Switch ENTRYPOINT to try to resolve loop on start

.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

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
@@ -95,7 +95,7 @@ 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 <backupbot_name> restic_repo v1 "rest:https://user:pass@host:8000/"`
 ```
 The secret will overwrite the `RESTIC_REPOSITORY` variable.
 

backupbot.py

@@ -18,7 +18,7 @@ from shutil import copyfile, rmtree
 
 VOLUME_PATH = "/var/lib/docker/volumes/"
 SECRET_PATH = '/secrets/'
-SERVICE = 'ALL'
+SERVICE = None
 
 logger = logging.getLogger("backupbot")
 logging.addLevelName(55, 'SUMMARY')
@@ -42,7 +42,7 @@ sys.excepthook = handle_exception
 @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')
+@click.option('repository', '--repo', '-r', envvar='RESTIC_REPOSITORY', required=True)
 def cli(loglevel, service, repository, machine_logs):
     global SERVICE
     if service:
@@ -54,8 +54,8 @@ def cli(loglevel, service, repository, machine_logs):
         if not isinstance(numeric_level, int):
             raise ValueError('Invalid log level: %s' % loglevel)
         logger.setLevel(numeric_level)
-    logHandler = logging.StreamHandler()
     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)
@@ -66,13 +66,9 @@ def cli(loglevel, service, repository, machine_logs):
 
 
 def init_repo():
-    if repo:= os.environ.get('RESTIC_REPOSITORY_FILE'):
-        # RESTIC_REPOSITORY_FILE and RESTIC_REPOSITORY are mutually exclusive
-        del os.environ['RESTIC_REPOSITORY']
-    else:
     repo = os.environ['RESTIC_REPOSITORY']
-        restic.repository = repo
     logger.debug(f"set restic repository location: {repo}")
+    restic.repository = repo
     restic.password_file = '/var/run/secrets/restic_password'
     try:
         restic.cat.config()
@@ -97,197 +93,44 @@ def export_secrets():
 @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 = get_backup_details(app_settings)
+    pre_commands, post_commands, backup_paths, apps = get_backup_cmds()
     copy_secrets(apps)
-    backup_paths.append(Path(SECRET_PATH))
+    backup_paths.append(SECRET_PATH)
     run_commands(pre_commands)
     backup_volumes(backup_paths, apps, int(retries))
     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 = get_backup_details(app_settings, volumes)
-    snapshots = get_snapshots(snapshot_id=snapshot)
-    if not snapshot:
-        logger.error("No Snapshots with ID {snapshots} for {apps} found.")
-        exit(1)
-    if not noninteractive:
-        snapshot_date = datetime.fromisoformat(snapshots[0]['time'])
-        delta = datetime.now(tz=timezone.utc) - snapshot_date
-        print(f"You are going to restore Snapshot {snapshot} of {apps} at {target}")
-        print("The following volume paths will be restored:")
-        for p in backup_paths:
-            print(f'\t{p}')
-        if not no_commands:
-            print("The following commands will be executed:")
-            for container, cmd in list(pre_commands.items()) + list(post_commands.items()):
-                print(f"\t{container.labels['com.docker.swarm.service.name']}:\t{cmd}")
-        print(f"This snapshot is {delta} old")
-        print("\nTHIS COMMAND WILL IRREVERSIBLY OVERWRITES FILES")
-        prompt = input("Type YES (uppercase) to continue: ")
-        if prompt != 'YES':
-            logger.error("Restore aborted")
-            exit(1)
-    print(f"Restoring Snapshot {snapshot} at {target}")
-    if not no_commands and pre_commands:
-        print(f"Run pre commands.")
-        run_commands(pre_commands)
-    result = restic_restore(snapshot_id=snapshot, include=backup_paths, target_dir=target)
-    if not no_commands and post_commands:
-        print(f"Run post commands.")
