qa: timeout when waiting for mgr to be available

Otherwise during upgrades we wait forever.

Signed-off-by: Josh Durgin <jdurgin@redhat.com>

diff --git a/qa/tasks/ceph.py b/qa/tasks/ceph.py
index 05c4c7d90abf3eda87c8a7e81bedec39637e0715..b8d8b8a42f57b761eb920339ee6e97d45168e011 100644 (file)
--- a/qa/tasks/ceph.py
+++ b/qa/tasks/ceph.py
@@ -1225,9 +1225,9 @@ def healthy(ctx, config):
     log.info('Waiting until %s daemons up and pgs clean...', cluster_name)
     manager = ctx.managers[cluster_name]
     try:
-        manager.wait_for_mgr_available()
-    except run.CommandFailedError:
-        log.info('ignoring mgr wait error, probably testing upgrade')
+        manager.wait_for_mgr_available(timeout=30)
+    except (run.CommandFailedError, AssertionError) as e:
+        log.info('ignoring mgr wait error, probably testing upgrade: %s', e)
 
     firstmon = teuthology.get_first_mon(ctx, config, cluster_name)
     (mon0_remote,) = ctx.cluster.only(firstmon).remotes.keys()