- Move flat service manifests into structured subdirs (apps/, bootstrap-jobs/, repair-jobs/, migration-jobs/, validation-jobs/, node-ops/, networking/) - Retire oneoffs/ directories across services - Remove oceanus cluster and its host roles; add aether cluster + terraform scaffolding - Reorganize scripts/ into ops/, render/, sync/, manual-tests/ - Add Makefile with render/validate/test/flux targets and repo-structure tests - Update flux-system application CRs to the new paths - Add hermes-automated-triage-24h-plan knowledge doc (+ comms mirror) - Refresh knowledge catalogs, dashboards, vmalert rules, quality contract Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
54 lines
1.6 KiB
YAML
54 lines
1.6 KiB
YAML
# services/maintenance/node-ops/image-sweeper-cronjob.yaml
|
|
apiVersion: batch/v1
|
|
kind: CronJob
|
|
metadata:
|
|
name: image-sweeper
|
|
namespace: maintenance
|
|
spec:
|
|
schedule: "30 4 * * 0"
|
|
suspend: true
|
|
concurrencyPolicy: Forbid
|
|
successfulJobsHistoryLimit: 2
|
|
failedJobsHistoryLimit: 2
|
|
jobTemplate:
|
|
spec:
|
|
template:
|
|
spec:
|
|
serviceAccountName: node-image-sweeper
|
|
restartPolicy: OnFailure
|
|
nodeSelector:
|
|
kubernetes.io/os: linux
|
|
kubernetes.io/arch: arm64
|
|
node-role.kubernetes.io/worker: "true"
|
|
tolerations:
|
|
- key: node-role.kubernetes.io/control-plane
|
|
operator: Exists
|
|
effect: NoSchedule
|
|
- key: node-role.kubernetes.io/master
|
|
operator: Exists
|
|
effect: NoSchedule
|
|
containers:
|
|
- name: image-sweeper
|
|
image: python:3.12.9-alpine3.20
|
|
command: ["/bin/sh", "/scripts/node_image_sweeper.sh"]
|
|
env:
|
|
- name: ONE_SHOT
|
|
value: "true"
|
|
securityContext:
|
|
privileged: true
|
|
runAsUser: 0
|
|
volumeMounts:
|
|
- name: host-root
|
|
mountPath: /host
|
|
- name: script
|
|
mountPath: /scripts
|
|
readOnly: true
|
|
volumes:
|
|
- name: host-root
|
|
hostPath:
|
|
path: /
|
|
- name: script
|
|
configMap:
|
|
name: node-image-sweeper-script
|
|
defaultMode: 0555
|