Update cert-manager Docker tag to v1.21.0

Reviewed-on: #252

charts/atlantis/Chart.yaml

@@ -4,10 +4,10 @@ description: Atlantis map and simulation service
 type: application
 # This is the chart version. This version number should be incremented each time you make changes
 # to the chart and its templates, including the app version.
-version: v2.17.1
+version: v2.22.0
 # This is the version number of the application being deployed. This version number should be
 # incremented each time you make changes to the application.
-appVersion: v2.17.1
+appVersion: v2.22.0
 dependencies:
   - name: diagrid-dashboard
     version: "0.1.0"

charts/atlantis/values.yaml

@@ -4,7 +4,7 @@
 replicaCount: 1
 image:
   repository: git.oceanbox.io/oceanbox/poseidon/atlantis
-  tag: v2.17.1
+  tag: v2.22.0
   pullPolicy: IfNotPresent
 init:
   enabled: false

charts/codex/Chart.yaml

@@ -13,9 +13,9 @@ type: application
 # This is the chart version. This version number should be incremented each time you make changes
 # to the chart and its templates, including the app version.
 # Versions are expected to follow Semantic Versioning (https://semver.org/)
-version: v2.17.1
+version: v2.22.0
 # This is the version number of the application being deployed. This version number should be
 # incremented each time you make changes to the application. Versions are not expected to
 # follow Semantic Versioning. They should reflect the version the application is using.
 # It is recommended to use it with quotes.
-appVersion: "v2.17.1"
+appVersion: "v2.22.0"

charts/codex/values.yaml

@@ -10,7 +10,7 @@ image:
   # This sets the pull policy for images.
   pullPolicy: IfNotPresent
   # Overrides the image tag whose default is the chart appVersion.
-  tag: v2.17.1
+  tag: v2.22.0
 # This is for the secrets for pulling an image from a private repository more information can be found here: https://kubernetes.io/docs/tasks/configure-pod-container/pull-image-private-registry/
 imagePullSecrets:
   - name: gitlab-pull-secret

charts/sorcerer/Chart.yaml

@@ -4,10 +4,10 @@ description: A Helm chart for Kubernetes
 type: application
 # This is the chart version. This version number should be incremented each time you make changes
 # to the chart and its templates, including the app version.
-version: v2.17.1
+version: v2.22.0
 # This is the version number of the application being deployed. This version number should be
 # incremented each time you make changes to the application.
-appVersion: v2.17.1
+appVersion: v2.22.0
 dependencies:
   - name: diagrid-dashboard
     version: "0.1.0"

charts/sorcerer/values.yaml

@@ -5,7 +5,7 @@
 replicaCount: 1
 image:
   repository: git.oceanbox.io/oceanbox/poseidon/sorcerer
-  tag: v2.17.1
+  tag: v2.22.0
   pullPolicy: IfNotPresent
 init:
   enabled: false

helmfile.d/argo.yaml.gotmpl

@@ -15,7 +15,7 @@ releases:
 - name: argocd
   namespace: argocd
   chart: argo/argo-cd
-  version: 9.5.21
+  version: 9.7.1
   condition: argo.enabled
   values:
   - ../values/argo/values/argocd.yaml.gotmpl
@@ -43,7 +43,7 @@ releases:
 - name: argo-workflows
   namespace: argocd
   chart: argo/argo-workflows
-  version: 1.0.18
+  version: 1.0.19
   condition: argo.workflows.enabled
   missingFileHandler: Info
 - name: manifests

helmfile.d/cert-manager.yaml.gotmpl

@@ -13,7 +13,7 @@ releases:
 - name: cert-manager
   namespace: cert-manager
   chart: cert-manager/cert-manager
-  version: v1.20.2
+  version: v1.21.0
   condition: cert_manager.enabled
   values:
   - ../values/cert-manager/values/cert-manager.yaml.gotmpl

helmfile.d/ingress-haproxy.yaml.gotmpl

@@ -13,7 +13,7 @@ releases:
 - name: ingress-haproxy
   namespace: ingress-haproxy
   chart: haproxytech/kubernetes-ingress
-  version: 1.52.0
+  version: 1.52.1
   condition: haproxy.enabled
   values:
   - ../values/ingress-haproxy/values/ingress-haproxy.yaml.gotmpl

helmfile.d/openfga.yaml.gotmpl

@@ -16,7 +16,7 @@ releases:
   namespace: {{ .Environment.Name }}-openfga
   {{- end }}
   chart: openfga/openfga
-  version: 0.3.9
+  version: 0.3.10
   condition: openfga.enabled
   values:
   - ../values/openfga/values/values.yaml

helmfile.d/postgres-operator.yaml.gotmpl

@@ -27,7 +27,7 @@ releases:
 - name: plugin-barman-cloud
   namespace: cnpg
   chart: cloudnative-pg/plugin-barman-cloud
-  version: 0.6.0
+  version: 0.7.0
   condition: postgres_operator.enabled
   values:
   - ../values/postgres-operator/values/plugin-barman-cloud.yaml.gotmpl

