon acks take too long

If it takes 2*mds_beacon_grace (default 30 seconds total) seconds
to get an ack back, maybe it's the monitor and not us. Try a reconnect,
which will just add the teensiest bit of load if we're wrong.

Signed-off-by: Greg Farnum <gregory.farnum@dreamhost.com>

1 files changed, 6 insertions, 0 deletions

diff --git a/src/mds/MDS.cc b/src/mds/MDS.cc
index a9b4001ff1d..a8c38a90e47 100644
--- a/src/mds/MDS.cc
+++ b/src/mds/MDS.cc
@@ -623,6 +623,12 @@ bool MDS::is_laggy()
     dout(5) << "is_laggy " << since << " > " << g_conf->mds_beacon_grace
 	    << " since last acked beacon" << dendl;
     was_laggy = true;
+    if (since > (g_conf->mds_beacon_grace*2)) {
+      // maybe it's not us?
+      dout(5) << "initiating monitor reconnect; maybe we're not the slow one"
+              << dendl;
+      monc->reopen_session();
+    }
     return true;
   }
   return false;