stack.basicstack.de/apps/monitoring/backup-k8s-resources-cronjob.yaml
CTO Agent e434fa751b feat(monitoring): backup-k8s-resources → restic --stdin to Hetzner S3 (DEV-487)
Rewrites the backup-k8s-resources CronJob to drop the local-path tarball
path and stream a YAML dump through `restic backup --stdin` into
`hetzner-s3:${BUCKET}/restic/k8s-resources`. Uses a two-container pattern:
init `alpine/k8s:1.29.4` dumps into an emptyDir, main `restic/restic:0.17.3`
reads that file on stdin. Retains `serviceAccountName: backup-sa`, drops
the `k3s-worker-2` nodeSelector (no more local-path pin), matches sibling
loki/grafana jobs on retention, `restic check --read-data-subset=5%`, and
textfile metrics (`backup_k8s_resources_success` / `_timestamp_seconds` /
`_check_status`).

Deployed in parallel with the legacy `backup-volumes` CronJob — the
`backup-storage` PVC keeps serving `backup-volumes` until DEV-482 step 6
(restore drill).

Server-side dry-run validated on the k3s control plane.

Co-Authored-By: Paperclip <noreply@paperclip.ing>
2026-08-16 15:39:06 +00:00

192 lines
7 KiB
YAML

---
# Kubernetes-resource backup via restic to Hetzner Object Storage
# (DEV-487, DEV-482 Option 4). Step 4 of the Option 4 rollout.
#
# Streams a concatenated YAML dump of cluster-scoped and per-namespace
# resources through `restic backup --stdin` into
# `s3:${S3_ENDPOINT}/${S3_BUCKET}/restic/k8s-resources`. No PVC mount
# (drops the local-path `backup-storage` dependency), no node pin.
#
# Two-container pattern:
# 1. `kubectl-dump` init container (`alpine/k8s:1.29.4`) writes
# /dump/cluster.yaml into an emptyDir. Uses `serviceAccountName:
# backup-sa` (unchanged from the legacy job).
# 2. `restic` main container (`restic/restic:0.17.3`, matches the
# loki/grafana siblings) reads that file on stdin and streams it
# into the restic repo with `--stdin-filename cluster.yaml`.
#
# Deployed in parallel with the legacy `backup-volumes` CronJob — do
# not retire that job or the `backup-storage` PVC until DEV-482 step 6
# (restore drill) has passed.
apiVersion: batch/v1
kind: CronJob
metadata:
name: backup-k8s-resources
namespace: monitoring
labels:
app: backup
type: k8s-resources
backend: restic
spec:
schedule: "0 2 * * *"
concurrencyPolicy: Forbid
successfulJobsHistoryLimit: 3
failedJobsHistoryLimit: 3
jobTemplate:
metadata:
labels:
app: backup
type: k8s-resources
backend: restic
spec:
backoffLimit: 2
activeDeadlineSeconds: 3600
template:
metadata:
labels:
app: backup
type: k8s-resources
backend: restic
spec:
restartPolicy: OnFailure
serviceAccountName: backup-sa
initContainers:
- name: kubectl-dump
image: alpine/k8s:1.29.4
command:
- /bin/sh
- -c
- |
set -eu
echo "=== kubectl-dump started at $(date -u +%FT%TZ) ==="
DUMP=/dump/cluster.yaml
: > "${DUMP}"
echo "--- namespaces ---"
kubectl get namespaces -o yaml >> "${DUMP}"
echo "---" >> "${DUMP}"
echo "--- cluster-scoped resources ---"
kubectl get persistentvolumes,storageclasses,clusterroles,clusterrolebindings \
-o yaml >> "${DUMP}"
echo "---" >> "${DUMP}"
echo "--- namespaced resources ---"
for ns in $(kubectl get namespaces -o jsonpath='{.items[*].metadata.name}'); do
echo " ns=${ns}"
kubectl get \
configmaps,secrets,services,deployments,statefulsets,daemonsets,jobs,cronjobs,ingresses,persistentvolumeclaims \
-n "${ns}" -o yaml >> "${DUMP}" 2>/dev/null || true
echo "---" >> "${DUMP}"
done
echo "dump size: $(wc -c < ${DUMP}) bytes"
echo "=== kubectl-dump finished at $(date -u +%FT%TZ) ==="
resources:
requests:
cpu: 50m
memory: 128Mi
limits:
cpu: 500m
memory: 512Mi
volumeMounts:
- name: dump
mountPath: /dump
containers:
- name: restic
image: restic/restic:0.17.3
env:
- name: AWS_ACCESS_KEY_ID
valueFrom:
secretKeyRef:
name: monitoring-s3-backup
key: access-key
- name: AWS_SECRET_ACCESS_KEY
valueFrom:
secretKeyRef:
name: monitoring-s3-backup
key: secret-key
- name: RESTIC_PASSWORD
valueFrom:
secretKeyRef:
name: monitoring-s3-backup
key: restic-password
- name: S3_ENDPOINT
valueFrom:
secretKeyRef:
name: monitoring-s3-backup
key: endpoint
- name: S3_BUCKET
valueFrom:
secretKeyRef:
name: monitoring-s3-backup
key: bucket
- name: RESTIC_REPOSITORY
value: "s3:$(S3_ENDPOINT)/$(S3_BUCKET)/restic/k8s-resources"
command:
- /bin/sh
- -c
- |
set -eu
echo "=== backup-k8s-resources-restic started at $(date -u +%FT%TZ) ==="
echo "Repository: ${RESTIC_REPOSITORY}"
# First-run tolerance: init if the repo isn't there yet.
if restic snapshots >/dev/null 2>&1; then
echo "Repo exists, skipping init."
else
echo "Repo missing, initialising..."
restic init
fi
echo "--- restic backup --stdin cluster.yaml ---"
restic backup --stdin \
--stdin-filename cluster.yaml \
--tag k8s-resources \
--host k3s < /dump/cluster.yaml
echo "--- restic forget/prune ---"
restic forget --tag k8s-resources \
--keep-daily 7 \
--keep-weekly 4 \
--keep-monthly 6 \
--prune
echo "--- restic check --read-data-subset=5% ---"
CHECK_STATUS=0
restic check --read-data-subset=5% || CHECK_STATUS=$?
echo "restic check exit: ${CHECK_STATUS}"
# Textfile-collector metrics; identical wiring to the
# loki/grafana siblings. Scrapeable once node-exporter's
# textfile collector path is enabled — tracked in DEV-482.
{
echo "backup_k8s_resources_success $([ ${CHECK_STATUS} -eq 0 ] && echo 1 || echo 0)"
echo "backup_k8s_resources_timestamp_seconds $(date +%s)"
echo "backup_k8s_resources_check_status ${CHECK_STATUS}"
} > /metrics/backup_k8s_resources.prom
echo "=== backup-k8s-resources-restic finished at $(date -u +%FT%TZ) ==="
exit ${CHECK_STATUS}
volumeMounts:
- name: dump
mountPath: /dump
readOnly: true
- name: metrics
mountPath: /metrics
- name: cache
mountPath: /root/.cache/restic
resources:
requests:
cpu: 100m
memory: 128Mi
limits:
cpu: 1500m
memory: 1Gi
volumes:
- name: dump
emptyDir: {}
- name: metrics
emptyDir: {}
- name: cache
emptyDir: {}