diff --git a/README.md b/README.md
index d4b03e0..dfe9161 100644
--- a/README.md
+++ b/README.md
@@ -31,8 +31,6 @@ A collection of delicious docker recipes.
 - [ ] libreswan
 - [ ] mitmproxy
 - [ ] nagios
-- [ ] nfs
-- [ ] openldap
 - [ ] openswan
 - [ ] postfix
 - [ ] pritunl
@@ -45,6 +43,7 @@ A collection of delicious docker recipes.
 
 ## Big Data
 
+- [x] airflow
 - [x] kafka-arm
 - [x] kafka-manager
 - [x] presto
@@ -264,7 +263,6 @@ A collection of delicious docker recipes.
 - [x] confluentinc/cp-kafka-rest
 - [x] streamsets/datacollector
 - [x] cachethq/docker
-- [x] puckel/docker-airflow
 - [x] drone/drone
 - [x] drupal
 - [x] elastalert
diff --git a/airflow/Dockerfile b/airflow/Dockerfile
new file mode 100644
index 0000000..a3f3a6a
--- /dev/null
+++ b/airflow/Dockerfile
@@ -0,0 +1,46 @@
+#
+# Dockerfile for airflow
+#
+
+FROM python:3.7-alpine
+
+ENV AIRFLOW_VERSION=1.10.5
+ENV AIRFLOW_EXTRAS=async,all_dbs,celery,crypto,devel_hadoop,jdbc,ldap,password,redis,s3,samba,slack,ssh,statsd
+ENV AIRFLOW_HOME=/opt/airflow
+ENV AIRFLOW_CONFIG=airflow.cfg
+
+ARG FERNET_KEY=4XHGZH0dZ40iOv6z5cyfrXVg5qg3s_d06A7BFfbSsqA=
+ENV FERNET_KEY=${FERNET_KEY}
+
+RUN set -xe \
+    && apk add --no-cache \
+        build-base \
+        cyrus-sasl-dev \
+        freetds \
+        freetds-dev \
+        krb5-dev \
+        libffi-dev \
+        mariadb-dev \
+        postgresql-dev \
+        python3-dev \
+    && pip install cython numpy \
+    && pip install apache-airflow[${AIRFLOW_EXTRAS}]==${AIRFLOW_VERSION} \
+    && pip install "websocket-client<0.55.0,>=0.35" \
+    && apk del \
+        build-base \
+        cyrus-sasl-dev \
+        freetds-dev \
+        krb5-dev \
+        libffi-dev \
+        mariadb-dev \
+        postgresql-dev \
+        python3-dev \
+    && rm -rf /root/.cache/pip
+
+WORKDIR ${AIRFLOW_HOME}
+VOLUME ${AIRFLOW_HOME}
+
+EXPOSE 8080
+
+ENTRYPOINT ["airflow"]
+CMD ["--help"]
diff --git a/airflow/README.md b/airflow/README.md
index cede12f..1cceb0a 100644
--- a/airflow/README.md
+++ b/airflow/README.md
@@ -1,6 +1,8 @@
 airflow
 =======
 
+![](https://airflow.apache.org/_images/pin_large.png)
+
 ## How It Works
 
 ```
@@ -20,13 +22,16 @@ airflow
 ## Quick Start
 
 ```bash
-# On Master
-$ docker-compose up -d
-$ chmod 777 data/airflow/dags
-$ docker-compose exec webserver cp -r /usr/local/lib/python3.7/site-packages/airflow/example_dags dags
+$ python -c 'from cryptography.fernet import Fernet; print(Fernet.generate_key().decode())'
+4XHGZH0dZ40iOv6z5cyfrXVg5qg3s_d06A7BFfbSsqA=
 
-# On Workers
-$ docker-compose up -d
-$ chmod 777 data/airflow/dags
-$ docker-compose exec worker cp -r /usr/local/lib/python3.7/site-packages/airflow/example_dags dags
+$ docker stack deploy -c docker-stack.yaml airflow
+$ docker service update --replicas-max-per-node=1 airflow_worker
+$ docker service update --replicas 3 airflow_worker
+
+$ curl http://localhost:8080/
+$ curl http://localhost:5555/
 ```
+
+> :warning: This docker image was built with a static `FERNET_KEY` environment variable.
+> You should set another value to it in `docker-stack.yaml`.
diff --git a/airflow/data/airflow.cfg b/airflow/data/airflow.cfg
new file mode 100644
index 0000000..5a2d71f
--- /dev/null
+++ b/airflow/data/airflow.cfg
@@ -0,0 +1,825 @@
+# -*- coding: utf-8 -*-
+#
+# Licensed to the Apache Software Foundation (ASF) under one
+# or more contributor license agreements.  See the NOTICE file
+# distributed with this work for additional information
+# regarding copyright ownership.  The ASF licenses this file
+# to you under the Apache License, Version 2.0 (the
+# "License"); you may not use this file except in compliance
+# with the License.  You may obtain a copy of the License at
+#
+#   http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing,
+# software distributed under the License is distributed on an
+# "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
+# KIND, either express or implied.  See the License for the
+# specific language governing permissions and limitations
+# under the License.
+
+
+# This is the template for Airflow's default configuration. When Airflow is
+# imported, it looks for a configuration file at $AIRFLOW_HOME/airflow.cfg. If
+# it doesn't exist, Airflow uses this template to generate it by replacing
+# variables in curly braces with their global values from configuration.py.
+
+# Users should not modify this file; they should customize the generated
+# airflow.cfg instead.
+
+
+# ----------------------- TEMPLATE BEGINS HERE -----------------------
+
+[core]
+# The folder where your airflow pipelines live, most likely a
+# subfolder in a code repository
+# This path must be absolute
+dags_folder = {AIRFLOW_HOME}/dags
+
+# The folder where airflow should store its log files
+# This path must be absolute
+base_log_folder = {AIRFLOW_HOME}/logs
+
+# Airflow can store logs remotely in AWS S3, Google Cloud Storage or Elastic Search.
+# Users must supply an Airflow connection id that provides access to the storage
+# location. If remote_logging is set to true, see UPDATING.md for additional
+# configuration requirements.
+remote_logging = False
+remote_log_conn_id =
+remote_base_log_folder =
+encrypt_s3_logs = False
+
+# Logging level
+logging_level = INFO
+fab_logging_level = WARN
+
+# Logging class
+# Specify the class that will specify the logging configuration
+# This class has to be on the python classpath
+# logging_config_class = my.path.default_local_settings.LOGGING_CONFIG
+logging_config_class =
+
+# Log format
+# Colour the logs when the controlling terminal is a TTY.
+colored_console_log = True
+colored_log_format = [%%(blue)s%%(asctime)s%%(reset)s] {{%%(blue)s%%(filename)s:%%(reset)s%%(lineno)d}} %%(log_color)s%%(levelname)s%%(reset)s - %%(log_color)s%%(message)s%%(reset)s
+colored_formatter_class = airflow.utils.log.colored_log.CustomTTYColoredFormatter
+
+log_format = [%%(asctime)s] {{%%(filename)s:%%(lineno)d}} %%(levelname)s - %%(message)s
+simple_log_format = %%(asctime)s %%(levelname)s - %%(message)s
+
+# Specify prefix pattern like mentioned below with stream handler TaskHandlerWithCustomFormatter
+# task_log_prefix_template =  {{ti.dag_id}}-{{ti.task_id}}-{{execution_date}}-{{try_number}}
+task_log_prefix_template =
+
+# Log filename format
+log_filename_template = {{{{ ti.dag_id }}}}/{{{{ ti.task_id }}}}/{{{{ ts }}}}/{{{{ try_number }}}}.log
+log_processor_filename_template = {{{{ filename }}}}.log
+dag_processor_manager_log_location = {AIRFLOW_HOME}/logs/dag_processor_manager/dag_processor_manager.log
+
+# Hostname by providing a path to a callable, which will resolve the hostname
+# The format is "package:function". For example,
+# default value "socket:getfqdn" means that result from getfqdn() of "socket" package will be used as hostname
+# No argument should be required in the function specified.
