fix(backup): decide snapshot capture per volume

A volume with a backing store of its own is not in a snapshot of the docker data root: it appears there as an existing empty directory, so the copy succeeds, the generation is stamped complete, and the volume is empty in it. The existing check only asked whether the path was inside the snapshot, which that empty directory answers with yes.

The driver, its options and the filesystem the mountpoint sits on now decide, per volume. An uncaptured volume is copied live - correct data without the point in time - while every other volume of the same run keeps its snapshot. One NFS volume no longer costs the whole host its consistent backup.

A volume resolving outside the subject degrades the same way instead of aborting the run.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
This commit is contained in:
2026-08-17 05:26:28 +02:00
parent e80f11d5e4
commit da9c3a1e6f
8 changed files with 359 additions and 26 deletions

View File

@@ -22,8 +22,8 @@ from .layout import (
stamp_directory,
)
from .policy import requires_stop, volume_is_fully_ignored
from .snapshot import volume_snapshot
from .volume import backup_volume, get_storage_path
from .snapshot import snapshot_source, volume_snapshot
from .volume import backup_volume, inspect_backing
def main() -> int:
@@ -86,7 +86,8 @@ def main() -> int:
else:
continue
live_source = get_storage_path(volume_name)
backing = inspect_backing(volume_name)
live_source = backing.source
def copy(
*,
@@ -104,13 +105,15 @@ def main() -> int:
)
if resolve_source is not None:
snapshot_source = resolve_source(live_source)
if os.path.isdir(snapshot_source):
copy(authoritative=True, source=snapshot_source)
source, reason = snapshot_source(
resolve_source, backing, args.snapshot_subject
)
if source is not None:
copy(authoritative=True, source=source)
else:
print(
f"WARNING: volume '{volume_name}' is not in the snapshot "
"(created after it was taken); copying it live instead.",
f"({reason}); copying it live instead.",
flush=True,
)
copy(authoritative=False)

View File

@@ -9,6 +9,13 @@ built for. That also removes the reason to stop containers at all.
The snapshot kind is stated by the caller rather than probed, because falling
back to a live copy when a probe is inconclusive would hand out backups that
look consistent and are not.
Which volumes a snapshot of the subject contains is a different question, and
it is decided per volume: a volume with a backing store of its own appears
inside the snapshot as an existing empty directory, so copying from there
succeeds and stores nothing. Such a volume is copied live instead - correct
data without the point in time - while every other volume of the same run
keeps its snapshot.
"""
from __future__ import annotations
@@ -18,6 +25,7 @@ from collections.abc import Callable, Iterator
from contextlib import contextmanager
from .shell import BackupException, execute_shell_command
from .volume import Backing
KINDS = ("btrfs", "zfs")
@@ -62,6 +70,60 @@ def _zfs(subject: str, name: str, run: Callable[[str], list[str]]) -> tuple[str,
_CREATE = {"btrfs": _btrfs, "zfs": _zfs}
def unsnapshotted(backing: Backing, subject: str) -> str | None:
"""Return why a snapshot of ``subject`` does not hold this volume's data.
Docker mounts a volume's own backing store lazily and unmounts it when the
last consumer stops, so the declaration is what gets checked: it is true at
every moment, where the mount table is only true while a container happens
to hold the volume.
Args:
backing: the volume as the daemon describes it.
subject: the snapshot subject, e.g. ``/var/lib/docker``.
Returns:
The reason, or None when the snapshot holds the volume.
"""
if backing.driver != "local":
return f"it uses the {backing.driver} driver"
if backing.options:
return f"it declares its own backing store {backing.options}"
if not backing.mountpoint:
return "it reports no mountpoint"
real = os.path.realpath(backing.mountpoint)
if os.path.ismount(real):
return f"its mountpoint {backing.mountpoint} sits on its own mount"
try:
crosses = os.stat(real).st_dev != os.stat(os.path.realpath(subject)).st_dev
except OSError as error:
return f"its mountpoint {backing.mountpoint} could not be read: {error}"
if crosses:
return f"its mountpoint {backing.mountpoint} crosses a filesystem boundary"
return None
def snapshot_source(
resolve: Callable[[str], str], backing: Backing, subject: str
) -> tuple[str | None, str]:
"""Resolve where to read a volume from, and why if not from the snapshot.
Returns:
``(path, "")`` to copy from the snapshot, or ``(None, reason)`` to copy
it live.
"""
reason = unsnapshotted(backing, subject)
if reason:
return None, reason
try:
source = resolve(backing.source)
except SnapshotError as error:
return None, str(error)
if not os.path.isdir(source):
return None, "it was created after the snapshot was taken"
return source, ""
@contextmanager
def volume_snapshot(
kind: str,

View File

@@ -1,16 +1,43 @@
from __future__ import annotations
import json
import os
import pathlib
from dataclasses import dataclass, field
from .shell import BackupException, execute_shell_command
def get_storage_path(volume_name: str) -> str:
path = execute_shell_command(
f"docker volume inspect --format '{{{{ .Mountpoint }}}}' {volume_name}"
@dataclass(frozen=True)
class Backing:
"""Where a docker volume actually keeps its data.
Args:
mountpoint: the path the daemon reports.
driver: the volume driver, ``local`` for the built-in one.
options: the driver options; a non-empty map means the mountpoint is a
mount target rather than the storage itself.
"""
mountpoint: str
driver: str = "local"
options: dict = field(default_factory=dict)
@property
def source(self) -> str:
return f"{self.mountpoint}/"
def inspect_backing(volume_name: str) -> Backing:
reported = execute_shell_command(
f"docker volume inspect --format '{{{{json .}}}}' {volume_name}"
)[0]
return f"{path}/"
data = json.loads(reported)
return Backing(
data.get("Mountpoint") or "",
data.get("Driver") or "",
data.get("Options") or {},
)
def get_last_backup_dir(