helmfile.d/prometheus.yaml.gotmpl

@@ -15,7 +15,7 @@ releases:
 - name: prometheus
   namespace: prometheus
   chart: prometheus/kube-prometheus-stack
-  version: 86.2.0
+  version: 86.3.2
   condition: prometheus.enabled
   values:
   - ../values/prometheus/values/prometheus.yaml.gotmpl

helmfile.d/proteus.yaml.gotmpl

@@ -15,6 +15,7 @@ releases:
   - ../values/env-{{ requiredEnv "ARGOCD_ENV_CLUSTER_NAME" }}.yaml
   - ../values/proteus/env.yaml.gotmpl
   - ../values/proteus/env-{{ requiredEnv "ARGOCD_ENV_CLUSTER_NAME" }}.yaml.gotmpl
+  - ../values/proteus/values/values-staging.yaml
   hooks:
   - events: [ prepare, cleanup ]
     showlogs: true

helmfile.d/spegel.yaml.gotmpl

@@ -13,7 +13,7 @@ releases:
 - name: spegel
   namespace: spegel
   chart: spegel/spegel
-  version: 0.7.1
+  version: 0.7.3
   condition: spegel.enabled
   values:
   - ../values/spegel/values/spegel.yaml.gotmpl

helmfile.d/umami.yaml.gotmpl

@@ -14,7 +14,7 @@ releases:
 - name: umami
   namespace: analytics
   chart: umami/umami
-  version: 7.9.4
+  version: 7.10.10
   condition: umami.enabled
   values:
   - ../values/umami/values/values.yaml

helmfile.d/uptermd.yaml.gotmpl

@@ -0,0 +1,43 @@
+bases:
+ - ../envs/environments.yaml.gotmpl
+
+repositories:
+- name: upterm
+  url: https://upterm.dev
+
+commonLabels:
+  tier: system
+
+releases:
+- name: uptermd
+  namespace: uptermd
+  chart: upterm/uptermd
+  version: 0.2.0
+  condition: uptermd.enabled
+  values:
+  - ../values/uptermd/values/values.yaml
+  - ../values/uptermd/values/values-{{ .Environment.Name }}.yaml
+  postRenderer: ../bin/kustomizer
+  postRendererArgs:
+  - ../values/uptermd/kustomize/{{ .Environment.Name }}
+  missingFileHandler: Info
+- name: manifests
+  namespace: uptermd
+  chart: manifests
+  condition: uptermd.enabled
+  missingFileHandler: Info
+  values:
+  - ../values/env.yaml
+  - ../values/env-{{ requiredEnv "ARGOCD_ENV_CLUSTER_NAME" }}.yaml
+  - ../values/uptermd/env.yaml.gotmpl
+  - ../values/uptermd/env-{{ requiredEnv "ARGOCD_ENV_CLUSTER_NAME" }}.yaml.gotmpl
+  hooks:
+  - events: [ prepare, cleanup ]
+    showlogs: true
+    command: ../bin/helmify
+    args:
+    - '{{`{{ if eq .Event.Name "prepare" }}build{{ else }}clean{{ end }}`}}'
+    - '{{`{{ .Release.Chart }}`}}'
+    - '{{`{{ .Environment.Name }}`}}'
+    - ../values/uptermd/manifests
+    - manifests

helmfile.d/velero.yaml.gotmpl

@@ -15,7 +15,7 @@ releases:
 - name: velero
   namespace: velero
   chart: velero/velero
-  version: 12.0.3
+  version: 12.1.0
   condition: velero.enabled
   values:
   - ../values/velero/values/velero.yaml.gotmpl

values/argo/env.yaml.gotmpl

@@ -27,5 +27,6 @@ argocd:
     image: "git.oceanbox.io/platform/manifests/helmfile-cmp:latest"
     imagePullSecrets:
       - gitlab-pull-secret
+  webhookSecret: ""
   additional_rbac_settings:
   - g, "eb17a659-4ce6-41bc-9153-d9b117c44479", role:org-admin

