Update backupbot.py and compose.yaml

Reviewed-on: #40

.drone.yml

@@ -1,28 +0,0 @@
----
-kind: pipeline
-name: linters
-steps:
-  - name: run shellcheck
-    image: koalaman/shellcheck-alpine
-    commands:
-      - shellcheck backup.sh
-
-  - name: publish image
-    image: plugins/docker
-    settings:
-      auto_tag: true
-      username: thecoopcloud
-      password:
-        from_secret: thecoopcloud_password
-      repo: thecoopcloud/backup-bot-two
-      tags: latest
-    depends_on:
-      - run shellcheck
-    when:
-      event:
-        exclude:
-          - pull_request
-
-trigger:
-  branch:
-    - main

.env.sample

@@ -1,23 +1,10 @@
-TYPE=backup-bot-two
+STACK_NAME=backup-bot-two
 
-SECRET_RESTIC_PASSWORD_VERSION=v1
+RESTIC_REPOSITORY=/backups/restic
 
-COMPOSE_FILE=compose.yml
+CRON_SCHEDULE='30 3 * * *'
 
-SERVER_NAME=example.com
+# Push Notifications
-RESTIC_HOST=minio.example.com
+#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
-CRON_SCHEDULE='*/5 * * * *'
+#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"

.envrc.sample

@@ -1,15 +0,0 @@
-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
-
-# optionally limit subset of services for testing
-#export SERVICES_OVERRIDE="ghost_domain_tld_app ghost_domain_tld_db"

.gitignore

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

Dockerfile

@@ -1,13 +0,0 @@
-FROM docker:19.03.13-dind
-
-RUN apk add --upgrade --no-cache \
-  bash \
-  curl \
-  jq \
-  restic
-
-COPY backup.sh /usr/bin/backup.sh
-COPY setup-cron.sh /usr/bin/setup-cron.sh
-RUN chmod +x /usr/bin/backup.sh /usr/bin/setup-cron.sh
-
-ENTRYPOINT [ "/usr/bin/setup-cron.sh" ]

README.md

@@ -1,72 +1,128 @@
 # Backupbot II
 
-[![Build Status](https://build.coopcloud.tech/api/badges/coop-cloud/backup-bot-two/status.svg)](https://build.coopcloud.tech/coop-cloud/backup-bot-two)
+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/).
 
-_This Time, It's Easily Configurable_
 
-Automatically take backups from running Docker Swarm services into a volume.
+## 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
+set -a && source .env && set +a
- - Backups require services to be stopped to take consistent copies
+```
 
-Backupbot II tries to help, by
+Set the secrets.
-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
+```
+printf "SECRET_HERE" | docker secret create SECRET_NAME -
+```
 
-### With Co-op Cloud
+Deploy using the `-c` flag to specify one or multiple compose files.
 
-1. Set up Docker Swarm and [`abra`][abra]
+```
-2. `abra app new backup-bot-two`
+docker stack deploy backup-bot-two -c compose.yaml
-3. `abra app config <your-app-name>`, and set storage options. Either configure `CRON_SCHEDULE`, or set up `swarm-cronjob`
+```
-4. `abra app secret generate <your-app-name> restic-password v1`, optionally with `--pass` before `<your-app-name>` to save the generated secret in `pass`.
-5. `abra app secret insert <your-app-name> ssh-key v1 ...` or similar, to load required secrets.
-4. `abra app deploy <your-app-name>`
 
-<!-- metadata -->
+## Push notifications
 
-* **Category**: Utilities
+The following env variables can be used to setup push notifications for backups. `PUSH_URL_START` is requested just before the backups starts, `PUSH_URL_SUCCESS` is only requested if the backup was successful and if the backup fails `PUSH_URL_FAIL` will be requested.
-* **Status**: 0, work-in-progress
+Each variable is optional and independent of the other.
-* **Image**: [`thecoopcloud/backup-bot-two`](https://hub.docker.com/r/thecoopcloud/backup-bot-two), 4, upstream
+```
-* **Healthcheck**: No
-* **Backups**: N/A
-* **Email**: N/A
-* **Tests**: No
-* **SSO**: N/A
 