+# If using IP address as hostname is preferred, use value "airflow.utils.net:get_host_ip_address"
+hostname_callable = socket:getfqdn
+
+# Default timezone in case supplied date times are naive
+# can be utc (default), system, or any IANA timezone string (e.g. Europe/Amsterdam)
+default_timezone = utc
+
+# The executor class that airflow should use. Choices include
+# SequentialExecutor, LocalExecutor, CeleryExecutor, DaskExecutor, KubernetesExecutor
+executor = CeleryExecutor
+
+# The SqlAlchemy connection string to the metadata database.
+# SqlAlchemy supports many different database engine, more information
+# their website
+sql_alchemy_conn = postgresql+psycopg2://airflow:airflow@postgres:5432/airflow
+
+# The encoding for the databases
+sql_engine_encoding = utf-8
+
+# If SqlAlchemy should pool database connections.
+sql_alchemy_pool_enabled = True
+
+# The SqlAlchemy pool size is the maximum number of database connections
+# in the pool. 0 indicates no limit.
+sql_alchemy_pool_size = 5
+
+# The maximum overflow size of the pool.
+# When the number of checked-out connections reaches the size set in pool_size,
+# additional connections will be returned up to this limit.
+# When those additional connections are returned to the pool, they are disconnected and discarded.
+# It follows then that the total number of simultaneous connections the pool will allow is pool_size + max_overflow,
+# and the total number of "sleeping" connections the pool will allow is pool_size.
+# max_overflow can be set to -1 to indicate no overflow limit;
+# no limit will be placed on the total number of concurrent connections. Defaults to 10.
+sql_alchemy_max_overflow = 10
+
+# The SqlAlchemy pool recycle is the number of seconds a connection
+# can be idle in the pool before it is invalidated. This config does
+# not apply to sqlite. If the number of DB connections is ever exceeded,
+# a lower config value will allow the system to recover faster.
+sql_alchemy_pool_recycle = 1800
+
+# Check connection at the start of each connection pool checkout.
+# Typically, this is a simple statement like “SELECT 1”.
+# More information here: https://docs.sqlalchemy.org/en/13/core/pooling.html#disconnect-handling-pessimistic
+sql_alchemy_pool_pre_ping = True
+
+# The schema to use for the metadata database
+# SqlAlchemy supports databases with the concept of multiple schemas.
+sql_alchemy_schema =
+
+# The amount of parallelism as a setting to the executor. This defines
+# the max number of task instances that should run simultaneously
+# on this airflow installation
+parallelism = 32
+
+# The number of task instances allowed to run concurrently by the scheduler
+dag_concurrency = 16
+
+# Are DAGs paused by default at creation
+dags_are_paused_at_creation = True
+
+# The maximum number of active DAG runs per DAG
+max_active_runs_per_dag = 16
+
+# Whether to load the examples that ship with Airflow. It's good to
+# get started, but you probably want to set this to False in a production
+# environment
+load_examples = False
+
+# Where your Airflow plugins are stored
+plugins_folder = {AIRFLOW_HOME}/plugins
+
+# Secret key to save connection passwords in the db
+fernet_key = {FERNET_KEY}
+
+# Whether to disable pickling dags
+donot_pickle = True
+
+# How long before timing out a python file import
+dagbag_import_timeout = 30
+
+# How long before timing out a DagFileProcessor, which processes a dag file
+dag_file_processor_timeout = 50
+
+# The class to use for running task instances in a subprocess
+task_runner = StandardTaskRunner
+
+# If set, tasks without a `run_as_user` argument will be run with this user
+# Can be used to de-elevate a sudo user running Airflow when executing tasks
+default_impersonation =
+
+# What security module to use (for example kerberos):
+security =
+
+# If set to False enables some unsecure features like Charts and Ad Hoc Queries.
+# In 2.0 will default to True.
+secure_mode = False
+
+# Turn unit test mode on (overwrites many configuration options with test
+# values at runtime)
+unit_test_mode = False
+
+# Name of handler to read task instance logs.
+# Default to use task handler.
+task_log_reader = task
+
+# Whether to enable pickling for xcom (note that this is insecure and allows for
+# RCE exploits). This will be deprecated in Airflow 2.0 (be forced to False).
+enable_xcom_pickling = True
+
+# When a task is killed forcefully, this is the amount of time in seconds that
+# it has to cleanup after it is sent a SIGTERM, before it is SIGKILLED
+killed_task_cleanup_time = 60
+
+# Whether to override params with dag_run.conf. If you pass some key-value pairs through `airflow dags backfill -c` or
+# `airflow dags trigger -c`, the key-value pairs will override the existing ones in params.
+dag_run_conf_overrides_params = False
+
+# Worker initialisation check to validate Metadata Database connection
+worker_precheck = False
+
+# When discovering DAGs, ignore any files that don't contain the strings `DAG` and `airflow`.
+dag_discovery_safe_mode = True
+
+# The number of retries each task is going to have by default. Can be overridden at dag or task level.
+default_task_retries = 0
+
+
+[cli]
+# In what way should the cli access the API. The LocalClient will use the
+# database directly, while the json_client will use the api running on the
+# webserver
+api_client = airflow.api.client.local_client
+
+# If you set web_server_url_prefix, do NOT forget to append it here, ex:
+# endpoint_url = http://localhost:8080/myroot
+# So api will look like: http://localhost:8080/myroot/api/experimental/...
+endpoint_url = http://localhost:8080
+
+[api]
+# How to authenticate users of the API
+auth_backend = airflow.api.auth.backend.default
+
+[lineage]
+# what lineage backend to use
+backend =
+
+[atlas]
+sasl_enabled = False
+host =
+port = 21000
+username =
+password =
+
+[operators]
+# The default owner assigned to each new operator, unless
+# provided explicitly or passed via `default_args`
+default_owner = airflow
+default_cpus = 1
+default_ram = 512
+default_disk = 512
+default_gpus = 0
+
+[hive]
+# Default mapreduce queue for HiveOperator tasks
+default_hive_mapred_queue =
+# Template for mapred_job_name in HiveOperator, supports the following named parameters:
+# hostname, dag_id, task_id, execution_date
+mapred_job_name_template = Airflow HiveOperator task for {{hostname}}.{{dag_id}}.{{task_id}}.{{execution_date}}
+
+[webserver]
+# The base url of your website as airflow cannot guess what domain or
+# cname you are using. This is used in automated emails that
+# airflow sends to point links to the right web server
+base_url = http://localhost:8080
+
+# The ip specified when starting the web server
+web_server_host = 0.0.0.0
+
+# The port on which to run the web server
+web_server_port = 8080
+
+# Paths to the SSL certificate and key for the web server. When both are
+# provided SSL will be enabled. This does not change the web server port.
+web_server_ssl_cert =
+web_server_ssl_key =
+
+# Number of seconds the webserver waits before killing gunicorn master that doesn't respond
+web_server_master_timeout = 120
+
+# Number of seconds the gunicorn webserver waits before timing out on a worker
+web_server_worker_timeout = 120
+
+# Number of workers to refresh at a time. When set to 0, worker refresh is
+# disabled. When nonzero, airflow periodically refreshes webserver workers by
+# bringing up new ones and killing old ones.
+worker_refresh_batch_size = 1
+
+# Number of seconds to wait before refreshing a batch of workers.
+worker_refresh_interval = 30
+
+# Secret key used to run your flask app
+# It should be as random as possible
+secret_key = {SECRET_KEY}
+
+# Number of workers to run the Gunicorn web server
+workers = 4
+
+# The worker class gunicorn should use. Choices include
+# sync (default), eventlet, gevent
+worker_class = sync
+
+# Log files for the gunicorn webserver. '-' means log to stderr.
+access_logfile = -
+error_logfile = -
+
+# Expose the configuration file in the web server
+expose_config = False
+
+# Default DAG view.  Valid values are:
+# tree, graph, duration, gantt, landing_times
+dag_default_view = tree
+
+# Default DAG orientation. Valid values are:
+# LR (Left->Right), TB (Top->Bottom), RL (Right->Left), BT (Bottom->Top)
+dag_orientation = LR
+
+# Puts the webserver in demonstration mode; blurs the names of Operators for
+# privacy.