values/argo/values/argocd.yaml.gotmpl

@@ -49,8 +49,8 @@ configs:
         name: {{ .name }}
         config:
           issuer: https://login.microsoftonline.com/{{ .tenant }}/v2.0
-          clientID: ${{ .name | replace "-" "_" }}_client_id
-          clientSecret: ${{ .name | replace "-" "_" }}_client_secret
+          clientID: ${{ .secret_ref.name }}:client_id
+          clientSecret: ${{ .secret_ref.name }}:client_secret
           insecureSkipEmailVerified: true
           requestedIDTokenClaims:
             groups:
@@ -62,7 +62,7 @@ configs:
             - email
             - groups
       staticClients:
-      - id: ${{ .name | replace "-" "_" }}_client_id
+      - id: ${{ .secret_ref.name }}:client_id
         name: Kubernetes
         # These are kubectl oidc plugin internal URLs
         redirectURIs:
@@ -99,6 +99,11 @@ configs:
     argo-helm:
       type: helm
       url: https://argoproj.github.io/argo-helm
+  {{- if .Values.argocd.webhookSecret }}
+  secret:
+    extra:
+      webhook.gitea.secret: {{ .Values.argocd.webhookSecret }}
+  {{- end }}
   # UI changes based on env
   styles: |
     /* blue, orange, red depending on env */
@@ -129,29 +134,11 @@ controller:
       cpu: {{ .Values.argocd.resources.controller.cpu  | default "250m" }}
       memory: {{ .Values.argocd.resources.controller.memory  | default "1000Mi" }}
 
-# Mount azure ca as file for SAML auth
 dex:
   metrics:
     enabled: true
     serviceMonitor:
       enabled: true
-  {{- with .Values.clusterConfig.oidc }}
-  env:
-  {{- range . }}
-  {{- if eq .group "devel" }}
-  - name: {{ .name | replace "-" "_" }}_client_secret
-    valueFrom:
-      secretKeyRef:
-        name: {{ .secret_ref.name }}
-        key: client_secret
-  - name: {{ .name | replace "-" "_" }}_client_id
-    valueFrom:
-      secretKeyRef:
-        name: {{ .secret_ref.name }}
-        key: client_id
-  {{- end }}
-  {{- end }}
-  {{- end }}
 
 redis:
   metrics:

values/atlantis/kustomize/staging/actor-config.yaml

@@ -3,10 +3,6 @@ kind: ConfigMap
 metadata:
   name: staging-atlantis-actor-config
 data:
-  XTRACT_IMAGE: "git.oceanbox.io/oceanbox/katamari/excavator:v1.5.1"
-  XTRACT_QUEUE: "dev-queue"
-  PLUME_IMAGE: "git.oceanbox.io/oceanbox/katamari/plume:v1.5.1"
-  PLUME_QUEUE: "dev-queue"
-  TEMPORAL_ADDRESS: "temporal-frontend.temporal:7233"
+  TEMPORAL_ADDRESS: "temporal-grpc.ekman.oceanbox.io:443"
+  TEMPORAL_TLS: "true"
   TEMPORAL_NAMESPACE: "staging-atlantis"
-  TEMPORAL_TASK_QUEUE: "atlantis"

values/atlantis/manifests/network/allow-temporal.yaml

@@ -0,0 +1,18 @@
+{{- if .Values.clusterConfig.cilium.enabled }}
+apiVersion: cilium.io/v2
+kind: CiliumNetworkPolicy
+metadata:
+  name: allow-temporal
+  namespace: {{ .Release.Namespace }}
+spec:
+  endpointSelector:
+    matchLabels:
+      app.kubernetes.io/name: atlantis
+  egress:
+  - toFQDNs:
+    - matchName: temporal-grpc.ekman.oceanbox.io
+    toPorts:
+    - ports:
+      - port: "443"
+        protocol: TCP
+{{- end }}

values/atlantis/values/values-staging.yaml.gotmpl

@@ -1,7 +1,7 @@
 replicaCount: 1
 image:
   repository: git.oceanbox.io/oceanbox/poseidon/atlantis
-  tag: 6442206c-debug
+  tag: 29de0c67-debug
 podAnnotations:
   dapr.io/app-id: "staging-atlantis"
 env:

values/codex/values/values-staging.yaml

@@ -38,4 +38,4 @@ volumeMounts:
     readOnly: true
     subPath: appsettings.json
 image:
-  tag: 6442206c-debug
+  tag: 9138d67d-debug

values/docs/values/values-staging.yaml

@@ -1,6 +1,6 @@
 fullnameOverride: staging-docs
 image:
-  tag: "72b01c0b-debug"
+  tag: "511c128c-debug"
 ingress:
   enabled: true
   className: "haproxy"

values/gitea/values/values.yaml

@@ -3,7 +3,7 @@ replicaCount: 1
 image:
   registry: "docker.gitea.com"
   repository: gitea
-  tag: "1.26.2"
+  tag: "1.26.4"
 
 resources:
   requests:
@@ -75,10 +75,11 @@ gitea:
       USERNAME: "nickname"
     mailer:
       ENABLED: true
-      FROM: "gitea@oceanbox.io"
-      PROTOCOL: "smtp"
-      SMTP_ADDR: "postfix-mail.postfix.svc.cluster.local"
+      FROM: "\"Oceanbox Gitea\" <no-reply@oceanbox.io>"
+      PROTOCOL: "smtp+starttls"
+      SMTP_ADDR: "mx.itpartner.no"
       SMTP_PORT: 587
+      USER: "no-reply@oceanbox.io"
     database:
       DB_TYPE: postgres
       MAX_OPEN_CONNS: 90
@@ -104,6 +105,11 @@ gitea:
         secretKeyRef:
           name: gitea-s3
           key: secret_key
+    - name: GITEA__mailer__PASSWD
+      valueFrom:
+        secretKeyRef:
+          name: gitea-smtp
+          key: password
     - name: GITEA__DATABASE__PASSWD
       valueFrom:
         secretKeyRef:

