helmrelease.yaml

---
apiVersion: helm.toolkit.fluxcd.io/v2
kind: HelmRelease
metadata:
  name: thanos
spec:
  interval: 30m
  timeout: 15m
  chart:
    spec:
      chart: thanos
      version: 1.17.2
      sourceRef:
        kind: HelmRepository
        name: stevehipwell-charts
        namespace: flux-system
  install:
    remediation:
      retries: 3
  upgrade:
    cleanupOnFail: true
    remediation:
      strategy: rollback
      retries: 3
  values:
    objstoreConfig:
      value:
        type: s3
        config:
          insecure: true
    additionalEndpoints:
      - dnssrv+_grpc._tcp.kube-prometheus-stack-thanos-discovery.monitoring.svc.cluster.local
    additionalReplicaLabels:
      - __replica__
    serviceMonitor:
      enabled: true
    compact:
      enabled: true
      extraArgs:
        - --compact.concurrency=4
        - --delete-delay=30m
        - --retention.resolution-raw=14d
        - --retention.resolution-5m=30d
        - --retention.resolution-1h=60d
      persistence: &persistence
        enabled: true
        storageClass: ${CLUSTER_STORAGE_HOSTPATH}
        size: 15Gi
    query:
      replicas: 3
      extraArgs:
        - --alert.query-url=https://thanos.${PUBLIC_DOMAIN}
    queryFrontend:
      enabled: true
      replicas: 3
      extraArgs:
        - --query-range.response-cache-config=$(THANOS_CACHE_CONFIG)
      extraEnv: &extraEnv
        - name: THANOS_CACHE_CONFIG
          valueFrom:
            configMapKeyRef:
              name: &configMap thanos-cache-configmap
              key: cache.yaml
      ingress:
        enabled: true
        ingressClassName: internal
        annotations:
          hajimari.io/appName: Thanos
          hajimari.io/icon: material-symbols:health-metrics
        hosts:
          - &host thanos.${PUBLIC_DOMAIN}
        tls:
          - hosts:
              - *host
      podAnnotations: &podAnnotations
        configmap.reloader.stakater.com/reload: *configMap
    rule:
      enabled: true
      replicas: 3
      extraArgs:
        - --web.prefix-header=X-Forwarded-Prefix
      alertmanagersConfig:
        value: |-
          alertmanagers:
            - api_version: v2
              static_configs:
                - dnssrv+_http-web._tcp.alertmanager-operated.monitoring.svc.cluster.local
      rules:
        value: |-
          groups:
            - name: PrometheusWatcher
              rules:
                - alert: PrometheusDown
                  annotations:
                    summary: A Prometheus has disappeared from Prometheus target discovery
                  expr: absent(up{job="kube-prometheus-stack-prometheus"})
                  for: 5m
                  labels:
                    severity: critical
      persistence: *persistence
    storeGateway:
      replicas: 3
      extraArgs:
        - --index-cache.config=$(THANOS_CACHE_CONFIG)
      extraEnv: *extraEnv
      persistence: *persistence
      podAnnotations: *podAnnotations
  valuesFrom:
    - kind: ConfigMap
      targetPath: objstoreConfig.value.config.bucket
      name: thanos-ceph-bucket
      valuesKey: BUCKET_NAME
    - kind: ConfigMap
      targetPath: objstoreConfig.value.config.endpoint
      name: thanos-ceph-bucket
      valuesKey: BUCKET_HOST
    - kind: ConfigMap
      targetPath: objstoreConfig.value.config.region
      name: thanos-ceph-bucket
      valuesKey: BUCKET_REGION
    - kind: Secret
      targetPath: objstoreConfig.value.config.access_key
      name: thanos-ceph-bucket
      valuesKey: AWS_ACCESS_KEY_ID
    - kind: Secret
      targetPath: objstoreConfig.value.config.secret_key
      name: thanos-ceph-bucket
      valuesKey: AWS_SECRET_ACCESS_KEY