fix(backup): mount the zfs snapshot itself so a container can read it

The zfs snapshot was read through <subject>/.zfs/snapshot/<name>. The
kernel automounts that directory through a usermode helper that runs in
the host's mount namespace, so a containerised baudolo never sees the
mount and finds no snapshot. The snapshot is now mounted explicitly at
<subject>/.baudolo-<tag>, beside where btrfs carves its own, and removed
in order: umount, rmdir, zfs destroy. A failed mount destroys the
snapshot at once instead of leaking one per run.

The e2e suite could not reach this code at all: zpool create on the /img
file failed with "no such pool or dataset", because the kernel opens
vdevs from a taskq thread that resolves paths in the host's root, where
the container's /img does not exist. The pool now sits on a loop device,
whose /dev/loopN node the kernel creates on the host as well, and it is
destroyed on exit once this script created it, since a pool is
kernel-wide.

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
This commit is contained in:
kevinveenbirkenbachandClaude Opus 5.5 committed 2026-10-18 00:22:53 +02:00
1 parent 389b418f42
commit 0735e5fa7b
3 files changed
+90 -15

No files matched your search

+30 -11
View File
@@ -58,27 +58,50 @@ def _resolver(subject: str, root: str) -> Callable[[str], str]:
return resolve
def _remove(
root: str, commands: list[list[str]], run: Callable[[list[str]], list[str]]
) -> None:
try:
for command in commands:
run(command)
except BackupError as error:
# Raising here would also mask whatever the body raised.
print(f"WARNING: {root} could not be removed: {error}", flush=True)
def _btrfs(
subject: str, name: str, run: Callable[[list[str]], list[str]]
) -> tuple[str, list[str]]:
) -> tuple[str, list[list[str]]]:
# The snapshot goes inside the subject, never beside it: the kernel rejects
# a snapshot whose destination is on another filesystem, which is exactly
# what the parent directory is when the subject is a mountpoint of its own.
target = str(Path(os.path.abspath(subject)) / f".{name}") # noqa: PTH100 - see _resolver
run(["btrfs", "subvolume", "snapshot", "-r", subject, target])
return target, ["btrfs", "subvolume", "delete", target]
return target, [["btrfs", "subvolume", "delete", target]]
def _zfs(
subject: str, name: str, run: Callable[[list[str]], list[str]]
) -> tuple[str, list[str]]:
) -> tuple[str, list[list[str]]]:
output = run(["zfs", "list", "-H", "-o", "name", subject])
dataset = (output[0] if output else "").strip()
if not dataset:
raise SnapshotError(f"no zfs dataset is mounted at {subject}")
run(["zfs", "snapshot", f"{dataset}@{name}"])
root = str(Path(subject) / ".zfs" / "snapshot" / name)
return root, ["zfs", "destroy", f"{dataset}@{name}"]
snapshot = f"{dataset}@{name}"
# Exception: mounted here rather than read through .zfs/snapshot, which the
# kernel automounts via a usermode helper in the host's mount namespace,
# so a containerised run never sees it.
root = str(Path(os.path.abspath(subject)) / f".{name}") # noqa: PTH100 - see _resolver
run(["zfs", "snapshot", snapshot])
remove = [["zfs", "destroy", snapshot]]
try:
run(["mkdir", root])
remove.insert(0, ["rmdir", root])
run(["mount", "-t", "zfs", snapshot, root])
except BaseException:
_remove(root, remove, run)
raise
return root, [["umount", root], *remove]
_CREATE = {"btrfs": _btrfs, "zfs": _zfs}
@@ -169,8 +192,4 @@ def volume_snapshot(
try:
yield _resolver(subject, root)
finally:
try:
run(remove)
except BackupError as error:
# Raising here would also mask whatever the body raised.
print(f"WARNING: {root} could not be removed: {error}", flush=True)
_remove(root, remove, run)