Release version 7.0.2

A volume whose containers must stop was copied twice: live first, then
with the containers stopped and --checksum. A live writer that truncates
a file under rsync (read errors mapping ...: No data available (61),
exit 23) aborted the run in the first pass, before the containers were
stopped, although the second pass rewrites every differing file anyway.
Seen in infinito-nexus CI on kix_kix_shared/objecticons.

The live copy now only warns when a stopped copy follows. Without a stop
it stays the only copy and still fails the run, and a failing stopped
copy still fails it.

The e2e test drives a writer that shrinks files mid-read; without the
fix it reproduces the CI failure verbatim.

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

CHANGELOG.md

@@ -1,5 +1,29 @@
 # Changelog
 
+## [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.
+  The pre-clean picked its candidates by owner, on the stated assumption that
+  extension members are superuser-owned and would therefore never be selected.
+  That holds only when a superuser installed the extension: a role that
+  installs one itself owns its functions, so they were listed for a one-by-one
+  *DROP* that postgres refuses — *cannot drop function
+  vector_in(cstring,oid,integer) because extension vector requires it*. Under
+  *ON_ERROR_STOP* that ends the whole restore, which is how a generation of an
+  application declaring the *vector* extension became unreplayable. Membership
+  now comes from *pg_depend* rather than from ownership; each branch carries
+  its oid and classid so one *NOT EXISTS* covers all seven instead of seven
+  separate predicates, and the schema branch is guarded too because an
+  extension can own a schema. Skipping the members suffices — the dump's
+  *CREATE EXTENSION IF NOT EXISTS* finds the surviving extension either way.
+
 ## [7.0.0] - 2026-08-18
 
 Breaking:

pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "backup-docker-to-local"
-version = "7.0.0"
+version = "7.0.2"
 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/restore/db/empty_preclean.sql

