Release version 1.8.0

Treating every failed swarm-task inspect as skippable opened a false-green
window: a transient inspect failure on a still-running, non-whitelisted
container skipped the stop and backed the volume up hot while the run
reported success. Re-check whether the container is still listed; only a
genuinely vanished container skips, an existing one re-raises so a broken
daemon keeps failing the run loudly. Covered by unit tests for both paths.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

.github/dependabot.yml

@@ -0,0 +1,21 @@
+---
+version: 2
+updates:
+  - package-ecosystem: github-actions
+    directory: /
+    schedule:
+      interval: weekly
+    groups:
+      actions:
+        patterns:
+          - "*"
+
+  - package-ecosystem: docker
+    directory: /
+    schedule:
+      interval: weekly
+
+  - package-ecosystem: pip
+    directory: /
+    schedule:
+      interval: weekly

.github/workflows/dependabot-auto-merge.yml

@@ -0,0 +1,29 @@
+---
+name: Dependabot auto-merge
+
+on: pull_request
+
+permissions:
+  contents: write
+  pull-requests: write
+
+jobs:
+  auto-merge:
+    # Enable auto-merge for minor/patch dependency bumps; majors stay manual.
+    # The merge only happens once every required status check (make test) is
+    # green, so the CI stays the gate.
+    if: github.actor == 'dependabot[bot]'
+    runs-on: ubuntu-latest
+    steps:
+      - name: Fetch dependency metadata
+        id: metadata
+        uses: dependabot/fetch-metadata@v2
+        with:
+          github-token: ${{ secrets.GITHUB_TOKEN }}
+
+      - name: Enable auto-merge (minor + patch)
+        if: steps.metadata.outputs.update-type != 'version-update:semver-major'
+        run: gh pr merge --auto --squash "$PR_URL"
+        env:
+          PR_URL: ${{ github.event.pull_request.html_url }}
+          GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}

CHANGELOG.md

@@ -1,3 +1,39 @@
+# Changelog
+
+## [1.8.0] - 2026-07-11
+
+Swarm-aware backups and replayable restores.
+
+- Backup: swarm task containers are never stopped or started manually
+  anymore; they are skipped visibly and backed up hot, while the sql dump
+  stays the consistent database backup.
+- Backup: a container that vanishes between listing and inspect no longer
+  aborts the run; a failing inspect on a container that still exists keeps
+  failing loudly.
+- Backup: pg_dump runs with the no-owner and no-privileges flags so dumps
+  are replayable by the owning app user.
+- Restore: the mariadb empty mode drops all tables in one client session
+  with FOREIGN_KEY_CHECKS disabled; FK-linked parent tables no longer abort
+  the replay with ERROR 1451.
+- Restore: the postgres empty mode drops only current-user-owned objects,
+  and the replay skips superuser-only dump lines without ever touching
+  COPY data blocks.
+- Restore: the replay streams the dump through a temp file instead of
+  buffering it in memory; multi-GB dumps no longer OOM the restore.
+- Tooling: the e2e runner reaches the DinD daemon via docker exec instead
+  of a host-published unencrypted API port.
+- Tooling: new end-to-end test reproducing the swarm stop flake, plus unit
+  tests for the restore filters and the swarm probes; the suite is 36 unit,
+  9 integration and 30 e2e tests.
+- Tooling: Dependabot with auto-merge for minor and patch updates.
+
+## [1.7.1] - 2026-05-26
+
+* 🔌 MariaDB SQL backups now connect over TCP loopback so the dump always matches the same wildcard-host grant the application uses — no more surprise `ERROR 1045 Access denied` when a localhost-bound auth row preempts.
+* 🧪 New regression and bug-repro tests pin the TCP behaviour and prove it under the exact preemption setup that caused the production failure on MariaDB 12.
+* 🩺 E2E test infrastructure: DinD bridge and inner daemon now default to MTU 1280 so registry pulls survive host paths with broken PMTUD (override via `E2E_DIND_MTU`).
+
+
 ## [1.7.0] - 2026-02-07
 
 * 🚀 Backup jobs now support all valid Docker Compose file names – case-insensitive and hassle-free.

pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "backup-docker-to-local"
-version = "1.7.0"
+version = "1.8.0"
 description = "Backup Docker volumes to local with rsync and optional DB dumps."
 readme = "README.md"
 requires-python = ">=3.9"

scripts/test-e2e.sh

@@ -16,15 +16,24 @@ DIND="${E2E_DIND_NAME:-baudolo-e2e-dind}"
 DIND_VOL="${E2E_DIND_VOL:-baudolo-e2e-dind-data}"
 E2E_TMP_VOL="${E2E_TMP_VOL:-baudolo-e2e-tmp}"
 
-DIND_HOST="${E2E_DIND_HOST:-tcp://127.0.0.1:2375}"
+# Host-side access to the DinD daemon goes through `docker exec` (dind()
+# below) instead of a host-published port: port publishing is not reachable
+# from every environment (sandboxed runners, hosts with broken loopback
+# publishing), while exec only needs the outer docker socket. The TCP
+# listener stays for the test container inside the dedicated network.
 DIND_HOST_IN_NET="${E2E_DIND_HOST_IN_NET:-tcp://${DIND}:2375}"
 
+dind() { docker exec "${DIND}" docker "$@"; }
+dind_stdin() { docker exec -i "${DIND}" docker "$@"; }
+
 IMG="${E2E_IMAGE:-baudolo:local}"
 RSYNC_IMG="${E2E_RSYNC_IMAGE:-ghcr.io/kevinveenbirkenbach/alpine-rsync}"
 
 READY_TIMEOUT_SECONDS="${E2E_READY_TIMEOUT_SECONDS:-120}"
 ARTIFACTS_DIR="${E2E_ARTIFACTS_DIR:-./artifacts}"
 
