Files
docker-volume-backup/tests/e2e/test_e2e_postgres_cluster_restore.py
Kevin Veen-Birkenbach 5f3ee0a669 fix(restore): refuse a cluster restore that would destroy what it cannot restore
The --empty pre-clean is a catalog-wide sweep: it drops every non-template database and every non-pg_ role of the instance. On a dedicated instance that is exactly right, because the dump recreates all of it. On a shared one it destroys databases the dump does not carry, with nothing to restore them from - and no test ever executed that sweep, because the e2e dropped the cluster by hand first and left the pre-clean with zero rows to generate.

Scoping the sweep to the dump's own inventory looks like the fix and is worse. A surviving database that owns or merely grants to one of the dump's roles pins that role in pg_shdepend; DROP OWNED BY only reaches the control database the pre-clean is connected to, so DROP ROLE fails - after phase 1 has already dropped the dump's databases. ON_ERROR_STOP aborts, the replay never starts, and the instance is left half emptied.

So the instance is checked instead. --empty now refuses when the instance holds a database the dump does not carry, names it, and touches nothing. The sweep stays as it was, safe behind that refusal. Reading the dump's inventory needs a real identifier parser: a quoted name may hold spaces, and psql options precede the target of a \\connect line.

The e2e no longer drops the cluster itself, so --empty has to do it and the replay has to put it back; a second pass then adds a foreign database and requires the refusal to leave both it and the restored data alone.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-17 08:15:58 +02:00