-        run_commands(post_commands)
-    logger.debug(result)
-
-
-def restic_restore(snapshot_id='latest', include=[], target_dir=None):
-    cmd = restic.cat.base_command() + ['restore', snapshot_id]
-    for path in include:
-        cmd.extend(['--include', path])
-    if target_dir:
-        cmd.extend(['--target', target_dir])
-    return restic.internal.command_executor.execute(cmd)
-
-
-def get_snapshots(snapshot_id=None):
-    if snapshot_id and snapshot_id != 'latest':
-        snapshots = restic.snapshots(snapshot_id=snapshot_id)
-        if SERVICE not in snapshots[0]['tags']:
-            logger.error(f'Snapshot with ID {snapshot_id} does not contain {SERVICE}')
-            exit(1)
-    else:
-        snapshots = restic.snapshots()
-        snapshots = list(filter(lambda x: x.get('tags') and SERVICE in x.get('tags'), snapshots))
-    if snapshot_id == 'latest':
-        return snapshots[-1:]
-    else:
-        return snapshots
-
-
-def parse_backup_labels(hook_type='backup', selected_container=[]):
+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}_")
-        settings = app_settings[stack_name] = app_settings.get(stack_name) or {}
-        if (backup := labels.get('backupbot.backup')) and bool(backup):
-            settings['enabled'] = True
-        if selected_container and container_name not in selected_container:
-            logger.debug(f"Skipping {s.name} because it's not a selected container")
-            continue
-        if 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 = []
-    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):
+            # 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
-            backup_apps.append(app)
-            add_backup_paths(backup_paths, settings, app, volumes)
-            if hooks:= settings.get('pre_hooks'):
-                pre_hooks.update(hooks)
-            if hooks:= settings.get('post_hooks'):
-                post_hooks.update(hooks)
-    return pre_hooks, post_hooks, list(backup_paths), backup_apps
-
-
-def add_backup_paths(backup_paths, settings, app, selected_volumes):
-    if (volumes := settings.get('volumes')):
-        if includes:= settings.get('included_volume_paths'):
-            included_volumes = list(zip(*includes))[0]
-            for volume, rel_paths in includes:
-                if not (volume_path:= volumes.get(volume)):
-                    logger.error(f'Can not find volume with the name {volume}')
-                    continue
-                if selected_volumes and volume not in selected_volumes:
-                    logger.debug(f'Skipping {volume}:{rel_paths} because the volume is not selected')
-                    continue
-                for p in rel_paths:
-                    absolute_path = Path(f"{volume_path}/{p}")
-                    backup_paths.add(absolute_path)
-        else:
-            included_volumes = []
-        excluded_volumes = settings.get('excluded_volumes') or []
-        for name, path in volumes.items():
-            if selected_volumes and name not in selected_volumes:
-                logger.debug(f'Skipping volume: {name} because the volume is not selected')
-                continue
-            if name in excluded_volumes:
-                logger.debug(f'Skipping volume: {name} because the volume is excluded')
-                continue
-            if name in included_volumes:
-                logger.debug(f'Skipping volume: {name} because a path is selected')
-                continue
-            backup_paths.add(path)
-    else:
-        logger.warning(f"{app} does not contain any volumes")
-
-
-def parse_volumes(stack_name, mounts):
-    volumes = {}
-    for m in mounts:
-        if m['Type'] != 'volume':
-            continue
-        relative_path = m['Source']
-        name = relative_path.removeprefix(stack_name + '_')
-        absolute_path = Path(f"{VOLUME_PATH}{relative_path}/_data/")
-        volumes[name] = absolute_path
-    return volumes
-
-
-def parse_excludes_includes(labels):
-    excluded_volumes = set()
-    included_volume_paths = set()
-    for label, value in labels.items():
-        if label.startswith('backupbot.backup.volumes.'):
-            volume_name = label.removeprefix('backupbot.backup.volumes.').removesuffix('.path')
-            if label.endswith('path'): 
-                relative_paths = tuple(value.split(','))
-                included_volume_paths.add((volume_name, relative_paths))
-            elif bool(value):
-                excluded_volumes.add(volume_name)
-    return excluded_volumes, included_volume_paths
+            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):
@@ -296,14 +139,14 @@ def copy_secrets(apps):
     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(
+                logger.error(
                     f"Container {s.name} is not running, secrets can not be copied.")