+DIND_MTU="${E2E_DIND_MTU:-1280}"
+
 KEEP_ON_FAIL="${E2E_KEEP_ON_FAIL:-0}"
 KEEP_VOLUMES="${E2E_KEEP_VOLUMES:-0}"
 DEBUG_SHELL="${E2E_DEBUG_SHELL:-0}"
@@ -46,8 +55,8 @@ dump_debug() {
     echo "=== Host docker info ==="
     docker info || true
     echo
-    echo "=== DinD reachable? (docker -H ${DIND_HOST} version) ==="
+    echo "=== DinD reachable? (docker exec ${DIND} docker version) ==="
-    docker -H "${DIND_HOST}" version || true
+    dind version || true
     echo
   } > "${ARTIFACTS_DIR}/debug-host-${TS}.txt" 2>&1 || true
 
@@ -56,45 +65,31 @@ dump_debug() {
 
   # DinD state
   {
-    echo "=== docker -H ps -a ==="
+    echo "=== dind ps -a ==="
-    docker -H "${DIND_HOST}" ps -a || true
+    dind ps -a || true
     echo
-    echo "=== docker -H images ==="
+    echo "=== dind images ==="
-    docker -H "${DIND_HOST}" images || true
+    dind images || true
     echo
-    echo "=== docker -H network ls ==="
+    echo "=== dind network ls ==="
-    docker -H "${DIND_HOST}" network ls || true
+    dind network ls || true
     echo
-    echo "=== docker -H volume ls ==="
+    echo "=== dind volume ls ==="
-    docker -H "${DIND_HOST}" volume ls || true
+    dind volume ls || true
     echo
-    echo "=== docker -H system df ==="
+    echo "=== dind system df ==="
-    docker -H "${DIND_HOST}" system df || true
+    dind system df || true
   } > "${ARTIFACTS_DIR}/debug-dind-${TS}.txt" 2>&1 || true
 
   # Try to capture recent events (best effort; might be noisy)
-  docker -H "${DIND_HOST}" events --since 10m --until 0s \
+  dind events --since 10m --until 0s \
     > "${ARTIFACTS_DIR}/dind-events-${TS}.txt" 2>&1 || true
 
-  # Dump shared /tmp content from the tmp volume:
+  # The shared tmp volume is mounted at /tmp inside the DinD container
-  # We create a temporary container that mounts the volume, then tar its content.
+  # itself, so tar it there and copy it out with the outer daemon.
-  # (Does not rely on host filesystem paths.)
   log "DEBUG: archiving shared /tmp (volume ${E2E_TMP_VOL})"
-  docker -H "${DIND_HOST}" run --rm \
+  docker exec "${DIND}" tar -czf "/tmpdump-${TS}.tar.gz" -C /tmp . >/dev/null 2>&1 || true
-    -v "${E2E_TMP_VOL}:/tmp" \
+  docker cp "${DIND}:/tmpdump-${TS}.tar.gz" "${ARTIFACTS_DIR}/e2e-tmp-${TS}.tar.gz" >/dev/null 2>&1 || true
-    alpine:3.20 \
-    bash -lc 'cd /tmp && tar -czf /out.tar.gz . || true' \
-    >/dev/null 2>&1 || true
-
-  # The above writes inside the container FS, not to host. So do it properly:
-  # Use "docker cp" from a temp container.
-  local tmpc="baudolo-e2e-tmpdump-${TS}"
-  docker -H "${DIND_HOST}" rm -f "${tmpc}" >/dev/null 2>&1 || true
-  docker -H "${DIND_HOST}" create --name "${tmpc}" -v "${E2E_TMP_VOL}:/tmp" alpine:3.20 \
-    bash -lc 'cd /tmp && tar -czf /tmpdump.tar.gz . || true' >/dev/null
-  docker -H "${DIND_HOST}" start -a "${tmpc}" >/dev/null 2>&1 || true
-  docker -H "${DIND_HOST}" cp "${tmpc}:/tmpdump.tar.gz" "${ARTIFACTS_DIR}/e2e-tmp-${TS}.tar.gz" >/dev/null 2>&1 || true
-  docker -H "${DIND_HOST}" rm -f "${tmpc}" >/dev/null 2>&1 || true
 
   log "DEBUG: artifacts written:"
   find "${ARTIFACTS_DIR}" -maxdepth 1 -mindepth 1 -print | sed 's/^/   /' || true
@@ -105,9 +100,9 @@ cleanup() {
     log "KEEP_ON_FAIL=1 and failure detected -> skipping cleanup."
     log "Next steps:"
     echo "   - Inspect DinD logs: docker logs ${DIND} | less"
-    echo "   - Use DinD daemon:  docker -H ${DIND_HOST} ps -a"
+    echo "   - Use DinD daemon:  docker exec ${DIND} docker ps -a"
-    echo "   - Shared tmp vol:   docker -H ${DIND_HOST} run --rm -v ${E2E_TMP_VOL}:/tmp alpine:3.20 ls -la /tmp"
+    echo "   - Shared tmp vol:   docker exec ${DIND} ls -la /tmp"
-    echo "   - DinD docker root: docker -H ${DIND_HOST} run --rm -v ${DIND_VOL}:/var/lib/docker alpine:3.20 ls -la /var/lib/docker/volumes"
+    echo "   - DinD docker root: docker exec ${DIND} ls -la /var/lib/docker/volumes"
     return 0
   fi
 
@@ -124,8 +119,11 @@ cleanup() {
 }
 trap cleanup EXIT INT TERM
 
-log "Creating network ${NET} (if missing)"
+log "(Re)creating network ${NET} with MTU ${DIND_MTU}"
-docker network inspect "${NET}" >/dev/null 2>&1 || docker network create "${NET}" >/dev/null
+docker network rm "${NET}" >/dev/null 2>&1 || true
+docker network create \
+  --opt com.docker.network.driver.mtu="${DIND_MTU}" \
+  "${NET}" >/dev/null
 
 log "Removing old ${DIND} (if any)"
 docker rm -f "${DIND}" >/dev/null 2>&1 || true
@@ -145,14 +143,14 @@ docker run -d --privileged \
   -e DOCKER_TLS_CERTDIR="" \
   -v "${DIND_VOL}:/var/lib/docker" \
   -v "${E2E_TMP_VOL}:/tmp" \
-  -p 2375:2375 \
   docker:dind \
   --host=tcp://0.0.0.0:2375 \
-  --tls=false >/dev/null
+  --tls=false \
+  --mtu="${DIND_MTU}" >/dev/null
 
