chore: publish 2.0.1+2.1.1-beta release

without path extraction

.drone.yml

@@ -0,0 +1,17 @@
+---
+kind: pipeline
+name: linters
+steps:
+  - name: publish image
+    image: plugins/docker
+    settings:
+      username: 3wordchant
+      password:
+        from_secret: git_coopcloud_tech_token_3wc
+      repo: git.coopcloud.tech/coop-cloud/backup-bot-two
+      tags: ${DRONE_SEMVER_BUILD}
+      registry: git.coopcloud.tech
+    when:
+      event:
+        include:
+          - tag

.env.sample

@@ -1,10 +1,34 @@
-STACK_NAME=backup-bot-two
+TYPE=backup-bot-two
+
+SECRET_RESTIC_PASSWORD_VERSION=v1
+
+COMPOSE_FILE=compose.yml
 
 RESTIC_REPOSITORY=/backups/restic
 
 CRON_SCHEDULE='30 3 * * *'
 
-# Push Notifications
+# Push Notifiactions
 #PUSH_URL_START=https://status.example.com/api/push/xxxxxxxxxx?status=up&msg=start
 #PUSH_URL_SUCCESS=https://status.example.com/api/push/xxxxxxxxxx?status=up&msg=OK
 #PUSH_URL_FAIL=https://status.example.com/api/push/xxxxxxxxxx?status=down&msg=fail
+
+# swarm-cronjob, instead of built-in cron
+#COMPOSE_FILE="$COMPOSE_FILE:compose.swarm-cronjob.yml"
+
+# SSH storage
+#SECRET_SSH_KEY_VERSION=v1
+#SSH_HOST_KEY="hostname ssh-rsa AAAAB3...
+#COMPOSE_FILE="$COMPOSE_FILE:compose.ssh.yml"
+
+# S3 storage
+#SECRET_AWS_SECRET_ACCESS_KEY_VERSION=v1
+#AWS_ACCESS_KEY_ID=something-secret
+#COMPOSE_FILE="$COMPOSE_FILE:compose.s3.yml"
+
+# Secret restic repository
+# use a secret to store the RESTIC_REPOSITORY if the repository location contains a secret value
+# i.E rest:https://user:SECRET_PASSWORD@host:8000/
+# it overwrites the RESTIC_REPOSITORY variable
+#SECRET_RESTIC_REPO_VERSION=v1
+#COMPOSE_FILE="$COMPOSE_FILE:compose.secret.yml"

.envrc.sample

@@ -0,0 +1,17 @@
+export RESTIC_HOST="user@domain.tld"
+export RESTIC_PASSWORD_FILE=/run/secrets/restic-password
+export BACKUP_DEST=/backups
+
+export SERVER_NAME=domain.tld
+export DOCKER_CONTEXT=$SERVER_NAME
+
+# uncomment either this:
+#export SSH_KEY_FILE=~/.ssh/id_rsa
+# or this:
+#export AWS_SECRET_ACCESS_KEY_FILE=s3
+#export AWS_ACCESS_KEY_ID=easter-october-emphatic-tug-urgent-customer
+# or this:
+#export HTTPS_PASSWORD_FILE=/run/secrets/https_password
+
+# optionally limit subset of services for testing
+#export SERVICES_OVERRIDE="ghost_domain_tld_app ghost_domain_tld_db"

.gitignore

@@ -1 +1 @@
-.env
+/testing

CHANGELOG.md

@@ -0,0 +1,6 @@
+# Change log
+
+## 2.0.0 (unreleased)
+
+- Rewrite from Bash to Python
+- Add support for push notifications (#24)

Dockerfile

@@ -0,0 +1,11 @@
+FROM docker:24.0.7-dind
+
+RUN apk add --upgrade --no-cache restic bash python3 py3-pip py3-click py3-docker-py py3-json-logger curl
+
+# Todo use requirements file with specific versions
+RUN pip install --break-system-packages resticpy==1.0.2
+
+COPY backupbot.py /usr/bin/backup
+COPY entrypoint.sh /entrypoint.sh
+
+ENTRYPOINT /entrypoint.sh

README.md

@@ -1,27 +1,106 @@
 # Backupbot II
 
-Wiki Cafe's configuration for a Backupbot II deployment. Originally slimmed down from an `abra` [recipe](https://git.coopcloud.tech/coop-cloud/backup-bot-two) by [Co-op Cloud](https://coopcloud.tech/).
+[![Build Status](https://build.coopcloud.tech/api/badges/coop-cloud/backup-bot-two/status.svg)](https://build.coopcloud.tech/coop-cloud/backup-bot-two)
+
+_This Time, It's Easily Configurable_
+
+Automatically take backups from all volumes of running Docker Swarm services and runs pre- and post commands.
+
+<!-- metadata -->
+
+* **Category**: Utilities
+* **Status**: 0, work-in-progress
+* **Image**: [`git.coopcloud.tech/coop-cloud/backup-bot-two`](https://git.coopcloud.tech/coop-cloud/-/packages/container/backup-bot-two), 4, upstream
+* **Healthcheck**: No
+* **Backups**: N/A
+* **Email**: N/A
+* **Tests**: No
+* **SSO**: N/A
+
+<!-- endmetadata -->
 
