feat: move kubernetes dir into templates to support jinja2 across all files (#831)

2023-07-05 21:17:10 -04:00
1 parent 7b0a154fed
commit fe41cf6ea5
@@ -0,0 +1,100 @@
+---
+apiVersion: helm.toolkit.fluxcd.io/v2beta1
+kind: HelmRelease
+metadata:
+  name: grafana
+  namespace: monitoring
+spec:
+  interval: 30m
+  chart:
+    spec:
+      chart: grafana
+      version: 6.57.4
+      sourceRef:
+        kind: HelmRepository
+        name: grafana
+        namespace: flux-system
+  maxHistory: 2
+  install:
+    createNamespace: true
+    remediation:
+      retries: 3
+  upgrade:
+    cleanupOnFail: true
+    remediation:
+      retries: 3
+  uninstall:
+    keepHistory: false
+  dependsOn:
+    - name: local-path-provisioner
+      namespace: kube-system
+    - name: ingress-nginx
+      namespace: networking
+  values:
+    deploymentStrategy:
+      type: Recreate
+    admin:
+      existingSecret: grafana-admin-secret
+    env:
+      GF_EXPLORE_ENABLED: true
+      GF_SERVER_ROOT_URL: "https://grafana.${SECRET_DOMAIN}"
+    grafana.ini:
+      analytics:
+        check_for_updates: false
+        check_for_plugin_updates: false
+    dashboardProviders:
+      dashboardproviders.yaml:
+        apiVersion: 1
+        providers:
+          - name: default
+            orgId: 1
+            folder: ""
+            type: file
+            disableDeletion: false
+            editable: true
+            options:
+              path: /var/lib/grafana/dashboards/default
+    datasources:
+      datasources.yaml:
+        apiVersion: 1
+        datasources:
+          - name: Prometheus
+            type: prometheus
+            access: proxy
+            url: http://kube-prometheus-stack-prometheus.monitoring.svc.cluster.local:9090
+            isDefault: true
+    dashboards:
+      default:
+        cert-manager:
+          url: https://raw.githubusercontent.com/monitoring-mixins/website/master/assets/cert-manager/dashboards/cert-manager.json
+          datasource: Prometheus
+        flux-cluster:
+          url: https://raw.githubusercontent.com/fluxcd/flux2/main/manifests/monitoring/monitoring-config/dashboards/cluster.json
+          datasource: Prometheus
+        flux-control-plane:
+          url: https://raw.githubusercontent.com/fluxcd/flux2/main/manifests/monitoring/monitoring-config/dashboards/control-plane.json
+          datasource: Prometheus
+    sidecar:
+      dashboards:
+        enabled: true
+        searchNamespace: ALL
+      datasources:
+        enabled: true
+        searchNamespace: ALL
+    serviceMonitor:
+      enabled: true
+    ingress:
+      enabled: true
+      ingressClassName: nginx
+      annotations:
+        hajimari.io/icon: simple-icons:grafana
+      hosts:
+        - &host "grafana.${SECRET_DOMAIN}"
+      tls:
+        - hosts:
+            - *host
+    persistence:
+      enabled: true
+      storageClassName: local-path
+    testFramework:
+      enabled: false
@@ -0,0 +1,7 @@
+---
+apiVersion: kustomize.config.k8s.io/v1beta1
+kind: Kustomization
+namespace: monitoring
+resources:
+  - ./secret.sops.yaml
+  - ./helmrelease.yaml
@@ -0,0 +1,9 @@
+---
+apiVersion: v1
+kind: Secret
+metadata:
+  name: grafana-admin-secret
+  namespace: monitoring
+stringData:
+  admin-user: admin
+  admin-password: "{{ bootstrap_grafana_admin_password }}"
@@ -0,0 +1,16 @@
+---
+apiVersion: kustomize.toolkit.fluxcd.io/v1
+kind: Kustomization
+metadata:
+  name: cluster-apps-grafana
+  namespace: flux-system
+spec:
+  path: ./kubernetes/apps/monitoring/grafana/app
+  prune: true
+  sourceRef:
+    kind: GitRepository
+    name: home-kubernetes
+  wait: false # no flux ks dependents
