feat(gatus): Add uptime monitoring

values/argo/manifests/sys-project.yaml

@@ -84,6 +84,8 @@ spec:
     server: https://kubernetes.default.svc
   - namespace: spegel
     server: https://kubernetes.default.svc
+  - namespace: uptime
+    server: https://kubernetes.default.svc
   sourceRepos:
   - https://argoproj.github.io/argo-helm
   - https://kubernetes-sigs.github.io/metrics-server/
@@ -122,3 +124,4 @@ spec:
   - https://operator.mariadb.com/mariadb-enterprise-operator
   - https://operator.mariadb.com
   - https://ot-container-kit.github.io/helm-charts
+  - https://twin.github.io/helm-charts

values/gatus/env-hel1.yaml.gotmpl

@@ -0,0 +1,2 @@
+gatus:
+  enabled: true

values/gatus/env-rossby.yaml.gotmpl

@@ -0,0 +1,2 @@
+gatus:
+ enabled: true

values/gatus/env.yaml.gotmpl

@@ -0,0 +1,4 @@
+gatus:
+  enabled: false
+  autosync: false
+  env: default

values/gatus/manifests/cluster.yaml

@@ -0,0 +1,14 @@
+apiVersion: postgresql.cnpg.io/v1
+kind: Cluster
+metadata:
+  name: prod-gatus-db
+  namespace: uptime
+spec:
+  instances: 1
+  imageName: ghcr.io/cloudnative-pg/postgresql:17
+  storage:
+    resizeInUseVolumes: true
+    size: 15Gi
+  backup:
+    retentionPolicy: 30d
+    target: prefer-standby

values/gatus/manifests/gatus.yaml

@@ -0,0 +1,38 @@
+{{- if .Values.clusterConfig.argo.enabled }}
+apiVersion: argoproj.io/v1alpha1
+kind: Application
+metadata:
+  name: gatus
+  namespace: argocd
+spec:
+  destination:
+    namespace: uptime
+    server: 'https://kubernetes.default.svc'
+  sources:
+  - repoURL: {{ .Values.clusterConfig.manifests }}
+    targetRevision: HEAD
+    path: helmfile.d
+    plugin:
+      name: helmfile-cmp
+      env:
+      - name: CLUSTER_NAME
+        value: {{ .Values.clusterConfig.cluster }}
+      - name: HELMFILE_ENVIRONMENT
+        value: default
+      - name: HELMFILE_FILE_PATH
+        value: gatus.yaml.gotmpl
+  project: sys
+  syncPolicy:
+    managedNamespaceMetadata:
+      labels:
+        component: sys
+    syncOptions:
+      - CreateNamespace=true
+      - ApplyOutOfSyncOnly=true
+      - ServerSideApply=true
+    {{- if .Values.gatus.autosync }}
+    automated:
+      prune: true
+      # selfHeal: false
+    {{- end }}
+{{- end }}

values/gatus/manifests/ingress.yaml

@@ -0,0 +1,31 @@
+apiVersion: networking.k8s.io/v1
+kind: Ingress
+metadata:
+  annotations:
+    cert-manager.io/cluster-issuer: letsencrypt-production
+    nginx.ingress.kubernetes.io/backend-protocol: HTTP
+    nginx.ingress.kubernetes.io/cors-allow-headers: Content-Type, x-gatus-cache
+    nginx.ingress.kubernetes.io/enable-cors: "true"
+    nginx.ingress.kubernetes.io/proxy-buffer-size: 128k
+    nginx.ingress.kubernetes.io/ssl-redirect: "true"
+  labels:
+    app.kubernetes.io/name: gatus
+  name: gatus
+  namespace: uptime
+spec:
+  ingressClassName: nginx
+  rules:
+  - host: uptime.srv.oceanbox.io
+    http:
+      paths:
+      - backend:
+          service:
+            name: gatus
+            port:
+              number: 80
+        path: /
+        pathType: ImplementationSpecific
+  tls:
+  - hosts:
+    - uptime.srv.oceanbox.io
+    secretName: gatus-tls

values/gatus/manifests/secret.yaml

@@ -0,0 +1,8 @@
+apiVersion: v1
+kind: Secret
+stringData:
+  DB_PASS: "test"
+metadata:
+  name: gatus
+  namespace: uptime
+type: Opaque

values/gatus/values/values.yaml

@@ -0,0 +1,88 @@
+image:
+  repository: twinproduction/gatus
+  tag: v5.26.0
+
+# Does envFrom secret named gatus
+secrets: true
+
+serviceMonitor:
+  enabled: true
+
+config:
+  web:
+    address: "[::]"
+  metrics: true
+
+  storage:
+    type: postgres
+    path: "postgres://app:${DB_PASS}@prod-gatus-db:5432/app"
+
+  ui:
+    title: Oceanbox
+    header: Oceanbox Monitoring
+    #logo: https://zarak.fr/resources/cyril-avatar.jpg
+    link: https://oceanbox.io
+
+  .defaults: &defaults
+    interval: 30s
+
+  .https-endpoint: &https-endpoint
+    <<: *defaults
+    conditions:
+      - "[STATUS] == 200"
+      - "[RESPONSE_TIME] <= 1000"
+      - "[CERTIFICATE_EXPIRATION] > 168h" # 7 days
+
+  .tls-endpoint: &tls-endpoint
+    <<: *defaults
+    conditions:
+      - "[CONNECTED] == true"
+      - "[RESPONSE_TIME] <= 1000"
+      - "[CERTIFICATE_EXPIRATION] > 168h" # 7 days
+
+  .tcp-endpoint: &tcp-endpoint
+    <<: *defaults
+    conditions:
+      - "[CONNECTED] == true"
+      - "[RESPONSE_TIME] <= 1000"
+
+  endpoints:
+    - name: Atlantis
+      <<: *https-endpoint
+      group: "Primary Services"
+      url: https://maps.oceanbox.io/healthz
+
+    - name: Sorcerer
+      <<: *https-endpoint
+      group: "Primary Services"
+      url: https://sorcerer.data.oceanbox.io/healthz
+
+    - name: Plume
+      <<: *https-endpoint
+      group: "Secondary Services"
+      url: https://plume.data.oceanbox.io/healthz
+
+    - name: Homepage
+      <<: *https-endpoint
+      group: "Secondary Services"
+      url: https://oceanbox.io
+
+    - name: Homepage
+      <<: *https-endpoint
+      group: "Experimental Services"
+      url: https://oceanbox.io
+
+    - name: Atlantis Beta
+      <<: *https-endpoint
+      group: "Experimental Services"
+      url: https://atlantis.beta.oceanbox.io/healthz
+
+    - name: Sorcerer Beta
+      <<: *https-endpoint
+      group: "Experimental Services"
+      url: https://sorcerer.ekman.oceanbox.io/healthz
+
+    - name: Plume Beta
+      <<: *https-endpoint
+      group: "Experimental Services"
+      url: https://plume.ekman.oceanbox.io/healthz