mirror of
https://github.com/kevinveenbirkenbach/docker-volume-backup.git
synced 2026-08-12 17:34:39 +00:00
Kevin Veen-Birkenbach
cd21f1fa67
Each volume is copied twice into the same destination: once hot with the container running, once cold after it is stopped (backup/app.py:127-131). rsync ran with -b, so --delete did not remove a file the source had dropped between the passes - it renamed it. Stopping a container is exactly what makes the source drop files: a graceful shutdown flushes, and the format rolls its commit point. For an opaque payload the twin is stale bytes nobody reads. For a format that enumerates its own directory it is corruption. Lucene resolves the current commit by parsing every file starting with segments as a radix-36 generation, so a restored segments_3~ raises NumberFormatException, the shard store cannot be read, and the primary is left NO_VALID_SHARD_COPY. With .security-7 unallocatable the reserved elastic user has no password hash, every probe gets HTTP 401, and the container never turns healthy. Seen in infinito-nexus-core CI run 30963648828: the restore drill waited 1200s on elasticsearch while all 29 other containers came back healthy; the generation held segments_3~ next to segments_4 in all three index directories. A run two days earlier passed the same drill because that stack was idle and nothing rolled between the passes - which is why this reads as flaky rather than broken. Reproduced with real rsync in all three shapes: two passes into the same destination with -b leave segments_3~ beside segments_4, without -b only segments_4 survives, and a single pass keeps segments_3. Measured on the same fixtures, dropping -b leaves the predecessor generation byte-identical and keeps the --link-dest hardlinks intact, so the incremental scheme is unaffected; generations get smaller, never larger. --link-dest already provides the cheap incrementals. -b contributed nothing on top of it but the twins, and no caller reads them: the restore path is an unfiltered rsync -avv --delete into the live volume (restore/files.py:35). Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
96 lines
3.7 KiB
Python
96 lines
3.7 KiB
Python
"""Contract of the rsync invocation that copies a volume."""
|
|
|
|
from __future__ import annotations
|
|
|
|
import tempfile
|
|
import unittest
|
|
from pathlib import Path
|
|
from unittest import mock
|
|
|
|
from baudolo.backup import volume as mod
|
|
|
|
|
|
class TestBackupVolume(unittest.TestCase):
|
|
def copy(self, **kwargs) -> str:
|
|
with tempfile.TemporaryDirectory() as tmp:
|
|
defaults = {
|
|
"versions_dir": tmp,
|
|
"volume_name": "demo",
|
|
"volume_dir": str(Path(tmp) / "gen" / "demo"),
|
|
"authoritative": False,
|
|
"source": "/var/lib/docker/volumes/demo/_data/",
|
|
}
|
|
defaults.update(kwargs)
|
|
with mock.patch.object(mod, "execute_shell_command") as run:
|
|
mod.backup_volume(
|
|
defaults.pop("versions_dir"),
|
|
defaults.pop("volume_name"),
|
|
defaults.pop("volume_dir"),
|
|
**defaults,
|
|
)
|
|
return run.call_args[0][0]
|
|
|
|
def test_the_quick_check_pass_carries_no_checksum(self) -> None:
|
|
self.assertNotIn("--checksum", self.copy(authoritative=False))
|
|
|
|
def test_the_authoritative_pass_compares_by_content(self) -> None:
|
|
self.assertIn("--checksum", self.copy(authoritative=True))
|
|
|
|
def test_it_reads_from_the_given_source(self) -> None:
|
|
command = self.copy(source="/snapshot/volumes/demo/_data/")
|
|
self.assertIn("/snapshot/volumes/demo/_data/", command)
|
|
|
|
def test_it_always_deletes_what_the_source_no_longer_has(self) -> None:
|
|
self.assertIn("--delete", self.copy())
|
|
|
|
def test_it_carries_no_kernel_objects_into_a_generation(self) -> None:
|
|
self.assertIn("--no-D", self.copy())
|
|
|
|
def test_it_keeps_no_twin_of_what_the_second_pass_replaces(self) -> None:
|
|
command = self.copy(authoritative=True)
|
|
self.assertIn("rsync -aP ", command)
|
|
self.assertNotIn("--backup", command)
|
|
|
|
def test_it_creates_the_destination(self) -> None:
|
|
with tempfile.TemporaryDirectory() as tmp:
|
|
dest = Path(tmp) / "gen" / "demo"
|
|
with mock.patch.object(mod, "execute_shell_command"):
|
|
mod.backup_volume(
|
|
tmp, "demo", str(dest), authoritative=False, source="/src/"
|
|
)
|
|
self.assertTrue((dest / "files").is_dir())
|
|
|
|
def test_source_is_required(self) -> None:
|
|
with self.assertRaises(TypeError):
|
|
mod.backup_volume("/v", "demo", "/d", authoritative=False)
|
|
|
|
def test_authoritative_is_required(self) -> None:
|
|
with self.assertRaises(TypeError):
|
|
mod.backup_volume("/v", "demo", "/d", source="/src/")
|
|
|
|
|
|
class TestLastBackupDir(unittest.TestCase):
|
|
def test_it_ignores_the_generation_being_written(self) -> None:
|
|
with tempfile.TemporaryDirectory() as tmp:
|
|
current = Path(tmp) / "20260101" / "demo" / "files"
|
|
current.mkdir(parents=True)
|
|
found = mod.get_last_backup_dir(tmp, "demo", str(current) + "/")
|
|
self.assertIsNone(found)
|
|
|
|
def test_it_finds_the_previous_generation(self) -> None:
|
|
with tempfile.TemporaryDirectory() as tmp:
|
|
older = Path(tmp) / "20260101" / "demo" / "files"
|
|
older.mkdir(parents=True)
|
|
current = Path(tmp) / "20260102" / "demo" / "files"
|
|
current.mkdir(parents=True)
|
|
found = mod.get_last_backup_dir(tmp, "demo", str(current) + "/")
|
|
self.assertEqual(found, str(older) + "/")
|
|
|
|
def test_a_first_run_has_no_predecessor(self) -> None:
|
|
with tempfile.TemporaryDirectory() as tmp:
|
|
self.assertIsNone(mod.get_last_backup_dir(tmp, "demo", f"{tmp}/x/"))
|
|
|
|
|
|
if __name__ == "__main__":
|
|
unittest.main()
|