Release version 2.0.0

Add a single source of truth in tests/e2e/helpers.py for the database
images and their in-container data dirs (POSTGRES_IMAGE=postgres:alpine,
POSTGRES_DATA_DIR=/var/lib/postgresql, MARIADB_IMAGE=mariadb:latest,
MARIADB_DATA_DIR=/var/lib/mysql) and route every test through it.
postgres:alpine now tracks 18+, which refuses a mount at
/var/lib/postgresql/data and stores data under /var/lib/postgresql, so
the mounts and the marker path move there. Drop the --rsync-image and the
renamed hard-restart flag from the invocations.

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

.github/FUNDING.yml

@@ -0,0 +1,7 @@
+github: kevinveenbirkenbach
+
+patreon: kevinveenbirkenbach
+
+buy_me_a_coffee: kevinveenbirkenbach
+
+custom: https://s.veen.world/paypaldonate

.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/ci.yml

@@ -0,0 +1,91 @@
+name: CI (make tests, stable, publish)
+
+on:
+  push:
+    branches: ["**"]
+    tags: ["v*.*.*"]   # SemVer tags like v1.2.3
+  pull_request:
+
+permissions:
+  contents: write      # push/update 'stable' tag
+  packages: write      # push to GHCR
+
+env:
+  IMAGE_NAME: baudolo
+  REGISTRY: ghcr.io
+  IMAGE_REPO: ${{ github.repository }}
+
+jobs:
+  test:
+    name: make test
+    runs-on: ubuntu-latest
+
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v7
+
+      - name: Show docker info
+        run: |
+          docker version
+          docker info
+
+      - name: Run all tests via Makefile
+        run: |
+          make test
+
+      - name: Upload E2E artifacts (always)
+        if: always()
+        uses: actions/upload-artifact@v7
+        with:
+          name: e2e-artifacts
+          path: artifacts
+          if-no-files-found: ignore
+
+  stable_and_publish:
+    name: Mark stable + publish image (SemVer tags only)
+    needs: [test]
+    runs-on: ubuntu-latest
+    if: startsWith(github.ref, 'refs/tags/v')
+
+    steps:
+      - name: Checkout (full history for tags)
+        uses: actions/checkout@v7
+        with:
+          fetch-depth: 0
+
+      - name: Derive version from tag
+        id: ver
+        run: |
+          TAG="${GITHUB_REF#refs/tags/}"   # v1.2.3
+          echo "tag=${TAG}" >> "$GITHUB_OUTPUT"
+
+      - name: Mark 'stable' git tag (force update)
+        run: |
+          git config user.name  "github-actions[bot]"
+          git config user.email "github-actions[bot]@users.noreply.github.com"
+          git tag -f stable "${GITHUB_SHA}"
+          git push -f origin stable
+
+      - name: Login to GHCR
+        uses: docker/login-action@v4
+        with:
+          registry: ${{ env.REGISTRY }}
+          username: ${{ github.actor }}
+          password: ${{ secrets.GITHUB_TOKEN }}
+
+      - name: Build image (Makefile)
+        run: |
+          make build
+
+      - name: Tag image for registry
+        run: |
+          # local image built by Makefile is: baudolo:local
+          docker tag "${IMAGE_NAME}:local" "${REGISTRY}/${IMAGE_REPO}:${{ steps.ver.outputs.tag }}"
+          docker tag "${IMAGE_NAME}:local" "${REGISTRY}/${IMAGE_REPO}:stable"
+          docker tag "${IMAGE_NAME}:local" "${REGISTRY}/${IMAGE_REPO}:sha-${GITHUB_SHA::12}"
+
+      - name: Push image
+        run: |
+          docker push "${REGISTRY}/${IMAGE_REPO}:${{ steps.ver.outputs.tag }}"
+          docker push "${REGISTRY}/${IMAGE_REPO}:stable"
+          docker push "${REGISTRY}/${IMAGE_REPO}:sha-${GITHUB_SHA::12}"

.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@v3
+        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 }}

.gitignore

@@ -1 +1,5 @@
-databases.csv
+__pycache__
+artifacts/
+*.egg-info
+dist/
+build/

.travis.yml

@@ -1,2 +0,0 @@
-language: shell
-script: shellcheck $(find . -type f -name '*.sh')

CHANGELOG.md

@@ -0,0 +1,115 @@
+# Changelog
+
+## [2.0.0] - 2026-07-12
+
+- Backup: renamed *--docker-compose-hard-restart-required* to
+  *--hard-compose-restart* and changed its default from *["mailu"]* to *[]*
+  (nargs="*"). The compose down/up is now opt-in: compose hosts pass
+  *mailu* explicitly, while swarm hosts pass nothing, since there the dir is
+  a stack whose overlay network collides with *compose up*. **Breaking:** the
+  old flag name is removed and the implicit mailu default is gone.
+- Backup: *--backups-dir* is now required (no */var/lib/backup/* default) so
+  a run can never silently target the wrong backup root. **Breaking.**
+- Restore: volume files are rsynced directly into the target volume's
+  mountpoint (resolved via *docker volume inspect*), mirroring the backup
+  path; the *alpine-rsync* helper image and the *--rsync-image* flag are
+  gone. The caller needs write access to the docker volume root (root on the
+  host, baudolo's normal privilege). **Breaking:** the restore *files*
+  subcommand no longer accepts *--rsync-image*.
+- Tests: the e2e suite tracks *postgres:alpine* (18+, mounted at
+  */var/lib/postgresql*) and *mariadb:latest* from a single source of truth.
+
+## [1.8.1] - 2026-07-12
+
+- Restore: the postgres empty mode also drops user-owned collations in
+  public; dumps containing CREATE COLLATION (e.g. OpenProject's ICU
+  collation versions_name) no longer abort the replay with 'collation
+  already exists'.
+- Maintenance: base image bumped from python 3.11-slim to 3.14-slim.
+
+## [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.
+
+
+## [1.6.0] - 2026-02-06
+
+* Compose handling is now fully delegated to the Infinito.Nexus compose wrapper or plain docker compose, removing all custom env and file detection to ensure a single, consistent source of truth.
+
+
+## [1.5.0] - 2026-01-31
+
+* * Make `databases.csv` optional: missing or empty files now emit warnings and no longer break backups
+* Fix Docker CLI compatibility by switching to `docker-ce-cli` and required build tools
+
+
+## [1.4.0] - 2026-01-31
+
+* Baudolo now restarts Docker Compose stacks in a wrapper-aware way (with a `docker compose` fallback), ensuring that all Compose overrides and env files are applied identically to the Infinito.Nexus workflow.
+
+
+## [1.3.0] - 2026-01-10
+
+* Empty databases.csv no longer causes baudolo-seed to fail
+
+
+## [1.2.0] - 2025-12-29
+
+* * Introduced **`--dump-only-sql`** mode for reliable, SQL-only database backups (replaces `--dump-only`).
+* Database configuration in `databases.csv` is now **strict and explicit** (`*` or concrete database name only).
+* **PostgreSQL cluster backups** are supported via `*`.
+* SQL dumps are written **atomically** to avoid corrupted or empty files.
+* Backups are **smarter and faster**: ignored volumes are skipped early, file backups run only when needed.
+* Improved reliability through expanded end-to-end tests and safer defaults.
+
+
+## [1.1.1] - 2025-12-28
+
+* * **Backup:** In ***--dump-only-sql*** mode, fall back to file backups with a warning when no database dump can be produced (e.g. missing `databases.csv` entry).
+
+
+## [1.1.0] - 2025-12-28
+
+* * **Backup:** Log a warning and skip database dumps when no databases.csv entry is present instead of raising an exception; introduce module-level logging and apply formatting cleanups across backup/restore code and tests.
+* **CLI:** Switch to an FHS-compliant default backup directory (/var/lib/backup) and use a stable default repository name instead of dynamic detection.
+* **Maintenance:** Update mirror configuration and ignore generated .egg-info files.
+
+
+## [1.0.0] - 2025-12-27
+
+* Official Release 🥳
+

Dockerfile

@@ -0,0 +1,37 @@
+# syntax=docker/dockerfile:1
+FROM python:3.14-slim
+
+WORKDIR /app
+
+# Base deps for build/runtime + docker repo key
+RUN apt-get update && apt-get install -y --no-install-recommends \
+    make \
+    rsync \
+    ca-certificates \
+    bash \
+    curl \
+    gnupg \
+  && rm -rf /var/lib/apt/lists/*
+
+# Install Docker CLI (docker-ce-cli) from Docker's official apt repo
+RUN bash -lc "set -euo pipefail \
+  && install -m 0755 -d /etc/apt/keyrings \
+  && curl -fsSL https://download.docker.com/linux/debian/gpg \
+     | gpg --dearmor -o /etc/apt/keyrings/docker.gpg \
+  && chmod a+r /etc/apt/keyrings/docker.gpg \
+  && . /etc/os-release \
+  && echo \"deb [arch=\$(dpkg --print-architecture) signed-by=/etc/apt/keyrings/docker.gpg] https://download.docker.com/linux/debian \${VERSION_CODENAME} stable\" \
+     > /etc/apt/sources.list.d/docker.list \
+  && apt-get update \
+  && apt-get install -y --no-install-recommends docker-ce-cli \
+  && rm -rf /var/lib/apt/lists/*"
+
+# Fail fast if docker client is missing
+RUN docker version || true
+RUN command -v docker
+
+COPY . .
+RUN make install
+
+ENV PYTHONUNBUFFERED=1
+CMD ["baudolo", "--help"]

MIRRORS

@@ -0,0 +1,4 @@
+git@github.com:kevinveenbirkenbach/backup-docker-to-local.git
+ssh://git@git.veen.world:2201/kevinveenbirkenbach/backup-docker-to-local.git
+ssh://git@code.infinito.nexus:2201/kevinveenbirkenbach/backup-docker-to-local.git
+https://pypi.org/project/backup-docker-to-local/

Makefile

@@ -0,0 +1,57 @@
+.PHONY: install build \
+		test-e2e test test-unit test-integration
+
+# Default python if no venv is active
+PY_DEFAULT ?= python3
+
+IMAGE_NAME ?= baudolo
+IMAGE_TAG  ?= local
+IMAGE      := $(IMAGE_NAME):$(IMAGE_TAG)
+
+install:
+	@set -eu; \
+	PY="$(PY_DEFAULT)"; \
+	if [ -n "$${VIRTUAL_ENV:-}" ] && [ -x "$${VIRTUAL_ENV}/bin/python" ]; then \
+		PY="$${VIRTUAL_ENV}/bin/python"; \
+	fi; \
+	echo ">>> Using python: $$PY"; \
+	"$$PY" -m pip install --upgrade pip; \
+	"$$PY" -m pip install -e .; \
+	command -v baudolo >/dev/null 2>&1 || { \
+		echo "ERROR: baudolo not found on PATH after install"; \
+		exit 2; \
+	}; \
+	baudolo --help >/dev/null 2>&1 || true
+
+# ------------------------------------------------------------
+# Build the baudolo Docker image
+# ------------------------------------------------------------
+build:
+	@echo ">> Building Docker image $(IMAGE)"
+	docker build -t $(IMAGE) .
+
+clean:
+	git clean -fdX .
+
+# ------------------------------------------------------------
+# Run E2E tests inside the container (Docker socket required)
+# ------------------------------------------------------------
+# E2E via isolated Docker-in-Docker (DinD)
+# - depends on local image build
+# - starts a DinD daemon container on a dedicated network
+# - loads the freshly built image into DinD
+# - runs the unittest suite inside a container that talks to DinD via DOCKER_HOST
+test-e2e: clean build
+	@bash scripts/test-e2e.sh
+
+test: test-unit test-integration test-e2e
+
+test-unit: clean build
+	@echo ">> Running unit tests"
+	@docker run --rm -t $(IMAGE) \
+	  bash -lc 'python -m unittest discover -t . -s tests/unit -p "test_*.py" -v'
+
+test-integration: clean build
+	@echo ">> Running integration tests"
+	@docker run --rm -t $(IMAGE) \
+	  bash -lc 'python -m unittest discover -t . -s tests/integration -p "test_*.py" -v'

README.md

@@ -1,67 +1,217 @@
-# Backup Docker Volumes to Local
+# baudolo – Deterministic Backup & Restore for Docker Volumes 📦🔄
-[![License: GPL v3](https://img.shields.io/badge/License-GPL%20v3-blue.svg)](./LICENSE.txt)
+[![GitHub Sponsors](https://img.shields.io/badge/Sponsor-GitHub%20Sponsors-blue?logo=github)](https://github.com/sponsors/kevinveenbirkenbach) [![Patreon](https://img.shields.io/badge/Support-Patreon-orange?logo=patreon)](https://www.patreon.com/c/kevinveenbirkenbach) [![Buy Me a Coffee](https://img.shields.io/badge/Buy%20me%20a%20Coffee-Funding-yellow?logo=buymeacoffee)](https://buymeacoffee.com/kevinveenbirkenbach) [![PayPal](https://img.shields.io/badge/Donate-PayPal-blue?logo=paypal)](https://s.veen.world/paypaldonate) [![License: AGPL v3](https://img.shields.io/badge/License-AGPL%20v3-blue.svg)](https://www.gnu.org/licenses/agpl-3.0) [![Docker Version](https://img.shields.io/badge/Docker-Yes-blue.svg)](https://www.docker.com) [![Python Version](https://img.shields.io/badge/Python-3.x-blue.svg)](https://www.python.org) [![GitHub stars](https://img.shields.io/github/stars/kevinveenbirkenbach/backup-docker-to-local.svg?style=social)](https://github.com/kevinveenbirkenbach/backup-docker-to-local/stargazers)
 
-## goal
-This script backups all docker-volumes with the help of rsync.
 
-## scheme
+`baudolo` is a backup and restore system for Docker volumes with
-It is part of the following scheme:
+**mandatory file backups** and **explicit, deterministic database dumps**.
-![backup scheme](https://www.veen.world/wp-content/uploads/2020/12/server-backup-768x567.jpg)
+It is designed for environments with many Docker services where:
-Further information you will find [in this blog post](https://www.veen.world/2020/12/26/how-i-backup-dedicated-root-servers/).
+- file-level backups must always exist
+- database dumps must be intentional, predictable, and auditable
 
-## Backup all volumes
+## ✨ Key Features
-Execute:
 
-```bash
+- 📦 Incremental Docker volume backups using `rsync --link-dest`
-./backup-docker-to-local.sh
+- 🗄 Optional SQL dumps for:
+  - PostgreSQL
+  - MariaDB / MySQL
+- 🌱 Explicit database definition for SQL backups (no auto-discovery)
+- 🧾 Backup integrity stamping via `dirval` (Python API)
+- ⏸ Automatic container stop/start when required for consistency
+- 🚫 Whitelisting of containers that do not require stopping
+- ♻️ Modular, maintainable Python architecture
+
+
+## 🧠 Core Concept (Important!)
+
+`baudolo` **separates file backups from database dumps**.
+
+- **Docker volumes are always backed up at file level**
+- **SQL dumps are created only for explicitly defined databases**
+
+This results in the following behavior:
+
+| Database defined | File backup | SQL dump |
+|------------------|-------------|----------|
+| No               | ✔ yes       | ✘ no     |
+| Yes              | ✔ yes       | ✔ yes    |
+
+## 📁 Backup Layout
+
+Backups are stored in a deterministic, fully nested structure:
+
+```text
+<backups-dir>/
+└── <machine-hash>/
+    └── <repo-name>/
+        └── <timestamp>/
+            └── <volume-name>/
+                ├── files/
+                └── sql/
+                    └── <database>.backup.sql
 ```
 
-## Recover
+### Meaning of each level
 
-### database
+* `<machine-hash>`
-```bash
+  SHA256 hash of `/etc/machine-id` (host separation)
-  docker exec -i mysql_container mysql -uroot -psecret database < db.sql
-```
 
-### volume
+* `<repo-name>`
-Execute:
+  Logical backup namespace (project / stack)
+
+* `<timestamp>`
+  Backup generation (`YYYYMMDDHHMMSS`)
+
+* `<volume-name>`
+  Docker volume name
+
+* `files/`
+  Incremental file backup (rsync)
+
+* `sql/`
+  Optional SQL dumps (only for defined databases)
+
+## 🚀 Installation
+
+### Local (editable install)
 
 ```bash
-
+python3 -m venv .venv
-bash ./recover-docker-from-local.sh "{{volume_name}}" "$(sha256sum /etc/machine-id | head -c 64)" "{{version_to_recover}}"
+source .venv/bin/activate
-
+pip install -e .
 ```
 
-### Database
+## 🌱 Database Definition (SQL Backup Scope)
 
-## Debug
+### How SQL backups are defined
-To checkout what's going on in the mount container type in the following command:
+
+`baudolo` creates SQL dumps **only** for databases that are **explicitly defined**
+via configuration (e.g. a databases definition file or seeding step).
+
+If a database is **not defined**:
+
+* its Docker volume is still backed up (files)
+* **no SQL dump is created**
+
+> No database definition → file backup only
+> Database definition present → file backup + SQL dump
+
+### Why explicit definition?
+
+`baudolo` does **not** inspect running containers to guess databases.
+
+Databases must be explicitly defined to guarantee:
+
+* deterministic backups
+* predictable restore behavior
+* reproducible environments
+* zero accidental production data exposure
+
+### Required database metadata
+
+Each database definition provides:
+
+* database instance (container or logical instance)
+* database name
+* database user
+* database password
+
+This information is used by `baudolo` to execute
+`pg_dump`, `pg_dumpall`, or `mariadb-dump`.
+
+## 💾 Running a Backup
 
