rados/valgrind-leaks: add timeout value for stop command

increase the timeout before stop command failed. in case
of monitor running under valgrind, we sometimes failed beacuse
of timeout.

Fixes: https://tracker.ceph.com/issues/63501
Signed-off-by: Nitzan Mordechai <nmordech@redhat.com>

diff --git a/qa/suites/rados/valgrind-leaks/1-start.yaml b/qa/suites/rados/valgrind-leaks/1-start.yaml
index cc8c8e537666c0f2b353f4a496ee4ae307d5933c..bfc72596cd3bb04745311af2dfb52f14c9e90dc0 100644 (file)
--- a/qa/suites/rados/valgrind-leaks/1-start.yaml
+++ b/qa/suites/rados/valgrind-leaks/1-start.yaml
@@ -25,6 +25,7 @@ overrides:
     valgrind:
       mon: [--tool=memcheck, --leak-check=full, --show-reachable=yes]
       osd: [--tool=memcheck]
+    stop-daemons-timeout: 1200
 roles:
 - [mon.a, mon.b, mon.c, mgr.x, mgr.y, osd.0, osd.1, osd.2, client.0]
 tasks:

diff --git a/qa/tasks/ceph.py b/qa/tasks/ceph.py
index 9b04e3dc675e0106ad7212ab4cca2a913d1af811..7077e6c3316b3ca5286b891942cba9c8e5794c0d 100644 (file)
--- a/qa/tasks/ceph.py
+++ b/qa/tasks/ceph.py
@@ -1514,7 +1514,8 @@ def run_daemon(ctx, config, type_):
     try:
         yield
     finally:
-        teuthology.stop_daemons_of_type(ctx, type_, cluster_name)
+        timeout = config.get('stop-daemons-timeout', 300)
+        teuthology.stop_daemons_of_type(ctx, type_, cluster_name, timeout=timeout)
 
 
 def healthy(ctx, config):