-<!-- endmetadata -->
+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
+```
 
-## Configuration
+## Commands
 
-Like Traefik, or `swarm-cronjob`, Backupbot II uses access to the Docker socket to read labels from running Docker Swarm services:
+
+- Find the ID or name of the backup container:
+   ```
+   docker ps --filter "name=backup-bot-two_app"
+   ```
+
+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.
+
+   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.
+
+   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.
+
+## Examples
+
+Create a backup:
+
+```
+docker exec -it <container_id_or_name> backup create --host app
+```
+
+Restore a snapshot:
+
+```
+docker exec -it <container_id_or_name> backup restore --snapshot <snapshot_id> --target /path/to/restore
+```
+
+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:
 
 ```
 services:
   db:
     deploy:
       labels:
-        backupbot.backup: "true"
+        backupbot.backup: ${BACKUP:-"true"} 
-        backupbot.backup.pre-hook: 'mysqldump -u root -p"$(cat /run/secrets/db_root_password)" -f /tmp/dump/dump.db'
+        backupbot.backup.pre-hook: 'mysqldump -u root -p"$(cat /run/secrets/db_root_password)" -f /volume_path/dump.db'
-        backupbot.backup.post-hook: "rm -rf /tmp/dump/dump.db"
+        backupbot.backup.post-hook: "rm -rf /volume_path/dump.db"
-        backupbot.backup.path: "/tmp/dump/,/etc/foo/"
 ```
 
 - `backupbot.backup` -- set to `true` to back up this service (REQUIRED)
-- `backupbot.backup.path` -- comma separated list of file paths within the service to copy (REQUIRED)
+- `backupbot.backup.pre-hook` -- command to run before copying files (optional), save all dumps into the volumes
-- `backupbot.backup.pre-hook` -- command to run before copying files (optional)
 - `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.
-
-## Development
-
-1. Install `direnv`
-2. `cp .envrc.sample .envrc`
-3. Edit `.envrc` as appropriate, including setting `DOCKER_CONTEXT` to a remote Docker context, if you're not running a swarm server locally.
-4. Run `./backup.sh` -- you can add the `--skip-backup` or `--skip-upload` options if you just want to test one other step
-
-[abra]: https://git.autonomic.zone/autonomic-cooperative/abra

