minio, velero y tal

velero/monitoring/grafana-dashboard-velero.json

@@ -0,0 +1,92 @@
+{
+  "annotations": {
+    "list": []
+  },
+  "editable": true,
+  "gnetId": null,
+  "graphTooltip": 0,
+  "panels": [
+    {
+      "type": "stat",
+      "title": "Backups - Total",
+      "targets": [
+        {
+          "expr": "sum(velero_backup_total)",
+          "legendFormat": "total"
+        }
+      ],
+      "id": 1,
+      "datasource": {
+        "type": "prometheus",
+        "uid": "prometheus"
+      },
+      "options": {
+        "reduceOptions": {
+          "calcs": [
+            "lastNotNull"
+          ]
+        }
+      }
+    },
+    {
+      "type": "timeSeries",
+      "title": "Backups por estado",
+      "targets": [
+        {
+          "expr": "sum by (phase) (increase(velero_backup_attempt_total[1h]))",
+          "legendFormat": "{{phase}}"
+        }
+      ],
+      "id": 2,
+      "datasource": {
+        "type": "prometheus",
+        "uid": "prometheus"
+      }
+    },
+    {
+      "type": "timeSeries",
+      "title": "Duraci\u00f3n de backups (p95)",
+      "targets": [
+        {
+          "expr": "histogram_quantile(0.95, sum(rate(velero_backup_duration_seconds_bucket[5m])) by (le))",
+          "legendFormat": "p95"
+        }
+      ],
+      "id": 3,
+      "datasource": {
+        "type": "prometheus",
+        "uid": "prometheus"
+      }
+    },
+    {
+      "type": "timeSeries",
+      "title": "Errores del node-agent",
+      "targets": [
+        {
+          "expr": "sum(rate(velero_node_agent_errors_total[5m]))",
+          "legendFormat": "errores"
+        }
+      ],
+      "id": 4,
+      "datasource": {
+        "type": "prometheus",
+        "uid": "prometheus"
+      }
+    }
+  ],
+  "schemaVersion": 37,
+  "style": "dark",
+  "tags": [
+    "velero",
+    "backup"
+  ],
+  "templating": {
+    "list": []
+  },
+  "time": {
+    "from": "now-24h",
+    "to": "now"
+  },
+  "title": "Velero (MinIO S3)",
+  "version": 1
+}

velero/monitoring/servicemonitor.yaml

@@ -0,0 +1,16 @@
+apiVersion: monitoring.coreos.com/v1
+kind: ServiceMonitor
+metadata:
+  name: velero
+  namespace: velero
+  labels:
+    release: prometheus  # ajusta al selector de tu Prometheus
+spec:
+  selector:
+    matchLabels:
+      app.kubernetes.io/name: velero
+  namespaceSelector:
+    matchNames: ["velero"]
+  endpoints:
+    - port: metrics
+      interval: 30s