 ```bash
-docker run -it --entrypoint /bin/sh --rm --volumes-from {{container_name}} -v /Backups/:/Backups/ kevinveenbirkenbach/alpine-rsync
+baudolo \
+  --compose-dir /srv/docker \
+  --databases-csv /etc/baudolo/databases.csv \
+  --database-containers central-postgres central-mariadb \
+  --images-no-stop-required alpine postgres mariadb mysql \
+  --images-no-backup-required redis busybox
 ```
 
-## Setup
+### Common Backup Flags
-Install pandas
 
-## Author
+| Flag            | Description                                 |
+| --------------- | ------------------------------------------- |
+| `--everything`  | Always stop containers and re-run rsync     |
+| `--dump-only-sql`| Skip file backups only for DB volumes when dumps succeed; non-DB volumes are still backed up; fallback to files if no dump.    |
+| `--shutdown`    | Do not restart containers after backup      |
+| `--backups-dir` | Backup root directory (default: `/Backups`) |
+| `--repo-name`   | Backup namespace under machine hash         |
 
-Kevin Veen-Birkenbach  
+## ♻️ Restore Operations
-- 📧 Email: [kevin@veen.world](mailto:kevin@veen.world)
-- 🌍 Website: [https://www.veen.world/](https://www.veen.world/)
 
-## License
+### Restore Volume Files
 
-This project is licensed under the GNU Affero General Public License v3.0. The full license text is available in the `LICENSE` file of this repository.
+```bash
+baudolo-restore files \
+  my-volume \
+  <machine-hash> \
+  <version> \
+  --backups-dir /Backups \
+  --repo-name my-repo
+```
 
-## More information
+Restore into a **different target volume**:
-- https://docs.docker.com/storage/volumes/
+
-- https://blog.ssdnodes.com/blog/docker-backup-volumes/
+```bash
-- https://www.baculasystems.com/blog/docker-backup-containers/
+baudolo-restore files \
-- https://gist.github.com/spalladino/6d981f7b33f6e0afe6bb
+  target-volume \
-- https://stackoverflow.com/questions/26331651/how-can-i-backup-a-docker-container-with-its-data-volumes
+  <machine-hash> \
-- https://netfuture.ch/2013/08/simple-versioned-timemachine-like-backup-using-rsync/
+  <version> \
-- https://zwischenzugs.com/2016/08/29/bash-to-python-converter/
+  --source-volume source-volume
-- https://en.wikipedia.org/wiki/Incremental_backup#Incremental
+```
-- https://unix.stackexchange.com/questions/567837/linux-backup-utility-for-incremental-backups
+
-- https://chat.openai.com/share/6d10f143-3f7c-4feb-8ae9-5644c3433a65
+### Restore PostgreSQL
+
+```bash
+baudolo-restore postgres \
+  my-volume \
+  <machine-hash> \
+  <version> \
+  --container postgres \
+  --db-name appdb \
+  --db-password secret \
+  --empty
+```
+
+### Restore MariaDB / MySQL
+
+```bash
+baudolo-restore mariadb \
+  my-volume \
+  <machine-hash> \
+  <version> \
+  --container mariadb \
+  --db-name shopdb \
+  --db-password secret \
+  --empty
+```
+
+> `baudolo` automatically detects whether `mariadb` or `mysql`
+> is available inside the container
+
+## 🔍 Backup Scheme
+
+The backup mechanism uses incremental backups with rsync and stamps directories with a unique hash. For more details on the backup scheme, check out [this blog post](https://blog.veen.world/blog/2020/12/26/how-i-backup-dedicated-root-servers/).  
+![Backup Scheme](https://blog.veen.world/wp-content/uploads/2020/12/server-backup-1024x755.jpg)
+
+## 👨‍💻 Author
+
+**Kevin Veen-Birkenbach**  
+- 📧 [kevin@veen.world](mailto:kevin@veen.world)  
+- 🌐 [https://www.veen.world/](https://www.veen.world/)
+
+## 📜 License
+
+This project is licensed under the **GNU Affero General Public License v3.0**. See the [LICENSE](./LICENSE) file for details.
+
+## 🔗 More Information
+
+- [Docker Volumes Documentation](https://docs.docker.com/storage/volumes/)
+- [Docker Backup Volumes Blog](https://blog.ssdnodes.com/blog/docker-backup-volumes/)
+- [Backup Strategies](https://en.wikipedia.org/wiki/Incremental_backup#Incremental)
+
+---
+
+Happy Backing Up! 🚀🔐

backup-docker-to-local.py

@@ -1,290 +0,0 @@
-#!/bin/python
-# Backups volumes of running containers
-
-import subprocess
-import os
-import re
-import pathlib
-import pandas
-from datetime import datetime
-import argparse
-
-class BackupException(Exception):
-    """Generic exception for backup errors."""
-    pass
-
-def execute_shell_command(command):
-    """Execute a shell command and return its output."""
-    print(command)
-    process = subprocess.Popen([command], stdout=subprocess.PIPE, stderr=subprocess.PIPE, shell=True)
-    out, err = process.communicate()
-    if process.returncode != 0:
-        raise BackupException(f"Error in command: {command}\nOutput: {out}\nError: {err}\nExit code: {process.returncode}")
-    return [line.decode("utf-8") for line in out.splitlines()]
-
-def create_version_directory():
-    """Create necessary directories for backup."""
-    version_dir = os.path.join(VERSIONS_DIR, BACKUP_TIME)
-    pathlib.Path(version_dir).mkdir(parents=True, exist_ok=True)
-    return version_dir
-
-def get_machine_id():
-    """Get the machine identifier."""
-    return execute_shell_command("sha256sum /etc/machine-id")[0][0:64]
-
-### GLOBAL CONFIGURATION ###
-
-IMAGES_NO_STOP_REQUIRED = [
-    'akaunting',
-    'baserow',
-    'discourse',
-    'element',
-    'gitea',
-    'listmonk',
-    'mastodon',
-    'matomo',
-    'nextcloud',
-    'openproject',
-    'peertube',
-    'pixelfed',
-    'wordpress' 
-]
-
-IMAGES_NO_BACKUP_REQUIRED = [
-    'redis', 
-    'memcached'
-    ]
-
-DIRNAME = os.path.dirname(__file__)
-
-DATABASES = pandas.read_csv(os.path.join(DIRNAME, "databases.csv"), sep=";")
-REPOSITORY_NAME = os.path.basename(DIRNAME)
-MACHINE_ID = get_machine_id()
-BACKUPS_DIR = '/Backups/'
-VERSIONS_DIR = os.path.join(BACKUPS_DIR, MACHINE_ID, REPOSITORY_NAME)
-BACKUP_TIME = datetime.now().strftime("%Y%m%d%H%M%S")
-VERSION_DIR = create_version_directory()
-
-def get_instance(container):
-    # The function is defined to take one parameter, 'container', 
-    # which is expected to be a string.
-
-    # This line uses regular expressions to split the 'container' string.
-    # 're.split' is a method that divides a string into a list, based on the occurrences of a pattern.
-    instance_name = re.split("(_|-)(database|db|postgres)", container)[0]
-    # The pattern "(_|-)(database|db|postgres)" is explained as follows:
-    #    - "(_|-)": Matches an underscore '_' or a hyphen '-'.
-    #    - "(database|db|postgres)": Matches one of the strings "database", "db", or "postgres".
-    # So, this pattern will match segments like "_database", "-db", "_postgres", etc.
-    # For example, in "central-db", it matches "-db".
-
-    # After splitting, [0] is used to select the first element of the list resulting from the split.
-    # This element is the string portion before the matched pattern.
-    # For "central-db", the split results in ["central", "db"], and [0] selects "central".
-
-    print(f"Extracted instance name: {instance_name}")
-    return instance_name
-
-def backup_database(container, volume_dir, db_type):
-    """Backup database (MariaDB or PostgreSQL) if applicable."""
-    print(f"Starting database backup for {container} using {db_type}...")
-    instance_name = get_instance(container)
-
-    # Filter the DataFrame for the given instance_name
-    database_entries = DATABASES.loc[DATABASES['instance'] == instance_name]
-
-    # Check if there are more than one entries
-    if len(database_entries) > 1:
-        raise BackupException(f"More than one entry found for instance '{instance_name}'")
-
-    # Check if there is no entry
-    if database_entries.empty:
-        raise BackupException(f"No entry found for instance '{instance_name}'")
-
-    # Get the first (and only) entry
-    for database_entry in database_entries.iloc:
-        database_name     = database_entry['database']
-        database_username = database_entry['username']
-        database_password = database_entry['password']
-        backup_destination_dir = os.path.join(volume_dir, "sql")
-        pathlib.Path(backup_destination_dir).mkdir(parents=True, exist_ok=True)
-        backup_destination_file = os.path.join(backup_destination_dir, f"{database_name}.backup.sql")
-        if db_type == 'mariadb':
-            backup_command = f"docker exec {container} /usr/bin/mariadb-dump -u {database_username} -p{database_password} {database_name} > {backup_destination_file}"
-        elif db_type == 'postgres':
-            if database_password:
-                # Include PGPASSWORD in the command when a password is provided
-                backup_command = (
-                    f"PGPASSWORD={database_password} docker exec -i {container} "
-                    f"pg_dump -U {database_username} -d {database_name} "
-                    f"-h localhost > {backup_destination_file}"
-                )
-            else:
-                # Exclude PGPASSWORD and use --no-password when the password is empty
-                backup_command = (
-                    f"docker exec -i {container} pg_dump -U {database_username} "
-                    f"-d {database_name} -h localhost --no-password "
-                    f"> {backup_destination_file}"
-                )
-        execute_shell_command(backup_command)
-        print(f"Database backup for database {container} completed.")
-
-def get_last_backup_dir(volume_name, current_backup_dir):
-    """Get the most recent backup directory for the specified volume."""
-    versions = sorted(os.listdir(VERSIONS_DIR), reverse=True)
-    for version in versions:
-        backup_dir = os.path.join(VERSIONS_DIR, version, volume_name, "files")
-        # Ignore current backup dir
-        if backup_dir != current_backup_dir:
-            if os.path.isdir(backup_dir):
-                return backup_dir
-    print(f"No previous backups available for volume: {volume_name}")
-    return None
-
-def getStoragePath(volume_name):
-    return execute_shell_command(f"docker volume inspect --format '{{{{ .Mountpoint }}}}' {volume_name}")
-
-def backup_volume(volume_name, volume_dir):
-    """Backup files of a volume with incremental backups."""
-    print(f"Starting backup routine for volume: {volume_name}")
-    files_rsync_destination_path = os.path.join(volume_dir, "files")
-    pathlib.Path(files_rsync_destination_path).mkdir(parents=True, exist_ok=True)
-
-    last_backup_dir = get_last_backup_dir(volume_name, files_rsync_destination_path)
-    link_dest_option = f"--link-dest='{last_backup_dir}'" if last_backup_dir else ""
-
-    source_dir = getStoragePath(volume_name)
-    rsync_command = f"rsync -abP --delete --delete-excluded {link_dest_option} {source_dir} {files_rsync_destination_path}"
-    execute_shell_command(rsync_command)
-    print(f"Backup routine for volume: {volume_name} completed.")
-
-def get_image_info(container):
-    return execute_shell_command(f"docker inspect --format '{{{{.Config.Image}}}}' {container}")
-
-def has_image(container,image):
-    """Check if the container is using the image"""
-    image_info = get_image_info(container)
-    return image in image_info[0]
-
-def stop_containers(containers):
-    """Stop a list of containers."""
-    for container in containers:
-        print(f"Stopping container {container}...")
-        execute_shell_command(f"docker stop {container}")
-
-def start_containers(containers):
-    """Start a list of stopped containers."""
-    for container in containers:
-        print(f"Starting container {container}...")
-        execute_shell_command(f"docker start {container}")
-
-def get_container_with_image(containers,image):
-    for container in containers:
-        if has_image(container,image):
-            return container
-    return False
-
-def is_image_whitelisted(container, images):
-    """Check if the container's image is one of the whitelisted images."""
-    image_info = get_image_info(container)
-    container_image = image_info[0]
-
-    for image in images:
-        if image in container_image:
-            return True
-    return False
-
-def is_container_stop_required(containers):
-    """Check if any of the containers are using images that are not whitelisted."""
-    return any(not is_image_whitelisted(container, IMAGES_NO_STOP_REQUIRED) for container in containers)
-
-def create_volume_directory(volume_name):
-    """Create necessary directories for backup."""
-    volume_dir = os.path.join(VERSION_DIR, volume_name)
-    pathlib.Path(volume_dir).mkdir(parents=True, exist_ok=True)
-    return volume_dir
-
-def is_image_ignored(container):
-    """Check if the container's image is one of the ignored images."""
-    for image in IMAGES_NO_BACKUP_REQUIRED:
-        if has_image(container, image):
-            return True
-    return False
-
-def backup_with_containers_paused(volume_name, volume_dir, containers, shutdown):
-    stop_containers(containers)
-    backup_volume(volume_name, volume_dir)
-    
-    # Just restart containers if shutdown is false
-    if not shutdown:
-        start_containers(containers)
-
-def backup_mariadb_or_postgres(container, volume_dir):
-    '''Performs database image specific backup procedures'''
-    for image in ['mariadb','postgres']:
-        if has_image(container, image):
-            backup_database(container, volume_dir, image)
-            return True
-    return False
-
-def default_backup_routine_for_volume(volume_name, containers, shutdown):
-    """Perform backup routine for a given volume."""
-    volume_dir=""
-    for container in containers:
-        
-        # Skip ignored images
-        if is_image_ignored(container):
-            print(f"Ignoring volume '{volume_name}' linked to container '{container}' with ignored image.")
-            continue 
-
-        # Directory which contains files and sqls
-        volume_dir = create_volume_directory(volume_name)
-        
-        # Execute Database backup and exit if successfull
-        if backup_mariadb_or_postgres(container, volume_dir):
-            return
-
-    # Execute backup if image is not ignored
-    if volume_dir:    
-        backup_volume(volume_name, volume_dir)
-        if is_container_stop_required(containers):
-            backup_with_containers_paused(volume_name, volume_dir, containers, shutdown)
-
-def backup_everything(volume_name, containers, shutdown):
-    """Perform file backup routine for a given volume."""
-    volume_dir=create_volume_directory(volume_name)
-    
-    # Execute sql dumps
-    for container in containers:
-        backup_mariadb_or_postgres(container, volume_dir)
-
-    # Execute file backups
-    backup_volume(volume_name, volume_dir)
-    backup_with_containers_paused(volume_name, volume_dir, containers, shutdown)
-
-def main():
-    parser = argparse.ArgumentParser(description='Backup Docker volumes.')
-    parser.add_argument('--everything', action='store_true',
-                        help='Force file backup for all volumes and additional execute database dumps')
-    parser.add_argument('--shutdown', action='store_true',
-                        help='Doesn\'t restart containers after backup')
-    args = parser.parse_args()
-
-    print('Start volume backups...')
-    volume_names = execute_shell_command("docker volume ls --format '{{.Name}}'")
-    
-    for volume_name in volume_names:
-        print(f'Start backup routine for volume: {volume_name}')
-        containers = execute_shell_command(f"docker ps --filter volume=\"{volume_name}\" --format '{{{{.Names}}}}'")
-        if not containers:
-            print('Skipped due to no running containers using this volume.')
-            continue
-        if args.everything:
-            backup_everything(volume_name, containers, args.shutdown)
-        else:    
-            default_backup_routine_for_volume(volume_name, containers, args.shutdown)
-
-    print('Finished volume backups.')
-
-if __name__ == "__main__":
-    main()

database_entry_seeder.py

@@ -1,44 +0,0 @@
-import pandas as pd
-import argparse
-import os
-
-def check_and_add_entry(file_path, instance, database, username, password):
-    # Check if the file exists and is not empty
-    if os.path.exists(file_path) and os.path.getsize(file_path) > 0:
-        # Read the existing CSV file with header
-        df = pd.read_csv(file_path, sep=';')
-    else:
-        # Create a new DataFrame with columns if file does not exist
-        df = pd.DataFrame(columns=['instance', 'database', 'username', 'password'])
-
-    # Check if the entry exists and remove it
-    mask = (df['instance'] == instance) & (df['database'] == database) & (df['username'] == username)
-    if not df[mask].empty:
-        print("Replacing existing entry.")
-        df = df[~mask]
-    else:
-        print("Adding new entry.")
-
-    # Create a new DataFrame for the new entry
-    new_entry = pd.DataFrame([{'instance': instance, 'database': database, 'username': username, 'password': password}])
-
-    # Add (or replace) the entry using concat
-    df = pd.concat([df, new_entry], ignore_index=True)
-
-    # Save the updated CSV file
-    df.to_csv(file_path, sep=';', index=False)
-
-def main():
-    parser = argparse.ArgumentParser(description="Check and replace (or add) a database entry in a CSV file.")
-    parser.add_argument("file_path", help="Path to the CSV file")
-    parser.add_argument("instance", help="Database instance")
-    parser.add_argument("database", help="Database name")
-    parser.add_argument("username", help="Username")
-    parser.add_argument("password", nargs='?', default="", help="Password (optional)")
-
-    args = parser.parse_args()
-
-    check_and_add_entry(args.file_path, args.instance, args.database, args.username, args.password)
-
-if __name__ == "__main__":
-    main()

databases.csv.tpl

@@ -1 +0,0 @@
-database;username;password;container

pyproject.toml

@@ -0,0 +1,29 @@
+[build-system]
+requires = ["setuptools>=69", "wheel"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "backup-docker-to-local"
+version = "2.0.0"
+description = "Backup Docker volumes to local with rsync and optional DB dumps."
+readme = "README.md"
+requires-python = ">=3.9"
+license = { text = "AGPL-3.0-or-later" }
+authors = [{ name = "Kevin Veen-Birkenbach" }]
+
+dependencies = [
+  "pandas",
+  "dirval",
+]
+
+[project.scripts]
+baudolo = "baudolo.backup.__main__:main"
+baudolo-restore = "baudolo.restore.__main__:main"
+baudolo-seed = "baudolo.seed.__main__:main"
+
+[tool.setuptools]
+package-dir = { "" = "src" }
+
+[tool.setuptools.packages.find]
+where = ["src"]
+exclude = ["tests*"]

recover-docker-from-local.sh

@@ -1,61 +0,0 @@
-#!/bin/bash
-
-# Check minimum number of arguments
-if [ $# -lt 3 ]; then
-  echo "ERROR: Not enough arguments. Please provide at least a volume name, backup hash, and version."
-  exit 1
-fi
-
-volume_name="$1"          # Volume-Name
-backup_hash="$2"          # Hashed Machine ID
-version="$3"              # version to backup
-container="${4:-}"        # optional
-mysql_root_password="${5:-}"  # optional
-database="${6:-}"         # optional
-backup_folder="Backups/$backup_hash/backup-docker-to-local/$version/$volume_name"
-backup_files="/$backup_folder/files"
-backup_sql="/$backup_folder/sql/backup.sql"
-
-echo "Inspect volume $volume_name"
-docker volume inspect "$volume_name"
-exit_status_volume_inspect=$?
-
-if [ $exit_status_volume_inspect -eq 0 ]; then
-    echo "Volume $volume_name already exists"
-else
-    echo "Create volume $volume_name"
-    docker volume create "$volume_name"
-    if [ $? -ne 0 ]; then
-        echo "ERROR: Failed to create volume $volume_name"
-        exit 1
-    fi
-fi
-
-if [ -f "$backup_sql" ]; then
-  if [ -n "$container" ] && [ -n "$mysql_root_password" ] && [ -n "$database" ]; then
-    echo "recover mysql dump"
-    cat "$backup_sql" | docker exec -i "$container" mariadb -u root --password="$mysql_root_password" "$database"
-    if [ $? -ne 0 ]; then
-        echo "ERROR: Failed to recover mysql dump"
-        exit 1
-    fi
-    exit 0
-  fi
-  echo "A database backup exists, but a parameter is missing. Files will be recovered instead."
-fi 
-
-if [ -d "$backup_files" ]; then    
-  echo "recover files"
-  docker run --rm -v "$volume_name:/recover/" -v "$backup_files:/backup/" "kevinveenbirkenbach/alpine-rsync" sh -c "rsync -avv --delete /backup/ /recover/"
-  if [ $? -ne 0 ]; then
-    echo "ERROR: Failed to recover files"
-    exit 1
-  fi
-  exit 0
-else
-  echo "ERROR: $backup_files doesn't exist"
-  exit 1
-fi
-
-echo "ERROR: Unhandled case"
-exit 1

scripts/test-e2e.sh

@@ -0,0 +1,225 @@
+#!/usr/bin/env bash
+set -euo pipefail
+
+# -----------------------------------------------------------------------------
+# E2E runner using Docker-in-Docker (DinD) with debug-on-failure
+#
+# Debug toggles:
+#   E2E_KEEP_ON_FAIL=1   -> keep DinD + volumes + network if tests fail
+#   E2E_KEEP_VOLUMES=1   -> keep volumes even on success/cleanup
+#   E2E_DEBUG_SHELL=1    -> open an interactive shell in the test container instead of running tests
+#   E2E_ARTIFACTS_DIR=./artifacts
+# -----------------------------------------------------------------------------
+
+NET="${E2E_NET:-baudolo-e2e-net}"
+DIND="${E2E_DIND_NAME:-baudolo-e2e-dind}"
+DIND_VOL="${E2E_DIND_VOL:-baudolo-e2e-dind-data}"
+E2E_TMP_VOL="${E2E_TMP_VOL:-baudolo-e2e-tmp}"
+
+# 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="${E2E_IMAGE:-baudolo:local}"
+
+READY_TIMEOUT_SECONDS="${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="${E2E_DEBUG_SHELL:-0}"
+
+FAILED=0
+TS="$(date +%Y%m%d%H%M%S)"
+
+mkdir -p "${ARTIFACTS_DIR}"
+
+log() { echo ">> $*"; }
+
+dump_debug() {
+  log "DEBUG: collecting diagnostics into ${ARTIFACTS_DIR}"
+
+  {
+    echo "=== Host docker version ==="
+    docker version || true
+    echo
+    echo "=== Host docker info ==="
+    docker info || true
+    echo
+    echo "=== DinD reachable? (docker exec ${DIND} docker version) ==="