+demo_mode = False
+
+# The amount of time (in secs) webserver will wait for initial handshake
+# while fetching logs from other worker machine
+log_fetch_timeout_sec = 5
+
+# By default, the webserver shows paused DAGs. Flip this to hide paused
+# DAGs by default
+hide_paused_dags_by_default = False
+
+# Consistent page size across all listing views in the UI
+page_size = 100
+
+# Define the color of navigation bar
+navbar_color = #007A87
+
+# Default dagrun to show in UI
+default_dag_run_display_number = 25
+
+# Enable werkzeug `ProxyFix` middleware
+enable_proxy_fix = False
+
+# Set secure flag on session cookie
+cookie_secure = False
+
+# Set samesite policy on session cookie
+cookie_samesite =
+
+# Default setting for wrap toggle on DAG code and TI log views.
+default_wrap = False
+
+# Send anonymous user activity to your analytics tool
+# analytics_tool = # choose from google_analytics, segment, or metarouter
+# analytics_id = XXXXXXXXXXX
+
+[email]
+email_backend = airflow.utils.email.send_email_smtp
+
+
+[smtp]
+# If you want airflow to send emails on retries, failure, and you want to use
+# the airflow.utils.email.send_email_smtp function, you have to configure an
+# smtp server here
+smtp_host = localhost
+smtp_starttls = True
+smtp_ssl = False
+# Uncomment and set the user/pass settings if you want to use SMTP AUTH
+# smtp_user = airflow
+# smtp_password = airflow
+smtp_port = 25
+smtp_mail_from = airflow@example.com
+
+[sentry]
+# Sentry (https://docs.sentry.io) integration
+sentry_dsn = 
+
+
+[celery]
+# This section only applies if you are using the CeleryExecutor in
+# [core] section above
+
+# The app name that will be used by celery
+celery_app_name = airflow.executors.celery_executor
+
+# The concurrency that will be used when starting workers with the
+# "airflow worker" command. This defines the number of task instances that
+# a worker will take, so size up your workers based on the resources on
+# your worker box and the nature of your tasks
+worker_concurrency = 16
+
+# The maximum and minimum concurrency that will be used when starting workers with the
+# "airflow worker" command (always keep minimum processes, but grow to maximum if necessary).
+# Note the value should be "max_concurrency,min_concurrency"
+# Pick these numbers based on resources on worker box and the nature of the task.
+# If autoscale option is available, worker_concurrency will be ignored.
+# http://docs.celeryproject.org/en/latest/reference/celery.bin.worker.html#cmdoption-celery-worker-autoscale
+# worker_autoscale = 16,12
+
+# When you start an airflow worker, airflow starts a tiny web server
+# subprocess to serve the workers local log files to the airflow main
+# web server, who then builds pages and sends them to users. This defines
+# the port on which the logs are served. It needs to be unused, and open
+# visible from the main web server to connect into the workers.
+worker_log_server_port = 8793
+
+# The Celery broker URL. Celery supports RabbitMQ, Redis and experimentally
+# a sqlalchemy database. Refer to the Celery documentation for more
+# information.
+# http://docs.celeryproject.org/en/latest/userguide/configuration.html#broker-settings
+broker_url = redis://redis:6379/1
+
+# The Celery result_backend. When a job finishes, it needs to update the
+# metadata of the job. Therefore it will post a message on a message bus,
+# or insert it into a database (depending of the backend)
+# This status is used by the scheduler to update the state of the task
+# The use of a database is highly recommended
+# http://docs.celeryproject.org/en/latest/userguide/configuration.html#task-result-backend-settings
+result_backend = db+postgresql://airflow:airflow@postgres/airflow
+
+# Celery Flower is a sweet UI for Celery. Airflow has a shortcut to start
+# it `airflow flower`. This defines the IP that Celery Flower runs on
+flower_host = 0.0.0.0
+
+# The root URL for Flower
+# Ex: flower_url_prefix = /flower
+flower_url_prefix =
+
+# This defines the port that Celery Flower runs on
+flower_port = 5555
+
+# Securing Flower with Basic Authentication
+# Accepts user:password pairs separated by a comma
+# Example: flower_basic_auth = user1:password1,user2:password2
+flower_basic_auth =
+
+# Default queue that tasks get assigned to and that worker listen on.
+default_queue = default
+
+# How many processes CeleryExecutor uses to sync task state.
+# 0 means to use max(1, number of cores - 1) processes.
+sync_parallelism = 0
+
+# Import path for celery configuration options
+celery_config_options = airflow.config_templates.default_celery.DEFAULT_CELERY_CONFIG
+
+# In case of using SSL
+ssl_active = False
+ssl_key =
+ssl_cert =
+ssl_cacert =
+
+# Celery Pool implementation.
+# Choices include: prefork (default), eventlet, gevent or solo.
+# See:
+#   https://docs.celeryproject.org/en/latest/userguide/workers.html#concurrency
+#   https://docs.celeryproject.org/en/latest/userguide/concurrency/eventlet.html
+pool = prefork
+
+[celery_broker_transport_options]
+# This section is for specifying options which can be passed to the
+# underlying celery broker transport.  See:
+# http://docs.celeryproject.org/en/latest/userguide/configuration.html#std:setting-broker_transport_options
+
+# The visibility timeout defines the number of seconds to wait for the worker
+# to acknowledge the task before the message is redelivered to another worker.
+# Make sure to increase the visibility timeout to match the time of the longest
+# ETA you're planning to use.
+#
+# visibility_timeout is only supported for Redis and SQS celery brokers.
+# See:
+#   http://docs.celeryproject.org/en/master/userguide/configuration.html#std:setting-broker_transport_options
+#
+#visibility_timeout = 21600
+
+[dask]
+# This section only applies if you are using the DaskExecutor in
+# [core] section above
+
+# The IP address and port of the Dask cluster's scheduler.
+cluster_address = 127.0.0.1:8786
+# TLS/ SSL settings to access a secured Dask scheduler.
+tls_ca =
+tls_cert =
+tls_key =
+
+
+[scheduler]
+# Task instances listen for external kill signal (when you clear tasks
+# from the CLI or the UI), this defines the frequency at which they should
+# listen (in seconds).
+job_heartbeat_sec = 5
+
+# The scheduler constantly tries to trigger new tasks (look at the
+# scheduler section in the docs for more information). This defines
+# how often the scheduler should run (in seconds).
+scheduler_heartbeat_sec = 5
+
+# The number of times to try to schedule each DAG file
+# -1 indicates unlimited number
+num_runs = -1
+
+# The number of seconds to wait between consecutive DAG file processing
+processor_poll_interval = 1
+
+# after how much time (seconds) a new DAGs should be picked up from the filesystem
+min_file_process_interval = 0
+
+# How often (in seconds) to scan the DAGs directory for new files. Default to 5 minutes.
+dag_dir_list_interval = 300
+
+# How often should stats be printed to the logs
+print_stats_interval = 30
+
+# If the last scheduler heartbeat happened more than scheduler_health_check_threshold ago (in seconds),
+# scheduler is considered unhealthy.
+# This is used by the health check in the "/health" endpoint
+scheduler_health_check_threshold = 30
+
+child_process_log_directory = {AIRFLOW_HOME}/logs/scheduler
+
+# Local task jobs periodically heartbeat to the DB. If the job has
+# not heartbeat in this many seconds, the scheduler will mark the
+# associated task instance as failed and will re-schedule the task.
+scheduler_zombie_task_threshold = 300
+
+# Turn off scheduler catchup by setting this to False.
+# Default behavior is unchanged and
+# Command Line Backfills still work, but the scheduler
+# will not do scheduler catchup if this is False,
+# however it can be set on a per DAG basis in the
+# DAG definition (catchup)
+catchup_by_default = True
+
+# This changes the batch size of queries in the scheduling main loop.
+# If this is too high, SQL query performance may be impacted by one
+# or more of the following:
+#  - reversion to full table scan
+#  - complexity of query predicate
+#  - excessive locking
+#
+# Additionally, you may hit the maximum allowable query length for your db.
+#
+# Set this to 0 for no limit (not advised)
+max_tis_per_query = 512
+
+# Statsd (https://github.com/etsy/statsd) integration settings
+statsd_on = False
+statsd_host = localhost
+statsd_port = 8125
+statsd_prefix = airflow
+
+# If you want to avoid send all the available metrics to StatsD,
+# you can configure an allow list of prefixes to send only the metrics that
+# start with the elements of the list (e.g: scheduler,executor,dagrun)
+statsd_allow_list =
+
+# The scheduler can run multiple threads in parallel to schedule dags.
+# This defines how many threads will run.
