- New PrometheusRule apps/monitoring/backup-restic-alerts.yaml with
seven warning-level rules:
* BackupLokiStale / BackupGrafanaStale / BackupK8sResourcesStale
-> time() - backup_<kind>_timestamp_seconds > 28h
* BackupLokiCheckFailed / BackupGrafanaCheckFailed /
BackupK8sResourcesCheckFailed -> backup_<kind>_check_status != 0
* ResticRepoOversize -> restic_repo_size_bytes > 20 GiB (per-repo)
- Emit restic_repo_size_bytes{repo="<kind>"} from all three restic
CronJobs (loki, grafana, k8s-resources) via `restic stats --json
--mode raw-data` so ResticRepoOversize has data to match once the
textfile-collector scrape path is wired.
- Companion promtool unit test backup-restic-alerts.test.yaml with
five scenarios (fresh/stale, check pass/fail, oversize) -- verified
locally with promtool 2.53.1: SUCCESS.
- README.md: document the three restic CronJobs, the shared
SealedSecret keys (access-key/secret-key/endpoint/bucket/
restic-password), the emitted textfile metrics, and the alert list.
Co-Authored-By: Paperclip <noreply@paperclip.ing>
175 lines
6.6 KiB
YAML
175 lines
6.6 KiB
YAML
---
|
|
# Loki data backup via restic to Hetzner Object Storage (DEV-485,
|
|
# DEV-482 Option 4). Step 2 of the Option 4 rollout.
|
|
#
|
|
# Streams the RWO PVC `loki-storage-encrypted` (mounted read-only)
|
|
# into `s3:${S3_ENDPOINT}/${S3_BUCKET}/restic/loki`, a client-side
|
|
# encrypted restic repository.
|
|
#
|
|
# podAffinity co-schedules with the Loki pod (app=loki, topology
|
|
# kubernetes.io/hostname). RWO permits additional read-only mounts
|
|
# on the node that holds the PVC's VolumeAttachment, so this
|
|
# survives Loki being rescheduled to a different worker.
|
|
apiVersion: batch/v1
|
|
kind: CronJob
|
|
metadata:
|
|
name: backup-loki-restic
|
|
namespace: monitoring
|
|
labels:
|
|
app: backup
|
|
type: loki
|
|
backend: restic
|
|
spec:
|
|
schedule: "0 3 * * *"
|
|
concurrencyPolicy: Forbid
|
|
successfulJobsHistoryLimit: 3
|
|
failedJobsHistoryLimit: 3
|
|
jobTemplate:
|
|
metadata:
|
|
labels:
|
|
app: backup
|
|
type: loki
|
|
backend: restic
|
|
spec:
|
|
backoffLimit: 2
|
|
activeDeadlineSeconds: 3600
|
|
template:
|
|
metadata:
|
|
labels:
|
|
app: backup
|
|
type: loki
|
|
backend: restic
|
|
spec:
|
|
restartPolicy: OnFailure
|
|
affinity:
|
|
podAffinity:
|
|
requiredDuringSchedulingIgnoredDuringExecution:
|
|
- labelSelector:
|
|
matchExpressions:
|
|
- key: app
|
|
operator: In
|
|
values:
|
|
- loki
|
|
topologyKey: kubernetes.io/hostname
|
|
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/loki"
|
|
command:
|
|
- /bin/sh
|
|
- -c
|
|
- |
|
|
set -eu
|
|
echo "=== backup-loki-restic started at $(date -u +%FT%TZ) ==="
|
|
echo "Repository: ${RESTIC_REPOSITORY}"
|
|
|
|
# First-run tolerance: init if the repo isn't there yet.
|
|
# `restic cat config` is the tightest existence probe; use
|
|
# `snapshots` per plan spec — either exits 0 iff the repo
|
|
# is initialised.
|
|
if restic snapshots >/dev/null 2>&1; then
|
|
echo "Repo exists, skipping init."
|
|
else
|
|
echo "Repo missing, initialising..."
|
|
restic init
|
|
fi
|
|
|
|
echo "--- restic backup /source ---"
|
|
restic backup /source \
|
|
--tag loki \
|
|
--host k3s \
|
|
--exclude '*.tmp'
|
|
|
|
echo "--- restic forget/prune ---"
|
|
restic forget --tag loki \
|
|
--keep-daily 7 \
|
|
--keep-weekly 4 \
|
|
--keep-monthly 6 \
|
|
--prune
|
|
|
|
echo "--- restic check --read-data-subset=5% ---"
|
|
CHECK_STATUS=0
|
|
restic check --read-data-subset=5% || CHECK_STATUS=$?
|
|
echo "restic check exit: ${CHECK_STATUS}"
|
|
|
|
echo "--- restic stats (repo size) ---"
|
|
# `restic stats --json --mode raw-data` prints e.g.
|
|
# {"total_size":123,"total_file_count":45,...}. Extract
|
|
# total_size without jq (not present in the restic image)
|
|
# via grep/cut; fall back to 0 on empty output.
|
|
REPO_SIZE_BYTES=$(restic stats --json --mode raw-data 2>/dev/null \
|
|
| grep -oE '"total_size":[0-9]+' \
|
|
| head -1 \
|
|
| cut -d: -f2)
|
|
REPO_SIZE_BYTES=${REPO_SIZE_BYTES:-0}
|
|
echo "restic repo size: ${REPO_SIZE_BYTES} bytes"
|
|
|
|
# Textfile-collector metrics. Written into an emptyDir per
|
|
# the current pattern used by the other backup CronJobs.
|
|
# Once a node-exporter textfile collector path is wired
|
|
# up, these become scrapeable — see the follow-up notes
|
|
# in DEV-482.
|
|
{
|
|
echo "backup_loki_success $([ ${CHECK_STATUS} -eq 0 ] && echo 1 || echo 0)"
|
|
echo "backup_loki_timestamp_seconds $(date +%s)"
|
|
echo "backup_loki_check_status ${CHECK_STATUS}"
|
|
echo "restic_repo_size_bytes{repo=\"loki\"} ${REPO_SIZE_BYTES}"
|
|
} > /metrics/backup_loki.prom
|
|
|
|
echo "=== backup-loki-restic finished at $(date -u +%FT%TZ) ==="
|
|
exit ${CHECK_STATUS}
|
|
volumeMounts:
|
|
- name: loki-data
|
|
mountPath: /source
|
|
readOnly: true
|
|
- name: metrics
|
|
mountPath: /metrics
|
|
- name: cache
|
|
mountPath: /root/.cache/restic
|
|
resources:
|
|
# Requests deliberately lowered from the plan doc's
|
|
# 200m/256Mi — worker-2 (Loki node) has ~150m free CPU
|
|
# and podAffinity forces us onto it. 100m/128Mi mirrors
|
|
# the sibling backup CronJobs; limits stay generous so
|
|
# restic can burst during pack/check.
|
|
requests:
|
|
cpu: 100m
|
|
memory: 128Mi
|
|
limits:
|
|
cpu: 1500m
|
|
memory: 1Gi
|
|
volumes:
|
|
- name: loki-data
|
|
persistentVolumeClaim:
|
|
claimName: loki-storage-encrypted
|
|
- name: metrics
|
|
emptyDir: {}
|
|
- name: cache
|
|
emptyDir: {}
|