Files
parking_solution/apps/server/src/backup-service.ts
T
julian 2910672b5a fix(backup): persist last-success/error status; wall-clock-based schedule
BackupService tracked last-success/last-error as plain in-process fields
and scheduled the daily backup via setInterval measured from process
start — so any server restart (deploy/crash/OOM/reboot, routine under
`restart: always`) silently reset the admin UI to "last successful
backup: Never" and drifted the actual cadence, independent of whether
backups were writing correctly to disk (they were — a real field
incident at park-buzi showed 7 valid rotating backups on disk with the
status stuck on "Never").

Persist last-success/error to new site_config columns (migration 0025)
and add BackupService.isDue(), computed from the persisted timestamp
instead of process uptime; server.ts now polls every 15 min and lets
isDue() gate the actual run. No API/UI contract change.

Claude-Session: https://claude.ai/code/session_01FWncR69HgGPuei1dLrW3cU
2026-08-30 18:11:23 +02:00

223 lines
9.0 KiB
TypeScript

import { constants } from "node:fs";
import { access, stat } from "node:fs/promises";
import { resolve } from "node:path";
import { eq, siteConfig, type Db } from "@parking/db";
import type { FastifyBaseLogger } from "fastify";
import { DEFAULT_BACKUP_RETENTION, runBackup, type BackupResult, type BackupRetention } from "./backup.js";
// Thin coordinator around the backup engine (backup.ts). The TARGET DIRECTORY is admin-chosen
// and stored in site_config.backup_target_dir (read fresh each run, so changing it in the UI
// takes effect with no restart). The ENCRYPTION KEY stays an env/Komodo secret (BACKUP_KEY) —
// a key must never live in the DB it backs up. Remembers the last outcome so the route + UI can
// show last-success / last-error, and serializes concurrent runs (manual + timer). See
// wiki/concepts/backup-recovery.md.
//
// Last-success/last-error are PERSISTED to site_config (backup_last_*), not just held in
// memory — an earlier version tracked these as plain in-process fields only, so every server
// restart (deploy, crash, OOM, host reboot — all routine under `restart: always`) silently
// reset the admin UI to "last successful backup: Never", even with valid, correctly-rotating
// backups already on disk (2026-08-30 field incident, park-buzi). See wiki/concepts/backup-recovery.md.
/** The dedicated backup-encryption key, from env (NOT the DB). Separate from EVENT_SIGNING_KEY. */
export function backupKeyFromEnv(): string {
return process.env.BACKUP_KEY ?? "";
}
export interface TargetCheck {
readonly ok: boolean;
/** Machine-readable reason when !ok: "empty" | "missing" | "not_a_dir" | "not_writable". */
readonly reason?: string;
}
export interface BackupStatus {
/** True once a target dir is set AND a usable key is present (else backups are a no-op). */
readonly configured: boolean;
/** The admin-chosen target dir (null if unset) — surfaced so the UI can show/edit it. */
readonly targetDir: string | null;
/** Admin-tuned retention (resolved: DB value or code default) — surfaced for the UI form. */
readonly keepLast: number;
readonly keepDailyDays: number;
/** Whether the env key is present + long enough (the UI flags a missing key distinctly). */
readonly keyPresent: boolean;
readonly running: boolean;
readonly lastSuccessAt: string | null;
readonly lastResult: { path: string; bytes: number; prunedFiles: number } | null;
readonly lastErrorAt: string | null;
readonly lastError: string | null;
}
/** Probe a candidate target path server-side: exists, is a directory, is writable. */
export async function checkTargetDir(dir: string): Promise<TargetCheck> {
const trimmed = dir.trim();
if (!trimmed) return { ok: false, reason: "empty" };
const path = resolve(trimmed);
let st: Awaited<ReturnType<typeof stat>>;
try {
st = await stat(path);
} catch {
return { ok: false, reason: "missing" };
}
if (!st.isDirectory()) return { ok: false, reason: "not_a_dir" };
try {
await access(path, constants.W_OK);
} catch {
return { ok: false, reason: "not_writable" };
}
return { ok: true };
}
export class BackupService {
readonly #db: Db;
readonly #logger?: FastifyBaseLogger;
#running = false;
constructor(db: Db, logger?: FastifyBaseLogger) {
this.#db = db;
this.#logger = logger;
}
/** Fresh read of the persisted row (single source of truth — no in-memory cache to go stale
* or reset on restart). */
#row(): { backupLastSuccessAt: string | null; backupLastResultJson: string | null; backupLastErrorAt: string | null; backupLastError: string | null } | undefined {
return this.#db.select().from(siteConfig).where(eq(siteConfig.id, 1)).get();
}
#persist(patch: {
backupLastSuccessAt?: string | null;
backupLastResultJson?: string | null;
backupLastErrorAt?: string | null;
