ceph: avoid picking MDS that is not active

Ignore replication or auth frag data if it indicates an MDS that is not
active.  This can happen if the MDS shuts down and the client has stale
data about the namespace distribution across the MDS cluster.  If that's
the case, fall back to directing the request based on the auth cap (which
should always be accurate).

Signed-off-by: Sage Weil <sage@newdream.net>

diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index 509339ceef720fbf9e5a19a955bc0a1fce646ed4..a6949cc7c69a3e2faef2eba265a45d32c25240bc 100644 (file)
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -693,9 +693,11 @@ static int __choose_mds(struct ceph_mds_client *mdsc,
                                dout("choose_mds %p %llx.%llx "
                                     "frag %u mds%d (%d/%d)\n",
                                     inode, ceph_vinop(inode),
-                                    frag.frag, frag.mds,
+                                    frag.frag, mds,
                                     (int)r, frag.ndist);
-                               return mds;
+                               if (ceph_mdsmap_get_state(mdsc->mdsmap, mds) >=
+                                   CEPH_MDS_STATE_ACTIVE)
+                                       return mds;
                        }
 
                        /* since this file/dir wasn't known to be
@@ -708,7 +710,9 @@ static int __choose_mds(struct ceph_mds_client *mdsc,
                                dout("choose_mds %p %llx.%llx "
                                     "frag %u mds%d (auth)\n",
                                     inode, ceph_vinop(inode), frag.frag, mds);
-                               return mds;
+                               if (ceph_mdsmap_get_state(mdsc->mdsmap, mds) >=
+                                   CEPH_MDS_STATE_ACTIVE)
+                                       return mds;
                        }
                }
        }