Switch ENTRYPOINT to try to resolve loop on start

[ci skip]

.drone.yml

@@ -2,11 +2,6 @@
 kind: pipeline
 name: linters
 steps:
-  - name: run shellcheck
-    image: koalaman/shellcheck-alpine
-    commands:
-      - shellcheck backup.sh
-
   - name: publish image
     image: plugins/docker
     settings:
@@ -14,31 +9,9 @@ steps:
       password:
         from_secret: git_coopcloud_tech_token_3wc
       repo: git.coopcloud.tech/coop-cloud/backup-bot-two
-      tags: 1.0.0
+      tags: 2.0.0
       registry: git.coopcloud.tech
-    depends_on:
-      - run shellcheck
     when:
       event:
         exclude:
           - pull_request
-
-trigger:
-  branch:
-    - bb2-classic
----
-kind: pipeline
-name: generate recipe catalogue
-steps:
-  - name: release a new version
-    image: plugins/downstream
-    settings:
-      server: https://build.coopcloud.tech
-      token:
-        from_secret: drone_abra-bot_token
-      fork: true
-      repositories:
-        - coop-cloud/auto-recipes-catalogue-json
-
-trigger:
-  event: tag

.env.sample

@@ -4,11 +4,14 @@ SECRET_RESTIC_PASSWORD_VERSION=v1
 
 COMPOSE_FILE=compose.yml
 
-SERVER_NAME=example.com
-RESTIC_HOST=minio.example.com
+RESTIC_REPOSITORY=/backups/restic
 
-CRON_SCHEDULE='*/5 * * * *'
-REMOVE_BACKUP_VOLUME_AFTER_UPLOAD=1
+CRON_SCHEDULE='30 3 * * *'
+
+# 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="$COMPOSE_FILE:compose.swarm-cronjob.yml"
@@ -23,7 +26,9 @@ REMOVE_BACKUP_VOLUME_AFTER_UPLOAD=1
 #AWS_ACCESS_KEY_ID=something-secret
 #COMPOSE_FILE="$COMPOSE_FILE:compose.s3.yml"
 
-# HTTPS storage
-#SECRET_HTTPS_PASSWORD_VERSION=v1
-#COMPOSE_FILE="$COMPOSE_FILE:compose.https.yml"
-#RESTIC_USER=<somebody>
+# Secret restic repository
+# use a secret to store the RESTIC_REPOSITORY if the repository location contains a secret value
+# i.E rest:https://user:SECRET_PASSWORD@host:8000/
+# it overwrites the RESTIC_REPOSITORY variable
+#SECRET_RESTIC_REPO_VERSION=v1
+#COMPOSE_FILE="$COMPOSE_FILE:compose.secret.yml"

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:24.0.6-dind
+FROM docker:24.0.7-dind
 
-RUN apk add --upgrade --no-cache \
-  bash \
-  curl \
-  jq \
-  restic
+RUN apk add --upgrade --no-cache restic bash python3 py3-pip py3-click py3-docker-py py3-json-logger curl
 
-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
+# Todo use requirements file with specific versions
+RUN pip install --break-system-packages resticpy==1.0.2
 
-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**: [`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 -->
+
 
 ## Background
 
@@ -20,28 +34,149 @@ 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 -->
-
-* **Category**: Utilities
-* **Status**: 0, work-in-progress
-* **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 -->
+* `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:
+```
+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
+
+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
+```
+
+
+## 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> --path /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:
 
 ```
@@ -49,24 +184,15 @@ services:
   db:
     deploy:
       labels:
-        backupbot.backup: "true"
-        backupbot.backup.pre-hook: 'mysqldump -u root -p"$(cat /run/secrets/db_root_password)" -f /tmp/dump/dump.db'
-        backupbot.backup.post-hook: "rm -rf /tmp/dump/dump.db"
-        backupbot.backup.path: "/tmp/dump/,/etc/foo/"
+        backupbot.backup: ${BACKUP:-"true"} 
+        backupbot.backup.pre-hook: 'mysqldump -u root -p"$(cat /run/secrets/db_root_password)" -f /volume_path/dump.db'
+        backupbot.backup.post-hook: "rm -rf /volume_path/dump.db"
 ```
 
 - `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)
+- `backupbot.backup.pre-hook` -- command to run before copying files (optional), save all dumps into the volumes
 - `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

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 -
+}

backup.sh

@@ -1,139 +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}"
-# shellcheck disable=SC2153
-https_password_file="${HTTPS_PASSWORD_FILE}"
-
-restic_repo=
-restic_extra_options=
-
-if [ -n "$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 [ -n "$https_password_file" ] && [ -f "$https_password_file" ]; then
-	HTTPS_PASSWORD="$(cat "${https_password_file}")"
-	export HTTPS_PASSWORD
-	restic_user="${RESTIC_USER:?RESTIC_USER not set}"
-	restic_repo="rest:https://$restic_user:$HTTPS_PASSWORD@$restic_host"
-fi
-
-if [ -z "$restic_repo" ]; then
-	echo "you must configure either SFTP, S3, or HTTPS 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 "$backup_path"
-
-	if [ "$REMOVE_BACKUP_VOLUME_AFTER_UPLOAD" -eq 1 ]; then
-		echo "Cleaning up ${backup_path}"
-		rm -rf "${backup_path:?}"/*
-	fi
-fi

backupbot.py

@@ -0,0 +1,365 @@
+#!/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', required=True)
+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
+                # 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()
+    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.https.yml

@@ -1,15 +0,0 @@
----
-version: "3.8"
-services:
-  app:
-    environment:
-      - HTTPS_PASSWORD_FILE=/run/secrets/https_password
-      - RESTIC_USER
-    secrets:
-      - source: https_password
-        mode: 0400
-
-secrets:
-  https_password:
-    external: true
-    name: ${STACK_NAME}_https_password_${SECRET_HTTPS_PASSWORD_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

@@ -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

@@ -2,34 +2,35 @@
 version: "3.8"
 services:
   app:
-    image: git.coopcloud.tech:1.0.0
-#    build: .
+    image: git.coopcloud.tech/coop-cloud/backup-bot-two:2.0.0
     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
-      - REMOVE_BACKUP_VOLUME_AFTER_UPLOAD=1
     secrets:
       - restic_password
     deploy:
       labels:
-        - "traefik.enable=true"
-        - "traefik.http.services.${STACK_NAME}.loadbalancer.server.port=8008"
-        - "traefik.http.routers.${STACK_NAME}.rule="
-        - "traefik.http.routers.${STACK_NAME}.entrypoints=web-secure"
-        - "traefik.http.routers.${STACK_NAME}.tls.certresolver=${LETS_ENCRYPT_ENV}"
-        - coop-cloud.${STACK_NAME}.version=0.2.0+1.0.0
-
-volumes:
-  backups:
+        - coop-cloud.${STACK_NAME}.version=0.1.0+latest
+        - coop-cloud.${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

@@ -0,0 +1,30 @@
+#!/bin/sh
+
+set -e
+
+if [ -n "$SSH_HOST_KEY" ]
+then
+    echo "$SSH_HOST_KEY" > /root/.ssh/known_hosts
+fi
+
+cron_schedule="${CRON_SCHEDULE:?CRON_SCHEDULE not set}"
+
+if [ -n "$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

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`

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