 
-## Deploying the app with Docker Swarm
+## Background
 
-Set the environment variables from the .env file during the shell session.
+There are lots of Docker volume backup systems; all of them have one or both of these limitations:
+ - You need to define all the volumes to back up in the configuration system
+ - Backups require services to be stopped to take consistent copies
 
+Backupbot II tries to help, by
+1. **letting you define backups using Docker labels**, so you can **easily collect your backups for use with another system** like docker-volume-backup.
+2. **running pre- and post-commands** before and after backups, for example to use database tools to take a backup from a running service.
+
+## Deployment
+
+### With Co-op Cloud
+
+
+* `abra app new backup-bot-two`
+* `abra app config <app-name>`
+    - set storage options. Either configure `CRON_SCHEDULE`, or set up `swarm-cronjob`
+* `abra app secret generate -a <backupbot_name>`
+* `abra app deploy <app-name>`
+
+## Configuration
+
+Per default Backupbot stores the backups locally in the repository `/backups/restic`, which is accessible as volume at `/var/lib/docker/volumes/<backupbot_name>_backups/_data/restic/`
+
+The backup location can be changed using the `RESTIC_REPOSITORY` env variable.
+
+### S3 Storage
+
+To use S3 storage as backup location set the following envs:
 ```
-set -a && source .env && set +a
+RESTIC_REPOSITORY=s3:<S3-SERVICE-URL>/<BUCKET-NAME>
+SECRET_AWS_SECRET_ACCESS_KEY_VERSION=v1
+AWS_ACCESS_KEY_ID=<MY_ACCESS_KEY>
+COMPOSE_FILE="$COMPOSE_FILE:compose.s3.yml"
 ```
+and add your `<SECRET_ACCESS_KEY>` as docker secret:
+`abra app secret insert <backupbot_name> aws_secret_access_key v1 <SECRET_ACCESS_KEY>`
 
-Set the secrets.
+See [restic s3 docs](https://restic.readthedocs.io/en/latest/030_preparing_a_new_repo.html#amazon-s3) for more information.
 
-```
-printf "SECRET_HERE" | docker secret create SECRET_NAME -
-```
+### SFTP Storage
 
-Deploy using the `-c` flag to specify one or multiple compose files.
+> With sftp it is not possible to prevent the backupbot from deleting backups in case of a compromised machine. Therefore we recommend to use S3, REST or rclone server without delete permissions.
 
+To use SFTP storage as backup location set the following envs:
 ```
-docker stack deploy backup-bot-two -c compose.yaml
+RESTIC_REPOSITORY=sftp:user@host:/restic-repo-path
+SECRET_SSH_KEY_VERSION=v1
+SSH_HOST_KEY="hostname ssh-rsa AAAAB3...
+COMPOSE_FILE="$COMPOSE_FILE:compose.ssh.yml"
 ```
+To get the `SSH_HOST_KEY` run the following command `ssh-keyscan <hostname>`
+
+Generate an ssh keypair: `ssh-keygen -t ed25519 -f backupkey -P ''`
+Add the key to your `authorized_keys`:
+`ssh-copy-id -i backupkey <user>@<hostname>`
+Add your `SSH_KEY` as docker secret:
+```
+abra app secret insert <backupbot_name> ssh_key v1 """$(cat backupkey)
+"""
+```
+> Attention: This command needs to be executed exactly as stated above, because it places a trailing newline at the end, if this is missing you will get the following error: `Load key "/run/secrets/ssh_key": error in libcrypto`
+
+### Restic REST server Storage
+
+You can simply set the `RESTIC_REPOSITORY` variable to your REST server URL `rest:http://host:8000/`.
+If you access the REST server with a password `rest:https://user:pass@host:8000/` you should hide the whole URL containing the password inside a secret.
+Uncomment these lines:
+```
+SECRET_RESTIC_REPO_VERSION=v1
+COMPOSE_FILE="$COMPOSE_FILE:compose.secret.yml"
+```
+Add your REST server url as secret:
+```
+abra app secret insert <backupbot_name> restic_repo v1 "rest:https://user:pass@host:8000/"
+```
+The secret will overwrite the `RESTIC_REPOSITORY` variable.
+
+
+See [restic REST docs](https://restic.readthedocs.io/en/latest/030_preparing_a_new_repo.html#rest-server) for more information.
 