@@ -3,8 +3,12 @@
 -- would run every DROP in one transaction and exhaust max_locks_per_transaction on
 -- large schemas (e.g. gitlab). Also drops user-owned non-public schemas so a dump
 -- that CREATE SCHEMAs (e.g. discourse's discourse_functions) does not fail on an
--- already-existing schema. Extension members (pg_trgm's set_limit) are
--- superuser-owned; IF EXISTS absorbs the CASCADE fallout.
+-- already-existing schema. Objects belonging to an extension are skipped: postgres
+-- refuses to drop them one by one ("cannot drop function vector_in(...) because
+-- extension vector requires it"), and the dump's CREATE EXTENSION IF NOT EXISTS
+-- finds the surviving extension either way. Owning them is not enough to make them
+-- droppable - an extension a role installed itself is owned by that role, so the
+-- owner filter alone lets pgvector's members through.
 SELECT format('DROP %s IF EXISTS public.%s CASCADE', obj.type, obj.name)
   FROM (
     SELECT format('%I', c.relname) AS name,
@@ -13,7 +17,8 @@ SELECT format('DROP %s IF EXISTS public.%s CASCADE', obj.type, obj.name)
              WHEN 'm' THEN 'MATERIALIZED VIEW'
              WHEN 'f' THEN 'FOREIGN TABLE'
              ELSE 'TABLE'
-           END AS type
+           END AS type,
+           c.oid AS objid, 'pg_class'::regclass AS classid
       FROM pg_class c JOIN pg_namespace n ON n.oid = c.relnamespace
      WHERE n.nspname = 'public' AND c.relkind IN ('r', 'p', 'v', 'm', 'f')
        AND pg_get_userbyid(c.relowner) = current_user
@@ -21,17 +26,20 @@ SELECT format('DROP %s IF EXISTS public.%s CASCADE', obj.type, obj.name)
     -- Overloaded functions share a proname; DROP needs the identity
     -- signature or psql aborts with "function name is not unique".
     SELECT format('%I(%s)', p.proname, pg_get_function_identity_arguments(p.oid)) AS name,
-           CASE p.prokind WHEN 'p' THEN 'PROCEDURE' ELSE 'FUNCTION' END AS type
+           CASE p.prokind WHEN 'p' THEN 'PROCEDURE' ELSE 'FUNCTION' END AS type,
+           p.oid AS objid, 'pg_proc'::regclass AS classid
       FROM pg_proc p JOIN pg_namespace n ON n.oid = p.pronamespace
      WHERE n.nspname = 'public' AND p.prokind IN ('f', 'p', 'w')
        AND pg_get_userbyid(p.proowner) = current_user
     UNION ALL
-    SELECT format('%I', c.relname) AS name, 'SEQUENCE' AS type
+    SELECT format('%I', c.relname) AS name, 'SEQUENCE' AS type,
+           c.oid AS objid, 'pg_class'::regclass AS classid
       FROM pg_class c JOIN pg_namespace n ON n.oid = c.relnamespace
      WHERE n.nspname = 'public' AND c.relkind = 'S'
        AND pg_get_userbyid(c.relowner) = current_user
     UNION ALL
-    SELECT format('%I', t.typname) AS name, 'TYPE' AS type
+    SELECT format('%I', t.typname) AS name, 'TYPE' AS type,
+           t.oid AS objid, 'pg_type'::regclass AS classid
       FROM pg_type t JOIN pg_namespace n ON n.oid = t.typnamespace
      WHERE n.nspname = 'public'
        AND pg_get_userbyid(t.typowner) = current_user
@@ -40,25 +48,36 @@ SELECT format('DROP %s IF EXISTS public.%s CASCADE', obj.type, obj.name)
                   SELECT 1 FROM pg_class c2
                    WHERE c2.oid = t.typrelid AND c2.relkind = 'c')))
     UNION ALL
-    SELECT format('%I', col.collname) AS name, 'COLLATION' AS type
+    SELECT format('%I', col.collname) AS name, 'COLLATION' AS type,
+           col.oid AS objid, 'pg_collation'::regclass AS classid
       FROM pg_collation col JOIN pg_namespace n ON n.oid = col.collnamespace
      WHERE n.nspname = 'public'
        AND pg_get_userbyid(col.collowner) = current_user
     UNION ALL
-    SELECT format('%I', ts.cfgname) AS name, 'TEXT SEARCH CONFIGURATION' AS type
+    SELECT format('%I', ts.cfgname) AS name, 'TEXT SEARCH CONFIGURATION' AS type,
+           ts.oid AS objid, 'pg_ts_config'::regclass AS classid
       FROM pg_ts_config ts JOIN pg_namespace n ON n.oid = ts.cfgnamespace
      WHERE n.nspname = 'public'
        AND pg_get_userbyid(ts.cfgowner) = current_user
     UNION ALL
-    SELECT format('%I', d.dictname) AS name, 'TEXT SEARCH DICTIONARY' AS type
+    SELECT format('%I', d.dictname) AS name, 'TEXT SEARCH DICTIONARY' AS type,
+           d.oid AS objid, 'pg_ts_dict'::regclass AS classid
       FROM pg_ts_dict d JOIN pg_namespace n ON n.oid = d.dictnamespace
      WHERE n.nspname = 'public'
        AND pg_get_userbyid(d.dictowner) = current_user
   ) obj
+ WHERE NOT EXISTS (
+         SELECT 1 FROM pg_depend dep
+          WHERE dep.classid = obj.classid AND dep.objid = obj.objid
+            AND dep.deptype = 'e')
 UNION ALL
 SELECT format('DROP SCHEMA IF EXISTS %I CASCADE', n.nspname)
   FROM pg_namespace n
  WHERE NOT starts_with(n.nspname, 'pg_')
    AND n.nspname NOT IN ('public', 'information_schema')
    AND pg_get_userbyid(n.nspowner) = current_user
+   AND NOT EXISTS (
+         SELECT 1 FROM pg_depend dep
+          WHERE dep.classid = 'pg_namespace'::regclass AND dep.objid = n.oid
+            AND dep.deptype = 'e')
 \gexec

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/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_postgres_empty_drop_hard.py

@@ -24,6 +24,7 @@ from .helpers import (
 # is not unique") and english_stem_nostop reproduces taiga's text search
 # dictionary abort (duplicate pg_ts_dict_dictname_index).
 SCENARIO_SQL = (
+    "CREATE EXTENSION pg_trgm;"
     "CREATE SCHEMA discourse_functions;"
     "CREATE TABLE discourse_functions.helper (id int);"
     "INSERT INTO discourse_functions.helper VALUES (1);"
@@ -166,6 +167,13 @@ class TestE2EPostgresEmptyDropHard(unittest.TestCase):
         )
         self.assertEqual(self._scalar("SELECT public.f(41) + public.f();"), "42")
 
+    def test_the_extension_survived_the_preclean(self) -> None:
+        self.assertEqual(
+            self._scalar("SELECT count(*) FROM pg_extension WHERE extname='pg_trgm';"),
+            "1",
+        )
+        self.assertEqual(self._scalar("SELECT similarity('abc','abc')::int;"), "1")
+
     def test_text_search_dictionary_restored_once(self) -> None:
         self.assertEqual(
             self._scalar(

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()