homelab/k8s/argocd/apps/10-storage-observability.yaml

# Wave 1 — MinIO (operator + tenant), Longhorn policy, Prometheus stack.
# Helm charts pull from public repos; values come from the git repo via a
# second "ref: values" source (ArgoCD multi-source pattern).
apiVersion: argoproj.io/v1alpha1
kind: Application
metadata:
  name: minio-operator
  namespace: argocd
  annotations:
    argocd.argoproj.io/sync-wave: "1"
spec:
  project: homelab
  sources:
    - repoURL: https://operator.min.io/
      chart: operator
      targetRevision: "5.0.18"
      helm:
        valueFiles:
          - $values/k8s/infra/minio/minio-operator-values.yaml
    - repoURL: https://forgejo.riotpiao.com/rock/homelab.git
      targetRevision: main
      ref: values
  destination:
    server: https://kubernetes.default.svc
    namespace: storage
  syncPolicy:
    automated:
      prune: true
      selfHeal: true
    syncOptions:
      - CreateNamespace=true
---
# Tenant + buckets + replication are raw CRs (MinIO Tenant CRD from operator).
apiVersion: argoproj.io/v1alpha1
kind: Application
metadata:
  name: minio-tenant
  namespace: argocd
  annotations:
    argocd.argoproj.io/sync-wave: "1"
spec:
  project: homelab
  source:
    repoURL: https://forgejo.riotpiao.com/rock/homelab.git
    targetRevision: main
    path: k8s/infra/minio
  destination:
    server: https://kubernetes.default.svc
    namespace: storage
  syncPolicy:
    automated:
      prune: true
      selfHeal: true
    syncOptions:
      - CreateNamespace=true
---
# Longhorn itself is substrate (bootstrap-installed); this app manages only its
# ServiceMonitor / policy manifests.
apiVersion: argoproj.io/v1alpha1
kind: Application
metadata:
  name: longhorn-config
  namespace: argocd
  annotations:
    argocd.argoproj.io/sync-wave: "1"
spec:
  project: homelab
  source:
    repoURL: https://forgejo.riotpiao.com/rock/homelab.git
    targetRevision: main
    path: k8s/infra/longhorn
  destination:
    server: https://kubernetes.default.svc
    namespace: longhorn-system
  # Longhorn writes disk state back into its own Node CRs — the disk key it
  # generates, storageReserved, diskType, evictionRequested. Git declares only
  # allowScheduling; without this the controller's writes read as drift forever.
  ignoreDifferences:
    - group: longhorn.io
      kind: Node
      jsonPointers:
        - /spec/disks
  syncPolicy:
    automated:
      prune: true
      selfHeal: true
---
apiVersion: argoproj.io/v1alpha1
kind: Application
metadata:
  name: prometheus
  namespace: argocd
  annotations:
    argocd.argoproj.io/sync-wave: "1"
spec:
  project: homelab
  sources:
    - repoURL: https://prometheus-community.github.io/helm-charts
      chart: kube-prometheus-stack
      targetRevision: "*"
      helm:
        skipCrds: true
        valueFiles:
          - $values/k8s/infra/monitoring/prometheus-values.yaml
    - repoURL: https://forgejo.riotpiao.com/rock/homelab.git
      targetRevision: main
      ref: values
  destination:
    server: https://kubernetes.default.svc
    namespace: monitoring
  syncPolicy:
    managedNamespaceMetadata:
      # node-exporter needs hostNetwork/hostPID/hostPath/hostPort; blocked by
      # default baseline PSS (DaemonSet created 0 pods, Prometheus STS stuck).
      labels:
        pod-security.kubernetes.io/enforce: privileged
    automated:
      prune: true
      selfHeal: true
    syncOptions:
      - CreateNamespace=true
      # ServerSideApply removed — it conflicts with managedNamespaceMetadata's
      # forced namespace apply ("--force cannot be used with --server-side").
      # helm.skipCrds: true above stops ArgoCD from ever managing the CRDs
      # through this Application (previously it kept re-patching them via
      # client-side apply and hitting etcd's 262144-byte annotation limit on
      # kubectl.kubernetes.io/last-applied-configuration, permanently failing
      # sync). CRDs are applied once via the separate prometheus-crds
      # Application below, which uses ServerSideApply=true (no namespace-
      # metadata conflict since CRDs are cluster-scoped).
---
# CRDs only, extracted to plain YAML (`helm show crds kube-prometheus-stack`)
# and committed to git under k8s/infra/monitoring/crds/, applied via Server-
# Side Apply to avoid the etcd 262144-byte last-applied-configuration
# annotation limit that client-side apply hits on these very large CRDs
# (prometheuses, alertmanagers, scrapeconfigs, etc). A plain git path source
# (not a remote Helm source) is used deliberately so ArgoCD applies exactly
# these 8 CRD manifests and nothing else — no ambiguity about what "CRDs only"
# means from a Helm chart. Split out from the main `prometheus` Application
# (helm.skipCrds: true there) because ServerSideApply conflicts with that
# app's managedNamespaceMetadata.
# NOTE: bump k8s/infra/monitoring/crds/kube-prometheus-stack-crds.yaml
# whenever the kube-prometheus-stack chart version changes materially
# (`helm show crds prometheus-community/kube-prometheus-stack > ...`).
apiVersion: argoproj.io/v1alpha1
kind: Application
metadata:
  name: prometheus-crds
  namespace: argocd
  annotations:
    argocd.argoproj.io/sync-wave: "0"
spec:
  project: homelab
  source:
    repoURL: https://forgejo.riotpiao.com/rock/homelab.git
    targetRevision: main
    path: k8s/infra/monitoring/crds
  destination:
    server: https://kubernetes.default.svc
    namespace: monitoring
  syncPolicy:
    automated:
      prune: true
      selfHeal: true
    syncOptions:
      - CreateNamespace=true
      - ServerSideApply=true
---
# Cluster monitoring config: custom PrometheusRules (per-app namespaces),
# ServiceMonitors (monitoring ns), and Grafana dashboard ConfigMaps (logging ns,
# grafana sidecar-discovered). Single source = k8s/infra/monitoring (one
# kustomization, no namespace transformer so per-app rule namespaces are kept).
# Wave 2: after prometheus-operator CRDs (wave 0) + stack (wave 1) and grafana
# (wave 2, logging). ServerSideApply avoids the etcd last-applied annotation
# limit on the large dashboard ConfigMap JSON.
apiVersion: argoproj.io/v1alpha1
kind: Application
metadata:
  name: monitoring-config
  namespace: argocd
  annotations:
    argocd.argoproj.io/sync-wave: "2"
spec:
  project: homelab
  source:
    repoURL: https://forgejo.riotpiao.com/rock/homelab.git
    targetRevision: main
    path: k8s/infra/monitoring
  destination:
    server: https://kubernetes.default.svc
    namespace: monitoring
  syncPolicy:
    automated:
      prune: true
      selfHeal: true
    syncOptions:
      - CreateNamespace=true
      - ServerSideApply=true
---
apiVersion: argoproj.io/v1alpha1
kind: Application
metadata:
  name: blackbox-exporter
  namespace: argocd
  annotations:
    argocd.argoproj.io/sync-wave: "1"
spec:
  project: homelab
  sources:
    - repoURL: https://prometheus-community.github.io/helm-charts
      chart: prometheus-blackbox-exporter
      targetRevision: "~11"
      helm:
        valueFiles:
          - $values/k8s/infra/monitoring/blackbox-exporter-values.yaml
    - repoURL: https://forgejo.riotpiao.com/rock/homelab.git
      targetRevision: main
      ref: values
  destination:
    server: https://kubernetes.default.svc
    namespace: monitoring
  syncPolicy:
    automated:
      prune: true
      selfHeal: true
---
# Distributed tracing: Tempo + OpenTelemetry Collector.
# Receives traces from instrumented services, stores in local volume (72h retention).
# Grafana datasource auto-configured, service graph + latency dashboards included.
apiVersion: argoproj.io/v1alpha1
kind: Application
metadata:
  name: tracing
  namespace: argocd
  annotations:
    argocd.argoproj.io/sync-wave: "1"
spec:
  project: homelab
  source:
    repoURL: https://forgejo.riotpiao.com/rock/homelab.git
    targetRevision: main
    path: k8s/infra/tracing
  destination:
    server: https://kubernetes.default.svc
    namespace: tracing
  syncPolicy:
    automated:
      prune: true
      selfHeal: true
    syncOptions:
      - CreateNamespace=true