 ## Push notifications
 
@@ -34,82 +113,71 @@ PUSH_URL_SUCCESS=https://status.example.com/api/push/xxxxxxxxxx?status=up&msg=OK
 PUSH_URL_FAIL=https://status.example.com/api/push/xxxxxxxxxx?status=down&msg=fail
 ```
 
-## Commands
 
+## Usage
 
-- Find the ID or name of the backup container:
-   ```
-   docker ps --filter "name=backup-bot-two_app"
-   ```
+Run the cronjob that creates a backup, including the push notifications and docker logging:
+`abra app cmd <backupbot_name> app run_cron`
 
-2. Run the desired command using `docker exec`:
-   ```
-   docker exec -it <container_id_or_name> backup <command> [options]
-   ```
-   Replace `<container_id_or_name>` with the ID or name of the backup container.
+Create a backup of all apps:
 
-   Available commands:
-   - `create`: Initiate the backup process.
-   - `restore`: Restore a specific snapshot to a target directory.
-   - `snapshots`: List available snapshots.
-   - `ls`: List files in a specific snapshot.
-   - `download`: Download specific files, volumes, or secrets from a snapshot.
+`abra app run <backupbot_name> app -- backup create`
 
-   Options:
-   - `--host`, `-h`: Specify the service name (e.g., `app`).
-   - `--repo`, `-r`: Specify the Restic repository location (e.g., `/run/secrets/restic_repo`).
-   - `--log`, `-l`: Set the log level (e.g., `debug`, `info`, `warning`, `error`).
-   - `--machine-logs`, `-m`: Enable machine-readable JSON logging.
+> The apps to backup up need to be deployed
 
-## Examples
+Create an individual backup:
 
-Create a backup:
+`abra app run <backupbot_name> app -- backup --host <target_app_name> create`
+
+Create a backup to a local repository:
+
+`abra app run <backupbot_name> app -- backup create -r /backups/restic`
+
+> It is recommended to shutdown/undeploy an app before restoring the data
+
+Restore the latest snapshot of all including apps:
+
+`abra app run <backupbot_name> app -- backup restore`
+
+Restore a specific snapshot of an individual app:
+
+`abra app run <backupbot_name> app -- backup --host <target_app_name> restore --snapshot <snapshot_id>`
+
+Show all snapshots:
+
+`abra app run <backupbot_name> app -- backup snapshots`
+
+Show all snapshots containing a specific app:
+
+`abra app run <backupbot_name> app -- backup --host <target_app_name> snapshots`
+
+Show all files inside the latest snapshot (can be very verbose):
+
+`abra app run <backupbot_name> app -- backup ls`
+
+Show specific files inside a selected snapshot:
+
+`abra app run <backupbot_name> app -- backup ls --snapshot <snapshot_id> --path /var/lib/docker/volumes/`
+
+Download files from a snapshot:
 
 ```
-docker exec -it <container_id_or_name> backup create --host app
+filename=$(abra app run <backupbot_name> app -- backup download --snapshot <snapshot_id> --path <absolute_path>)
+abra app cp <backupbot_name> app:$filename .
 ```
 
-Restore a snapshot:
+## Run restic
 
 ```
-docker exec -it <container_id_or_name> backup restore --snapshot <snapshot_id> --target /path/to/restore
+abra app run <backupbot_name> app bash
+export AWS_SECRET_ACCESS_KEY=$(cat $AWS_SECRET_ACCESS_KEY_FILE)
+export RESTIC_PASSWORD=$(cat $RESTIC_PASSWORD_FILE)
+restic snapshots
 ```
 
-List snapshots:
-
-  ```
-  docker exec -it <container_id_or_name> backup snapshots
-  ```
-
-List files in a snapshot:
-
-```
-docker exec -it <container_id_or_name> backup ls --snapshot <snapshot_id> --path /path/to/directory
-```
-
-Download files, volumes, or secrets from a snapshot:
-
-```
-docker exec -it <container_id_or_name> backup download --snapshot <snapshot_id> [--path /path/to/file] [--volumes] [--secrets]
-```
-
-Note: Make sure to replace `<container_id_or_name>` and `<snapshot_id>` with the appropriate values for your setup.
-
-Remember to review and adjust the Docker Compose file and environment variables according to your specific requirements before running the backup commands.
-
-When using `docker exec`, you don't need to specify the volume mounts or the Restic repository location as command-line arguments because they are already defined in the Docker Compose file and are available within the running container.
-
-If you need to access the downloaded files, volumes, or secrets from the backup, you can use `docker cp` to copy them from the container to the host machine:
-
-```
-docker cp <container_id_or_name>:/path/to/backup/file /path/on/host
-```
-
-This allows you to retrieve the backed-up data from the container.
-
 ## Recipe Configuration
 
-Backupbot II uses access to the Docker socket to read labels from running Docker Swarm services:
+Like Traefik, or `swarm-cronjob`, Backupbot II uses access to the Docker socket to read labels from running Docker Swarm services:
 
 ```
 services:
@@ -126,3 +194,5 @@ services:
 - `backupbot.backup.post-hook` -- command to run after copying files (optional)
 
 As in the above example, you can reference Docker Secrets, e.g. for looking up database passwords, by reading the files in `/run/secrets` directly.
+
+[abra]: https://git.autonomic.zone/autonomic-cooperative/abra

abra.sh

@@ -0,0 +1,10 @@
+export BACKUPBOT_VERSION=v1
+export SSH_CONFIG_VERSION=v1
+
+run_cron () {
+    schedule="$(crontab -l | tr -s " " | cut -d ' ' -f-5)"
+    rm -f /tmp/backup.log
+    echo "* * * * *  $(crontab -l | tr -s " " | cut -d ' ' -f6-)" | crontab -
+    while [ ! -f /tmp/backup.log ]; do sleep 1; done
+    echo "$schedule $(crontab -l | tr -s " " | cut -d ' ' -f6-)" | crontab -
+}

