mirror of
https://github.com/kevinveenbirkenbach/docker-volume-backup.git
synced 2026-08-01 12:34:50 +00:00
Kevin Veen-Birkenbach
d4317827bd
Backing up a live volume with rsync copies a moving target: a database
written to mid-copy lands on disk in a state no engine ever committed.
Stopping the container avoids that at the cost of downtime.
A snapshot removes both. `--snapshot {btrfs,zfs}` with `--snapshot-subject`
freezes the docker root once per run, and every volume copy is then read
from that frozen tree while the containers keep serving. A restore of such
a copy is an ordinary crash recovery, which every supported engine performs
on its own at startup.
An unsupported filesystem or an unknown snapshot kind fails loudly rather
than degrading to a live copy, since a silent fallback would return exactly
the torn backup the mode exists to prevent. `--shutdown` is rejected
alongside `--snapshot` instead of being ignored: under a snapshot no
container is ever stopped, so accepting the flag would promise downtime
semantics the run does not deliver.
Copies out of a snapshot skip rsync's --checksum verification. The source
is immutable for the lifetime of the copy, so size-and-mtime cannot race,
and dropping the second full read roughly halves the I/O per volume.
backup/app.py grew past what one module could carry and is split into
layout, policy and dumps along the lines it already had internally.
Tests: unit coverage for the new snapshot, layout, policy, volume and cli
units; e2e cases drive real btrfs, zfs and ext4 filesystems on loop devices
in a privileged container, including a MariaDB that is written to across
the snapshot and must recover from the restored copy without losing a
committed row. CI installs zfs and sets E2E_REQUIRE_FILESYSTEMS so a
missing kernel module fails the build instead of silently skipping a
filesystem.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
52 lines
1.8 KiB
Python
52 lines
1.8 KiB
Python
"""Contract of where a backup run puts its directories."""
|
|
|
|
from __future__ import annotations
|
|
|
|
import tempfile
|
|
import unittest
|
|
from pathlib import Path
|
|
from unittest import mock
|
|
|
|
from baudolo.backup import layout as mod
|
|
|
|
|
|
class TestVersionDirectory(unittest.TestCase):
|
|
def test_it_creates_the_generation_directory(self) -> None:
|
|
with tempfile.TemporaryDirectory() as tmp:
|
|
created = mod.create_version_directory(tmp, "20260731020304")
|
|
self.assertTrue(Path(created).is_dir())
|
|
self.assertEqual(Path(created).name, "20260731020304")
|
|
|
|
def test_it_is_idempotent(self) -> None:
|
|
with tempfile.TemporaryDirectory() as tmp:
|
|
first = mod.create_version_directory(tmp, "20260731")
|
|
second = mod.create_version_directory(tmp, "20260731")
|
|
self.assertEqual(first, second)
|
|
|
|
def test_it_creates_missing_parents(self) -> None:
|
|
with tempfile.TemporaryDirectory() as tmp:
|
|
nested = str(Path(tmp) / "machine" / "repo")
|
|
created = mod.create_version_directory(nested, "20260731")
|
|
self.assertTrue(Path(created).is_dir())
|
|
|
|
|
|
class TestVolumeDirectory(unittest.TestCase):
|
|
def test_it_nests_the_volume_under_the_generation(self) -> None:
|
|
with tempfile.TemporaryDirectory() as tmp:
|
|
created = mod.create_volume_directory(tmp, "postgres_data")
|
|
self.assertEqual(Path(created).parent, Path(tmp))
|
|
self.assertTrue(Path(created).is_dir())
|
|
|
|
|
|
class TestMachineId(unittest.TestCase):
|
|
def test_it_takes_the_hash_without_the_filename(self) -> None:
|
|
digest = "a" * 64
|
|
with mock.patch.object(
|
|
mod, "execute_shell_command", return_value=[f"{digest} /etc/machine-id"]
|
|
):
|
|
self.assertEqual(mod.get_machine_id(), digest)
|
|
|
|
|
|
if __name__ == "__main__":
|
|
unittest.main()
|