+  interval: 30m
+  retryInterval: 1m
+  timeout: 5m
@@ -0,0 +1,142 @@
+#jinja2: trim_blocks: True, lstrip_blocks: True
+---
+apiVersion: helm.toolkit.fluxcd.io/v2beta1
+kind: HelmRelease
+metadata:
+  name: kube-prometheus-stack
+  namespace: monitoring
+spec:
+  interval: 30m
+  timeout: 15m
+  chart:
+    spec:
+      chart: kube-prometheus-stack
+      version: 47.1.0
+      sourceRef:
+        kind: HelmRepository
+        name: prometheus-community
+        namespace: flux-system
+  maxHistory: 2
+  install:
+    createNamespace: true
+    crds: CreateReplace
+    remediation:
+      retries: 3
+  upgrade:
+    cleanupOnFail: true
+    crds: CreateReplace
+    remediation:
+      retries: 3
+  uninstall:
+    keepHistory: false
+  dependsOn:
+    - name: local-path-provisioner
+      namespace: kube-system
+    - name: ingress-nginx
+      namespace: networking
+  values:
+    cleanPrometheusOperatorObjectNames: true
+    alertmanager:
+      enabled: false
+    grafana:
+      enabled: false
+      forceDeployDashboards: true
+      sidecar:
+        dashboards:
+          multicluster:
+            etcd:
+              enabled: true
+    kube-state-metrics:
+      metricLabelsAllowlist:
+        - "pods=[*]"
+        - "deployments=[*]"
+        - "persistentvolumeclaims=[*]"
+      prometheus:
+        monitor:
+          enabled: true
+          relabelings:
+            - action: replace
+              regex: (.*)
+              replacement: $1
+              sourceLabels: ["__meta_kubernetes_pod_node_name"]
+              targetLabel: kubernetes_node
+    kubelet:
+      enabled: true
+      serviceMonitor:
+        metricRelabelings:
+          # Remove duplicate metrics
+          - sourceLabels: ["__name__"]
+            regex: "(apiserver_audit|apiserver_client|apiserver_delegated|apiserver_envelope|apiserver_storage|apiserver_webhooks|authentication_token|cadvisor_version|container_blkio|container_cpu|container_fs|container_last|container_memory|container_network|container_oom|container_processes|container|csi_operations|disabled_metric|get_token|go|hidden_metric|kubelet_certificate|kubelet_cgroup|kubelet_container|kubelet_containers|kubelet_cpu|kubelet_device|kubelet_graceful|kubelet_http|kubelet_lifecycle|kubelet_managed|kubelet_node|kubelet_pleg|kubelet_pod|kubelet_run|kubelet_running|kubelet_runtime|kubelet_server|kubelet_started|kubelet_volume|kubernetes_build|kubernetes_feature|machine_cpu|machine_memory|machine_nvm|machine_scrape|node_namespace|plugin_manager|prober_probe|process_cpu|process_max|process_open|process_resident|process_start|process_virtual|registered_metric|rest_client|scrape_duration|scrape_samples|scrape_series|storage_operation|volume_manager|volume_operation|workqueue)_(.+)"
+            action: keep
+          - sourceLabels: ["node"]
+            targetLabel: instance
+            action: replace
+    kubeApiServer:
+      enabled: true
+      serviceMonitor:
+        metricRelabelings:
+          # Remove duplicate metrics
+          - sourceLabels: ["__name__"]
+            regex: "(aggregator_openapi|aggregator_unavailable|apiextensions_openapi|apiserver_admission|apiserver_audit|apiserver_cache|apiserver_cel|apiserver_client|apiserver_crd|apiserver_current|apiserver_envelope|apiserver_flowcontrol|apiserver_init|apiserver_kube|apiserver_longrunning|apiserver_request|apiserver_requested|apiserver_response|apiserver_selfrequest|apiserver_storage|apiserver_terminated|apiserver_tls|apiserver_watch|apiserver_webhooks|authenticated_user|authentication|disabled_metric|etcd_bookmark|etcd_lease|etcd_request|field_validation|get_token|go|grpc_client|hidden_metric|kube_apiserver|kubernetes_build|kubernetes_feature|node_authorizer|pod_security|process_cpu|process_max|process_open|process_resident|process_start|process_virtual|registered_metric|rest_client|scrape_duration|scrape_samples|scrape_series|serviceaccount_legacy|serviceaccount_stale|serviceaccount_valid|watch_cache|workqueue)_(.+)"