backupbot.py

@@ -18,7 +18,7 @@ from shutil import copyfile, rmtree
 
 VOLUME_PATH = "/var/lib/docker/volumes/"
 SECRET_PATH = '/secrets/'
-SERVICE = None
+SERVICE = 'ALL'
 
 logger = logging.getLogger("backupbot")
 logging.addLevelName(55, 'SUMMARY')
@@ -54,8 +54,8 @@ def cli(loglevel, service, repository, machine_logs):
         if not isinstance(numeric_level, int):
             raise ValueError('Invalid log level: %s' % loglevel)
         logger.setLevel(numeric_level)
-    if machine_logs:
     logHandler = logging.StreamHandler()
+    if machine_logs:
         formatter = jsonlogger.JsonFormatter(
             "%(levelname)s %(filename)s %(lineno)s %(process)d %(message)s", rename_fields={"levelname": "message_type"})
         logHandler.setFormatter(formatter)
@@ -66,9 +66,13 @@ def cli(loglevel, service, repository, machine_logs):
 
 
 def init_repo():
+    if repo:= os.environ.get('RESTIC_REPOSITORY_FILE'):
+        # RESTIC_REPOSITORY_FILE and RESTIC_REPOSITORY are mutually exclusive
+        del os.environ['RESTIC_REPOSITORY']
+    else:
         repo = os.environ['RESTIC_REPOSITORY']
-    logger.debug(f"set restic repository location: {repo}")
         restic.repository = repo
+    logger.debug(f"set restic repository location: {repo}")
     restic.password_file = '/var/run/secrets/restic_password'
     try:
         restic.cat.config()
@@ -87,54 +91,203 @@ def export_secrets():
             with open(os.environ[env]) as file:
                 secret = file.read()
                 os.environ[env.removesuffix('_FILE')] = secret
-
-            if env == 'RESTIC_REPOSITORY_FILE':
-                # RESTIC_REPOSITORY_FILE and RESTIC_REPOSITORY are mutually exclusive
-                logger.info("RESTIC_REPOSITORY set to RESTIC_REPOSITORY_FILE. Unsetting RESTIC_REPOSITORY_FILE.")
-                del os.environ['RESTIC_REPOSITORY_FILE']
+                # logger.debug(f"Read secret value: {secret}")
 
 
 @cli.command()
 @click.option('retries', '--retries', '-r', envvar='RETRIES', default=1)
 def create(retries):
-    pre_commands, post_commands, backup_paths, apps = get_backup_cmds()
+    app_settings = parse_backup_labels()
+    pre_commands, post_commands, backup_paths, apps = get_backup_details(app_settings)
     copy_secrets(apps)
-    backup_paths.append(SECRET_PATH)
+    backup_paths.append(Path(SECRET_PATH))
     run_commands(pre_commands)
     backup_volumes(backup_paths, apps, int(retries))
     run_commands(post_commands)
 
