Compare commits
1 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
| a9128e8450 |
17
.drone.yml
17
.drone.yml
@ -1,17 +0,0 @@
|
||||
---
|
||||
kind: pipeline
|
||||
name: linters
|
||||
steps:
|
||||
- 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
|
||||
40
.env.sample
40
.env.sample
@ -1,40 +0,0 @@
|
||||
TYPE=backup-bot-two
|
||||
|
||||
SECRET_RESTIC_PASSWORD_VERSION=v1
|
||||
|
||||
COMPOSE_FILE=compose.yml
|
||||
|
||||
RESTIC_REPOSITORY=/backups/restic
|
||||
|
||||
CRON_SCHEDULE='30 3 * * *'
|
||||
|
||||
# Push Notifiactions
|
||||
#PUSH_PROMETHEUS_URL=https://pushgateway.example.com/metrics/job/backup
|
||||
# or
|
||||
#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
|
||||
|
||||
# Push Basic Auth
|
||||
#COMPOSE_FILE="$COMPOSE_FILE:compose.pushbasicauth.yml"
|
||||
#SECRET_PUSH_BASICAUTH=v1
|
||||
|
||||
# swarm-cronjob, instead of built-in cron
|
||||
#COMPOSE_FILE="$COMPOSE_FILE:compose.swarm-cronjob.yml"
|
||||
|
||||
# SSH storage
|
||||
#SECRET_SSH_KEY_VERSION=v1
|
||||
#SSH_HOST_KEY="hostname ssh-rsa AAAAB3...
|
||||
#COMPOSE_FILE="$COMPOSE_FILE:compose.ssh.yml"
|
||||
|
||||
# S3 storage
|
||||
#SECRET_AWS_SECRET_ACCESS_KEY_VERSION=v1
|
||||
#AWS_ACCESS_KEY_ID=something-secret
|
||||
#COMPOSE_FILE="$COMPOSE_FILE:compose.s3.yml"
|
||||
|
||||
# Secret restic repository
|
||||
# use a secret to store the RESTIC_REPOSITORY if the repository location contains a secret value
|
||||
# i.E rest:https://user:SECRET_PASSWORD@host:8000/
|
||||
# it overwrites the RESTIC_REPOSITORY variable
|
||||
#SECRET_RESTIC_REPO_VERSION=v1
|
||||
#COMPOSE_FILE="$COMPOSE_FILE:compose.secret.yml"
|
||||
@ -1,17 +0,0 @@
|
||||
export RESTIC_HOST="user@domain.tld"
|
||||
export RESTIC_PASSWORD_FILE=/run/secrets/restic-password
|
||||
export BACKUP_DEST=/backups
|
||||
|
||||
export SERVER_NAME=domain.tld
|
||||
export DOCKER_CONTEXT=$SERVER_NAME
|
||||
|
||||
# uncomment either this:
|
||||
#export SSH_KEY_FILE=~/.ssh/id_rsa
|
||||
# or this:
|
||||
#export AWS_SECRET_ACCESS_KEY_FILE=s3
|
||||
#export AWS_ACCESS_KEY_ID=easter-october-emphatic-tug-urgent-customer
|
||||
# or this:
|
||||
#export HTTPS_PASSWORD_FILE=/run/secrets/https_password
|
||||
|
||||
# optionally limit subset of services for testing
|
||||
#export SERVICES_OVERRIDE="ghost_domain_tld_app ghost_domain_tld_db"
|
||||
1
.gitignore
vendored
1
.gitignore
vendored
@ -1 +0,0 @@
|
||||
/testing
|
||||
@ -1,6 +0,0 @@
|
||||
# Change log
|
||||
|
||||
## 2.0.0 (unreleased)
|
||||
|
||||
- Rewrite from Bash to Python
|
||||
- Add support for push notifications (#24)
|
||||
17
Dockerfile
17
Dockerfile
@ -1,11 +1,14 @@
|
||||
FROM docker:24.0.7-dind
|
||||
FROM alpine:3
|
||||
|
||||
RUN apk add --upgrade --no-cache restic bash python3 py3-pip py3-click py3-docker-py py3-json-logger curl
|
||||
ENV RESTIC_PASSWORD_FILE=
|
||||
ENV RESTIC_REPOSITORY=
|
||||
ENV AWS_ACCESS_KEY_ID=
|
||||
ENV AWS_SECRET_ACCESS_KEY=
|
||||
|
||||
# Todo use requirements file with specific versions
|
||||
RUN pip install --break-system-packages resticpy==1.0.2
|
||||
RUN apk add --update --no-cache docker-cli bash jq restic
|
||||
|
||||
COPY backupbot.py /usr/bin/backup
|
||||
COPY entrypoint.sh /entrypoint.sh
|
||||
RUN echo "* * * * * /backup.sh" | crontab -
|
||||
RUN crontab -l
|
||||
COPY backup.sh /
|
||||
|
||||
ENTRYPOINT /entrypoint.sh
|
||||
ENTRYPOINT ["crond", "-f", "-L", "/dev/stdout"]
|
||||
|
||||
240
README.md
240
README.md
@ -1,221 +1,45 @@
|
||||
# Backupbot II
|
||||
# Backupbot II: This Time It's Easily Configurable
|
||||
|
||||
[](https://build.coopcloud.tech/coop-cloud/backup-bot-two)
|
||||
Automatically backup files from running Docker Swarm services based on labels.
|
||||
|
||||
_This Time, It's Easily Configurable_
|
||||
## TODO
|
||||
|
||||
Automatically take backups from all volumes of running Docker Swarm services and runs pre- and post commands.
