Write periodic backup scheduler

.editorconfig

@@ -0,0 +1,10 @@
+root = true
+
+[*]
+indent_style = space
+end_of_line = lf
+insert_final_newline = true
+max_line_length = 79
+
+[*.py]
+indent_size = 4

Dockerfile

@@ -1,19 +1,18 @@
 FROM debian
 MAINTAINER "MuzHack" <[email protected]>
 
-RUN apt-get update && apt-get install -y cron python3 python3-pip lsb-release wget
+RUN apt-get update && apt-get install -y python3 python3-pip lsb-release wget
 RUN echo "deb http://download.rethinkdb.com/apt `lsb_release -cs` main" | tee /etc/apt/sources.list.d/rethinkdb.list
 RUN wget -qO- https://download.rethinkdb.com/apt/pubkey.gpg | apt-key add -
 RUN apt-get update && apt-get install -y rethinkdb
 RUN apt-get clean -y && apt-get autoclean -y && apt-get autoremove -y && rm -rf /var/lib/apt/lists/* /tmp/* /var/tmp/*
 
 WORKDIR /app
-COPY ./crontab /etc/cron.d/
-COPY ./requirements.txt /app/
-RUN mkdir -p /app/rethinkdb
-COPY ./rethinkdb/backup.py /app/rethinkdb/
 
+COPY ./requirements.txt /app/
 RUN pip3 install -r requirements.txt
 RUN rm -rf requirements.txt
 
-CMD python3 cron.py
+COPY ./schedule-rethinkdb-backup.py /app/
+
+CMD python3 schedule-rethinkdb-backup.py

rethinkdb/backup.py → backup-rethinkdb.py

@@ -1,4 +1,5 @@
 #!/usr/bin/env python3
+"""Script to back up RethinkDB either locally or remotely to S3."""
 import subprocess
 import argparse
 import os.path
@@ -24,10 +25,11 @@ def _get_environment_value(key):
     return value
 
 
-parser = argparse.ArgumentParser(description='Back up local RethinkDB instance')
+parser = argparse.ArgumentParser(
+    description='Back up local RethinkDB instance')
 parser.add_argument('--s3-bucket', default=None, help='Specify S3 bucket')
 parser.add_argument('--remove', action='store_true', default=False,
-    help='Remove backup archive when done?')
+                    help='Remove backup archive when done?')
 args = parser.parse_args()
 
 date_time_str = datetime.utcnow().strftime('%Y-%m-%dT%H:%M')
@@ -37,16 +39,18 @@ def _get_environment_value(key):
 command = ['rethinkdb', 'dump', '-f', filename]
 auth_key = os.environ.get('RETHINKDB_AUTH_KEY')
 if auth_key:
-    command.extend(['-a', auth_key,])
+    command.extend(['-a', auth_key, ])
 _info('Backing up database to {}...'.format(filename))
 subprocess.check_call(command, stdout=subprocess.PIPE)
 
 if args.s3_bucket:
-    _info('Uploading \'{}\' to S3 bucket \'{}\'...'.format(filename, args.s3_bucket))
+    _info('Uploading \'{}\' to S3 bucket \'{}\'...'.format(filename,
+          args.s3_bucket))
     access_key_id = _get_environment_value('AWS_ACCESS_KEY_ID')
     secret = _get_environment_value('AWS_SECRET_ACCESS_KEY')
-    s3_client = boto3.client('s3', region_name='eu-central-1', aws_access_key_id=access_key_id,
-        aws_secret_access_key=secret)
+    s3_client = boto3.client('s3', region_name='eu-central-1',
+                             aws_access_key_id=access_key_id,
+                             aws_secret_access_key=secret)
     s3_client.upload_file(filename, args.s3_bucket, filename)
     # TODO: Implement deleting backups that are older than 100 days
 

schedule-rethinkdb-backup.py

@@ -0,0 +1,69 @@
+#!/usr/bin/env python3
+"""Script to schedule RethinkDB backup."""
+import asyncio
+import subprocess
+from datetime import datetime, date, timedelta
+import sys
+import logging
+import contextlib
+
+
+def _configure_logging():
+    logging.getLogger().setLevel(logging.WARNING)
+    logger = logging.getLogger('app')
+    logger.setLevel(logging.DEBUG)
+
+    ch = logging.StreamHandler()
+    formatter = logging.Formatter(
+        '%(asctime)s - %(name)s - %(levelname)s - %(message)s')
+    ch.setFormatter(formatter)
+    logger.addHandler(ch)
+
+    return logger
+
+
+_logger = _configure_logging()
+
+
+def _schedule_backup(loop):
+    hour = 18
+
+    now = datetime.now()
+    today = date.today()
+    desired_time = datetime(today.year, today.month, today.day, hour=hour)
+    if now.hour >= hour:
+        _logger.debug(
+            'Delaying until {} next day since we\'re already at {}'.format(
+                hour, now.hour))
+        desired_time = desired_time + timedelta(days=1)
+    else:
+        _logger.debug('Delaying until {} same day'.format(hour))
+    desired_seconds = (desired_time - now).seconds
+
+    _logger.debug(
+        'Delaying for {} second(s) before backup'.format(desired_seconds))
+    loop.call_later(desired_seconds, _backup, loop)
+
+
+def _backup(loop):
+    """Perform actual backup."""
+    now = datetime.now()
+    _logger.info('Backing up at {}...'.format(
+        now.strftime('%Y-%m-%d %H:%M:%S')))
+    _logger.info('Backed up successfully!')
+    _logger.debug('Scheduling next backup')
+    _schedule_backup(loop)
+
+
+def _main():
+    with contextlib.closing(asyncio.get_event_loop()) as loop:
+        _schedule_backup(loop)
+        try:
+            loop.run_forever()
+        except KeyboardInterrupt:
+            _logger.info('Interrupted')
+            sys.exit(0)
+
+
+if __name__ == '__main__':
+    _main()