values/headscale/values/values.yaml

@@ -118,6 +118,7 @@ configMaps:
               "elianne.ersdal@oceanbox.io",
               "hanskristian.djuve@oceanbox.io",
               "erlend.mundal@oceanbox.io",
+              "hanna.fagrell@oceanbox.io",
             ],
             "group:manager": [
               "svenn.hanssen@oceanbox.io",
@@ -130,7 +131,6 @@ configMaps:
             "group:intern": [
               "haavahak@stud.ntnu.no",
               "haavahak@ntnu.no",
-              "hanna.fagrell@oceanbox.io",
             ],
             "group:ceph": [
               "jonas.juselius@oceanbox.io",

values/ingest/manifests/workerdeployment-py.yaml

@@ -19,7 +19,7 @@ spec:
         runAsGroup: 0
       containers:
         - name: ingest-py
-          image: git.oceanbox.io/oceanbox/churn/ingest-py:v2.3.11
+          image: git.oceanbox.io/oceanbox/churn/ingest-py:v0.1.6
           resources:
             requests:
               memory: 512Mi

values/ingest/manifests/workerdeployment.yaml

@@ -19,7 +19,7 @@ spec:
         runAsGroup: 0
       containers:
         - name: ingest
-          image: git.oceanbox.io/oceanbox/churn/ingest:v2.3.11
+          image: git.oceanbox.io/oceanbox/churn/ingest:v0.1.6
           resources:
             requests:
               memory: 512Mi

values/makai/values/values.yaml

@@ -1,6 +1,6 @@
 replicaCount: 1
 image:
-  tag: "7080a0bd-debug"
+  tag: "e926ae4b-debug"
 env:
   - name: APP_VERSION
     value: "0.0.0"

values/proteus/manifests/network.yaml

@@ -16,9 +16,6 @@ spec:
     - ports:
       - port: "7233"
         protocol: TCP
-  # k8s API server (for batch/v1 Job create/poll/delete)
-  - toEntities:
-    - kube-apiserver
   # DNS
   - toEndpoints:
     - matchLabels:
@@ -30,15 +27,11 @@ spec:
         protocol: UDP
       - port: "53"
         protocol: TCP
-  # RabbitMQ on oceanbox: NodePorts (30672/31672) or MetalLB IPs on standard port 5672
+  # OTel collector (tos1 LoadBalancer 10.255.241.12) for Temporal traces, exported cross-cluster
   - toCIDR:
-    - 10.255.241.0/24
+    - 10.255.241.12/32
     toPorts:
     - ports:
-      - port: "5672"
-        protocol: TCP
-      - port: "30672"
-        protocol: TCP
-      - port: "31672"
+      - port: "4317"
         protocol: TCP
 {{- end }}

values/proteus/manifests/pvc.yaml

@@ -0,0 +1,37 @@
+apiVersion: v1
+kind: PersistentVolume
+metadata:
+  name: pv-proteus-ceph-archives
+spec:
+  accessModes:
+  - ReadWriteMany
+  capacity:
+    storage: 1Gi
+  csi:
+    driver: rook-ceph.cephfs.csi.ceph.com
+    nodeStageSecretRef:
+      name: rook-csi-cephfs-node
+      namespace: rook-ceph
+    volumeAttributes:
+      clusterID: rook-ceph
+      fsName: data
+      rootPath: /
+      staticVolume: "true"
+    volumeHandle: pv-proteus-ceph-archives
+  persistentVolumeReclaimPolicy: Retain
+  volumeMode: Filesystem
+---
+apiVersion: v1
+kind: PersistentVolumeClaim
+metadata:
+  name: proteus-ceph-archives
+  namespace: proteus
+spec:
+  accessModes:
+  - ReadWriteMany
+  resources:
+    requests:
+      storage: 1Gi
+  storageClassName: ""
+  volumeMode: Filesystem
+  volumeName: pv-proteus-ceph-archives

