qa/tasks/cephfs/test_sessionmap: reap connections immediately

We have to reap connections promptly for this test to work.

This test was broken indirectly by d51d80b3234e17690061f65dc7e1515f4244a5a3,
which moved the counter decrement to reap time instead of mark_down/stop
time.

The reaping is asynchronous, so allow for a delay in the count change.

Fixes: https://tracker.ceph.com/issues/50622
Signed-off-by: Sage Weil <sage@newdream.net>

diff --git a/qa/tasks/cephfs/test_sessionmap.py b/qa/tasks/cephfs/test_sessionmap.py
index 79f1fb45e243a05f57a32b30c0b464f6de2f80cf..ad6fd1d609cb9b21701caed068a68cde1fa6285d 100644 (file)
--- a/qa/tasks/cephfs/test_sessionmap.py
+++ b/qa/tasks/cephfs/test_sessionmap.py
@@ -41,21 +41,26 @@ class TestSessionMap(CephFSTestCase):
         the conn count goes back to where it started (i.e. we aren't
         leaving connections open)
         """
+        self.config_set('mds', 'ms_async_reap_threshold', '1')
+
         self.mount_a.umount_wait()
         self.mount_b.umount_wait()
 
         status = self.fs.status()
         s = self._get_connection_count(status=status)
         self.fs.rank_tell(["session", "ls"], status=status)
-        e = self._get_connection_count(status=status)
-
-        self.assertEqual(s, e)
+        self.wait_until_true(
+            lambda: self._get_connection_count(status=status) == s,
+            timeout=30
+        )
 
     def test_mount_conn_close(self):
         """
         That when a client unmounts, the thread count on the MDS goes back
         to what it was before the client mounted
         """
+        self.config_set('mds', 'ms_async_reap_threshold', '1')
+
         self.mount_a.umount_wait()
         self.mount_b.umount_wait()
 
@@ -64,9 +69,10 @@ class TestSessionMap(CephFSTestCase):
         self.mount_a.mount_wait()
         self.assertGreater(self._get_connection_count(status=status), s)
         self.mount_a.umount_wait()
-        e = self._get_connection_count(status=status)
-
-        self.assertEqual(s, e)
+        self.wait_until_true(
+            lambda: self._get_connection_count(status=status) == s,
+            timeout=30
+        )
 
     def test_version_splitting(self):
         """