Release version 7.1.1

The entrypoint installs root@localhost without unix_socket auth and sets
its password during init, so the passwordless socket probe only passed
when it landed in the window before SET PASSWORD. Missing that window
timed the e2e MariaDB suites out at random.

The probe now authenticates with the root password it already received
and requires @@skip_networking = 0, so the entrypoint's temporary server
no longer counts as ready. The anonymous-preemption bootstrap logs in
with the root password as well.

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>

CHANGELOG.md

@@ -1,5 +1,39 @@
 # Changelog
 
+## [7.1.1] - 2026-10-17
+
+Fixed:
+
+- Tests: e2e MariaDB probe ran root passwordless and timed out at random
+- Tests: probe now logs in with the root password, skips the temp server
+- Tests: anonymous-preemption bootstrap now uses the root password too
+
+Upgrade notes:
+
+- 7.1.0 never reached stable: its CI failed, no image was published
+- 7.1.1 is the first published -aHAX build; 7.1.0 upgrade notes apply
+
+## [7.1.0] - 2026-10-17
+
+Fixed:
+
+- Backup: rsync -a stored no xattrs, ACLs or hardlinks; now -aHAX
+- Restore: restore_volume_files had the same gap; now -aHAX too
+- An OpenCloud volume lost its storage metadata through a DR drill
+
+Upgrade notes:
+
+- First backup re-copies every attribute-carrying volume once in full
+- A destination without xattr support now fails the backup run outright
+- exFAT, xattr-less NFS and object-storage FUSE mounts must move first
+
+## [7.0.2] - 2026-09-23
+
+* Backup: failed live pre-copy no longer aborts when a stopped copy follows
+* Backup: stopped --checksum copy replaces pre-copy hit by live writer (rc 23)
+* Backup: failing sole live copy or failing stopped copy still fails the run
+* Tests: e2e live writer shrinking files mid-read reproduces the rsync failure
+
 ## [7.0.1] - 2026-08-18
 
 - Restore: *--empty* no longer aborts on a database that carries an extension.

pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "backup-docker-to-local"
-version = "7.0.1"
+version = "7.1.1"
 description = "Backup Docker volumes to local with rsync and optional DB dumps."
 readme = "README.md"
 requires-python = ">=3.9"
@@ -19,7 +19,7 @@ dependencies = [
 [project.optional-dependencies]
 # Pinned: a ruff minor bump changes which rules fire, and `make test` gates on
 # a clean run, so an unpinned lint would fail the suite on an unrelated day.
-lint = ["ruff==0.16.1"]
+lint = ["ruff==0.16.7"]
 
 [project.scripts]
 baudolo = "baudolo.backup.__main__:main"

src/baudolo/backup/app.py

@@ -23,6 +23,7 @@ from .layout import (
     write_manifest,
 )
 from .policy import requires_stop, volume_is_fully_ignored
+from .shell import BackupError
 from .snapshot import snapshot_source, volume_snapshot
 from .volume import backup_volume, inspect_backing
 
@@ -125,13 +126,23 @@ def main() -> int:
                     copy(authoritative=False)
                 continue
 
-            copy(authoritative=False)
-            if requires_stop(containers, args.images_no_stop_required):
-                stoppable = filter_stoppable(containers)
-                change_containers_status(stoppable, "stop")
-                copy(authoritative=True)
-                if not args.shutdown:
-                    change_containers_status(stoppable, "start")
+            if not requires_stop(containers, args.images_no_stop_required):
+                copy(authoritative=False)
+                continue
+
+            try:
+                copy(authoritative=False)
+            except BackupError as error:
+                print(
+                    f"WARNING: live pre-copy of volume '{volume_name}' failed; "
+                    f"the copy with its containers stopped replaces it.\n{error}",
+                    flush=True,
+                )
+            stoppable = filter_stoppable(containers)
+            change_containers_status(stoppable, "stop")
+            copy(authoritative=True)
+            if not args.shutdown:
+                change_containers_status(stoppable, "start")
 
     write_manifest(version_dir, outcomes)
     stamp_directory(version_dir)

src/baudolo/backup/volume.py

@@ -75,7 +75,7 @@ def backup_volume(
     pathlib.Path(dest).mkdir(parents=True, exist_ok=True)
 
     last = get_last_backup_dir(versions_dir, volume_name, dest)
-    cmd = ["rsync", "-aP", "--no-D", "--delete", "--delete-excluded"]
+    cmd = ["rsync", "-aHAX", "-P", "--no-D", "--delete", "--delete-excluded"]
     if authoritative:
         cmd.append("--checksum")
     if last:

src/baudolo/restore/files.py

@@ -59,6 +59,6 @@ def restore_volume_files(volume_name: str, backup_files_dir: str) -> int:
     # rsync reads "dir/" as its contents and "dir" as the directory itself.
     src = f"{Path(backup_files_dir)}{os.sep}"
     dest = f"{Path(mountpoint)}{os.sep}"
-    run(["rsync", "-avv", "--delete", src, dest])
+    run(["rsync", "-aHAX", "-vv", "--delete", src, dest])
     print("File restore complete.")
     return 0