backup.sh

@@ -1,126 +0,0 @@
-#!/bin/bash
-
-server_name="${SERVER_NAME:?SERVER_NAME not set}"
-
-restic_password_file="${RESTIC_PASSWORD_FILE:?RESTIC_PASSWORD_FILE not set}"
-
-restic_host="${RESTIC_HOST:?RESTIC_HOST not set}"
-
-backup_path="${BACKUP_DEST:?BACKUP_DEST not set}"
-
-# shellcheck disable=SC2153
-ssh_key_file="${SSH_KEY_FILE}"
-s3_key_file="${AWS_SECRET_ACCESS_KEY_FILE}"
-
-restic_repo=
-restic_extra_options=
-
-if [ -n "$ssh_key_file" ] && [ -f "$ssh_key_file" ]; then
-	restic_repo="sftp:$restic_host:/$server_name"
-
-	# Only check server against provided SSH_HOST_KEY, if set
-	if [ -n "$SSH_HOST_KEY" ]; then
-		tmpfile=$(mktemp)
-		echo "$SSH_HOST_KEY" >>"$tmpfile"
-		echo "using host key $SSH_HOST_KEY"
-		ssh_options="-o 'UserKnownHostsFile $tmpfile'"
-	elif [ "$SSH_HOST_KEY_DISABLE" = "1" ]; then
-		echo "disabling SSH host key checking"
-		ssh_options="-o 'StrictHostKeyChecking=No'"
-	else
-		echo "neither SSH_HOST_KEY nor SSH_HOST_KEY_DISABLE set"
-	fi
-	restic_extra_options="sftp.command=ssh $ssh_options -i $ssh_key_file $restic_host -s sftp"
-fi
-
-if [ -n "$s3_key_file" ] && [ -f "$s3_key_file" ] && [ -n "$AWS_ACCESS_KEY_ID" ]; then
-	AWS_SECRET_ACCESS_KEY="$(cat "${s3_key_file}")"
-	export AWS_SECRET_ACCESS_KEY
-	restic_repo="s3:$restic_host:/$server_name"
-fi
-
-if [ -z "$restic_repo" ]; then
-	echo "you must configure either SFTP or S3 storage, see README"
-	exit 1
-fi
-
-echo "restic_repo: $restic_repo"
-
-# Pre-bake-in some default restic options
-_restic() {
-	if [ -z "$restic_extra_options" ]; then
-		# shellcheck disable=SC2068
-		restic -p "$restic_password_file" \
-			--quiet -r "$restic_repo" \
-			$@
-	else
-		# shellcheck disable=SC2068
-		restic -p "$restic_password_file" \
-			--quiet -r "$restic_repo" \
-			-o "$restic_extra_options" \
-			$@
-	fi
-}
-
-if [ -n "$SERVICES_OVERRIDE" ]; then
-	# this is fine because docker service names should never include spaces or
-	# glob characters
-	# shellcheck disable=SC2206
-	services=($SERVICES_OVERRIDE)
-else
-	mapfile -t services < <(docker service ls --format '{{ .Name }}')
-fi
-
-if [[ \ $*\  != *\ --skip-backup\ * ]]; then
-    rm -rf "${backup_path}"
-
-	for service in "${services[@]}"; do
-		echo "service: $service"
-		details=$(docker service inspect "$service" --format "{{ json .Spec.Labels }}")
-		if echo "$details" | jq -r '.["backupbot.backup"]' | grep -q 'true'; then
-			pre=$(echo "$details" | jq -r '.["backupbot.backup.pre-hook"]')
-			post=$(echo "$details" | jq -r '.["backupbot.backup.post-hook"]')
-			path=$(echo "$details" | jq -r '.["backupbot.backup.path"]')
-
-			if [ "$path" = "null" ]; then
-				echo "ERROR: missing 'path' for $service"
-				continue # or maybe exit?
-			fi
-
-			container=$(docker container ls -f "name=$service" --format '{{ .ID }}')
-
-			echo "backing up $service"
-
-			if [ "$pre" != "null" ]; then
-				# run the precommand
-				# shellcheck disable=SC2086
-				docker exec "$container" sh -c "$pre"
-			fi
-
-			# run the backup
-			for p in ${path//,/ }; do
-				# creates the parent folder, so `docker cp` has reliable behaviour no matter if $p ends with `/` or `/.`
-				dir=$backup_path/$service/$(dirname "$p")
-				test -d "$dir" || mkdir -p "$dir"
-				docker cp -a "$container:$p" "$dir/$(basename "$p")"
-			done
-
-			if [ "$post" != "null" ]; then
-				# run the postcommand
-				# shellcheck disable=SC2086
-				docker exec "$container" sh -c "$post"
-			fi
-		fi
-	done
-
-	# check if restic repo exists, initialise if not
-	if [ -z "$(_restic cat config)" ] 2>/dev/null; then
-		echo "initializing restic repo"
-		_restic init
-	fi
-fi
-
-if [[ \ $*\  != *\ --skip-upload\ * ]]; then
-	_restic backup --host "$server_name" --tag coop-cloud "$backup_path"
-fi
-

