Monitoring

monitoring/grafana/dashboards/system-overview.json

@@ -0,0 +1,37 @@
+{
+  "title": "System Overview",
+  "uid": "system-overview",
+  "version": 1,
+  "panels": [
+    {
+      "title": "CPU Usage",
+      "type": "gauge",
+      "gridPos": {"h": 8, "w": 6, "x": 0, "y": 0},
+      "targets": [{"expr": "node:cpu_usage:avg5m"}]
+    },
+    {
+      "title": "Memory Usage",
+      "type": "gauge",
+      "gridPos": {"h": 8, "w": 6, "x": 6, "y": 0},
+      "targets": [{"expr": "(node_memory_MemTotal_bytes - node_memory_MemAvailable_bytes) / node_memory_MemTotal_bytes * 100"}]
+    },
+    {
+      "title": "Disk Usage",
+      "type": "gauge",
+      "gridPos": {"h": 8, "w": 6, "x": 12, "y": 0},
+      "targets": [{"expr": "(node_filesystem_size_bytes{mountpoint=\"/\"} - node_filesystem_free_bytes{mountpoint=\"/\"}) / node_filesystem_size_bytes{mountpoint=\"/\"} * 100"}]
+    },
+    {
+      "title": "Container CPU Usage",
+      "type": "graph",
+      "gridPos": {"h": 8, "w": 12, "x": 0, "y": 8},
+      "targets": [{"expr": "sum by(name) (rate(container_cpu_usage_seconds_total{name!=\"\"}[5m])) * 100"}]
+    },
+    {
+      "title": "Container Memory Usage",
+      "type": "graph",
+      "gridPos": {"h": 8, "w": 12, "x": 12, "y": 8},
+      "targets": [{"expr": "sum by(name) (container_memory_usage_bytes{name!=\"\"})"}]
+    }
+  ]
+}

monitoring/grafana/provisioning/dashboards/dashboards.yml

@@ -0,0 +1,12 @@
+apiVersion: 1
+
+providers:
+  - name: 'Default'
+    orgId: 1
+    folder: ''
+    type: file
+    disableDeletion: false
+    updateIntervalSeconds: 10
+    allowUiUpdates: true
+    options:
+      path: /var/lib/grafana/dashboards

monitoring/grafana/provisioning/datasources/datasource.yml

@@ -0,0 +1,8 @@
+apiVersion: 1
+
+datasources:
+  - name: Prometheus
+    type: prometheus
+    access: proxy
+    url: http://prometheus:9090
+    isDefault: true