backupLastError?: string | null;
}): void {
const updatedAt = new Date().toISOString();
const existing = this.#row();
if (existing) {
this.#db.update(siteConfig).set({ ...patch, updatedAt }).where(eq(siteConfig.id, 1)).run();
} else {
this.#db.insert(siteConfig).values({ id: 1, ...patch, updatedAt }).run();
}
}
/** The admin-chosen target dir from site_config (null/empty = unset). Read fresh each call. */
targetDir(): string | null {
const row = this.#db.select().from(siteConfig).where(eq(siteConfig.id, 1)).get();
const dir = row?.backupTargetDir?.trim();
return dir ? dir : null;
}
/** Resolved retention from site_config, falling back to the code default per field. Read fresh. */
retention(): BackupRetention {
const row = this.#db.select().from(siteConfig).where(eq(siteConfig.id, 1)).get();
const keepLast = row?.backupKeepLast;
const keepDailyDays = row?.backupKeepDailyDays;
return {
keepLast: keepLast != null && keepLast >= 0 ? keepLast : DEFAULT_BACKUP_RETENTION.keepLast,
keepDailyDays:
keepDailyDays != null && keepDailyDays >= 0 ? keepDailyDays : DEFAULT_BACKUP_RETENTION.keepDailyDays,
};
}
get keyPresent(): boolean {
return backupKeyFromEnv().length >= 16;
}
get configured(): boolean {
return this.targetDir() !== null && this.keyPresent;
}
status(): BackupStatus {
const r = this.retention();
const row = this.#row();
let lastResult: BackupStatus["lastResult"] = null;
if (row?.backupLastResultJson) {
try {
lastResult = JSON.parse(row.backupLastResultJson) as BackupStatus["lastResult"];
} catch {
lastResult = null; // corrupt/foreign value in the column — don't let it crash status()
}
}
return {
configured: this.configured,
targetDir: this.targetDir(),
keepLast: r.keepLast,
keepDailyDays: r.keepDailyDays,
keyPresent: this.keyPresent,
running: this.#running,
lastSuccessAt: row?.backupLastSuccessAt ?? null,
lastResult,
lastErrorAt: row?.backupLastErrorAt ?? null,
lastError: row?.backupLastError ?? null,
};
}
/**
* Run one backup. `trigger` is just for the log line. Serialized: if one is already in
* flight, resolves to that same promise. Reads the target dir + key at run time. Records
* last-success/last-error. Re-throws on failure so a manual caller (the route) can surface
* it; the scheduled timer wraps + swallows.
*/
#inflight: Promise<BackupResult> | null = null;
async run(trigger: "manual" | "scheduled"): Promise<BackupResult> {
if (this.#inflight) return this.#inflight;
const targetDir = this.targetDir();
const key = backupKeyFromEnv();
if (!targetDir) throw new Error("backup: no target directory configured");
if (key.length < 16) throw new Error("backup: BACKUP_KEY missing or too short (need ≥16 chars)");
this.#running = true;
this.#inflight = (async () => {
try {
this.#logger?.info(`backup: starting (${trigger}) → ${targetDir}`);
const res = await runBackup(this.#db, { targetDir, key, retention: this.retention() }, this.#logger);
this.#persist({
backupLastSuccessAt: new Date().toISOString(),
backupLastResultJson: JSON.stringify({ path: res.path, bytes: res.bytes, prunedFiles: res.prunedFiles }),
backupLastErrorAt: null,
backupLastError: null,
});
return res;
} catch (err) {
const message = (err as Error).message;
this.#persist({ backupLastErrorAt: new Date().toISOString(), backupLastError: message });
this.#logger?.error(`backup: failed (${trigger}): ${message}`);
throw err;
} finally {
this.#running = false;
this.#inflight = null;
}
})();
return this.#inflight;
}
/**
* Scheduled-run wrapper: never throws (a timer must not crash the process). Safe to call on
* a short, frequent poll (see server.ts) — it's a no-op unless `isDue()` says a full interval
* has actually elapsed since the last recorded success, so frequent polling doesn't cause
* frequent backups.
*/
async runScheduled(): Promise<void> {
if (!this.configured) return; // silent no-op when backups aren't set up
if (!this.isDue()) return;
try {
await this.run("scheduled");
} catch {
/* recorded in last-error; already logged */
}
}
/**
* Wall-clock check: has enough time elapsed since the last successful backup for a new one
* to be due? Deliberately based on the PERSISTED last-success instant, not "time since this
* process started" — a `setInterval(..., 24h)` measured from process start silently drifts
* (or skips a whole day) across every restart, since the countdown restarts from zero each
* time regardless of when the last real backup happened. See wiki/concepts/backup-recovery.md.
*/
isDue(now: Date = new Date(), intervalMs = 24 * 60 * 60 * 1000): boolean {
const lastSuccessAt = this.#row()?.backupLastSuccessAt;
if (!lastSuccessAt) return true; // never recorded a success → due immediately once configured
const last = new Date(lastSuccessAt).getTime();
if (Number.isNaN(last)) return true;
return now.getTime() - last >= intervalMs;
}
}