 log "Waiting for DinD to be ready..."
 for i in $(seq 1 "${READY_TIMEOUT_SECONDS}"); do
-  if docker -H "${DIND_HOST}" version >/dev/null 2>&1; then
+  if dind version >/dev/null 2>&1; then
     log "DinD is ready."
     break
   fi
@@ -168,13 +166,13 @@ done
 
 log "Pre-pulling helper images in DinD..."
 log " - Pulling: ${RSYNC_IMG}"
-docker -H "${DIND_HOST}" pull "${RSYNC_IMG}"
+dind pull "${RSYNC_IMG}"
 
 log "Ensuring alpine exists in DinD (for debug helpers)"
-docker -H "${DIND_HOST}" pull alpine:3.20 >/dev/null
+dind pull alpine:3.20 >/dev/null
 
 log "Loading ${IMG} image into DinD..."
-docker save "${IMG}" | docker -H "${DIND_HOST}" load >/dev/null
+docker save "${IMG}" | dind_stdin load >/dev/null
 
 log "Running E2E tests inside DinD"
 set +e

src/baudolo/backup/app.py

@@ -16,8 +16,10 @@ from .docker import (
     change_containers_status,
     containers_using_volume,
     docker_volume_names,
+    filter_stoppable,
     get_image_info,
     has_image,
+    is_swarm_task,
 )
 from .shell import execute_shell_command
 from .volume import backup_volume
@@ -66,9 +68,13 @@ def volume_is_fully_ignored(
 
 def requires_stop(containers: list[str], images_no_stop_required: list[str]) -> bool:
     """
-    Stop is required if ANY container image is NOT in the whitelist patterns.
+    Stop is required if ANY stoppable container image is NOT in the
+    whitelist patterns. Swarm task containers never count: baudolo must
+    not cycle them (see docker.is_swarm_task).
     """
     for c in containers:
+        if is_swarm_task(c):
+            continue
         img = get_image_info(c)
         if not any(pat in img for pat in images_no_stop_required):
             return True
@@ -219,20 +225,22 @@ def main() -> int:
 
         if args.everything:
             # "everything": always do pre-rsync, then stop + rsync again
+            stoppable = filter_stoppable(containers)
             backup_volume(versions_dir, volume_name, vol_dir)
-            change_containers_status(containers, "stop")
+            change_containers_status(stoppable, "stop")
             backup_volume(versions_dir, volume_name, vol_dir)
             if not args.shutdown:
-                change_containers_status(containers, "start")
+                change_containers_status(stoppable, "start")
             continue
 
         # default: rsync, and if needed stop + rsync
         backup_volume(versions_dir, volume_name, vol_dir)
         if requires_stop(containers, args.images_no_stop_required):
-            change_containers_status(containers, "stop")
+            stoppable = filter_stoppable(containers)
+            change_containers_status(stoppable, "stop")
             backup_volume(versions_dir, volume_name, vol_dir)
             if not args.shutdown:
-                change_containers_status(containers, "start")
+                change_containers_status(stoppable, "start")
 
     # Stamp the backup version directory using dirval (python lib)
     stamp_directory(version_dir)

src/baudolo/backup/db.py

@@ -115,8 +115,10 @@ def backup_database(
         dump_file = os.path.join(out_dir, f"{db_name}.backup.sql")
 
         if db_type == "mariadb":
+            # Force TCP so auth matches '<user>'@'%' instead of socket -> 'localhost'.
             cmd = (
                 f"docker exec {container} /usr/bin/mariadb-dump "
+                f"-h 127.0.0.1 --protocol=tcp "
                 f"-u {user} -p{password} {db_name}"
             )
             _atomic_write_cmd(cmd, dump_file)
@@ -127,7 +129,8 @@ def backup_database(
             try:
                 cmd = (
                     f"PGPASSWORD={password} docker exec -i {container} "
-                    f"pg_dump -U {user} -d {db_name} -h localhost"
+                    f"pg_dump -U {user} -d {db_name} -h localhost "
+                    f"--no-owner --no-privileges"
                 )
                 _atomic_write_cmd(cmd, dump_file)
                 produced = True

src/baudolo/backup/docker.py

@@ -1,6 +1,6 @@
 from __future__ import annotations
 
-from .shell import execute_shell_command
+from .shell import BackupException, execute_shell_command
 
 
 def get_image_info(container: str) -> str:
@@ -24,6 +24,43 @@ def containers_using_volume(volume_name: str) -> list[str]:
     )
 
 
+def is_swarm_task(container: str) -> bool:
+    """Swarm-managed task containers must never be stopped or started
+    manually: the orchestrator replaces the stopped task and a later
+    `docker start` fails on the detached overlay network. A container that
+    vanished between listing and inspect (--rm one-shots, task-history GC)
+    counts as not stoppable instead of aborting the whole backup run; if the
+    container still exists the inspect failure re-raises, so a broken daemon
+    keeps failing the run loudly instead of silently skipping the stop."""
+    try:
+        out = execute_shell_command(
+            "docker inspect --format "
+            f"'{{{{index .Config.Labels \"com.docker.swarm.task.id\"}}}}' {container}"
+        )
+    except BackupException:
+        still_listed = execute_shell_command(
+            f"docker ps -a --filter name=^{container}$ --format '{{{{.Names}}}}'"
+        )
+        if still_listed and still_listed[0].strip():
+            raise
+        return True
+    return bool(out and out[0].strip())
+
+
+def filter_stoppable(containers: list[str]) -> list[str]:
+    """Containers baudolo may stop/start itself (everything but swarm tasks)."""
+    stoppable = []
+    for container in containers:
+        if is_swarm_task(container):
+            print(
+                f"Skipping stop/start for swarm task container '{container}'.",
+                flush=True,
+            )
+            continue
+        stoppable.append(container)
+    return stoppable
+
+
 def change_containers_status(containers: list[str], status: str) -> None:
     """Stop or start a list of containers."""
     if not containers:

src/baudolo/restore/db/mariadb.py

@@ -47,18 +47,6 @@ def restore_mariadb_sql(
         # IMPORTANT:
         # Do NOT hardcode 'mysql' here. Use the detected client.
         # MariaDB 11 images may not contain the mysql binary at all.
-        docker_exec(
-            container,
-            [
-                client,
-                "-u",
-                user,
-                f"--password={password}",
-                "-e",
-                "SET FOREIGN_KEY_CHECKS=0;",
-            ],
-        )
-
         result = docker_exec(
             container,
             [
@@ -74,7 +62,16 @@ def restore_mariadb_sql(
         )
         tables = result.stdout.decode().split()
 