values/proteus/manifests/rbac.yaml

@@ -1,55 +0,0 @@
-# TODO: the SA the temporal-worker-controller assigns to the pod (assumed `default`).
----
-apiVersion: rbac.authorization.k8s.io/v1
-kind: Role
-metadata:
-  name: proteus-dev-queue
-  namespace: dev-queue
-rules:
-  - apiGroups: ["batch"]
-    resources: ["jobs"]
-    verbs: ["create", "delete", "get", "list", "watch"]
-  - apiGroups: [""]
-    resources: ["pods", "pods/log"]
-    verbs: ["get", "list"]
----
-apiVersion: rbac.authorization.k8s.io/v1
-kind: RoleBinding
-metadata:
-  name: proteus-dev-queue
-  namespace: dev-queue
-roleRef:
-  apiGroup: rbac.authorization.k8s.io
-  kind: Role
-  name: proteus-dev-queue
-subjects:
-  - kind: ServiceAccount
-    name: default
-    namespace: proteus
----
-apiVersion: rbac.authorization.k8s.io/v1
-kind: Role
-metadata:
-  name: proteus-prod-queue
-  namespace: prod-queue
-rules:
-  - apiGroups: ["batch"]
-    resources: ["jobs"]
-    verbs: ["create", "delete", "get", "list", "watch"]
-  - apiGroups: [""]
-    resources: ["pods", "pods/log"]
-    verbs: ["get", "list"]
----
-apiVersion: rbac.authorization.k8s.io/v1
-kind: RoleBinding
-metadata:
-  name: proteus-prod-queue
-  namespace: prod-queue
-roleRef:
-  apiGroup: rbac.authorization.k8s.io
-  kind: Role
-  name: proteus-prod-queue
-subjects:
-  - kind: ServiceAccount
-    name: default
-    namespace: proteus

values/proteus/manifests/workerdeployment.yaml

@@ -1,14 +1,10 @@
-# TEMPORAL_NAMESPACE  : {env}-atlantis
-# ARCHIVE_PVC                             : the queue's archive PVC (prod+beta -> prod-queue, staging -> dev-queue)
-# Status/inbox/quota now flow via Temporal activities to the Atlantis notify worker; no RabbitMQ.
-# ---
 # apiVersion: temporal.io/v1alpha1
 # kind: WorkerDeployment
 # metadata:
 #   name: proteus-prod
 #   namespace: proteus
 # spec:
-#   replicas: 1
+#   replicas: 2
 #   workerOptions:
 #     temporalNamespace: prod-atlantis
 #     connectionRef:
@@ -21,14 +17,20 @@
 #       securityContext:
 #         runAsUser: 0
 #         runAsGroup: 0
+#       volumes:
+#         - name: archives
+#           persistentVolumeClaim:
+#             claimName: proteus-ceph-archives
 #       containers:
 #         - name: proteus
-#           image: git.oceanbox.io/oceanbox/poseidon/proteus:CHANGEME
+#           image: git.oceanbox.io/oceanbox/poseidon/proteus:v2.17.0
 #           resources:
 #             requests:
-#               memory: 256Mi
-#             limits:
+#               cpu: "1"
 #               memory: 1Gi
+#             limits:
+#               cpu: "2"
+#               memory: 4Gi
 #           env:
 #             - name: TEMPORAL_TASK_QUEUES
 #               value: plume,xtract
@@ -38,6 +40,32 @@
 #               value: prod
 #             - name: ARCHIVE_PVC
 #               value: prod-queue-ceph-archives
+#             - name: MAX_CONCURRENT_ACTIVITIES
+#               value: "2"
+#             - name: OTEL_EXPORTER_OTLP_ENDPOINT
+#               value: http://10.255.241.12:4317
+#           volumeMounts:
+#             - name: archives
+#               mountPath: /data
+#           ports:
+#             - name: health
+#               containerPort: 8080
+#           livenessProbe:
+#             httpGet:
+#               path: /healthz
+#               port: health
+#             initialDelaySeconds: 20
+#             periodSeconds: 15
+#             timeoutSeconds: 5
+#             failureThreshold: 6
+#           readinessProbe:
+#             httpGet:
+#               path: /readyz
+#               port: health
+#             initialDelaySeconds: 5
+#             periodSeconds: 15
+#             timeoutSeconds: 5
+#             failureThreshold: 3
 # ---
 # apiVersion: temporal.io/v1alpha1
 # kind: WorkerDeployment
@@ -73,10 +101,9 @@
 #               value: beta-atlantis
 #             - name: APP_ENV
 #               value: beta
-#             # beta schedules into prod-queue (same as prod), so the same archive PVC.
 #             - name: ARCHIVE_PVC
 #               value: prod-queue-ceph-archives
-# ---
+---
 apiVersion: temporal.io/v1alpha1
 kind: WorkerDeployment
 metadata:
@@ -96,20 +123,48 @@ spec:
       securityContext:
         runAsUser: 0
         runAsGroup: 0
+      volumes:
+        - name: archives
+          persistentVolumeClaim:
+            claimName: proteus-ceph-archives
       containers:
         - name: proteus
-          image: git.oceanbox.io/oceanbox/poseidon/proteus:v2.17.0
+          image: "{{ .Values.image.repository }}:{{ .Values.image.tag }}"
           resources:
             requests:
-              memory: 256Mi
-            limits:
+              cpu: 500m
               memory: 1Gi
+            limits:
+              cpu: "2"
+              memory: 4Gi
           env:
             - name: TEMPORAL_TASK_QUEUES
               value: plume,xtract
             - name: TEMPORAL_NAMESPACE
               value: staging-atlantis
-            - name: APP_ENV
-              value: staging
-            - name: ARCHIVE_PVC
-              value: dev-queue-ceph-archives
+            - name: MAX_CONCURRENT_ACTIVITIES
+              value: "10"
+            - name: OTEL_EXPORTER_OTLP_ENDPOINT
+              value: http://10.255.241.12:4317
+          volumeMounts:
+            - name: archives
+              mountPath: /data
+          ports:
+            - name: health
+              containerPort: 8080
+          livenessProbe:
+            httpGet:
+              path: /healthz
+              port: health
+            initialDelaySeconds: 20
+            periodSeconds: 15
+            timeoutSeconds: 5
+            failureThreshold: 6
+          readinessProbe:
+            httpGet:
+              path: /readyz
+              port: health
+            initialDelaySeconds: 5
+            periodSeconds: 15
+            timeoutSeconds: 5
+            failureThreshold: 3

