homelab/kubernetes/infrastructure/monitoring/kube-prometheus-stack.yaml

---
apiVersion: source.toolkit.fluxcd.io/v1
kind: HelmRepository
metadata:
  name: monitoring
  namespace: monitoring
spec:
  interval: 5m0s
  url: https://prometheus-community.github.io/helm-charts
---
apiVersion: helm.toolkit.fluxcd.io/v2
kind: HelmRelease
metadata:
  name: kube-prometheus-stack
  namespace: monitoring
spec:
  interval: 30m
  chart:
    spec:
      chart: kube-prometheus-stack
      version: "65.5.0"
      sourceRef:
        kind: HelmRepository
        name: monitoring
        namespace: monitoring
      interval: 12h
  values:
    # Prometheus Volume
    prometheus:
      prometheusSpec:
        scrapeInterval: 30s
        evaluationInterval: 30s
        ruleSelectorNilUsesHelmValues: false
        serviceMonitorSelectorNilUsesHelmValues: false
        podMonitorSelectorNilUsesHelmValues: false
        probeSelectorNilUsesHelmValues: false
        scrapeConfigSelectorNilUsesHelmValues: false
        enableAdminAPI: true
        walCompression: true
        enableFeatures:
          - auto-gomemlimit
          - memory-snapshot-on-shutdown
          - new-service-discovery-manager
        retention: 30d
        retentionSize: 40GB
        resources:
          requests:
            cpu: 100m
          limits:
            memory: 1500Mi
        storageSpec:
          volumeClaimTemplate:
            spec:
              storageClassName: nfs-csi
              accessModes: ["ReadWriteOnce"]
              resources:
                requests:
                  storage: 50Gi

    # ServiceMonitor configurations
    serviceMonitors:
      node-exporter:
        metricRelabelings:
          - action: replace
            regex: (.*)
            replacement: $1
            sourceLabels:
              - __meta_kubernetes_pod_node_name
            targetLabel: kubernetes_node
      kubelet:
        metricRelabelings:
          - action: replace
            sourceLabels:
              - node
            targetLabel: instance