+max_threads = 2
+
+authenticate = False
+
+# Turn off scheduler use of cron intervals by setting this to False.
+# DAGs submitted manually in the web UI or with trigger_dag will still run.
+use_job_schedule = True
+
+[ldap]
+# set this to ldaps://<your.ldap.server>:<port>
+uri =
+user_filter = objectClass=*
+user_name_attr = uid
+group_member_attr = memberOf
+superuser_filter =
+data_profiler_filter =
+bind_user = cn=Manager,dc=example,dc=com
+bind_password = insecure
+basedn = dc=example,dc=com
+cacert = /etc/ca/ldap_ca.crt
+search_scope = LEVEL
+
+# This setting allows the use of LDAP servers that either return a
+# broken schema, or do not return a schema.
+ignore_malformed_schema = False
+
+[kerberos]
+ccache = /tmp/airflow_krb5_ccache
+# gets augmented with fqdn
+principal = airflow
+reinit_frequency = 3600
+kinit_path = kinit
+keytab = airflow.keytab
+
+
+[github_enterprise]
+api_rev = v3
+
+[admin]
+# UI to hide sensitive variable fields when set to True
+hide_sensitive_variable_fields = True
+
+[elasticsearch]
+# Elasticsearch host
+host =
+# Format of the log_id, which is used to query for a given tasks logs
+log_id_template = {{dag_id}}-{{task_id}}-{{execution_date}}-{{try_number}}
+# Used to mark the end of a log stream for a task
+end_of_log_mark = end_of_log
+# Qualified URL for an elasticsearch frontend (like Kibana) with a template argument for log_id
+# Code will construct log_id using the log_id template from the argument above.
+# NOTE: The code will prefix the https:// automatically, don't include that here.
+frontend =
+# Write the task logs to the stdout of the worker, rather than the default files
+write_stdout = False
+# Instead of the default log formatter, write the log lines as JSON
+json_format = False
+# Log fields to also attach to the json output, if enabled
+json_fields = asctime, filename, lineno, levelname, message
+
+[elasticsearch_configs]
+
+use_ssl = False
+verify_certs = True
+
+[kubernetes]
+# The repository, tag and imagePullPolicy of the Kubernetes Image for the Worker to Run
+worker_container_repository =
+worker_container_tag =
+worker_container_image_pull_policy = IfNotPresent
+
+# If True (default), worker pods will be deleted upon termination
+delete_worker_pods = True
+
+# Number of Kubernetes Worker Pod creation calls per scheduler loop
+worker_pods_creation_batch_size = 1
+
+# The Kubernetes namespace where airflow workers should be created. Defaults to `default`
+namespace = default
+
+# The name of the Kubernetes ConfigMap Containing the Airflow Configuration (this file)
+airflow_configmap =
+
+# For docker image already contains DAGs, this is set to `True`, and the worker will search for dags in dags_folder,
+# otherwise use git sync or dags volume claim to mount DAGs
+dags_in_image = False
+
+# For either git sync or volume mounted DAGs, the worker will look in this subpath for DAGs
+dags_volume_subpath =
+
+# For DAGs mounted via a volume claim (mutually exclusive with git-sync and host path)
+dags_volume_claim =
+
+# For volume mounted logs, the worker will look in this subpath for logs
+logs_volume_subpath =
+
+# A shared volume claim for the logs
+logs_volume_claim =
+
+# For DAGs mounted via a hostPath volume (mutually exclusive with volume claim and git-sync)
+# Useful in local environment, discouraged in production
+dags_volume_host =
+
+# A hostPath volume for the logs
+# Useful in local environment, discouraged in production
+logs_volume_host =
+
+# A list of configMapsRefs to envFrom. If more than one configMap is
+# specified, provide a comma separated list: configmap_a,configmap_b
+env_from_configmap_ref =
+
+# A list of secretRefs to envFrom. If more than one secret is
+# specified, provide a comma separated list: secret_a,secret_b
+env_from_secret_ref =
+
+# Git credentials and repository for DAGs mounted via Git (mutually exclusive with volume claim)
+git_repo =
+git_branch =
+git_subpath =
+# Use git_user and git_password for user authentication or git_ssh_key_secret_name and git_ssh_key_secret_key
+# for SSH authentication
+git_user =
+git_password =
+git_sync_root = /git
+git_sync_dest = repo
+# Mount point of the volume if git-sync is being used.
+# i.e. {AIRFLOW_HOME}/dags
+git_dags_folder_mount_point =
+
+# To get Git-sync SSH authentication set up follow this format
+#
+# airflow-secrets.yaml:
+# ---
+# apiVersion: v1
+# kind: Secret
+# metadata:
+#   name: airflow-secrets
+# data:
+#   # key needs to be gitSshKey
+#   gitSshKey: <base64_encoded_data>
+# ---
+# airflow-configmap.yaml:
+# apiVersion: v1
+# kind: ConfigMap
+# metadata:
+#   name: airflow-configmap
+# data:
+#   known_hosts: |
+#       github.com ssh-rsa <...>
+#   airflow.cfg: |
+#       ...
+#
+# git_ssh_key_secret_name = airflow-secrets
+# git_ssh_known_hosts_configmap_name = airflow-configmap
+git_ssh_key_secret_name =
+git_ssh_known_hosts_configmap_name =
+
+# To give the git_sync init container credentials via a secret, create a secret
+# with two fields: GIT_SYNC_USERNAME and GIT_SYNC_PASSWORD (example below) and
+# add `git_sync_credentials_secret = <secret_name>` to your airflow config under the kubernetes section
+#
+# Secret Example:
+# apiVersion: v1
+# kind: Secret
+# metadata:
+#   name: git-credentials
+# data:
+#   GIT_SYNC_USERNAME: <base64_encoded_git_username>
+#   GIT_SYNC_PASSWORD: <base64_encoded_git_password>
+git_sync_credentials_secret =
+
+# For cloning DAGs from git repositories into volumes: https://github.com/kubernetes/git-sync
+git_sync_container_repository = k8s.gcr.io/git-sync
+git_sync_container_tag = v3.1.1
+git_sync_init_container_name = git-sync-clone
+git_sync_run_as_user = 65533
+
+# The name of the Kubernetes service account to be associated with airflow workers, if any.
+# Service accounts are required for workers that require access to secrets or cluster resources.
+# See the Kubernetes RBAC documentation for more:
+#   https://kubernetes.io/docs/admin/authorization/rbac/
+worker_service_account_name =
+
+# Any image pull secrets to be given to worker pods, If more than one secret is
+# required, provide a comma separated list: secret_a,secret_b
+image_pull_secrets =
+
+# GCP Service Account Keys to be provided to tasks run on Kubernetes Executors
+# Should be supplied in the format: key-name-1:key-path-1,key-name-2:key-path-2
+gcp_service_account_keys =
+
+# Use the service account kubernetes gives to pods to connect to kubernetes cluster.
+# It's intended for clients that expect to be running inside a pod running on kubernetes.
+# It will raise an exception if called from a process not running in a kubernetes environment.
+in_cluster = True
+
+# When running with in_cluster=False change the default cluster_context or config_file
+# options to Kubernetes client. Leave blank these to use default behaviour like `kubectl` has.
+# cluster_context =
+# config_file =
+
+
+# Affinity configuration as a single line formatted JSON object.
+# See the affinity model for top-level key names (e.g. `nodeAffinity`, etc.):
+#   https://kubernetes.io/docs/reference/generated/kubernetes-api/v1.12/#affinity-v1-core
+affinity =
+
+# A list of toleration objects as a single line formatted JSON array
+# See:
+#   https://kubernetes.io/docs/reference/generated/kubernetes-api/v1.12/#toleration-v1-core
+tolerations =
+
+# **kwargs parameters to pass while calling a kubernetes client core_v1_api methods from Kubernetes Executor
+# provided as a single line formatted JSON dictionary string.
+# List of supported params in **kwargs are similar for all core_v1_apis, hence a single config variable for all apis
+# See:
+#   https://raw.githubusercontent.com/kubernetes-client/python/master/kubernetes/client/apis/core_v1_api.py
+kube_client_request_args =
+
+# Worker pods security context options
+# See:
+#   https://kubernetes.io/docs/tasks/configure-pod-container/security-context/
+
+# Specifies the uid to run the first process of the worker pods containers as
+run_as_user =
+
+# Specifies a gid to associate with all containers in the worker pods
+# if using a git_ssh_key_secret_name use an fs_group
+# that allows for the key to be read, e.g. 65533
+fs_group =
+
+# Annotations configuration as a single line formatted JSON object.