tests/e2e/helpers/fixtures.py

@@ -25,7 +25,7 @@ def backup_run(
     images_no_stop_required: list[str],
     images_no_backup_required: list[str] | None = None,
     only_sql: bool = False,
-) -> None:
+) -> subprocess.CompletedProcess:
     cmd = [
         "baudolo",
         "--compose-dir",
@@ -49,7 +49,7 @@ def backup_run(
         cmd += ["--only-sql"]
 
     try:
-        run(cmd, capture=True, check=True)
+        return run(cmd, capture=True, check=True)
     except subprocess.CalledProcessError as e:
         print(">>> baudolo failed (exit code:", e.returncode, ")")
         if e.stdout:

tests/e2e/helpers/process.py

@@ -96,12 +96,13 @@ def wait_for_mariadb(
     container: str, *, root_password: str, timeout_s: int = 90
 ) -> None:
     """
-    Liveness probe for MariaDB.
+    Readiness probe for MariaDB, as root over the socket.
 
-    IMPORTANT (MariaDB 11):
-    Root TCP auth is often restricted (unix_socket auth), so a TCP ping like
-    `mariadb-admin -uroot -p... -h localhost ping` can fail even though the server is up.
-    We therefore check readiness via a socket-based query.
+    The entrypoint drops root@127.0.0.1, so root is socket-only, and it
+    installs root@localhost without unix_socket auth: a probe without the
+    password only passes in the init window before the password is set.
+    `@@skip_networking` must be 0 so the entrypoint's temporary server,
+    which shuts down right after init, does not count as ready.
     """
     deadline = time.time() + timeout_s
     while time.time() < deadline:
@@ -112,12 +113,15 @@ def wait_for_mariadb(
                 container,
                 "sh",
                 "-lc",
-                'mariadb -uroot --protocol=socket -e "SELECT 1;"',
+                (
+                    f"mariadb -uroot -p{root_password} --protocol=socket "
+                    '-N -e "SELECT @@skip_networking;"'
+                ),
             ],
             capture=True,
             check=False,
         )
-        if p.returncode == 0:
+        if p.returncode == 0 and p.stdout.strip() == "0":
             return
         time.sleep(1)
     raise TimeoutError(

tests/e2e/test_e2e_files_live_writer_precopy.py

@@ -0,0 +1,110 @@
+"""A writer that shrinks files mid-read fails the live pre-copy, not the run."""
+
+import unittest
+
+from .helpers import (
+    backup_path,
+    backup_run,
+    cleanup_docker,
+    create_minimal_compose_dir,
+    ensure_empty_dir,
+    latest_version_dir,
+    require_docker,
+    run,
+    unique,
+    wait_for_log,
+    write_databases_csv,
+)
+
+CHURN_FILES = 8
+
+WRITER = f"""
+trap 'exit 0' TERM
+echo hello > /data/hello.txt
+for i in $(seq 1 {CHURN_FILES}); do
+  (while :; do truncate -s 0 /data/churn$i; truncate -s 16M /data/churn$i; done) &
+done
+echo ready
+wait
+"""
+
+
+class TestE2EFilesLiveWriterPreCopy(unittest.TestCase):
+    @classmethod
+    def setUpClass(cls) -> None:
+        require_docker()
+        cls.prefix = unique("baudolo-e2e-live-writer")
+        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.volume = f"{cls.prefix}-vol"
+        cls.writer = f"{cls.prefix}-writer"
+        cls.containers = [cls.writer]
+        cls.volumes = [cls.volume]
+
+        run(["docker", "volume", "create", cls.volume])
+        run(
+            [
+                "docker",
+                "run",
+                "-d",
+                "--name",
+                cls.writer,
+                "-v",
+                f"{cls.volume}:/data",
+                "alpine:3.20",
+                "sh",
+                "-c",
+                WRITER,
+            ]
+        )
+        wait_for_log(cls.writer, "ready")
+
+        cls.databases_csv = f"/tmp/{cls.prefix}/databases.csv"
+        write_databases_csv(cls.databases_csv, [])
+
+        cls.result = backup_run(
+            backups_dir=cls.backups_dir,
+            repo_name=cls.repo_name,
+            compose_dir=cls.compose_dir,
+            databases_csv=cls.databases_csv,
+            database_containers=["dummy-db"],
+            images_no_stop_required=["dummy-image"],
+        )
+
+        cls.hash, cls.version = latest_version_dir(cls.backups_dir, cls.repo_name)
+
+    @classmethod
+    def tearDownClass(cls) -> None:
+        cleanup_docker(containers=cls.containers, volumes=cls.volumes)
+
+    def test_the_live_pre_copy_hit_the_writer(self) -> None:
+        self.assertIn(
+            f"WARNING: live pre-copy of volume '{self.volume}' failed",
+            self.result.stdout,
+            "the writer never shrank a file under rsync, so this run proves nothing",
+        )
+
+    def test_the_stopped_copy_captured_the_volume(self) -> None:
+        files = (
+            backup_path(self.backups_dir, self.repo_name, self.version, self.volume)
+            / "files"
+        )
+        self.assertEqual((files / "hello.txt").read_text().strip(), "hello")
+        self.assertEqual(
+            sorted(p.name for p in files.glob("churn*")),
+            sorted(f"churn{i}" for i in range(1, CHURN_FILES + 1)),
+        )
+
+    def test_the_writer_runs_again_after_the_backup(self) -> None:
+        state = run(
+            ["docker", "inspect", "-f", "{{.State.Running}}", self.writer]
+        ).stdout.strip()
+        self.assertEqual(state, "true")
+
+
+if __name__ == "__main__":
+    unittest.main()