|
||||
- [ ] Make a Docker image of this
|
||||
- [ ] Rip out or improve Restic stuff
|
||||
- [ ] Add secret handling for database backups
|
||||
- [ ] Continuous linting with shellcheck
|
||||
|
||||
<!-- metadata -->
|
||||
## Label format
|
||||
|
||||
* **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
|
||||
* **Healthcheck**: No
|
||||
* **Backups**: N/A
|
||||
* **Email**: N/A
|
||||
* **Tests**: No
|
||||
* **SSO**: N/A
|
||||
(Haven't done secrets yet, here are two options)
|
||||
|
||||
<!-- endmetadata -->
|
||||
|
||||
|
||||
## Background
|
||||
|
||||
There are lots of Docker volume backup systems; all of them have one or both of these limitations:
|
||||
- You need to define all the volumes to back up in the configuration system
|
||||
- Backups require services to be stopped to take consistent copies
|
||||
|
||||
Backupbot II tries to help, by
|
||||
1. **letting you define backups using Docker labels**, so you can **easily collect your backups for use with another system** like docker-volume-backup.
|
||||
2. **running pre- and post-commands** before and after backups, for example to use database tools to take a backup from a running service.
|
||||
|
||||
## Deployment
|
||||
|
||||
### With Co-op Cloud
|
||||
|
||||
|
||||
* `abra app new backup-bot-two`
|
||||
* `abra app config <app-name>`
|
||||
- set storage options. Either configure `CRON_SCHEDULE`, or set up `swarm-cronjob`
|
||||
* `abra app secret generate -a <backupbot_name>`
|
||||
* `abra app deploy <app-name>`
|
||||
|
||||
## Configuration
|
||||
|
||||
Per default Backupbot stores the backups locally in the repository `/backups/restic`, which is accessible as volume at `/var/lib/docker/volumes/<backupbot_name>_backups/_data/restic/`
|
||||
|
||||
The backup location can be changed using the `RESTIC_REPOSITORY` env variable.
|
||||
|
||||
### S3 Storage
|
||||
|
||||
To use S3 storage as backup location set the following envs:
|
||||
v1:
|
||||
```
|
||||
RESTIC_REPOSITORY=s3:<S3-SERVICE-URL>/<BUCKET-NAME>
|
||||
SECRET_AWS_SECRET_ACCESS_KEY_VERSION=v1
|
||||
AWS_ACCESS_KEY_ID=<MY_ACCESS_KEY>
|
||||
COMPOSE_FILE="$COMPOSE_FILE:compose.s3.yml"
|
||||
```
|
||||
and add your `<SECRET_ACCESS_KEY>` as docker secret:
|
||||
`abra app secret insert <backupbot_name> aws_secret_access_key v1 <SECRET_ACCESS_KEY>`
|
||||
|
||||
See [restic s3 docs](https://restic.readthedocs.io/en/latest/030_preparing_a_new_repo.html#amazon-s3) for more information.
|
||||
|
||||
### SFTP Storage
|
||||
|
||||
> With sftp it is not possible to prevent the backupbot from deleting backups in case of a compromised machine. Therefore we recommend to use S3, REST or rclone server without delete permissions.
|
||||
|
||||
To use SFTP storage as backup location set the following envs:
|
||||
```
|
||||
RESTIC_REPOSITORY=sftp:user@host:/restic-repo-path
|
||||
SECRET_SSH_KEY_VERSION=v1
|
||||
SSH_HOST_KEY="hostname ssh-rsa AAAAB3...
|
||||
COMPOSE_FILE="$COMPOSE_FILE:compose.ssh.yml"
|
||||
```
|
||||
To get the `SSH_HOST_KEY` run the following command `ssh-keyscan <hostname>`
|
||||
|
||||
Generate an ssh keypair: `ssh-keygen -t ed25519 -f backupkey -P ''`
|
||||
Add the key to your `authorized_keys`:
|
||||
`ssh-copy-id -i backupkey <user>@<hostname>`
|
||||
Add your `SSH_KEY` as docker secret:
|
||||
```
|
||||
abra app secret insert <backupbot_name> ssh_key v1 """$(cat backupkey)
|
||||
"""
|
||||
```
|
||||
> Attention: This command needs to be executed exactly as stated above, because it places a trailing newline at the end, if this is missing you will get the following error: `Load key "/run/secrets/ssh_key": error in libcrypto`
|
||||
|
||||
### Restic REST server Storage
|
||||
|
||||
You can simply set the `RESTIC_REPOSITORY` variable to your REST server URL `rest:http://host:8000/`.
|
||||
If you access the REST server with a password `rest:https://user:pass@host:8000/` you should hide the whole URL containing the password inside a secret.
|
||||
Uncomment these lines:
|
||||
```
|
||||
SECRET_RESTIC_REPO_VERSION=v1
|
||||
COMPOSE_FILE="$COMPOSE_FILE:compose.secret.yml"
|
||||
```
|
||||
Add your REST server url as secret:
|
||||
```
|
||||
`abra app secret insert <backupbot_name> restic_repo v1 "rest:https://user:pass@host:8000/"`
|
||||
```
|
||||
The secret will overwrite the `RESTIC_REPOSITORY` variable.
|
||||
|
||||
|
||||
See [restic REST docs](https://restic.readthedocs.io/en/latest/030_preparing_a_new_repo.html#rest-server) for more information.
|
||||
|
||||
## Push notifications
|
||||
|
||||
It is possible to configure three push events, that may trigger on the backup cronjob. Those can be used to detect failures from mointoring systems.
