From 63ee42a85ceae2f443a3071ec7385a348f33f5f0 Mon Sep 17 00:00:00 2001
From: Alexander Kukushkin <cyberdemn@gmail.com>
Date: Tue, 30 Nov 2021 16:33:38 +0100
Subject: [PATCH] Clear event on the leader node when /status was updated
 (#2125)

Not doing so causing excessive HA loop runs with Zookeeper.
This moment wasn't fixed correctly in the #1875
---
 patroni/dcs/zookeeper.py | 23 +++++++++++++----------
 tests/test_zookeeper.py  |  2 ++
 2 files changed, 15 insertions(+), 10 deletions(-)

diff --git a/patroni/dcs/zookeeper.py b/patroni/dcs/zookeeper.py
index 4ac03cad..71ef44ea 100644
--- a/patroni/dcs/zookeeper.py
+++ b/patroni/dcs/zookeeper.py
@@ -283,17 +283,20 @@ class ZooKeeper(AbstractDCS):
                 logger.exception('get_cluster')
                 self.cluster_watcher(None)
                 raise ZooKeeperError('ZooKeeper in not responding properly')
-        # The /status ZNode was updated or doesn't exist and we are not leader
-        elif (self._fetch_status and not self._fetch_cluster or not cluster.last_lsn
-              or cluster.has_permanent_logical_slots(self._name, False) and not cluster.slots) and\
-                not (cluster.leader and cluster.leader.name == self._name):
-            try:
-                last_lsn, slots = self.get_status(cluster.leader)
+        # The /status ZNode was updated or doesn't exist
+        elif self._fetch_status and not self._fetch_cluster or not cluster.last_lsn \
+                or cluster.has_permanent_logical_slots(self._name, False) and not cluster.slots:
+            # If current node is the leader just clear the event without fetching anything (we are updating the /status)
+            if cluster.leader and cluster.leader.name == self._name:
                 self.event.clear()
-                cluster = Cluster(cluster.initialize, cluster.config, cluster.leader, last_lsn,
-                                  cluster.members, cluster.failover, cluster.sync, cluster.history, slots)
-            except Exception:
-                pass
+            else:
+                try:
+                    last_lsn, slots = self.get_status(cluster.leader)
+                    self.event.clear()
+                    cluster = Cluster(cluster.initialize, cluster.config, cluster.leader, last_lsn,
+                                      cluster.members, cluster.failover, cluster.sync, cluster.history, slots)
+                except Exception:
+                    pass
         return cluster
 
     def _bypass_caches(self):
diff --git a/tests/test_zookeeper.py b/tests/test_zookeeper.py
index 09857fb2..4ff89d8b 100644
--- a/tests/test_zookeeper.py
+++ b/tests/test_zookeeper.py
@@ -173,6 +173,8 @@ class TestZooKeeper(unittest.TestCase):
         self.assertRaises(ZooKeeperError, self.zk.get_cluster)
         cluster = self.zk.get_cluster(True)
         self.assertIsInstance(cluster.leader, Leader)
+        self.zk.status_watcher(None)
+        self.zk.get_cluster()
         self.zk.touch_member({'foo': 'foo'})
         self.zk._name = 'bar'
         self.zk.status_watcher(None)