 
-def get_backup_cmds():
+@cli.command()
+@click.option('snapshot', '--snapshot', '-s', envvar='SNAPSHOT', default='latest')
+@click.option('target', '--target', '-t', envvar='TARGET', default='/')
+@click.option('noninteractive', '--noninteractive', envvar='NONINTERACTIVE', is_flag=True)
+@click.option('volumes', '--volumes', '-v', envvar='VOLUMES', multiple=True)
+@click.option('container', '--container', '-c', envvar='CONTAINER', multiple=True)
+@click.option('no_commands', '--no-commands', envvar='NO_COMMANDS', is_flag=True)
+def restore(snapshot, target, noninteractive, volumes, container, no_commands):
+    app_settings = parse_backup_labels('restore', container)
+    if SERVICE != 'ALL':
+        app_settings = {SERVICE: app_settings[SERVICE]}
+    pre_commands, post_commands, backup_paths, apps = get_backup_details(app_settings, volumes)
+    snapshots = get_snapshots(snapshot_id=snapshot)
+    if not snapshot:
+        logger.error("No Snapshots with ID {snapshots} for {apps} found.")
+        exit(1)
+    if not noninteractive:
+        snapshot_date = datetime.fromisoformat(snapshots[0]['time'])
+        delta = datetime.now(tz=timezone.utc) - snapshot_date
+        print(f"You are going to restore Snapshot {snapshot} of {apps} at {target}")
+        print("The following volume paths will be restored:")
+        for p in backup_paths:
+            print(f'\t{p}')
+        if not no_commands:
+            print("The following commands will be executed:")
+            for container, cmd in list(pre_commands.items()) + list(post_commands.items()):
+                print(f"\t{container.labels['com.docker.swarm.service.name']}:\t{cmd}")
+        print(f"This snapshot is {delta} old")
+        print("\nTHIS COMMAND WILL IRREVERSIBLY OVERWRITES FILES")
+        prompt = input("Type YES (uppercase) to continue: ")
+        if prompt != 'YES':
+            logger.error("Restore aborted")
+            exit(1)
+    print(f"Restoring Snapshot {snapshot} at {target}")
+    if not no_commands and pre_commands:
+        print(f"Run pre commands.")
+        run_commands(pre_commands)
+    result = restic_restore(snapshot_id=snapshot, include=backup_paths, target_dir=target)
+    if not no_commands and post_commands:
+        print(f"Run post commands.")
+        run_commands(post_commands)
+    logger.debug(result)
+
+
+def restic_restore(snapshot_id='latest', include=[], target_dir=None):
+    cmd = restic.cat.base_command() + ['restore', snapshot_id]
+    for path in include:
+        cmd.extend(['--include', path])
+    if target_dir:
+        cmd.extend(['--target', target_dir])
+    return restic.internal.command_executor.execute(cmd)
+
+
+def get_snapshots(snapshot_id=None):
+    if snapshot_id and snapshot_id != 'latest':
+        snapshots = restic.snapshots(snapshot_id=snapshot_id)
+        if SERVICE not in snapshots[0]['tags']:
+            logger.error(f'Snapshot with ID {snapshot_id} does not contain {SERVICE}')
+            exit(1)
+    else:
+        snapshots = restic.snapshots()
+        snapshots = list(filter(lambda x: x.get('tags') and SERVICE in x.get('tags'), snapshots))
+    if snapshot_id == 'latest':
+        return snapshots[-1:]
+    else:
+        return snapshots
+
+
+def parse_backup_labels(hook_type='backup', selected_container=[]):
     client = docker.from_env()
     container_by_service = {
-        c.labels['com.docker.swarm.service.name']: c for c in client.containers.list()}
-    backup_paths = set()
-    backup_apps = set()
-    pre_commands = {}
-    post_commands = {}
+        c.labels.get('com.docker.swarm.service.name'): c for c in client.containers.list()}
     services = client.services.list()
+    app_settings = {}
     for s in services:
-        labels = s.attrs['Spec']['Labels']
-        if (backup := labels.get('backupbot.backup')) and bool(backup):
-            # volumes: s.attrs['Spec']['TaskTemplate']['ContainerSpec']['Mounts'][0]['Source']
+        specs = s.attrs['Spec']
+        labels = specs['Labels']
         stack_name = labels['com.docker.stack.namespace']
-            # Remove this lines to backup only a specific service
-            # This will unfortenately decrease restice performance
-            # if SERVICE and SERVICE != stack_name:
-            #     continue
-            backup_apps.add(stack_name)
-            backup_paths = backup_paths.union(
-                Path(VOLUME_PATH).glob(f"{stack_name}_*"))
-            if not (container := container_by_service.get(s.name)):
-                logger.error(
-                    f"Container {s.name} is not running, hooks can not be executed")
+        container_name = s.name.removeprefix(f"{stack_name}_")
+        settings = app_settings[stack_name] = app_settings.get(stack_name) or {}
+        if (backup := labels.get('backupbot.backup')) and bool(backup):
+            settings['enabled'] = True
+        if selected_container and container_name not in selected_container:
+            logger.debug(f"Skipping {s.name} because it's not a selected container")
             continue
-            if prehook := labels.get('backupbot.backup.pre-hook'):
-                pre_commands[container] = prehook
-            if posthook := labels.get('backupbot.backup.post-hook'):
-                post_commands[container] = posthook
-    return pre_commands, post_commands, list(backup_paths), list(backup_apps)
+        if mounts:= specs['TaskTemplate']['ContainerSpec'].get('Mounts'):
+            volumes = parse_volumes(stack_name, mounts)
+            volumes.update(settings.get('volumes') or {})
+            settings['volumes'] = volumes
+            excluded_volumes, included_volume_paths = parse_excludes_includes(labels)
+            settings['excluded_volumes'] = excluded_volumes.union(settings.get('excluded_volumes') or set())
+            settings['included_volume_paths'] = included_volume_paths.union(settings.get('included_volume_paths') or set())
+        if container := container_by_service.get(s.name):
+            if command := labels.get(f'backupbot.{hook_type}.pre-hook'):
+                if not (pre_hooks:= settings.get('pre_hooks')):
+                    pre_hooks = settings['pre_hooks'] = {}
+                pre_hooks[container] = command
+            if command := labels.get(f'backupbot.{hook_type}.post-hook'):
+                if not (post_hooks:= settings.get('post_hooks')):
+                    post_hooks = settings['post_hooks'] = {}
+                post_hooks[container] = command
+        else:
+            logger.debug(f"Container {s.name} is not running.")
+            if labels.get(f'backupbot.{hook_type}.pre-hook') or labels.get(f'backupbot.{hook_type}.post-hook'):
+                logger.error(f"Container {s.name} contain hooks but it's not running")
+    return app_settings
+
+
+def get_backup_details(app_settings, volumes=[]):
+    backup_paths = set()
+    backup_apps = []
+    pre_hooks= {}
+    post_hooks = {}
+    for app, settings in app_settings.items():
+        if settings.get('enabled'):
+            if SERVICE != 'ALL' and SERVICE != app:
+                continue
+            backup_apps.append(app)
+            add_backup_paths(backup_paths, settings, app, volumes)
+            if hooks:= settings.get('pre_hooks'):
+                pre_hooks.update(hooks)
+            if hooks:= settings.get('post_hooks'):
+                post_hooks.update(hooks)
+    return pre_hooks, post_hooks, list(backup_paths), backup_apps
+
+
+def add_backup_paths(backup_paths, settings, app, selected_volumes):
+    if (volumes := settings.get('volumes')):
+        if includes:= settings.get('included_volume_paths'):
+            included_volumes = list(zip(*includes))[0]
+            for volume, rel_paths in includes:
+                if not (volume_path:= volumes.get(volume)):
+                    logger.error(f'Can not find volume with the name {volume}')
+                    continue
+                if selected_volumes and volume not in selected_volumes:
+                    logger.debug(f'Skipping {volume}:{rel_paths} because the volume is not selected')
+                    continue
+                for p in rel_paths:
+                    absolute_path = Path(f"{volume_path}/{p}")
+                    backup_paths.add(absolute_path)
+        else:
+            included_volumes = []
+        excluded_volumes = settings.get('excluded_volumes') or []
+        for name, path in volumes.items():
+            if selected_volumes and name not in selected_volumes:
+                logger.debug(f'Skipping volume: {name} because the volume is not selected')
+                continue
+            if name in excluded_volumes:
+                logger.debug(f'Skipping volume: {name} because the volume is excluded')
+                continue
+            if name in included_volumes:
+                logger.debug(f'Skipping volume: {name} because a path is selected')
+                continue
+            backup_paths.add(path)
+    else:
+        logger.warning(f"{app} does not contain any volumes")
+
+
+def parse_volumes(stack_name, mounts):
+    volumes = {}
+    for m in mounts:
+        if m['Type'] != 'volume':
+            continue
+        relative_path = m['Source']
+        name = relative_path.removeprefix(stack_name + '_')
+        absolute_path = Path(f"{VOLUME_PATH}{relative_path}/_data/")
+        volumes[name] = absolute_path
+    return volumes
+
+
+def parse_excludes_includes(labels):
+    excluded_volumes = set()
+    included_volume_paths = set()
+    for label, value in labels.items():
+        if label.startswith('backupbot.backup.volumes.'):
+            volume_name = label.removeprefix('backupbot.backup.volumes.').removesuffix('.path')
+            if label.endswith('path'): 
+                relative_paths = tuple(value.split(','))
+                included_volume_paths.add((volume_name, relative_paths))
+            elif bool(value):
+                excluded_volumes.add(volume_name)
+    return excluded_volumes, included_volume_paths
 
