Files
FabledCurator/backend/app/tasks/backup.py
T
bvandeusen 171c486939 refactor(dry-B2): ImportSettings.load()/load_sync() classmethods for the singleton row
The `select(ImportSettings).where(id == 1)).scalar_one()` singleton load was
repeated 15× across services, API, and 5 task modules. Added async load() +
sync load_sync() classmethods on the model and migrated all 15 full-row sites
(callers already imported ImportSettings, so no new imports; dropped download's
now-orphaned select import). Left maintenance.py's deliberate column-select
(import_scan_path only) as-is.

Rest of the service layer was already adequately DRY — the Record/to_dict
pattern is only 2 instances and the savepoint find-or-create recovery is
correctly per-entity, so neither was forced into a shared abstraction.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-28 14:03:26 -04:00

297 lines
10 KiB
Python

"""FC-3h: backup/restore Celery tasks.
All tasks live on the maintenance queue (per celery_app.task_routes).
task_run lifecycle tracking is automatic via FC-3i signals — these
tasks just record the operator-facing artifact metadata into
BackupRun.
"""
from __future__ import annotations
import logging
from datetime import UTC, datetime
from pathlib import Path
from celery.exceptions import SoftTimeLimitExceeded
from sqlalchemy import select
from sqlalchemy.exc import DBAPIError, OperationalError
from ..celery_app import celery
from ..config import get_config
from ..models import BackupRun, ImportSettings
from ..services import backup_service
from ._sync_engine import sync_session_factory as _sync_session_factory
log = logging.getLogger(__name__)
IMAGES_ROOT = Path("/images")
def _mark_failed(session, row: BackupRun, exc: BaseException) -> None:
"""Flip a BackupRun row from running/restoring to error with a
truncated error message and finished_at. Caller already holds the
session open."""
row.status = "error"
row.error = f"{type(exc).__name__}: {exc}"[:2000]
row.finished_at = datetime.now(UTC)
session.add(row)
session.commit()
@celery.task(
name="backend.app.tasks.backup.backup_db_task",
bind=True,
autoretry_for=(OperationalError, DBAPIError),
retry_backoff=10, retry_backoff_max=120, max_retries=2,
soft_time_limit=600, time_limit=720,
)
def backup_db_task(self, *, tag: str | None = None,
triggered_by: str = "manual") -> dict:
"""Create one DB backup. Returns {'backup_run_id': N}."""
SessionLocal = _sync_session_factory()
cfg = get_config()
now = datetime.now(UTC)
with SessionLocal() as session:
row = BackupRun(
kind="db", status="running", tag=tag,
triggered_by=triggered_by, started_at=now, manifest={},
)
session.add(row)
session.commit()
session.refresh(row)
run_id = row.id
try:
result = backup_service.backup_db(
db_url=cfg.database_url_sync, images_root=IMAGES_ROOT,
tag=tag, triggered_by=triggered_by,
)
except (SoftTimeLimitExceeded, Exception) as exc:
with SessionLocal() as session:
row = session.get(BackupRun, run_id)
if row is not None:
_mark_failed(session, row, exc)
raise
with SessionLocal() as session:
row = session.get(BackupRun, run_id)
row.status = "ok"
row.finished_at = datetime.now(UTC)
row.sql_path = result["sql_path"]
row.size_bytes = result["size_bytes"]
row.manifest = {
"manifest_path": result["manifest_path"],
"ts": result["ts"],
}
session.commit()
return {"backup_run_id": run_id}
@celery.task(
name="backend.app.tasks.backup.backup_images_task",
bind=True,
autoretry_for=(OperationalError, DBAPIError),
retry_backoff=30, retry_backoff_max=300, max_retries=1,
soft_time_limit=21600, time_limit=23400,
)
def backup_images_task(self, *, tag: str | None = None,
triggered_by: str = "manual") -> dict:
"""Create one images backup. Same shape as backup_db_task; uses
tar_path instead of sql_path."""
SessionLocal = _sync_session_factory()
now = datetime.now(UTC)
with SessionLocal() as session:
row = BackupRun(
kind="images", status="running", tag=tag,
triggered_by=triggered_by, started_at=now, manifest={},
)
session.add(row)
session.commit()
session.refresh(row)
run_id = row.id
try:
result = backup_service.backup_images(
images_root=IMAGES_ROOT,
tag=tag, triggered_by=triggered_by,
)
except (SoftTimeLimitExceeded, Exception) as exc:
with SessionLocal() as session:
row = session.get(BackupRun, run_id)
if row is not None:
_mark_failed(session, row, exc)
raise
with SessionLocal() as session:
row = session.get(BackupRun, run_id)
row.status = "ok"
row.finished_at = datetime.now(UTC)
row.tar_path = result["tar_path"]
row.size_bytes = result["size_bytes"]
row.manifest = {
"manifest_path": result["manifest_path"],
"ts": result["ts"],
}
session.commit()
return {"backup_run_id": run_id}
@celery.task(
name="backend.app.tasks.backup.restore_db_task",
bind=True,
max_retries=0, # NEVER auto-retry a half-applied restore.
