feat!: template all ansible dir and rename template to bootstrap (#847)

2023-07-12 11:44:23 -04:00
1 parent c7f10b0c6d
commit c9d988a66f
@@ -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_nodes.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