-        for tbl in tables:
+        if tables:
+            # SET FOREIGN_KEY_CHECKS is session-scoped, so it must share one
+            # client session with the DROPs or FK constraints still fire.
+            drop_sql = (
+                "SET FOREIGN_KEY_CHECKS=0; "
+                + " ".join(
+                    f"DROP TABLE IF EXISTS `{db_name}`.`{tbl}`;" for tbl in tables
+                )
+                + " SET FOREIGN_KEY_CHECKS=1;"
+            )
             docker_exec(
                 container,
                 [
@@ -83,22 +80,10 @@ def restore_mariadb_sql(
                     user,
                     f"--password={password}",
                     "-e",
-                    f"DROP TABLE IF EXISTS `{db_name}`.`{tbl}`;",
+                    drop_sql,
                 ],
             )
 
-        docker_exec(
-            container,
-            [
-                client,
-                "-u",
-                user,
-                f"--password={password}",
-                "-e",
-                "SET FOREIGN_KEY_CHECKS=1;",
-            ],
-        )
-
     with open(sql_path, "rb") as f:
         docker_exec(
             container, [client, "-u", user, f"--password={password}", db_name], stdin=f

src/baudolo/restore/db/postgres.py

@@ -1,9 +1,41 @@
 from __future__ import annotations
 
 import os
+import tempfile
+from collections.abc import Iterable, Iterator
 
 from ..run import docker_exec
 
+_SUPERUSER_ONLY_PREFIXES = (b"COMMENT ON EXTENSION", b"ALTER DEFAULT PRIVILEGES")
+
+
+def filter_superuser_only_lines(lines: Iterable[bytes]) -> Iterator[bytes]:
+    """Drop superuser-only statements an app-level psql replay cannot run.
+
+    Args:
+        lines: dump lines including their trailing newlines.
+
+    Yields:
+        Every line except top-level statements starting with a superuser-only
+        prefix. Lines inside COPY ... FROM stdin data blocks are passed
+        through untouched: a data row may legally start with the same bytes,
+        and dropping it would silently corrupt the restored table.
+    """
+    in_copy = False
+    for line in lines:
+        if in_copy:
+            yield line
+            if line.rstrip(b"\r\n") == b"\\.":
+                in_copy = False
+            continue
+        if line.startswith(b"COPY ") and line.rstrip(b"\r\n").endswith(b"FROM stdin;"):
+            in_copy = True
+            yield line
+            continue
+        if line.startswith(_SUPERUSER_ONLY_PREFIXES):
+            continue
+        yield line
+
 
 def restore_postgres_sql(
     *,
@@ -21,17 +53,43 @@ def restore_postgres_sql(
     docker_env = {"PGPASSWORD": password}
 
     if empty:
+        # Owner-filtered: extension members (pg_trgm's set_limit) are superuser-owned; IF EXISTS absorbs CASCADE fallout.
         drop_sql = r"""
 DO $$ DECLARE r RECORD;
 BEGIN
   FOR r IN (
-    SELECT table_name AS name, 'TABLE' AS type FROM information_schema.tables WHERE table_schema='public'
+    SELECT c.relname AS name,
+           CASE c.relkind
+             WHEN 'v' THEN 'VIEW'
+             WHEN 'm' THEN 'MATERIALIZED VIEW'
+             WHEN 'f' THEN 'FOREIGN TABLE'
+             ELSE 'TABLE'
+           END AS type
+      FROM pg_class c JOIN pg_namespace n ON n.oid = c.relnamespace
+     WHERE n.nspname = 'public' AND c.relkind IN ('r', 'p', 'v', 'm', 'f')
+       AND pg_get_userbyid(c.relowner) = current_user
     UNION ALL
-    SELECT routine_name AS name, 'FUNCTION' AS type FROM information_schema.routines WHERE specific_schema='public'
+    SELECT p.proname AS name,
+           CASE p.prokind WHEN 'p' THEN 'PROCEDURE' ELSE 'FUNCTION' END AS type
+      FROM pg_proc p JOIN pg_namespace n ON n.oid = p.pronamespace
+     WHERE n.nspname = 'public' AND p.prokind IN ('f', 'p', 'w')
+       AND pg_get_userbyid(p.proowner) = current_user
     UNION ALL
-    SELECT sequence_name AS name, 'SEQUENCE' AS type FROM information_schema.sequences WHERE sequence_schema='public'
+    SELECT c.relname AS name, 'SEQUENCE' AS type
+      FROM pg_class c JOIN pg_namespace n ON n.oid = c.relnamespace
+     WHERE n.nspname = 'public' AND c.relkind = 'S'
+       AND pg_get_userbyid(c.relowner) = current_user
+    UNION ALL
+    SELECT t.typname AS name, 'TYPE' AS type
+      FROM pg_type t JOIN pg_namespace n ON n.oid = t.typnamespace
+     WHERE n.nspname = 'public'
+       AND pg_get_userbyid(t.typowner) = current_user
+       AND (t.typtype IN ('e', 'd')
+            OR (t.typtype = 'c' AND EXISTS (
+                  SELECT 1 FROM pg_class c2
+                   WHERE c2.oid = t.typrelid AND c2.relkind = 'c')))
   ) LOOP
-    EXECUTE format('DROP %s public.%I CASCADE', r.type, r.name);
+    EXECUTE format('DROP %s IF EXISTS public.%I CASCADE', r.type, r.name);
   END LOOP;
 END $$;
 """
@@ -42,11 +100,17 @@ END $$;
             docker_env=docker_env,
         )
 
