feat: Added kube-prometheus-stack

clusters/testing/kustomization.yaml

@@ -13,6 +13,7 @@ resources:
   - ../../controllers/lldap-controller/lldap-controller.yaml
   - ../../controllers/authelia-controller/authelia-controller.yaml
   - ../../controllers/dragonfly-operator/dragonfly-operator.yaml
+  - ../../controllers/kube-prometheus-stack/kube-prometheus-stack.yaml
 
   - ../../configs/artifacts.yaml
   - ../../configs/cilium-config/cilium-config.yaml

controllers/artifacts.yaml

@@ -49,3 +49,8 @@ spec:
       copy:
         - from: "@foundation/controllers/dragonfly-operator/**"
           to: "@artifact/"
+    - name: kube-prometheus-stack
+      originRevision: "@foundation"
+      copy:
+        - from: "@foundation/controllers/kube-prometheus-stack/**"
+          to: "@artifact/"

controllers/kube-prometheus-stack/cluster-restore.yaml

@@ -0,0 +1,16 @@
+apiVersion: postgresql.cnpg.io/v1
+kind: Cluster
+metadata:
+  name: db
+spec:
+  bootstrap:
+    recovery:
+      source: source
+  externalClusters:
+    - name: source
+      plugin:
+        name: barman-cloud.cloudnative-pg.io
+        parameters:
+          barmanObjectName: garage-store
+          serverName: db
+  plugins: []

controllers/kube-prometheus-stack/cluster.yaml

@@ -0,0 +1,15 @@
+apiVersion: postgresql.cnpg.io/v1
+kind: Cluster
+metadata:
+  name: db
+  namespace: monitoring
+  # TODO: Add labels?
+spec:
+  storage:
+    size: 8Gi
+    storageClass: local-path
+  plugins:
+    - name: barman-cloud.cloudnative-pg.io
+      isWALArchiver: true
+      parameters:
+        barmanObjectName: garage-store

controllers/kube-prometheus-stack/dragonfly.yaml

@@ -0,0 +1,7 @@
+apiVersion: dragonflydb.io/v1alpha1
+kind: Dragonfly
+metadata:
+  name: dragonfly
+  namespace: monitoring
+spec:
+  replicas: 1

controllers/kube-prometheus-stack/grafana-ldap.toml

@@ -0,0 +1,53 @@
+# This is only the ldap config, you also need to enable ldap support in the main config file
+# of Grafana. See https://grafana.com/docs/grafana/latest/auth/ldap/#enable-ldap
+# You can test that it is working correctly by trying usernames at: https://<your grafana instance>/admin/ldap
+
+[[servers]]
+# Ldap server host (specify multiple hosts space separated)
+host = "lldap.lldap.svc.cluster.local"
+# Default port is 389 or 636 if use_ssl = true
+port = 3890
+# Set to true if LDAP server should use an encrypted TLS connection (either with STARTTLS or LDAPS)
+use_ssl = false
+# If set to true, use LDAP with STARTTLS instead of LDAPS
+start_tls = false
+# set to true if you want to skip SSL cert validation
+ssl_skip_verify = false
+# set to the path to your root CA certificate or leave unset to use system defaults
+# root_ca_cert = "/path/to/certificate.crt"
+# Authentication against LDAP servers requiring client certificates
+# client_cert = "/path/to/client.crt"
+# client_key = "/path/to/client.key"
+
+# Search user bind dn
+bind_dn = "${BIND_DN}"
+# Search user bind password
+# If the password contains # or ; you have to wrap it with triple quotes. Ex """#password;"""
+bind_password = "${LDAP_PASSWORD}"
+
+# User search filter
+search_filter = "(&(|(uid=%s)(mail=%s))(objectClass=person))"
+# If you want to limit to only users of a specific group use this instead:
+# search_filter = "(&(uid=%s)(memberOf=cn=<your group>,ou=groups,dc=huizinga,dc=dev))"
+
+# An array of base dns to search through
+search_base_dns = ["dc=huizinga,dc=dev"]
+
+# Specify names of the LDAP attributes your LDAP uses
+[servers.attributes]
+member_of = "memberOf"
+email = "mail"
+name = "givenName"
+surname = "sn"
+username = "uid"
+
+# If you want to map your ldap groups to grafana's groups, see: https://grafana.com/docs/grafana/latest/auth/ldap/#group-mappings
+# As a quick example, here is how you would map lldap's admin group to grafana's admin
+[[servers.group_mappings]]
+group_dn = "cn=lldap_admin,ou=groups,dc=huizinga,dc=dev"
+org_role = "Admin"
+grafana_admin = true
+
+[[servers.group_mappings]]
+group_dn = "*"
+org_role = "Viewer"

