add VictoriaMetrics cluster metrics collection

2026-10-16 00:56:05 +00:00
parent 6f43b5e343
commit c7fce94b04
3 changed files with 128 additions and 0 deletions
@@ -0,0 +1,13 @@
+# Umbrella chart for the official VictoriaMetrics Kubernetes monitoring stack.
+# Argo CD renders this dependency from Git just like the existing Longhorn and
+# MetalLB wrapper charts.
+apiVersion: v2
+name: victoria-metrics-app
+description: Forwards Kubernetes and node metrics to external VictoriaMetrics
+version: 0.1.0
+dependencies:
+  - name: victoria-metrics-k8s-stack
+    # Pin the exact chart version so monitoring upgrades are explicit and
+    # reviewable rather than changing during an unrelated Argo CD sync.
+    version: 0.96.0
+    repository: oci://ghcr.io/victoriametrics/helm-charts
@@ -0,0 +1,74 @@
+# Values for the upstream victoria-metrics-k8s-stack dependency. This cluster
+# collects metrics only; durable storage and visualization run on the NetBird-
+# connected VPS at 100.71.24.9.
+victoria-metrics-k8s-stack:
+  # Identify this source if more clusters write to the same database later.
+  vmagent:
+    enabled: true
+    spec:
+      scrapeInterval: 30s
+      externalLabels:
+        cluster: gitops-starter
+      resources:
+        requests:
+          cpu: 100m
+          memory: 128Mi
+        limits:
+          memory: 512Mi
+
+  external:
+    vm:
+      # Queries are served from the VictoriaMetrics base URL. Remote write uses
+      # its Prometheus-compatible ingestion endpoint. NetBird encrypts the path
+      # between the Talos nodes and VPS, so no public endpoint is involved.
+      read:
+        url: http://100.71.24.9:8428
+      write:
+        url: http://100.71.24.9:8428/api/v1/write
+
+  # Storage and UI already live on prd-vps-hel-01; do not duplicate them here.
+  vmsingle:
+    enabled: false
+  vmcluster:
+    enabled: false
+  vmdistributed:
+    enabled: false
+  grafana:
+    enabled: false
+
+  # Alert delivery is a separate follow-up once notification destinations are
+  # chosen. Disabling it also avoids deploying rules with nowhere to notify.
+  vmalert:
+    enabled: false
+  alertmanager:
+    enabled: false
+  defaultRules:
+    enabled: false
+  defaultDashboards:
+    enabled: false
+
+  # One node-exporter Pod runs on every node, including tainted control planes.
+  # Talos exposes the host root filesystem read-only; mount propagation is not
+  # needed and can be rejected by immutable hosts, so keep it disabled.
+  prometheus-node-exporter:
+    enabled: true
+    hostRootFsMount:
+      enabled: true
+      mountPropagation: None
+    resources:
+      requests:
+        cpu: 20m
+        memory: 32Mi
+      limits:
+        memory: 128Mi
+
+  # kube-state-metrics reports desired/current Kubernetes object state (for
+  # example unavailable Deployment replicas), complementing host metrics.
+  kube-state-metrics:
+    enabled: true
+    resources:
+      requests:
+        cpu: 20m
+        memory: 64Mi
+      limits:
+        memory: 256Mi