+            action: keep
+          # Remove high cardinality metrics
+          - sourceLabels: ["__name__"]
+            regex: (apiserver|etcd|rest_client)_request(|_sli|_slo)_duration_seconds_bucket
+            action: drop
+          - sourceLabels: ["__name__"]
+            regex: (apiserver_response_sizes_bucket|apiserver_watch_events_sizes_bucket)
+            action: drop
+    kubeControllerManager:
+      enabled: true
+      endpoints: &cp
+      {% for item in bootstrap_hosts.master %}
+        - {{ item.address }}
+      {% endfor %}
+      serviceMonitor:
+        metricRelabelings:
+          # Remove duplicate metrics
+          - sourceLabels: ["__name__"]
+            regex: "(apiserver_audit|apiserver_client|apiserver_delegated|apiserver_envelope|apiserver_storage|apiserver_webhooks|attachdetach_controller|authenticated_user|authentication|cronjob_controller|disabled_metric|endpoint_slice|ephemeral_volume|garbagecollector_controller|get_token|go|hidden_metric|job_controller|kubernetes_build|kubernetes_feature|leader_election|node_collector|node_ipam|process_cpu|process_max|process_open|process_resident|process_start|process_virtual|pv_collector|registered_metric|replicaset_controller|rest_client|retroactive_storageclass|root_ca|running_managed|scrape_duration|scrape_samples|scrape_series|service_controller|storage_count|storage_operation|ttl_after|volume_operation|workqueue)_(.+)"
+            action: keep
+    kubeEtcd:
+      enabled: true
+      endpoints: *cp
+    kubeProxy:
+      enabled: false # Disabled because eBPF
+    kubeScheduler:
+      enabled: true
+      endpoints: *cp
+      serviceMonitor:
+        metricRelabelings:
+          # Remove duplicate metrics
+          - sourceLabels: ["__name__"]
+            regex: "(apiserver_audit|apiserver_client|apiserver_delegated|apiserver_envelope|apiserver_storage|apiserver_webhooks|authenticated_user|authentication|disabled_metric|go|hidden_metric|kubernetes_build|kubernetes_feature|leader_election|process_cpu|process_max|process_open|process_resident|process_start|process_virtual|registered_metric|rest_client|scheduler|scrape_duration|scrape_samples|scrape_series|workqueue)_(.+)"
+            action: keep
+    prometheus:
+      ingress:
+        enabled: true
+        ingressClassName: nginx
+        annotations:
+          hajimari.io/appName: Prometheus
+          hajimari.io/icon: simple-icons:prometheus
+        pathType: Prefix
+        hosts:
+          - &host "prometheus.${SECRET_DOMAIN}"
+        tls:
+          - hosts:
+              - *host
+      prometheusSpec:
+        ruleSelectorNilUsesHelmValues: false
+        serviceMonitorSelectorNilUsesHelmValues: false
+        podMonitorSelectorNilUsesHelmValues: false
+        probeSelectorNilUsesHelmValues: false
+        enableAdminAPI: true
+        walCompression: true
+        retentionSize: 8GB
+        storageSpec:
+          volumeClaimTemplate:
+            spec:
+              storageClassName: local-path
+              resources:
+                requests:
+                  storage: 10Gi
@@ -0,0 +1,6 @@
+---
+apiVersion: kustomize.config.k8s.io/v1beta1
+kind: Kustomization
+namespace: monitoring
+resources:
+  - ./helmrelease.yaml
@@ -0,0 +1,16 @@
+---
+apiVersion: kustomize.toolkit.fluxcd.io/v1
+kind: Kustomization