values/proteus/values/values-staging.yaml

@@ -0,0 +1,3 @@
+image:
+  repository: git.oceanbox.io/oceanbox/poseidon/proteus
+  tag: 7b97e45c-debug

values/sorcerer/kustomize/staging-ekman/deployment_patch.yaml

@@ -22,9 +22,4 @@
   value:
     secretRef:
       name: staging-sorcerer-env
-- op: add
-  path: /spec/template/spec/containers/0/envFrom/-
-  value:
-    configMapRef:
-      name: staging-sorcerer-kueue-config
 

values/sorcerer/kustomize/staging-ekman/kueue-config.yaml

@@ -1,7 +0,0 @@
-apiVersion: v1
-kind: ConfigMap
-metadata:
-  name: staging-sorcerer-kueue-config
-data:
-  KUEUE_NAMESPACE: "dev-queue"
-  KUEUE_ARCHIVE_PVC: "dev-queue-ceph-archives"

values/sorcerer/kustomize/staging-ekman/kustomization.yaml

@@ -19,7 +19,6 @@ resources:
 - configurations.yaml
 - keyvault.yaml
 - rbac.yaml
-- kueue-config.yaml
 - secretstore.yaml
 - statestore.yaml
 - tracing.yaml

values/sorcerer/kustomize/staging-ekman/rbac.yaml

@@ -8,7 +8,6 @@ rules:
   - ""
   resourceNames:
   - staging-sorcerer-appsettings
-  - staging-sorcerer-kueue-config
   resources:
   - configmaps
   verbs:
@@ -24,24 +23,6 @@ rules:
   verbs:
   - get
   - watch
-- apiGroups:
-  - jobset.x-k8s.io
-  resources:
-  - jobsets
-  verbs:
-  - create
-  - delete
-  - get
-  - list
-  - watch
-- apiGroups:
-  - ""
-  resources:
-  - pods
-  - pods/log
-  verbs:
-  - get
-  - list
 ---
 apiVersion: rbac.authorization.k8s.io/v1
 kind: RoleBinding

values/sorcerer/values/values-staging.yaml

@@ -1,7 +1,7 @@
 replicaCount: 1
 image:
   repository: git.oceanbox.io/oceanbox/poseidon/sorcerer
-  tag: 6442206c-debug
+  tag: 9138d67d-debug
 podAnnotations:
   dapr.io/enabled: "true"
   dapr.io/app-id: "staging-sorcerer"

values/system/hel1/network/allow-itpartner-mail-egress.yaml

@@ -0,0 +1,17 @@
+{{- if .Values.clusterConfig.cilium.enabled }}
+apiVersion: cilium.io/v2
+kind: CiliumClusterwideNetworkPolicy
+metadata:
+  name: allow-itpartner-mail-egress
+spec:
+  endpointSelector: {}
+  egress:
+  - toFQDNs:
+    - matchName: mx.itpartner.no
+    toPorts:
+    - ports:
+      - port: "587"
+        protocol: TCP
+      - port: "465"
+        protocol: TCP
+{{- end }}

values/temporal/env-ekman.yaml.gotmpl

@@ -1,6 +1,6 @@
 temporal:
   enabled: true
-  autosync: false
+  autosync: true
   ingress: true
   grpcIngress: true
   workerController: true

values/temporal/manifests/ingress.yaml

@@ -8,6 +8,8 @@ metadata:
     cert-manager.io/cluster-issuer: {{ .Values.clusterConfig.ingress_clusterissuer }}
     nginx.ingress.kubernetes.io/backend-protocol: HTTP
     nginx.ingress.kubernetes.io/ssl-redirect: "true"
+    nginx.ingress.kubernetes.io/proxy-buffer-size: "16k"
+    nginx.ingress.kubernetes.io/proxy-busy-buffers-size: "24k"
     oceanbox.io/expose: internal
   labels:
     app.kubernetes.io/name: temporal