-    with open(sql_path, "rb") as f:
+    # Filter into a spooled temp file instead of building the whole dump in
+    # memory: production dumps reach many GB and the previous read/splitlines/
+    # join needed roughly three times the dump size in RSS.
+    with open(sql_path, "rb") as src, tempfile.TemporaryFile() as filtered:
+        for line in filter_superuser_only_lines(src):
+            filtered.write(line)
+        filtered.seek(0)
         docker_exec(
             container,
             ["psql", "-v", "ON_ERROR_STOP=1", "-U", user, "-d", db_name],
-            stdin=f,
+            stdin=filtered,
             docker_env=docker_env,
         )
 

tests/e2e/test_e2e_mariadb_anonymous_preemption.py

@@ -0,0 +1,162 @@
+"""
+Bug-repro for: mariadb-dump fails with `ERROR 1045 Access denied for user
+'<u>'@'localhost' (using password: YES)` when only '<u>'@'%' is granted and a
+preempting ''@'localhost' user is present.
+
+The fix forces TCP loopback in baudolo.backup.db so the dump matches the
+'<u>'@'%' grant instead of the socket->localhost auth row.
+
+This file:
+- builds the exact preconditions that triggered the production failure,
+- as a NEGATIVE control, runs a socket-based mariadb-dump (== the old code path)
+  and asserts that it fails with the literal 1045 / @'localhost' error,
+- as a POSITIVE proof, calls backup_database() (where the fix lives) against
+  the same DB container and asserts the dump file is produced and contains the
+  seed data.
+
+Note: the volume-rsync stage of baudolo is intentionally NOT exercised here.
+That stage needs root on /var/lib/docker/volumes, which is provided by the
+DinD wrapper in `make test-e2e` but not by an on-host invocation. The bug we
+are verifying is in the DB-dump stage, so testing backup_database() directly
+keeps the assertion focused and the test runnable both on-host and in DinD.
+"""
+
+import os
+import tempfile
+import unittest
+
+import pandas
+
+from baudolo.backup import db as db_mod
+
+from .helpers import (
+    cleanup_docker,
+    require_docker,
+    run,
+    unique,
+    wait_for_mariadb,
+    wait_for_mariadb_sql,
+)
+
+
+class TestE2EMariaDBAnonymousPreemption(unittest.TestCase):
+    @classmethod
+    def setUpClass(cls) -> None:
+        require_docker()
+        cls.prefix = unique("baudolo-e2e-mariadb-anon")
+        cls.db_container = f"{cls.prefix}-mariadb"
+        cls.db_volume = f"{cls.prefix}-mariadb-vol"
+        cls.containers = [cls.db_container]
+        cls.volumes = [cls.db_volume]
+
+        cls.db_name = "appdb"
+        cls.db_user = "tcponly"
+        cls.db_password = "tcponlypw"
+        cls.root_password = "rootpw"
+
+        run(["docker", "volume", "create", cls.db_volume])
+
+        # Boot WITHOUT MARIADB_USER/MARIADB_PASSWORD/MARIADB_DATABASE so the
+        # entrypoint does not auto-create '<u>'@'%'. We provision the user
+        # explicitly below to mirror the SQL path used by svc-db-mariadb.
+        run(
+            [
+                "docker",
+                "run",
+                "-d",
+                "--name",
+                cls.db_container,
+                "-e",
+                f"MARIADB_ROOT_PASSWORD={cls.root_password}",
+                "-v",
+                f"{cls.db_volume}:/var/lib/mysql",
+                "mariadb:12.2",
+            ]
+        )
+
+        wait_for_mariadb(
+            cls.db_container, root_password=cls.root_password, timeout_s=120
+        )
+
+        # Provision: '<u>'@'%' (the app/backup grant) + anonymous ''@'localhost'
+        # (the preemption trigger). Mirrors the production state that produced
+        # `ERROR 1045 ... '<u>'@'localhost' (using password: YES)`.
+        bootstrap_sql = (
+            f"CREATE DATABASE {cls.db_name};"
+            f"CREATE USER '{cls.db_user}'@'%' IDENTIFIED BY '{cls.db_password}';"
+            f"GRANT ALL PRIVILEGES ON {cls.db_name}.* TO '{cls.db_user}'@'%';"
+            f"CREATE USER ''@'localhost' IDENTIFIED BY 'anonpw-not-{cls.db_password}';"
+            "FLUSH PRIVILEGES;"
+            f"CREATE TABLE {cls.db_name}.t (id INT PRIMARY KEY, v VARCHAR(50));"
+            f"INSERT INTO {cls.db_name}.t VALUES (1,'ok');"
+        )
+        run(
+            [
+                "docker",
+                "exec",
+                cls.db_container,
+                "sh",
+                "-lc",
+                f'mariadb -uroot --protocol=socket -e "{bootstrap_sql}"',
+            ]
+        )
+
+        # Sanity: '<u>' can log in over TCP (matches '%'). If THIS fails,
+        # the precondition for the fix to even apply is broken.
+        wait_for_mariadb_sql(
+            cls.db_container, user=cls.db_user, password=cls.db_password, timeout_s=60
+        )
+
+    @classmethod
+    def tearDownClass(cls) -> None:
+        cleanup_docker(containers=cls.containers, volumes=cls.volumes)
+
+    def test_negative_control_socket_dump_fails_with_1045(self) -> None:
+        # Reproduces the OLD code path (no -h/--protocol). MUST fail with 1045
+        # under the configured preemption. If this ever starts passing, either
+        # the MariaDB auth semantics changed or the anonymous-user setup did
+        # not take effect — in both cases the positive test below loses its
+        # ability to discriminate "fix works" vs "bug never reproduced".
+        p = run(
+            [
+                "docker",
+                "exec",
+                self.db_container,
+                "sh",
+                "-lc",
+                f"mariadb-dump -u{self.db_user} -p{self.db_password} {self.db_name}",
+            ],
+            capture=True,
+            check=False,
+        )
+        self.assertNotEqual(p.returncode, 0, "socket-based dump unexpectedly succeeded")
+        self.assertIn("1045", (p.stderr or "") + (p.stdout or ""))
+        self.assertIn("@'localhost'", (p.stderr or "") + (p.stdout or ""))
+
+    def test_backup_database_succeeds_with_tcp_fix(self) -> None:
+        # Drives the function where the fix lives. No rsync, no privileged
+        # paths — just the dump that the negative-control proved is failing
+        # under the same preemption setup.
+        with tempfile.TemporaryDirectory() as volume_dir:
+            df = pandas.DataFrame(
+                [(self.db_container, self.db_name, self.db_user, self.db_password)],
+                columns=["instance", "database", "username", "password"],
+            )
+            produced = db_mod.backup_database(
+                container=self.db_container,
+                volume_dir=volume_dir,
+                db_type="mariadb",
+                databases_df=df,
+                database_containers=[self.db_container],
+            )
+            self.assertTrue(produced, "backup_database did not produce a dump")
+            dump_path = os.path.join(volume_dir, "sql", f"{self.db_name}.backup.sql")
+            self.assertTrue(os.path.isfile(dump_path), f"expected dump at {dump_path}")
+            with open(dump_path, "r", encoding="utf-8", errors="replace") as f:
+                content = f.read()
+            self.assertIn("INSERT INTO", content)
+            self.assertIn("'ok'", content)
+
+
+if __name__ == "__main__":
+    unittest.main(verbosity=2)