+    dind version || true
+    echo
+  } > "${ARTIFACTS_DIR}/debug-host-${TS}.txt" 2>&1 || true
+
+  # DinD logs
+  docker logs --tail=5000 "${DIND}" > "${ARTIFACTS_DIR}/dind-logs-${TS}.txt" 2>&1 || true
+
+  # DinD state
+  {
+    echo "=== dind ps -a ==="
+    dind ps -a || true
+    echo
+    echo "=== dind images ==="
+    dind images || true
+    echo
+    echo "=== dind network ls ==="
+    dind network ls || true
+    echo
+    echo "=== dind volume ls ==="
+    dind volume ls || true
+    echo
+    echo "=== dind system df ==="
+    dind system df || true
+  } > "${ARTIFACTS_DIR}/debug-dind-${TS}.txt" 2>&1 || true
+
+  # Try to capture recent events (best effort; might be noisy)
+  dind events --since 10m --until 0s \
+    > "${ARTIFACTS_DIR}/dind-events-${TS}.txt" 2>&1 || true
+
+  # The shared tmp volume is mounted at /tmp inside the DinD container
+  # itself, so tar it there and copy it out with the outer daemon.
+  log "DEBUG: archiving shared /tmp (volume ${E2E_TMP_VOL})"
+  docker exec "${DIND}" tar -czf "/tmpdump-${TS}.tar.gz" -C /tmp . >/dev/null 2>&1 || true
+  docker cp "${DIND}:/tmpdump-${TS}.tar.gz" "${ARTIFACTS_DIR}/e2e-tmp-${TS}.tar.gz" >/dev/null 2>&1 || true
+
+  log "DEBUG: artifacts written:"
+  find "${ARTIFACTS_DIR}" -maxdepth 1 -mindepth 1 -print | sed 's/^/   /' || true
+}
+
+cleanup() {
+  if [ "${FAILED}" -eq 1 ] && [ "${KEEP_ON_FAIL}" = "1" ]; then
+    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 exec ${DIND} docker ps -a"
+    echo "   - Shared tmp vol:   docker exec ${DIND} ls -la /tmp"
+    echo "   - DinD docker root: docker exec ${DIND} ls -la /var/lib/docker/volumes"
+    return 0
+  fi
+
+  log "Cleanup: stopping ${DIND} and removing network ${NET}"
+  docker rm -f "${DIND}" >/dev/null 2>&1 || true
+  docker network rm "${NET}" >/dev/null 2>&1 || true
+
+  if [ "${KEEP_VOLUMES}" != "1" ]; then
+    docker volume rm -f "${DIND_VOL}" >/dev/null 2>&1 || true
+    docker volume rm -f "${E2E_TMP_VOL}" >/dev/null 2>&1 || true
+  else
+    log "Keeping volumes (E2E_KEEP_VOLUMES=1): ${DIND_VOL}, ${E2E_TMP_VOL}"
+  fi
+}
+trap cleanup EXIT INT TERM
+
+log "(Re)creating network ${NET} with MTU ${DIND_MTU}"
+docker network rm "${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
+
+log "(Re)creating DinD data volume ${DIND_VOL}"
+docker volume rm -f "${DIND_VOL}" >/dev/null 2>&1 || true
+docker volume create "${DIND_VOL}" >/dev/null
+
+log "(Re)creating shared /tmp volume ${E2E_TMP_VOL}"
+docker volume rm -f "${E2E_TMP_VOL}" >/dev/null 2>&1 || true
+docker volume create "${E2E_TMP_VOL}" >/dev/null
+
+log "Starting Docker-in-Docker daemon ${DIND}"
+docker run -d --privileged \
+  --name "${DIND}" \
+  --network "${NET}" \
+  -e DOCKER_TLS_CERTDIR="" \
+  -v "${DIND_VOL}:/var/lib/docker" \
+  -v "${E2E_TMP_VOL}:/tmp" \
+  docker:dind \
+  --host=tcp://0.0.0.0:2375 \
+  --tls=false \
+  --mtu="${DIND_MTU}" >/dev/null
+
+log "Waiting for DinD to be ready..."
+for i in $(seq 1 "${READY_TIMEOUT_SECONDS}"); do
+  if dind version >/dev/null 2>&1; then
+    log "DinD is ready."
+    break
+  fi
+  sleep 1
+  if [ "${i}" -eq "${READY_TIMEOUT_SECONDS}" ]; then
+    echo "ERROR: DinD did not become ready in time"
+    docker logs --tail=200 "${DIND}" || true
+    FAILED=1
+    dump_debug || true
+    exit 1
+  fi
+done
+
+log "Ensuring alpine exists in DinD (for debug helpers)"
+dind pull alpine:3.20 >/dev/null
+
+log "Loading ${IMG} image into DinD..."
+docker save "${IMG}" | dind_stdin load >/dev/null
+
+log "Running E2E tests inside DinD"
+set +e
+if [ "${DEBUG_SHELL}" = "1" ]; then
+  log "E2E_DEBUG_SHELL=1 -> opening shell in test container"
+  docker run --rm -it \
+    --network "${NET}" \
+    -e DOCKER_HOST="${DIND_HOST_IN_NET}" \
+    -v "${DIND_VOL}:/var/lib/docker" \
+    -v "${E2E_TMP_VOL}:/tmp" \
+    "${IMG}" \
+    bash -lc '
+      set -e
+      if [ ! -f /etc/machine-id ]; then
+        mkdir -p /etc
+        cat /proc/sys/kernel/random/uuid > /etc/machine-id
+      fi
+      echo ">> DOCKER_HOST=${DOCKER_HOST}"
+      docker ps -a || true
+      exec bash
+    '
+  rc=$?
+else
+  docker run --rm \
+    --network "${NET}" \
+    -e DOCKER_HOST="${DIND_HOST_IN_NET}" \
+    -v "${DIND_VOL}:/var/lib/docker" \
+    -v "${E2E_TMP_VOL}:/tmp" \
+    "${IMG}" \
+    bash -lc '
+    set -euo pipefail
+    set -x
+    export PYTHONUNBUFFERED=1
+
+    export TMPDIR=/tmp TMP=/tmp TEMP=/tmp
+
+    if [ ! -f /etc/machine-id ]; then
+        mkdir -p /etc
+        cat /proc/sys/kernel/random/uuid > /etc/machine-id
+    fi
+
+    python -m unittest discover -t . -s tests/e2e -p "test_*.py" -v -f
+    '
+  rc=$?
+fi
+set -e
+
+if [ "${rc}" -ne 0 ]; then
+  FAILED=1
+  echo "ERROR: E2E tests failed (exit code: ${rc})"
+  dump_debug || true
+  exit "${rc}"
+fi
+
+log "E2E tests passed."

src/baudolo/backup/__init__.py

@@ -0,0 +1 @@
+"""Baudolo backup package."""

src/baudolo/backup/__main__.py

@@ -0,0 +1,9 @@
+#!/usr/bin/env python3
+
+from __future__ import annotations
+
+from .app import main
+
+
+if __name__ == "__main__":
+    raise SystemExit(main())

src/baudolo/backup/app.py

@@ -0,0 +1,252 @@
+from __future__ import annotations
+
+import os
+import pathlib
+import sys
+from datetime import datetime
+
+import pandas
+from dirval import create_stamp_file
+from pandas.errors import EmptyDataError
+
+from .cli import parse_args
+from .compose import handle_docker_compose_services
+from .db import backup_database
+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
+
+
+def get_machine_id() -> str:
+    return execute_shell_command("sha256sum /etc/machine-id")[0][0:64]
+
+
+def stamp_directory(version_dir: str) -> None:
+    """
+    Use dirval as a Python library to stamp the directory (no CLI dependency).
+    """
+    create_stamp_file(version_dir)
+
+
+def create_version_directory(versions_dir: str, backup_time: str) -> str:
+    version_dir = os.path.join(versions_dir, backup_time)
+    pathlib.Path(version_dir).mkdir(parents=True, exist_ok=True)
+    return version_dir
+
+
+def create_volume_directory(version_dir: str, volume_name: str) -> str:
+    path = os.path.join(version_dir, volume_name)
+    pathlib.Path(path).mkdir(parents=True, exist_ok=True)
+    return path
+
+
+def is_image_ignored(container: str, images_no_backup_required: list[str]) -> bool:
+    if not images_no_backup_required:
+        return False
+    img = get_image_info(container)
+    return any(pat in img for pat in images_no_backup_required)
+
+
+def volume_is_fully_ignored(
+    containers: list[str], images_no_backup_required: list[str]
+) -> bool:
+    """
+    Skip file backup only if all containers linked to the volume are ignored.
+    """
+    if not containers:
+        return False
+    return all(is_image_ignored(c, images_no_backup_required) for c in containers)
+
+
+def requires_stop(containers: list[str], images_no_stop_required: list[str]) -> bool:
+    """
+    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
+    return False
+
+
+def backup_mariadb_or_postgres(
+    *,
+    container: str,
+    volume_dir: str,
+    databases_df: "pandas.DataFrame",
+    database_containers: list[str],
+) -> tuple[bool, bool]:
+    """
+    Returns (is_db_container, dumped_any)
+    """
+    for img in ["mariadb", "postgres"]:
+        if has_image(container, img):
+            dumped = backup_database(
+                container=container,
+                volume_dir=volume_dir,
+                db_type=img,
+                databases_df=databases_df,
+                database_containers=database_containers,
+            )
+            return True, dumped
+    return False, False
+
+
+def _empty_databases_df() -> "pandas.DataFrame":
+    """
+    Create an empty DataFrame with the expected schema for databases.csv.
+
+    This allows the backup to continue without DB dumps when the CSV is missing
+    or empty (pandas EmptyDataError).
+    """
+    return pandas.DataFrame(columns=["instance", "database", "username", "password"])
+
+
+def _load_databases_df(csv_path: str) -> "pandas.DataFrame":
+    """
+    Load databases.csv robustly.
+
+    - Missing file     -> warn, continue with empty df
+    - Empty file       -> warn, continue with empty df
+    - Valid CSV        -> return dataframe
+    """
+    try:
+        return pandas.read_csv(csv_path, sep=";", keep_default_na=False, dtype=str)
+    except FileNotFoundError:
+        print(
+            f"WARNING: databases.csv not found: {csv_path}. Continuing without database dumps.",
+            file=sys.stderr,
+            flush=True,
+        )
+        return _empty_databases_df()
+    except EmptyDataError:
+        print(
+            f"WARNING: databases.csv exists but is empty: {csv_path}. Continuing without database dumps.",
+            file=sys.stderr,
+            flush=True,
+        )
+        return _empty_databases_df()
+
+
+def _backup_dumps_for_volume(
+    *,
+    containers: list[str],
+    vol_dir: str,
+    databases_df: "pandas.DataFrame",
+    database_containers: list[str],
+) -> tuple[bool, bool]:
+    """
+    Returns (found_db_container, dumped_any)
+    """
+    found_db = False
+    dumped_any = False
+
+    for c in containers:
+        is_db, dumped = backup_mariadb_or_postgres(
+            container=c,
+            volume_dir=vol_dir,
+            databases_df=databases_df,
+            database_containers=database_containers,
+        )
+        if is_db:
+            found_db = True
+        if dumped:
+            dumped_any = True
+
+    return found_db, dumped_any
+
+
+def main() -> int:
+    args = parse_args()
+
+    machine_id = get_machine_id()
+    backup_time = datetime.now().strftime("%Y%m%d%H%M%S")
+
+    versions_dir = os.path.join(args.backups_dir, machine_id, args.repo_name)
+    version_dir = create_version_directory(versions_dir, backup_time)
+
+    # IMPORTANT:
+    # - keep_default_na=False prevents empty fields from turning into NaN
+    # - dtype=str keeps all columns stable for comparisons/validation
+    #
+    # Robust behavior:
+    # - if the file is missing or empty, we continue without DB dumps.
+    databases_df = _load_databases_df(args.databases_csv)
+
+    print("💾 Start volume backups...", flush=True)
+
+    for volume_name in docker_volume_names():
+        print(f"Start backup routine for volume: {volume_name}", flush=True)
+        containers = containers_using_volume(volume_name)
+
+        # EARLY SKIP: if all linked containers are ignored, do not create any dirs
+        if volume_is_fully_ignored(containers, args.images_no_backup_required):
+            print(
+                f"Skipping volume '{volume_name}' entirely (all linked containers are ignored).",
+                flush=True,
+            )
+            continue
+
+        vol_dir = create_volume_directory(version_dir, volume_name)
+
+        found_db, dumped_any = _backup_dumps_for_volume(
+            containers=containers,
+            vol_dir=vol_dir,
+            databases_df=databases_df,
+            database_containers=args.database_containers,
+        )
+
+        # dump-only-sql logic:
+        if args.dump_only_sql:
+            if found_db:
+                if not dumped_any:
+                    print(
+                        f"WARNING: dump-only-sql requested but no DB dump was produced for DB volume '{volume_name}'. "
+                        "Falling back to file backup.",
+                        flush=True,
+                    )
+                    # fall through to file backup below
+                else:
+                    # DB volume successfully dumped -> skip file backup
+                    continue
+            # Non-DB volume -> always do file backup (fall through)
+
+        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(stoppable, "stop")
+            backup_volume(versions_dir, volume_name, vol_dir)
+            if not args.shutdown:
+                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):
+            stoppable = filter_stoppable(containers)
+            change_containers_status(stoppable, "stop")
+            backup_volume(versions_dir, volume_name, vol_dir)
+            if not args.shutdown:
+                change_containers_status(stoppable, "start")
+
+    # Stamp the backup version directory using dirval (python lib)
+    stamp_directory(version_dir)
+    print("Finished volume backups.", flush=True)
+
+    print("Handling Docker Compose services...", flush=True)
+    handle_docker_compose_services(args.compose_dir, args.hard_compose_restart)
+
+    return 0

src/baudolo/backup/cli.py

@@ -0,0 +1,82 @@
+from __future__ import annotations
+
+import argparse
+import os
+
+
+def parse_args() -> argparse.Namespace:
+    dirname = os.path.dirname(__file__)
+    default_databases_csv = os.path.join(dirname, "databases.csv")
+
+    p = argparse.ArgumentParser(description="Backup Docker volumes.")
+
+    p.add_argument(
+        "--compose-dir",
+        type=str,
+        required=True,
+        help="Path to the parent directory containing docker-compose setups",
+    )
+    p.add_argument(
+        "--hard-compose-restart",
+        nargs="*",
+        default=[],
+        help="Compose dir names that require 'docker-compose down && up -d' (default: none; pass e.g. 'mailu' under compose where the DB cannot be backed up hot)",
+    )
+
+    p.add_argument(
+        "--repo-name",
+        default="backup-docker-to-local",
+        help="Backup repo folder name under <backups-dir>/<machine-id>/ (default: git repo folder name)",
+    )
+    p.add_argument(
+        "--databases-csv",
+        default=default_databases_csv,
+        help=f"Path to databases.csv (default: {default_databases_csv})",
+    )
+    p.add_argument(
+        "--backups-dir",
+        required=True,
+        help="Backup root directory (e.g. /var/lib/backup/)",
+    )
+
+    p.add_argument(
+        "--database-containers",
+        nargs="+",
+        required=True,
+        help="Container names treated as special instances for database backups",
+    )
+    p.add_argument(
+        "--images-no-stop-required",
+        nargs="+",
+        required=True,
+        help="Image name patterns for which containers should not be stopped during file backup",
+    )
+    p.add_argument(
+        "--images-no-backup-required",
+        nargs="+",
+        default=[],
+        help="Image name patterns for which no backup should be performed",
+    )
+
+    p.add_argument(
+        "--everything",
+        action="store_true",
+        help="Force file backup for all volumes and also execute database dumps (like old script)",
+    )
+    p.add_argument(
+        "--shutdown",
+        action="store_true",
+        help="Do not restart containers after backup",
+    )
+
+    p.add_argument(
+        "--dump-only-sql",
+        action="store_true",
+        help=(
+            "Create database dumps only for DB volumes. "
+            "File backups are skipped for DB volumes if a dump succeeds, "
+            "but non-DB volumes are still backed up. "
+            "If a DB dump cannot be produced, baudolo falls back to a file backup."
+        ),
+    )
+    return p.parse_args()

src/baudolo/backup/compose.py

@@ -0,0 +1,99 @@
+from __future__ import annotations
+
+import os
+import shutil
+import subprocess
+from pathlib import Path
+from typing import List, Optional
+
+
+def _build_compose_cmd(project_dir: str, passthrough: List[str]) -> List[str]:
+    """
+    Build the compose command for this project directory.
+
+    Policy:
+    - If `compose` wrapper exists (Infinito.Nexus): use it and delegate ALL logic to it.
+    - Else: use plain `docker compose` with --chdir.
+    - NO custom compose file/env detection in this project.
+    """
+    pdir = Path(project_dir).resolve()
+
+    wrapper = shutil.which("compose")
+    if wrapper:
+        # "--" ensures wrapper stops parsing its own args.
+        return [wrapper, "--chdir", str(pdir), "--", *passthrough]
+
+    docker = shutil.which("docker")
+    if docker:
+        return [docker, "compose", "--chdir", str(pdir), *passthrough]
+
+    raise RuntimeError("Neither 'compose' nor 'docker' found in PATH")
+
+
+def _find_compose_file(project_dir: str) -> Optional[Path]:
+    """
+    Detect a compose file in `project_dir` (case-insensitive).
+
+    Supported names:
+    - compose.yml / compose.yaml
+    - docker-compose.yml / docker-compose.yaml
+    """
+    pdir = Path(project_dir)
+    if not pdir.is_dir():
+        return None
+
+    # Map lowercase filename -> actual Path (preserves original casing)
+    by_lower = {p.name.lower(): p for p in pdir.iterdir() if p.is_file()}
+
+    # Preferred order (policy decision)
+    candidates = [
+        "docker-compose.yml",
+        "docker-compose.yaml",
+        "compose.yml",
+        "compose.yaml",
+    ]
+
+    for name in candidates:
+        found = by_lower.get(name)
+        if found is not None:
+            return found
+
+    return None
+
+
+def hard_restart_docker_services(dir_path: str) -> None:
+    print(f"Hard restart compose services in: {dir_path}", flush=True)
+
+    down_cmd = _build_compose_cmd(dir_path, ["down"])
+    up_cmd = _build_compose_cmd(dir_path, ["up", "-d"])
+
+    print(">>> " + " ".join(down_cmd), flush=True)
+    subprocess.run(down_cmd, check=True)
+
+    print(">>> " + " ".join(up_cmd), flush=True)
+    subprocess.run(up_cmd, check=True)
+
+
+def handle_docker_compose_services(
+    parent_directory: str,
+    hard_restart_required: list[str],
+) -> None:
+    for entry in os.scandir(parent_directory):
+        if not entry.is_dir():
+            continue
+
+        dir_path = entry.path
+        name = os.path.basename(dir_path)
+
+        print(f"Checking directory: {dir_path}", flush=True)
+
+        compose_file = _find_compose_file(dir_path)
+        if compose_file is None:
+            print("No supported compose file found. Skipping.", flush=True)
+            continue
+
+        if name in hard_restart_required:
+            print(f"{name}: hard restart required.", flush=True)
+            hard_restart_docker_services(dir_path)
+        else:
+            print(f"{name}: no restart required.", flush=True)

src/baudolo/backup/db.py

@@ -0,0 +1,147 @@
+from __future__ import annotations
+
+import os
+import pathlib
+import re
+import logging
+from typing import Optional
+
+import pandas
+
+from .shell import BackupException, execute_shell_command
+
+log = logging.getLogger(__name__)
+
+
+def get_instance(container: str, database_containers: list[str]) -> str:
+    """
+    Derive a stable instance name from the container name.
+    """
+    if container in database_containers:
+        return container
+    return re.split(r"(_|-)(database|db|postgres)", container)[0]
+
+
+def _validate_database_value(value: Optional[str], *, instance: str) -> str:
+    """
+    Enforce explicit database semantics:
+
+    - "*"       => dump ALL databases (cluster dump for Postgres)
+    - "<name>"  => dump exactly this database
+    - ""        => invalid configuration (would previously result in NaN / nan.backup.sql)
+    """
+    v = (value or "").strip()
+    if v == "":
+        raise ValueError(
+            f"Invalid databases.csv entry for instance '{instance}': "
+            "column 'database' must be '*' or a concrete database name (not empty)."
+        )
+    return v
+
+
+def _atomic_write_cmd(cmd: str, out_file: str) -> None:
+    """
+    Write dump output atomically:
+    - write to <file>.tmp
+    - rename to <file> only on success
+
+    This prevents empty or partial dump files from being treated as valid backups.
+    """
+    tmp = f"{out_file}.tmp"
+    execute_shell_command(f"{cmd} > {tmp}")
+    execute_shell_command(f"mv {tmp} {out_file}")
+
+
+def fallback_pg_dumpall(
+    container: str, username: str, password: str, out_file: str
+) -> None:
+    """
+    Perform a full Postgres cluster dump using pg_dumpall.
+    """
+    cmd = (
+        f"PGPASSWORD={password} docker exec -i {container} "
+        f"pg_dumpall -U {username} -h localhost"
+    )
+    _atomic_write_cmd(cmd, out_file)
+
+
+def backup_database(
+    *,
+    container: str,
+    volume_dir: str,
+    db_type: str,
+    databases_df: "pandas.DataFrame",
+    database_containers: list[str],
+) -> bool:
+    """
+    Backup databases for a given DB container.
+
+    Returns True if at least one dump was produced.
+    """
+    instance_name = get_instance(container, database_containers)
+
+    entries = databases_df[databases_df["instance"] == instance_name]
+    if entries.empty:
+        log.debug("No database entries for instance '%s'", instance_name)
+        return False
+
+    out_dir = os.path.join(volume_dir, "sql")
+    pathlib.Path(out_dir).mkdir(parents=True, exist_ok=True)
+
+    produced = False
+
+    for row in entries.itertuples(index=False):
+        raw_db = getattr(row, "database", "")
+        user = (getattr(row, "username", "") or "").strip()
+        password = (getattr(row, "password", "") or "").strip()
+
+        db_value = _validate_database_value(raw_db, instance=instance_name)
+
+        # Explicit: dump ALL databases
+        if db_value == "*":
+            if db_type != "postgres":
+                raise ValueError(
+                    f"databases.csv entry for instance '{instance_name}': "
+                    "'*' is currently only supported for Postgres."
+                )
+
+            cluster_file = os.path.join(out_dir, f"{instance_name}.cluster.backup.sql")
+            fallback_pg_dumpall(container, user, password, cluster_file)
+            produced = True
+            continue
+
+        # Concrete database dump
+        db_name = db_value
+        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)
+            produced = True