+# See the naming convention in:
+#   https://kubernetes.io/docs/concepts/overview/working-with-objects/annotations/
+worker_annotations =
+
+
+[kubernetes_node_selectors]
+# The Key-value pairs to be given to worker pods.
+# The worker pods will be scheduled to the nodes of the specified key-value pairs.
+# Should be supplied in the format: key = value
+
+[kubernetes_environment_variables]
+# The scheduler sets the following environment variables into your workers. You may define as
+# many environment variables as needed and the kubernetes launcher will set them in the launched workers.
+# Environment variables in this section are defined as follows
+#     <environment_variable_key> = <environment_variable_value>
+#
+# For example if you wanted to set an environment variable with value `prod` and key
+# `ENVIRONMENT` you would follow the following format:
+#     ENVIRONMENT = prod
+#
+# Additionally you may override worker airflow settings with the AIRFLOW__<SECTION>__<KEY>
+# formatting as supported by airflow normally.
+
+[kubernetes_secrets]
+# The scheduler mounts the following secrets into your workers as they are launched by the
+# scheduler. You may define as many secrets as needed and the kubernetes launcher will parse the
+# defined secrets and mount them as secret environment variables in the launched workers.
+# Secrets in this section are defined as follows
+#     <environment_variable_mount> = <kubernetes_secret_object>=<kubernetes_secret_key>
+#
+# For example if you wanted to mount a kubernetes secret key named `postgres_password` from the
+# kubernetes secret object `airflow-secret` as the environment variable `POSTGRES_PASSWORD` into
+# your workers you would follow the following format:
+#     POSTGRES_PASSWORD = airflow-secret=postgres_credentials
+#
+# Additionally you may override worker airflow settings with the AIRFLOW__<SECTION>__<KEY>
+# formatting as supported by airflow normally.
+
+[kubernetes_labels]
+# The Key-value pairs to be given to worker pods.
+# The worker pods will be given these static labels, as well as some additional dynamic labels
+# to identify the task.
+# Should be supplied in the format: key = value
diff --git a/airflow/data/dags/.gitkeep b/airflow/data/dags/.gitkeep
new file mode 100644
index 0000000..e69de29
diff --git a/airflow/data/dags/__init__.py b/airflow/data/dags/__init__.py
new file mode 100644
index 0000000..e69de29
diff --git a/airflow/data/dags/tutorial.py b/airflow/data/dags/tutorial.py
new file mode 100644
index 0000000..e994c1c
--- /dev/null
+++ b/airflow/data/dags/tutorial.py
@@ -0,0 +1,104 @@
+# -*- coding: utf-8 -*-
+#
+# Licensed to the Apache Software Foundation (ASF) under one
+# or more contributor license agreements.  See the NOTICE file
+# distributed with this work for additional information
+# regarding copyright ownership.  The ASF licenses this file
+# to you under the Apache License, Version 2.0 (the
+# "License"); you may not use this file except in compliance
+# with the License.  You may obtain a copy of the License at
+#
+#   http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing,
+# software distributed under the License is distributed on an
+# "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
+# KIND, either express or implied.  See the License for the
+# specific language governing permissions and limitations
+# under the License.
+
+"""
+### Tutorial Documentation
+Documentation that goes along with the Airflow tutorial located
+[here](https://airflow.apache.org/tutorial.html)
+"""
+from datetime import timedelta
+
+import airflow
+from airflow import DAG
+from airflow.operators.bash_operator import BashOperator
+
+# These args will get passed on to each operator
+# You can override them on a per-task basis during operator initialization
+default_args = {
+    'owner': 'Airflow',
+    'depends_on_past': False,
+    'start_date': airflow.utils.dates.days_ago(2),
+    'email': ['airflow@example.com'],
+    'email_on_failure': False,
+    'email_on_retry': False,
+    'retries': 1,
+    'retry_delay': timedelta(minutes=5),
+    # 'queue': 'bash_queue',
+    # 'pool': 'backfill',
+    # 'priority_weight': 10,
+    # 'end_date': datetime(2016, 1, 1),
+    # 'wait_for_downstream': False,
+    # 'dag': dag,
+    # 'sla': timedelta(hours=2),
+    # 'execution_timeout': timedelta(seconds=300),
+    # 'on_failure_callback': some_function,
+    # 'on_success_callback': some_other_function,
+    # 'on_retry_callback': another_function,
+    # 'sla_miss_callback': yet_another_function,
+    # 'trigger_rule': 'all_success'
+}
+
+dag = DAG(
+    'tutorial',
+    default_args=default_args,
+    description='A simple tutorial DAG',
+    schedule_interval=timedelta(days=1),
+)
+
+# t1, t2 and t3 are examples of tasks created by instantiating operators
+t1 = BashOperator(
+    task_id='print_date',
+    bash_command='date',
+    dag=dag,
+)
+
+t1.doc_md = """\
+#### Task Documentation
+You can document your task using the attributes `doc_md` (markdown),
+`doc` (plain text), `doc_rst`, `doc_json`, `doc_yaml` which gets
+rendered in the UI's Task Instance Details page.
+![img](http://montcs.bloomu.edu/~bobmon/Semesters/2012-01/491/import%20soul.png)
+"""
+
+dag.doc_md = __doc__
+
+t2 = BashOperator(
+    task_id='sleep',
+    depends_on_past=False,
+    bash_command='sleep 5',
+    dag=dag,
+)
+
+templated_command = """
+{% for i in range(5) %}
+    echo "{{ ds }}"
+    echo "{{ macros.ds_add(ds, 7)}}"
+    echo "{{ params.my_param }}"
+{% endfor %}
+"""
+
+t3 = BashOperator(
+    task_id='templated',
+    depends_on_past=False,
+    bash_command=templated_command,
+    params={'my_param': 'Parameter I passed in'},
+    dag=dag,
+)
+
+t1 >> [t2, t3]
diff --git a/airflow/data/default_airflow.cfg b/airflow/data/default_airflow.cfg
new file mode 100644
index 0000000..ae46feb
--- /dev/null
+++ b/airflow/data/default_airflow.cfg
@@ -0,0 +1,825 @@
+# -*- coding: utf-8 -*-
+#
+# Licensed to the Apache Software Foundation (ASF) under one
+# or more contributor license agreements.  See the NOTICE file
+# distributed with this work for additional information
+# regarding copyright ownership.  The ASF licenses this file
+# to you under the Apache License, Version 2.0 (the
+# "License"); you may not use this file except in compliance
+# with the License.  You may obtain a copy of the License at
+#
+#   http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing,
+# software distributed under the License is distributed on an
+# "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
+# KIND, either express or implied.  See the License for the
+# specific language governing permissions and limitations
+# under the License.
+
+
+# This is the template for Airflow's default configuration. When Airflow is
+# imported, it looks for a configuration file at $AIRFLOW_HOME/airflow.cfg. If
+# it doesn't exist, Airflow uses this template to generate it by replacing
+# variables in curly braces with their global values from configuration.py.
+
+# Users should not modify this file; they should customize the generated
+# airflow.cfg instead.
+
+
+# ----------------------- TEMPLATE BEGINS HERE -----------------------
+
+[core]
+# The folder where your airflow pipelines live, most likely a
+# subfolder in a code repository
+# This path must be absolute
+dags_folder = {AIRFLOW_HOME}/dags
+
+# The folder where airflow should store its log files
+# This path must be absolute
+base_log_folder = {AIRFLOW_HOME}/logs
+
+# Airflow can store logs remotely in AWS S3, Google Cloud Storage or Elastic Search.
+# Users must supply an Airflow connection id that provides access to the storage
+# location. If remote_logging is set to true, see UPDATING.md for additional
+# configuration requirements.
+remote_logging = False
+remote_log_conn_id =
+remote_base_log_folder =
+encrypt_s3_logs = False
+
+# Logging level
+logging_level = INFO
+fab_logging_level = WARN
+
+# Logging class
+# Specify the class that will specify the logging configuration
+# This class has to be on the python classpath
+# logging_config_class = my.path.default_local_settings.LOGGING_CONFIG
+logging_config_class =
+
+# Log format
+# Colour the logs when the controlling terminal is a TTY.