values/temporal/manifests/network/temporal-policies.yaml

@@ -60,4 +60,19 @@ spec:
         protocol: UDP
       - port: "53"
         protocol: TCP
+---
+apiVersion: cilium.io/v2
+kind: CiliumNetworkPolicy
+metadata:
+  name: allow-web-oidc-login
+  namespace: temporal
+spec:
+  description: Allow Temporal Web UI OIDC login to Entra ID
+  endpointSelector:
+    matchLabels:
+      app.kubernetes.io/component: web
+  egress:
+  - toFQDNs:
+    - matchName: login.microsoftonline.com
+    - matchPattern: '*.microsoftonline.com'
 {{- end }}

values/temporal/manifests/temporal-db.yaml

@@ -12,9 +12,20 @@ spec:
     initdb:
       database: temporal
       owner: temporal
+  # headroom for ~240 server connections (30/pod x 8 pods) plus CNPG's own
+  postgresql:
+    parameters:
+      max_connections: "300"
+  resources:
+    requests:
+      cpu: 500m
+      memory: 1Gi
+    limits:
+      cpu: "2"
+      memory: 2Gi
   storage:
     resizeInUseVolumes: true
-    size: 10Gi
+    size: 20Gi
 ---
 apiVersion: postgresql.cnpg.io/v1
 kind: Database

values/temporal/values/temporal.yaml

@@ -1,8 +1,11 @@
 server:
+  replicaCount: 2
   config:
+    logLevel: "info"
     persistence:
       defaultStore: default
       visibilityStore: visibility
+      # immutable after first deploy
       numHistoryShards: 512
       datastores:
         default:
@@ -20,7 +23,7 @@ server:
             maxConns: 20
             maxIdleConns: 20
             maxConnLifetime: "1h"
-        # TODO: migrate visibility to Elasticsearch for advanced visibility search.
+        # NOTE: Postgres 12+ gives advanced visibility; no Elasticsearch needed.
         visibility:
           sql:
             createDatabase: false
@@ -41,8 +44,129 @@ server:
         timerType: histogram
         listenAddress: "0.0.0.0:9090"
 
+  metrics:
+    serviceMonitor:
+      enabled: true
+      interval: 30s
+
+  resources:
+    requests:
+      cpu: 250m
+      memory: 512Mi
+    limits:
+      cpu: "1"
+      memory: 1Gi
+
+  frontend:
+    podDisruptionBudget:
+      maxUnavailable: 1
+    topologySpreadConstraints:
+    - maxSkew: 1
+      topologyKey: kubernetes.io/hostname
+      whenUnsatisfiable: ScheduleAnyway
+      labelSelector:
+        matchLabels:
+          app.kubernetes.io/name: temporal
+          app.kubernetes.io/instance: temporal
+          app.kubernetes.io/component: frontend
+
+  history:
+    resources:
+      requests:
+        cpu: 250m
+        memory: 768Mi
+      limits:
+        cpu: "1"
+        memory: 1536Mi
+    podDisruptionBudget:
+      maxUnavailable: 1
+    topologySpreadConstraints:
+    - maxSkew: 1
+      topologyKey: kubernetes.io/hostname
+      whenUnsatisfiable: ScheduleAnyway
+      labelSelector:
+        matchLabels:
+          app.kubernetes.io/name: temporal
+          app.kubernetes.io/instance: temporal
+          app.kubernetes.io/component: history
+
+  matching:
+    podDisruptionBudget:
+      maxUnavailable: 1
+    topologySpreadConstraints:
+    - maxSkew: 1
+      topologyKey: kubernetes.io/hostname
+      whenUnsatisfiable: ScheduleAnyway
+      labelSelector:
+        matchLabels:
+          app.kubernetes.io/name: temporal
+          app.kubernetes.io/instance: temporal
+          app.kubernetes.io/component: matching
+
+  worker:
+    podDisruptionBudget:
+      maxUnavailable: 1
+    topologySpreadConstraints:
+    - maxSkew: 1
+      topologyKey: kubernetes.io/hostname
+      whenUnsatisfiable: ScheduleAnyway
+      labelSelector:
+        matchLabels:
+          app.kubernetes.io/name: temporal
+          app.kubernetes.io/instance: temporal
+          app.kubernetes.io/component: worker
+
+# no persistent debug pod; use temporalio/admin-tools on demand
+admintools:
+  enabled: false
+
 web:
   enabled: true
+  replicaCount: 2
+  resources:
+    requests:
+      cpu: 50m
+      memory: 128Mi
+    limits:
+      cpu: 250m
+      memory: 256Mi
+  podDisruptionBudget:
+    maxUnavailable: 1
+  topologySpreadConstraints:
+  - maxSkew: 1
+    topologyKey: kubernetes.io/hostname
+    whenUnsatisfiable: ScheduleAnyway
+    labelSelector:
+      matchLabels:
+        app.kubernetes.io/name: temporal
+        app.kubernetes.io/instance: temporal
+        app.kubernetes.io/component: web
+  # NOTE: native OIDC SSO via Entra ID (same oceanbox-oidc secret as Grafana); gates UI login only
+  additionalEnv:
+    - name: TEMPORAL_AUTH_ENABLED
+      value: "true"
+    - name: TEMPORAL_AUTH_TYPE
+      value: "oidc"
+    - name: TEMPORAL_AUTH_PROVIDER_URL
+      value: "https://login.microsoftonline.com/3f737008-e9a0-4485-9d27-40329d288089/v2.0"
+    - name: TEMPORAL_AUTH_CLIENT_ID
+      valueFrom:
+        secretKeyRef:
+          name: oceanbox-oidc
+          key: client_id
+    - name: TEMPORAL_AUTH_CLIENT_SECRET
+      valueFrom:
+        secretKeyRef:
+          name: oceanbox-oidc
+          key: client_secret
+    - name: TEMPORAL_AUTH_CALLBACK_URL
+      value: "https://temporal.ekman.oceanbox.io/auth/sso/callback"
+    - name: TEMPORAL_AUTH_SCOPES
+      value: "openid,profile,email,offline_access"
 
