feat: Adds a command to setup the restic repository in s3

README.md

@@ -49,15 +49,23 @@ 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:
+1. 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:
+2. 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 <backupbot_name> aws_secret_access_key v1 <SECRET_ACCESS_KEY>
+```
+
+3. Intialze you restic repository:
+```
+abra app cmd --chaos <backup_name> app setup_restic_s3
+```
+
 
 See [restic s3 docs](https://restic.readthedocs.io/en/latest/030_preparing_a_new_repo.html#amazon-s3) for more information.
 
@@ -157,7 +165,7 @@ Show all files inside the latest snapshot (can be very verbose):
 
 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 <backupbot_name> app -- backup ls --snapshot <snapshot_id> /var/lib/docker/volumes/`
 
 Download files from a snapshot:
 
@@ -179,19 +187,55 @@ restic snapshots
 
 Like Traefik, or `swarm-cronjob`, Backupbot II uses access to the Docker socket to read labels from running Docker Swarm services:
 
+1. Add `ENABLE_BACKUPS=true` to .env.sample
+
+2. Add backupbot labels to the compose file
+
 ```
 services:
   db:
     deploy:
       labels:
-        backupbot.backup: ${BACKUP:-"true"} 
+        backupbot.backup: "${ENABLE_BACKUPS:-true}"
-        backupbot.backup.pre-hook: 'mysqldump -u root -p"$(cat /run/secrets/db_root_password)" -f /volume_path/dump.db'
+        backupbot.backup.pre-hook: "/pg_backup.sh backup"
-        backupbot.backup.post-hook: "rm -rf /volume_path/dump.db"
+        backupbot.backup.volumes.db.path: "backup.sql"
+        backupbot.restore.post-hook: '/pg_backup.sh restore'
+        backupbot.backup.volumes.redis: "false"
 ```
 
 - `backupbot.backup` -- set to `true` to back up this service (REQUIRED)
-- `backupbot.backup.pre-hook` -- command to run before copying files (optional), save all dumps into the volumes
+    - this is the only required backup label, per default it will backup all volumes
-- `backupbot.backup.post-hook` -- command to run after copying files (optional)
+- `backupbot.backup.volumes.<volume_name>.path` -- only backup the listed relative paths from `<volume_name>`
+- `backupbot.backup.volumes.<volume_name>: false` -- exclude <volume_name> from the backup
+- `backupbot.backup.pre-hook` -- command to run before copying files
+    - i.e. save all database dumps into the volumes
+- `backupbot.backup.post-hook` -- command to run after copying files
+- `backupbot.restore.pre-hook` -- command to run before restoring files
+- `backupbot.restore.post-hook` -- command to run after restoring files
+    - i.e. read all database dumps from the volumes
+
+3. (Optional) add backup/restore scripts to the compose file
+
+```
+services:
+  db:
+    configs:
+        - source: pg_backup
+          target: /pg_backup.sh
+          mode: 0555
+
+
+configs:
+  pg_backup:
+    name: ${STACK_NAME}_pg_backup_${PG_BACKUP_VERSION}
+    file: pg_backup.sh
+```
+
+Version the config file in `abra.sh`:
+
+```
+export PG_BACKUP_VERSION=v1
+```
 
 As in the above example, you can reference Docker Secrets, e.g. for looking up database passwords, by reading the files in `/run/secrets` directly.
 

abra.sh

@@ -8,3 +8,7 @@ run_cron () {
     while [ ! -f /tmp/backup.log ]; do sleep 1; done
     echo "$schedule $(crontab -l | tr -s " " | cut -d ' ' -f6-)" | crontab -
 }
+
+setup_restic_s3() {
+    AWS_SECRET_ACCESS_KEY=$(cat /run/secrets/aws_secret_access_key) restic -r $RESTIC_REPOSITORY init
+}

backupbot.py

@@ -107,24 +107,26 @@ def create(retries):
 
 
 @cli.command()
-@click.option('snapshot', '--snapshot', '-s', envvar='SNAPSHOT', default='latest')
+@click.option('snapshot_id', '--snapshot', '-s', envvar='SNAPSHOT', default='latest')
 @click.option('target', '--target', '-t', envvar='TARGET', default='/')
 @click.option('noninteractive', '--noninteractive', envvar='NONINTERACTIVE', is_flag=True)
 @click.option('volumes', '--volumes', '-v', envvar='VOLUMES', multiple=True)
 @click.option('container', '--container', '-c', envvar='CONTAINER', multiple=True)
 @click.option('no_commands', '--no-commands', envvar='NO_COMMANDS', is_flag=True)
-def restore(snapshot, target, noninteractive, volumes, container, no_commands):
+def restore(snapshot_id, 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)
+    snapshots = get_snapshots(snapshot_id)
-    if not snapshot:
+    if not snapshots:
-        logger.error(f"No Snapshots with ID {snapshots} for {apps_versions.keys()} found.")
+        logger.error(f"No Snapshots with ID {snapshot_id} for {apps_versions.keys()} found.")
         exit(1)
+    snapshot = snapshots[0]
+    snapshot_id = snapshot['short_id']
     if not noninteractive:
-        print(f"Snapshot to restore: \t{snapshot}")
+        print(f"Snapshot to restore: \t{snapshot_id}")
-        restore_app_versions = app_versions_from_tags(snapshots[0].get('tags'))
+        restore_app_versions = app_versions_from_tags(snapshot.get('tags'))
         print("Apps:")
         for app, version in apps_versions.items():
             restore_version = restore_app_versions.get(app)
@@ -138,7 +140,7 @@ def restore(snapshot, target, noninteractive, volumes, container, 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'])
+        snapshot_date = datetime.fromisoformat(snapshot['time'])
         delta = datetime.now(tz=timezone.utc) - snapshot_date
         print(f"This snapshot is {delta} old")
         print("\nTHIS COMMAND WILL IRREVERSIBLY OVERWRITES FILES")
@@ -146,18 +148,18 @@ def restore(snapshot, target, noninteractive, volumes, container, no_commands):
         if prompt != 'YES':
             logger.error("Restore aborted")
             exit(1)
-    print(f"Restoring Snapshot {snapshot} at {target}")
+    print(f"Restoring Snapshot {snapshot_id} 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)
+    result = restic_restore(snapshot_id=snapshot_id, 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):
+def restic_restore(snapshot_id, include=[], target_dir=None):
     cmd = restic.cat.base_command() + ['restore', snapshot_id]
     for path in include:
         cmd.extend(['--include', path])
@@ -188,6 +190,10 @@ def app_versions_from_tags(tags):
     else:
         return {}
 
+def str2bool(value: str) -> bool:
+  return value.lower() in ("yes", "true", "t", "1")
+
+
 def parse_backup_labels(hook_type='backup', selected_container=[]):
     client = docker.from_env()
     container_by_service = {
@@ -201,7 +207,7 @@ def parse_backup_labels(hook_type='backup', selected_container=[]):
         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):
+        if (backup := labels.get('backupbot.backup')) and str2bool(backup):
             settings['enabled'] = True
         if version:
             settings['version'] = version
@@ -302,7 +308,7 @@ def parse_excludes_includes(labels):
             if label.endswith('path'): 
                 relative_paths = tuple(value.split(','))
                 included_volume_paths.add((volume_name, relative_paths))
-            elif bool(value):
+            elif not str2bool(value):
                 excluded_volumes.add(volume_name)
     return excluded_volumes, included_volume_paths
 
@@ -353,14 +359,14 @@ def run_commands(commands):
             logger.error(
                 f"Failed to run command {command} in {container.name}: {result.output.decode()}")
         else:
-            logger.info(result.output.decode())
+            logger.debug(result.output.decode())
 
 
 def backup_volumes(backup_paths, apps_versions, retries, dry_run=False):
     while True:
         try:
             logger.info("Backup these paths:")
-            logger.debug("\n".join(map(str, backup_paths)))
+            logger.info("\n".join(map(str, backup_paths)))
             backup_paths = list(filter(path_exists, backup_paths))
             cmd = restic.cat.base_command()
             parent = get_snapshots('latest') 
@@ -409,22 +415,31 @@ def snapshots():
 
 @cli.command()
 @click.option('snapshot', '--snapshot', '-s', envvar='SNAPSHOT', default='latest')
-@click.option('path', '--path', '-p', envvar='INCLUDE_PATH')
+@click.option('show_all', '--all', '-a', envvar='SHOW_ALL', is_flag=True)
-def ls(snapshot, path):
+@click.option('timestamps', '--timestamps', '-t', envvar='TIMESTAMPS', is_flag=True)
-    results = list_files(snapshot, path)
+@click.argument('path', required=False, default='/var/lib/docker/volumes/')
-    for r in results:
+def ls(snapshot, show_all, timestamps, path):
-        if r.get('path'):
-            print(f"{r['ctime']}\t{r['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 os.environ.get('INCLUDE_PATH'):
+        path = os.environ.get('INCLUDE_PATH')
+    if show_all:
+        path = None
+    results = list_files(snapshot, path)
+    for r in results:
+        if r.get('path'):
+            if timestamps:
+                print(f"{r['ctime']}\t{r['path']}")
+            else:
+                print(f"{r['path']}")
+
+
+def list_files(snapshot, path):
+    cmd = restic.cat.base_command() + ['ls']
     cmd.append(snapshot)
     if path:
         cmd.append(path)
@@ -451,6 +466,12 @@ def list_files(snapshot, path):
 @click.option('secrets', '--secrets', '-c', is_flag=True, envvar='SECRETS')
 def download(snapshot, path, volumes, secrets):
     file_dumps = []
+    if snapshot == 'latest':
+        latest_snapshot = get_snapshots('latest')
+        if not latest_snapshot:
+            logger.error(f"There is no latest snapshot for {SERVICE}")
+            exit(1)
+        snapshot = latest_snapshot[0]['short_id']
     if not any([path, volumes, secrets]):
         volumes = secrets = True
     if path:
@@ -515,13 +536,6 @@ 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)
     cmd = cmd + [snapshot, path]
     print(f"Dumping {path} from snapshot '{snapshot}'")
     output = subprocess.run(cmd, capture_output=True)

compose.yml

@@ -2,7 +2,7 @@
 version: "3.8"
 services:
   app:
-    image: git.coopcloud.tech/coop-cloud/backup-bot-two:2.2.1-beta
+    image: git.coopcloud.tech/coop-cloud/backup-bot-two:2.3.0-beta
     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.${STACK_NAME}.version=2.2.0+2.2.1-beta
+        - coop-cloud.${STACK_NAME}.version=2.3.0+2.3.0-beta
         - coop-cloud.${STACK_NAME}.timeout=${TIMEOUT:-300}
         - coop-cloud.backupbot.enabled=true
     #entrypoint: ['tail', '-f','/dev/null']

pg_backup.sh

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