+colored_console_log = True
+colored_log_format = [%%(blue)s%%(asctime)s%%(reset)s] {{%%(blue)s%%(filename)s:%%(reset)s%%(lineno)d}} %%(log_color)s%%(levelname)s%%(reset)s - %%(log_color)s%%(message)s%%(reset)s
+colored_formatter_class = airflow.utils.log.colored_log.CustomTTYColoredFormatter
+
+log_format = [%%(asctime)s] {{%%(filename)s:%%(lineno)d}} %%(levelname)s - %%(message)s
+simple_log_format = %%(asctime)s %%(levelname)s - %%(message)s
+
+# Specify prefix pattern like mentioned below with stream handler TaskHandlerWithCustomFormatter
+# task_log_prefix_template =  {{ti.dag_id}}-{{ti.task_id}}-{{execution_date}}-{{try_number}}
+task_log_prefix_template =
+
+# Log filename format
+log_filename_template = {{{{ ti.dag_id }}}}/{{{{ ti.task_id }}}}/{{{{ ts }}}}/{{{{ try_number }}}}.log
+log_processor_filename_template = {{{{ filename }}}}.log
+dag_processor_manager_log_location = {AIRFLOW_HOME}/logs/dag_processor_manager/dag_processor_manager.log
+
+# Hostname by providing a path to a callable, which will resolve the hostname
+# The format is "package:function". For example,
+# default value "socket:getfqdn" means that result from getfqdn() of "socket" package will be used as hostname
+# No argument should be required in the function specified.
+# If using IP address as hostname is preferred, use value "airflow.utils.net:get_host_ip_address"
+hostname_callable = socket:getfqdn
+
+# Default timezone in case supplied date times are naive
+# can be utc (default), system, or any IANA timezone string (e.g. Europe/Amsterdam)
+default_timezone = utc
+
+# The executor class that airflow should use. Choices include
+# SequentialExecutor, LocalExecutor, CeleryExecutor, DaskExecutor, KubernetesExecutor
+executor = SequentialExecutor
+
+# The SqlAlchemy connection string to the metadata database.
+# SqlAlchemy supports many different database engine, more information
+# their website
+sql_alchemy_conn = sqlite:///{AIRFLOW_HOME}/airflow.db
+
+# The encoding for the databases
+sql_engine_encoding = utf-8
+
+# If SqlAlchemy should pool database connections.
+sql_alchemy_pool_enabled = True
+
+# The SqlAlchemy pool size is the maximum number of database connections
+# in the pool. 0 indicates no limit.
+sql_alchemy_pool_size = 5
+
+# The maximum overflow size of the pool.
+# When the number of checked-out connections reaches the size set in pool_size,
+# additional connections will be returned up to this limit.
+# When those additional connections are returned to the pool, they are disconnected and discarded.
+# It follows then that the total number of simultaneous connections the pool will allow is pool_size + max_overflow,
+# and the total number of "sleeping" connections the pool will allow is pool_size.
+# max_overflow can be set to -1 to indicate no overflow limit;
+# no limit will be placed on the total number of concurrent connections. Defaults to 10.
+sql_alchemy_max_overflow = 10
+
+# The SqlAlchemy pool recycle is the number of seconds a connection
+# can be idle in the pool before it is invalidated. This config does
+# not apply to sqlite. If the number of DB connections is ever exceeded,
+# a lower config value will allow the system to recover faster.
+sql_alchemy_pool_recycle = 1800
+
+# Check connection at the start of each connection pool checkout.
+# Typically, this is a simple statement like “SELECT 1”.
+# More information here: https://docs.sqlalchemy.org/en/13/core/pooling.html#disconnect-handling-pessimistic
+sql_alchemy_pool_pre_ping = True
+
+# The schema to use for the metadata database
+# SqlAlchemy supports databases with the concept of multiple schemas.
+sql_alchemy_schema =
+
+# The amount of parallelism as a setting to the executor. This defines
+# the max number of task instances that should run simultaneously
+# on this airflow installation
+parallelism = 32
+
+# The number of task instances allowed to run concurrently by the scheduler
+dag_concurrency = 16
+
+# Are DAGs paused by default at creation
+dags_are_paused_at_creation = True
+
+# The maximum number of active DAG runs per DAG
+max_active_runs_per_dag = 16
+
+# Whether to load the examples that ship with Airflow. It's good to
+# get started, but you probably want to set this to False in a production
+# environment
+load_examples = True
+
+# Where your Airflow plugins are stored
+plugins_folder = {AIRFLOW_HOME}/plugins
+
+# Secret key to save connection passwords in the db
+fernet_key = {FERNET_KEY}
+
+# Whether to disable pickling dags
+donot_pickle = True
+
+# How long before timing out a python file import
+dagbag_import_timeout = 30
+
+# How long before timing out a DagFileProcessor, which processes a dag file
+dag_file_processor_timeout = 50
+
+# The class to use for running task instances in a subprocess
+task_runner = StandardTaskRunner
+
+# If set, tasks without a `run_as_user` argument will be run with this user
+# Can be used to de-elevate a sudo user running Airflow when executing tasks
+default_impersonation =
+
+# What security module to use (for example kerberos):
+security =
+
+# If set to False enables some unsecure features like Charts and Ad Hoc Queries.
+# In 2.0 will default to True.
+secure_mode = False
+
+# Turn unit test mode on (overwrites many configuration options with test
+# values at runtime)
+unit_test_mode = False
+
+# Name of handler to read task instance logs.
+# Default to use task handler.
+task_log_reader = task
+
+# Whether to enable pickling for xcom (note that this is insecure and allows for
+# RCE exploits). This will be deprecated in Airflow 2.0 (be forced to False).
+enable_xcom_pickling = True
+
+# When a task is killed forcefully, this is the amount of time in seconds that
+# it has to cleanup after it is sent a SIGTERM, before it is SIGKILLED
+killed_task_cleanup_time = 60
+
+# Whether to override params with dag_run.conf. If you pass some key-value pairs through `airflow dags backfill -c` or
+# `airflow dags trigger -c`, the key-value pairs will override the existing ones in params.
+dag_run_conf_overrides_params = False
+
+# Worker initialisation check to validate Metadata Database connection
+worker_precheck = False
+
+# When discovering DAGs, ignore any files that don't contain the strings `DAG` and `airflow`.
+dag_discovery_safe_mode = True
+
+# The number of retries each task is going to have by default. Can be overridden at dag or task level.
+default_task_retries = 0
+
+
+[cli]
+# In what way should the cli access the API. The LocalClient will use the
+# database directly, while the json_client will use the api running on the
+# webserver
+api_client = airflow.api.client.local_client
+
+# If you set web_server_url_prefix, do NOT forget to append it here, ex:
+# endpoint_url = http://localhost:8080/myroot
+# So api will look like: http://localhost:8080/myroot/api/experimental/...
+endpoint_url = http://localhost:8080
+
+[api]
+# How to authenticate users of the API
+auth_backend = airflow.api.auth.backend.default
+
+[lineage]
+# what lineage backend to use
+backend =
+
+[atlas]
+sasl_enabled = False
+host =
+port = 21000
+username =
+password =
+
+[operators]
+# The default owner assigned to each new operator, unless
+# provided explicitly or passed via `default_args`
+default_owner = airflow
+default_cpus = 1
+default_ram = 512
+default_disk = 512
+default_gpus = 0
+
+[hive]
+# Default mapreduce queue for HiveOperator tasks
+default_hive_mapred_queue =
+# Template for mapred_job_name in HiveOperator, supports the following named parameters:
+# hostname, dag_id, task_id, execution_date
+mapred_job_name_template = Airflow HiveOperator task for {{hostname}}.{{dag_id}}.{{task_id}}.{{execution_date}}
+
+[webserver]
+# The base url of your website as airflow cannot guess what domain or
+# cname you are using. This is used in automated emails that
+# airflow sends to point links to the right web server
+base_url = http://localhost:8080
+
+# The ip specified when starting the web server
+web_server_host = 0.0.0.0
+
+# The port on which to run the web server
+web_server_port = 8080
+
+# Paths to the SSL certificate and key for the web server. When both are
+# provided SSL will be enabled. This does not change the web server port.
