fc3h: remove backend/app/services/migrators/backup.py + rollback.py (relocated to backup_service.py)
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
This commit is contained in:
@@ -1,146 +0,0 @@
|
||||
"""pg_dump + tar.zst-based backup, restorable via pair of subprocess calls.
|
||||
|
||||
Backups live under <images_root>/_backups/. Each backup is two files
|
||||
(SQL + tarball) plus a manifest JSON. Tagged backups (e.g. tag='pre_migration')
|
||||
are how rollback.py finds the most recent restorable snapshot.
|
||||
"""
|
||||
from __future__ import annotations
|
||||
|
||||
import json
|
||||
import shutil
|
||||
import subprocess
|
||||
from datetime import UTC, datetime
|
||||
from pathlib import Path
|
||||
from typing import Any
|
||||
|
||||
_BACKUPS_DIRNAME = "_backups"
|
||||
|
||||
|
||||
def _libpq_url(sa_url: str) -> str:
|
||||
"""Strip SQLAlchemy driver suffix so pg_dump/psql accept the URL.
|
||||
|
||||
SQLAlchemy uses URLs like `postgresql+psycopg://...` or
|
||||
`postgresql+asyncpg://...`. libpq tools (pg_dump, psql) only know
|
||||
the plain `postgresql://` scheme.
|
||||
"""
|
||||
for driver in ("postgresql+psycopg", "postgresql+asyncpg", "postgresql+psycopg2"):
|
||||
if sa_url.startswith(driver + "://"):
|
||||
return "postgresql://" + sa_url[len(driver) + 3:]
|
||||
return sa_url
|
||||
|
||||
|
||||
def _backups_dir(images_root: Path | None = None) -> Path:
|
||||
# Overridable for tests via monkeypatch.
|
||||
root = images_root if images_root is not None else Path("/images")
|
||||
p = root / _BACKUPS_DIRNAME
|
||||
p.mkdir(parents=True, exist_ok=True)
|
||||
return p
|
||||
|
||||
|
||||
_DEFAULT_SUBPROCESS_TIMEOUT_S = 30 * 60 # 30 minutes
|
||||
|
||||
|
||||
def _run_subprocess(cmd: list[str], **kwargs: Any):
|
||||
# Overridable for tests via monkeypatch. Hard wall-clock timeout
|
||||
# guards against pg_dump / tar / zstd hangs on NFS — without it the
|
||||
# task pretends to be 'running' forever (operator hit this 2026-05-
|
||||
# 23 with two backups stuck in MigrationRun). On timeout
|
||||
# subprocess.run raises TimeoutExpired which the caller surfaces as
|
||||
# a task error.
|
||||
return subprocess.run(
|
||||
cmd,
|
||||
capture_output=True,
|
||||
check=True,
|
||||
timeout=_DEFAULT_SUBPROCESS_TIMEOUT_S,
|
||||
**{k: v for k, v in kwargs.items() if not k.startswith("_")},
|
||||
)
|
||||
|
||||
|
||||
def create_backup(
|
||||
*, db_url: str, images_root: Path, tag: str = "manual",
|
||||
) -> dict:
|
||||
"""Create a backup: pg_dump SQL + tar.zst of images.
|
||||
|
||||
Returns a manifest dict. Writes <ts>.sql, <ts>.tar.zst, <ts>.json into
|
||||
<images_root>/_backups/.