 
 def copy_secrets(apps):
@@ -143,14 +296,14 @@ def copy_secrets(apps):
     os.mkdir(SECRET_PATH)
     client = docker.from_env()
     container_by_service = {
-        c.labels['com.docker.swarm.service.name']: c for c in client.containers.list()}
+        c.labels.get('com.docker.swarm.service.name'): c for c in client.containers.list()}
     services = client.services.list()
     for s in services:
         app_name = s.attrs['Spec']['Labels']['com.docker.stack.namespace']
         if (app_name in apps and
                 (app_secs := s.attrs['Spec']['TaskTemplate']['ContainerSpec'].get('Secrets'))):
             if not container_by_service.get(s.name):
-                logger.error(
+                logger.warning(
                     f"Container {s.name} is not running, secrets can not be copied.")
                 continue
             container_id = container_by_service[s.name].id
@@ -161,6 +314,7 @@ def copy_secrets(apps):
                         f"For the secret {sec['SecretName']} the file {src} does not exist for {s.name}")
                     continue
                 dst = SECRET_PATH + sec['SecretName']
+                logger.debug(f"Copy Secret {sec['SecretName']}")
                 copyfile(src, dst)
 
 
@@ -188,12 +342,21 @@ def run_commands(commands):
 def backup_volumes(backup_paths, apps, retries, dry_run=False):
     while True:
         try:
-            result = restic.backup(backup_paths, dry_run=dry_run, tags=apps)
+            logger.info("Backup these paths:")
+            logger.debug("\n".join(map(str, backup_paths)))
+            backup_paths = list(filter(path_exists, backup_paths))
+            cmd = restic.cat.base_command()
+            parent = get_snapshots('latest') 
+            if parent:
+                # https://restic.readthedocs.io/en/stable/040_backup.html#file-change-detection
+                cmd.extend(['--parent', parent[0]['short_id']])
+            tags = set(apps + [SERVICE])
+            logger.info("Start volume backup")
+            result = restic.internal.backup.run(cmd, backup_paths, dry_run=dry_run, tags=tags)
             logger.summary("backup finished", extra=result)
             return
         except ResticFailedError as error:
-            logger.error(
-                f"Backup failed for {apps}. Could not Backup these paths: {backup_paths}")
+            logger.error(f"Backup failed for {SERVICE}.")
             logger.error(error, exc_info=True)
             if retries > 0:
                 retries -= 1
@@ -201,49 +364,20 @@ def backup_volumes(backup_paths, apps, retries, dry_run=False):
                 exit(1)
 