216 lines
6.7 KiB
Python

import unittest
from .helpers import (
POSTGRES_DATA_DIR,
POSTGRES_IMAGE,
backup_path,
backup_run,
cleanup_docker,
create_minimal_compose_dir,
ensure_empty_dir,
latest_version_dir,
require_docker,
run,
unique,
wait_for_postgres,
write_databases_csv,
)
# One statement per entry: psql wraps a multi-statement -c in a transaction,
# and CREATE DATABASE is forbidden inside one.
SEED_SQL = (
"CREATE ROLE app LOGIN PASSWORD 'apppw'",
"CREATE DATABASE first OWNER app",
"CREATE DATABASE second OWNER app",
)
SIBLING_SQL = (
"CREATE ROLE neighbour LOGIN PASSWORD 'neighbourpw'",
"CREATE DATABASE sibling OWNER neighbour",
)
SIBLING_PAYLOAD = "CREATE TABLE t (v text); INSERT INTO t VALUES ('sibling-payload');"
FIRST_SQL = "CREATE TABLE t (v text); INSERT INTO t VALUES ('first-payload');"
SECOND_SQL = "CREATE TABLE t (v text); INSERT INTO t VALUES ('second-payload');"
class TestE2EPostgresClusterRestore(unittest.TestCase):
@classmethod
def setUpClass(cls) -> None:
require_docker()
cls.prefix = unique("baudolo-e2e-pg-cluster")
cls.backups_dir = f"/tmp/{cls.prefix}/Backups"
ensure_empty_dir(cls.backups_dir)
cls.compose_dir = create_minimal_compose_dir(f"/tmp/{cls.prefix}")
cls.repo_name = cls.prefix
cls.pg_container = f"{cls.prefix}-pg"
cls.pg_volume = f"{cls.prefix}-pg-vol"
cls.containers = [cls.pg_container]
cls.volumes = [cls.pg_volume]
run(["docker", "volume", "create", cls.pg_volume])
run(
[
"docker",
"run",
"-d",
"--name",
cls.pg_container,
"-e",
"POSTGRES_PASSWORD=pgpw",
"-v",
f"{cls.pg_volume}:{POSTGRES_DATA_DIR}",
POSTGRES_IMAGE,
]
)
wait_for_postgres(cls.pg_container, user="postgres")
for statement in SEED_SQL:
cls._psql("postgres", statement)
cls._psql("first", FIRST_SQL)
cls._psql("second", SECOND_SQL)
cls.databases_csv = f"/tmp/{cls.prefix}/databases.csv"
write_databases_csv(
cls.databases_csv, [(cls.pg_container, "*", "postgres", "pgpw")]
)
backup_run(
backups_dir=cls.backups_dir,
repo_name=cls.repo_name,
compose_dir=cls.compose_dir,
databases_csv=cls.databases_csv,
database_containers=[cls.pg_container],
images_no_stop_required=[POSTGRES_IMAGE],
)
cls.hash, cls.version = latest_version_dir(cls.backups_dir, cls.repo_name)
cls.dump = (
backup_path(cls.backups_dir, cls.repo_name, cls.version, cls.pg_volume)
/ "sql"
/ f"{cls.pg_container}.cluster.backup.sql"
)
run(
[
"baudolo-restore",
"cluster",
cls.pg_volume,
cls.hash,
cls.version,
"--backups-dir",
cls.backups_dir,
"--repo-name",
cls.repo_name,
"--container",
cls.pg_container,
"--instance",
cls.pg_container,
"--db-user",
"postgres",
"--db-password",
"pgpw",
"--empty",
]
)
for statement in SIBLING_SQL:
cls._psql("postgres", statement)
cls._psql("sibling", SIBLING_PAYLOAD)
cls.refused = run(cls._restore_argv(), check=False)
@classmethod
def _restore_argv(cls) -> list:
return [
"baudolo-restore",
"cluster",
cls.pg_volume,
cls.hash,
cls.version,
"--backups-dir",
cls.backups_dir,
"--repo-name",
cls.repo_name,
"--container",
cls.pg_container,
"--instance",
cls.pg_container,
"--db-user",
"postgres",
"--db-password",
"pgpw",
"--empty",
]
@classmethod
def tearDownClass(cls) -> None:
cleanup_docker(containers=cls.containers, volumes=cls.volumes)
@classmethod
def _psql(cls, database: str, sql: str) -> str:
p = run(
[
"docker",
"exec",
cls.pg_container,
"sh",
"-lc",
f'psql -U postgres -d {database} -t -A -c "{sql}"',
]
)
return (p.stdout or "").strip()
def test_the_backup_wrote_a_cluster_dump(self) -> None:
self.assertTrue(self.dump.is_file(), f"no cluster dump at {self.dump}")
def test_the_preclean_really_dropped_a_populated_cluster(self) -> None:
self.assertEqual(self._psql("first", "SELECT v FROM t"), "first-payload")
def test_a_second_empty_is_refused_once_a_foreign_database_exists(self) -> None:
self.assertNotEqual(self.refused.returncode, 0, self.refused.stdout)
self.assertIn("sibling", self.refused.stderr)
def test_the_refusal_left_the_foreign_database_alone(self) -> None:
self.assertEqual(self._psql("sibling", "SELECT v FROM t"), "sibling-payload")
def test_the_refusal_dropped_nothing_of_its_own(self) -> None:
self.assertEqual(self._psql("first", "SELECT v FROM t"), "first-payload")
def test_both_databases_are_back(self) -> None:
listed = self._psql(
"postgres",
"SELECT datname FROM pg_database WHERE datname IN ('first','second') ORDER BY 1",
)
self.assertEqual(listed.split(), ["first", "second"])
def test_each_database_carries_its_own_payload(self) -> None:
self.assertEqual(self._psql("first", "SELECT v FROM t"), "first-payload")
self.assertEqual(self._psql("second", "SELECT v FROM t"), "second-payload")
def test_the_superusers_own_create_was_filtered(self) -> None:
self.assertEqual(
self._psql(
"postgres", "SELECT rolsuper FROM pg_roles WHERE rolname = 'postgres'"
),
"t",
)
def test_the_owning_role_is_back(self) -> None:
self.assertEqual(
self._psql(
"postgres", "SELECT rolname FROM pg_roles WHERE rolname = 'app'"
),
"app",
)
def test_ownership_survived(self) -> None:
self.assertEqual(
self._psql(
"postgres",
"SELECT pg_get_userbyid(datdba) FROM pg_database WHERE datname = 'first'",
),
"app",
)
if __name__ == "__main__":
unittest.main()