+web_server_ssl_cert =
+web_server_ssl_key =
+
+# Number of seconds the webserver waits before killing gunicorn master that doesn't respond
+web_server_master_timeout = 120
+
+# Number of seconds the gunicorn webserver waits before timing out on a worker
+web_server_worker_timeout = 120
+
+# Number of workers to refresh at a time. When set to 0, worker refresh is
+# disabled. When nonzero, airflow periodically refreshes webserver workers by
+# bringing up new ones and killing old ones.
+worker_refresh_batch_size = 1
+
+# Number of seconds to wait before refreshing a batch of workers.
+worker_refresh_interval = 30
+
+# Secret key used to run your flask app
+# It should be as random as possible
+secret_key = {SECRET_KEY}
+
+# Number of workers to run the Gunicorn web server
+workers = 4
+
+# The worker class gunicorn should use. Choices include
+# sync (default), eventlet, gevent
+worker_class = sync
+
+# Log files for the gunicorn webserver. '-' means log to stderr.
+access_logfile = -
+error_logfile = -
+
+# Expose the configuration file in the web server
+expose_config = False
+
+# Default DAG view.  Valid values are:
+# tree, graph, duration, gantt, landing_times
+dag_default_view = tree
+
+# Default DAG orientation. Valid values are:
+# LR (Left->Right), TB (Top->Bottom), RL (Right->Left), BT (Bottom->Top)
+dag_orientation = LR
+
+# Puts the webserver in demonstration mode; blurs the names of Operators for
+# privacy.
+demo_mode = False
+
+# The amount of time (in secs) webserver will wait for initial handshake
+# while fetching logs from other worker machine
+log_fetch_timeout_sec = 5
+
+# By default, the webserver shows paused DAGs. Flip this to hide paused
+# DAGs by default
+hide_paused_dags_by_default = False
+
+# Consistent page size across all listing views in the UI
+page_size = 100
+
+# Define the color of navigation bar
+navbar_color = #007A87
+
+# Default dagrun to show in UI
+default_dag_run_display_number = 25
+
+# Enable werkzeug `ProxyFix` middleware
+enable_proxy_fix = False
+
+# Set secure flag on session cookie
+cookie_secure = False
+
+# Set samesite policy on session cookie
+cookie_samesite =
+
+# Default setting for wrap toggle on DAG code and TI log views.
+default_wrap = False
+
+# Send anonymous user activity to your analytics tool
+# analytics_tool = # choose from google_analytics, segment, or metarouter
+# analytics_id = XXXXXXXXXXX
+
+[email]
+email_backend = airflow.utils.email.send_email_smtp
+
+
+[smtp]
+# If you want airflow to send emails on retries, failure, and you want to use
+# the airflow.utils.email.send_email_smtp function, you have to configure an
+# smtp server here
+smtp_host = localhost
+smtp_starttls = True
+smtp_ssl = False
+# Uncomment and set the user/pass settings if you want to use SMTP AUTH
+# smtp_user = airflow
+# smtp_password = airflow
+smtp_port = 25
+smtp_mail_from = airflow@example.com
+
+[sentry]
+# Sentry (https://docs.sentry.io) integration
+sentry_dsn = 
+
+
+[celery]
+# This section only applies if you are using the CeleryExecutor in
+# [core] section above
+
+# The app name that will be used by celery
+celery_app_name = airflow.executors.celery_executor
+
+# The concurrency that will be used when starting workers with the
+# "airflow worker" command. This defines the number of task instances that
+# a worker will take, so size up your workers based on the resources on
+# your worker box and the nature of your tasks
+worker_concurrency = 16
+
+# The maximum and minimum concurrency that will be used when starting workers with the
+# "airflow worker" command (always keep minimum processes, but grow to maximum if necessary).
+# Note the value should be "max_concurrency,min_concurrency"
+# Pick these numbers based on resources on worker box and the nature of the task.
+# If autoscale option is available, worker_concurrency will be ignored.
+# http://docs.celeryproject.org/en/latest/reference/celery.bin.worker.html#cmdoption-celery-worker-autoscale
+# worker_autoscale = 16,12
+
+# When you start an airflow worker, airflow starts a tiny web server
+# subprocess to serve the workers local log files to the airflow main
+# web server, who then builds pages and sends them to users. This defines
+# the port on which the logs are served. It needs to be unused, and open
+# visible from the main web server to connect into the workers.
+worker_log_server_port = 8793
+
+# The Celery broker URL. Celery supports RabbitMQ, Redis and experimentally
+# a sqlalchemy database. Refer to the Celery documentation for more
+# information.
+# http://docs.celeryproject.org/en/latest/userguide/configuration.html#broker-settings
+broker_url = sqla+mysql://airflow:airflow@localhost:3306/airflow
+
+# The Celery result_backend. When a job finishes, it needs to update the
+# metadata of the job. Therefore it will post a message on a message bus,
+# or insert it into a database (depending of the backend)
+# This status is used by the scheduler to update the state of the task
+# The use of a database is highly recommended
+# http://docs.celeryproject.org/en/latest/userguide/configuration.html#task-result-backend-settings
+result_backend = db+mysql://airflow:airflow@localhost:3306/airflow
+
+# Celery Flower is a sweet UI for Celery. Airflow has a shortcut to start
+# it `airflow flower`. This defines the IP that Celery Flower runs on
+flower_host = 0.0.0.0
+
+# The root URL for Flower
+# Ex: flower_url_prefix = /flower
+flower_url_prefix =
+
+# This defines the port that Celery Flower runs on
+flower_port = 5555
+
+# Securing Flower with Basic Authentication
+# Accepts user:password pairs separated by a comma
+# Example: flower_basic_auth = user1:password1,user2:password2
+flower_basic_auth =
+
+# Default queue that tasks get assigned to and that worker listen on.
+default_queue = default
+
+# How many processes CeleryExecutor uses to sync task state.
+# 0 means to use max(1, number of cores - 1) processes.
+sync_parallelism = 0
+
+# Import path for celery configuration options
+celery_config_options = airflow.config_templates.default_celery.DEFAULT_CELERY_CONFIG
+
+# In case of using SSL
+ssl_active = False
+ssl_key =
+ssl_cert =
+ssl_cacert =
+
+# Celery Pool implementation.
+# Choices include: prefork (default), eventlet, gevent or solo.
+# See:
+#   https://docs.celeryproject.org/en/latest/userguide/workers.html#concurrency
+#   https://docs.celeryproject.org/en/latest/userguide/concurrency/eventlet.html
+pool = prefork
+
+[celery_broker_transport_options]
+# This section is for specifying options which can be passed to the
+# underlying celery broker transport.  See:
+# http://docs.celeryproject.org/en/latest/userguide/configuration.html#std:setting-broker_transport_options
+
+# The visibility timeout defines the number of seconds to wait for the worker
+# to acknowledge the task before the message is redelivered to another worker.
+# Make sure to increase the visibility timeout to match the time of the longest
+# ETA you're planning to use.
+#
+# visibility_timeout is only supported for Redis and SQS celery brokers.
+# See:
+#   http://docs.celeryproject.org/en/master/userguide/configuration.html#std:setting-broker_transport_options
+#
+#visibility_timeout = 21600
+
+[dask]
+# This section only applies if you are using the DaskExecutor in
+# [core] section above
+
+# The IP address and port of the Dask cluster's scheduler.
+cluster_address = 127.0.0.1:8786
+# TLS/ SSL settings to access a secured Dask scheduler.
+tls_ca =
+tls_cert =
+tls_key =
+
+
+[scheduler]
+# Task instances listen for external kill signal (when you clear tasks
+# from the CLI or the UI), this defines the frequency at which they should
+# listen (in seconds).
+job_heartbeat_sec = 5
+
+# The scheduler constantly tries to trigger new tasks (look at the
+# scheduler section in the docs for more information). This defines
+# how often the scheduler should run (in seconds).
+scheduler_heartbeat_sec = 5
+
+# The number of times to try to schedule each DAG file
+# -1 indicates unlimited number
+num_runs = -1
+
+# The number of seconds to wait between consecutive DAG file processing
+processor_poll_interval = 1
+
+# after how much time (seconds) a new DAGs should be picked up from the filesystem
+min_file_process_interval = 0
+
+# How often (in seconds) to scan the DAGs directory for new files. Default to 5 minutes.
