refactor

monitoring/alerts.yml

@@ -0,0 +1,67 @@
+# Правила алертов для мониторинга Lottery Bot
+groups:
+  - name: lottery_bot_alerts
+    rules:
+      # Алерт при падении сервиса
+      - alert: LotteryBotDown
+        expr: up{job="lottery-bot"} == 0
+        for: 1m
+        labels:
+          severity: critical
+        annotations:
+          summary: "Lottery Bot is down"
+          description: "Lottery Bot has been down for more than 1 minute."
+
+      # Алерт при высокой нагрузке на память
+      - alert: HighMemoryUsage
+        expr: (process_resident_memory_bytes / process_virtual_memory_max_bytes) > 0.9
+        for: 5m
+        labels:
+          severity: warning
+        annotations:
+          summary: "High memory usage detected"
+          description: "Memory usage is above 90% for more than 5 minutes."
+
+  - name: database_alerts
+    rules:
+      # Алерт при недоступности PostgreSQL
+      - alert: PostgreSQLDown
+        expr: up{job="postgres"} == 0
+        for: 2m
+        labels:
+          severity: critical
+        annotations:
+          summary: "PostgreSQL is down"
+          description: "PostgreSQL database has been down for more than 2 minutes."
+
+      # Алерт при недоступности Redis
+      - alert: RedisDown
+        expr: up{job="redis"} == 0
+        for: 2m
+        labels:
+          severity: warning
+        annotations:
+          summary: "Redis is down"
+          description: "Redis cache has been down for more than 2 minutes."
+
+  - name: performance_alerts
+    rules:
+      # Алерт при высокой загрузке CPU
+      - alert: HighCPUUsage
+        expr: rate(process_cpu_seconds_total[5m]) * 100 > 80
+        for: 10m
+        labels:
+          severity: warning
+        annotations:
+          summary: "High CPU usage detected"
+          description: "CPU usage is above 80% for more than 10 minutes."
+
+      # Алерт при большом количестве ошибок
+      - alert: HighErrorRate
+        expr: rate(lottery_bot_errors_total[5m]) > 0.1
+        for: 3m
+        labels:
+          severity: warning
+        annotations:
+          summary: "High error rate detected"
+          description: "Error rate is above 0.1 errors per second for more than 3 minutes."

monitoring/prometheus.yml

@@ -0,0 +1,48 @@
+# Prometheus configuration для мониторинга Lottery Bot
+global:
+  scrape_interval: 15s
+  evaluation_interval: 15s
+
+# Правила алертов
+rule_files:
+  - "alerts.yml"
+
+# Настройки Alertmanager
+alerting:
+  alertmanagers:
+    - static_configs:
+        - targets:
+          # - alertmanager:9093
+
+# Targets для мониторинга
+scrape_configs:
+  # Prometheus self-monitoring
+  - job_name: 'prometheus'
+    static_configs:
+      - targets: ['localhost:9090']
+    scrape_interval: 5s
+
+  # Мониторинг Lottery Bot (если добавите метрики)
+  - job_name: 'lottery-bot'
+    static_configs:
+      - targets: ['lottery-bot:8000']
+    scrape_interval: 10s
+    metrics_path: /metrics
+    
+  # Мониторинг PostgreSQL
+  - job_name: 'postgres'
+    static_configs:
+      - targets: ['postgres:5432']
+    scrape_interval: 30s
+
+  # Мониторинг Redis
+  - job_name: 'redis'
+    static_configs:
+      - targets: ['redis:6379']
+    scrape_interval: 30s
+
+  # Node exporter (если добавите)
+  - job_name: 'node-exporter'
+    static_configs:
+      - targets: ['node-exporter:9100']
+    scrape_interval: 15s