Switch to abra-bot for deployment

Re toolshed/organising#668

.drone.yml

@@ -2,27 +2,16 @@
 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: abra-bot
-      username: thecoopcloud
       password:
-        from_secret: thecoopcloud_password
+        from_secret: git_coopcloud_tech_token_abra_bot
-      repo: thecoopcloud/backup-bot-two
+      repo: git.coopcloud.tech/coop-cloud/backup-bot-two
-      tags: latest
+      tags: ${DRONE_SEMVER_BUILD}
-    depends_on:
+      registry: git.coopcloud.tech
-      - run shellcheck
     when:
       event:
-        exclude:
+        include:
-          - pull_request
+          - tag
-
-trigger:
-  branch:
-    - main

.env.sample

@@ -4,10 +4,20 @@ SECRET_RESTIC_PASSWORD_VERSION=v1
 
 COMPOSE_FILE=compose.yml
 
-SERVER_NAME=example.com
+RESTIC_REPOSITORY=/backups/restic
-RESTIC_HOST=minio.example.com
 
-CRON_SCHEDULE='*/5 * * * *'
+CRON_SCHEDULE='30 3 * * *'
+
+# Push Notifiactions
+#PUSH_PROMETHEUS_URL=https://pushgateway.example.com/metrics/job/backup
+# or
+#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
+
+# Push Basic Auth
+#COMPOSE_FILE="$COMPOSE_FILE:compose.pushbasicauth.yml"
+#SECRET_PUSH_BASICAUTH=v1
 
 # swarm-cronjob, instead of built-in cron
 #COMPOSE_FILE="$COMPOSE_FILE:compose.swarm-cronjob.yml"
@@ -21,3 +31,10 @@ CRON_SCHEDULE='*/5 * * * *'
 #SECRET_AWS_SECRET_ACCESS_KEY_VERSION=v1
 #AWS_ACCESS_KEY_ID=something-secret
 #COMPOSE_FILE="$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

@@ -10,6 +10,8 @@ export DOCKER_CONTEXT=$SERVER_NAME
 # 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 @@
-/testing
+.venv

CHANGELOG.md

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

Dockerfile

@@ -1,13 +1,11 @@
-FROM docker:19.03.13-dind
+FROM docker:24.0.7-dind
 
-RUN apk add --upgrade --no-cache \
+RUN apk add --upgrade --no-cache restic bash python3 py3-pip py3-click py3-docker-py py3-json-logger curl
-  bash \
-  curl \
-  jq \
-  restic
 
-COPY backup.sh /usr/bin/backup.sh
+# Todo use requirements file with specific versions
-COPY setup-cron.sh /usr/bin/setup-cron.sh
+RUN pip install --break-system-packages resticpy==1.0.2
-RUN chmod +x /usr/bin/backup.sh /usr/bin/setup-cron.sh
 
-ENTRYPOINT [ "/usr/bin/setup-cron.sh" ]
+COPY backupbot.py /usr/bin/backup
+COPY entrypoint.sh /entrypoint.sh
+
+ENTRYPOINT /entrypoint.sh

README.md

@@ -4,7 +4,21 @@
 
 _This Time, It's Easily Configurable_
 
-Automatically take backups from running Docker Swarm services into a volume.
+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 -->
+
 
 ## Background
 
@@ -20,53 +34,253 @@ Backupbot II tries to help, by
 
 ### With Co-op Cloud
 
-1. Set up Docker Swarm and [`abra`][abra]
-2. `abra app new backup-bot-two`
-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 -->
+* `abra app new backup-bot-two`
-
+* `abra app config <app-name>`
-* **Category**: Utilities
+    - set storage options. Either configure `CRON_SCHEDULE`, or set up `swarm-cronjob`
-* **Status**: 0, work-in-progress
+* `abra app secret generate -a <backupbot_name>`
-* **Image**: [`thecoopcloud/backup-bot-two`](https://hub.docker.com/r/thecoopcloud/backup-bot-two), 4, upstream
+* `abra app deploy <app-name>`
-* **Healthcheck**: No
-* **Backups**: N/A
-* **Email**: N/A
-* **Tests**: No
-* **SSO**: N/A
-
-<!-- endmetadata -->
 