 
-@cli.command()
-@click.option('snapshot', '--snapshot', '-s', envvar='SNAPSHOT', default='latest')
-@click.option('target', '--target', '-t', envvar='TARGET', default='/')
-@click.option('noninteractive', '--noninteractive', envvar='NONINTERACTIVE', is_flag=True)
-def restore(snapshot, target, noninteractive):
-    # Todo: recommend to shutdown the container
-    service_paths = VOLUME_PATH
-    if SERVICE:
-        service_paths = service_paths + f'{SERVICE}_*'
-    snapshots = restic.snapshots(snapshot_id=snapshot)
-    if not snapshot:
-        logger.error("No Snapshots with ID {snapshots}")
-        exit(1)
-    if not noninteractive:
-        snapshot_date = datetime.fromisoformat(snapshots[0]['time'])
-        delta = datetime.now(tz=timezone.utc) - snapshot_date
-        print(
-            f"You are going to restore Snapshot {snapshot} of {service_paths} at {target}")
-        print(f"This snapshot is {delta} old")
-        print(
-            f"THIS COMMAND WILL IRREVERSIBLY OVERWRITES {target}{service_paths.removeprefix('/')}")
-        prompt = input("Type YES (uppercase) to continue: ")
-        if prompt != 'YES':
-            logger.error("Restore aborted")
-            exit(1)
-    print(f"Restoring Snapshot {snapshot} of {service_paths} at {target}")
-    # TODO: use tags if no snapshot is selected, to use a snapshot including SERVICE
-    result = restic.restore(snapshot_id=snapshot,
-                            include=service_paths, target_dir=target)
-    logger.debug(result)
+def path_exists(path):
+    if not path.exists():
+        logger.error(f'{path} does not exist')
+    return path.exists()
 
 
 @cli.command()
 def snapshots():
-    snapshots = restic.snapshots()
-    no_snapshots = True
+    snapshots = get_snapshots()
     for snap in snapshots:
-        if not SERVICE or (tags := snap.get('tags')) and SERVICE in tags:
         print(snap['time'], snap['id'])
-            no_snapshots = False
-    if no_snapshots:
+    if not snapshots:
         err_msg = "No Snapshots found"
-        if SERVICE:
+        if SERVICE != 'ALL':
             service_name = SERVICE.replace('_', '.')
             err_msg += f' for app {service_name}'
         logger.warning(err_msg)
@@ -261,7 +395,6 @@ def ls(snapshot, path):
 
 def list_files(snapshot, path):
     cmd = restic.cat.base_command() + ['ls']
-    if SERVICE:
     cmd = cmd + ['--tag', SERVICE]
     cmd.append(snapshot)
     if path:
@@ -271,7 +404,7 @@ def list_files(snapshot, path):
     except ResticFailedError as error:
         if 'no snapshot found' in str(error):
             err_msg = f'There is no snapshot "{snapshot}"'
-            if SERVICE:
+            if SERVICE != 'ALL':
                 err_msg += f' for the app "{SERVICE}"'
             logger.error(err_msg)
             exit(1)
@@ -303,7 +436,7 @@ def download(snapshot, path, volumes, secrets):
         tarinfo.size = len(binary_output)
         file_dumps.append((binary_output, tarinfo))
     if volumes:
-        if not SERVICE:
+        if SERVICE == 'ALL':
             logger.error("Please specify '--host' when using '--volumes'")
             exit(1)
         files = list_files(snapshot, VOLUME_PATH)
@@ -316,7 +449,7 @@ def download(snapshot, path, volumes, secrets):
                 tarinfo.size = len(binary_output)
                 file_dumps.append((binary_output, tarinfo))
     if secrets:
-        if not SERVICE:
+        if SERVICE == 'ALL':
             logger.error("Please specify '--host' when using '--secrets'")
             exit(1)
         filename = f"{SERVICE}.json"
@@ -353,7 +486,6 @@ def get_formatted_size(file_path):
 
 def dump(snapshot, path):
     cmd = restic.cat.base_command() + ['dump']
-    if SERVICE:
     cmd = cmd + ['--tag', SERVICE]
     cmd = cmd + [snapshot, path]
     print(f"Dumping {path} from snapshot '{snapshot}'")

compose.s3.yml

@@ -0,0 +1,14 @@
+---
+version: "3.8"
+services:
+  app:
+    environment:
+      - AWS_ACCESS_KEY_ID
+      - AWS_SECRET_ACCESS_KEY_FILE=/run/secrets/aws_secret_access_key
+    secrets:
+      - aws_secret_access_key
+
+secrets:
+  aws_secret_access_key:
+    external: true
+    name: ${STACK_NAME}_aws_secret_access_key_${SECRET_AWS_SECRET_ACCESS_KEY_VERSION}

compose.secret.yml

@@ -0,0 +1,13 @@
+---
+version: "3.8"
+services:
+  app:
+    environment:
+      - RESTIC_REPOSITORY_FILE=/run/secrets/restic_repo
+    secrets:
+      - restic_repo
+
+secrets:
+  restic_repo:
+    external: true
+    name: ${STACK_NAME}_restic_repo_${SECRET_RESTIC_REPO_VERSION}

compose.ssh.yml

@@ -0,0 +1,23 @@
+---
+version: "3.8"
+services:
+  app:
+    environment:
+      - SSH_KEY_FILE=/run/secrets/ssh_key
+      - SSH_HOST_KEY
+    secrets:
+      - source: ssh_key
+        mode: 0400
+    configs:
+      - source: ssh_config
+        target: /root/.ssh/config
+
+secrets:
+  ssh_key:
+    external: true
+    name: ${STACK_NAME}_ssh_key_${SECRET_SSH_KEY_VERSION}
+
+configs:
+  ssh_config:
+    name: ${STACK_NAME}_ssh_config_${SSH_CONFIG_VERSION}
+    file: ssh_config