|
||||
The events are:
|
||||
- start
|
||||
- success
|
||||
- fail
|
||||
|
||||
### Using a Prometheus Push Gateway
|
||||
|
||||
[A prometheus push gateway](https://git.coopcloud.tech/coop-cloud/monitoring-ng#setup-push-gateway) can be used by setting the following env variables:
|
||||
- `PUSH_PROMETHEUS_URL=pushgateway.example.com/metrics/job/backup`
|
||||
|
||||
### Using custom URLs
|
||||
|
||||
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
|
||||
```
|
||||
|
||||
### Push endpoint behind basic auth
|
||||
|
||||
Insert the basic auth secret
|
||||
`abra app secret insert <backupbot_name> push_basicauth v1 "user:password"`
|
||||
|
||||
Enable basic auth in the env file, by uncommenting the following line:
|
||||
```
|
||||
#COMPOSE_FILE="$COMPOSE_FILE:compose.pushbasicauth.yml"
|
||||
#SECRET_PUSH_BASICAUTH=v1
|
||||
```
|
||||
|
||||
## Usage
|
||||
|
||||
Run the cronjob that creates a backup, including the push notifications and docker logging:
|
||||
`abra app cmd <backupbot_name> app run_cron`
|
||||
|
||||
Create a backup of all apps:
|
||||
|
||||
`abra app run <backupbot_name> app -- backup create`
|
||||
|
||||
> The apps to backup up need to be deployed
|
||||
|
||||
Create an individual backup:
|
||||
|
||||
`abra app run <backupbot_name> app -- backup --host <target_app_name> create`
|
||||
|
||||
Create a backup to a local repository:
|
||||
|
||||
`abra app run <backupbot_name> app -- backup create -r /backups/restic`
|
||||
|
||||
> It is recommended to shutdown/undeploy an app before restoring the data
|
||||
|
||||
Restore the latest snapshot of all including apps:
|
||||
|
||||
`abra app run <backupbot_name> app -- backup restore`
|
||||
|
||||
Restore a specific snapshot of an individual app:
|
||||
|
||||
`abra app run <backupbot_name> app -- backup --host <target_app_name> restore --snapshot <snapshot_id>`
|
||||
|
||||
Show all snapshots:
|
||||
|
||||
`abra app run <backupbot_name> app -- backup snapshots`
|
||||
|
||||
Show all snapshots containing a specific app:
|
||||
|
||||
`abra app run <backupbot_name> app -- backup --host <target_app_name> snapshots`
|
||||
|
||||
Show all files inside the latest snapshot (can be very verbose):
|
||||
|
||||
`abra app run <backupbot_name> app -- backup ls`
|
||||
|
||||
Show specific files inside a selected snapshot:
|
||||
|
||||
`abra app run <backupbot_name> app -- backup ls --snapshot <snapshot_id> --path /var/lib/docker/volumes/`
|
||||
|
||||
Download files from a snapshot:
|
||||
|
||||
```
|
||||
filename=$(abra app run <backupbot_name> app -- backup download --snapshot <snapshot_id> --path <absolute_path>)
|
||||
abra app cp <backupbot_name> app:$filename .
|
||||
```
|
||||
|
||||
## Run restic
|
||||
|
||||
```
|
||||
abra app run <backupbot_name> app bash
|
||||
export AWS_SECRET_ACCESS_KEY=$(cat $AWS_SECRET_ACCESS_KEY_FILE)
|
||||
export RESTIC_PASSWORD=$(cat $RESTIC_PASSWORD_FILE)
|
||||
restic snapshots
|
||||
```
|
||||
|
||||
## Recipe Configuration
|
||||
|
||||
Like Traefik, or `swarm-cronjob`, Backupbot II uses access to the Docker socket to read labels from running Docker Swarm services:
|
||||
|
||||
```
|
||||
services:
|
||||
db:
|
||||
deploy:
|
||||
labels:
|
||||
backupbot.backup: ${BACKUP:-"true"}
|
||||
backupbot.backup.pre-hook: 'mysqldump -u root -p"$(cat /run/secrets/db_root_password)" -f /volume_path/dump.db'
|
||||
backupbot.backup.post-hook: "rm -rf /volume_path/dump.db"
|
||||
backupbot.backup: "true"
|
||||
backupbot.backup.repos: "$some_thing"
|
||||
backupbot.backup.at: "* * * * *"
|
||||
backupbot.backup.pre-hook: 'mysqldump -u root -p"$(cat /run/secrets/db_root_password)" -f /tmp/dump/dump.db'
|
||||
backupbot.backup.post-hook: "rm -rf /tmp/dump/dump.db"
|
||||
backupbot.backup.path: "/tmp/dump/"
|
||||
```
|
||||
v2:
|
||||
```
|
||||
deploy:
|
||||
labels:
|
||||
backupbot.backup: "true"
|
||||
backupbot.backup.repos: "$some_thing"
|
||||
backupbot.backup.at: "* * * * *"
|
||||
backupbot.backup.post-hook: "rm -rf /tmp/dump/dump.db"
|
||||
backupbot.backup.secrets": "db_root_password",
|
||||
backupbot.backup.pre-hook: 'mysqldump -u root -p"$DB_ROOT_PASSWORD" -f /tmp/dump/dump.db'
|
||||
```
|
||||
|
||||
- `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
|
||||
- `backupbot.backup.post-hook` -- command to run after copying files (optional)
|
||||
## Questions:
|
||||
|
||||
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.
|
||||
- Should frequency be configurable per service, centrally, or both?