 ## 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:
+```
+RESTIC_REPOSITORY=s3:<S3-SERVICE-URL>/<BUCKET-NAME>
+SECRET_AWS_SECRET_ACCESS_KEY_VERSION=v1
+AWS_ACCESS_KEY_ID=<MY_ACCESS_KEY>
+COMPOSE_FILE="$COMPOSE_FILE:compose.s3.yml"
+```
+and add your `<SECRET_ACCESS_KEY>` as docker secret:
+`abra app secret insert <backupbot_name> aws_secret_access_key v1 <SECRET_ACCESS_KEY>`
+
+See [restic s3 docs](https://restic.readthedocs.io/en/latest/030_preparing_a_new_repo.html#amazon-s3) for more information.
+
+### SFTP Storage
+
+> With sftp it is not possible to prevent the backupbot from deleting backups in case of a compromised machine. Therefore we recommend to use S3, REST or rclone server without delete permissions.
+
+To use SFTP storage as backup location set the following envs:
+```
+RESTIC_REPOSITORY=sftp:user@host:/restic-repo-path
+SECRET_SSH_KEY_VERSION=v1
+SSH_HOST_KEY="hostname ssh-rsa AAAAB3...
+COMPOSE_FILE="$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
+
+It is possible to configure three push events, that may trigger on the backup cronjob. Those can be used to detect failures from mointoring systems.
+The events are:
+- start
+- success
+- fail
+
+### Using a Prometheus Push Gateway
+
+[A prometheus push gateway](https://git.coopcloud.tech/coop-cloud/monitoring-ng#setup-push-gateway) can be used by setting the following env variables:
+- `PUSH_PROMETHEUS_URL=pushgateway.example.com/metrics/job/backup`
+
+### Using custom URLs
+
+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.
+Each variable is optional and independent of the other.
+
+```
+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
+```
+
+### Push endpoint behind basic auth
+
+Insert the basic auth secret
+`abra app secret insert <backupbot_name> push_basicauth v1 "user:password"`
+
+Enable basic auth in the env file, by uncommenting the following line:
+```
+#COMPOSE_FILE="$COMPOSE_FILE:compose.pushbasicauth.yml"
+#SECRET_PUSH_BASICAUTH=v1
+```
+
+## Usage
+
+Run the cronjob that creates a backup, including the push notifications and docker logging:
+`abra app cmd <backupbot_name> app run_cron`
+
+Create a backup of all apps:
+
+`abra app run <backupbot_name> app -- backup create`
+
+> The apps to backup up need to be deployed
+
+Create an individual backup:
+
+`abra app run <backupbot_name> app -- backup --host <target_app_name> create`
+
+Create a backup to a local repository:
+
+`abra app run <backupbot_name> app -- backup create -r /backups/restic`
+
+> It is recommended to shutdown/undeploy an app before restoring the data
+
+Restore the latest snapshot of all including apps:
+
+`abra app run <backupbot_name> app -- backup restore`
+
+Restore a specific snapshot of an individual app:
+
+`abra app run <backupbot_name> app -- backup --host <target_app_name> restore --snapshot <snapshot_id>`
+
+Show all snapshots:
+
+`abra app run <backupbot_name> app -- backup snapshots`
+
+Show all snapshots containing a specific app:
+
+`abra app run <backupbot_name> app -- backup --host <target_app_name> snapshots`
+
+Show all files inside the latest snapshot (can be very verbose):
+
+`abra app run <backupbot_name> app -- backup ls`
+
+Show specific files inside a selected snapshot:
+
+`abra app run <backupbot_name> app -- backup ls --snapshot <snapshot_id> /var/lib/docker/volumes/`
+
+Download files from a snapshot:
+
+```
+filename=$(abra app run <backupbot_name> app -- backup download --snapshot <snapshot_id> --path <absolute_path>)
+abra app cp <backupbot_name> app:$filename .
+```
+
+## Run restic
+
+```
+abra app run <backupbot_name> app bash
+export AWS_SECRET_ACCESS_KEY=$(cat $AWS_SECRET_ACCESS_KEY_FILE)
+export RESTIC_PASSWORD=$(cat $RESTIC_PASSWORD_FILE)
+restic snapshots
+```
+
+## Recipe Configuration
+
 Like Traefik, or `swarm-cronjob`, Backupbot II uses access to the Docker socket to read labels from running Docker Swarm services:
 