soft_time_limit=1200, time_limit=1800,
)
def restore_db_task(self, *, source_backup_run_id: int) -> dict:
"""Restore from a previous DB backup. Inserts a NEW BackupRun row
(kind='db', status='restoring') linked to the source via
restored_from_id; flips to 'restored' on success or 'error' on
failure. Operator sees the restore as a row in the dashboard."""
SessionLocal = _sync_session_factory()
cfg = get_config()
now = datetime.now(UTC)
with SessionLocal() as session:
src = session.get(BackupRun, source_backup_run_id)
if src is None or src.kind != "db" or not src.sql_path:
raise ValueError(
f"BackupRun id={source_backup_run_id} is not a valid DB backup"
)
marker = BackupRun(
kind="db", status="restoring",
triggered_by="restore", started_at=now,
restored_from_id=src.id,
manifest={"source_sql_path": src.sql_path},
)
session.add(marker)
session.commit()
session.refresh(marker)
marker_id = marker.id
sql_path = src.sql_path
try:
backup_service.restore_db(
db_url=cfg.database_url_sync, sql_path=Path(sql_path),
)
except (SoftTimeLimitExceeded, Exception) as exc:
with SessionLocal() as session:
row = session.get(BackupRun, marker_id)
if row is not None:
_mark_failed(session, row, exc)
raise
with SessionLocal() as session:
row = session.get(BackupRun, marker_id)
row.status = "restored"
row.finished_at = datetime.now(UTC)
session.commit()
return {"backup_run_id": marker_id}
@celery.task(
name="backend.app.tasks.backup.restore_images_task",
bind=True, max_retries=0,
soft_time_limit=21600, time_limit=23400,
)
def restore_images_task(self, *, source_backup_run_id: int) -> dict:
"""Mirrors restore_db_task; uses backup_service.restore_images."""
SessionLocal = _sync_session_factory()
now = datetime.now(UTC)
with SessionLocal() as session:
src = session.get(BackupRun, source_backup_run_id)
if src is None or src.kind != "images" or not src.tar_path:
raise ValueError(
f"BackupRun id={source_backup_run_id} is not a valid images backup"
)
marker = BackupRun(
kind="images", status="restoring",
triggered_by="restore", started_at=now,
restored_from_id=src.id,
manifest={"source_tar_path": src.tar_path},
)
session.add(marker)
session.commit()
session.refresh(marker)
marker_id = marker.id
tar_path = src.tar_path
try:
backup_service.restore_images(
images_root=IMAGES_ROOT, tar_path=Path(tar_path),
)
except (SoftTimeLimitExceeded, Exception) as exc:
with SessionLocal() as session:
row = session.get(BackupRun, marker_id)
if row is not None:
_mark_failed(session, row, exc)
raise
with SessionLocal() as session:
row = session.get(BackupRun, marker_id)
row.status = "restored"
row.finished_at = datetime.now(UTC)
session.commit()
return {"backup_run_id": marker_id}
@celery.task(
name="backend.app.tasks.backup.prune_backups",
soft_time_limit=300, time_limit=600,
)
def prune_backups() -> dict:
"""Daily Beat. Per-kind retention from ImportSettings.
Returns {"db_deleted": N, "images_deleted": M, "files_unlinked": K}.
Tagged rows (tag IS NOT NULL) are never pruned.
Status='running' / 'restoring' rows are never pruned (recovery
sweep from FC-3i handles those via task_run).
"""
SessionLocal = _sync_session_factory()
counts = {"db_deleted": 0, "images_deleted": 0, "files_unlinked": 0}
with SessionLocal() as session:
s = ImportSettings.load_sync(session)
for kind, keep in (
("db", s.backup_db_keep_last_n),
("images", s.backup_images_keep_last_n),
):
candidates = session.execute(
select(BackupRun)
.where(BackupRun.kind == kind)
.where(BackupRun.tag.is_(None))
.where(BackupRun.status.in_(["ok", "error"]))
.order_by(BackupRun.started_at.desc())
.offset(keep)
).scalars().all()
for row in candidates:
result = backup_service.unlink_artifact_files(
sql_path=row.sql_path,
tar_path=row.tar_path,
manifest_path=(row.manifest or {}).get("manifest_path"),
)
counts["files_unlinked"] += sum(
1 for v in result.values() if v
)
session.delete(row)
counts[f"{kind}_deleted"] += 1
session.commit()
return counts
@celery.task(
name="backend.app.tasks.backup.backup_db_nightly",
soft_time_limit=60, time_limit=120,
)
def backup_db_nightly() -> dict:
"""Hourly tick. Dispatches a real backup ONLY if the configured
UTC hour matches and the nightly setting is enabled. Returns
either {'skipped': '<reason>'} or {'dispatched': '<task_id>'}."""
SessionLocal = _sync_session_factory()
with SessionLocal() as session:
s = ImportSettings.load_sync(session)
nightly_enabled = s.backup_db_nightly_enabled
configured_hour = s.backup_db_nightly_hour_utc
if not nightly_enabled:
return {"skipped": "nightly disabled"}
now_hour = datetime.now(UTC).hour
if now_hour != configured_hour:
return {"skipped": f"hour={now_hour} != configured={configured_hour}"}
res = backup_db_task.delay(triggered_by="nightly")
return {"dispatched": res.id}