+            continue
+
+        if db_type == "postgres":
+            try:
+                cmd = (
+                    f"PGPASSWORD={password} docker exec -i {container} "
+                    f"pg_dump -U {user} -d {db_name} -h localhost "
+                    f"--no-owner --no-privileges"
+                )
+                _atomic_write_cmd(cmd, dump_file)
+                produced = True
+            except BackupException as e:
+                # Explicit DB dump failed -> hard error
+                raise BackupException(
+                    f"Postgres dump failed for instance '{instance_name}', "
+                    f"database '{db_name}'. This database was explicitly configured "
+                    "and therefore must succeed.\n"
+                    f"{e}"
+                )
+            continue
+
+    return produced

src/baudolo/backup/docker.py

@@ -0,0 +1,82 @@
+from __future__ import annotations
+
+from .shell import BackupException, execute_shell_command
+
+
+def get_image_info(container: str) -> str:
+    return execute_shell_command(
+        f"docker inspect --format '{{{{.Config.Image}}}}' {container}"
+    )[0]
+
+
+def has_image(container: str, pattern: str) -> bool:
+    """Return True if container's image contains the pattern."""
+    return pattern in get_image_info(container)
+
+
+def docker_volume_names() -> list[str]:
+    return execute_shell_command("docker volume ls --format '{{.Name}}'")
+
+
+def containers_using_volume(volume_name: str) -> list[str]:
+    return execute_shell_command(
+        f"docker ps --filter volume=\"{volume_name}\" --format '{{{{.Names}}}}'"
+    )
+
+
+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:
+        print(f"No containers to {status}.", flush=True)
+        return
+    names = " ".join(containers)
+    print(f"{status.capitalize()} containers: {names}...", flush=True)
+    execute_shell_command(f"docker {status} {names}")
+
+
+def docker_volume_exists(volume: str) -> bool:
+    # Avoid throwing exceptions for exists checks.
+    try:
+        execute_shell_command(
+            f"docker volume inspect {volume} >/dev/null 2>&1 && echo OK"
+        )
+        return True
+    except Exception:
+        return False

src/baudolo/backup/shell.py

@@ -0,0 +1,26 @@
+from __future__ import annotations
+
+import subprocess
+
+
+class BackupException(Exception):
+    """Generic exception for backup errors."""
+
+
+def execute_shell_command(command: str) -> list[str]:
+    """Execute a shell command and return its output lines."""
+    print(command, flush=True)
+    process = subprocess.Popen(
+        [command],
+        stdout=subprocess.PIPE,
+        stderr=subprocess.PIPE,
+        shell=True,
+    )
+    out, err = process.communicate()
+    if process.returncode != 0:
+        raise BackupException(
+            f"Error in command: {command}\n"
+            f"Output: {out}\nError: {err}\n"
+            f"Exit code: {process.returncode}"
+        )
+    return [line.decode("utf-8") for line in out.splitlines()]

src/baudolo/backup/volume.py

@@ -0,0 +1,46 @@
+from __future__ import annotations
+
+import os
+import pathlib
+
+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}"
+    )[0]
+    return f"{path}/"
+
+
+def get_last_backup_dir(
+    versions_dir: str, volume_name: str, current_backup_dir: str
+) -> str | None:
+    versions = sorted(os.listdir(versions_dir), reverse=True)
+    for version in versions:
+        candidate = os.path.join(versions_dir, version, volume_name, "files", "")
+        if candidate != current_backup_dir and os.path.isdir(candidate):
+            return candidate
+    return None
+
+
+def backup_volume(versions_dir: str, volume_name: str, volume_dir: str) -> None:
+    """Perform incremental file backup of a Docker volume."""
+    dest = os.path.join(volume_dir, "files") + "/"
+    pathlib.Path(dest).mkdir(parents=True, exist_ok=True)
+
+    last = get_last_backup_dir(versions_dir, volume_name, dest)
+    link_dest = f"--link-dest='{last}'" if last else ""
+    source = get_storage_path(volume_name)
+
+    cmd = f"rsync -abP --delete --delete-excluded {link_dest} {source} {dest}"
+
+    try:
+        execute_shell_command(cmd)
+    except BackupException as e:
+        if "file has vanished" in str(e):
+            print(
+                "Warning: Some files vanished before transfer. Continuing.", flush=True
+            )
+        else:
+            raise

src/baudolo/restore/__init__.py

@@ -0,0 +1 @@
+__all__ = ["main"]

src/baudolo/restore/__main__.py

@@ -0,0 +1,141 @@
+from __future__ import annotations
+
+import argparse
+import sys
+
+from .paths import BackupPaths
+from .files import restore_volume_files
+from .db.postgres import restore_postgres_sql
+from .db.mariadb import restore_mariadb_sql
+
+
+def _add_common_backup_args(p: argparse.ArgumentParser) -> None:
+    p.add_argument("volume_name", help="Docker volume name (target volume)")
+    p.add_argument("backup_hash", help="Hashed machine id")
+    p.add_argument("version", help="Backup version directory name")
+
+    p.add_argument(
+        "--backups-dir",
+        default="/Backups",
+        help="Backup root directory (default: /Backups)",
+    )
+    p.add_argument(
+        "--repo-name",
+        default="backup-docker-to-local",
+        help="Backup repo folder name under <backups-dir>/<hash>/ (default: backup-docker-to-local)",
+    )
+
+
+def main(argv: list[str] | None = None) -> int:
+    parser = argparse.ArgumentParser(
+        prog="baudolo-restore",
+        description="Restore docker volume files and DB dumps.",
+    )
+    sub = parser.add_subparsers(dest="cmd", required=True)
+
+    # ------------------------------------------------------------------
+    # files
+    # ------------------------------------------------------------------
+    p_files = sub.add_parser("files", help="Restore files into a docker volume")
+    _add_common_backup_args(p_files)
+    p_files.add_argument(
+        "--source-volume",
+        default=None,
+        help=(
+            "Volume name used as backup source path key. "
+            "Defaults to <volume_name> (target volume). "
+            "Use this when restoring from one volume backup into a different target volume."
+        ),
+    )
+
+    # ------------------------------------------------------------------
+    # postgres
+    # ------------------------------------------------------------------
+    p_pg = sub.add_parser("postgres", help="Restore a single PostgreSQL database dump")
+    _add_common_backup_args(p_pg)
+    p_pg.add_argument("--container", required=True)
+    p_pg.add_argument("--db-name", required=True)
+    p_pg.add_argument("--db-user", default=None, help="Defaults to db-name if omitted")
+    p_pg.add_argument("--db-password", required=True)
+    p_pg.add_argument("--empty", action="store_true")
+
+    # ------------------------------------------------------------------
+    # mariadb
+    # ------------------------------------------------------------------
+    p_mdb = sub.add_parser(
+        "mariadb", help="Restore a single MariaDB/MySQL-compatible dump"
+    )
+    _add_common_backup_args(p_mdb)
+    p_mdb.add_argument("--container", required=True)
+    p_mdb.add_argument("--db-name", required=True)
+    p_mdb.add_argument("--db-user", default=None, help="Defaults to db-name if omitted")
+    p_mdb.add_argument("--db-password", required=True)
+    p_mdb.add_argument("--empty", action="store_true")
+
+    args = parser.parse_args(argv)
+
+    try:
+        if args.cmd == "files":
+            # target volume = args.volume_name
+            # source volume (backup key) defaults to target volume
+            source_volume = args.source_volume or args.volume_name
+
+            bp_files = BackupPaths(
+                source_volume,
+                args.backup_hash,
+                args.version,
+                repo_name=args.repo_name,
+                backups_dir=args.backups_dir,
+            )
+
+            return restore_volume_files(
+                args.volume_name,
+                bp_files.files_dir(),
+            )
+
+        if args.cmd == "postgres":
+            user = args.db_user or args.db_name
+            restore_postgres_sql(
+                container=args.container,
+                db_name=args.db_name,
+                user=user,
+                password=args.db_password,
+                sql_path=BackupPaths(
+                    args.volume_name,
+                    args.backup_hash,
+                    args.version,
+                    repo_name=args.repo_name,
+                    backups_dir=args.backups_dir,
+                ).sql_file(args.db_name),
+                empty=args.empty,
+            )
+            return 0
+
+        if args.cmd == "mariadb":
+            user = args.db_user or args.db_name
+            restore_mariadb_sql(
+                container=args.container,
+                db_name=args.db_name,
+                user=user,
+                password=args.db_password,
+                sql_path=BackupPaths(
+                    args.volume_name,
+                    args.backup_hash,
+                    args.version,
+                    repo_name=args.repo_name,
+                    backups_dir=args.backups_dir,
+                ).sql_file(args.db_name),
+                empty=args.empty,
+            )
+            return 0
+
+        parser.error("Unhandled command")
+        return 2
+
+    except Exception as e:
+        print(f"ERROR: {e}", file=sys.stderr)
+        return 1
+
+
+if __name__ == "__main__":
+    raise SystemExit(main())

src/baudolo/restore/db/__init__.py

@@ -0,0 +1 @@
+"""Database restore handlers (Postgres, MariaDB/MySQL)."""

src/baudolo/restore/db/mariadb.py

@@ -0,0 +1,92 @@
+from __future__ import annotations
+
+import os
+import sys
+
+from ..run import docker_exec, docker_exec_sh
+
+
+def _pick_client(container: str) -> str:
+    """
+    Prefer 'mariadb', fallback to 'mysql'.
+    Some MariaDB images no longer ship a 'mysql' binary, so we must not assume it exists.
+    """
+    script = r"""
+set -eu
+if command -v mariadb >/dev/null 2>&1; then echo mariadb; exit 0; fi
+if command -v mysql   >/dev/null 2>&1; then echo mysql;   exit 0; fi
+exit 42
+"""
+    try:
+        out = docker_exec_sh(container, script, capture=True).stdout.decode().strip()
+        if not out:
+            raise RuntimeError("empty client detection output")
+        return out
+    except Exception as e:
+        print(
+            "ERROR: neither 'mariadb' nor 'mysql' found in container.", file=sys.stderr
+        )
+        raise e
+
+
+def restore_mariadb_sql(
+    *,
+    container: str,
+    db_name: str,
+    user: str,
+    password: str,
+    sql_path: str,
+    empty: bool,
+) -> None:
+    client = _pick_client(container)
+
+    if not os.path.isfile(sql_path):
+        raise FileNotFoundError(sql_path)
+
+    if empty:
+        # IMPORTANT:
+        # Do NOT hardcode 'mysql' here. Use the detected client.
+        # MariaDB 11 images may not contain the mysql binary at all.
+        result = docker_exec(
+            container,
+            [
+                client,
+                "-u",
+                user,
+                f"--password={password}",
+                "-N",
+                "-e",
+                f"SELECT table_name FROM information_schema.tables WHERE table_schema = '{db_name}';",
+            ],
+            capture=True,
+        )
+        tables = result.stdout.decode().split()
+
+        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,
+                [
+                    client,
+                    "-u",
+                    user,
+                    f"--password={password}",
+                    "-e",
+                    drop_sql,
+                ],
+            )
+
+    with open(sql_path, "rb") as f:
+        docker_exec(
+            container, [client, "-u", user, f"--password={password}", db_name], stdin=f
+        )
+
+    print(f"MariaDB/MySQL restore complete for db '{db_name}'.")

src/baudolo/restore/db/postgres.py

@@ -0,0 +1,122 @@
+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(
+    *,
+    container: str,
+    db_name: str,
+    user: str,
+    password: str,
+    sql_path: str,
+    empty: bool,
+) -> None:
+    if not os.path.isfile(sql_path):
+        raise FileNotFoundError(sql_path)
+
+    # Make password available INSIDE the container for psql.
+    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 $$ DECLARE r RECORD;
+BEGIN
+  FOR r IN (
+    SELECT c.relname AS name,
+           CASE c.relkind
+             WHEN 'v' THEN 'VIEW'
+             WHEN 'm' THEN 'MATERIALIZED VIEW'
+             WHEN 'f' THEN 'FOREIGN TABLE'
+             ELSE 'TABLE'
+           END AS type
+      FROM pg_class c JOIN pg_namespace n ON n.oid = c.relnamespace
+     WHERE n.nspname = 'public' AND c.relkind IN ('r', 'p', 'v', 'm', 'f')
+       AND pg_get_userbyid(c.relowner) = current_user
+    UNION ALL
+    SELECT p.proname AS name,
+           CASE p.prokind WHEN 'p' THEN 'PROCEDURE' ELSE 'FUNCTION' END AS type
+      FROM pg_proc p JOIN pg_namespace n ON n.oid = p.pronamespace
+     WHERE n.nspname = 'public' AND p.prokind IN ('f', 'p', 'w')
+       AND pg_get_userbyid(p.proowner) = current_user
+    UNION ALL
+    SELECT c.relname AS name, 'SEQUENCE' AS type
+      FROM pg_class c JOIN pg_namespace n ON n.oid = c.relnamespace
+     WHERE n.nspname = 'public' AND c.relkind = 'S'
+       AND pg_get_userbyid(c.relowner) = current_user
+    UNION ALL
+    SELECT t.typname AS name, 'TYPE' AS type
+      FROM pg_type t JOIN pg_namespace n ON n.oid = t.typnamespace
+     WHERE n.nspname = 'public'
+       AND pg_get_userbyid(t.typowner) = current_user
+       AND (t.typtype IN ('e', 'd')
+            OR (t.typtype = 'c' AND EXISTS (
+                  SELECT 1 FROM pg_class c2
+                   WHERE c2.oid = t.typrelid AND c2.relkind = 'c')))
+    UNION ALL
+    SELECT col.collname AS name, 'COLLATION' AS type
+      FROM pg_collation col JOIN pg_namespace n ON n.oid = col.collnamespace
+     WHERE n.nspname = 'public'
+       AND pg_get_userbyid(col.collowner) = current_user
+  ) LOOP
+    EXECUTE format('DROP %s IF EXISTS public.%I CASCADE', r.type, r.name);
+  END LOOP;
+END $$;
+"""
+        docker_exec(
+            container,
+            ["psql", "-v", "ON_ERROR_STOP=1", "-U", user, "-d", db_name],
+            stdin=drop_sql.encode(),
+            docker_env=docker_env,
+        )
+
+    # 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=filtered,
+            docker_env=docker_env,
+        )
+
+    print(f"PostgreSQL restore complete for db '{db_name}'.")

src/baudolo/restore/files.py

@@ -0,0 +1,37 @@
+from __future__ import annotations
+
+import os
+import sys
+
+from .run import docker_volume_exists, run
+
+
+def restore_volume_files(volume_name: str, backup_files_dir: str) -> int:
+    if not os.path.isdir(backup_files_dir):
+        print(f"ERROR: backup files dir not found: {backup_files_dir}", file=sys.stderr)
+        return 2
+
+    if not docker_volume_exists(volume_name):
+        print(f"Volume {volume_name} does not exist. Creating...")
+        run(["docker", "volume", "create", volume_name])
+    else:
+        print(f"Volume {volume_name} already exists.")
+
+    cp = run(
+        ["docker", "volume", "inspect", "--format", "{{ .Mountpoint }}", volume_name],
+        capture=True,
+    )
+    raw = cp.stdout or b""
+    mountpoint = (raw.decode() if isinstance(raw, bytes) else raw).strip()
+    if not mountpoint:
+        print(
+            f"ERROR: could not resolve mountpoint for volume {volume_name}",
+            file=sys.stderr,
+        )
+        return 2
+
+    src = os.path.join(backup_files_dir, "")
+    dest = os.path.join(mountpoint, "")
+    run(["rsync", "-avv", "--delete", src, dest])
+    print("File restore complete.")
+    return 0

src/baudolo/restore/paths.py

@@ -0,0 +1,29 @@
+from __future__ import annotations
+
+import os
+from dataclasses import dataclass
+
+
+@dataclass(frozen=True)
+class BackupPaths:
+    volume_name: str
+    backup_hash: str
+    version: str
+    repo_name: str
+    backups_dir: str = "/Backups"
+
+    def root(self) -> str:
+        # Always build an absolute path under backups_dir
+        return os.path.join(
+            self.backups_dir,
+            self.backup_hash,
+            self.repo_name,
+            self.version,
+            self.volume_name,
+        )
+
+    def files_dir(self) -> str:
+        return os.path.join(self.root(), "files")
+
+    def sql_file(self, db_name: str) -> str:
+        return os.path.join(self.root(), "sql", f"{db_name}.backup.sql")

src/baudolo/restore/run.py

@@ -0,0 +1,89 @@
+from __future__ import annotations
+
+import subprocess
+import sys
+from typing import Optional
+
+
+def run(
+    cmd: list[str],
+    *,
+    stdin=None,
+    capture: bool = False,
+    env: Optional[dict] = None,
+) -> subprocess.CompletedProcess:
+    try:
+        kwargs: dict = {
+            "check": True,
+            "capture_output": capture,
+            "env": env,
+        }
+
+        # If stdin is raw data (bytes/str), pass it via input=.
+        # IMPORTANT: when using input=..., do NOT pass stdin=... as well.
+        if isinstance(stdin, (bytes, str)):
+            kwargs["input"] = stdin
+        else:
+            kwargs["stdin"] = stdin
+
+        return subprocess.run(cmd, **kwargs)
+
+    except subprocess.CalledProcessError as e:
+        msg = f"ERROR: command failed ({e.returncode}): {' '.join(cmd)}"
+        print(msg, file=sys.stderr)
+        if e.stdout:
+            try:
+                print(e.stdout.decode(), file=sys.stderr)
+            except Exception:
+                print(e.stdout, file=sys.stderr)
+        if e.stderr:
+            try:
+                print(e.stderr.decode(), file=sys.stderr)
+            except Exception:
+                print(e.stderr, file=sys.stderr)
+        raise
+
+
+def docker_exec(
+    container: str,
+    argv: list[str],
+    *,
+    stdin=None,
+    capture: bool = False,
+    env: Optional[dict] = None,
+    docker_env: Optional[dict[str, str]] = None,
+) -> subprocess.CompletedProcess:
+    cmd: list[str] = ["docker", "exec", "-i"]
+    if docker_env:
+        for k, v in docker_env.items():
+            cmd.extend(["-e", f"{k}={v}"])
+    cmd.extend([container, *argv])
+    return run(cmd, stdin=stdin, capture=capture, env=env)
+
+
+def docker_exec_sh(
+    container: str,
+    script: str,
+    *,
+    stdin=None,
+    capture: bool = False,
+    env: Optional[dict] = None,
+    docker_env: Optional[dict[str, str]] = None,
+) -> subprocess.CompletedProcess:
+    return docker_exec(
+        container,
+        ["sh", "-lc", script],
+        stdin=stdin,
+        capture=capture,
+        env=env,
+        docker_env=docker_env,
+    )
+
+
+def docker_volume_exists(volume: str) -> bool:
+    p = subprocess.run(
+        ["docker", "volume", "inspect", volume],
+        stdout=subprocess.DEVNULL,
+        stderr=subprocess.DEVNULL,
+    )
+    return p.returncode == 0

src/baudolo/seed/__main__.py

@@ -0,0 +1,117 @@
+#!/usr/bin/env python3
+from __future__ import annotations
+
+import argparse
+import os
+import re
+import sys
+import pandas as pd
+from typing import Optional
+from pandas.errors import EmptyDataError
+
+DB_NAME_RE = re.compile(r"^[a-zA-Z0-9_][a-zA-Z0-9_-]*$")
+
+
+def _validate_database_value(value: Optional[str], *, instance: str) -> str:
+    v = (value or "").strip()
+    if v == "":
+        raise ValueError(
+            f"Invalid databases.csv entry for instance '{instance}': "
+            "column 'database' must be '*' or a concrete database name (not empty)."
+        )
+    if v == "*":
+        return "*"
+    if v.lower() == "nan":
+        raise ValueError(
+            f"Invalid databases.csv entry for instance '{instance}': database must not be 'nan'."
+        )
+    if not DB_NAME_RE.match(v):
+        raise ValueError(
+            f"Invalid databases.csv entry for instance '{instance}': "
+            f"invalid database name '{v}'. Allowed: letters, numbers, '_' and '-'."
+        )
+    return v
+
+
+def _empty_df() -> pd.DataFrame:
+    return pd.DataFrame(columns=["instance", "database", "username", "password"])
+
+
+def check_and_add_entry(
+    file_path: str,
+    instance: str,
+    database: Optional[str],
+    username: str,
+    password: str,
+) -> None:
+    """
+    Add or update an entry in databases.csv.
+
+    The function enforces strict validation:
+    - database MUST be set
+    - database MUST be '*' or a valid database name
+    """
+    database = _validate_database_value(database, instance=instance)
+
+    if os.path.exists(file_path):
+        try:
+            df = pd.read_csv(
+                file_path,
+                sep=";",
+                dtype=str,
+                keep_default_na=False,
+            )
+        except EmptyDataError:
+            print(
+                f"WARNING: databases.csv exists but is empty: {file_path}. Creating header columns.",
+                file=sys.stderr,
+            )
+            df = _empty_df()
+    else:
+        df = _empty_df()
+    mask = (df["instance"] == instance) & (df["database"] == database)
+
+    if mask.any():
+        print("Updating existing entry.")
+        df.loc[mask, ["username", "password"]] = [username, password]
+    else:
+        print("Adding new entry.")
+        new_entry = pd.DataFrame(
+            [[instance, database, username, password]],
+            columns=["instance", "database", "username", "password"],
+        )
+        df = pd.concat([df, new_entry], ignore_index=True)
+
+    df.to_csv(file_path, sep=";", index=False)
+
+
+def main() -> None:
+    parser = argparse.ArgumentParser(
+        description="Seed or update databases.csv for backup configuration."
+    )
+    parser.add_argument("file", help="Path to databases.csv")
+    parser.add_argument("instance", help="Instance name (e.g. bigbluebutton)")
+    parser.add_argument(
+        "database",
+        help="Database name or '*' to dump all databases",
+    )
+    parser.add_argument("username", help="Database username")
+    parser.add_argument("password", help="Database password")
+
+    args = parser.parse_args()
+
+    try:
+        check_and_add_entry(
+            file_path=args.file,
+            instance=args.instance,
+            database=args.database,
+            username=args.username,
+            password=args.password,
+        )
+    except Exception as exc:
+        print(f"ERROR: {exc}", file=sys.stderr)
+        sys.exit(1)
+
+
+if __name__ == "__main__":
+    main()

tests/e2e/helpers.py

@@ -0,0 +1,265 @@
+# tests/e2e/helpers.py
+from __future__ import annotations
+
+import shutil
+import subprocess
+import time
+import uuid
+from pathlib import Path
+
+# SPOT for the database images and their in-container data dirs the e2e
+# suite runs against. postgres:alpine tracks latest (18+), which mounts at
+# /var/lib/postgresql (not /var/lib/postgresql/data); bump here only.
+POSTGRES_IMAGE = "postgres:alpine"
+POSTGRES_DATA_DIR = "/var/lib/postgresql"
+MARIADB_IMAGE = "mariadb:latest"
+MARIADB_DATA_DIR = "/var/lib/mysql"
+
+
+def run(
+    cmd: list[str],
+    *,
+    capture: bool = True,
+    check: bool = True,
+    cwd: str | None = None,
+) -> subprocess.CompletedProcess:
+    try:
+        return subprocess.run(
+            cmd,
+            check=check,
+            cwd=cwd,
+            text=True,
+            capture_output=capture,
+        )
+    except subprocess.CalledProcessError as e:
+        # Print captured output so failing E2E tests are "live" / debuggable in CI logs
+        print(">>> command failed:", " ".join(cmd))
+        print(">>> exit code:", e.returncode)
+        if e.stdout:
+            print(">>> STDOUT:\n" + e.stdout)
+        if e.stderr:
+            print(">>> STDERR:\n" + e.stderr)
+        raise
+
+
+def sh(
+    cmd: str, *, capture: bool = True, check: bool = True
+) -> subprocess.CompletedProcess:
+    return run(["sh", "-lc", cmd], capture=capture, check=check)
+
+
+def unique(prefix: str) -> str:
+    return f"{prefix}-{uuid.uuid4().hex[:10]}"
+
+
+def require_docker() -> None:
+    run(["docker", "version"], capture=True, check=True)
+
+
+def machine_hash() -> str:
+    out = sh("sha256sum /etc/machine-id | awk '{print $1}'").stdout.strip()
+    if len(out) < 16:
+        raise RuntimeError("Could not determine machine hash from /etc/machine-id")
+    return out
+
+
+def wait_for_log(container: str, pattern: str, timeout_s: int = 60) -> None:
+    deadline = time.time() + timeout_s
+    while time.time() < deadline:
+        p = run(["docker", "logs", container], capture=True, check=False)
+        if pattern in (p.stdout or ""):
+            return
+        time.sleep(1)
+    raise TimeoutError(f"Timed out waiting for log pattern '{pattern}' in {container}")
+
+
+def wait_for_postgres(
+    container: str, *, user: str = "postgres", timeout_s: int = 90
+) -> None:
+    """
+    Docker-outside-of-Docker friendly readiness: check from inside the DB container.
+    """
+    deadline = time.time() + timeout_s
+    while time.time() < deadline:
+        p = run(
+            [
+                "docker",
+                "exec",
+                container,
+                "sh",
+                "-lc",
+                f"pg_isready -U {user} -h localhost",
+            ],
+            capture=True,
+            check=False,
+        )
+        if p.returncode == 0:
+            return
+        time.sleep(1)
+    raise TimeoutError(
+        f"Timed out waiting for Postgres readiness in container {container}"
+    )
+
+
+def wait_for_mariadb(
+    container: str, *, root_password: str, timeout_s: int = 90
+) -> None:
+    """
+    Liveness probe for MariaDB.
+
+    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.
+    """
+    deadline = time.time() + timeout_s
+    while time.time() < deadline:
+        p = run(
+            [
+                "docker",
+                "exec",
+                container,
+                "sh",
+                "-lc",
+                'mariadb -uroot --protocol=socket -e "SELECT 1;"',
+            ],
+            capture=True,
+            check=False,
+        )
+        if p.returncode == 0:
+            return
+        time.sleep(1)
+    raise TimeoutError(
+        f"Timed out waiting for MariaDB readiness in container {container}"
+    )
+
+
+def wait_for_mariadb_sql(
+    container: str, *, user: str, password: str, timeout_s: int = 90
+) -> None:
+    """
+    SQL login readiness for the *dedicated test user* over TCP.
+
+    This is separate from wait_for_mariadb(root) because root may be socket-only,
+    while the tests use a normal user that should work via TCP.
+    """
+    deadline = time.time() + timeout_s
+    while time.time() < deadline:
+        p = run(
+            [
+                "docker",
+                "exec",
+                container,
+                "sh",
+                "-lc",
+                f'mariadb -h 127.0.0.1 -u{user} -p{password} -e "SELECT 1;"',
+            ],
+            capture=True,
+            check=False,
+        )
+        if p.returncode == 0:
+            return
+        time.sleep(1)
+    raise TimeoutError(
+        f"Timed out waiting for MariaDB SQL login readiness in container {container}"
+    )
+
+
+def backup_run(
+    *,
+    backups_dir: str,
+    repo_name: str,
+    compose_dir: str,
+    databases_csv: str,
+    database_containers: list[str],
+    images_no_stop_required: list[str],
+    images_no_backup_required: list[str] | None = None,
+    dump_only_sql: bool = False,
+) -> None:
+    cmd = [
+        "baudolo",
+        "--compose-dir",
+        compose_dir,
+        "--hard-compose-restart",
+        "mailu",
+        "--repo-name",
+        repo_name,
+        "--databases-csv",
+        databases_csv,
+        "--backups-dir",
+        backups_dir,
+        "--database-containers",
+        *database_containers,
+        "--images-no-stop-required",
+        *images_no_stop_required,
+    ]
+    if images_no_backup_required:
+        cmd += ["--images-no-backup-required", *images_no_backup_required]
+    if dump_only_sql:
+        cmd += ["--dump-only-sql"]
+
+    try:
+        run(cmd, capture=True, check=True)
+    except subprocess.CalledProcessError as e:
+        print(">>> baudolo failed (exit code:", e.returncode, ")")
+        if e.stdout:
+            print(">>> baudolo STDOUT:\n" + e.stdout)
+        if e.stderr:
+            print(">>> baudolo STDERR:\n" + e.stderr)
+        raise
+
+
+def latest_version_dir(backups_dir: str, repo_name: str) -> tuple[str, str]:
+    """
+    Returns (hash, version) for the latest backup.
+    """
+    h = machine_hash()
+    root = Path(backups_dir) / h / repo_name
+    if not root.is_dir():
+        raise FileNotFoundError(str(root))
+
+    versions = sorted([p.name for p in root.iterdir() if p.is_dir()])
+    if not versions:
+        raise RuntimeError(f"No versions found under {root}")
+    return h, versions[-1]
+
+
+def backup_path(backups_dir: str, repo_name: str, version: str, volume: str) -> Path:
+    h = machine_hash()
+    return Path(backups_dir) / h / repo_name / version / volume
+
+
+def create_minimal_compose_dir(base: str) -> str:
+    """
+    baudolo requires --compose-dir. Create an empty dir with one non-compose subdir.
+    """
+    p = Path(base) / "compose-root"
+    p.mkdir(parents=True, exist_ok=True)
+    (p / "noop").mkdir(parents=True, exist_ok=True)
+    return str(p)
+
+
+def write_databases_csv(path: str, rows: list[tuple[str, str, str, str]]) -> None:
+    """
+    rows: (instance, database, username, password)
+    database may be '' (empty) to trigger pg_dumpall behavior if you want, but here we use db name.
+    """
+    Path(path).parent.mkdir(parents=True, exist_ok=True)
+    with open(path, "w", encoding="utf-8") as f:
+        f.write("instance;database;username;password\n")
+        for inst, db, user, pw in rows:
+            f.write(f"{inst};{db};{user};{pw}\n")
+
+
+def cleanup_docker(*, containers: list[str], volumes: list[str]) -> None:
+    for c in containers:
+        run(["docker", "rm", "-f", c], capture=True, check=False)
+    for v in volumes:
+        run(["docker", "volume", "rm", "-f", v], capture=True, check=False)
+
+
+def ensure_empty_dir(path: str) -> None:
+    p = Path(path)
+    if p.exists():
+        shutil.rmtree(p)
+    p.mkdir(parents=True, exist_ok=True)

tests/e2e/test_e2e_cli_contract_dump_only_sql.py

@@ -0,0 +1,29 @@
+import unittest
+
+from .helpers import run
+
+
+class TestE2ECLIContractDumpOnlySql(unittest.TestCase):
+    def test_help_mentions_new_flag(self) -> None:
+        cp = run(["baudolo", "--help"], capture=True, check=True)
+        out = (cp.stdout or "") + "\n" + (cp.stderr or "")
+        self.assertIn(
+            "--dump-only-sql",
+            out,
+            f"Expected '--dump-only-sql' to appear in --help output. Output:\n{out}",
+        )
+
+    def test_old_flag_is_rejected(self) -> None:
+        cp = run(["baudolo", "--dump-only"], capture=True, check=False)
+        self.assertEqual(
+            cp.returncode,
+            2,
+            f"Expected exitcode 2 for unknown args, got {cp.returncode}\n"
+            f"STDOUT={cp.stdout}\nSTDERR={cp.stderr}",
+        )
+        err = (cp.stderr or "") + "\n" + (cp.stdout or "")
+        # Argparse typically prints "unrecognized arguments"
+        self.assertTrue(
+            ("unrecognized arguments" in err) or ("usage:" in err.lower()),
+            f"Expected argparse-style error output. Output:\n{err}",
+        )

tests/e2e/test_e2e_dump_only_fallback_to_files.py

@@ -0,0 +1,181 @@
+# tests/e2e/test_e2e_dump_only_fallback_to_files.py
+import unittest
+
+from .helpers import (
+    POSTGRES_IMAGE,
+    POSTGRES_DATA_DIR,
+    backup_path,
+    cleanup_docker,
+    create_minimal_compose_dir,
+    ensure_empty_dir,
+    latest_version_dir,
+    require_docker,
+    run,
+    unique,
+    write_databases_csv,
+    wait_for_postgres,
+)
+
+
+class TestE2EDumpOnlyFallbackToFiles(unittest.TestCase):
+    @classmethod
+    def setUpClass(cls) -> None:
+        require_docker()
+        cls.prefix = unique("baudolo-e2e-dump-only-sql-fallback")
+        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.pg_container = f"{cls.prefix}-pg"
+        cls.pg_volume = f"{cls.prefix}-pg-vol"
+        cls.restore_volume = f"{cls.prefix}-restore-vol"
+
+        cls.containers = [cls.pg_container]
+        cls.volumes = [cls.pg_volume, cls.restore_volume]
+
+        run(["docker", "volume", "create", cls.pg_volume])
+
+        # Start Postgres (creates a real DB volume)
+        run(
+            [
+                "docker",
+                "run",
+                "-d",
+                "--name",
+                cls.pg_container,
+                "-e",
+                "POSTGRES_PASSWORD=pgpw",
+                "-e",
+                "POSTGRES_DB=appdb",
+                "-e",
+                "POSTGRES_USER=postgres",
+                "-v",
+                f"{cls.pg_volume}:{POSTGRES_DATA_DIR}",
+                POSTGRES_IMAGE,
+            ]
+        )
+        wait_for_postgres(cls.pg_container, user="postgres", timeout_s=90)
+
+        # Add a deterministic marker file into the volume
+        cls.marker = "dump-only-sql-fallback-marker"
+        run(
+            [
+                "docker",
+                "exec",
+                cls.pg_container,
+                "sh",
+                "-lc",
+                f"echo '{cls.marker}' > {POSTGRES_DATA_DIR}/marker.txt",
+            ]
+        )
+
+        # databases.csv WITHOUT matching entry for this instance -> should skip dump
+        cls.databases_csv = f"/tmp/{cls.prefix}/databases.csv"
+        write_databases_csv(cls.databases_csv, [])  # empty except header
+
+        # Run baudolo with --dump-only-sql and a DB container present:
+        # Expected: WARNING + FALLBACK to file backup (files/ must exist)
+        cmd = [
+            "baudolo",
+            "--compose-dir",
+            cls.compose_dir,
+            "--hard-compose-restart",
+            "mailu",
+            "--repo-name",
+            cls.repo_name,
+            "--databases-csv",
+            cls.databases_csv,
+            "--backups-dir",
+            cls.backups_dir,
+            "--database-containers",
+            cls.pg_container,
+            "--images-no-stop-required",
+            "postgres",
+            "mariadb",
+            "mysql",
+            "alpine",
+            "--dump-only-sql",
+        ]
+        cp = run(cmd, capture=True, check=True)
+
+        cls.stdout = cp.stdout or ""
+        cls.hash, cls.version = latest_version_dir(cls.backups_dir, cls.repo_name)
+
+        # Restore files into a fresh volume to prove file backup happened
+        run(["docker", "volume", "create", cls.restore_volume])
+        run(
+            [
+                "baudolo-restore",
+                "files",
+                cls.restore_volume,
+                cls.hash,
+                cls.version,
+                "--backups-dir",
+                cls.backups_dir,
+                "--repo-name",
+                cls.repo_name,
+                "--source-volume",
+                cls.pg_volume,
+            ]
+        )
+
+    @classmethod
+    def tearDownClass(cls) -> None:
+        cleanup_docker(containers=cls.containers, volumes=cls.volumes)
+
+    def test_warns_about_missing_dump_in_dump_only_mode(self) -> None:
+        self.assertIn(
+            "WARNING: dump-only-sql requested but no DB dump was produced",
+            self.stdout,
+            f"Expected warning in baudolo output. STDOUT:\n{self.stdout}",
+        )
+
+    def test_files_backup_exists_due_to_fallback(self) -> None:
+        p = (
+            backup_path(
+                self.backups_dir,
+                self.repo_name,
+                self.version,
+                self.pg_volume,
+            )
+            / "files"
+        )
+        self.assertTrue(p.is_dir(), f"Expected files backup dir at: {p}")
+
+    def test_sql_dump_not_present(self) -> None:
+        # There should be no sql dumps because databases.csv had no matching entry.
+        sql_dir = (
+            backup_path(
+                self.backups_dir,
+                self.repo_name,
+                self.version,
+                self.pg_volume,
+            )
+            / "sql"
+        )
+        # Could exist (dir created) in some edge cases, but should contain no *.sql dumps.
+        if sql_dir.exists():
+            dumps = list(sql_dir.glob("*.sql"))
+            self.assertEqual(
+                len(dumps),
+                0,
+                f"Did not expect SQL dump files, found: {dumps}",
+            )
+
+    def test_restored_files_contain_marker(self) -> None:
+        p = run(
+            [
+                "docker",
+                "run",
+                "--rm",
+                "-v",
+                f"{self.restore_volume}:/data",
+                "alpine:3.20",
+                "sh",
+                "-lc",
+                "cat /data/marker.txt",
+            ]
+        )
+        self.assertEqual((p.stdout or "").strip(), self.marker)

tests/e2e/test_e2e_dump_only_sql_mixed_run.py

@@ -0,0 +1,186 @@
+import unittest
+
+from .helpers import (
+    POSTGRES_IMAGE,
+    POSTGRES_DATA_DIR,
+    backup_path,
+    cleanup_docker,
+    create_minimal_compose_dir,
+    ensure_empty_dir,
+    latest_version_dir,
+    require_docker,
+    run,
+    unique,
+    wait_for_postgres,
+    write_databases_csv,
+)
+
+
+class TestE2EDumpOnlySqlMixedRun(unittest.TestCase):
+    @classmethod
+    def setUpClass(cls) -> None:
+        require_docker()
+        cls.prefix = unique("baudolo-e2e-dump-only-sql-mixed-run")
+        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
+
+        # --- Volumes ---
+        cls.db_volume = f"{cls.prefix}-vol-db"
+        cls.files_volume = f"{cls.prefix}-vol-files"
+
+        # Track for cleanup
+        cls.containers: list[str] = []
+        cls.volumes = [cls.db_volume, cls.files_volume]
+
+        # Create volumes
+        run(["docker", "volume", "create", cls.db_volume])
+        run(["docker", "volume", "create", cls.files_volume])
+
+        # Put a marker into the non-db volume
+        run(
+            [
+                "docker",
+                "run",
+                "--rm",
+                "-v",
+                f"{cls.files_volume}:/data",
+                "alpine:3.20",
+                "sh",
+                "-lc",
+                "echo 'hello-non-db' > /data/hello.txt",
+            ]
+        )
+
+        # --- Start Postgres container using the DB volume ---
+        cls.pg_container = f"{cls.prefix}-pg"
+        cls.containers.append(cls.pg_container)
+
+        cls.pg_password = "postgres"
+        cls.pg_db = "testdb"
+        cls.pg_user = "postgres"
+
+        run(
+            [
+                "docker",
+                "run",
+                "-d",
+                "--name",
+                cls.pg_container,
+                "-e",
+                f"POSTGRES_PASSWORD={cls.pg_password}",
+                "-v",
+                f"{cls.db_volume}:{POSTGRES_DATA_DIR}",
+                POSTGRES_IMAGE,
+            ]
+        )
+        wait_for_postgres(cls.pg_container, user="postgres", timeout_s=90)
+
+        # Create deterministic content in DB so dump is non-empty
+        run(
+            [
+                "docker",
+                "exec",
+                cls.pg_container,
+                "sh",
+                "-lc",
+                f'psql -U postgres -c "CREATE DATABASE {cls.pg_db};" || true',
+            ],
+            check=True,
+        )
+        run(
+            [
+                "docker",
+                "exec",
+                cls.pg_container,
+                "sh",
+                "-lc",
+                (
+                    f"psql -U postgres -d {cls.pg_db} -c "
+                    '"CREATE TABLE IF NOT EXISTS t (id INT PRIMARY KEY, v TEXT);'
+                    "INSERT INTO t(id,v) VALUES (1,'hello-db') "
+                    'ON CONFLICT (id) DO UPDATE SET v=EXCLUDED.v;"'
+                ),
+            ],
+            check=True,
+        )
+
+        # databases.csv with an entry => dump should succeed
+        cls.databases_csv = f"/tmp/{cls.prefix}/databases.csv"
+        write_databases_csv(
+            cls.databases_csv,
+            [(cls.pg_container, cls.pg_db, cls.pg_user, cls.pg_password)],
+        )
+
+        # Run baudolo with dump-only-sql
+        cmd = [
+            "baudolo",
+            "--compose-dir",
+            cls.compose_dir,
+            "--databases-csv",
+            cls.databases_csv,
+            "--database-containers",
+            cls.pg_container,
+            "--images-no-stop-required",
+            "alpine",
+            "postgres",
+            "mariadb",
+            "mysql",
+            "--dump-only-sql",
+            "--backups-dir",
+            cls.backups_dir,
+            "--repo-name",
+            cls.repo_name,
+        ]
+        cp = run(cmd, capture=True, check=True)
+        cls.stdout = cp.stdout
+        cls.stderr = cp.stderr
+
+        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_db_volume_has_dump_and_no_files_dir(self) -> None:
+        base = backup_path(
+            self.backups_dir, self.repo_name, self.version, self.db_volume
+        )
+
+        dumps = base / "sql"
+        files = base / "files"
+
+        self.assertTrue(dumps.exists(), f"Expected dumps dir for DB volume at: {dumps}")
+        self.assertFalse(
+            files.exists(),
+            f"Did not expect files dir for DB volume when dump succeeded at: {files}",
+        )
+
+        # Optional: at least one dump file exists
+        dump_files = list(dumps.glob("*.sql")) + list(dumps.glob("*.sql.gz"))
+        self.assertTrue(
+            dump_files,
+            f"Expected at least one SQL dump file in {dumps}, found none.",
+        )
+
+    def test_non_db_volume_has_files_dir(self) -> None:
+        base = backup_path(
+            self.backups_dir, self.repo_name, self.version, self.files_volume
+        )
+        files = base / "files"
+        self.assertTrue(
+            files.exists(),
+            f"Expected files dir for non-DB volume at: {files}",
+        )
+
+    def test_dump_only_sql_does_not_disable_non_db_files_backup(self) -> None:
+        # Regression guard: even with --dump-only-sql, non-DB volumes must still be backed up as files
+        base = backup_path(
+            self.backups_dir, self.repo_name, self.version, self.files_volume
+        )
+        self.assertTrue(
+            (base / "files").exists(),
+            f"Expected non-DB volume files backup to exist at: {base / 'files'}",
+        )

tests/e2e/test_e2e_files_full.py

@@ -0,0 +1,114 @@
+import unittest
+
+from .helpers import (
+    backup_run,
+    backup_path,
+    cleanup_docker,
+    create_minimal_compose_dir,
+    ensure_empty_dir,
+    latest_version_dir,
+    require_docker,
+    unique,
+    write_databases_csv,
+    run,
+)
+
+
+class TestE2EFilesFull(unittest.TestCase):
+    @classmethod
+    def setUpClass(cls) -> None:
+        require_docker()
+        cls.prefix = unique("baudolo-e2e-files-full")
+        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_src = f"{cls.prefix}-vol-src"