+metadata:
+  name: cluster-apps-kube-prometheus-stack
+  namespace: flux-system
+spec:
+  path: ./kubernetes/apps/monitoring/kube-prometheus-stack/app
+  prune: true
+  sourceRef:
+    kind: GitRepository
+    name: home-kubernetes
+  wait: false # no flux ks dependents
+  interval: 30m
+  retryInterval: 1m
+  timeout: 5m
@@ -0,0 +1,54 @@
+---
+apiVersion: helm.toolkit.fluxcd.io/v2beta1
+kind: HelmRelease
+metadata:
+  name: kubernetes-dashboard
+  namespace: monitoring
+spec:
+  interval: 30m
+  chart:
+    spec:
+      chart: kubernetes-dashboard
+      version: 6.0.8
+      sourceRef:
+        kind: HelmRepository
+        name: kubernetes-dashboard
+        namespace: flux-system
+  maxHistory: 2
+  install:
+    createNamespace: true
+    remediation:
+      retries: 3
+  upgrade:
+    cleanupOnFail: true
+    remediation:
+      retries: 3
+  uninstall:
+    keepHistory: false
+  dependsOn:
+    - name: ingress-nginx
+      namespace: networking
+  values:
+    env:
+      TZ: "${TIMEZONE}"
+    extraArgs:
+      - --enable-skip-login
+      - --disable-settings-authorizer
+      - --enable-insecure-login
+      - --token-ttl=43200
+    ingress:
+      enabled: true
+      className: nginx
+      annotations:
+        cert-manager.io/cluster-issuer: letsencrypt-staging
+        hajimari.io/icon: mdi:kubernetes
+      hosts:
+        - &host "kubernetes.${SECRET_DOMAIN}"
+      tls:
+        - hosts:
+            - *host
+          secretName: kubernetes-dashboard-tls
+    metricsScraper:
+      enabled: true
+    serviceMonitor:
+      enabled: false
@@ -0,0 +1,7 @@
+---
+apiVersion: kustomize.config.k8s.io/v1beta1
+kind: Kustomization
+namespace: monitoring
+resources:
+  - ./rbac.yaml
+  - ./helmrelease.yaml
@@ -0,0 +1,41 @@
+# For dashboard sign in token:
+# kubectl -n monitoring get secret kubernetes-dashboard -o jsonpath='{.data.token}' | base64 -d
+---
+apiVersion: v1
+kind: ServiceAccount
+metadata:
+  name: kubernetes-dashboard
+  namespace: monitoring
+  labels:
+    app.kubernetes.io/managed-by: Helm
+  annotations:
+    meta.helm.sh/release-name: kubernetes-dashboard
+    meta.helm.sh/release-namespace: monitoring
+secrets:
+  - name: kubernetes-dashboard
+---
+apiVersion: v1
+kind: Secret
+type: kubernetes.io/service-account-token
+metadata:
+  name: kubernetes-dashboard
+  namespace: monitoring
+  labels:
+    app.kubernetes.io/managed-by: Helm
+  annotations:
+    meta.helm.sh/release-name: kubernetes-dashboard
+    meta.helm.sh/release-namespace: monitoring
+    kubernetes.io/service-account.name: kubernetes-dashboard
+---
+apiVersion: rbac.authorization.k8s.io/v1
+kind: ClusterRoleBinding
+metadata:
+  name: system:kubernetes-dashboard
+roleRef:
+  apiGroup: rbac.authorization.k8s.io
+  kind: ClusterRole
+  name: cluster-admin
+subjects:
+  - kind: ServiceAccount
+    name: kubernetes-dashboard
+    namespace: monitoring
@@ -0,0 +1,16 @@
+---
+apiVersion: kustomize.toolkit.fluxcd.io/v1
+kind: Kustomization
+metadata:
+  name: cluster-apps-kubernetes-dashboard
+  namespace: flux-system
+spec:
+  path: ./kubernetes/apps/monitoring/kubernetes-dashboard/app
+  prune: true
+  sourceRef:
+    kind: GitRepository
+    name: home-kubernetes
+  wait: false # no flux ks dependents
+  interval: 30m
+  retryInterval: 1m
+  timeout: 5m
@@ -0,0 +1,8 @@
+---
+apiVersion: kustomize.config.k8s.io/v1beta1
+kind: Kustomization
+resources:
+  - ./namespace.yaml
+  - ./grafana/ks.yaml
+  - ./kube-prometheus-stack/ks.yaml
+  - ./kubernetes-dashboard/ks.yaml
@@ -0,0 +1,7 @@
+---
+apiVersion: v1
+kind: Namespace
+metadata:
+  name: monitoring
+  labels:
+    kustomize.toolkit.fluxcd.io/prune: disabled