Files
railiance-cluster/tools/cmd/railiance-restore-s2
Bernd Worsch 2420915d30
Some checks failed
railiance-tests / smoke (push) Has been cancelled
fix(backup): SQLite hot backup instead of etcd snapshot
k3s runs in SQLite mode (no --cluster-init). Replace etcd-snapshot
with sqlite3 .backup for a WAL-aware hot copy of state.db.
Update restore guide to match. Cron installed under root crontab.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-03-26 21:56:19 +00:00

68 lines
2.3 KiB
Bash
Executable File

#!/usr/bin/env bash
# tools/cmd/railiance-restore-s2 — S2 Kubernetes Runtime restore guide
# Lists available backups and prints restore instructions.
# Actual restore of etcd requires cluster downtime — see instructions below.
set -euo pipefail
BACKUP_DIR="/opt/backup/railiance/cluster"
AGE_KEY="${HOME}/.config/sops/age/keys.txt"
echo ""
echo "railiance-cluster (S2) — Available Backups"
echo "============================================"
echo ""
if [[ ! -d "${BACKUP_DIR}" ]]; then
echo " No backup directory found at ${BACKUP_DIR}"
echo " Run: sudo make backup"
exit 1
fi
LAST=""
[[ -f "${BACKUP_DIR}/.last-backup" ]] && LAST="$(cat "${BACKUP_DIR}/.last-backup")"
[[ -n "${LAST}" ]] && echo " Last backup: ${LAST}" || echo " Last backup: unknown"
echo ""
list_type() {
local label="$1" pattern="$2"
echo " ${label}:"
local files
files="$(find "${BACKUP_DIR}" -name "${pattern}" 2>/dev/null | sort -r)"
if [[ -z "${files}" ]]; then
echo " (none)"
else
echo "${files}" | while read -r f; do
echo " $(basename "${f}") [$(du -sh "${f}" | cut -f1)]"
done
fi
echo ""
}
list_type "k3s state (SQLite)" "k3s-state-*.db.age"
list_type "Helm values" "helm-values-*.tar.gz.age"
list_type "kubeconfig" "kubeconfig-*.yaml.age"
echo "============================================"
echo ""
echo "Decrypt any file:"
echo " age -d -i ${AGE_KEY} <file>"
echo ""
echo "Restore kubeconfig:"
echo " age -d -i ${AGE_KEY} ${BACKUP_DIR}/kubeconfig-<ts>.yaml.age > ~/.kube/config-hosteurope"
echo ""
echo "Restore k3s state (SQLite) — WARNING: destroys current cluster state:"
echo " # 1. Decrypt the state db"
echo " age -d -i ${AGE_KEY} ${BACKUP_DIR}/k3s-state-<ts>.db.age > /tmp/k3s-restore.db"
echo " # 2. Stop k3s"
echo " sudo systemctl stop k3s"
echo " # 3. Replace the state db"
echo " sudo cp /var/lib/rancher/k3s/server/db/state.db /var/lib/rancher/k3s/server/db/state.db.bak"
echo " sudo cp /tmp/k3s-restore.db /var/lib/rancher/k3s/server/db/state.db"
echo " sudo rm -f /var/lib/rancher/k3s/server/db/state.db-shm /var/lib/rancher/k3s/server/db/state.db-wal"
echo " # 4. Start k3s"
echo " sudo systemctl start k3s"
echo ""
echo "Restore Helm values (for re-running helm upgrade after cluster restore):"
echo " age -d -i ${AGE_KEY} ${BACKUP_DIR}/helm-values-<ts>.tar.gz.age | tar -xz -C /tmp/helm-restore/"
echo ""