+        cls.volume_dst = f"{cls.prefix}-vol-dst"
+        cls.containers = []
+        cls.volumes = [cls.volume_src, cls.volume_dst]
+
+        # create source volume with a file
+        run(["docker", "volume", "create", cls.volume_src])
+        run(
+            [
+                "docker",
+                "run",
+                "--rm",
+                "-v",
+                f"{cls.volume_src}:/data",
+                "alpine:3.20",
+                "sh",
+                "-lc",
+                "mkdir -p /data && echo 'hello' > /data/hello.txt",
+            ]
+        )
+
+        # databases.csv (unused, but required by CLI)
+        cls.databases_csv = f"/tmp/{cls.prefix}/databases.csv"
+        write_databases_csv(cls.databases_csv, [])
+
+        # Run backup (files should be copied)
+        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=["alpine", "postgres", "mariadb", "mysql"],
+        )
+
+        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_files_backup_exists(self) -> None:
+        p = (
+            backup_path(
+                self.backups_dir,
+                self.repo_name,
+                self.version,
+                self.volume_src,
+            )
+            / "files"
+            / "hello.txt"
+        )
+        self.assertTrue(p.is_file(), f"Expected backed up file at: {p}")
+
+    def test_restore_files_into_new_volume(self) -> None:
+        # restore files from volume_src backup into volume_dst
+        run(
+            [
+                "baudolo-restore",
+                "files",
+                self.volume_dst,
+                self.hash,
+                self.version,
+                "--backups-dir",
+                self.backups_dir,
+                "--repo-name",
+                self.repo_name,
+                "--source-volume",
+                self.volume_src,
+            ]
+        )
+
+        # verify restored file exists in dst volume
+        p = run(
+            [
+                "docker",
+                "run",
+                "--rm",
+                "-v",
+                f"{self.volume_dst}:/data",
+                "alpine:3.20",
+                "sh",
+                "-lc",
+                "cat /data/hello.txt",
+            ]
+        )
+        self.assertEqual((p.stdout or "").strip(), "hello")

tests/e2e/test_e2e_files_no_copy.py

@@ -0,0 +1,119 @@
+import unittest
+
+from .helpers import (
+    backup_run,
+    backup_path,
+    cleanup_docker,
+    create_minimal_compose_dir,
+    ensure_empty_dir,
+    latest_version_dir,
+    require_docker,
+    unique,
+    write_databases_csv,
+    run,
+)
+
+
+class TestE2EFilesNoCopy(unittest.TestCase):
+    @classmethod
+    def setUpClass(cls) -> None:
+        require_docker()
+        cls.prefix = unique("baudolo-e2e-files-nocopy")
+        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_src = f"{cls.prefix}-vol-src"
+        cls.containers: list[str] = []
+        cls.volumes = [cls.volume_src]
+
+        # Create source volume and write a marker file
+        run(["docker", "volume", "create", cls.volume_src])
+        run(
+            [
+                "docker",
+                "run",
+                "--rm",
+                "-v",
+                f"{cls.volume_src}:/data",
+                "alpine:3.20",
+                "sh",
+                "-lc",
+                "echo 'hello' > /data/hello.txt",
+            ]
+        )
+
+        cls.databases_csv = f"/tmp/{cls.prefix}/databases.csv"
+        write_databases_csv(cls.databases_csv, [])
+
+        # dump-only-sql => non-DB volumes are STILL backed up as files
+        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=["alpine", "postgres", "mariadb", "mysql"],
+            dump_only_sql=True,
+        )
+
+        cls.hash, cls.version = latest_version_dir(cls.backups_dir, cls.repo_name)
+
+        # Wipe the volume to ensure restore actually restores something
+        run(["docker", "volume", "rm", "-f", cls.volume_src])
+        run(["docker", "volume", "create", cls.volume_src])
+
+    @classmethod
+    def tearDownClass(cls) -> None:
+        cleanup_docker(containers=cls.containers, volumes=cls.volumes)
+
+    def test_files_backup_present_for_non_db_volume(self) -> None:
+        p = (
+            backup_path(self.backups_dir, self.repo_name, self.version, self.volume_src)
+            / "files"
+        )
+        self.assertTrue(p.exists(), f"Expected files backup dir at: {p}")
+
+    def test_restore_files_succeeds_and_restores_content(self) -> None:
+        p = run(
+            [
+                "baudolo-restore",
+                "files",
+                self.volume_src,
+                self.hash,
+                self.version,
+                "--backups-dir",
+                self.backups_dir,
+                "--repo-name",
+                self.repo_name,
+            ],
+            check=False,
+        )
+        self.assertEqual(
+            p.returncode,
+            0,
+            f"Expected exitcode 0, got {p.returncode}\nSTDOUT={p.stdout}\nSTDERR={p.stderr}",
+        )
+
+        cp = run(
+            [
+                "docker",
+                "run",
+                "--rm",
+                "-v",
+                f"{self.volume_src}:/data",
+                "alpine:3.20",
+                "sh",
+                "-lc",
+                "cat /data/hello.txt",
+            ],
+            capture=True,
+            check=True,
+        )
+        self.assertEqual(
+            cp.stdout.strip(),
+            "hello",
+            f"Unexpected restored content. STDOUT={cp.stdout}\nSTDERR={cp.stderr}",
+        )

tests/e2e/test_e2e_images_no_backup_required_early_skip.py

@@ -0,0 +1,131 @@
+# tests/e2e/test_e2e_images_no_backup_required_early_skip.py
+import unittest
+
+from .helpers import (
+    backup_path,
+    cleanup_docker,
+    create_minimal_compose_dir,
+    ensure_empty_dir,
+    latest_version_dir,
+    require_docker,
+    run,
+    unique,
+    write_databases_csv,
+)
+
+
+class TestE2EImagesNoBackupRequiredEarlySkip(unittest.TestCase):
+    @classmethod
+    def setUpClass(cls) -> None:
+        require_docker()
+
+        cls.prefix = unique("baudolo-e2e-early-skip-no-backup-required")
+        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
+
+        # --- Docker resources ---
+        cls.redis_container = f"{cls.prefix}-redis"
+        cls.ignored_volume = f"{cls.prefix}-redis-vol"
+        cls.normal_volume = f"{cls.prefix}-files-vol"
+
+        cls.containers = [cls.redis_container]
+        cls.volumes = [cls.ignored_volume, cls.normal_volume]
+
+        # Create volumes
+        run(["docker", "volume", "create", cls.ignored_volume])
+        run(["docker", "volume", "create", cls.normal_volume])
+
+        # Start redis container using the ignored volume
+        run(
+            [
+                "docker",
+                "run",
+                "-d",
+                "--name",
+                cls.redis_container,
+                "-v",
+                f"{cls.ignored_volume}:/data",
+                "redis:alpine",
+            ]
+        )
+
+        # Put deterministic content into the normal volume
+        run(
+            [
+                "docker",
+                "run",
+                "--rm",
+                "-v",
+                f"{cls.normal_volume}:/data",
+                "alpine:3.20",
+                "sh",
+                "-lc",
+                "mkdir -p /data && echo 'hello' > /data/hello.txt",
+            ]
+        )
+
+        # databases.csv required by CLI (can be empty)
+        cls.databases_csv = f"/tmp/{cls.prefix}/databases.csv"
+        write_databases_csv(cls.databases_csv, [])
+
+        # Run baudolo with images-no-backup-required redis
+        cmd = [
+            "baudolo",
+            "--compose-dir",
+            cls.compose_dir,
+            "--hard-compose-restart",
+            "mailu",
+            "--repo-name",
+            cls.repo_name,
+            "--databases-csv",
+            cls.databases_csv,
+            "--backups-dir",
+            cls.backups_dir,
+            "--database-containers",
+            "dummy-db",
+            "--images-no-stop-required",
+            "alpine",
+            "redis",
+            "postgres",
+            "mariadb",
+            "mysql",
+            "--images-no-backup-required",
+            "redis",
+        ]
+        cp = run(cmd, capture=True, check=True)
+        cls.stdout = cp.stdout or ""
+        cls.stderr = cp.stderr or ""
+
+        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_ignored_volume_has_no_backup_directory_at_all(self) -> None:
+        p = backup_path(
+            self.backups_dir,
+            self.repo_name,
+            self.version,
+            self.ignored_volume,
+        )
+        self.assertFalse(
+            p.exists(),
+            f"Expected NO backup directory to be created for ignored volume, but found: {p}",
+        )
+
+    def test_normal_volume_is_still_backed_up(self) -> None:
+        p = (
+            backup_path(
+                self.backups_dir,
+                self.repo_name,
+                self.version,
+                self.normal_volume,
+            )
+            / "files"
+            / "hello.txt"
+        )
+        self.assertTrue(p.is_file(), f"Expected backed up file at: {p}")

tests/e2e/test_e2e_mariadb_anonymous_preemption.py

@@ -0,0 +1,164 @@
+"""
+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 (
+    MARIADB_IMAGE,
+    MARIADB_DATA_DIR,
+    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}:{MARIADB_DATA_DIR}",
+                MARIADB_IMAGE,
+            ]
+        )
+
+        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_mariadb_full.py

@@ -0,0 +1,168 @@
+# tests/e2e/test_e2e_mariadb_full.py
+import unittest
+
+from .helpers import (
+    MARIADB_IMAGE,
+    MARIADB_DATA_DIR,
+    backup_run,
+    backup_path,
+    cleanup_docker,
+    create_minimal_compose_dir,
+    ensure_empty_dir,
+    latest_version_dir,
+    require_docker,
+    unique,
+    write_databases_csv,
+    run,
+    wait_for_mariadb,
+    wait_for_mariadb_sql,
+)
+
+
+class TestE2EMariaDBFull(unittest.TestCase):
+    @classmethod
+    def setUpClass(cls) -> None:
+        require_docker()
+        cls.prefix = unique("baudolo-e2e-mariadb-full")
+        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.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 = "test"
+        cls.db_password = "testpw"
+        cls.root_password = "rootpw"
+
+        run(["docker", "volume", "create", cls.db_volume])
+
+        # Start MariaDB with a dedicated TCP-capable user for tests.
+        run(
+            [
+                "docker",
+                "run",
+                "-d",
+                "--name",
+                cls.db_container,
+                "-e",
+                f"MARIADB_ROOT_PASSWORD={cls.root_password}",
+                "-e",
+                f"MARIADB_DATABASE={cls.db_name}",
+                "-e",
+                f"MARIADB_USER={cls.db_user}",
+                "-e",
+                f"MARIADB_PASSWORD={cls.db_password}",
+                "-v",
+                f"{cls.db_volume}:{MARIADB_DATA_DIR}",
+                MARIADB_IMAGE,
+            ]
+        )
+
+        # Liveness + actual SQL login readiness (TCP)
+        wait_for_mariadb(
+            cls.db_container, root_password=cls.root_password, timeout_s=90
+        )
+        wait_for_mariadb_sql(
+            cls.db_container, user=cls.db_user, password=cls.db_password, timeout_s=90
+        )
+
+        # Create table + data via the dedicated user (TCP)
+        run(
+            [
+                "docker",
+                "exec",
+                cls.db_container,
+                "sh",
+                "-lc",
+                f"mariadb -h 127.0.0.1 -u{cls.db_user} -p{cls.db_password} "
+                f'-e "CREATE TABLE {cls.db_name}.t (id INT PRIMARY KEY, v VARCHAR(50)); '
+                f"INSERT INTO {cls.db_name}.t VALUES (1,'ok');\"",
+            ]
+        )
+
+        cls.databases_csv = f"/tmp/{cls.prefix}/databases.csv"
+        # IMPORTANT: baudolo backup expects credentials for the DB dump.
+        write_databases_csv(
+            cls.databases_csv,
+            [(cls.db_container, cls.db_name, cls.db_user, cls.db_password)],
+        )
+
+        # Backup with file+dump
+        backup_run(
+            backups_dir=cls.backups_dir,
+            repo_name=cls.repo_name,
+            compose_dir=cls.compose_dir,
+            databases_csv=cls.databases_csv,
+            database_containers=[cls.db_container],
+            images_no_stop_required=["mariadb", "mysql", "alpine", "postgres"],
+        )
+
+        cls.hash, cls.version = latest_version_dir(cls.backups_dir, cls.repo_name)
+
+        # Wipe DB via the dedicated user (TCP)
+        run(
+            [
+                "docker",
+                "exec",
+                cls.db_container,
+                "sh",
+                "-lc",
+                f"mariadb -h 127.0.0.1 -u{cls.db_user} -p{cls.db_password} "
+                f'-e "DROP TABLE {cls.db_name}.t;"',
+            ]
+        )
+
+        # Restore DB (uses baudolo-restore which execs mysql/mariadb inside the container)
+        run(
+            [
+                "baudolo-restore",
+                "mariadb",
+                cls.db_volume,
+                cls.hash,
+                cls.version,
+                "--backups-dir",
+                cls.backups_dir,
+                "--repo-name",
+                cls.repo_name,
+                "--container",
+                cls.db_container,
+                "--db-name",
+                cls.db_name,
+                "--db-user",
+                cls.db_user,
+                "--db-password",
+                cls.db_password,
+                "--empty",
+            ]
+        )
+
+    @classmethod
+    def tearDownClass(cls) -> None:
+        cleanup_docker(containers=cls.containers, volumes=cls.volumes)
+
+    def test_dump_file_exists(self) -> None:
+        p = (
+            backup_path(self.backups_dir, self.repo_name, self.version, self.db_volume)
+            / "sql"
+            / f"{self.db_name}.backup.sql"
+        )
+        self.assertTrue(p.is_file(), f"Expected dump file at: {p}")
+
+    def test_data_restored(self) -> None:
+        p = run(
+            [
+                "docker",
+                "exec",
+                self.db_container,
+                "sh",
+                "-lc",
+                f"mariadb -h 127.0.0.1 -u{self.db_user} -p{self.db_password} "
+                f'-N -e "SELECT v FROM {self.db_name}.t WHERE id=1;"',
+            ]
+        )
+        self.assertEqual((p.stdout or "").strip(), "ok")

tests/e2e/test_e2e_mariadb_no_copy.py

@@ -0,0 +1,165 @@
+# tests/e2e/test_e2e_mariadb_no_copy.py
+import unittest
+
+from .helpers import (
+    MARIADB_IMAGE,
+    MARIADB_DATA_DIR,
+    backup_run,
+    backup_path,
+    cleanup_docker,
+    create_minimal_compose_dir,
+    ensure_empty_dir,
+    latest_version_dir,
+    require_docker,
+    unique,
+    write_databases_csv,
+    run,
+    wait_for_mariadb,
+    wait_for_mariadb_sql,
+)
+
+
+class TestE2EMariaDBNoCopy(unittest.TestCase):
+    @classmethod
+    def setUpClass(cls) -> None:
+        require_docker()
+        cls.prefix = unique("baudolo-e2e-mariadb-nocopy")
+        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.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 = "test"
+        cls.db_password = "testpw"
+        cls.root_password = "rootpw"
+
+        run(["docker", "volume", "create", cls.db_volume])
+
+        run(
+            [
+                "docker",
+                "run",
+                "-d",
+                "--name",
+                cls.db_container,
+                "-e",
+                f"MARIADB_ROOT_PASSWORD={cls.root_password}",
+                "-e",
+                f"MARIADB_DATABASE={cls.db_name}",
+                "-e",
+                f"MARIADB_USER={cls.db_user}",
+                "-e",
+                f"MARIADB_PASSWORD={cls.db_password}",
+                "-v",
+                f"{cls.db_volume}:{MARIADB_DATA_DIR}",
+                MARIADB_IMAGE,
+            ]
+        )
+
+        wait_for_mariadb(
+            cls.db_container, root_password=cls.root_password, timeout_s=90
+        )
+        wait_for_mariadb_sql(
+            cls.db_container, user=cls.db_user, password=cls.db_password, timeout_s=90
+        )
+
+        # Create table + data (TCP)
+        run(
+            [
+                "docker",
+                "exec",
+                cls.db_container,
+                "sh",
+                "-lc",
+                f"mariadb -h 127.0.0.1 -u{cls.db_user} -p{cls.db_password} "
+                f'-e "CREATE TABLE {cls.db_name}.t (id INT PRIMARY KEY, v VARCHAR(50)); '
+                f"INSERT INTO {cls.db_name}.t VALUES (1,'ok');\"",
+            ]
+        )
+
+        cls.databases_csv = f"/tmp/{cls.prefix}/databases.csv"
+        write_databases_csv(
+            cls.databases_csv,
+            [(cls.db_container, cls.db_name, cls.db_user, cls.db_password)],
+        )
+
+        # dump-only-sql => no files
+        backup_run(
+            backups_dir=cls.backups_dir,
+            repo_name=cls.repo_name,
+            compose_dir=cls.compose_dir,
+            databases_csv=cls.databases_csv,
+            database_containers=[cls.db_container],
+            images_no_stop_required=["mariadb", "mysql", "alpine", "postgres"],
+            dump_only_sql=True,
+        )
+
+        cls.hash, cls.version = latest_version_dir(cls.backups_dir, cls.repo_name)
+
+        # Wipe table (TCP)
+        run(
+            [
+                "docker",
+                "exec",
+                cls.db_container,
+                "sh",
+                "-lc",
+                f"mariadb -h 127.0.0.1 -u{cls.db_user} -p{cls.db_password} "
+                f'-e "DROP TABLE {cls.db_name}.t;"',
+            ]
+        )
+
+        # Restore DB
+        run(
+            [
+                "baudolo-restore",
+                "mariadb",
+                cls.db_volume,
+                cls.hash,
+                cls.version,
+                "--backups-dir",
+                cls.backups_dir,
+                "--repo-name",
+                cls.repo_name,
+                "--container",
+                cls.db_container,
+                "--db-name",
+                cls.db_name,
+                "--db-user",
+                cls.db_user,
+                "--db-password",
+                cls.db_password,
+                "--empty",
+            ]
+        )
+
+    @classmethod
+    def tearDownClass(cls) -> None:
+        cleanup_docker(containers=cls.containers, volumes=cls.volumes)
+
+    def test_files_backup_not_present(self) -> None:
+        p = (
+            backup_path(self.backups_dir, self.repo_name, self.version, self.db_volume)
+            / "files"
+        )
+        self.assertFalse(p.exists(), f"Did not expect files backup dir at: {p}")
+
+    def test_data_restored(self) -> None:
+        p = run(
+            [
+                "docker",
+                "exec",
+                self.db_container,
+                "sh",
+                "-lc",
+                f"mariadb -h 127.0.0.1 -u{self.db_user} -p{self.db_password} "
+                f'-N -e "SELECT v FROM {self.db_name}.t WHERE id=1;"',
+            ]
+        )
+        self.assertEqual((p.stdout or "").strip(), "ok")

tests/e2e/test_e2e_postgres_full.py

@@ -0,0 +1,145 @@
+# tests/e2e/test_e2e_postgres_full.py
+import unittest
+
+from .helpers import (
+    POSTGRES_IMAGE,
+    POSTGRES_DATA_DIR,
+    backup_run,
+    backup_path,
+    cleanup_docker,
+    create_minimal_compose_dir,
+    ensure_empty_dir,
+    latest_version_dir,
+    require_docker,
+    unique,
+    write_databases_csv,
+    run,
+    wait_for_postgres,
+)
+
+
+class TestE2EPostgresFull(unittest.TestCase):
+    @classmethod
+    def setUpClass(cls) -> None:
+        require_docker()
+        cls.prefix = unique("baudolo-e2e-postgres-full")
+        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.pg_container = f"{cls.prefix}-pg"
+        cls.pg_volume = f"{cls.prefix}-pg-vol"
+        cls.containers = [cls.pg_container]
+        cls.volumes = [cls.pg_volume]
+
+        run(["docker", "volume", "create", cls.pg_volume])
+
+        run(
+            [
+                "docker",
+                "run",
+                "-d",
+                "--name",
+                cls.pg_container,
+                "-e",
+                "POSTGRES_PASSWORD=pgpw",
+                "-e",
+                "POSTGRES_DB=appdb",
+                "-e",
+                "POSTGRES_USER=postgres",
+                "-v",
+                f"{cls.pg_volume}:{POSTGRES_DATA_DIR}",
+                POSTGRES_IMAGE,
+            ]
+        )
+        wait_for_postgres(cls.pg_container, user="postgres", timeout_s=90)
+
+        # Create a table + data
+        run(
+            [
+                "docker",
+                "exec",
+                cls.pg_container,
+                "sh",
+                "-lc",
+                "psql -U postgres -d appdb -c \"CREATE TABLE t (id int primary key, v text); INSERT INTO t VALUES (1,'ok');\"",
+            ]
+        )
+
+        cls.databases_csv = f"/tmp/{cls.prefix}/databases.csv"
+        write_databases_csv(
+            cls.databases_csv, [(cls.pg_container, "appdb", "postgres", "pgpw")]
+        )
+
+        backup_run(
+            backups_dir=cls.backups_dir,
+            repo_name=cls.repo_name,
+            compose_dir=cls.compose_dir,
+            databases_csv=cls.databases_csv,
+            database_containers=[cls.pg_container],