controllers/kube-prometheus-stack/helm-release.yaml

@@ -0,0 +1,30 @@
+apiVersion: helm.toolkit.fluxcd.io/v2
+kind: HelmRelease
+metadata:
+  name: kube-prometheus-stack
+  namespace: monitoring
+spec:
+  interval: 12h
+  install:
+    strategy:
+      name: RetryOnFailure
+      retryInterval: 2m
+  upgrade:
+    strategy:
+      name: RetryOnFailure
+      retryInterval: 3m
+  chart:
+    spec:
+      chart: kube-prometheus-stack
+      version: "80.6.x"
+      sourceRef:
+        kind: HelmRepository
+        name: prometheus-community
+      interval: 24h
+  values:
+    grafana:
+      ldap:
+        existingSecret: grafana-ldap-toml
+  valuesFrom:
+    - kind: ConfigMap
+      name: values-base

controllers/kube-prometheus-stack/helm-repository.yaml

@@ -0,0 +1,9 @@
+apiVersion: source.toolkit.fluxcd.io/v1
+kind: HelmRepository
+metadata:
+  name: prometheus-community
+  namespace: monitoring
+spec:
+  type: "oci"
+  interval: 24h
+  url: oci://ghcr.io/prometheus-community/charts/

controllers/kube-prometheus-stack/kube-prometheus-stack.yaml

@@ -0,0 +1,18 @@
+apiVersion: kustomize.toolkit.fluxcd.io/v1
+kind: Kustomization
+metadata:
+  name: kube-prometheus-stack
+  namespace: flux-system
+spec:
+  interval: 1h
+  retryInterval: 2m
+  timeout: 5m
+  dependsOn:
+    - name: dragonfly-operator
+    - name: lldap-controller
+  sourceRef:
+    kind: ExternalArtifact
+    name: kube-prometheus-stack
+  path: ./
+  prune: true
+  wait: true

controllers/kube-prometheus-stack/kustomization.yaml

@@ -0,0 +1,31 @@
+apiVersion: kustomize.config.k8s.io/v1beta1
+kind: Kustomization
+resources:
+  - namespace.yaml
+  - helm-repository.yaml
+  - helm-release.yaml
+  - dragonfly.yaml
+  - cluster.yaml
+  - secret-s3-garage.yaml
+  - object-store.yaml
+
+configurations:
+  - name-reference.yaml
+
+configMapGenerator:
+  - name: values-base
+    namespace: monitoring
+    files:
+      - values.yaml
+
+secretGenerator:
+  - name: grafana-ldap-toml
+    namespace: monitoring
+    files:
+      - ldap-toml=grafana-ldap.toml
+
+# Uncomment to restore database from backup
+# patches:
+#   - path: cluster-restore.yaml
+#     target:
+#       kind: Cluster

controllers/kube-prometheus-stack/name-reference.yaml

@@ -0,0 +1,11 @@
+nameReference:
+  - kind: ConfigMap
+    version: v1
+    fieldSpecs:
+      - path: spec/valuesFrom/name
+        kind: HelmRelease
+  - kind: Secret
+    version: v1
+    fieldSpecs:
+      - path: spec/values/grafana/ldap/existingSecret
+        kind: HelmRelease