tests/e2e/test_e2e_swarm_task_skip.py

@@ -0,0 +1,196 @@
+# tests/e2e/test_e2e_swarm_task_skip.py
+#
+# Reproduces the swarm flake fixed on this branch: baudolo used to stop a
+# swarm task container around the volume file backup because its image was
+# not whitelisted; the orchestrator immediately replaced the stopped task and
+# the later `docker start` failed on the detached overlay network, killing
+# the backup run. With the fix the task container is skipped (backed up hot):
+# the backup succeeds, the very same container instance keeps running, and
+# the service never has to replace a task.
+import time
+import unittest
+
+from .helpers import (
+    backup_path,
+    backup_run,
+    create_minimal_compose_dir,
+    ensure_empty_dir,
+    latest_version_dir,
+    require_docker,
+    run,
+    unique,
+    write_databases_csv,
+)
+
+
+def _swarm_state() -> str:
+    return run(
+        ["docker", "info", "--format", "{{.Swarm.LocalNodeState}}"]
+    ).stdout.strip()
+
+
+def _task_container_id(service: str, timeout_s: int = 60) -> str:
+    deadline = time.time() + timeout_s
+    while time.time() < deadline:
+        out = run(
+            [
+                "docker",
+                "ps",
+                "--filter",
+                f"label=com.docker.swarm.service.name={service}",
+                "--format",
+                "{{.ID}}",
+            ]
+        ).stdout.strip()
+        if out:
+            return out.splitlines()[0]
+        time.sleep(2)
+    raise RuntimeError(f"No running task container for service {service}")
+
+
+def _started_at(container_id: str) -> str:
+    return run(
+        ["docker", "inspect", "--format", "{{.State.StartedAt}}", container_id]
+    ).stdout.strip()
+
+
+class TestE2ESwarmTaskSkip(unittest.TestCase):
+    @classmethod
+    def setUpClass(cls) -> None:
+        require_docker()
+        cls.prefix = unique("baudolo-e2e-swarm-skip")
+        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.swarm_initted = False
+        if _swarm_state() != "active":
+            run(["docker", "swarm", "init", "--advertise-addr", "127.0.0.1"])
+            cls.swarm_initted = True
+
+        cls.volume = f"{cls.prefix}-vol"
+        cls.service = f"{cls.prefix}-svc"
+        cls.volumes = [cls.volume]
+
+        run(["docker", "volume", "create", cls.volume])
+        run(
+            [
+                "docker",
+                "run",
+                "--rm",
+                "-v",
+                f"{cls.volume}:/data",
+                "alpine:3.20",
+                "sh",
+                "-lc",
+                "echo 'swarm-payload' > /data/payload.txt",
+            ]
+        )
+
+        run(
+            [
+                "docker",
+                "service",
+                "create",
+                "--name",
+                cls.service,
+                "--replicas",
+                "1",
+                "--mount",
+                f"type=volume,source={cls.volume},target=/data",
+                "alpine:3.20",
+                "sleep",
+                "3600",
+            ]
+        )
+        cls.task_cid = _task_container_id(cls.service)
+        cls.task_started_at = _started_at(cls.task_cid)
+
+        cls.databases_csv = f"/tmp/{cls.prefix}/databases.csv"
+        write_databases_csv(cls.databases_csv, [])
+
+        # Whitelist that matches nothing: on main this forces a stop of every
+        # container at the volume, i.e. exactly the flake; on this branch the
+        # swarm task must be skipped instead. (An empty list would leave the
+        # --images-no-stop-required flag without arguments and argparse-fail.)
+        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=["image-that-matches-nothing"],
+        )
+        cls.hash, cls.version = latest_version_dir(cls.backups_dir, cls.repo_name)
+
+    @classmethod
+    def tearDownClass(cls) -> None:
+        run(["docker", "service", "rm", cls.service], check=False)
+        deadline = time.time() + 30
+        while time.time() < deadline:
+            out = run(
+                [
+                    "docker",
+                    "ps",
+                    "-aq",
+                    "--filter",
+                    f"label=com.docker.swarm.service.name={cls.service}",
+                ],
+                check=False,
+            ).stdout.strip()
+            if not out:
+                break
+            time.sleep(2)
+        for v in cls.volumes:
+            run(["docker", "volume", "rm", "-f", v], check=False)
+        if cls.swarm_initted:
+            run(["docker", "swarm", "leave", "--force"], check=False)
+
+    def test_volume_backed_up_hot(self) -> None:
+        p = (
+            backup_path(
+                self.backups_dir,
+                self.repo_name,
+                self.version,
+                self.volume,
+            )
+            / "files"
+            / "payload.txt"
+        )
+        self.assertTrue(p.is_file(), f"Expected backed up file at: {p}")
+
+    def test_task_container_never_stopped(self) -> None:
+        out = run(
+            ["docker", "ps", "-q", "--no-trunc", "--filter", f"id={self.task_cid}"]
+        ).stdout.strip()
+        self.assertTrue(
+            out.startswith(self.task_cid) or self.task_cid.startswith(out.strip()[:12]),
+            f"Task container {self.task_cid} is no longer running",
+        )
+        self.assertEqual(
+            self.task_started_at,
+            _started_at(self.task_cid),
+            "Task container was restarted during the backup",
+        )
+
+    def test_service_never_replaced_the_task(self) -> None:
+        states = run(
+            [
+                "docker",
+                "service",
+                "ps",
+                self.service,
+                "--format",
+                "{{.DesiredState}} {{.CurrentState}}",
+            ]
+        ).stdout.strip()
+        lines = [line for line in states.splitlines() if line.strip()]
+        self.assertEqual(
+            len(lines), 1, f"Service task history shows replacements:\n{states}"
+        )
+        self.assertIn("Running", lines[0])
+
+
+if __name__ == "__main__":
+    unittest.main()