|
||||
|
||||
[abra]: https://git.autonomic.zone/autonomic-cooperative/abra
|
||||
```
|
||||
- "backupbot.backup.at: "* * * * *"
|
||||
```
|
||||
|
||||
12
abra.sh
12
abra.sh
@ -1,12 +0,0 @@
|
||||
export BACKUPBOT_VERSION=v1
|
||||
export SSH_CONFIG_VERSION=v1
|
||||
export ENTRYPOINT_VERSION=v17
|
||||
export CRONJOB_VERSION=v2
|
||||
|
||||
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 -
|
||||
}
|
||||
59
backup.sh
Executable file
59
backup.sh
Executable file
@ -0,0 +1,59 @@
|
||||
#!/bin/bash
|
||||
|
||||
### FIXME: just for testing
|
||||
echo $RESTIC_PASSWORD_FILE
|
||||
echo $RESTIC_REPOSITORY
|
||||
echo $AWS_ACCESS_KEY_ID
|
||||
echo $AWS_SECRET_ACCESS_KEY
|
||||
|
||||
export DOCKER_CONTEXT=default
|
||||
|
||||
mkdir /tmp/backups
|
||||
backup_path=/tmp/backups
|
||||
|
||||
mapfile -t services < <(docker service ls --format '{{ .Name }}')
|
||||
|
||||
# FIXME: just for testing
|
||||
services=("cloud_local_db")
|
||||
|
||||
for service in "${services[@]}"; do
|
||||
echo "service: $service"
|
||||
details=$(docker service inspect "$service" --format "{{ json .Spec.Labels }}")
|
||||
if echo "$details" | jq -r '.["backupbot.backup"]' | grep -q 'true'; then
|
||||
pre=$(echo "$details" | jq -r '.["backupbot.backup.pre-hook"]')
|
||||
post=$(echo "$details" | jq -r '.["backupbot.backup.post-hook"]')
|
||||
path=$(echo "$details" | jq -r '.["backupbot.backup.path"]')
|
||||
|
||||
if [ "$path" = "null" ]; then
|
||||
echo "ERROR: missing 'path' for $service"
|
||||
continue # or maybe exit?
|
||||
fi
|
||||
|
||||
container=$(docker container ls -f "name=$service" --format '{{ .ID }}')
|
||||
|
||||
echo "backing up $service"
|
||||
test -d "$backup_path/$service" || mkdir "$backup_path/$service"
|
||||
|
||||
if [ "$pre" != "null" ]; then
|
||||
# run the precommand
|
||||
# shellcheck disable=SC2086
|
||||
docker exec "$container" $pre
|
||||
fi
|
||||
|
||||
# run the backup
|
||||
docker cp -a "$container:$path" "$backup_path/$service"
|
||||
|
||||
if [ "$post" != "null" ]; then
|
||||
# run the postcommand
|
||||
# shellcheck disable=SC2086
|
||||
docker exec "$container" $post
|
||||
fi
|
||||
fi
|
||||
|
||||
# Check if restic repo exists
|
||||
if [ -z "$(restic cat config)" ] 2>/dev/null; then
|
||||
echo "initializing restic repo"
|
||||
restic init "$backup_path"
|
||||
fi
|
||||
restic backup --tag coop-cloud "$backup_path" # --quiet
|
||||
done
|
||||
372
backupbot.py
372
backupbot.py
@ -1,372 +0,0 @@
|
||||
#!/usr/bin/python3
|
||||
|
||||
import os
|
||||
import sys
|
||||
import click
|
||||
import json
|
||||
import subprocess
|
||||
import logging
|
||||
import docker
|
||||
import restic
|
||||
import tarfile
|
||||
import io
|
||||
from pythonjsonlogger import jsonlogger
|
||||
from datetime import datetime, timezone
|
||||
from restic.errors import ResticFailedError
|
||||
from pathlib import Path
|
||||
from shutil import copyfile, rmtree
|
||||
|
||||
VOLUME_PATH = "/var/lib/docker/volumes/"
|
||||
SECRET_PATH = '/secrets/'
|
||||
SERVICE = None
|
||||
|
||||
logger = logging.getLogger("backupbot")
|
||||
logging.addLevelName(55, 'SUMMARY')
|
||||
setattr(logging, 'SUMMARY', 55)
|
||||
setattr(logger, 'summary', lambda message, *args, **
|
||||
kwargs: logger.log(55, message, *args, **kwargs))
|
||||
|
||||
|
||||
def handle_exception(exc_type, exc_value, exc_traceback):
|
||||
if issubclass(exc_type, KeyboardInterrupt):
|
||||
sys.__excepthook__(exc_type, exc_value, exc_traceback)
|
||||
return
|
||||
logger.critical("Uncaught exception", exc_info=(
|
||||
exc_type, exc_value, exc_traceback))
|
||||
|
||||
|
||||
sys.excepthook = handle_exception
|
||||
|
||||
|
||||
@click.group()
|
||||
@click.option('-l', '--log', 'loglevel')
|
||||
@click.option('-m', '--machine-logs', 'machine_logs', is_flag=True)
|
||||
@click.option('service', '--host', '-h', envvar='SERVICE')
|
||||
@click.option('repository', '--repo', '-r', envvar='RESTIC_REPOSITORY')
|
||||
def cli(loglevel, service, repository, machine_logs):
|
||||
global SERVICE
|
||||
if service:
|
||||
SERVICE = service.replace('.', '_')
|
||||
if repository:
|
||||
os.environ['RESTIC_REPOSITORY'] = repository
|
||||
if loglevel:
|
||||
numeric_level = getattr(logging, loglevel.upper(), None)
|
||||
if not isinstance(numeric_level, int):
|
||||
raise ValueError('Invalid log level: %s' % loglevel)
|
||||
logger.setLevel(numeric_level)
|
||||
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)
|
||||
|
||||
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']
|
||||
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}")
|
||||
else:
|
||||
raise error
|
||||
|
||||
|
||||
def export_secrets():
|
||||
for env in os.environ:
|
||||
if env.endswith('FILE') and not "COMPOSE_FILE" in env:
|
||||
logger.debug(f"exported secret: {env}")
|
||||
with open(os.environ[env]) as file:
|
||||
secret = file.read()
|
||||
os.environ[env.removesuffix('_FILE')] = secret
|
||||
# logger.debug(f"Read secret value: {secret}")
|
||||
|
||||
|
||||
@cli.command()
|
||||
@click.option('retries', '--retries', '-r', envvar='RETRIES', default=1)
|
||||
def create(retries):
|
||||
pre_commands, post_commands, backup_paths, apps = get_backup_cmds()
|
||||
copy_secrets(apps)
|
||||
backup_paths.append(SECRET_PATH)
|
||||
run_commands(pre_commands)
|
||||
backup_volumes(backup_paths, apps, int(retries))
|
||||
run_commands(post_commands)
|
||||
|
||||
|
||||
def get_backup_cmds():
|
||||
client = docker.from_env()
|
||||
container_by_service = {
|
||||
c.labels.get('com.docker.swarm.service.name'): c for c in client.containers.list()}
|
||||
backup_paths = set()
|
||||
backup_apps = set()
|
||||
pre_commands = {}
|
||||
post_commands = {}
|
||||
services = client.services.list()
|
||||
for s in services:
|
||||
labels = s.attrs['Spec']['Labels']
|
||||
if (backup := labels.get('backupbot.backup')) and bool(backup):
|
||||
# volumes: s.attrs['Spec']['TaskTemplate']['ContainerSpec']['Mounts'][0]['Source']
|
||||
stack_name = labels['com.docker.stack.namespace']
|
||||
# Remove this lines to backup only a specific service
|
||||
# This will unfortenately decrease restice performance
|
||||
# if SERVICE and SERVICE != stack_name:
|
||||
# continue
|
||||
backup_apps.add(stack_name)
|
||||
backup_paths = backup_paths.union(
|
||||
Path(VOLUME_PATH).glob(f"{stack_name}_*"))
|
||||
if not (container := container_by_service.get(s.name)):
|
||||
logger.error(
|
||||
f"Container {s.name} is not running, hooks can not be executed")
|
||||
continue
|
||||
if prehook := labels.get('backupbot.backup.pre-hook'):
|
||||
pre_commands[container] = prehook
|
||||
if posthook := labels.get('backupbot.backup.post-hook'):
|
||||
post_commands[container] = posthook
|
||||
return pre_commands, post_commands, list(backup_paths), list(backup_apps)
|
||||
|
||||
|
||||
def copy_secrets(apps):
|
||||
# TODO: check if it is deployed
|
||||
rmtree(SECRET_PATH, ignore_errors=True)
|
||||
os.mkdir(SECRET_PATH)
|
||||
client = docker.from_env()
|
||||
container_by_service = {
|
||||
c.labels.get('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(
|
||||
f"Container {s.name} is not running, secrets can not be copied.")
|
||||
continue
|
||||
container_id = container_by_service[s.name].id
|
||||
for sec in app_secs:
|
||||
src = f'/var/lib/docker/containers/{container_id}/mounts/secrets/{sec["SecretID"]}'
|
||||
if not Path(src).exists():
|
||||
logger.error(
|
||||
f"For the secret {sec['SecretName']} the file {src} does not exist for {s.name}")
|
||||
continue
|
||||
dst = SECRET_PATH + sec['SecretName']
|
||||
logger.debug("Copy Secret {sec['SecretName']}")
|
||||
copyfile(src, dst)
|
||||
|
||||
|
||||
def run_commands(commands):
|
||||
for container, command in commands.items():
|
||||
if not command:
|
||||
continue
|
||||
# Remove bash/sh wrapping
|
||||
command = command.removeprefix('bash -c').removeprefix('sh -c').removeprefix(' ')
|
||||
# Remove quotes surrounding the command
|
||||
if (len(command) >= 2 and command[0] == command[-1] and (command[0] == "'" or command[0] == '"')):
|
||||
command = command[1:-1]
|
||||
# Use bash's pipefail to return exit codes inside a pipe to prevent silent failure
|
||||
command = f"bash -c 'set -o pipefail;{command}'"
|
||||
logger.info(f"run command in {container.name}:")
|
||||
logger.info(command)
|
||||
result = container.exec_run(command)
|
||||
if result.exit_code:
|
||||
logger.error(
|
||||
f"Failed to run command {command} in {container.name}: {result.output.decode()}")
|
||||
else:
|
||||
logger.info(result.output.decode())
|
||||
|
||||
|
||||
def backup_volumes(backup_paths, apps, retries, dry_run=False):
|
||||
while True:
|
||||
try:
|
||||
logger.info("Start volume backup")
|
||||
logger.debug(backup_paths)
|
||||
result = restic.backup(backup_paths, dry_run=dry_run, tags=apps)
|
||||
logger.summary("backup finished", extra=result)
|
||||
return
|
||||
except ResticFailedError as error:
|
||||
logger.error(
|
||||
f"Backup failed for {apps}. Could not Backup these paths: {backup_paths}")
|
||||
logger.error(error, exc_info=True)
|
||||
if retries > 0:
|
||||
retries -= 1
|
||||
else:
|
||||
exit(1)
|
||||
|
||||
|
||||
@cli.command()
|
||||
@click.option('snapshot', '--snapshot', '-s', envvar='SNAPSHOT', default='latest')
|
||||
@click.option('target', '--target', '-t', envvar='TARGET', default='/')
|
||||
@click.option('noninteractive', '--noninteractive', envvar='NONINTERACTIVE', is_flag=True)
|
||||
def restore(snapshot, target, noninteractive):
|
||||
# Todo: recommend to shutdown the container
|
||||
service_paths = VOLUME_PATH
|
||||
if SERVICE:
|
||||
service_paths = service_paths + f'{SERVICE}_*'
|
||||
snapshots = restic.snapshots(snapshot_id=snapshot)
|
||||
if not snapshot:
|
||||
logger.error("No Snapshots with ID {snapshots}")
|
||||
exit(1)
|
||||
if not noninteractive:
|
||||
snapshot_date = datetime.fromisoformat(snapshots[0]['time'])
|
||||
delta = datetime.now(tz=timezone.utc) - snapshot_date
|
||||
print(
|
||||
f"You are going to restore Snapshot {snapshot} of {service_paths} at {target}")
|
||||
print(f"This snapshot is {delta} old")
|
||||
print(
|
||||
f"THIS COMMAND WILL IRREVERSIBLY OVERWRITES {target}{service_paths.removeprefix('/')}")
|
||||
prompt = input("Type YES (uppercase) to continue: ")
|
||||
if prompt != 'YES':
|
||||
logger.error("Restore aborted")
|
||||
exit(1)
|
||||
print(f"Restoring Snapshot {snapshot} of {service_paths} at {target}")
|
||||
# TODO: use tags if no snapshot is selected, to use a snapshot including SERVICE
|
||||
result = restic.restore(snapshot_id=snapshot,
|
||||
include=service_paths, target_dir=target)
|
||||
logger.debug(result)
|
||||
|
||||
|
||||
@cli.command()
|
||||
def snapshots():
|
||||
snapshots = restic.snapshots()
|
||||
no_snapshots = True
|
||||
for snap in snapshots:
|
||||
if not SERVICE or (tags := snap.get('tags')) and SERVICE in tags:
|
||||
print(snap['time'], snap['id'])
|
||||
no_snapshots = False
|
||||
if no_snapshots:
|
||||
err_msg = "No Snapshots found"
|
||||
if SERVICE:
|
||||
service_name = SERVICE.replace('_', '.')
|
||||
err_msg += f' for app {service_name}'
|
||||
logger.warning(err_msg)
|
||||
|
||||
|
||||
@cli.command()
|
||||
@click.option('snapshot', '--snapshot', '-s', envvar='SNAPSHOT', default='latest')
|
||||
@click.option('path', '--path', '-p', envvar='INCLUDE_PATH')
|
||||
def ls(snapshot, path):
|
||||
results = list_files(snapshot, path)
|
||||
for r in results:
|
||||
if r.get('path'):
|
||||
print(f"{r['ctime']}\t{r['path']}")
|
||||
|
||||
|
||||
def list_files(snapshot, path):
|
||||
cmd = restic.cat.base_command() + ['ls']
|
||||
if SERVICE:
|
||||
cmd = cmd + ['--tag', SERVICE]
|
||||
cmd.append(snapshot)
|
||||
if path:
|
||||
cmd.append(path)
|
||||
try:
|
||||
output = restic.internal.command_executor.execute(cmd)
|
||||
except ResticFailedError as error:
|
||||
if 'no snapshot found' in str(error):
|
||||
err_msg = f'There is no snapshot "{snapshot}"'
|
||||
if SERVICE:
|
||||
err_msg += f' for the app "{SERVICE}"'
|
||||
logger.error(err_msg)
|
||||
exit(1)
|
||||
else:
|
||||
raise error
|
||||
output = output.replace('}\n{', '}|{')
|
||||
results = list(map(json.loads, output.split('|')))
|
||||
return results
|
||||
|
||||
|
||||
@cli.command()
|
||||
@click.option('snapshot', '--snapshot', '-s', envvar='SNAPSHOT', default='latest')
|
||||
@click.option('path', '--path', '-p', envvar='INCLUDE_PATH')
|
||||
@click.option('volumes', '--volumes', '-v', envvar='VOLUMES')
|
||||
@click.option('secrets', '--secrets', '-c', is_flag=True, envvar='SECRETS')
|
||||
def download(snapshot, path, volumes, secrets):
|
||||
file_dumps = []
|
||||
if not any([path, volumes, secrets]):
|
||||
volumes = secrets = True
|
||||
if path:
|
||||
path = path.removesuffix('/')
|
||||
binary_output = dump(snapshot, path)
|
||||
files = list_files(snapshot, path)
|
||||
filetype = [f.get('type') for f in files if f.get('path') == path][0]
|
||||
filename = Path(path).name
|
||||
if filetype == 'dir':
|
||||
filename = filename + ".tar"
|
||||
tarinfo = tarfile.TarInfo(name=filename)
|
||||
tarinfo.size = len(binary_output)
|
||||
file_dumps.append((binary_output, tarinfo))
|
||||
if volumes:
|
||||
if not SERVICE:
|
||||
logger.error("Please specify '--host' when using '--volumes'")
|
||||
exit(1)
|
||||
files = list_files(snapshot, VOLUME_PATH)
|
||||
for f in files[1:]:
|
||||
path = f['path']
|
||||
if Path(path).name.startswith(SERVICE) and f['type'] == 'dir':
|
||||
binary_output = dump(snapshot, path)
|
||||
filename = f"{Path(path).name}.tar"
|
||||
tarinfo = tarfile.TarInfo(name=filename)
|
||||
tarinfo.size = len(binary_output)
|
||||
file_dumps.append((binary_output, tarinfo))
|
||||
if secrets:
|
||||
if not SERVICE:
|
||||
logger.error("Please specify '--host' when using '--secrets'")
|
||||
exit(1)
|
||||
filename = f"{SERVICE}.json"
|
||||
files = list_files(snapshot, SECRET_PATH)
|
||||
secrets = {}
|
||||
for f in files[1:]:
|
||||
path = f['path']
|
||||
if Path(path).name.startswith(SERVICE) and f['type'] == 'file':
|
||||
secret = dump(snapshot, path).decode()
|
||||
secret_name = path.removeprefix(f'{SECRET_PATH}{SERVICE}_')
|
||||
secrets[secret_name] = secret
|
||||
binary_output = json.dumps(secrets).encode()
|
||||
tarinfo = tarfile.TarInfo(name=filename)
|
||||
tarinfo.size = len(binary_output)
|
||||
file_dumps.append((binary_output, tarinfo))
|
||||
with tarfile.open('/tmp/backup.tar.gz', "w:gz") as tar:
|
||||
print(f"Writing files to /tmp/backup.tar.gz...")
|
||||
for binary_output, tarinfo in file_dumps:
|
||||
tar.addfile(tarinfo, fileobj=io.BytesIO(binary_output))
|
||||
size = get_formatted_size('/tmp/backup.tar.gz')
|
||||
print(
|
||||
f"Backup has been written to /tmp/backup.tar.gz with a size of {size}")
|
||||
|
||||
|
||||
def get_formatted_size(file_path):
|
||||
file_size = os.path.getsize(file_path)
|
||||
units = ['Bytes', 'KB', 'MB', 'GB', 'TB']
|
||||
for unit in units:
|
||||
if file_size < 1024:
|
||||
return f"{round(file_size, 3)} {unit}"
|
||||
file_size /= 1024
|
||||
return f"{round(file_size, 3)} {units[-1]}"
|
||||
|
||||
|
||||
def dump(snapshot, path):
|
||||
cmd = restic.cat.base_command() + ['dump']
|
||||
if SERVICE:
|
||||
cmd = cmd + ['--tag', SERVICE]
|
||||
cmd = cmd + [snapshot, path]
|
||||
print(f"Dumping {path} from snapshot '{snapshot}'")
|
||||
output = subprocess.run(cmd, capture_output=True)
|
||||
if output.returncode:
|
||||
logger.error(
|
||||
f"error while dumping {path} from snapshot '{snapshot}': {output.stderr}")
|
||||
exit(1)
|
||||
return output.stdout
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
cli()
|
||||
@ -1,11 +0,0 @@
|
||||
---
|
||||
version: "3.8"
|
||||
services:
|
||||
app:
|
||||
secrets:
|
||||
- push_basicauth
|
||||
|
||||
secrets:
|
||||
push_basicauth:
|
||||
external: true
|
||||
name: ${STACK_NAME}_push_basicauth_${SECRET_PUSH_BASICAUTH}
|
||||
@ -1,14 +0,0 @@
|
||||
---
|
||||
version: "3.8"
|
||||
services:
|
||||
app:
|
||||
environment:
|
||||
- AWS_ACCESS_KEY_ID
|
||||
- AWS_SECRET_ACCESS_KEY_FILE=/run/secrets/aws_secret_access_key
|
||||
secrets:
|
||||
- aws_secret_access_key
|
||||
|
||||
secrets:
|
||||
aws_secret_access_key:
|
||||
external: true
|
||||
name: ${STACK_NAME}_aws_secret_access_key_${SECRET_AWS_SECRET_ACCESS_KEY_VERSION}
|
||||
@ -1,13 +0,0 @@
|
||||
---
|
||||
version: "3.8"
|
||||
services:
|
||||
app:
|
||||
environment:
|
||||
- RESTIC_REPOSITORY_FILE=/run/secrets/restic_repo
|
||||
secrets:
|
||||
- restic_repo
|
||||
|
||||
secrets:
|
||||
restic_repo:
|
||||
external: true
|
||||
name: ${STACK_NAME}_restic_repo_${SECRET_RESTIC_REPO_VERSION}
|
||||
@ -1,23 +0,0 @@
|
||||
---
|
||||
version: "3.8"
|
||||
services:
|
||||
app:
|
||||
environment:
|
||||
- SSH_KEY_FILE=/run/secrets/ssh_key
|
||||
- SSH_HOST_KEY
|
||||
secrets:
|
||||
- source: ssh_key
|
||||
mode: 0400
|
||||
configs:
|
||||
- source: ssh_config
|
||||
target: /root/.ssh/config
|
||||
|
||||
secrets:
|
||||
ssh_key:
|
||||
external: true
|
||||
name: ${STACK_NAME}_ssh_key_${SECRET_SSH_KEY_VERSION}
|
||||
|
||||
configs:
|
||||
ssh_config:
|
||||
name: ${STACK_NAME}_ssh_config_${SSH_CONFIG_VERSION}
|
||||
file: ssh_config
|
||||
@ -1,15 +0,0 @@
|
||||
---
|
||||
version: "3.8"
|
||||
services:
|
||||
app:
|
||||
deploy:
|
||||
mode: replicated
|
||||
replicas: 0
|
||||
labels:
|
||||
- "swarm.cronjob.enable=true"
|
||||
# Note(3wc): every 5m, testing
|
||||
- "swarm.cronjob.schedule=*/5 * * * *"
|
||||
# Note(3wc): blank label to be picked up by `abra recipe sync`
|
||||
restart_policy:
|
||||
condition: none
|
||||
entrypoint: [ "/usr/bin/backup.sh" ]
|
||||
51
compose.yml
51
compose.yml
@ -1,51 +0,0 @@
|
||||
---
|
||||
version: "3.8"
|
||||
services:
|
||||
app:
|
||||
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/"
|
||||
- "/var/lib/docker/containers/:/var/lib/docker/containers/:ro"
|
||||
- backups:/backups
|
||||
environment:
|
||||
- CRON_SCHEDULE
|
||||
- RESTIC_REPOSITORY
|
||||
- RESTIC_PASSWORD_FILE=/run/secrets/restic_password
|
||||
secrets:
|
||||
- restic_password
|
||||
configs:
|
||||
- source: entrypoint
|
||||
target: /entrypoint.sh
|
||||
mode: 666
|
||||
- source: cronjob
|
||||
target: /cronjob.sh
|
||||
mode: 666
|
||||
deploy:
|
||||
labels:
|
||||
