SIENTIAPDE-1083: add prometheus metrics to opc_manager.

ingestor/managers/opc_manager.py

@@ -7,11 +7,12 @@ from asyncua.sync import Client
 from sientia_do.notifications.models import NotificationLevel
 from sientia_do.notifications.handlers import NotificationHandler
 from ingestor.managers.data_manager import DataManager
+import ingestor.metrics as metrics
 
 
 class OpcManager():
     def __init__(self, name: str, url: str, data_manager: DataManager,
-                 logger: Logger, server_uri: str, notification_handler: NotificationHandler,
+                 logger: Logger, server_uri: str, notification_handler: NotificationHandler, pod_id: str,
                  cert_path: str = None, private_key_path: str = None, server_cert_path: str = None):
         self.url = url
         self.name = name
@@ -26,8 +27,10 @@ class OpcManager():
         self.nodes = {}
         self.subscriptions = {}
         self.data_manager = data_manager
-
         self.notification_handler = notification_handler
+        self.pod_id = pod_id
+        metrics.OPC_CONNECTION_STATUS.labels(pod_id=self.pod_id, server_name=self.name, server_url=self.url).set(0)
+        metrics.OPC_TAGS_SUBSCRIBED.labels(pod_id=self.pod_id, server_name=self.name).set(0)
 
     def __str__(self):
         return f"OpcManager(name={self.name}, url={self.url}, server_uri={self.server_uri})\n" \
@@ -82,11 +85,20 @@ class OpcManager():
             Exception: If the connection to the OPC server fails.
         """
 
-        self.client = Client(self.url)
-        if self.cert_path:
-            self.set_security()
-        self.logger.info('Starting connection...')
-        self.client.connect()
+        metrics.OPC_CONNECTIONS_TOTAL.labels(pod_id=self.pod_id, server_name=self.name).inc()
+        try:
+            self.client = Client(self.url)
+            if self.cert_path:
+                self.set_security()
+            self.logger.info(f'Starting connection to {self.name}...')
+            self.client.connect()
+            metrics.OPC_CONNECTION_STATUS.labels(pod_id=self.pod_id, server_name=self.name, server_url=self.url).set(1)
+            self.logger.info(f'Connection to {self.name} successful.')
+        except Exception as e:
+            metrics.OPC_CONNECTION_STATUS.labels(pod_id=self.pod_id, server_name=self.name, server_url=self.url).set(0)
+            metrics.OPC_CONNECTIONS_FAILED.labels(pod_id=self.pod_id, server_name=self.name).inc()
+            self.logger.error(f"Failed to connect to {self.name}: {e}")
+            raise
 
     def create_subscription(self, name: str, period: int = 500):
         """
@@ -105,11 +117,14 @@ class OpcManager():
 
         if not self.client:
             raise ValueError("Client not connected. Call connect first.")
-
-        p = period if period != None else 500
-        self.subscriptions[name] = self.client.create_subscription(
-            p, self)
-        self.logger.info('Subscription created.')
+        try:
+            p = period if period is not None else 500
+            self.subscriptions[name] = self.client.create_subscription(p, self)
+            self.logger.info(f'Subscription {name} created on {self.name}.')
+            metrics.OPC_SUBSCRIPTIONS_CREATED.labels(pod_id=self.pod_id, server_name=self.name, slot_name=name).inc()
+        except Exception as e:
+            self.logger.error(f"Failed to create subscription {name} on {self.name}: {e}")
+            raise
 
     def subscribe(self, subscription: str, nodes: dict, collect_period: int):
         """
@@ -129,14 +144,13 @@ class OpcManager():
         """
 
         if not self.subscriptions.get(subscription):
-            raise ValueError(
-                "Subscription not created. Call create_subscription first.")
+            raise ValueError("Subscription not created. Call create_subscription first.")
 
-        self.logger.info(f"Subscribing to {subscription}...")
+        self.logger.info(f"Subscribing to {subscription} on {self.name}...")
         self.logger.info(f"Subscribing to nodes: {nodes}")
-        self.addr_nodes = [self.client.get_node(
-            n) for n in nodes if n not in self.nodes]
+        self.addr_nodes = [self.client.get_node(n) for n in nodes if n not in self.nodes]
         self.nodes.update(nodes)
+        metrics.OPC_TAGS_SUBSCRIBED.labels(pod_id=self.pod_id, server_name=self.name).set(len(self.nodes))
         self.collect_period = collect_period
 
         for node, config in self.nodes.items():
@@ -202,6 +216,8 @@ class OpcManager():
         finally:
             del self.client
             self.client = None
+            metrics.OPC_CONNECTION_STATUS.labels(pod_id=self.pod_id, server_name=self.name, server_url=self.url).set(0)
+            metrics.OPC_TAGS_SUBSCRIBED.labels(pod_id=self.pod_id, server_name=self.name).set(0)
             self.logger.warning("Disconnected from OPC UA server.")
 
     def datachange_notification(self, node, _val, data):
@@ -236,6 +252,7 @@ class OpcManager():
 
         self.nodes[tag]['cycle_rule']['cycle_count'] = 0
         self.non_receive_count = 0
+        metrics.OPC_CYCLES_WITHOUT_DATA.labels(pod_id=self.pod_id, server_name=self.name).set(0)
 
         data = {
             'tag': tag,
@@ -278,6 +295,7 @@ class OpcManager():
         """
 
         self.non_receive_count += 1
+        metrics.OPC_CYCLES_WITHOUT_DATA.labels(pod_id=self.pod_id, server_name=self.name).set(self.non_receive_count)
         if self.non_receive_count >= 5:
             self.notification_handler.build_and_send_notification(
                 notification_id=f'OPC_LISTENNING_STOPPED__{self.name}',
@@ -287,6 +305,7 @@ class OpcManager():
                 level=NotificationLevel.ERROR
             )
         if self.non_receive_count >= 15:
+            metrics.OPC_RECONNECTIONS_TOTAL.labels(pod_id=self.pod_id, server_name=self.name).inc()
             self.notification_handler.build_and_send_notification(
                 notification_id=f'OPC_CONNECTION_RETRY__{self.name}',
                 message=f'Retrying to connect to server {self.name}',