Switch to backup-bot-two image

.drone.yml

@@ -9,9 +9,9 @@ steps:
       password:
         from_secret: git_coopcloud_tech_token_3wc
       repo: git.coopcloud.tech/coop-cloud/backup-bot-two
-      tags: ${DRONE_SEMVER_BUILD}
+      tags: 2.0.0
       registry: git.coopcloud.tech
     when:
       event:
-        include:
-          - tag
+        exclude:
+          - pull_request

.env.sample

@@ -8,11 +8,6 @@ RESTIC_REPOSITORY=/backups/restic
 
 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"
 

CHANGELOG.md

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

Dockerfile

@@ -1,11 +1,10 @@
 FROM docker:24.0.7-dind
 
-RUN apk add --upgrade --no-cache restic bash python3 py3-pip py3-click py3-docker-py py3-json-logger curl
+RUN apk add --upgrade --no-cache restic bash python3 py3-pip
 
 # Todo use requirements file with specific versions
-RUN pip install --break-system-packages resticpy==1.0.2
+RUN pip install click==8.1.7 docker==6.1.3 resticpy==1.0.2
 
 COPY backupbot.py /usr/bin/backup
-COPY entrypoint.sh /entrypoint.sh
 
-ENTRYPOINT /entrypoint.sh
+ENTRYPOINT /bin/bash

README.md

@@ -10,7 +10,7 @@ Automatically take backups from all volumes of running Docker Swarm services and
 
 * **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
+* **Image**: [`thecoopcloud/backup-bot-two`](https://hub.docker.com/r/thecoopcloud/backup-bot-two), 4, upstream
 * **Healthcheck**: No
 * **Backups**: N/A
 * **Email**: N/A
@@ -38,12 +38,12 @@ Backupbot II tries to help, by
 * `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 secret generate -a <app_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/`
+Per default Backupbot stores the backups locally in the repository `/backups/restic`, which is accessible as volume at `/var/lib/docker/volumes/<app_name>_backups/_data/restic/`
 
 The backup location can be changed using the `RESTIC_REPOSITORY` env variable.
 
@@ -57,7 +57,7 @@ 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>`
+`abra app secret insert <app_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.
 
@@ -79,10 +79,9 @@ 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 """$(cat backupkey)
+abra app secret insert <app_name> ssh_key v1 """$(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
 
@@ -95,81 +94,67 @@ 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/"
+`abra app secret insert <app_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`
+`abra app run <app_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`
+`abra app run <app_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`
+`abra app run <app_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`
+`abra app run <app_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>`
+`abra app run <app_name> app -- backup --host <target_app_name> restore --snapshot <snapshot_id>`
 
 Show all snapshots:
 
-`abra app run <backupbot_name> app -- backup snapshots`
+`abra app run <app_name> app -- backup snapshots`
 
 Show all snapshots containing a specific app:
 
-`abra app run <backupbot_name> app -- backup --host <target_app_name> snapshots`
+`abra app run <app_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`
+`abra app run <app_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/`
+`abra app run <app_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 .
+filename=$(abra app run <app_name> app -- backup download --snapshot <snapshot_id> --path <absolute_path>)
+abra app cp <app_name> app:$filename .
 ```
 
 ## Run restic
 
 ```
-abra app run <backupbot_name> app bash
+abra app run <app_name> app bash
 export AWS_SECRET_ACCESS_KEY=$(cat $AWS_SECRET_ACCESS_KEY_FILE)
 export RESTIC_PASSWORD=$(cat $RESTIC_PASSWORD_FILE)
 restic snapshots
@@ -196,20 +181,3 @@ services:
 As in the above example, you can reference Docker Secrets, e.g. for looking up database passwords, by reading the files in `/run/secrets` directly.
 
 [abra]: https://git.autonomic.zone/autonomic-cooperative/abra
-
-## 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 *
-```

abra.sh

@@ -1,10 +1,3 @@
+export ENTRYPOINT_VERSION=v1
 export BACKUPBOT_VERSION=v1
 export SSH_CONFIG_VERSION=v1
-
-run_cron () {
-    schedule="$(crontab -l | tr -s " " | cut -d ' ' -f-5)"
-    rm -f /tmp/backup.log
-    echo "* * * * *  $(crontab -l | tr -s " " | cut -d ' ' -f6-)" | crontab -
-    while [ ! -f /tmp/backup.log ]; do sleep 1; done
-    echo "$schedule $(crontab -l | tr -s " " | cut -d ' ' -f6-)" | crontab -
-}

backupbot.py

@@ -1,7 +1,6 @@
 #!/usr/bin/python3
 
 import os
-import sys
 import click
 import json
 import subprocess
@@ -10,40 +9,22 @@ 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
+# logging.basicConfig(level=logging.INFO)
 