- coop-cloud.${STACK_NAME}.version=0.1.0+latest
|
||||
- coop-cloud.${STACK_NAME}.timeout=${TIMEOUT:-300}
|
||||
- coop-cloud.backupbot.enabled=true
|
||||
#entrypoint: ['tail', '-f','/dev/null']
|
||||
healthcheck:
|
||||
test: "pgrep crond"
|
||||
interval: 30s
|
||||
timeout: 10s
|
||||
retries: 10
|
||||
start_period: 5m
|
||||
|
||||
secrets:
|
||||
restic_password:
|
||||
external: true
|
||||
name: ${STACK_NAME}_restic_password_${SECRET_RESTIC_PASSWORD_VERSION}
|
||||
|
||||
configs:
|
||||
entrypoint:
|
||||
name: ${STACK_NAME}_entrypoint_${ENTRYPOINT_VERSION}
|
||||
file: entrypoint.sh
|
||||
cronjob:
|
||||
name: ${STACK_NAME}_cronjob_${CRONJOB_VERSION}
|
||||
file: cronjob.sh
|
||||
|
||||
volumes:
|
||||
backups:
|
||||
40
cronjob.sh
40
cronjob.sh
@ -1,40 +0,0 @@
|
||||
#!/bin/sh
|
||||
|
||||
set -e
|
||||
|
||||
CURL_OPTS="-s"
|
||||
# Check for basic auth
|
||||
if [ -n "$(cat /run/secrets/push_basicauth)" ]
|
||||
then
|
||||
CURL_OPTS="$CURL_OPTS -u $(cat /run/secrets/push_basicauth)"
|
||||
fi
|
||||
|
||||
if [ -n "$PUSH_PROMETHEUS_URL" ]
|
||||
then
|
||||
push_start_notification="(echo 'backup 1' | curl $CURL_OPTS --data-binary @- $PUSH_PROMETHEUS_URL)"
|
||||
push_success_notification="(echo 'backup 0' | curl $CURL_OPTS --data-binary @- $PUSH_PROMETHEUS_URL)"
|
||||
push_fail_notification="(echo 'backup -1' | curl $CURL_OPTS --data-binary @- $PUSH_PROMETHEUS_URL)"
|
||||
else
|
||||
if [ -n "$PUSH_URL_START" ]
|
||||
then
|
||||
push_start_notification="curl $CURL_OPTS '$PUSH_URL_START'"
|
||||
fi
|
||||
|
||||
if [ -n "$PUSH_URL_FAIL" ]
|
||||
then
|
||||
push_fail_notification="curl $CURL_OPTS '$PUSH_URL_FAIL'"
|
||||
fi
|
||||
|
||||
if [ -n "$PUSH_URL_SUCCESS" ]
|
||||
then
|
||||
push_success_notification="curl $CURL_OPTS '$PUSH_URL_SUCCESS'"
|
||||
fi
|
||||
fi
|
||||
|
||||
eval "$push_start_notification"
|
||||
if [ "$(backup --machine-logs create 2>&1 | tee /tmp/backup.log && (grep -q 'backup finished' /tmp/backup.log))" ]
|
||||
then
|
||||
eval "$push_success_notification"
|
||||
else
|
||||
eval "$push_fail_notification"
|
||||
fi
|
||||
20
docker-compose.yml
Normal file
20
docker-compose.yml
Normal file
@ -0,0 +1,20 @@
|
||||
version: "3.8"
|
||||
|
||||
services:
|
||||
app:
|
||||
build: .
|
||||
environment:
|
||||
RESTIC_PASSWORD_FILE: "/run/secrets/restic_password"
|
||||
RESTIC_REPOSITORY: "s3:http://172.20.0.2:9000/backup" # https://restic.readthedocs.io/en/stable/030_preparing_a_new_repo.html
|
||||
AWS_ACCESS_KEY_ID: "root"
|
||||
AWS_SECRET_ACCESS_KEY: "foobar"
|
||||
secrets:
|
||||
- restic_password
|
||||
volumes:
|
||||
- /var/run/docker.sock:/var/run/docker.sock
|
||||
|
||||
secrets:
|
||||
restic_password:
|
||||
#external: true
|
||||
#name: restic_password
|
||||
file: restic_password
|
||||
@ -1,15 +0,0 @@
|
||||
#!/bin/sh
|
||||
|
||||
set -e
|
||||
|
||||
if [ -n "$SSH_HOST_KEY" ]
|
||||
then
|
||||
echo "$SSH_HOST_KEY" > /root/.ssh/known_hosts
|
||||
fi
|
||||
|
||||
cron_schedule="${CRON_SCHEDULE:?CRON_SCHEDULE not set}"
|
||||
|
||||
echo "$cron_schedule /cronjob.sh" | crontab -
|
||||
crontab -l
|
||||
|
||||
crond -f -d8 -L /dev/stdout
|
||||
@ -1,3 +0,0 @@
|
||||
Breaking Change: the variables `SERVER_NAME` and `RESTIC_HOST` are merged into `RESTIC_REPOSITORY`. The format can be looked up here: https://restic.readthedocs.io/en/stable/030_preparing_a_new_repo.html
|
||||
ssh/sftp: `sftp:user@host:/repo-path`
|
||||
S3: `s3:https://s3.example.com/bucket_name`
|
||||
@ -1,3 +0,0 @@
|
||||
{
|
||||
"$schema": "https://docs.renovatebot.com/renovate-schema.json"
|
||||
}
|
||||
@ -1,4 +0,0 @@
|
||||
Host *
|
||||
IdentityFile /run/secrets/ssh_key
|
||||
ServerAliveInterval 60
|
||||
ServerAliveCountMax 240
|
||||
Reference in New Issue
Block a user