compose.swarm-cronjob.yml

@@ -0,0 +1,15 @@
+---
+version: "3.8"
+services:
+  app:
+    deploy:
+      mode: replicated
+      replicas: 0
+      labels:
+        - "swarm.cronjob.enable=true"
+        # Note(3wc): every 5m, testing
+        - "swarm.cronjob.schedule=*/5 * * * *"
+        # Note(3wc): blank label to be picked up by `abra recipe sync`
+      restart_policy:
+        condition: none
+    entrypoint: [ "/usr/bin/backup.sh" ]

compose.yaml

@@ -1,44 +0,0 @@
-services:
-  app:
-    image: docker:24.0.7-dind
-    volumes:
-      - "/var/run/docker.sock:/var/run/docker.sock"
-      - "/var/lib/docker/volumes/:/var/lib/docker/volumes/"
-      - "/var/lib/docker/containers/:/var/lib/docker/containers/:ro"
-    environment:
-      - CRON_SCHEDULE
-      - RESTIC_REPOSITORY_FILE=/run/secrets/restic_repo
-      - RESTIC_PASSWORD_FILE=/run/secrets/restic_password
-    secrets:
-      - restic_repo
-      - restic_password
-    configs:
-      - source: entrypoint
-        target: /entrypoint.sh
-        mode: 0555
-      - source: backupbot
-        target: /usr/bin/backup
-        mode: 0555
-    entrypoint: ['/entrypoint.sh']
-    healthcheck:
-      test: "pgrep crond"
-      interval: 30s
-      timeout: 10s
-      retries: 10
-      start_period: 5m
-
-secrets:
-  restic_repo:
-    external: true
-    name: ${STACK_NAME}_restic_repo
-  restic_password:
-    external: true
-    name: ${STACK_NAME}_restic_password
-
-configs:
-  entrypoint:
-    name: ${STACK_NAME}_entrypoint
-    file: entrypoint.sh
-  backupbot:
-    name: ${STACK_NAME}_backupbot
-    file: backupbot.py

compose.yml

@@ -0,0 +1,36 @@
+---
+version: "3.8"
+services:
+  app:
+    image: git.coopcloud.tech/coop-cloud/backup-bot-two:2.1.1-beta
+    volumes:
+      - "/var/run/docker.sock:/var/run/docker.sock"
+      - "/var/lib/docker/volumes/:/var/lib/docker/volumes/"
+      - "/var/lib/docker/containers/:/var/lib/docker/containers/:ro"
+      - backups:/backups
+    environment:
+      - CRON_SCHEDULE
+      - RESTIC_REPOSITORY
+      - RESTIC_PASSWORD_FILE=/run/secrets/restic_password
+    secrets:
+      - restic_password
+    deploy:
+      labels:
+        - coop-cloud.${STACK_NAME}.version=2.0.1+2.1.1-beta
+        - coop-cloud.${STACK_NAME}.timeout=${TIMEOUT:-300}
+        - coop-cloud.backupbot.enabled=true
+    #entrypoint: ['tail', '-f','/dev/null']
+    healthcheck:
+      test: "pgrep crond"
+      interval: 30s
+      timeout: 10s
+      retries: 10
+      start_period: 5m
+
+secrets:
+  restic_password:
+    external: true
+    name: ${STACK_NAME}_restic_password_${SECRET_RESTIC_PASSWORD_VERSION}
+    
+volumes:
+  backups:

entrypoint.sh

@@ -1,11 +1,11 @@
 #!/bin/sh
 
-set -e -o pipefail
+set -e
 
-apk add --upgrade --no-cache restic bash python3 py3-pip py3-click py3-docker-py py3-json-logger curl
-
-# Todo use requirements file with specific versions
-pip install --break-system-packages resticpy==1.0.2
+if [ -n "$SSH_HOST_KEY" ]
+then
+    echo "$SSH_HOST_KEY" > /root/.ssh/known_hosts
+fi
 
 cron_schedule="${CRON_SCHEDULE:?CRON_SCHEDULE not set}"
 

release/1.0.0+2.0.0-beta

@@ -0,0 +1 @@
+This is the first beta release of the new backup-bot-two rewrite in python. Be aware when updating, it can break. Please read the readme and update your config according to it.

release/1.0.0+latest

@@ -0,0 +1,3 @@
+Breaking Change: the variables `SERVER_NAME` and `RESTIC_HOST` are merged into `RESTIC_REPOSITORY`. The format can be looked up here: https://restic.readthedocs.io/en/stable/030_preparing_a_new_repo.html
+ssh/sftp: `sftp:user@host:/repo-path`
+S3:  `s3:https://s3.example.com/bucket_name`

renovate.json

@@ -0,0 +1,3 @@
+{
+  "$schema": "https://docs.renovatebot.com/renovate-schema.json"
+}

ssh_config

@@ -0,0 +1,4 @@
+Host *
+    IdentityFile    /run/secrets/ssh_key
+    ServerAliveInterval 60
+    ServerAliveCountMax 240