 schema:
   useHelmHooks: false
+  # NOTE: run as an ArgoCD sync hook so the controller-mutated Job isn't diffed and stays OutOfSync forever
+  jobAnnotations:
+    argocd.argoproj.io/hook: Sync
+    argocd.argoproj.io/hook-delete-policy: BeforeHookCreation

values/uptermd/env-hel1.yaml.gotmpl

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

values/uptermd/env.yaml.gotmpl

@@ -0,0 +1,3 @@
+uptermd:
+  enabled: false
+  autosync: false

values/uptermd/kustomize/base/kustomization.yaml

@@ -0,0 +1,4 @@
+apiVersion: kustomize.config.k8s.io/v1beta1
+kind: Kustomization
+resources:
+  - _manifest.yaml

values/uptermd/kustomize/default/kustomization.yaml

@@ -0,0 +1,24 @@
+apiVersion: kustomize.config.k8s.io/v1beta1
+kind: Kustomization
+resources:
+  - ../base
+patches:
+  - target:
+      kind: Ingress
+      name: uptermd
+    patch: |
+      $patch: delete
+      apiVersion: networking.k8s.io/v1
+      kind: Ingress
+      metadata:
+        name: uptermd
+  - target:
+      group: cert-manager.io
+      kind: Issuer
+      name: uptermd-letsencrypt
+    patch: |
+      $patch: delete
+      apiVersion: cert-manager.io/v1
+      kind: Issuer
+      metadata:
+        name: uptermd-letsencrypt

values/uptermd/manifests/ingress.yaml

@@ -0,0 +1,30 @@
+apiVersion: networking.k8s.io/v1
+kind: Ingress
+metadata:
+  name: uptermd
+  namespace: uptermd
+  labels:
+    app.kubernetes.io/name: uptermd
+  annotations:
+    cert-manager.io/cluster-issuer: ca-issuer
+    haproxy.org/backend-protocol: h1
+    haproxy.org/timeout-tunnel: "3600s"
+    haproxy.org/timeout-client: "3600s"
+    haproxy.org/timeout-server: "3600s"
+spec:
+  ingressClassName: haproxy
+  rules:
+    - host: upterm.hel1.obx
+      http:
+        paths:
+          - path: /
+            pathType: Prefix
+            backend:
+              service:
+                name: uptermd
+                port:
+                  number: 80
+  tls:
+    - hosts:
+        - upterm.hel1.obx
+      secretName: uptermd-tls

values/uptermd/manifests/uptermd.yaml

@@ -0,0 +1,37 @@
+{{- if .Values.clusterConfig.argo.enabled }}
+apiVersion: argoproj.io/v1alpha1
+kind: Application
+metadata:
+  name: uptermd
+  namespace: argocd
+spec:
+  destination:
+    namespace: uptermd
+    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: uptermd.yaml.gotmpl
+  project: sys
+  syncPolicy:
+    managedNamespaceMetadata:
+      labels:
+        component: sys
+    syncOptions:
+      - CreateNamespace=true
+      - ApplyOutOfSyncOnly=true
+      - ServerSideApply=true
+    {{- if .Values.uptermd.autosync }}
+    automated:
+      prune: true
+    {{- end }}
+{{- end }}

values/uptermd/values/values.yaml

@@ -0,0 +1,20 @@
+replicaCount: 1
+
+websocket:
+  enabled: true
+
+service:
+  type: ClusterIP
+
+resources:
+  limits:
+    memory: 512Mi
+  requests:
+    cpu: 100m
+    memory: 512Mi
+
+# No SSH host key is provided, so uptermd generates an ephemeral one on each
+# pod start
+host_keys: {}
+
+authorized_keys: []