Automated upload for dev.t09.de

otc/dev.t09.de/stacks/ci-sizer/sizer-receiver/deployment.yaml

@@ -62,7 +62,7 @@ spec:
             - name: RECEIVER_SESSION_TTL
               value: "12h"
             - name: RECEIVER_ALLOWED_ORG
-              value: "giteaAdmin"
+              value: "DevFW-CICD"
             - name: RECEIVER_CPU_SIZING_MODE
               value: "observe"
             - name: RECEIVER_MEMORY_QOS

otc/dev.t09.de/stacks/ci-sizer/sizer-receiver/secret.yaml

@@ -1,9 +0,0 @@
-apiVersion: v1
-kind: Secret
-metadata:
-  name: sizer-oidc-client
-  labels:
-    app: sizer-receiver
-type: Opaque
-stringData:
-  client-secret: "73eda9068bd00dfe67d29f087b5540cb1cd82cc1dd2ac0f838558ac8bbcfcb3a"

otc/dev.t09.de/stacks/core/dex.yaml

@@ -27,6 +27,3 @@ spec:
     - repoURL: https://edp.buildth.ing/DevFW-CICD/stacks-instances
       targetRevision: HEAD
       ref: values
-    - repoURL: https://edp.buildth.ing/DevFW-CICD/stacks-instances
-      targetRevision: HEAD
-      path: "otc/dev.t09.de/stacks/core/dex/manifests"

otc/dev.t09.de/stacks/core/dex/manifests/dex-sizer-client.yaml

@@ -1,8 +0,0 @@
-apiVersion: v1
-kind: Secret
-metadata:
-  name: dex-sizer-client
-  namespace: dex
-type: Opaque
-stringData:
-  clientSecret: "73eda9068bd00dfe67d29f087b5540cb1cd82cc1dd2ac0f838558ac8bbcfcb3a"

otc/dev.t09.de/stacks/forgejo/forgejo-server/values.yaml

@@ -1,3 +1,4 @@
+
 # We use recreate to make sure only one instance with one version is running, because Forgejo might break or data gets inconsistant.
 strategy:
   type: Recreate
@@ -173,8 +174,10 @@ service:
 
 image:
   pullPolicy: "IfNotPresent"
-  # DB has v15a/v15b migrations from workflow-webhook build.
-  # Using that image until a proper v15+ EDP release is cut.
-  fullOverride: edp.buildth.ing/devfw-cicd/edp-forgejo:workflow-webhook-20260305
+  # Overrides the image tag whose default is the chart appVersion.
+  #tag: "8.0.3"
+  # Adds -rootless suffix to image name
+  # rootless: true
+  fullOverride: edp.buildth.ing/devfw-cicd/edp-forgejo:14.0.2-edp1-rootless
 
 forgejo: {}

otc/dev.t09.de/stacks/garm/garm/values.yaml

@@ -26,9 +26,7 @@ credentials:
 
 image:
   repository: edp.buildth.ing/devfw-cicd/garm-forgejo
-  # NOTE: v0.1.7-forgejo-23 has exec format error (wrong arch build)
-  # Rolled back to -22 until -23 is rebuilt for amd64
-  tag: v0.1.7-forgejo-22
+  tag: v0.1.7-forgejo-23
 
 providerConfig:
   edgeConnect:

otc/dev.t09.de/stacks/observability/victoria-k8s-stack/manifests/backup-alerts.yaml

@@ -0,0 +1,78 @@
+apiVersion: operator.victoriametrics.com/v1beta1
+kind: VMRule
+metadata:
+  name: backup-alerts
+  namespace: observability
+spec:
+  groups:
+    - name: backup-schedule-staleness
+      rules:
+        - alert: BackupCronJobNotScheduled
+          expr: |
+            time() - kube_cronjob_status_last_schedule_time{cronjob=~"forgejo-s3-backup|secrets-backup", namespace="gitea"}
+            > 26 * 3600
+          for: 5m
+          labels:
+            severity: critical
+            cronjob: "{{ $labels.cronjob }}"
+          annotations:
+            value: "{{ $value | humanizeDuration }}"
+            description: >-
+              CronJob {{ $labels.namespace }}/{{ $labels.cronjob }} has not been
+              scheduled for over 26 hours in cluster {{ $labels.cluster_environment }}.
+              Last schedule was {{ $value | humanizeDuration }} ago.
+            summary: "Backup CronJob {{ $labels.cronjob }} is stale"
+
+        - alert: BackupCronJobNeverScheduled
+          expr: |
+            kube_cronjob_status_last_schedule_time{cronjob=~"forgejo-s3-backup|secrets-backup", namespace="gitea"}
+            == 0
+          for: 30m
+          labels:
+            severity: critical
+            cronjob: "{{ $labels.cronjob }}"
+          annotations:
+            description: >-
+              CronJob {{ $labels.namespace }}/{{ $labels.cronjob }} has never been
+              scheduled in cluster {{ $labels.cluster_environment }}.
+            summary: "Backup CronJob {{ $labels.cronjob }} never ran"
+
+    - name: backup-job-failures
+      rules:
+        - alert: BackupJobFailed
+          expr: |
+            max by(cluster_environment, namespace, job_name) (
+              kube_job_status_failed{job_name=~"forgejo-s3-backup-.*|secrets-backup-.*", namespace="gitea"}
+            ) > 0
+          for: 30s
+          labels:
+            severity: critical
+            job_name: "{{ $labels.job_name }}"
+          annotations:
+            value: "{{ $value }}"
+            description: >-
+              Backup job {{ $labels.namespace }}/{{ $labels.job_name }} has
+              {{ $value }} failed pod(s) in cluster {{ $labels.cluster_environment }}.
+            summary: "Backup job {{ $labels.job_name }} failed"
+
+    - name: backup-job-duration
+      rules:
+        - alert: BackupJobTooSlow
+          expr: |
+            (
+              time() - kube_job_status_start_time{job_name=~"forgejo-s3-backup-.*|secrets-backup-.*", namespace="gitea"}
+            ) > 300
+            and
+            kube_job_status_active{job_name=~"forgejo-s3-backup-.*|secrets-backup-.*", namespace="gitea"} > 0
+          for: 1m
+          labels:
+            severity: major
+            job_name: "{{ $labels.job_name }}"
+          annotations:
+            value: "{{ $value | humanizeDuration }}"
+            description: >-
+              Backup job {{ $labels.namespace }}/{{ $labels.job_name }} has been
+              running for {{ $value | humanizeDuration }} (threshold: 5m)
+              in cluster {{ $labels.cluster_environment }}. This may indicate a
+              hung process or connectivity issue.
+            summary: "Backup job {{ $labels.job_name }} running too long"