+1. Add `ENABLE_BACKUPS=true` to .env.sample
+
+2. Add backupbot labels to the compose file
+
 ```
 services:
   db:
     deploy:
       labels:
-        backupbot.backup: "true"
+        backupbot.backup: "${ENABLE_BACKUPS:-true}"
-        backupbot.backup.pre-hook: 'mysqldump -u root -p"$(cat /run/secrets/db_root_password)" -f /tmp/dump/dump.db'
+        backupbot.backup.pre-hook: "/pg_backup.sh backup"
-        backupbot.backup.post-hook: "rm -rf /tmp/dump/dump.db"
+        backupbot.backup.volumes.db.path: "backup.sql"
-        backupbot.backup.path: "/tmp/dump/,/etc/foo/"
+        backupbot.restore.post-hook: '/pg_backup.sh restore'
+        backupbot.backup.volumes.redis: "false"
 ```
 
 - `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)
+    - this is the only required backup label, per default it will backup all volumes
-- `backupbot.backup.pre-hook` -- command to run before copying files (optional)
+- `backupbot.backup.volumes.<volume_name>.path` -- only backup the listed relative paths from `<volume_name>`
-- `backupbot.backup.post-hook` -- command to run after copying files (optional)
+- `backupbot.backup.volumes.<volume_name>: false` -- exclude <volume_name> from the backup
+- `backupbot.backup.pre-hook` -- command to run before copying files
+    - i.e. save all database dumps into the volumes
+- `backupbot.backup.post-hook` -- command to run after copying files
+- `backupbot.restore.pre-hook` -- command to run before restoring files
+- `backupbot.restore.post-hook` -- command to run after restoring files
+    - i.e. read all database dumps from the volumes
+
+3. (Optional) add backup/restore scripts to the compose file
+
+```
+services:
+  db:
+    configs:
+        - source: pg_backup
+          target: /pg_backup.sh
+          mode: 0555
+
+
+configs:
+  pg_backup:
+    name: ${STACK_NAME}_pg_backup_${PG_BACKUP_VERSION}
+    file: pg_backup.sh
+```
+
+Version the config file in `abra.sh`:
+
+```
+export PG_BACKUP_VERSION=v1
+```
 
 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
+
+## Backupbot Development
+
+1. Copy modified backupbot.py into the container:
+
+```
+cp backupbot.py /tmp/backupbot.py; git stash; abra app cp <backupbot_name> /tmp/backupbot.py app:/usr/bin/backupbot.py; git checkout main; git stash pop
+```
+
+2. Testing stuff with the python interpreter inside the container:
+
+```
+abra app run <backupbot_name> app bash
+cd /usr/bin/
+python
+from backupbot import *
+```
+
+### Versioning
+
+- App version: changes to `backup.py` (build a new image)
+- Co-op Cloud package version: changes to recipe.
+
+        For example, starting with 1.0.0+2.0.0:
+            "patch" change to recipe: 1.0.1+2.0.0
+            "patch" change to backup.py: increment both, so 1.1.0+2.0.1
+                   because bumping the image version would result in a minor recipe release
+
+https://git.coopcloud.tech/coop-cloud/backup-bot-two/issues/4

abra.sh

@@ -0,0 +1,11 @@
+export SSH_CONFIG_VERSION=v1
+export ENTRYPOINT_VERSION=v17
+export CRONJOB_VERSION=v2
+
+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 -
+}

