Initial commit

monitoring/alert.rules.yml

@@ -0,0 +1,11 @@
+groups:
+  - name: general
+    rules:
+      - alert: InstanceDown
+        expr: up == 0
+        for: 1m
+        labels:
+          severity: critical
+        annotations:
+          summary: "Endpoint {{ $labels.instance }} недоступен"
+          description: "Таргет job={{ $labels.job }} на хосте {{ $labels.instance }} не отвечает более 1 минуты."

monitoring/alertmanager.yml

@@ -0,0 +1,15 @@
+global:
+  resolve_timeout: 5m
+
+route:
+  receiver: 'default'
+  group_by: ['alertname', 'job']
+  group_wait: 10s
+  group_interval: 5m
+  repeat_interval: 1h
+
+receivers:
+  - name: 'default'
+    webhook_configs:
+      - url: 'http://host.docker.internal:5001/alerts'
+        send_resolved: true

monitoring/prometheus.yml

@@ -0,0 +1,28 @@
+global:
+  scrape_interval: 15s
+  evaluation_interval: 15s
+
+scrape_configs:
+  - job_name: 'nginx'
+    static_configs:
+      - targets: ['nginx_exporter:9113']
+
+  - job_name: 'php-fpm'
+    static_configs:
+      - targets: ['php_fpm_exporter:9253']
+
+  - job_name: 'postgres'
+    static_configs:
+      - targets: ['postgres_exporter:9187']
+
+  - job_name: 'memcached'
+    static_configs:
+      - targets: ['memcached_exporter:9150']
+
+alerting:
+  alertmanagers:
+    - static_configs:
+        - targets: ['alertmanager:9093']
+
+rule_files:
+  - /etc/prometheus/alert.rules.yml