feat(cherry): add kube-prometheus-stack

clusters/cherry/apps/kube-prometheus-stack.yaml

@@ -0,0 +1,204 @@
+apiVersion: argoproj.io/v1alpha1
+kind: Application
+metadata:
+  name: cherry-kube-prometheus-stack
+  namespace: argocd
+  finalizers:
+    - resources-finalizer.argocd.argoproj.io
+spec:
+  project: monitoring
+  syncPolicy:
+    automated:
+      prune: true
+      selfHeal: true
+    syncOptions:
+      - CreateNamespace=true
+      - ServerSideApply=true
+  destination:
+    server: https://kubernetes.default.svc
+    namespace: monitoring
+  source:
+    chart: kube-prometheus-stack
+    repoURL: https://prometheus-community.github.io/helm-charts
+    targetRevision: 51.2.0
+    helm:
+      releaseName: monitoring
+      values: |
+        cleanPrometheusOperatorObjectNames: true
+        fullnameOverride: "monitoring"
+
+        defaultRules:
+          create: true
+          rules:
+            alertmanager: true
+            etcd: false
+            configReloaders: true
+            general: true
+            k8s: true
+            kubeApiserverAvailability: true
+            kubeApiserverBurnrate: true
+            kubeApiserverHistogram: true
+            kubeApiserverSlos: true
+            kubeControllerManager: true
+            kubelet: true
+            kubeProxy: false
+            kubePrometheusGeneral: true
+            kubePrometheusNodeRecording: true
+            kubernetesApps: true
+            kubernetesResources: true
+            kubernetesStorage: true
+            kubernetesSystem: true
+            kubeSchedulerAlerting: true
+            kubeSchedulerRecording: true
+            kubeStateMetrics: true
+            network: true
+            node: true
+            nodeExporterAlerting: true
+            nodeExporterRecording: true
+            prometheus: true
+            prometheusOperator: true
+            windows: false
+
+        prometheus:
+          fullnameOverride: prometheus
+
+          ingress:
+            enabled: true
+            ingressClassName: nginx
+            annotations:
+              cert-manager.io/cluster-issuer: letsencrypt-prod
+            hosts:
+              - prometheus.ops.mareshq.com
+            paths:
+              - /
+            pathType: Prefix
+            tls:
+              - hosts:
+                  - prometheus.ops.mareshq.com
+                secretName: prometheus-ingress-tls
+
+          podDisruptionBudget:
+            enabled: true
+            minAvailable: 1
+
+          prometheusSpec:
+            serviceMonitorSelectorNilUsesHelmValues: false
+            podMonitorSelectorNilUsesHelmValues: false
+            ruleSelectorNilUsesHelmValues: false
+
+            replicas: 2
+
+            retention: 45d
+
+            resources:
+              limits:
+                cpu: 1000m
+                memory: 2Gi
+              requests:
+                cpu: 500m
+                memory: 2Gi
+
+            storageSpec:
+              volumeClaimTemplate:
+                spec:
+                  storageClassName: hcloud-volumes
+                  accessModes: ["ReadWriteOnce"]
+                  resources:
+                    requests:
+                      storage: 50Gi
+
+          serviceMonitor:
+            selfMonitor: true
+
+        alertmanager:
+          enabled: true
+          ingress:
+            enabled: true
+            ingressClassName: nginx
+            annotations:
+              cert-manager.io/cluster-issuer: letsencrypt-prod
+            hosts:
+              - alertmanager.ops.mareshq.com
+            paths:
+              - /
+            pathType: Prefix
+            tls:
+              - hosts:
+                  - alertmanager.ops.mareshq.com
+                secretName: alertmanager-ingress-tls
+
+          podDisruptionBudget:
+            enabled: true
+            minAvailable: 1
+
+          alertmanagerSpec:
+            replicas: 2
+            resources:
+              limits:
+                cpu: 250m
+                memory: 256Mi
+              requests:
+                cpu: 100m
+                memory: 256Mi
+
+            storage:
+              volumeClaimTemplate:
+                spec:
+                  storageClassName: hcloud-volumes
+                  resources:
+                    requests:
+                      storage: 10Gi
+
+        grafana:
+          enabled: true
+          defaultDashboardsEnabled: true
+
+          adminPassword: zud!edy7WER5uqg7gjq
+
+          ingress:
+            enabled: true
+            ingressClassName: nginx
+            annotations:
+              cert-manager.io/cluster-issuer: letsencrypt-prod
+            hosts:
+              - grafana.ops.mareshq.com
+            paths:
+              - /
+            pathType: Prefix
+            tls:
+              - hosts:
+                - grafana.ops.mareshq.com
+                secretName: grafana-ingress-tls
+
+          serviceMonitor:
+            selfMonitor: true
+
+          grafana.ini:
+            server:
+              root_url: https://grafana.ops.mareshq.com
+            # auth.gitlab:
+            #   enabled: true
+            #   allow_sign_up: true
+            #   client_id: old
+            #   client_secret: old
+            #   scopes: read_api
+            #   auth_url: https://gitlab.mareshq.com/oauth/authorize
+            #   token_url: https://gitlab.mareshq.com/oauth/token
+            #   api_url: https://gitlab.mareshq.com/api/v4
+            #   allowed_groups: mareshq
+            auth.basic:
+              enabled: true
+            auth:
+              disable_login_form: false
+
+        kubeProxy:
+          enabled: false
+
+        kubeEtcd:
+          enabled: false
+
+        prometheus-node-exporter:
+          fullnameOverride: node-exporter
+
+        kube-state-metrics:
+          fullnameOverride: kube-state-metrics