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 +1,649 @@
+#!/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 = "ALL"
+
+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, envvar="MACHINE_LOGS"
+)
+@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)
+    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)
+    logger.addHandler(logHandler)
+
+    export_secrets()
+    init_repo()
+
+
+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"]
+        restic.repository = repo
+    logger.debug(f"set restic repository location: {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
+                # logger.debug(f"Read secret value: {secret}")
+
+
+@cli.command()
+@click.option("retries", "--retries", "-r", envvar="RETRIES", default=1)
+def create(retries):
+    app_settings = parse_backup_labels()
+    pre_commands, post_commands, backup_paths, apps_versions = get_backup_details(
+        app_settings
+    )
+    copy_secrets(apps_versions)
+    backup_paths.append(Path(SECRET_PATH))
+    run_commands(pre_commands)
+    backup_volumes(backup_paths, apps_versions, int(retries))
+    run_commands(post_commands)
+
+
+@cli.command()
+@click.option("snapshot_id", "--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_id, target, noninteractive, volumes, container, no_commands):
+    app_settings = parse_backup_labels("restore", container)
+    if SERVICE != "ALL":
+        if not app_settings.get(SERVICE):
+            logger.error(
+                f"The app {SERVICE} is not running, use the restore-path argument to restore paths of undeployed apps"
+            )
+            exit(1)
+        app_settings = {SERVICE: app_settings.get(SERVICE)}
+    pre_commands, post_commands, backup_paths, apps_versions = get_backup_details(
+        app_settings, volumes
+    )
+    snapshots = get_snapshots(snapshot_id)
+    if not snapshots:
+        logger.error(
+            f"No Snapshots with ID {snapshot_id} for {apps_versions.keys()} found."
+        )
+        exit(1)
+    snapshot = snapshots[0]
+    snapshot_id = snapshot["short_id"]
+    if not noninteractive:
+        print(f"Snapshot to restore: \t{snapshot_id}")
+        restore_app_versions = app_versions_from_tags(snapshot.get("tags"))
+        print("Apps:")
+        for app, version in apps_versions.items():
+            restore_version = restore_app_versions.get(app)
+            print(f"\t{app} \t {restore_version}")
+            if version != restore_version:
+                print(f"WARNING!!! The running app is deployed with version {version}")
+        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}")
+        snapshot_date = datetime.fromisoformat(snapshot["time"])
+        delta = datetime.now(tz=timezone.utc) - snapshot_date
+        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_id} at {target}")
+    if not no_commands and pre_commands:
+        print(f"Run pre commands.")
+        run_commands(pre_commands)
+    if backup_paths:
+        result = restic_restore(
+            snapshot_id=snapshot_id, include=backup_paths, target_dir=target
+        )
+        logger.debug(result)
+    else:
+        print("No paths to restore.")
+    if not no_commands and post_commands:
+        print(f"Run post commands.")
+        run_commands(post_commands)
+
+
+@cli.command()
+@click.option("snapshot_id", "--snapshot", "-s", envvar="SNAPSHOT", default="latest")
+@click.option("target", "--target", "-t", envvar="TARGET", default="/")
+@click.option(
+    "noninteractive", "--noninteractive", envvar="NONINTERACTIVE", is_flag=True
+)
+@click.argument("paths", nargs=-1, required=True, envvar="INCLUDE_PATH")
+def restore_path(snapshot_id, target, noninteractive, paths):
+    """PATHS: list of paths to restore"""
+    snapshots = get_snapshots(snapshot_id)
+    if not snapshots:
+        logger.error(f"No Snapshots with ID {snapshot_id} for app {SERVICE} found.")
+        exit(1)
+    snapshot = snapshots[0]
+    snapshot_id = snapshot["short_id"]
+    if not noninteractive:
+        print(f"Snapshot to restore: \t{snapshot_id}")
+        restore_app_versions = app_versions_from_tags(snapshot.get("tags"))
+        print("Apps:")
+        for app, version in restore_app_versions.items():
+            if SERVICE == "ALL" or SERVICE == app:
+                print(f"\t{app} \t {version}")
+        print("The following paths will be restored:")
+        for p in paths:
+            print(f"\t{p}")
+        snapshot_date = datetime.fromisoformat(snapshot["time"])
+        delta = datetime.now(tz=timezone.utc) - snapshot_date
+        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_id} at {target}")
+    result = restic_restore(snapshot_id=snapshot_id, include=paths, target_dir=target)
+    logger.debug(result)
+
+
+def restic_restore(snapshot_id, 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 not SERVICE in app_versions_from_tags(snapshots[0].get("tags")):
+            logger.error(f"Snapshot with ID {snapshot_id} does not contain {SERVICE}")
+            exit(1)
+    else:
+        snapshots = restic.snapshots()
+        snapshots = list(
+            filter(