backupbot.py

@@ -0,0 +1,369 @@
+#!/usr/bin/python3
+
+import os
+import sys
+import click
+import json
+import subprocess
+import logging
+import docker
+import restic
+import tarfile
+import io
+from pythonjsonlogger import jsonlogger
+from datetime import datetime, timezone
+from restic.errors import ResticFailedError
+from pathlib import Path
+from shutil import copyfile, rmtree
+
+VOLUME_PATH = "/var/lib/docker/volumes/"
+SECRET_PATH = '/secrets/'
+SERVICE = None
+
+logger = logging.getLogger("backupbot")
+logging.addLevelName(55, 'SUMMARY')
+setattr(logging, 'SUMMARY', 55)
+setattr(logger, 'summary', lambda message, *args, **
+        kwargs: logger.log(55, message, *args, **kwargs))
+
+
+def handle_exception(exc_type, exc_value, exc_traceback):
+    if issubclass(exc_type, KeyboardInterrupt):
+        sys.__excepthook__(exc_type, exc_value, exc_traceback)
+        return
+    logger.critical("Uncaught exception", exc_info=(
+        exc_type, exc_value, exc_traceback))
+
+
+sys.excepthook = handle_exception
+
+
+@click.group()
+@click.option('-l', '--log', 'loglevel')
+@click.option('-m', '--machine-logs', 'machine_logs', is_flag=True)
+@click.option('service', '--host', '-h', envvar='SERVICE')
+@click.option('repository', '--repo', '-r', envvar='RESTIC_REPOSITORY')
+def cli(loglevel, service, repository, machine_logs):
+    global SERVICE
+    if service:
+        SERVICE = service.replace('.', '_')
+    if repository:
+        os.environ['RESTIC_REPOSITORY'] = repository
+    if loglevel:
+        numeric_level = getattr(logging, loglevel.upper(), None)
+        if not isinstance(numeric_level, int):
+            raise ValueError('Invalid log level: %s' % loglevel)
+        logger.setLevel(numeric_level)
+    if machine_logs:
+        logHandler = logging.StreamHandler()
+        formatter = jsonlogger.JsonFormatter(
+            "%(levelname)s %(filename)s %(lineno)s %(process)d %(message)s", rename_fields={"levelname": "message_type"})
+        logHandler.setFormatter(formatter)
+        logger.addHandler(logHandler)
+
+    export_secrets()
+    init_repo()
+
+
+def init_repo():
+    repo = os.environ['RESTIC_REPOSITORY']
+    logger.debug(f"set restic repository location: {repo}")
+    restic.repository = repo
+    restic.password_file = '/var/run/secrets/restic_password'
+    try:
+        restic.cat.config()
+    except ResticFailedError as error:
+        if 'unable to open config file' in str(error):
+            result = restic.init()
+            logger.info(f"Initialized restic repo: {result}")
+        else:
+            raise error
+
+
+def export_secrets():
+    for env in os.environ:
+        if env.endswith('FILE') and not "COMPOSE_FILE" in env:
+            logger.debug(f"exported secret: {env}")
+            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']
+
+
+@cli.command()
+@click.option('retries', '--retries', '-r', envvar='RETRIES', default=1)
+def create(retries):
+    pre_commands, post_commands, backup_paths, apps = get_backup_cmds()
+    copy_secrets(apps)
+    backup_paths.append(SECRET_PATH)
+    run_commands(pre_commands)
+    backup_volumes(backup_paths, apps, int(retries))
+    run_commands(post_commands)
+
+
+def get_backup_cmds():
+    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 = {}
+    services = client.services.list()
+    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']
+            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")
+                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)
+
+
+def copy_secrets(apps):
+    # TODO: check if it is deployed
+    rmtree(SECRET_PATH, ignore_errors=True)
+    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()}
+    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(
+                    f"Container {s.name} is not running, secrets can not be copied.")
+                continue
+            container_id = container_by_service[s.name].id
+            for sec in app_secs:
+                src = f'/var/lib/docker/containers/{container_id}/mounts/secrets/{sec["SecretID"]}'
+                if not Path(src).exists():
+                    logger.error(
+                        f"For the secret {sec['SecretName']} the file {src} does not exist for {s.name}")
+                    continue
+                dst = SECRET_PATH + sec['SecretName']
+                copyfile(src, dst)
+
+
+def run_commands(commands):
+    for container, command in commands.items():
+        if not command:
+            continue
+        # Remove bash/sh wrapping
+        command = command.removeprefix('bash -c').removeprefix('sh -c').removeprefix(' ')
+        # Remove quotes surrounding the command
+        if (len(command) >= 2 and command[0] == command[-1] and (command[0] == "'" or command[0] == '"')):
+            command = command[1:-1]
+        # Use bash's pipefail to return exit codes inside a pipe to prevent silent failure
+        command = f"bash -c 'set -o pipefail;{command}'"
+        logger.info(f"run command in {container.name}:")
+        logger.info(command)
+        result = container.exec_run(command)
+        if result.exit_code:
+            logger.error(
