Code import - branch main

ingestor/metrics.py

@@ -0,0 +1,158 @@
+"""
+Prometheus metrics configuration for the OPC Ingestor application.
+
+This module defines all the metrics used for monitoring and observability
+of the OPC Ingestor system. It includes metrics for:
+
+- Application health and performance
+- OPC server connections and subscriptions
+- Data processing and storage operations
+- Resource management and load balancing
+- Error tracking and notification systems
+
+All metrics follow Prometheus naming conventions and include appropriate
+labels for multi-dimensional analysis and alerting.
+"""
+
+from prometheus_client import Counter, Gauge, Histogram
+
+# Metric label definitions for consistent labeling across all metrics
+POD_ID_LABEL = ['pod_id']
+SERVER_LABELS = ['pod_id', 'server_name', 'server_url']
+KAFKA_LABELS = ['pod_id', 'topic']
+REDIS_LABELS = ['pod_id', 'operation']
+NOTIFICATION_LABELS = ['pod_id', 'level', 'block']
+
+MAIN_LABELS = ['pod_id']
+
+# --- Reliability Metrics ---
+TAG_WRITTEN_COUNT = Counter(
+    'ingestor_tag_written_count',
+    'Number of writing process to the collection',
+    [*MAIN_LABELS, 'tag_name', 'collection_name'],
+)
+
+# --- General Application Metrics ---
+APP_LOOP_COUNT = Counter(
+    'app_main_loop_total',
+    'Total number of times the application main loop has run',
+    POD_ID_LABEL,
+)
+APP_LOOP_DURATION = Histogram(
+    'app_main_loop_duration_seconds',
+    'Duration of the application main loop in seconds',
+    POD_ID_LABEL,
+)
+APP_ERRORS_TOTAL = Counter(
+    'app_errors_total',
+    'Total number of unhandled errors in the main loop',
+    POD_ID_LABEL,
+)
+APP_UP = Gauge(
+    'app_up',
+    'Indicates if the application is running (1) or shutting down (0)',
+    POD_ID_LABEL,
+)
+
+# --- Ingestor Manager Metrics ---
+ACTIVE_INGESTORS = Gauge(
+    'ingestor_active_total',
+    'Number of active ingestors reported by Redis',
+    POD_ID_LABEL,
+)
+SLOTS_TOTAL = Gauge(
+    'ingestor_slots_total',
+    'Total number of slots configured in Redis',
+    POD_ID_LABEL,
+)
+LEASES_TOTAL = Gauge(
+    'ingestor_leases_total',
+    'Total number of leases (allocated slots) in Redis',
+    POD_ID_LABEL,
+)
+SLOTS_MANAGED = Gauge(
+    'ingestor_slots_managed_current',
+    'Number of slots currently managed by this ingestor instance',
+    POD_ID_LABEL,
+)
+SLOTS_ACQUIRED = Counter(
+    'ingestor_slots_acquired_total',
+    'Total number of slots acquired by this instance',
+    POD_ID_LABEL,
+)
+SLOTS_RELEASED = Counter(
+    'ingestor_slots_released_total',
+    'Total number of slots released by this instance',
+    POD_ID_LABEL,
+)
+
+# --- OPC Manager Metrics ---
+OPC_MANAGERS_ACTIVE = Gauge(
+    'ingestor_opc_managers_active',
+    'Number of active OPC Managers in this instance',
+    POD_ID_LABEL,
+)
+OPC_SUBSCRIPTION_ERRORS = Counter(
+    'ingestor_opc_subscription_errors_total',
+    'Errors when trying to subscribe to OPC tags',
+    ['pod_id', 'server', 'slot'],
+)
+
+OPC_CONNECTIONS_TOTAL = Counter(
+    'opc_connections_initiated_total',
+    'Total connection attempts to OPC servers',
+    ['pod_id', 'server_name'],
+)
+OPC_CONNECTIONS_FAILED = Counter(
+    'opc_connections_failed_total',
+    'Total failed connection attempts to OPC servers',
+    ['pod_id', 'server_name'],
+)
+OPC_CONNECTION_STATUS = Gauge(
+    'opc_connection_status',
+    'Connection status with the OPC server (1=connected, 0=disconnected)',
+    SERVER_LABELS,
+)
+OPC_SUBSCRIPTIONS_CREATED = Counter(
+    'opc_subscriptions_created_total',
+    'Total OPC subscriptions created',
+    ['pod_id', 'server_name', 'slot_name'],
+)
+OPC_TAGS_SUBSCRIBED = Gauge(
+    'opc_tags_subscribed_current',
+    'Current number of OPC tags subscribed on a server',
+    ['pod_id', 'server_name'],
+)
+OPC_CYCLES_WITHOUT_DATA = Gauge(
+    'opc_cycles_without_data',
+    'Current number of cycles without receiving data from a server',
+    ['pod_id', 'server_name'],
+)
+OPC_RECONNECTIONS_TOTAL = Counter(
+    'opc_reconnections_tried_total',
+    'Reconnection attempts to an OPC server after a loss',
+    ['pod_id', 'server_name'],
+)
+
+# --- Data Manager (Kafka) Metrics ---
+KAFKA_MESSAGES_SENT = Counter(
+    'kafka_messages_sent_total', 'Total messages sent to Kafka', KAFKA_LABELS
+)
+KAFKA_MESSAGES_ERRORS = Counter(
+    'kafka_messages_errors_total',
+    'Total errors sending messages to Kafka',
+    KAFKA_LABELS,
+)
+KAFKA_CONNECTION_STATUS = Gauge(
+    'kafka_connection_status',
+    'Connection status with Kafka (1=connected, 0=disconnected)',
+    POD_ID_LABEL,
+)
+
+
+# --- Notification Metrics ---
+NOTIFICATIONS_SENT = Counter(
+    'notifications_sent_total',
+    'Total number of notifications sent',
+    NOTIFICATION_LABELS,
+)