 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
+SERVICE = None
 
 
 @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):
+@click.option('repository', '--repo', '-r', envvar='RESTIC_REPOSITORY', required=True)
+def cli(loglevel, service, repository):
     global SERVICE
     if service:
         SERVICE = service.replace('.', '_')
@@ -53,33 +34,22 @@ def cli(loglevel, service, repository, machine_logs):
         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)
-
+        logging.basicConfig(level=numeric_level)
     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']
+    logging.debug(f"set restic repository location: {repo}")
     restic.repository = repo
-    logger.debug(f"set restic repository location: {repo}")
     restic.password_file = '/var/run/secrets/restic_password'
     try:
         restic.cat.config()
     except ResticFailedError as error:
         if 'unable to open config file' in str(error):
             result = restic.init()
-            logger.info(f"Initialized restic repo: {result}")
+            logging.info(f"Initialized restic repo: {result}")
         else:
             raise error
 
@@ -87,250 +57,77 @@ def init_repo():
 def export_secrets():
     for env in os.environ:
         if env.endswith('FILE') and not "COMPOSE_FILE" in env:
-            logger.debug(f"exported secret: {env}")
+            logging.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}")
+                # logging.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))
+def create():
+    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_versions, int(retries))
+    backup_volumes(backup_paths, apps)
     run_commands(post_commands)
 
 
-@cli.command()
-@click.option('snapshot', '--snapshot', '-s', envvar='SNAPSHOT', default='latest')
-@click.option('target', '--target', '-t', envvar='TARGET', default='/')
-@click.option('noninteractive', '--noninteractive', envvar='NONINTERACTIVE', is_flag=True)
-@click.option('volumes', '--volumes', '-v', envvar='VOLUMES', multiple=True)
-@click.option('container', '--container', '-c', envvar='CONTAINER', multiple=True)
-@click.option('no_commands', '--no-commands', envvar='NO_COMMANDS', is_flag=True)
-def restore(snapshot, target, noninteractive, volumes, container, no_commands):
-    app_settings = parse_backup_labels('restore', container)
-    if SERVICE != 'ALL':
-        app_settings = {SERVICE: app_settings[SERVICE]}
-    pre_commands, post_commands, backup_paths, apps_versions = get_backup_details(app_settings, volumes)
-    snapshots = get_snapshots(snapshot_id=snapshot)
-    if not snapshot:
-        logger.error(f"No Snapshots with ID {snapshots} for {apps_versions.keys()} found.")
-        exit(1)
-    if not noninteractive:
-        print(f"Snapshot to restore: \t{snapshot}")
-        restore_app_versions = app_versions_from_tags(snapshots[0].get('tags'))
-        print("Apps:")
-        for app, version in restore_app_versions.items():
-            print(f"\t{app} \t {version}")
-            if apps_versions.get(app) != version:
-                print(f"WARNING!!! The running app is deployed with version {apps_versions.get(app)}")
-        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(snapshots[0]['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} at {target}")
-    if not no_commands and pre_commands:
-        print(f"Run pre commands.")
-        run_commands(pre_commands)
-    result = restic_restore(snapshot_id=snapshot, include=backup_paths, target_dir=target)
-    if not no_commands and post_commands:
-        print(f"Run post commands.")
-        run_commands(post_commands)
-    logger.debug(result)
-
-
-def restic_restore(snapshot_id='latest', include=[], target_dir=None):
-    cmd = restic.cat.base_command() + ['restore', snapshot_id]
-    for path in include:
-        cmd.extend(['--include', path])
-    if target_dir:
-        cmd.extend(['--target', target_dir])
-    return restic.internal.command_executor.execute(cmd)
-
-
-def get_snapshots(snapshot_id=None):
-    if snapshot_id and snapshot_id != 'latest':
-        snapshots = restic.snapshots(snapshot_id=snapshot_id)
-        if 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 parse_backup_labels(hook_type='backup', selected_container=[]):
+def get_backup_cmds():
     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 bool(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=[]):
+        c.labels['com.docker.swarm.service.name']: c for c in client.containers.list()}
     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:
+    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):
+            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)):
+                logging.error(
+                    f"Container {s.name} is not running, hooks can not be executed")
                 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}')
-                    continue
-                if selected_volumes and volume not in selected_volumes:
-                    logger.debug(f'Skipping {volume}:{rel_paths} because the volume is not selected')
-                    continue
-                for p in rel_paths:
-                    absolute_path = Path(f"{volume_path}/{p}")
-                    backup_paths.add(absolute_path)
-        else:
-            included_volumes = []
-        excluded_volumes = settings.get('excluded_volumes') or []
-        for name, path in volumes.items():
-            if selected_volumes and name not in selected_volumes:
-                logger.debug(f'Skipping volume: {name} because the volume is not selected')
-                continue
-            if name in excluded_volumes:
-                logger.debug(f'Skipping volume: {name} because the volume is excluded')
-                continue
-            if name in included_volumes:
-                logger.debug(f'Skipping volume: {name} because a path is selected')
-                continue
-            backup_paths.add(path)
-    else:
-        logger.warning(f"{app} does not contain any volumes")
-
-
-def parse_volumes(stack_name, mounts):
-    volumes = {}
-    for m in mounts:
-        if m['Type'] != 'volume':
-            continue
-        relative_path = m['Source']
-        name = relative_path.removeprefix(stack_name + '_')
-        absolute_path = Path(f"{VOLUME_PATH}{relative_path}/_data/")
-        volumes[name] = absolute_path
-    return volumes
-
-
-def parse_excludes_includes(labels):
-    excluded_volumes = set()
-    included_volume_paths = set()
-    for label, value in labels.items():
-        if label.startswith('backupbot.backup.volumes.'):
-            volume_name = label.removeprefix('backupbot.backup.volumes.').removesuffix('.path')
-            if label.endswith('path'): 
-                relative_paths = tuple(value.split(','))
-                included_volume_paths.add((volume_name, relative_paths))
-            elif bool(value):
-                excluded_volumes.add(volume_name)
-    return excluded_volumes, included_volume_paths
+            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
+    #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()}
+        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.warning(
+                logging.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}")
+                    logging.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)
 