+            images_no_stop_required=["postgres", "mariadb", "mysql", "alpine"],
+        )
+
+        cls.hash, cls.version = latest_version_dir(cls.backups_dir, cls.repo_name)
+
+        # Wipe schema
+        run(
+            [
+                "docker",
+                "exec",
+                cls.pg_container,
+                "sh",
+                "-lc",
+                'psql -U postgres -d appdb -c "DROP TABLE t;"',
+            ]
+        )
+
+        # Restore
+        run(
+            [
+                "baudolo-restore",
+                "postgres",
+                cls.pg_volume,
+                cls.hash,
+                cls.version,
+                "--backups-dir",
+                cls.backups_dir,
+                "--repo-name",
+                cls.repo_name,
+                "--container",
+                cls.pg_container,
+                "--db-name",
+                "appdb",
+                "--db-user",
+                "postgres",
+                "--db-password",
+                "pgpw",
+                "--empty",
+            ]
+        )
+
+    @classmethod
+    def tearDownClass(cls) -> None:
+        cleanup_docker(containers=cls.containers, volumes=cls.volumes)
+
+    def test_dump_file_exists(self) -> None:
+        p = (
+            backup_path(self.backups_dir, self.repo_name, self.version, self.pg_volume)
+            / "sql"
+            / "appdb.backup.sql"
+        )
+        self.assertTrue(p.is_file(), f"Expected dump file at: {p}")
+
+    def test_data_restored(self) -> None:
+        p = run(
+            [
+                "docker",
+                "exec",
+                self.pg_container,
+                "sh",
+                "-lc",
+                'psql -U postgres -d appdb -t -c "SELECT v FROM t WHERE id=1;"',
+            ]
+        )
+        self.assertEqual((p.stdout or "").strip(), "ok")

tests/e2e/test_e2e_postgres_no_copy.py

@@ -0,0 +1,141 @@
+# tests/e2e/test_e2e_postgres_no_copy.py
+import unittest
+
+from .helpers import (
+    POSTGRES_IMAGE,
+    POSTGRES_DATA_DIR,
+    backup_run,
+    backup_path,
+    cleanup_docker,
+    create_minimal_compose_dir,
+    ensure_empty_dir,
+    latest_version_dir,
+    require_docker,
+    unique,
+    write_databases_csv,
+    run,
+    wait_for_postgres,
+)
+
+
+class TestE2EPostgresNoCopy(unittest.TestCase):
+    @classmethod
+    def setUpClass(cls) -> None:
+        require_docker()
+        cls.prefix = unique("baudolo-e2e-postgres-nocopy")
+        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.pg_container = f"{cls.prefix}-pg"
+        cls.pg_volume = f"{cls.prefix}-pg-vol"
+        cls.containers = [cls.pg_container]
+        cls.volumes = [cls.pg_volume]
+
+        run(["docker", "volume", "create", cls.pg_volume])
+        run(
+            [
+                "docker",
+                "run",
+                "-d",
+                "--name",
+                cls.pg_container,
+                "-e",
+                "POSTGRES_PASSWORD=pgpw",
+                "-e",
+                "POSTGRES_DB=appdb",
+                "-e",
+                "POSTGRES_USER=postgres",
+                "-v",
+                f"{cls.pg_volume}:{POSTGRES_DATA_DIR}",
+                POSTGRES_IMAGE,
+            ]
+        )
+        wait_for_postgres(cls.pg_container, user="postgres", timeout_s=90)
+
+        run(
+            [
+                "docker",
+                "exec",
+                cls.pg_container,
+                "sh",
+                "-lc",
+                "psql -U postgres -d appdb -c \"CREATE TABLE t (id int primary key, v text); INSERT INTO t VALUES (1,'ok');\"",
+            ]
+        )
+
+        cls.databases_csv = f"/tmp/{cls.prefix}/databases.csv"
+        write_databases_csv(
+            cls.databases_csv, [(cls.pg_container, "appdb", "postgres", "pgpw")]
+        )
+
+        backup_run(
+            backups_dir=cls.backups_dir,
+            repo_name=cls.repo_name,
+            compose_dir=cls.compose_dir,
+            databases_csv=cls.databases_csv,
+            database_containers=[cls.pg_container],
+            images_no_stop_required=["postgres", "mariadb", "mysql", "alpine"],
+            dump_only_sql=True,
+        )
+
+        cls.hash, cls.version = latest_version_dir(cls.backups_dir, cls.repo_name)
+
+        run(
+            [
+                "docker",
+                "exec",
+                cls.pg_container,
+                "sh",
+                "-lc",
+                'psql -U postgres -d appdb -c "DROP TABLE t;"',
+            ]
+        )
+
+        run(
+            [
+                "baudolo-restore",
+                "postgres",
+                cls.pg_volume,
+                cls.hash,
+                cls.version,
+                "--backups-dir",
+                cls.backups_dir,
+                "--repo-name",
+                cls.repo_name,
+                "--container",
+                cls.pg_container,
+                "--db-name",
+                "appdb",
+                "--db-user",
+                "postgres",
+                "--db-password",
+                "pgpw",
+                "--empty",
+            ]
+        )
+
+    @classmethod
+    def tearDownClass(cls) -> None:
+        cleanup_docker(containers=cls.containers, volumes=cls.volumes)
+
+    def test_files_backup_not_present(self) -> None:
+        p = (
+            backup_path(self.backups_dir, self.repo_name, self.version, self.pg_volume)
+            / "files"
+        )
+        self.assertFalse(p.exists(), f"Did not expect files backup dir at: {p}")
+
+    def test_data_restored(self) -> None:
+        p = run(
+            [
+                "docker",
+                "exec",
+                self.pg_container,
+                "sh",
+                "-lc",
+                'psql -U postgres -d appdb -t -c "SELECT v FROM t WHERE id=1;"',
+            ]
+        )
+        self.assertEqual((p.stdout or "").strip(), "ok")

tests/e2e/test_e2e_seed_star_and_db_entries_backup_postgres.py

@@ -0,0 +1,234 @@
+import unittest
+
+from .helpers import (
+    POSTGRES_IMAGE,
+    POSTGRES_DATA_DIR,
+    backup_path,
+    cleanup_docker,
+    create_minimal_compose_dir,
+    ensure_empty_dir,
+    latest_version_dir,
+    require_docker,
+    run,
+    unique,
+    wait_for_postgres,
+)
+
+
+class TestE2ESeedStarAndDbEntriesBackupPostgres(unittest.TestCase):
+    @classmethod
+    def setUpClass(cls) -> None:
+        require_docker()
+
+        cls.prefix = unique("baudolo-e2e-seed-star-and-db")
+        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
+
+        # --- Volumes ---
+        cls.db_volume = f"{cls.prefix}-vol-db"
+        cls.files_volume = f"{cls.prefix}-vol-files"
+        cls.volumes = [cls.db_volume, cls.files_volume]
+
+        run(["docker", "volume", "create", cls.db_volume])
+        run(["docker", "volume", "create", cls.files_volume])
+
+        # Put a marker into the non-db volume
+        cls.marker = "hello-non-db-seed-star"
+        run(
+            [
+                "docker",
+                "run",
+                "--rm",
+                "-v",
+                f"{cls.files_volume}:/data",
+                "alpine:3.20",
+                "sh",
+                "-lc",
+                f"echo '{cls.marker}' > /data/hello.txt",
+            ]
+        )
+
+        # --- Start Postgres container using the DB volume ---
+        cls.pg_container = f"{cls.prefix}-pg"
+        cls.containers = [cls.pg_container]
+
+        cls.pg_password = "postgres"
+        cls.pg_user = "postgres"
+
+        run(
+            [
+                "docker",
+                "run",
+                "-d",
+                "--name",
+                cls.pg_container,
+                "-e",
+                f"POSTGRES_PASSWORD={cls.pg_password}",
+                "-v",
+                f"{cls.db_volume}:{POSTGRES_DATA_DIR}",
+                POSTGRES_IMAGE,
+            ]
+        )
+        wait_for_postgres(cls.pg_container, user="postgres", timeout_s=90)
+
+        # Create two DBs and deterministic content, so pg_dumpall is meaningful
+        cls.pg_db1 = "testdb1"
+        cls.pg_db2 = "testdb2"
+
+        run(
+            [
+                "docker",
+                "exec",
+                cls.pg_container,
+                "sh",
+                "-lc",
+                (
+                    f'psql -U {cls.pg_user} -c "CREATE DATABASE {cls.pg_db1};" || true; '
+                    f'psql -U {cls.pg_user} -c "CREATE DATABASE {cls.pg_db2};" || true; '
+                ),
+            ],
+            check=True,
+        )
+
+        run(
+            [
+                "docker",
+                "exec",
+                cls.pg_container,
+                "sh",
+                "-lc",
+                (
+                    f"psql -U {cls.pg_user} -d {cls.pg_db1} -c "
+                    '"CREATE TABLE IF NOT EXISTS t (id INT PRIMARY KEY, v TEXT);'
+                    "INSERT INTO t(id,v) VALUES (1,'hello-db1') "
+                    'ON CONFLICT (id) DO UPDATE SET v=EXCLUDED.v;"'
+                ),
+            ],
+            check=True,
+        )
+        run(
+            [
+                "docker",
+                "exec",
+                cls.pg_container,
+                "sh",
+                "-lc",
+                (
+                    f"psql -U {cls.pg_user} -d {cls.pg_db2} -c "
+                    '"CREATE TABLE IF NOT EXISTS t (id INT PRIMARY KEY, v TEXT);'
+                    "INSERT INTO t(id,v) VALUES (1,'hello-db2') "
+                    'ON CONFLICT (id) DO UPDATE SET v=EXCLUDED.v;"'
+                ),
+            ],
+            check=True,
+        )
+
+        # --- Seed databases.csv using CLI (star + concrete db) ---
+        cls.databases_csv = f"/tmp/{cls.prefix}/databases.csv"
+
+        # IMPORTANT: because we pass --database-containers <container>,
+        # get_instance() will use the container name as instance key.
+        instance = cls.pg_container
+
+        # Seed star entry (pg_dumpall)
+        run(
+            [
+                "baudolo-seed",
+                cls.databases_csv,
+                instance,
+                "*",
+                cls.pg_user,
+                cls.pg_password,
+            ]
+        )
+
+        # Seed concrete DB entry (pg_dump)
+        run(
+            [
+                "baudolo-seed",
+                cls.databases_csv,
+                instance,
+                cls.pg_db1,
+                cls.pg_user,
+                cls.pg_password,
+            ]
+        )
+
+        # --- Run baudolo with dump-only-sql ---
+        cmd = [
+            "baudolo",
+            "--compose-dir",
+            cls.compose_dir,
+            "--databases-csv",
+            cls.databases_csv,
+            "--database-containers",
+            cls.pg_container,
+            "--images-no-stop-required",
+            "alpine",
+            "postgres",
+            "mariadb",
+            "mysql",
+            "--dump-only-sql",
+            "--backups-dir",
+            cls.backups_dir,
+            "--repo-name",
+            cls.repo_name,
+        ]
+        cp = run(cmd, capture=True, check=True)
+        cls.stdout = cp.stdout or ""
+        cls.stderr = cp.stderr or ""
+
+        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_db_volume_has_cluster_dump_and_concrete_db_dump_and_no_files(self) -> None:
+        base = backup_path(
+            self.backups_dir, self.repo_name, self.version, self.db_volume
+        )
+        sql_dir = base / "sql"
+        files_dir = base / "files"
+
+        self.assertTrue(sql_dir.exists(), f"Expected sql dir at: {sql_dir}")
+        self.assertFalse(
+            files_dir.exists(),
+            f"Did not expect files dir for DB volume when dump-only-sql succeeded: {files_dir}",
+        )
+
+        # Cluster dump file produced by '*' entry
+        cluster = sql_dir / f"{self.pg_container}.cluster.backup.sql"
+        self.assertTrue(cluster.is_file(), f"Expected cluster dump file at: {cluster}")
+
+        # Concrete DB dump produced by normal entry
+        db1 = sql_dir / f"{self.pg_db1}.backup.sql"
+        self.assertTrue(db1.is_file(), f"Expected db dump file at: {db1}")
+
+        # Basic sanity: cluster dump usually contains CREATE DATABASE statements
+        txt = cluster.read_text(encoding="utf-8", errors="ignore")
+        self.assertIn(
+            "CREATE DATABASE",
+            txt,
+            "Expected cluster dump to contain CREATE DATABASE statements",
+        )
+
+    def test_non_db_volume_still_has_files_backup(self) -> None:
+        base = backup_path(
+            self.backups_dir, self.repo_name, self.version, self.files_volume
+        )
+        files_dir = base / "files"
+
+        self.assertTrue(
+            files_dir.exists(), f"Expected files dir for non-DB volume at: {files_dir}"
+        )
+
+        marker = files_dir / "hello.txt"
+        self.assertTrue(marker.is_file(), f"Expected marker file at: {marker}")
+        self.assertEqual(
+            marker.read_text(encoding="utf-8").strip(),
+            self.marker,
+        )

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/integration/test_seed_integration.py

@@ -0,0 +1,213 @@
+import csv
+import subprocess
+import sys
+import tempfile
+import unittest
+from pathlib import Path
+
+
+def run_seed(
+    csv_path: Path, instance: str, database: str, username: str, password: str
+) -> subprocess.CompletedProcess:
+    """
+    Run the real CLI module (E2E-style) using subprocess.
+
+    Seed contract (current):
+    - database must be "*" or a valid name (non-empty, matches allowed charset)
+    - password is required
+    - entry is keyed by (instance, database); username/password get updated
+    """
+    cp = subprocess.run(
+        [
+            sys.executable,
+            "-m",
+            "baudolo.seed",
+            str(csv_path),
+            instance,
+            database,
+            username,
+            password,
+        ],
+        text=True,
+        capture_output=True,
+        check=False,
+    )
+    if cp.returncode != 0:
+        raise AssertionError(
+            "seed command failed unexpectedly.\n"
+            f"returncode: {cp.returncode}\n"
+            f"stdout:\n{cp.stdout}\n"
+            f"stderr:\n{cp.stderr}\n"
+        )
+    return cp
+
+
+def run_seed_expect_fail(
+    csv_path: Path, instance: str, database: str, username: str, password: str
+) -> subprocess.CompletedProcess:
+    """
+    Same as run_seed, but expects non-zero exit. Returns CompletedProcess for inspection.
+    """
+    return subprocess.run(
+        [
+            sys.executable,
+            "-m",
+            "baudolo.seed",
+            str(csv_path),
+            instance,
+            database,
+            username,
+            password,
+        ],
+        text=True,
+        capture_output=True,
+        check=False,
+    )
+
+
+def read_csv_semicolon(path: Path) -> list[dict]:
+    with path.open("r", encoding="utf-8", newline="") as f:
+        reader = csv.DictReader(f, delimiter=";")
+        return list(reader)
+
+
+def read_text(path: Path) -> str:
+    return path.read_text(encoding="utf-8")
+
+
+class TestSeedIntegration(unittest.TestCase):
+    def test_creates_file_and_adds_entry_when_missing(self) -> None:
+        with tempfile.TemporaryDirectory() as td:
+            p = Path(td) / "databases.csv"
+            self.assertFalse(p.exists())
+
+            cp = run_seed(p, "docker.test", "appdb", "alice", "secret")
+
+            self.assertEqual(cp.returncode, 0)
+            self.assertTrue(p.exists())
+
+            rows = read_csv_semicolon(p)
+            self.assertEqual(len(rows), 1)
+            self.assertEqual(rows[0]["instance"], "docker.test")
+            self.assertEqual(rows[0]["database"], "appdb")
+            self.assertEqual(rows[0]["username"], "alice")
+            self.assertEqual(rows[0]["password"], "secret")
+
+    def test_replaces_existing_entry_same_instance_and_database_updates_username_and_password(
+        self,
+    ) -> None:
+        """
+        Replacement semantics:
+        - Key is (instance, database)
+        - username/password are updated in-place
+        """
+        with tempfile.TemporaryDirectory() as td:
+            p = Path(td) / "databases.csv"
+
+            run_seed(p, "docker.test", "appdb", "alice", "oldpw")
+            rows = read_csv_semicolon(p)
+            self.assertEqual(len(rows), 1)
+            self.assertEqual(rows[0]["username"], "alice")
+            self.assertEqual(rows[0]["password"], "oldpw")
+
+            run_seed(p, "docker.test", "appdb", "bob", "newpw")
+            rows = read_csv_semicolon(p)
+
+            self.assertEqual(len(rows), 1, "Expected replacement, not a duplicate row")
+            self.assertEqual(rows[0]["instance"], "docker.test")
+            self.assertEqual(rows[0]["database"], "appdb")
+            self.assertEqual(rows[0]["username"], "bob")
+            self.assertEqual(rows[0]["password"], "newpw")
+
+    def test_allows_star_database_for_dump_all(self) -> None:
+        with tempfile.TemporaryDirectory() as td:
+            p = Path(td) / "databases.csv"
+
+            cp = run_seed(p, "bigbluebutton", "*", "postgres", "pw")
+            self.assertEqual(cp.returncode, 0)
+
+            rows = read_csv_semicolon(p)
+            self.assertEqual(len(rows), 1)
+            self.assertEqual(rows[0]["instance"], "bigbluebutton")
+            self.assertEqual(rows[0]["database"], "*")
+            self.assertEqual(rows[0]["username"], "postgres")
+            self.assertEqual(rows[0]["password"], "pw")
+
+    def test_replaces_existing_star_entry(self) -> None:
+        with tempfile.TemporaryDirectory() as td:
+            p = Path(td) / "databases.csv"
+
+            run_seed(p, "bigbluebutton", "*", "postgres", "pw1")
+            run_seed(p, "bigbluebutton", "*", "postgres", "pw2")
+
+            rows = read_csv_semicolon(p)
+            self.assertEqual(len(rows), 1)
+            self.assertEqual(rows[0]["database"], "*")
+            self.assertEqual(rows[0]["password"], "pw2")
+
+    def test_rejects_empty_database_value(self) -> None:
+        with tempfile.TemporaryDirectory() as td:
+            p = Path(td) / "databases.csv"
+
+            cp = run_seed_expect_fail(p, "docker.test", "", "alice", "pw")
+            self.assertNotEqual(cp.returncode, 0)
+
+            combined = ((cp.stdout or "") + "\n" + (cp.stderr or "")).lower()
+            self.assertIn("error:", combined)
+            self.assertIn("database", combined)
+            self.assertIn("not empty", combined)
+
+            self.assertFalse(p.exists(), "Should not create file on invalid input")
+
+    def test_rejects_invalid_database_name_characters(self) -> None:
+        with tempfile.TemporaryDirectory() as td:
+            p = Path(td) / "databases.csv"
+
+            cp = run_seed_expect_fail(p, "docker.test", "app db", "alice", "pw")
+            self.assertNotEqual(cp.returncode, 0)
+
+            combined = ((cp.stdout or "") + "\n" + (cp.stderr or "")).lower()
+            self.assertIn("error:", combined)
+            self.assertIn("invalid database name", combined)
+
+            self.assertFalse(p.exists(), "Should not create file on invalid input")
+
+    def test_rejects_nan_database_name(self) -> None:
+        with tempfile.TemporaryDirectory() as td:
+            p = Path(td) / "databases.csv"
+
+            cp = run_seed_expect_fail(p, "docker.test", "nan", "alice", "pw")
+            self.assertNotEqual(cp.returncode, 0)
+
+            combined = ((cp.stdout or "") + "\n" + (cp.stderr or "")).lower()
+            self.assertIn("error:", combined)
+            self.assertIn("must not be 'nan'", combined)
+
+            self.assertFalse(p.exists(), "Should not create file on invalid input")
+
+    def test_accepts_hyphen_and_underscore_database_names(self) -> None:
+        with tempfile.TemporaryDirectory() as td:
+            p = Path(td) / "databases.csv"
+
+            run_seed(p, "docker.test", "my_db-1", "alice", "pw")
+
+            rows = read_csv_semicolon(p)
+            self.assertEqual(len(rows), 1)
+            self.assertEqual(rows[0]["database"], "my_db-1")
+
+    def test_file_is_semicolon_delimited_and_has_header(self) -> None:
+        with tempfile.TemporaryDirectory() as td:
+            p = Path(td) / "databases.csv"
+
+            run_seed(p, "docker.test", "appdb", "alice", "pw")
+
+            txt = read_text(p)
+            self.assertTrue(
+                txt.startswith("instance;database;username;password"),
+                f"Unexpected header / delimiter in file:\n{txt}",
+            )
+            self.assertIn(";", txt)
+
+
+if __name__ == "__main__":
+    unittest.main()

tests/unit/backup/test_app_databases_csv.py

@@ -0,0 +1,77 @@
+import io
+import os
+import tempfile
+import unittest
+from contextlib import redirect_stderr
+
+import pandas as pd
+
+# Adjust if your package name/import path differs.
+from baudolo.backup.app import _load_databases_df
+
+
+EXPECTED_COLUMNS = ["instance", "database", "username", "password"]
+
+
+class TestLoadDatabasesDf(unittest.TestCase):
+    def test_missing_csv_is_handled_with_warning_and_empty_df(self) -> None:
+        with tempfile.TemporaryDirectory() as td:
+            missing_path = os.path.join(td, "does-not-exist.csv")
+
+            buf = io.StringIO()
+            with redirect_stderr(buf):
+                df = _load_databases_df(missing_path)
+
+            stderr = buf.getvalue()
+            self.assertIn("WARNING:", stderr)
+            self.assertIn("databases.csv not found", stderr)
+
+            self.assertIsInstance(df, pd.DataFrame)
+            self.assertListEqual(list(df.columns), EXPECTED_COLUMNS)