tests/e2e/test_e2e_mariadb_anonymous_preemption.py

@@ -100,7 +100,10 @@ class TestE2EMariaDBAnonymousPreemption(unittest.TestCase):
                 cls.db_container,
                 "sh",
                 "-lc",
-                f'mariadb -uroot --protocol=socket -e "{bootstrap_sql}"',
+                (
+                    f"mariadb -uroot -p{cls.root_password} --protocol=socket "
+                    f'-e "{bootstrap_sql}"'
+                ),
             ]
         )
 

tests/unit/backup/test_app_live_precopy.py

@@ -0,0 +1,70 @@
+"""Contract of app.main's live copy when no snapshot is taken."""
+
+from __future__ import annotations
+
+import unittest
+from unittest import mock
+
+from baudolo.backup import app
+from baudolo.backup.shell import BackupError
+from baudolo.backup.volume import Backing
+
+from . import BASE_ARGV
+
+
+def drive(*, stop: bool, fail_live: bool) -> list[str]:
+    events: list[str] = []
+
+    def record(versions_dir, volume_name, volume_dir, *, authoritative, source):
+        events.append("authoritative" if authoritative else "live")
+        if fail_live and not authoritative:
+            raise BackupError("rsync exit code 23")
+
+    with (
+        mock.patch("sys.argv", BASE_ARGV),
+        mock.patch.object(app, "get_machine_id", return_value="machine"),
+        mock.patch.object(app, "create_version_directory", return_value="/gen"),
+        mock.patch.object(app, "create_volume_directory", return_value="/gen/vol"),
+        mock.patch.object(app, "load_databases_df", return_value=None),
+        mock.patch.object(app, "docker_volume_names", return_value=["vol"]),
+        mock.patch.object(app, "containers_using_volume", return_value=["c"]),
+        mock.patch.object(app, "volume_is_fully_ignored", return_value=False),
+        mock.patch.object(app, "backup_dumps_for_volume", return_value=(False, False)),
+        mock.patch.object(
+            app,
+            "inspect_backing",
+            return_value=Backing("/var/lib/docker/volumes/vol/_data"),
+        ),
+        mock.patch.object(app, "requires_stop", return_value=stop),
+        mock.patch.object(app, "filter_stoppable", return_value=["c"]),
+        mock.patch.object(
+            app,
+            "change_containers_status",
+            side_effect=lambda containers, status: events.append(status),
+        ),
+        mock.patch.object(app, "write_manifest"),
+        mock.patch.object(app, "stamp_directory"),
+        mock.patch.object(app, "handle_docker_compose_services"),
+        mock.patch.object(app, "backup_volume", side_effect=record),
+    ):
+        app.main()
+    return events
+
+
+class TestLivePreCopy(unittest.TestCase):
+    def test_a_failed_pre_copy_is_replaced_by_the_stopped_copy(self) -> None:
+        self.assertEqual(
+            drive(stop=True, fail_live=True),
+            ["live", "stop", "authoritative", "start"],
+        )
+
+    def test_a_failed_live_copy_without_a_stop_aborts_the_run(self) -> None:
+        with self.assertRaises(BackupError):
+            drive(stop=False, fail_live=True)
+
+    def test_a_volume_without_a_stop_is_copied_live_once(self) -> None:
+        self.assertEqual(drive(stop=False, fail_live=False), ["live"])
+
+
+if __name__ == "__main__":
+    unittest.main()

tests/unit/backup/test_volume.py

@@ -46,9 +46,12 @@ class TestBackupVolume(unittest.TestCase):
     def test_it_carries_no_kernel_objects_into_a_generation(self) -> None:
         self.assertIn("--no-D", self.copy())
 
+    def test_it_stores_the_metadata_a_restore_has_to_give_back(self) -> None:
+        self.assertIn("-aHAX", self.copy())
+
     def test_it_keeps_no_twin_of_what_the_second_pass_replaces(self) -> None:
         command = self.copy(authoritative=True)
-        self.assertEqual(command[:2], ["rsync", "-aP"])
+        self.assertEqual(command[:3], ["rsync", "-aHAX", "-P"])
         self.assertNotIn("--backup", command)
 
     def test_it_creates_the_destination(self) -> None: