Remove redundant stuff from entrypoint

Reviewed-on: #40

.drone.yml

@@ -2,11 +2,16 @@
 kind: pipeline
 name: linters
 steps:
-  - name: run shellcheck
-    image: koalaman/shellcheck-alpine
-    commands:
-      - shellcheck backup.sh
-
-trigger:
-  branch:
-    - main
+  - name: publish image
+    image: plugins/docker
+    settings:
+      username: 3wordchant
+      password:
+        from_secret: git_coopcloud_tech_token_3wc
+      repo: git.coopcloud.tech/coop-cloud/backup-bot-two
+      tags: 2.0.0
+      registry: git.coopcloud.tech
+    when:
+      event:
+        exclude:
+          - pull_request

.env.sample

@@ -8,6 +8,11 @@ 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"
 

Dockerfile

@@ -0,0 +1,10 @@
+FROM docker:24.0.7-dind
+
+RUN apk add --upgrade --no-cache restic bash python3 py3-pip
+
+# Todo use requirements file with specific versions
+RUN pip install click==8.1.7 docker==6.1.3 resticpy==1.0.2
+
+COPY backupbot.py /usr/bin/backup
+
+ENTRYPOINT /bin/bash

README.md

@@ -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 <app_name>`
+* `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/<app_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/<backupbot_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 <app_name> aws_secret_access_key v1 <SECRET_ACCESS_KEY>`
+`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.
 
@@ -79,9 +79,10 @@ 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 <app_name> ssh_key v1 """$(cat backupkey)
+abra app secret insert <backupbot_name> ssh_key v1 """$(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
 
@@ -94,67 +95,81 @@ COMPOSE_FILE="$COMPOSE_FILE:compose.secret.yml"
 ```
 Add your REST server url as secret:
 ```
-`abra app secret insert <app_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.
 
 
 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 <app_name> app -- backup create`
+`abra app run <backupbot_name> app -- backup create`
 
 > The apps to backup up need to be deployed
 
 Create an individual backup:
 
-`abra app run <app_name> app -- backup --host <target_app_name> create`
+`abra app run <backupbot_name> app -- backup --host <target_app_name> create`
 
 Create a backup to a local repository:
 
-`abra app run <app_name> app -- backup create -r /backups/restic`
+`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 <app_name> app -- backup restore`
+`abra app run <backupbot_name> app -- backup restore`
 
 Restore a specific snapshot of an individual app:
 
-`abra app run <app_name> app -- backup --host <target_app_name> restore --snapshot <snapshot_id>`
+`abra app run <backupbot_name> app -- backup --host <target_app_name> restore --snapshot <snapshot_id>`
 
 Show all snapshots:
 
-`abra app run <app_name> app -- backup snapshots`
+`abra app run <backupbot_name> app -- backup snapshots`
 
 Show all snapshots containing a specific app:
 
-`abra app run <app_name> app -- backup --host <target_app_name> snapshots`
+`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 <app_name> app -- backup ls`
+`abra app run <backupbot_name> app -- backup ls`
 
 Show specific files inside a selected snapshot:
 
-`abra app run <app_name> app -- backup ls --snapshot <snapshot_id> --path /var/lib/docker/volumes/`
+`abra app run <backupbot_name> app -- backup ls --snapshot <snapshot_id> --path /var/lib/docker/volumes/`
 
 Download files from a snapshot:
 
 ```
-filename=$(abra app run <app_name> app -- backup download --snapshot <snapshot_id> --path <absolute_path>)
-abra app cp <app_name> app:$filename .
+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 <app_name> app bash
+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

abra.sh

@@ -1,3 +1,11 @@
-export ENTRYPOINT_VERSION=v1
+export ENTRYPOINT_VERSION=v2
 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

@@ -1,6 +1,7 @@
 #!/usr/bin/python3
 
 import os
+import sys
 import click
 import json
 import subprocess
@@ -9,22 +10,40 @@ 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 = 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):
+def cli(loglevel, service, repository, machine_logs):
     global SERVICE
     if service:
         SERVICE = service.replace('.', '_')
@@ -34,14 +53,21 @@ def cli(loglevel, service, repository):
         numeric_level = getattr(logging, loglevel.upper(), None)
         if not isinstance(numeric_level, int):
             raise ValueError('Invalid log level: %s' % loglevel)
-        logging.basicConfig(level=numeric_level)
+        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']
-    logging.debug(f"set restic repository location: {repo}")
+    logger.debug(f"set restic repository location: {repo}")
     restic.repository = repo
     restic.password_file = '/var/run/secrets/restic_password'
     try:
@@ -49,7 +75,7 @@ def init_repo():
     except ResticFailedError as error:
         if 'unable to open config file' in str(error):
             result = restic.init()
-            logging.info(f"Initialized restic repo: {result}")
+            logger.info(f"Initialized restic repo: {result}")
         else:
             raise error
 
@@ -57,20 +83,21 @@ def init_repo():
 def export_secrets():
     for env in os.environ:
         if env.endswith('FILE') and not "COMPOSE_FILE" in env:
-            logging.debug(f"exported secret: {env}")
+            logger.debug(f"exported secret: {env}")
             with open(os.environ[env]) as file:
                 secret = file.read()
                 os.environ[env.removesuffix('_FILE')] = secret
-                # logging.debug(f"Read secret value: {secret}")
+                # logger.debug(f"Read secret value: {secret}")
 
 
 @cli.command()
-def create():
+@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)
+    backup_volumes(backup_paths, apps, int(retries))
     run_commands(post_commands)
 
 
@@ -86,6 +113,7 @@ def get_backup_cmds():
     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
@@ -94,8 +122,8 @@ def get_backup_cmds():
             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(
+            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'):
@@ -106,7 +134,7 @@ def get_backup_cmds():
 
 
 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()
@@ -118,14 +146,15 @@ def copy_secrets(apps):
         if (app_name in apps and
                 (app_secs := s.attrs['Spec']['TaskTemplate']['ContainerSpec'].get('Secrets'))):
             if not container_by_service.get(s.name):
-                logging.error(
+                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():
-                    logging.error(f"For the secret {sec['SecretName']} the file {src} does not exist for {s.name}")
+                    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)
@@ -136,37 +165,42 @@ def run_commands(commands):
         if not command:
             continue
         # Remove bash/sh wrapping
-        command = command.removeprefix('bash -c').removeprefix('sh -c')
+        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[1:-1]
+            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}'"
-        logging.info(f"run command in {container.name}:")
-        logging.info(command)
+        logger.info(f"run command in {container.name}:")
+        logger.info(command)
         result = container.exec_run(command)
         if result.exit_code:
-            logging.error(
+            logger.error(
                 f"Failed to run command {command} in {container.name}: {result.output.decode()}")
         else:
-            logging.info(result.output.decode())
+            logger.info(result.output.decode())
 
 
-def backup_volumes(backup_paths, apps, dry_run=False):
-    try:
-        result = restic.backup(backup_paths, dry_run=dry_run, tags=apps)
-        print(result)
-        logging.info(result)
-    except ResticFailedError as error:
-        logging.error(f"Backup failed for {apps}. Could not Backup these paths: {backup_paths}")
-        logging.error(error)
-        exit(1)
+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', default=False)
+@click.option('noninteractive', '--noninteractive', envvar='NONINTERACTIVE', is_flag=True)
 def restore(snapshot, target, noninteractive):
     # Todo: recommend to shutdown the container
     service_paths = VOLUME_PATH
@@ -174,7 +208,7 @@ def restore(snapshot, target, noninteractive):
         service_paths = service_paths + f'{SERVICE}_*'
     snapshots = restic.snapshots(snapshot_id=snapshot)
     if not snapshot:
-        logging.error("No Snapshots with ID {snapshots}")
+        logger.error("No Snapshots with ID {snapshots}")
         exit(1)
     if not noninteractive:
         snapshot_date = datetime.fromisoformat(snapshots[0]['time'])
@@ -186,12 +220,13 @@ def restore(snapshot, target, noninteractive):
             f"THIS COMMAND WILL IRREVERSIBLY OVERWRITES {target}{service_paths.removeprefix('/')}")
         prompt = input("Type YES (uppercase) to continue: ")
         if prompt != 'YES':
-            logging.error("Restore aborted")
+            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)
-    logging.debug(result)
+    logger.debug(result)
 
 
 @cli.command()
@@ -205,8 +240,9 @@ def snapshots():
     if no_snapshots:
         err_msg = "No Snapshots found"
         if SERVICE:
-            err_msg += f' for app {SERVICE}'
-        logging.warning(err_msg)
+            service_name = SERVICE.replace('_', '.')
+            err_msg += f' for app {service_name}'
+        logger.warning(err_msg)
 
 
 @cli.command()
@@ -230,10 +266,10 @@ 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}'
+            err_msg = f'There is no snapshot "{snapshot}"'
             if SERVICE:
-                err_msg += f'for the app {SERVICE}'
-            logging.error(err_msg)
+                err_msg += f' for the app "{SERVICE}"'
+            logger.error(err_msg)
             exit(1)
         else:
             raise error
@@ -245,8 +281,8 @@ 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', is_flag=True)
-@click.option('secrets', '--secrets', '-c', is_flag=True)
+@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]):
@@ -264,7 +300,7 @@ def download(snapshot, path, volumes, secrets):
         file_dumps.append((binary_output, tarinfo))
     if volumes:
         if not SERVICE:
-            logging.error("Please specify '--host' when using '--volumes'")
+            logger.error("Please specify '--host' when using '--volumes'")
             exit(1)
         files = list_files(snapshot, VOLUME_PATH)
         for f in files[1:]:
@@ -277,7 +313,7 @@ def download(snapshot, path, volumes, secrets):
                 file_dumps.append((binary_output, tarinfo))
     if secrets:
         if not SERVICE:
-            logging.error("Please specify '--host' when using '--secrets'")
+            logger.error("Please specify '--host' when using '--secrets'")
             exit(1)
         filename = f"{SERVICE}.json"
         files = list_files(snapshot, SECRET_PATH)
@@ -297,7 +333,8 @@ 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):
@@ -318,7 +355,7 @@ def dump(snapshot, path):
     print(f"Dumping {path} from snapshot '{snapshot}'")
     output = subprocess.run(cmd, capture_output=True)
     if output.returncode:
-        logging.error(
+        logger.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: docker:24.0.7-dind
+    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/"
@@ -23,10 +23,8 @@ services:
       - source: entrypoint
         target: /entrypoint.sh
         mode: 0555
-      - source: backupbot
-        target: /usr/bin/backup
-        mode: 0555
     entrypoint: ['/entrypoint.sh']
+   #entrypoint: ['tail', '-f','/dev/null']
     healthcheck:
       test: "pgrep crond"
       interval: 30s
@@ -46,6 +44,3 @@ configs:
   entrypoint:
     name: ${STACK_NAME}_entrypoint_${ENTRYPOINT_VERSION}
     file: entrypoint.sh
-  backupbot:
-    name: ${STACK_NAME}_backupbot_${BACKUPBOT_VERSION}
-    file: backupbot.py

entrypoint.sh

@@ -2,10 +2,10 @@
 
 set -e -o pipefail
 
-apk add --upgrade --no-cache restic bash python3 py3-pip
+apk add --upgrade --no-cache restic bash python3 py3-pip py3-click py3-docker-py py3-json-logger curl
 
 # Todo use requirements file with specific versions
-pip install click==8.1.7 docker==6.1.3 resticpy==1.0.2
+pip install --break-system-packages resticpy==1.0.2
 
 if [ -n "$SSH_HOST_KEY" ]
 then
@@ -14,7 +14,22 @@ fi
 
 cron_schedule="${CRON_SCHEDULE:?CRON_SCHEDULE not set}"
 
-echo "$cron_schedule backup create" | crontab -
+if [ -n "$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