+                lambda x: SERVICE in app_versions_from_tags(x.get("tags")), snapshots
+            )
+        )
+    if snapshot_id == "latest":
+        return snapshots[-1:]
+    else:
+        return snapshots
+
+
+def app_versions_from_tags(tags):
+    if tags:
+        app_versions = map(lambda x: x.split(":"), tags)
+        return {i[0]: i[1] if len(i) > 1 else None for i in app_versions}
+    else:
+        return {}
+
+
+def str2bool(value: str) -> bool:
+    return value.lower() in ("yes", "true", "t", "1")
+
+
+def parse_backup_labels(hook_type="backup", selected_container=[]):
+    client = docker.from_env()
+    container_by_service = {
+        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:
+        specs = s.attrs["Spec"]
+        labels = specs["Labels"]
+        stack_name = labels["com.docker.stack.namespace"]
+        container_name = s.name.removeprefix(f"{stack_name}_")
+        version = labels.get(f"coop-cloud.{stack_name}.version")
+        settings = app_settings[stack_name] = app_settings.get(stack_name) or {}
+        if (backup := labels.get("backupbot.backup")) and str2bool(backup):
+            settings["enabled"] = True
+        if version:
+            settings["version"] = version
+        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 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_versions = {}
+    pre_hooks = {}
+    post_hooks = {}
+    for app, settings in app_settings.items():
+        if settings.get("enabled"):
+            if SERVICE != "ALL" and SERVICE != app:
+                continue
+            backup_apps_versions[app] = settings.get("version")
+            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_versions
+
+
+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} for {app}"
+                    )
+                    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 not str2bool(value):
+                excluded_volumes.add(volume_name)
+    return excluded_volumes, included_volume_paths
+
+
+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.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.warning(
+                    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"]
+                logger.debug(f"Copy Secret {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.debug(result.output.decode())
+
+
+def backup_volumes(backup_paths, apps_versions, retries, dry_run=False):
+    while True:
+        try:
+            logger.info("Backup these paths:")
+            logger.info("\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 = [f"{app}:{version}" for app, version in apps_versions.items()]
+            if SERVICE == "ALL":
+                tags.append(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 {SERVICE}.")
+            logger.error(error, exc_info=True)
+            if retries > 0:
+                retries -= 1
+            else:
+                exit(1)
+
+
+def path_exists(path):
+    if not path.exists():
+        logger.error(f"{path} does not exist")
+    return path.exists()
+
+
+@cli.command()
+def snapshots():
+    snapshots = get_snapshots()
+    for snap in snapshots:
+        output = [snap["time"].split(".")[0], snap["short_id"]]
+        if tags := snap.get("tags"):
+            app_versions = app_versions_from_tags(tags)
+            if version := app_versions.get(SERVICE):
+                output.append(version)
+        print(*output)
+    if not snapshots:
+        err_msg = "No Snapshots found"
+        if SERVICE != "ALL":
+            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("show_all", "--all", "-a", envvar="SHOW_ALL", is_flag=True)
+@click.option("timestamps", "--timestamps", "-t", envvar="TIMESTAMPS", is_flag=True)
+@click.argument(
+    "path", required=False, default="/var/lib/docker/volumes/", envvar="INCLUDE_PATH"
+)
+def ls(snapshot, show_all, timestamps, path):
+    if snapshot == "latest":
+        latest_snapshot = get_snapshots("latest")
+        if not latest_snapshot:
+            logger.error(f"There is no latest snapshot for {SERVICE}")
+            exit(1)
+        snapshot = latest_snapshot[0]["short_id"]
+    if show_all:
+        path = None
+    results = list_files(snapshot, path)
+    for r in results:
+        if r.get("path"):
+            if timestamps:
+                print(f"{r['ctime']}\t{r['path']}")
+            else:
+                print(f"{r['path']}")
+
+
+def list_files(snapshot, path):
+    cmd = restic.cat.base_command() + ["ls"]
+    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 != "ALL":
+                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 snapshot == "latest":
+        latest_snapshot = get_snapshots("latest")
+        if not latest_snapshot:
+            logger.error(f"There is no latest snapshot for {SERVICE}")
+            exit(1)
+        snapshot = latest_snapshot[0]["short_id"]
+    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 SERVICE == "ALL":
+            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 SERVICE == "ALL":
+            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"]
+    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.pushbasicauth.yml