tests/unit/backup/test_db_mariadb_dump.py

@@ -0,0 +1,70 @@
+import tempfile
+import unittest
+from unittest.mock import patch
+
+import pandas
+
+from baudolo.backup import db as db_mod
+
+
+def _df(rows):
+    return pandas.DataFrame(
+        rows, columns=["instance", "database", "username", "password"]
+    )
+
+
+def _capture_commands(*, db_type, rows, container):
+    captured = []
+
+    def _capture(cmd):
+        captured.append(cmd)
+        return []
+
+    with tempfile.TemporaryDirectory() as td:
+        with patch.object(db_mod, "execute_shell_command", side_effect=_capture):
+            db_mod.backup_database(
+                container=container,
+                volume_dir=td,
+                db_type=db_type,
+                databases_df=_df(rows),
+                database_containers=[container],
+            )
+    return captured
+
+
+class TestMariaDBDumpUsesTCP(unittest.TestCase):
+    # Regression guard for 'Access denied for user <user>@localhost' when only
+    # '<user>'@'%' is granted: the in-container mariadb-dump MUST force TCP so
+    # the connection is auth-matched against '%' instead of socket->localhost.
+
+    def test_mariadb_dump_forces_tcp_loopback(self):
+        captured = _capture_commands(
+            db_type="mariadb",
+            rows=[("mariadb", "appdb", "appuser", "s3cret")],
+            container="mariadb",
+        )
+        dump_cmds = [c for c in captured if "mariadb-dump" in c]
+        self.assertEqual(
+            len(dump_cmds), 1, f"expected one dump command, got: {captured}"
+        )
+
+        cmd = dump_cmds[0]
+        self.assertIn("-h 127.0.0.1", cmd)
+        self.assertIn("--protocol=tcp", cmd)
+        self.assertIn("-u appuser", cmd)
+        self.assertIn("-ps3cret", cmd)
+        self.assertIn(" appdb", cmd)
+
+    def test_postgres_dump_unaffected(self):
+        captured = _capture_commands(
+            db_type="postgres",
+            rows=[("pg", "appdb", "appuser", "s3cret")],
+            container="pg",
+        )
+        dump_cmds = [c for c in captured if "pg_dump" in c and "pg_dumpall" not in c]
+        self.assertEqual(len(dump_cmds), 1)
+        self.assertNotIn("--protocol=tcp", dump_cmds[0])
+
+
+if __name__ == "__main__":
+    unittest.main(verbosity=2)

tests/unit/backup/test_docker_swarm.py

@@ -0,0 +1,53 @@
+import unittest
+from unittest.mock import patch
+
+from baudolo.backup import docker as docker_mod
+from baudolo.backup.shell import BackupException
+
+
+class TestIsSwarmTask(unittest.TestCase):
+    @patch.object(docker_mod, "execute_shell_command", return_value=["task-id-123"])
+    def test_true_when_task_label_present(self, _mock) -> None:
+        self.assertTrue(docker_mod.is_swarm_task("c1"))
+
+    @patch.object(docker_mod, "execute_shell_command", return_value=[""])
+    def test_false_when_label_empty(self, _mock) -> None:
+        self.assertFalse(docker_mod.is_swarm_task("c1"))
+
+    @patch.object(docker_mod, "execute_shell_command", return_value=[])
+    def test_false_when_no_output(self, _mock) -> None:
+        self.assertFalse(docker_mod.is_swarm_task("c1"))
+
+    @patch.object(
+        docker_mod,
+        "execute_shell_command",
+        side_effect=[BackupException("gone"), []],
+    )
+    def test_vanished_container_counts_as_not_stoppable(self, _mock) -> None:
+        # A container removed between listing and inspect must not abort the
+        # whole backup run; treating it as a swarm task keeps it out of every
+        # stop/start and image-inspect path.
+        self.assertTrue(docker_mod.is_swarm_task("gone-container"))
+
+    @patch.object(
+        docker_mod,
+        "execute_shell_command",
+        side_effect=[BackupException("daemon hiccup"), ["still-here"]],
+    )
+    def test_inspect_failure_on_existing_container_still_fails(self, _mock) -> None:
+        # If the container still exists, an inspect failure must keep failing
+        # the run: silently skipping the stop would back up a hot volume and
+        # report green without the stop guarantee.
+        with self.assertRaises(BackupException):
+            docker_mod.is_swarm_task("still-here")
+
+
+class TestFilterStoppable(unittest.TestCase):
+    @patch.object(docker_mod, "is_swarm_task", side_effect=[False, True, False])
+    def test_mixed_list_keeps_order_and_drops_tasks(self, _mock) -> None:
+        result = docker_mod.filter_stoppable(["plain-1", "swarm-task", "plain-2"])
+        self.assertEqual(result, ["plain-1", "plain-2"])
+
+
+if __name__ == "__main__":
+    unittest.main()