|
||||
"""
|
||||
ts = datetime.now(UTC).strftime("%Y%m%dT%H%M%SZ")
|
||||
out_dir = _backups_dir(images_root)
|
||||
sql_path = out_dir / f"fc_{ts}.sql"
|
||||
tar_path = out_dir / f"fc_{ts}.tar.zst"
|
||||
manifest_path = out_dir / f"fc_{ts}.json"
|
||||
|
||||
_run_subprocess(
|
||||
["pg_dump", "--no-owner", "--no-acl", "-f", str(sql_path), _libpq_url(db_url)],
|
||||
_test_ts=ts,
|
||||
)
|
||||
_run_subprocess(
|
||||
[
|
||||
"tar", "--zstd", "-cf", str(tar_path),
|
||||
"-C", str(images_root.parent), images_root.name,
|
||||
f"--exclude={images_root.name}/_backups",
|
||||
f"--exclude={images_root.name}/_quarantine",
|
||||
],
|
||||
_test_ts=ts,
|
||||
)
|
||||
|
||||
manifest = {
|
||||
"backup_id": ts,
|
||||
"tag": tag,
|
||||
"created_at": datetime.now(UTC).isoformat(),
|
||||
"sql_path": str(sql_path),
|
||||
"tar_path": str(tar_path),
|
||||
}
|
||||
manifest_path.write_text(json.dumps(manifest, indent=2))
|
||||
return manifest
|
||||
|
||||
|
||||
def list_backups(images_root: Path) -> list[dict]:
|
||||
out_dir = _backups_dir(images_root)
|
||||
items = []
|
||||
for mf in sorted(out_dir.glob("fc_*.json"), reverse=True):
|
||||
try:
|
||||
items.append(json.loads(mf.read_text()))
|
||||
except Exception:
|
||||
continue
|
||||
return items
|
||||
|
||||
|
||||
def find_latest_backup(images_root: Path, *, tag: str) -> dict | None:
|
||||
for mf in list_backups(images_root):
|
||||
if mf.get("tag") == tag:
|
||||
return mf
|
||||
return None
|
||||
|
||||
|
||||
def restore_backup(
|
||||
*, manifest: dict, db_url: str, images_root: Path,
|
||||
) -> dict:
|
||||
"""Restore from a backup manifest.
|
||||
|
||||
1. Replay the .sql via psql.
|
||||
2. Wipe /images/ contents (except _backups/, which holds the file we're using).
|
||||
3. Untar the .tar.zst into /images/.
|
||||
"""
|
||||
sql_path = Path(manifest["sql_path"])
|
||||
tar_path = Path(manifest["tar_path"])
|
||||
|
||||
_run_subprocess(
|
||||
["psql", "-d", _libpq_url(db_url), "-f", str(sql_path)],
|
||||
)
|
||||
|
||||
# Wipe everything in images_root EXCEPT _backups/ (we'd delete the backup
|
||||
# we're restoring from!).
|
||||
for entry in images_root.iterdir():
|
||||
if entry.name == _BACKUPS_DIRNAME:
|
||||
continue
|
||||
if entry.is_dir():
|
||||
shutil.rmtree(entry)
|
||||
else:
|
||||
entry.unlink()
|
||||
|
||||
_run_subprocess(
|
||||
["tar", "--zstd", "-xf", str(tar_path), "-C", str(images_root.parent)],
|
||||
)
|
||||
|
||||
return {"restored_from": manifest["backup_id"]}
|
||||
@@ -1,21 +0,0 @@
|
||||
"""Restore from the most recent 'pre_migration'-tagged backup."""
|
||||
from __future__ import annotations
|
||||
|
||||
from pathlib import Path
|
||||
|
||||
from . import backup as backup_mod
|
||||
|
||||
|
||||
class NoBackupFoundError(Exception):
|
||||
"""Raised when rollback() is called with no pre_migration backup on disk."""
|
||||
|
||||
|
||||
def rollback_to_pre_migration(*, db_url: str, images_root: Path) -> dict:
|
||||
manifest = backup_mod.find_latest_backup(images_root, tag="pre_migration")
|
||||
if manifest is None:
|
||||
raise NoBackupFoundError(
|
||||
"no pre_migration-tagged backup found under <images_root>/_backups/"
|
||||
)
|
||||
return backup_mod.restore_backup(
|
||||
manifest=manifest, db_url=db_url, images_root=images_root,
|
||||
)
|
||||
Reference in New Issue
Block a user