@@ -0,0 +1,11 @@
+---
+version: "3.8"
+services:
+  app:
+    secrets:
+      - push_basicauth
+
+secrets:
+  push_basicauth:
+    external: true
+    name: ${STACK_NAME}_push_basicauth_${SECRET_PUSH_BASICAUTH}

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

@@ -5,12 +5,19 @@ services:
     environment:
       - SSH_KEY_FILE=/run/secrets/ssh_key
       - SSH_HOST_KEY
-      - SSH_HOST_KEY_DISABLE
     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.yml

@@ -2,28 +2,50 @@
 version: "3.8"
 services:
   app:
-    image: thecoopcloud/backup-bot-two:latest
+    image: git.coopcloud.tech/coop-cloud/backup-bot-two:2.3.0-beta
-    build: .
     volumes:
       - "/var/run/docker.sock:/var/run/docker.sock"
-      - "backups:/backups"
+      - "/var/lib/docker/volumes/:/var/lib/docker/volumes/"
+      - "/var/lib/docker/containers/:/var/lib/docker/containers/:ro"
+      - backups:/backups
     environment:
       - CRON_SCHEDULE
-      - RESTIC_REPO
+      - RESTIC_REPOSITORY
       - RESTIC_PASSWORD_FILE=/run/secrets/restic_password
-      - BACKUP_DEST=/backups
-      - RESTIC_HOST
-      - SERVER_NAME
     secrets:
       - restic_password
+    configs:
+      - source: entrypoint
+        target: /entrypoint.sh
+        mode: 666
+      - source: cronjob
+        target: /cronjob.sh
+        mode: 666
     deploy:
       labels:
-        - coop-cloud.${STACK_NAME}.app.version=
+        - coop-cloud.${STACK_NAME}.version=2.3.0+2.3.0-beta
-
+        - coop-cloud.${STACK_NAME}.timeout=${TIMEOUT:-300}
-volumes:
+        - coop-cloud.backupbot.enabled=true
-  backups:
+    #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}
+
+configs:
+  entrypoint:
+    name: ${STACK_NAME}_entrypoint_${ENTRYPOINT_VERSION}
+    file: entrypoint.sh
+  cronjob:
+    name: ${STACK_NAME}_cronjob_${CRONJOB_VERSION}
+    file: cronjob.sh
+
+volumes:
+  backups:

cronjob.sh

@@ -0,0 +1,40 @@
+#!/bin/sh
+
+set -e
+
+CURL_OPTS="-s"
+# Check for basic auth
+if [ -n "$(cat /run/secrets/push_basicauth)" ]
+then
+    CURL_OPTS="$CURL_OPTS -u $(cat /run/secrets/push_basicauth)"
+fi
+
+if [ -n "$PUSH_PROMETHEUS_URL" ]
+then
+    push_start_notification="(echo 'backup 1' | curl $CURL_OPTS --data-binary @- $PUSH_PROMETHEUS_URL)"
+    push_success_notification="(echo 'backup 0' | curl $CURL_OPTS --data-binary @- $PUSH_PROMETHEUS_URL)"
+    push_fail_notification="(echo 'backup -1' | curl $CURL_OPTS --data-binary @- $PUSH_PROMETHEUS_URL)"
+else
+    if [ -n "$PUSH_URL_START" ]
+    then
+        push_start_notification="curl $CURL_OPTS '$PUSH_URL_START'"
+    fi
+
+    if [ -n "$PUSH_URL_FAIL" ]
+    then
+        push_fail_notification="curl $CURL_OPTS '$PUSH_URL_FAIL'"
+    fi
+
+    if [ -n "$PUSH_URL_SUCCESS" ]
+    then
+        push_success_notification="curl $CURL_OPTS '$PUSH_URL_SUCCESS'"
+    fi
+fi
+
+eval "$push_start_notification"
+if [ "$(backup --machine-logs create  2>&1 | tee /tmp/backup.log && (grep -q 'backup finished' /tmp/backup.log))" ]
+then
+    eval "$push_success_notification"
+else
+    eval "$push_fail_notification"
+fi

entrypoint.sh

@@ -0,0 +1,15 @@
+#!/bin/sh
+
+set -e
+
+if [ -n "$SSH_HOST_KEY" ]
+then
+    echo "$SSH_HOST_KEY" > /root/.ssh/known_hosts
+fi
+
+cron_schedule="${CRON_SCHEDULE:?CRON_SCHEDULE not set}"
+
+echo "$cron_schedule /cronjob.sh" | crontab -
+crontab -l
+
+crond -f -d8 -L /dev/stdout

pg_backup.sh

@@ -0,0 +1,34 @@
+#!/bin/bash
+
+set -e
+
+BACKUP_FILE='/var/lib/postgresql/data/backup.sql'
+
+function backup {
+  export PGPASSWORD=$(cat $POSTGRES_PASSWORD_FILE)
+  pg_dump -U ${POSTGRES_USER} ${POSTGRES_DB} > $BACKUP_FILE
+}
+
+function restore {
+    cd /var/lib/postgresql/data/
+    restore_config(){
+        # Restore allowed connections
+        cat pg_hba.conf.bak > pg_hba.conf
+        su postgres -c 'pg_ctl reload'
+    }
+    # Don't allow any other connections than local
+    cp pg_hba.conf pg_hba.conf.bak
+    echo "local all all trust" > pg_hba.conf
+    su postgres -c 'pg_ctl reload'
+    trap restore_config EXIT INT TERM
+
+    # Recreate Database
+    psql -U ${POSTGRES_USER} -d postgres -c "DROP DATABASE ${POSTGRES_DB} WITH (FORCE);" 
+    createdb -U ${POSTGRES_USER} ${POSTGRES_DB}
+    psql -U ${POSTGRES_USER} -d ${POSTGRES_DB} -1 -f $BACKUP_FILE
+
+    trap - EXIT INT TERM
+    restore_config
+}
+
+$@

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"
+}

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

ssh_config

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