tests/unit/restore/test_mariadb_empty_drop.py

@@ -0,0 +1,44 @@
+import tempfile
+import unittest
+from unittest.mock import MagicMock, patch
+
+from baudolo.restore.db import mariadb as mariadb_mod
+
+
+class TestMariadbEmptyDrop(unittest.TestCase):
+    def test_drops_run_in_one_session_with_fk_checks_off(self) -> None:
+        calls = []
+
+        def _capture(container, argv, **kwargs):
+            calls.append(argv)
+            result = MagicMock()
+            result.stdout = b"users\nfetches\n"
+            return result
+
+        with tempfile.NamedTemporaryFile(suffix=".sql") as sql:
+            sql.write(b"CREATE TABLE t (id int);\n")
+            sql.flush()
+            with (
+                patch.object(mariadb_mod, "docker_exec", side_effect=_capture),
+                patch.object(mariadb_mod, "_pick_client", return_value="mariadb"),
+            ):
+                mariadb_mod.restore_mariadb_sql(
+                    container="db",
+                    db_name="mailu",
+                    user="mailu",
+                    password="pw",
+                    sql_path=sql.name,
+                    empty=True,
+                )
+
+        drop_calls = [argv for argv in calls if any("DROP TABLE" in a for a in argv)]
+        self.assertEqual(len(drop_calls), 1, f"expected ONE drop session: {calls}")
+        drop_sql = drop_calls[0][-1]
+        self.assertTrue(drop_sql.startswith("SET FOREIGN_KEY_CHECKS=0; "))
+        self.assertIn("DROP TABLE IF EXISTS `mailu`.`users`;", drop_sql)
+        self.assertIn("DROP TABLE IF EXISTS `mailu`.`fetches`;", drop_sql)
+        self.assertTrue(drop_sql.endswith("SET FOREIGN_KEY_CHECKS=1;"))
+
+
+if __name__ == "__main__":
+    unittest.main()

tests/unit/restore/test_postgres_filter.py

@@ -0,0 +1,63 @@
+import unittest
+
+from baudolo.restore.db.postgres import filter_superuser_only_lines
+
+
+def _filter(raw: bytes) -> bytes:
+    return b"".join(filter_superuser_only_lines(raw.splitlines(keepends=True)))
+
+
+class TestFilterSuperuserOnlyLines(unittest.TestCase):
+    def test_drops_superuser_only_statements(self) -> None:
+        raw = (
+            b"CREATE TABLE t (id int);\n"
+            b"COMMENT ON EXTENSION pg_trgm IS 'trigram';\n"
+            b"ALTER DEFAULT PRIVILEGES IN SCHEMA public GRANT ALL ON TABLES TO x;\n"
+            b"INSERT INTO t VALUES (1);\n"
+        )
+        self.assertEqual(
+            _filter(raw),
+            b"CREATE TABLE t (id int);\nINSERT INTO t VALUES (1);\n",
+        )
+
+    def test_copy_data_rows_are_never_filtered(self) -> None:
+        raw = (
+            b"COPY public.snippets (body) FROM stdin;\n"
+            b"COMMENT ON EXTENSION looks like sql but is data\n"
+            b"ALTER DEFAULT PRIVILEGES stored as text\n"
+            b"\\.\n"
+            b"ALTER DEFAULT PRIVILEGES IN SCHEMA public REVOKE ALL ON TABLES FROM y;\n"
+        )
+        self.assertEqual(
+            _filter(raw),
+            b"COPY public.snippets (body) FROM stdin;\n"
+            b"COMMENT ON EXTENSION looks like sql but is data\n"
+            b"ALTER DEFAULT PRIVILEGES stored as text\n"
+            b"\\.\n",
+        )
+
+    def test_consecutive_copy_blocks_keep_state(self) -> None:
+        raw = (
+            b"COPY public.a (v) FROM stdin;\n"
+            b"row-a\n"
+            b"\\.\n"
+            b"COMMENT ON EXTENSION dropme IS 'x';\n"
+            b"COPY public.b (v) FROM stdin;\n"
+            b"COMMENT ON EXTENSION kept-as-data\n"
+            b"\\.\n"
+        )
+        out = _filter(raw)
+        self.assertNotIn(b"dropme", out)
+        self.assertIn(b"COMMENT ON EXTENSION kept-as-data\n", out)
+
+    def test_everything_else_passes_through_verbatim(self) -> None:
+        raw = (
+            b"SET statement_timeout = 0;\n"
+            b"CREATE EXTENSION IF NOT EXISTS pg_trgm;\n"
+            b"GRANT ALL ON SCHEMA public TO app;\n"
+        )
+        self.assertEqual(_filter(raw), raw)
+
+
+if __name__ == "__main__":
+    unittest.main()

tests/unit/test_backup.py

@@ -4,10 +4,11 @@ from unittest.mock import patch
 from baudolo.backup.app import requires_stop
 
 
+@patch("baudolo.backup.app.is_swarm_task", return_value=False)
 class TestRequiresStop(unittest.TestCase):
     @patch("baudolo.backup.app.get_image_info")
     def test_requires_stop_false_when_all_images_are_whitelisted(
-        self, mock_get_image_info
+        self, mock_get_image_info, _mock_is_swarm_task
     ):
         # All containers use images containing allowed substrings
         mock_get_image_info.side_effect = [
@@ -20,7 +21,7 @@ class TestRequiresStop(unittest.TestCase):
 
     @patch("baudolo.backup.app.get_image_info")
     def test_requires_stop_true_when_any_image_is_not_whitelisted(
-        self, mock_get_image_info
+        self, mock_get_image_info, _mock_is_swarm_task
     ):
         mock_get_image_info.side_effect = [
             "repo/mastodon:v4",
@@ -31,10 +32,23 @@ class TestRequiresStop(unittest.TestCase):
         self.assertTrue(requires_stop(containers, whitelist))
 
     @patch("baudolo.backup.app.get_image_info")
-    def test_requires_stop_true_when_whitelist_empty(self, mock_get_image_info):
+    def test_requires_stop_true_when_whitelist_empty(
+        self, mock_get_image_info, _mock_is_swarm_task
+    ):
         mock_get_image_info.return_value = "repo/anything:latest"
         self.assertTrue(requires_stop(["c1"], []))
 
 
+class TestRequiresStopSwarm(unittest.TestCase):
+    @patch("baudolo.backup.app.get_image_info")
+    @patch("baudolo.backup.app.is_swarm_task", return_value=True)
+    def test_swarm_tasks_never_require_stop(
+        self, _mock_is_swarm_task, mock_get_image_info
+    ):
+        mock_get_image_info.return_value = "repo/not-whitelisted:latest"
+        self.assertFalse(requires_stop(["c1"], []))
+        mock_get_image_info.assert_not_called()
+
+
 if __name__ == "__main__":
     unittest.main()