Update cluster_node_count to account for the quorum_standby state

check_patroni/cli.py

@@ -252,7 +252,7 @@ def cluster_node_count(
     The "healthy" checks only ensures that:
     * a leader has the running state
     * a standby_leader has the running or streaming (V3.0.4) state
-    * a replica or sync-standby has the running or streaming (V3.0.4) state
+    * a replica, quorum standby or sync-standby has the running or streaming (V3.0.4) state
 
     Since we dont check the lag or timeline, "in archive recovery" is not considered a valid state
     for this service. See cluster_has_leader and cluster_has_replica for specialized checks.

check_patroni/cluster.py

@@ -45,7 +45,12 @@ def debug_member(member: Any, health: str) -> None:
                 debug_member(member, "healthy")
                 continue
 
-            if role in ["standby_leader", "replica", "sync_standby"] and (
+            if role in [
+                "standby_leader",
+                "replica",
+                "sync_standby",
+                "quorum_standby",
+            ] and (
                 (self.has_detailed_states() and state == "streaming")
                 or (not self.has_detailed_states() and state == "running")
             ):

tests/__init__.py

@@ -55,7 +55,12 @@ def cluster_api_set_replica_running(in_json: Path, target_dir: Path) -> Path:
     with in_json.open() as f:
         js = json.load(f)
     for node in js["members"]:
-        if node["role"] in ["replica", "sync_standby", "standby_leader"]:
+        if node["role"] in [
+            "replica",
+            "sync_standby",
+            "standby_leader",
+            "quorum_standby",
+        ]:
             if node["state"] in ["streaming", "in archive recovery"]:
                 node["state"] = "running"
     assert target_dir.is_dir()

tests/json/cluster_node_count_ok_quorum.json

@@ -0,0 +1,33 @@
+{
+  "members": [
+    {
+      "name": "srv1",
+      "role": "leader",
+      "state": "running",
+      "api_url": "https://10.20.199.3:8008/patroni",
+      "host": "10.20.199.3",
+      "port": 5432,
+      "timeline": 51
+    },
+    {
+      "name": "srv2",
+      "role": "quorum_standby",
+      "state": "streaming",
+      "api_url": "https://10.20.199.4:8008/patroni",
+      "host": "10.20.199.4",
+      "port": 5432,
+      "timeline": 51,
+      "lag": 0
+    },
+    {
+      "name": "srv3",
+      "role": "quorum_standby",
+      "state": "streaming",
+      "api_url": "https://10.20.199.5:8008/patroni",
+      "host": "10.20.199.5",
+      "port": 5432,
+      "timeline": 51,
+      "lag": 0
+    }
+  ]
+}

tests/json/cluster_node_count_ok_sync.json

@@ -0,0 +1,33 @@
+{
+  "members": [
+    {
+      "name": "srv1",
+      "role": "leader",
+      "state": "running",
+      "api_url": "https://10.20.199.3:8008/patroni",
+      "host": "10.20.199.3",
+      "port": 5432,
+      "timeline": 51
+    },
+    {
+      "name": "srv2",
+      "role": "sync_standby",
+      "state": "streaming",
+      "api_url": "https://10.20.199.4:8008/patroni",
+      "host": "10.20.199.4",
+      "port": 5432,
+      "timeline": 51,
+      "lag": 0
+    },
+    {
+      "name": "srv3",
+      "role": "replica",
+      "state": "streaming",
+      "api_url": "https://10.20.199.5:8008/patroni",
+      "host": "10.20.199.5",
+      "port": 5432,
+      "timeline": 51,
+      "lag": 0
+    }
+  ]
+}

tests/test_cluster_node_count.py

@@ -40,6 +40,67 @@ def test_cluster_node_count_ok(
     assert result.exit_code == 0
 
 
+@pytest.fixture
+def cluster_node_count_ok_sync(
+    patroni_api: PatroniAPI, old_replica_state: bool, datadir: Path, tmp_path: Path
+) -> Iterator[None]:
+    cluster_path: Union[str, Path] = "cluster_node_count_ok_sync.json"
+    patroni_path = "cluster_has_replica_patroni_verion_3.1.0.json"
+    if old_replica_state:
+        cluster_path = cluster_api_set_replica_running(datadir / cluster_path, tmp_path)
+        patroni_path = "cluster_has_replica_patroni_verion_3.0.0.json"
+    with patroni_api.routes({"cluster": cluster_path, "patroni": patroni_path}):
+        yield None
+
+
+@pytest.mark.usefixtures("cluster_node_count_ok_sync")
+def test_cluster_node_count_ok_sync(
+    runner: CliRunner, patroni_api: PatroniAPI, old_replica_state: bool
+) -> None:
+    result = runner.invoke(main, ["-e", patroni_api.endpoint, "cluster_node_count"])
+    if old_replica_state:
+        assert (
+            result.output
+            == "CLUSTERNODECOUNT OK - members is 3 | healthy_members=3 members=3 role_leader=1 role_replica=1 role_sync_standby=1 state_running=3\n"
+        )
+    else:
+        assert (
+            result.output
+            == "CLUSTERNODECOUNT OK - members is 3 | healthy_members=3 members=3 role_leader=1 role_replica=1 role_sync_standby=1 state_running=1 state_streaming=2\n"
+        )
+    assert result.exit_code == 0
+
+
+@pytest.fixture
+def cluster_node_count_ok_quorum(
+    patroni_api: PatroniAPI, old_replica_state: bool, datadir: Path, tmp_path: Path
+) -> Iterator[None]:
+    cluster_path: Union[str, Path] = "cluster_node_count_ok_quorum.json"
+    patroni_path = "cluster_has_replica_patroni_verion_3.1.0.json"
+    if old_replica_state:
+        cluster_path = cluster_api_set_replica_running(datadir / cluster_path, tmp_path)
+        patroni_path = "cluster_has_replica_patroni_verion_3.0.0.json"
+    with patroni_api.routes({"cluster": cluster_path, "patroni": patroni_path}):
+        yield None
+
+
+@pytest.mark.usefixtures("cluster_node_count_ok_quorum")
+def test_cluster_node_count_ok_quorum(
+    runner: CliRunner, patroni_api: PatroniAPI, old_replica_state: bool
+) -> None:
+    result = runner.invoke(main, ["-e", patroni_api.endpoint, "cluster_node_count"])
+    if old_replica_state:
+        assert (
+            result.output
+            == "CLUSTERNODECOUNT OK - members is 3 | healthy_members=3 members=3 role_leader=1 role_quorum_standby=2 state_running=3\n"
+        )
+    else:
+        assert (
+            result.output
+            == "CLUSTERNODECOUNT OK - members is 3 | healthy_members=3 members=3 role_leader=1 role_quorum_standby=2 state_running=1 state_streaming=2\n"
+        )
+
+
 @pytest.mark.usefixtures("cluster_node_count_ok")
 def test_cluster_node_count_ok_with_thresholds(
     runner: CliRunner, patroni_api: PatroniAPI, old_replica_state: bool