Create opnsense_server_ha_state metric

in order to replace
 and  that will be removed
in version 1.0.0.

Also use Enum to store possible OPNsense HA states to avoid typo

README.md

@@ -30,8 +30,13 @@ This exporter gives following metrics, all metrics received following labels:
 
 ### Enums
 
-- `opnsense_main_ha_state`: OPNSense HA state of the MAIN server
+- `opnsense_main_ha_state`: (deprecated) OPNSense HA state of the MAIN server
-- `opnsense_backup_ha_state`: OPNSense HA state of the BACKUP server
+- `opnsense_backup_ha_state`: (deprecated) OPNSense HA state of the BACKUP server
+- `opnsense_server_ha_state`: OPNSense HA state, on of following value:
+  - **active**: that OPNSense server is receiving traffic
+  - **hot_standby**: the OPNSense server is ready to be promote as active server
+  - **maintenancemode**: the OPNSense server was turned into maintenance mode
+  - **unavailable**: the OPNSense server wasn't accessible or return unexpected value
 
 ### Gauges
 
@@ -93,10 +98,8 @@ You can setup env through `.env` file or environment variables with defined as d
 
 ## Roadmap
 
-- allow to configure interfaces to get traffic rates for lan,wan and/or other names
-- refactor server in a class to avoid transmitted params over methods
 - allow to change the listening port (today it force using `8000`)
-- allow to configure timeouts using environemnt variables
+- allow to configure timeouts using environment variables
 - improves logging to get a debug mode to understand errors based on unexpected payloads
 
 ## Changelog
@@ -108,6 +111,8 @@ You can setup env through `.env` file or environment variables with defined as d
 - replace `active_server_bytes_received` and
   `active_server_bytes_transmitted` by
   `opnsense_active_server_traffic_rate`
+- add `opnsense_server_ha_state` and mark `opnsense_main_ha_state`
+  and `opnsense_backup_ha_state` as deprecated.
 
 ### Version 0.4.0 (2023-09-02)
 

opnsense_exporter/opnsense_api.py

@@ -7,6 +7,13 @@ from requests import RequestException
 logger = logging.getLogger(__name__)
 
 
+class OPNSenseHAState(Enum):
+    ACTIVE = "active"
+    HOT_STANDBY = "hot_standby"
+    UNAVAILABLE = "unavailable"
+    MAINTENANCE_MODE = "maintenancemode"
+
+
 class OPNSenseTrafficMetric(Enum):
     IN = "rate_bits_in"
     OUT = "rate_bits_out"
@@ -77,26 +84,26 @@ class OPNSenseAPI:
         response.raise_for_status()
         return response.json()
 
-    def get_interface_vip_status(self):
+    def get_interface_vip_status(self) -> OPNSenseHAState:
         try:
             data = self.get("/api/diagnostics/interface/get_vip_status/")
         except RequestException as ex:
             logger.error(
                 "Get VIP STATUS on %s failed with the following error %r", self.host, ex
             )
-            return "unavailable"
+            return OPNSenseHAState.UNAVAILABLE
         if data["carp"]["maintenancemode"]:
-            return "maintenancemode"
+            return OPNSenseHAState.MAINTENANCE_MODE
         is_active = all([row["status"] == "MASTER" for row in data["rows"]])
         if is_active:
-            return "active"
+            return OPNSenseHAState.ACTIVE
         is_backup = all([row["status"] == "BACKUP" for row in data["rows"]])
         if is_backup:
-            return "hot_standby"
+            return OPNSenseHAState.HOT_STANDBY
         logger.warning(
             "this host %s is no active nor backup received payload %s", self.host, data
         )
-        return "unavailable"
+        return OPNSenseHAState.UNAVAILABLE
 
     def get_traffic(self, interfaces):
         try:

opnsense_exporter/server.py

@@ -1,4 +1,5 @@
 import argparse
+import logging
 import os
 import socket
 import time
@@ -6,12 +7,21 @@ import time
 from dotenv import load_dotenv
 from prometheus_client import Enum, Gauge, start_http_server
 
-from opnsense_exporter.opnsense_api import OPNSenseAPI, OPNSenseRole
+from opnsense_exporter.opnsense_api import OPNSenseAPI, OPNSenseHAState, OPNSenseRole
 
+logger = logging.getLogger(__name__)
 load_dotenv()
 