+                f"Failed to run command {command} in {container.name}: {result.output.decode()}")
+        else:
+            logger.info(result.output.decode())
+
+
+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.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(error, exc_info=True)
+            if retries > 0:
+                retries -= 1
+            else:
+                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)
+
+
+@cli.command()
+def snapshots():
+    snapshots = restic.snapshots()
+    no_snapshots = True
+    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:
+        err_msg = "No Snapshots found"
+        if SERVICE:
+            service_name = SERVICE.replace('_', '.')
+            err_msg += f' for app {service_name}'
+        logger.warning(err_msg)
+
+
+@cli.command()
+@click.option('snapshot', '--snapshot', '-s', envvar='SNAPSHOT', default='latest')
+@click.option('path', '--path', '-p', envvar='INCLUDE_PATH')
+def ls(snapshot, path):
+    results = list_files(snapshot, path)
+    for r in results:
+        if r.get('path'):
+            print(f"{r['ctime']}\t{r['path']}")
+
+
+def list_files(snapshot, path):
+    cmd = restic.cat.base_command() + ['ls']
+    if SERVICE:
+        cmd = cmd + ['--tag', SERVICE]
+    cmd.append(snapshot)
+    if path:
+        cmd.append(path)
+    try:
+        output = restic.internal.command_executor.execute(cmd)
+    except ResticFailedError as error:
+        if 'no snapshot found' in str(error):
+            err_msg = f'There is no snapshot "{snapshot}"'
+            if SERVICE:
+                err_msg += f' for the app "{SERVICE}"'
+            logger.error(err_msg)
+            exit(1)
+        else:
+            raise error
+    output = output.replace('}\n{', '}|{')
+    results = list(map(json.loads, output.split('|')))
+    return results
+
+
+@cli.command()
+@click.option('snapshot', '--snapshot', '-s', envvar='SNAPSHOT', default='latest')
+@click.option('path', '--path', '-p', envvar='INCLUDE_PATH')
+@click.option('volumes', '--volumes', '-v', envvar='VOLUMES')
+@click.option('secrets', '--secrets', '-c', is_flag=True, envvar='SECRETS')
+def download(snapshot, path, volumes, secrets):
+    file_dumps = []
+    if not any([path, volumes, secrets]):
+        volumes = secrets = True
+    if path:
+        path = path.removesuffix('/')
+        binary_output = dump(snapshot, path)
+        files = list_files(snapshot, path)
+        filetype = [f.get('type') for f in files if f.get('path') == path][0]
+        filename = Path(path).name
+        if filetype == 'dir':
+            filename = filename + ".tar"
+        tarinfo = tarfile.TarInfo(name=filename)
+        tarinfo.size = len(binary_output)
+        file_dumps.append((binary_output, tarinfo))
+    if volumes:
+        if not SERVICE:
+            logger.error("Please specify '--host' when using '--volumes'")
+            exit(1)
+        files = list_files(snapshot, VOLUME_PATH)
+        for f in files[1:]:
+            path = f['path']
+            if Path(path).name.startswith(SERVICE) and f['type'] == 'dir':
+                binary_output = dump(snapshot, path)
+                filename = f"{Path(path).name}.tar"
+                tarinfo = tarfile.TarInfo(name=filename)
+                tarinfo.size = len(binary_output)
+                file_dumps.append((binary_output, tarinfo))
+    if secrets:
+        if not SERVICE:
+            logger.error("Please specify '--host' when using '--secrets'")
+            exit(1)
+        filename = f"{SERVICE}.json"
+        files = list_files(snapshot, SECRET_PATH)
+        secrets = {}
+        for f in files[1:]:
+            path = f['path']
+            if Path(path).name.startswith(SERVICE) and f['type'] == 'file':
+                secret = dump(snapshot, path).decode()
+                secret_name = path.removeprefix(f'{SECRET_PATH}{SERVICE}_')
+                secrets[secret_name] = secret
+        binary_output = json.dumps(secrets).encode()
+        tarinfo = tarfile.TarInfo(name=filename)
+        tarinfo.size = len(binary_output)
+        file_dumps.append((binary_output, tarinfo))
+    with tarfile.open('/tmp/backup.tar.gz', "w:gz") as tar:
+        print(f"Writing files to /tmp/backup.tar.gz...")
+        for binary_output, tarinfo in file_dumps:
+            tar.addfile(tarinfo, fileobj=io.BytesIO(binary_output))
+    size = get_formatted_size('/tmp/backup.tar.gz')
+    print(
+        f"Backup has been written to /tmp/backup.tar.gz with a size of {size}")
+
+
+def get_formatted_size(file_path):
+    file_size = os.path.getsize(file_path)
+    units = ['Bytes', 'KB', 'MB', 'GB', 'TB']
+    for unit in units:
+        if file_size < 1024:
+            return f"{round(file_size, 3)} {unit}"
+        file_size /= 1024
+    return f"{round(file_size, 3)} {units[-1]}"
+
+
+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}'")
+    output = subprocess.run(cmd, capture_output=True)
+    if output.returncode:
+        logger.error(
+            f"error while dumping {path} from snapshot '{snapshot}': {output.stderr}")
+        exit(1)
+    return output.stdout
+
+
+if __name__ == '__main__':
+    cli()