controllers/kube-prometheus-stack/namespace.yaml

@@ -0,0 +1,4 @@
+apiVersion: v1
+kind: Namespace
+metadata:
+  name: monitoring

controllers/kube-prometheus-stack/object-store.yaml

@@ -0,0 +1,20 @@
+apiVersion: barmancloud.cnpg.io/v1
+kind: ObjectStore
+metadata:
+  name: garage-store
+  namespace: monitoring
+spec:
+  configuration:
+    destinationPath: s3://cnpg-backup/authelia
+    s3Credentials:
+      accessKeyId:
+        name: s3-garage
+        key: ACCESS_KEY_ID
+      secretAccessKey:
+        name: s3-garage
+        key: ACCESS_SECRET_KEY
+      region:
+        name: s3-garage
+        key: REGION
+    wal:
+      compression: gzip

controllers/kube-prometheus-stack/secret-s3-garage.yaml

@@ -0,0 +1,9 @@
+apiVersion: v1
+kind: Secret
+metadata:
+  name: s3-garage
+  namespace: monitoring
+  annotations:
+    reflector.v1.k8s.emberstack.com/reflects: "cnpg-system/s3-garage"
+type: Opaque
+data: {}

controllers/kube-prometheus-stack/service-user.yaml

@@ -0,0 +1,6 @@
+apiVersion: lldap.huizinga.dev/v1
+kind: ServiceUser
+metadata:
+  name: grafana
+  namespace: monitoring
+spec: {}

controllers/kube-prometheus-stack/values.yaml

@@ -0,0 +1,86 @@
+alertmanager:
+  alertsmanagerSpec:
+    replicas: 1
+  route:
+    main:
+      enabled: true
+      hostnames:
+        - "alerts.staging.huizinga.dev"
+      parentRefs:
+        - name: gateway
+          namespace: default
+
+prometheus:
+  prometheusSpec:
+    replicas: 1
+  route:
+    main:
+      enabled: true
+      hostnames:
+        - "prometheus.staging.huizinga.dev"
+      parentRefs:
+        - name: gateway
+          namespace: default
+
+grafana:
+  replicas: 1
+
+  # ingress:
+  #   enabled: true
+  #   hosts:
+  #     - grafana.${domain}
+  #   tls:
+  #     - secretName: ${domain//./-}-tls
+  #   annotations:
+  #     traefik.ingress.kubernetes.io/router.entryPoints: "websecure"
+  #     traefik.ingress.kubernetes.io/router.middlewares: "authelia-forwardauth-authelia@kubernetescrd"
+  #     traefik.ingress.kubernetes.io/router.tls: "true"
+
+  envValueFrom:
+    BIND_DN:
+      secretKeyRef:
+        name: grafana-lldap-credentials
+        key: bind_dn
+    LDAP_PASSWORD:
+      secretKeyRef:
+        name: grafana-lldap-credentials
+        key: password
+
+  grafana.ini:
+    auth.ldap:
+      enabled: true
+
+    # auth.proxy:
+    #   enabled: true
+    #   header_name: Remote-User
+    #   header_property: username
+    #   auto_sign_up: true
+    #   headers: Groups:Remote-Group
+    #   enable_login_token: false
+    #   sync_ttl: 0
+    #   signout_redirect_url: https://login.${domain}/logout?rd=https://grafana.${domain}
+
+    database:
+      type: postgres
+      host: $__file{/etc/secrets/db/host}
+      name: $__file{/etc/secrets/db/dbname}
+      user: $__file{/etc/secrets/db/user}
+      password: $__file{/etc/secrets/db/password}
+
+    remote_cache:
+      type: redis
+      connstr: addr=dragonflydb.monitoring:6379
+
+  ldap:
+    enabled: true
+
+  extraSecretMounts:
+    - name: db-app-mount
+      secretName: db-app
+      defaultMode: 0440
+      mountPath: /etc/secrets/db
+      readOnly: true
+
+# We are not running kube-proxy
+kubeProxy:
+  enabled: false