+            self.assertTrue(df.empty)
+
+    def test_empty_csv_is_handled_with_warning_and_empty_df(self) -> None:
+        with tempfile.TemporaryDirectory() as td:
+            empty_path = os.path.join(td, "databases.csv")
+            # Create an empty file (0 bytes)
+            with open(empty_path, "w", encoding="utf-8") as f:
+                f.write("")
+
+            buf = io.StringIO()
+            with redirect_stderr(buf):
+                df = _load_databases_df(empty_path)
+
+            stderr = buf.getvalue()
+            self.assertIn("WARNING:", stderr)
+            self.assertIn("exists but is empty", stderr)
+
+            self.assertIsInstance(df, pd.DataFrame)
+            self.assertListEqual(list(df.columns), EXPECTED_COLUMNS)
+            self.assertTrue(df.empty)
+
+    def test_valid_csv_loads_without_warning(self) -> None:
+        with tempfile.TemporaryDirectory() as td:
+            csv_path = os.path.join(td, "databases.csv")
+
+            content = "instance;database;username;password\nmyapp;*;dbuser;secret\n"
+            with open(csv_path, "w", encoding="utf-8") as f:
+                f.write(content)
+
+            buf = io.StringIO()
+            with redirect_stderr(buf):
+                df = _load_databases_df(csv_path)
+
+            stderr = buf.getvalue()
+            self.assertEqual(stderr, "")  # no warning expected
+
+            self.assertIsInstance(df, pd.DataFrame)
+            self.assertListEqual(list(df.columns), EXPECTED_COLUMNS)
+            self.assertEqual(len(df), 1)
+            self.assertEqual(df.loc[0, "instance"], "myapp")
+            self.assertEqual(df.loc[0, "database"], "*")
+            self.assertEqual(df.loc[0, "username"], "dbuser")
+            self.assertEqual(df.loc[0, "password"], "secret")
+
+
+if __name__ == "__main__":
+    unittest.main()

tests/unit/backup/test_compose.py

@@ -0,0 +1,311 @@
+from __future__ import annotations
+
+import shutil
+import tempfile
+import unittest
+from pathlib import Path
+from typing import List
+from unittest.mock import patch
+
+
+def _touch(p: Path) -> None:
+    p.parent.mkdir(parents=True, exist_ok=True)
+
+    # If the path already exists as a directory (e.g. ".env" created by ".env/env"),
+    # remove it so we can create a file with the same name.
+    if p.exists() and p.is_dir():
+        shutil.rmtree(p)
+
+    p.write_text("x", encoding="utf-8")
+
+
+def _setup_compose_dir(
+    tmp_path: Path,
+    name: str = "mailu",
+    *,
+    compose_name: str = "docker-compose.yml",
+    with_override: bool = False,
+    with_ca_override: bool = False,
+    env_layout: str | None = None,  # None | ".env" | ".env/env"
+) -> Path:
+    d = tmp_path / name
+    d.mkdir(parents=True, exist_ok=True)
+
+    _touch(d / compose_name)
+
+    if with_override:
+        _touch(d / "docker-compose.override.yml")
+
+    if with_ca_override:
+        _touch(d / "docker-compose.ca.override.yml")
+
+    if env_layout == ".env":
+        _touch(d / ".env")
+    elif env_layout == ".env/env":
+        _touch(d / ".env" / "env")
+
+    return d
+
+
+class TestCompose(unittest.TestCase):
+    @classmethod
+    def setUpClass(cls) -> None:
+        from baudolo.backup import compose as mod
+
+        cls.compose_mod = mod
+
+    def test_find_compose_file_supports_all_valid_names_case_insensitive(self) -> None:
+        with tempfile.TemporaryDirectory() as td:
+            tmp_path = Path(td)
+
+            variants = [
+                "compose.yml",
+                "compose.yaml",
+                "docker-compose.yml",
+                "docker-compose.yaml",
+                "docker-compose.yAml",
+            ]
+
+            for i, name in enumerate(variants):
+                d = _setup_compose_dir(
+                    tmp_path,
+                    name=f"project{i}",
+                    compose_name=name,
+                )
+                found = self.compose_mod._find_compose_file(str(d))
+                self.assertIsNotNone(found)
+                self.assertEqual(found.name, name)
+
+    def test_find_compose_file_returns_none_when_missing(self) -> None:
+        with tempfile.TemporaryDirectory() as td:
+            tmp_path = Path(td)
+            d = tmp_path / "empty"
+            d.mkdir(parents=True, exist_ok=True)
+
+            found = self.compose_mod._find_compose_file(str(d))
+            self.assertIsNone(found)
+
+    def test_build_cmd_uses_wrapper_when_present(self) -> None:
+        with tempfile.TemporaryDirectory() as td:
+            tmp_path = Path(td)
+            d = _setup_compose_dir(
+                tmp_path,
+                with_override=True,
+                with_ca_override=True,
+                env_layout=".env",
+            )
+
+            def fake_which(name: str):
+                if name == "compose":
+                    return "/usr/local/bin/compose"
+                return None
+
+            with patch.object(self.compose_mod.shutil, "which", fake_which):
+                cmd = self.compose_mod._build_compose_cmd(str(d), ["up", "-d"])
+
+            self.assertEqual(
+                cmd,
+                [
+                    "/usr/local/bin/compose",
+                    "--chdir",
+                    str(d.resolve()),
+                    "--",
+                    "up",
+                    "-d",
+                ],
+            )
+
+    def test_build_cmd_fallback_uses_plain_docker_compose_chdir(self) -> None:
+        with tempfile.TemporaryDirectory() as td:
+            tmp_path = Path(td)
+            d = _setup_compose_dir(
+                tmp_path,
+                with_override=True,
+                with_ca_override=True,
+                env_layout=".env",
+            )
+
+            def fake_which(name: str):
+                if name == "compose":
+                    return None
+                if name == "docker":
+                    return "/usr/bin/docker"
+                return None
+
+            with patch.object(self.compose_mod.shutil, "which", fake_which):
+                cmd = self.compose_mod._build_compose_cmd(
+                    str(d), ["up", "-d", "--force-recreate"]
+                )
+
+            expected: List[str] = [
+                "/usr/bin/docker",
+                "compose",
+                "--chdir",
+                str(d.resolve()),
+                "up",
+                "-d",
+                "--force-recreate",
+            ]
+            self.assertEqual(cmd, expected)
+
+    def test_hard_restart_calls_run_twice_with_correct_cmds_wrapper(self) -> None:
+        with tempfile.TemporaryDirectory() as td:
+            tmp_path = Path(td)
+            d = _setup_compose_dir(tmp_path, name="mailu", env_layout=".env")
+
+            def fake_which(name: str):
+                if name == "compose":
+                    return "/usr/local/bin/compose"
+                return None
+
+            with patch.object(self.compose_mod.shutil, "which", fake_which):
+                calls = []
+
+                def fake_run(cmd, check: bool):
+                    calls.append((cmd, check))
+                    return 0
+
+                with patch.object(self.compose_mod.subprocess, "run", fake_run):
+                    self.compose_mod.hard_restart_docker_services(str(d))
+
+            self.assertEqual(
+                calls,
+                [
+                    (
+                        [
+                            "/usr/local/bin/compose",
+                            "--chdir",
+                            str(d.resolve()),
+                            "--",
+                            "down",
+                        ],
+                        True,
+                    ),
+                    (
+                        [
+                            "/usr/local/bin/compose",
+                            "--chdir",
+                            str(d.resolve()),
+                            "--",
+                            "up",
+                            "-d",
+                        ],
+                        True,
+                    ),
+                ],
+            )
+
+    def test_hard_restart_calls_run_twice_with_correct_cmds_fallback(self) -> None:
+        with tempfile.TemporaryDirectory() as td:
+            tmp_path = Path(td)
+            d = _setup_compose_dir(
+                tmp_path,
+                name="mailu",
+                with_override=True,
+                with_ca_override=True,
+                env_layout=".env/env",
+            )
+
+            def fake_which(name: str):
+                if name == "compose":
+                    return None
+                if name == "docker":
+                    return "/usr/bin/docker"
+                return None
+
+            with patch.object(self.compose_mod.shutil, "which", fake_which):
+                calls = []
+
+                def fake_run(cmd, check: bool):
+                    calls.append((cmd, check))
+                    return 0
+
+                with patch.object(self.compose_mod.subprocess, "run", fake_run):
+                    self.compose_mod.hard_restart_docker_services(str(d))
+
+            self.assertEqual(
+                calls,
+                [
+                    (
+                        [
+                            "/usr/bin/docker",
+                            "compose",
+                            "--chdir",
+                            str(d.resolve()),
+                            "down",
+                        ],
+                        True,
+                    ),
+                    (
+                        [
+                            "/usr/bin/docker",
+                            "compose",
+                            "--chdir",
+                            str(d.resolve()),
+                            "up",
+                            "-d",
+                        ],
+                        True,
+                    ),
+                ],
+            )
+
+
+class HardRestartArgTests(unittest.TestCase):
+    """The hard-restart list defaults to empty (no compose down/up); callers
+    opt in per dir, e.g. compose hosts pass 'mailu' while swarm hosts, where
+    the dir is a stack whose overlay network collides with compose up, pass
+    nothing."""
+
+    def _parse(self, extra: List[str]):
+        import sys
+
+        from baudolo.backup import cli
+
+        argv = [
+            "baudolo",
+            "--compose-dir",
+            "/tmp",
+            "--backups-dir",
+            "/tmp/backup",
+            "--database-containers",
+            "postgres",
+            "--images-no-stop-required",
+            "redis",
+            *extra,
+        ]
+        with patch.object(sys, "argv", argv):
+            return cli.parse_args()
+
+    def test_default_is_empty(self) -> None:
+        args = self._parse([])
+        self.assertEqual(args.hard_compose_restart, [])
+
+    def test_empty_flag_stays_empty(self) -> None:
+        args = self._parse(["--hard-compose-restart"])
+        self.assertEqual(args.hard_compose_restart, [])
+
+    def test_explicit_names_preserved(self) -> None:
+        args = self._parse(["--hard-compose-restart", "mailu", "foo"])
+        self.assertEqual(args.hard_compose_restart, ["mailu", "foo"])
+
+    def test_backups_dir_is_required(self) -> None:
+        import sys
+
+        from baudolo.backup import cli
+
+        argv = [
+            "baudolo",
+            "--compose-dir",
+            "/tmp",
+            "--database-containers",
+            "postgres",
+            "--images-no-stop-required",
+            "redis",
+        ]
+        with patch.object(sys, "argv", argv), self.assertRaises(SystemExit):
+            cli.parse_args()
+
+
+if __name__ == "__main__":
+    unittest.main(verbosity=2)

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_empty_drop.py

@@ -0,0 +1,43 @@
+"""The --empty pre-clean drop must cover every object class a dump can
+re-CREATE ahead of tables; a missed class aborts the replay under
+ON_ERROR_STOP (OpenProject's ICU collation public.versions_name did)."""
+
+import tempfile
+import unittest
+from pathlib import Path
+from unittest import mock
+
+from baudolo.restore.db import postgres
+
+
+class TestPostgresEmptyDrop(unittest.TestCase):
+    def _drop_sql(self) -> str:
+        with tempfile.NamedTemporaryFile(suffix=".sql") as fh:
+            Path(fh.name).write_bytes(b"SELECT 1;\n")
+            with mock.patch.object(postgres, "docker_exec") as run:
+                postgres.restore_postgres_sql(
+                    container="c",
+                    db_name="db",
+                    user="u",
+                    password="p",
+                    sql_path=fh.name,
+                    empty=True,
+                )
+        first_call = run.call_args_list[0]
+        return first_call.kwargs["stdin"].decode()
+
+    def test_drop_covers_collations(self) -> None:
+        sql = self._drop_sql()
+        self.assertIn("pg_collation", sql)
+        self.assertIn("'COLLATION' AS type", sql)
+        self.assertIn("pg_get_userbyid(col.collowner) = current_user", sql)
+
+    def test_drop_still_covers_the_other_classes(self) -> None:
+        sql = self._drop_sql()
+        for marker in ("pg_class", "pg_proc", "'SEQUENCE' AS type", "'TYPE' AS type"):
+            self.assertIn(marker, sql)
+        self.assertIn("DROP %s IF EXISTS public.%I CASCADE", sql)
+
+
+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/seed/test_main.py

@@ -0,0 +1,215 @@
+from __future__ import annotations
+
+import unittest
+from unittest.mock import MagicMock, patch
+
+import pandas as pd
+from pandas.errors import EmptyDataError
+
+import baudolo.seed.__main__ as seed_main
+
+
+class TestSeedMain(unittest.TestCase):
+    @patch("baudolo.seed.__main__.pd.DataFrame")
+    def test_empty_df_creates_expected_columns(self, df_ctor: MagicMock) -> None:
+        seed_main._empty_df()
+        df_ctor.assert_called_once_with(
+            columns=["instance", "database", "username", "password"]
+        )
+
+    def test_validate_database_value_rejects_empty(self) -> None:
+        with self.assertRaises(ValueError):
+            seed_main._validate_database_value("", instance="x")
+
+    def test_validate_database_value_accepts_star(self) -> None:
+        self.assertEqual(seed_main._validate_database_value("*", instance="x"), "*")
+
+    def test_validate_database_value_rejects_nan(self) -> None:
+        with self.assertRaises(ValueError):
+            seed_main._validate_database_value("nan", instance="x")
+
+    def test_validate_database_value_rejects_invalid_name(self) -> None:
+        with self.assertRaises(ValueError):
+            seed_main._validate_database_value("bad name", instance="x")
+
+    def _mock_df_mask_any(self, *, any_value: bool) -> MagicMock:
+        """
+        Build a DataFrame-like mock such that:
+          mask = (df["instance"] == instance) & (df["database"] == database)
+          mask.any() returns any_value
+        """
+        df = MagicMock(spec=pd.DataFrame)
+
+        left = MagicMock()
+        right = MagicMock()
+
+        mask = MagicMock()
+        mask.any.return_value = any_value
+
+        # (left & right) => mask
+        left.__and__.return_value = mask
+
+        # df["instance"] / df["database"] => return objects whose == produces left/right
+        col = MagicMock()
+        col.__eq__.side_effect = [left, right]
+        df.__getitem__.return_value = col
+
+        return df
+
+    @patch("baudolo.seed.__main__.os.path.exists", return_value=False)
+    @patch("baudolo.seed.__main__.pd.read_csv")
+    @patch("baudolo.seed.__main__._empty_df")
+    @patch("baudolo.seed.__main__.pd.concat")
+    def test_check_and_add_entry_file_missing_adds_entry(
+        self,
+        concat: MagicMock,
+        empty_df: MagicMock,
+        read_csv: MagicMock,
+        exists: MagicMock,
+    ) -> None:
+        df_existing = self._mock_df_mask_any(any_value=False)
+        empty_df.return_value = df_existing
+
+        df_out = MagicMock(spec=pd.DataFrame)
+        concat.return_value = df_out
+
+        seed_main.check_and_add_entry(
+            file_path="/tmp/databases.csv",
+            instance="inst",
+            database="db",
+            username="user",
+            password="pass",
+        )
+
+        read_csv.assert_not_called()
+        empty_df.assert_called_once()
+        concat.assert_called_once()
+        df_out.to_csv.assert_called_once_with(
+            "/tmp/databases.csv", sep=";", index=False
+        )
+
+    @patch("baudolo.seed.__main__.os.path.exists", return_value=True)
+    @patch("baudolo.seed.__main__.pd.read_csv", side_effect=EmptyDataError("empty"))
+    @patch("baudolo.seed.__main__._empty_df")
+    @patch("baudolo.seed.__main__.pd.concat")
+    @patch("baudolo.seed.__main__.print")
+    def test_check_and_add_entry_empty_file_warns_and_creates_columns_and_adds(
+        self,
+        print_: MagicMock,
+        concat: MagicMock,
+        empty_df: MagicMock,
+        read_csv: MagicMock,
+        exists: MagicMock,
+    ) -> None:
+        df_existing = self._mock_df_mask_any(any_value=False)
+        empty_df.return_value = df_existing
+
+        df_out = MagicMock(spec=pd.DataFrame)
+        concat.return_value = df_out
+
+        seed_main.check_and_add_entry(
+            file_path="/tmp/databases.csv",
+            instance="inst",
+            database="db",
+            username="user",
+            password="pass",
+        )
+
+        exists.assert_called_once_with("/tmp/databases.csv")
+        read_csv.assert_called_once()
+        empty_df.assert_called_once()
+        concat.assert_called_once()
+
+        # Assert: at least one print call contains the WARNING and prints to stderr
+        warning_calls = []
+        for call in print_.call_args_list:
+            args, kwargs = call
+            if args and "WARNING: databases.csv exists but is empty" in str(args[0]):
+                warning_calls.append((args, kwargs))
+
+        self.assertTrue(
+            warning_calls,
+            "Expected a WARNING print when databases.csv is empty, but none was found.",
+        )
+        # Ensure the warning goes to stderr
+        _, warn_kwargs = warning_calls[0]
+        self.assertEqual(warn_kwargs.get("file"), seed_main.sys.stderr)
+
+        df_out.to_csv.assert_called_once_with(
+            "/tmp/databases.csv", sep=";", index=False
+        )
+
+    @patch("baudolo.seed.__main__.os.path.exists", return_value=True)
+    @patch("baudolo.seed.__main__.pd.read_csv")
+    def test_check_and_add_entry_updates_existing_row(
+        self,
+        read_csv: MagicMock,
+        exists: MagicMock,
+    ) -> None:
+        df = self._mock_df_mask_any(any_value=True)
+        read_csv.return_value = df
+
+        seed_main.check_and_add_entry(
+            file_path="/tmp/databases.csv",
+            instance="inst",
+            database="db",
+            username="user",
+            password="pass",
+        )
+
+        df.to_csv.assert_called_once_with("/tmp/databases.csv", sep=";", index=False)
+
+    @patch("baudolo.seed.__main__.check_and_add_entry")
+    @patch("baudolo.seed.__main__.argparse.ArgumentParser.parse_args")
+    def test_main_calls_check_and_add_entry(
+        self, parse_args: MagicMock, cae: MagicMock
+    ) -> None:
+        ns = MagicMock()
+        ns.file = "/tmp/databases.csv"
+        ns.instance = "inst"
+        ns.database = "db"
+        ns.username = "user"
+        ns.password = "pass"
+        parse_args.return_value = ns
+
+        seed_main.main()
+
+        cae.assert_called_once_with(
+            file_path="/tmp/databases.csv",
+            instance="inst",
+            database="db",
+            username="user",
+            password="pass",
+        )
+
+    @patch("baudolo.seed.__main__.sys.exit")
+    @patch("baudolo.seed.__main__.print")
+    @patch(
+        "baudolo.seed.__main__.check_and_add_entry", side_effect=RuntimeError("boom")
+    )
+    @patch("baudolo.seed.__main__.argparse.ArgumentParser.parse_args")
+    def test_main_exits_nonzero_on_error(
+        self,
+        parse_args: MagicMock,
+        cae: MagicMock,
+        print_: MagicMock,
+        exit_: MagicMock,
+    ) -> None:
+        ns = MagicMock()
+        ns.file = "/tmp/databases.csv"
+        ns.instance = "inst"
+        ns.database = "db"
+        ns.username = "user"
+        ns.password = "pass"
+        parse_args.return_value = ns
+
+        seed_main.main()
+
+        self.assertTrue(print_.called)
+        _, kwargs = print_.call_args
+        self.assertEqual(kwargs.get("file"), seed_main.sys.stderr)
+        exit_.assert_called_once_with(1)
+
+
+if __name__ == "__main__":
+    unittest.main(verbosity=2)

tests/unit/test_backup.py

@@ -0,0 +1,54 @@
+import unittest
+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, _mock_is_swarm_task
+    ):
+        # All containers use images containing allowed substrings
+        mock_get_image_info.side_effect = [
+            "repo/mastodon:v4",
+            "repo/wordpress:latest",
+        ]
+        containers = ["c1", "c2"]
+        whitelist = ["mastodon", "wordpress"]
+        self.assertFalse(requires_stop(containers, whitelist))
+
+    @patch("baudolo.backup.app.get_image_info")
+    def test_requires_stop_true_when_any_image_is_not_whitelisted(
+        self, mock_get_image_info, _mock_is_swarm_task
+    ):
+        mock_get_image_info.side_effect = [
+            "repo/mastodon:v4",
+            "repo/nginx:latest",
+        ]
+        containers = ["c1", "c2"]
+        whitelist = ["mastodon", "wordpress"]
+        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, _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()