QPID-4944: HA Sporadic failure in ha_tests: tes_failover_send_receive and test_expected_backup_timeout

Very sporadic failures so difficult to verify the fix.

- Simplified Membership, centralized status change, make it atomic.
- Fix test bug in test_expected_backup_timeout: not waiting on final status check, race.
- Remove out-of-date status info from log prefixes:  Guard, ReplicatingSubscription

git-svn-id: https://svn.apache.org/repos/asf/qpid/trunk@1495466 13f79535-47bb-0310-9956-ffa450edef68

2 files changed, 4 insertions, 7 deletions

diff --git a/qpid/cpp/src/tests/ha_test.py b/qpid/cpp/src/tests/ha_test.py
index f3c1d3a957..f2fc50054f 100755
--- a/qpid/cpp/src/tests/ha_test.py
+++ b/qpid/cpp/src/tests/ha_test.py
@@ -107,7 +107,7 @@ class HaBroker(Broker):
         ha_port = ha_port or HaPort(test)
         args = copy(args)
         args += ["--load-module", BrokerTest.ha_lib,
-                 "--log-enable=trace+:ha::", # FIXME aconway 2013-06-14: debug+
+                 "--log-enable=debug+:ha::",
                  # Non-standard settings for faster tests.
                  "--link-maintenance-interval=0.1",
                  # Heartbeat and negotiate time are needed so that a broker wont
diff --git a/qpid/cpp/src/tests/ha_tests.py b/qpid/cpp/src/tests/ha_tests.py
index 60e3444c45..368ac02506 100755
--- a/qpid/cpp/src/tests/ha_tests.py
+++ b/qpid/cpp/src/tests/ha_tests.py
@@ -1121,13 +1121,10 @@ class RecoveryTests(HaBrokerTest):
         but can still rejoin.
         """
         cluster = HaCluster(self, 3, args=["--ha-backup-timeout=0.5"]);
-        cluster[0].wait_status("active") # Primary ready
-        for b in cluster[1:3]: b.wait_status("ready") # Backups ready
         for i in [0,1]: cluster.kill(i, False)
-        cluster[2].promote()    # New primary, expected backup will 1
-        cluster[2].wait_status("recovering")
+        cluster[2].promote()    # New primary, expected backup will be 1
         # Should not go active till the expected backup connects or times out.
-        self.assertEqual(cluster[2].ha_status(), "recovering")
+        cluster[2].wait_status("recovering")
         # Messages should be held till expected backup times out
         s = cluster[2].connect().session().sender("q;{create:always}")
         s.send("foo", sync=False)
@@ -1135,7 +1132,7 @@ class RecoveryTests(HaBrokerTest):
         try: s.sync(timeout=.01); self.fail("Expected Timeout exception")
         except Timeout: pass
         s.sync(timeout=1)       # And released after the timeout.
-        self.assertEqual(cluster[2].ha_status(), "active")
+        cluster[2].wait_status("active")
 
     def test_join_ready_cluster(self):
         """If we join a cluster where the primary is dead, the new primary is