compose.s3.yml

@@ -1,14 +0,0 @@
----
-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.ssh.yml

@@ -1,16 +0,0 @@
----
-version: "3.8"
-services:
-  app:
-    environment:
-      - SSH_KEY_FILE=/run/secrets/ssh_key
-      - SSH_HOST_KEY
-      - SSH_HOST_KEY_DISABLE
-    secrets:
-      - source: ssh_key
-        mode: 0400
-
-secrets:
-  ssh_key:
-    external: true
-    name: ${STACK_NAME}_ssh_key_${SECRET_SSH_KEY_VERSION}

compose.swarm-cronjob.yml

@@ -1,15 +0,0 @@
----
-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

@@ -0,0 +1,44 @@
+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

@@ -1,29 +0,0 @@
----
-version: "3.8"
-services:
-  app:
-    image: thecoopcloud/backup-bot-two:latest
-    build: .
-    volumes:
-      - "/var/run/docker.sock:/var/run/docker.sock"
-      - "backups:/backups"
-    environment:
-      - CRON_SCHEDULE
-      - RESTIC_REPO
-      - RESTIC_PASSWORD_FILE=/run/secrets/restic_password
-      - BACKUP_DEST=/backups
-      - RESTIC_HOST
-      - SERVER_NAME
-    secrets:
-      - restic_password
-    deploy:
-      labels:
-        - coop-cloud.${STACK_NAME}.app.version=
-
-volumes:
-  backups:
-
-secrets:
-  restic_password:
-    external: true
-    name: ${STACK_NAME}_restic_password_${SECRET_RESTIC_PASSWORD_VERSION}

entrypoint.sh

@@ -0,0 +1,30 @@
+#!/bin/sh
+
+set -e -o pipefail
+
+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
+
+cron_schedule="${CRON_SCHEDULE:?CRON_SCHEDULE not set}"
+
+if [ -n "$PUSH_URL_START" ]
+then
+    push_start_notification="curl -s '$PUSH_URL_START' &&"
+fi
+
+if [ -n "$PUSH_URL_FAIL" ]
+then
+    push_fail_notification="|| curl -s '$PUSH_URL_FAIL'"
+fi
+
+if [ -n "$PUSH_URL_SUCCESS" ]
+then
+    push_notification=" && (grep -q 'backup finished' /tmp/backup.log && curl -s '$PUSH_URL_SUCCESS' $push_fail_notification)"
+fi
+
+echo "$cron_schedule $push_start_notification backup --machine-logs create  2>&1 | tee /tmp/backup.log $push_notification" | crontab -
+crontab -l
+
+crond -f -d8 -L /dev/stdout

setup-cron.sh

@@ -1,11 +0,0 @@
-#!/bin/bash
-
-set -e
-set -o pipefail
-
-cron_schedule="${CRON_SCHEDULE:?CRON_SCHEDULE not set}"
-
-echo "$cron_schedule /usr/bin/backup.sh" | crontab -
-crontab -l
-
-crond -f -d8 -L /dev/stdout