mds: handle missing/corrupt data during boot

These errors trickle up to boot_start from e.g.
CInode::_fetched when something goes wrong.

Signed-off-by: John Spray <john.spray@redhat.com>

diff --git a/src/mds/MDS.cc b/src/mds/MDS.cc
index 5aea27d9c3140a839191fa14d5438816300e8818..be3d39bc19fe6b3bf0a85c42eeddec509e1cc97f 100644 (file)
--- a/src/mds/MDS.cc
+++ b/src/mds/MDS.cc
@@ -1939,7 +1939,14 @@ void MDS::boot_start(BootStep step, int r)
       dout(0) << "boot_start encountered an error EAGAIN"
               << ", respawning since we fell behind journal" << dendl;
       respawn();
+    } else if (r == -EINVAL || r == -ENOENT) {
+      // Invalid or absent data, indicates damaged on-disk structures
+      clog->error() << "Error loading MDS rank " << whoami << ": "
+        << cpp_strerror(r);
+      damaged();
+      assert(r == 0);  // Unreachable, damaged() calls respawn()
     } else {
+      // Completely unexpected error, give up and die
       dout(0) << "boot_start encountered an error, failing" << dendl;
       suicide();
       return;