 
@@ -339,71 +136,77 @@ def run_commands(commands):
         if not command:
             continue
         # Remove bash/sh wrapping
-        command = command.removeprefix('bash -c').removeprefix('sh -c').removeprefix(' ')
+        command = command.removeprefix('bash -c').removeprefix('sh -c')
         # Remove quotes surrounding the command
         if (len(command) >= 2 and command[0] == command[-1] and (command[0] == "'" or command[0] == '"')):
-            command = command[1:-1]
+            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)
+        logging.info(f"run command in {container.name}:")
+        logging.info(command)
         result = container.exec_run(command)
         if result.exit_code:
-            logger.error(
+            logging.error(
                 f"Failed to run command {command} in {container.name}: {result.output.decode()}")
         else:
-            logger.info(result.output.decode())
+            logging.info(result.output.decode())
 
 
-def backup_volumes(backup_paths, apps_versions, retries, dry_run=False):
-    while True:
+def backup_volumes(backup_paths, apps, dry_run=False):
     try:
-            logger.info("Backup these paths:")
-            logger.debug("\n".join(map(str, backup_paths)))
-            backup_paths = list(filter(path_exists, backup_paths))
-            cmd = restic.cat.base_command()
-            parent = get_snapshots('latest') 
-            if parent:
-                # https://restic.readthedocs.io/en/stable/040_backup.html#file-change-detection
-                cmd.extend(['--parent', parent[0]['short_id']])
-            tags = [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
+        result = restic.backup(backup_paths, dry_run=dry_run, tags=apps)
+        print(result)
+        logging.info(result)
     except ResticFailedError as error:
-            logger.error(f"Backup failed for {SERVICE}.")
-            logger.error(error, exc_info=True)
-            if retries > 0:
-                retries -= 1
-            else:
+        logging.error(f"Backup failed for {apps}. Could not Backup these paths: {backup_paths}")
+        logging.error(error)
         exit(1)
 
 
-def path_exists(path):
-    if not path.exists():
-        logger.error(f'{path} does not exist')
-    return path.exists()
+@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', default=False)
+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:
+        logging.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':
+            logging.error("Restore aborted")
+            exit(1)
+    print(f"Restoring Snapshot {snapshot} of {service_paths} at {target}")
+    result = restic.restore(snapshot_id=snapshot,
+                            include=service_paths, target_dir=target)
+    logging.debug(result)
 
 
 @cli.command()
 def snapshots():
-    snapshots = get_snapshots()
+    snapshots = restic.snapshots()
+    no_snapshots = True
     for snap in snapshots:
-        output = [snap['time'], snap['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:
+        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 != 'ALL':
-            service_name = SERVICE.replace('_', '.')
-            err_msg += f' for app {service_name}'
-        logger.warning(err_msg)
+        if SERVICE:
+            err_msg += f' for app {SERVICE}'
+        logging.warning(err_msg)
 
