"""Are the backups keeping up? One row on the System view, and the nav dot. The backups run on their own at night, so the only way to notice one has stopped is to be told. The System view's health endpoint asks `backup_part`, which answers with a part like any other: `ok`, or `stale` with the sentence that says what is wrong. It warns when - the newest database backup is more than a day old, or there is none; - the newest database backup failed; - the weekly check of the off-site bucket found files missing from it, and no media run has finished since to send them again. No part at all when backups aren't set up (no off-site destination and the nightly backup off): someone who chose not to back up is not told so every fifteen seconds. """ from __future__ import annotations from dataclasses import dataclass from datetime import datetime from sqlalchemy import select from ..models import BackupRun, ImportSettings from . import backup_destination # A nightly backup is due every 24 hours. The hour of slack covers the dump # itself and a beat tick that lands a little late. DUMP_DUE_SECONDS = 25 * 3600 @dataclass(frozen=True) class BackupFacts: expected: bool offsite: bool last_dump_at: datetime | None = None last_dump_error: str | None = None missing: int = 0 def _age(seconds: float) -> str: hours = int(seconds // 3600) if hours >= 48: return f"{hours // 24} days" if hours >= 1: return f"{hours} h" return f"{max(1, int(seconds // 60))} min" def verdict(facts: BackupFacts, now: datetime) -> dict | None: """The part for these facts, or None when backups aren't set up.""" if not facts.expected: return None where = "to the off-site bucket" if facts.offsite else "on this server" problems = [] if facts.last_dump_error: problems.append(f"The last database backup failed: {facts.last_dump_error}") if facts.last_dump_at is None: if not facts.last_dump_error: problems.append(f"No database backup has been taken {where} yet") else: age = (now - facts.last_dump_at).total_seconds() if age >= DUMP_DUE_SECONDS: problems.append(f"The newest database backup {where} is {_age(age)} old") if facts.missing: problems.append( f"The bucket check found {facts.missing:,} file(s) missing from the bucket; " "the next media run sends them again" ) part = {"key": "backup", "kind": "backup", "name": "Backups"} if problems: return {**part, "state": "stale", "detail": ". ".join(problems)} age = (now - facts.last_dump_at).total_seconds() return {**part, "state": "ok", "detail": f"The newest database backup {where} is {_age(age)} old"} def gather(session) -> BackupFacts: """Read the facts `verdict` judges, from a sync session.""" settings = ImportSettings.load_sync(session) offsite = backup_destination.describe(settings)["configured"] expected = offsite or bool(settings.backup_db_nightly_enabled) if not expected: return BackupFacts(expected=False, offsite=False) def newest(kind: str, statuses: tuple[str, ...]): return session.execute( select(BackupRun).where(BackupRun.kind == kind) .where(BackupRun.status.in_(statuses)) .order_by(BackupRun.started_at.desc()).limit(1) ).scalar_one_or_none() last_ok = newest("db", ("ok",)) last_done = newest("db", ("ok", "error")) failed = None if last_done is not None and last_done.status == "error": failed = last_done.error or "no reason recorded" missing = 0 if offsite: check = newest("reconcile", ("ok",)) dropped = int((check.manifest or {}).get("dropped") or 0) if check else 0 if dropped: sent_since = session.execute( select(BackupRun.id).where(BackupRun.kind == "media") .where(BackupRun.status == "ok") .where(BackupRun.finished_at > check.finished_at).limit(1) ).scalar_one_or_none() missing = 0 if sent_since is not None else dropped return BackupFacts( expected=True, offsite=offsite, last_dump_at=(last_ok.finished_at or last_ok.started_at) if last_ok else None, last_dump_error=failed, missing=missing, ) def backup_part(session, now: datetime) -> dict | None: return verdict(gather(session), now)