-HA_STATES = ["active", "hot_standby", "unavailable", "maintenancemode"]
+HA_STATES = [enum.value for enum in list(OPNSenseHAState)]
-main_ha_state = Enum(
+
+
+class DeprecatedPromEnum(Enum, DeprecationWarning):
+    def state(self, *args, **kwargs):
+        super().state(*args, **kwargs)
+        logger.warning("This metric %s will be removed in v1.0.0", self._name)
+
+
+main_ha_state = DeprecatedPromEnum(
     "opnsense_main_ha_state",
     "OPNSense HA state of the MAIN server",
     [
@@ -21,7 +31,7 @@ main_ha_state = Enum(
     ],
     states=HA_STATES,
 )
-backup_ha_state = Enum(
+backup_ha_state = DeprecatedPromEnum(
     "opnsense_backup_ha_state",
     "OPNSense HA state of the BACKUP server",
     [
@@ -31,6 +41,18 @@ backup_ha_state = Enum(
     ],
     states=HA_STATES,
 )
+
+opnsense_server_ha_state = Enum(
+    "opnsense_server_ha_state",
+    "OPNSense server HA state",
+    [
+        "instance",
+        "host",
+        "role",
+    ],
+    states=HA_STATES,
+)
+
 opnsense_active_server_traffic_rate = Gauge(
     "opnsense_active_server_traffic_rate",
     "Active OPNSense server bytes in/out per interface",
@@ -64,15 +86,15 @@ class OPNSensePrometheusExporter:
         main_state = self.main.get_interface_vip_status()
         backup_sate = self.backup.get_interface_vip_status()
         main_ha_state.labels(instance=self.exporter_instance, **self.main.labels).state(
-            main_state
+            main_state.value
         )
         backup_ha_state.labels(
             instance=self.exporter_instance, **self.backup.labels
-        ).state(backup_sate)
+        ).state(backup_sate.value)
         active_opnsense = None
-        if main_state == "active":
+        if main_state == OPNSenseHAState.ACTIVE:
             active_opnsense = self.main
-        if backup_sate == "active":
+        if backup_sate == OPNSenseHAState.ACTIVE:
             active_opnsense = self.backup
         if active_opnsense:
             for traffic in active_opnsense.get_traffic(self.interfaces):

tests/test_opnsense_api.py

@@ -26,9 +26,9 @@ def test_get_interface_vip_status_active():
     )
 
     assert (
-        OPNSenseAPI(
+        OPNSenseAPI(OPNSenseRole.MAIN, MAIN_HOST, LOGIN, PASSWORD)
-            OPNSenseRole.MAIN, MAIN_HOST, LOGIN, PASSWORD
+        .get_interface_vip_status()
-        ).get_interface_vip_status()
+        .value
         == "active"
     )
 
@@ -42,9 +42,9 @@ def test_get_interface_vip_status_backup():
     )
 
     assert (
-        OPNSenseAPI(
+        OPNSenseAPI(OPNSenseRole.MAIN, MAIN_HOST, LOGIN, PASSWORD)
-            OPNSenseRole.MAIN, MAIN_HOST, LOGIN, PASSWORD
+        .get_interface_vip_status()
-        ).get_interface_vip_status()
+        .value
         == "hot_standby"
     )
 
@@ -58,9 +58,9 @@ def test_get_interface_vip_status_mainteance_mode():
     )
 
     assert (
-        OPNSenseAPI(
+        OPNSenseAPI(OPNSenseRole.MAIN, MAIN_HOST, LOGIN, PASSWORD)
-            OPNSenseRole.MAIN, MAIN_HOST, LOGIN, PASSWORD
+        .get_interface_vip_status()
-        ).get_interface_vip_status()
+        .value
         == "maintenancemode"
     )
 
@@ -73,9 +73,9 @@ def test_get_interface_vip_status_unavailable_weird_case():
         body=generate_get_vip_status_paylaod("MASTER", "BACKUP", False),
     )
     assert (
-        OPNSenseAPI(
+        OPNSenseAPI(OPNSenseRole.MAIN, MAIN_HOST, LOGIN, PASSWORD)
-            OPNSenseRole.MAIN, MAIN_HOST, LOGIN, PASSWORD
+        .get_interface_vip_status()
-        ).get_interface_vip_status()
+        .value
         == "unavailable"
     )
 
@@ -89,9 +89,9 @@ def test_get_interface_vip_status_unavailable_rest_api_error():
         status=404,
     )
     assert (
-        OPNSenseAPI(
+        OPNSenseAPI(OPNSenseRole.MAIN, MAIN_HOST, LOGIN, PASSWORD)
-            OPNSenseRole.MAIN, MAIN_HOST, LOGIN, PASSWORD
+        .get_interface_vip_status()
-        ).get_interface_vip_status()
+        .value
         == "unavailable"
     )