 
 @cli.command()
@@ -418,12 +221,8 @@ def ls(snapshot, path):
 
 def list_files(snapshot, path):
     cmd = restic.cat.base_command() + ['ls']
-    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 SERVICE:
+        cmd = cmd + ['--tag', SERVICE]
     cmd.append(snapshot)
     if path:
         cmd.append(path)
@@ -431,10 +230,10 @@ def list_files(snapshot, path):
         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)
+            err_msg = f'There is no snapshot {snapshot}'
+            if SERVICE:
+                err_msg += f'for the app {SERVICE}'
+            logging.error(err_msg)
             exit(1)
         else:
             raise error
@@ -446,8 +245,8 @@ def list_files(snapshot, path):
 @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')
+@click.option('volumes', '--volumes', '-v', is_flag=True)
+@click.option('secrets', '--secrets', '-c', is_flag=True)
 def download(snapshot, path, volumes, secrets):
     file_dumps = []
     if not any([path, volumes, secrets]):
@@ -464,8 +263,8 @@ def download(snapshot, path, volumes, secrets):
         tarinfo.size = len(binary_output)
         file_dumps.append((binary_output, tarinfo))
     if volumes:
-        if SERVICE == 'ALL':
-            logger.error("Please specify '--host' when using '--volumes'")
+        if not SERVICE:
+            logging.error("Please specify '--host' when using '--volumes'")
             exit(1)
         files = list_files(snapshot, VOLUME_PATH)
         for f in files[1:]:
@@ -477,8 +276,8 @@ def download(snapshot, path, volumes, secrets):
                 tarinfo.size = len(binary_output)
                 file_dumps.append((binary_output, tarinfo))
     if secrets:
-        if SERVICE == 'ALL':
-            logger.error("Please specify '--host' when using '--secrets'")
+        if not SERVICE:
+            logging.error("Please specify '--host' when using '--secrets'")
             exit(1)
         filename = f"{SERVICE}.json"
         files = list_files(snapshot, SECRET_PATH)
@@ -498,8 +297,7 @@ def download(snapshot, path, volumes, secrets):
         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}")
+    print(f"Backup has been written to /tmp/backup.tar.gz with a size of {size}")
 
 
 def get_formatted_size(file_path):
@@ -514,18 +312,13 @@ def get_formatted_size(file_path):
 
 def dump(snapshot, path):
     cmd = restic.cat.base_command() + ['dump']
-    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']
-    cmd.append(snapshot)
+    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(
+        logging.error(
             f"error while dumping {path} from snapshot '{snapshot}': {output.stderr}")
         exit(1)
     return output.stdout

compose.yml

@@ -2,7 +2,7 @@
 version: "3.8"
 services:
   app:
-    image: git.coopcloud.tech/coop-cloud/backup-bot-two:2.2.0-beta
+    image: git.coopcloud.tech/coop-cloud:2.0.0
     volumes:
       - "/var/run/docker.sock:/var/run/docker.sock"
       - "/var/lib/docker/volumes/:/var/lib/docker/volumes/"
@@ -16,10 +16,14 @@ services:
       - restic_password
     deploy:
       labels:
-        - coop-cloud.${STACK_NAME}.version=2.1.0+2.2.0-beta
+        - coop-cloud.${STACK_NAME}.version=0.1.0+latest
         - coop-cloud.${STACK_NAME}.timeout=${TIMEOUT:-300}
         - coop-cloud.backupbot.enabled=true
-    #entrypoint: ['tail', '-f','/dev/null']
+    configs:
+      - source: entrypoint
+        target: /entrypoint.sh
+        mode: 0555
+    entrypoint: ['/entrypoint.sh']
     healthcheck:
       test: "pgrep crond"
       interval: 30s
@@ -34,3 +38,8 @@ secrets:
     
 volumes:
   backups:
+
+configs:
+  entrypoint:
+    name: ${STACK_NAME}_entrypoint_${ENTRYPOINT_VERSION}
+    file: entrypoint.sh

entrypoint.sh

@@ -1,6 +1,11 @@
 #!/bin/sh
 
-set -e
+set -e -o pipefail
+
+apk add --upgrade --no-cache restic bash python3 py3-pip
+
+# Todo use requirements file with specific versions
+pip install click==8.1.7 docker==6.1.3 resticpy==1.0.2
 
 if [ -n "$SSH_HOST_KEY" ]
 then
@@ -9,22 +14,7 @@ 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 $push_notification" | crontab -
+echo "$cron_schedule backup create" | crontab -
 crontab -l
 
 crond -f -d8 -L /dev/stdout

release/1.0.0+2.0.0-beta

@@ -1 +0,0 @@
-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.