                 continue
             container_id = container_by_service[s.name].id
@@ -314,7 +157,6 @@ def copy_secrets(apps):
                         f"For the secret {sec['SecretName']} the file {src} does not exist for {s.name}")
                     continue
                 dst = SECRET_PATH + sec['SecretName']
-                logger.debug(f"Copy Secret {sec['SecretName']}")
                 copyfile(src, dst)
 
 
@@ -342,21 +184,12 @@ def run_commands(commands):
 def backup_volumes(backup_paths, apps, retries, dry_run=False):
     while True:
         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 = set(apps + [SERVICE])
-            logger.info("Start volume backup")
-            result = restic.internal.backup.run(cmd, backup_paths, dry_run=dry_run, tags=tags)
+            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 {SERVICE}.")
+            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
@@ -364,20 +197,49 @@ def backup_volumes(backup_paths, apps, retries, dry_run=False):
                 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', 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 = get_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'])
-    if not snapshots:
+            no_snapshots = False
+    if no_snapshots:
         err_msg = "No Snapshots found"
-        if SERVICE != 'ALL':
+        if SERVICE:
             service_name = SERVICE.replace('_', '.')
             err_msg += f' for app {service_name}'
         logger.warning(err_msg)
@@ -395,6 +257,7 @@ def ls(snapshot, path):
 
 def list_files(snapshot, path):
     cmd = restic.cat.base_command() + ['ls']
+    if SERVICE:
         cmd = cmd + ['--tag', SERVICE]
     cmd.append(snapshot)
     if path:
@@ -404,7 +267,7 @@ def list_files(snapshot, path):
     except ResticFailedError as error:
         if 'no snapshot found' in str(error):
             err_msg = f'There is no snapshot "{snapshot}"'
-            if SERVICE != 'ALL':
+            if SERVICE:
                 err_msg += f' for the app "{SERVICE}"'
             logger.error(err_msg)
             exit(1)
@@ -436,7 +299,7 @@ def download(snapshot, path, volumes, secrets):
         tarinfo.size = len(binary_output)
         file_dumps.append((binary_output, tarinfo))
     if volumes:
-        if SERVICE == 'ALL':
+        if not SERVICE:
             logger.error("Please specify '--host' when using '--volumes'")
             exit(1)
         files = list_files(snapshot, VOLUME_PATH)
@@ -449,7 +312,7 @@ def download(snapshot, path, volumes, secrets):
                 tarinfo.size = len(binary_output)
                 file_dumps.append((binary_output, tarinfo))
     if secrets:
-        if SERVICE == 'ALL':
+        if not SERVICE:
             logger.error("Please specify '--host' when using '--secrets'")
             exit(1)
         filename = f"{SERVICE}.json"
@@ -486,6 +349,7 @@ def get_formatted_size(file_path):
 
 def dump(snapshot, path):
     cmd = restic.cat.base_command() + ['dump']
+    if SERVICE:
         cmd = cmd + ['--tag', SERVICE]
     cmd = cmd + [snapshot, path]
     print(f"Dumping {path} from snapshot '{snapshot}'")

compose.yml

@@ -2,7 +2,7 @@
 version: "3.8"
 services:
   app:
-    image: git.coopcloud.tech/coop-cloud/backup-bot-two:2.1.1-beta
+    image: git.coopcloud.tech/coop-cloud/backup-bot-two:2.0.0
     volumes:
       - "/var/run/docker.sock:/var/run/docker.sock"
       - "/var/lib/docker/volumes/:/var/lib/docker/volumes/"
@@ -16,7 +16,7 @@ services:
       - restic_password
     deploy:
       labels:
-        - coop-cloud.${STACK_NAME}.version=2.0.1+2.1.1-beta
+        - coop-cloud.${STACK_NAME}.version=0.1.0+latest
         - coop-cloud.${STACK_NAME}.timeout=${TIMEOUT:-300}
         - coop-cloud.backupbot.enabled=true
     #entrypoint: ['tail', '-f','/dev/null']

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.