+dag_dir_list_interval = 300
+
+# How often should stats be printed to the logs
+print_stats_interval = 30
+
+# If the last scheduler heartbeat happened more than scheduler_health_check_threshold ago (in seconds),
+# scheduler is considered unhealthy.
+# This is used by the health check in the "/health" endpoint
+scheduler_health_check_threshold = 30
+
+child_process_log_directory = {AIRFLOW_HOME}/logs/scheduler
+
+# Local task jobs periodically heartbeat to the DB. If the job has
+# not heartbeat in this many seconds, the scheduler will mark the
+# associated task instance as failed and will re-schedule the task.
+scheduler_zombie_task_threshold = 300
+
+# Turn off scheduler catchup by setting this to False.
+# Default behavior is unchanged and
+# Command Line Backfills still work, but the scheduler
+# will not do scheduler catchup if this is False,
+# however it can be set on a per DAG basis in the
+# DAG definition (catchup)
+catchup_by_default = True
+
+# This changes the batch size of queries in the scheduling main loop.
+# If this is too high, SQL query performance may be impacted by one
+# or more of the following:
+#  - reversion to full table scan
+#  - complexity of query predicate
+#  - excessive locking
+#
+# Additionally, you may hit the maximum allowable query length for your db.
+#
+# Set this to 0 for no limit (not advised)
+max_tis_per_query = 512
+
+# Statsd (https://github.com/etsy/statsd) integration settings
+statsd_on = False
+statsd_host = localhost
+statsd_port = 8125
+statsd_prefix = airflow
+
+# If you want to avoid send all the available metrics to StatsD,
+# you can configure an allow list of prefixes to send only the metrics that
+# start with the elements of the list (e.g: scheduler,executor,dagrun)
+statsd_allow_list =
+
+# The scheduler can run multiple threads in parallel to schedule dags.
+# This defines how many threads will run.
+max_threads = 2
+
+authenticate = False
+
+# Turn off scheduler use of cron intervals by setting this to False.
+# DAGs submitted manually in the web UI or with trigger_dag will still run.
+use_job_schedule = True
+
+[ldap]
+# set this to ldaps://<your.ldap.server>:<port>
+uri =
+user_filter = objectClass=*
+user_name_attr = uid
+group_member_attr = memberOf
+superuser_filter =
+data_profiler_filter =
+bind_user = cn=Manager,dc=example,dc=com
+bind_password = insecure
+basedn = dc=example,dc=com
+cacert = /etc/ca/ldap_ca.crt
+search_scope = LEVEL
+
+# This setting allows the use of LDAP servers that either return a
+# broken schema, or do not return a schema.
+ignore_malformed_schema = False
+
+[kerberos]
+ccache = /tmp/airflow_krb5_ccache
+# gets augmented with fqdn
+principal = airflow
+reinit_frequency = 3600
+kinit_path = kinit
+keytab = airflow.keytab
+
+
+[github_enterprise]
+api_rev = v3
+
+[admin]
+# UI to hide sensitive variable fields when set to True
+hide_sensitive_variable_fields = True
+
+[elasticsearch]
+# Elasticsearch host
+host =
+# Format of the log_id, which is used to query for a given tasks logs
+log_id_template = {{dag_id}}-{{task_id}}-{{execution_date}}-{{try_number}}
+# Used to mark the end of a log stream for a task
+end_of_log_mark = end_of_log
+# Qualified URL for an elasticsearch frontend (like Kibana) with a template argument for log_id
+# Code will construct log_id using the log_id template from the argument above.
+# NOTE: The code will prefix the https:// automatically, don't include that here.
+frontend =
+# Write the task logs to the stdout of the worker, rather than the default files
+write_stdout = False
+# Instead of the default log formatter, write the log lines as JSON
+json_format = False
+# Log fields to also attach to the json output, if enabled
+json_fields = asctime, filename, lineno, levelname, message
+
+[elasticsearch_configs]
+
+use_ssl = False
+verify_certs = True
+
+[kubernetes]
+# The repository, tag and imagePullPolicy of the Kubernetes Image for the Worker to Run
+worker_container_repository =
+worker_container_tag =
+worker_container_image_pull_policy = IfNotPresent
+
+# If True (default), worker pods will be deleted upon termination
+delete_worker_pods = True
+
+# Number of Kubernetes Worker Pod creation calls per scheduler loop
+worker_pods_creation_batch_size = 1
+
+# The Kubernetes namespace where airflow workers should be created. Defaults to `default`
+namespace = default
+
+# The name of the Kubernetes ConfigMap Containing the Airflow Configuration (this file)
+airflow_configmap =
+
+# For docker image already contains DAGs, this is set to `True`, and the worker will search for dags in dags_folder,
+# otherwise use git sync or dags volume claim to mount DAGs
+dags_in_image = False
+
+# For either git sync or volume mounted DAGs, the worker will look in this subpath for DAGs
+dags_volume_subpath =
+
+# For DAGs mounted via a volume claim (mutually exclusive with git-sync and host path)
+dags_volume_claim =
+
+# For volume mounted logs, the worker will look in this subpath for logs
+logs_volume_subpath =
+
+# A shared volume claim for the logs
+logs_volume_claim =
+
+# For DAGs mounted via a hostPath volume (mutually exclusive with volume claim and git-sync)
+# Useful in local environment, discouraged in production
+dags_volume_host =
+
+# A hostPath volume for the logs
+# Useful in local environment, discouraged in production
+logs_volume_host =
+
+# A list of configMapsRefs to envFrom. If more than one configMap is
+# specified, provide a comma separated list: configmap_a,configmap_b
+env_from_configmap_ref =
+
+# A list of secretRefs to envFrom. If more than one secret is
+# specified, provide a comma separated list: secret_a,secret_b
+env_from_secret_ref =
+
+# Git credentials and repository for DAGs mounted via Git (mutually exclusive with volume claim)
+git_repo =
+git_branch =
+git_subpath =
+# Use git_user and git_password for user authentication or git_ssh_key_secret_name and git_ssh_key_secret_key
+# for SSH authentication
+git_user =
+git_password =
+git_sync_root = /git
+git_sync_dest = repo
+# Mount point of the volume if git-sync is being used.
+# i.e. {AIRFLOW_HOME}/dags
+git_dags_folder_mount_point =
+
+# To get Git-sync SSH authentication set up follow this format
+#
+# airflow-secrets.yaml:
+# ---
+# apiVersion: v1
+# kind: Secret
+# metadata:
+#   name: airflow-secrets
+# data:
+#   # key needs to be gitSshKey
+#   gitSshKey: <base64_encoded_data>
+# ---
+# airflow-configmap.yaml:
+# apiVersion: v1
+# kind: ConfigMap
+# metadata:
+#   name: airflow-configmap
+# data:
+#   known_hosts: |
+#       github.com ssh-rsa <...>
+#   airflow.cfg: |
+#       ...
+#
+# git_ssh_key_secret_name = airflow-secrets
+# git_ssh_known_hosts_configmap_name = airflow-configmap
+git_ssh_key_secret_name =
+git_ssh_known_hosts_configmap_name =
+
+# To give the git_sync init container credentials via a secret, create a secret
+# with two fields: GIT_SYNC_USERNAME and GIT_SYNC_PASSWORD (example below) and
+# add `git_sync_credentials_secret = <secret_name>` to your airflow config under the kubernetes section
+#
+# Secret Example:
+# apiVersion: v1
+# kind: Secret
+# metadata:
+#   name: git-credentials
+# data:
+#   GIT_SYNC_USERNAME: <base64_encoded_git_username>
+#   GIT_SYNC_PASSWORD: <base64_encoded_git_password>
+git_sync_credentials_secret =
+
+# For cloning DAGs from git repositories into volumes: https://github.com/kubernetes/git-sync
+git_sync_container_repository = k8s.gcr.io/git-sync
+git_sync_container_tag = v3.1.1
+git_sync_init_container_name = git-sync-clone
+git_sync_run_as_user = 65533
+
+# The name of the Kubernetes service account to be associated with airflow workers, if any.
+# Service accounts are required for workers that require access to secrets or cluster resources.
+# See the Kubernetes RBAC documentation for more:
+#   https://kubernetes.io/docs/admin/authorization/rbac/
+worker_service_account_name =
+
+# Any image pull secrets to be given to worker pods, If more than one secret is
+# required, provide a comma separated list: secret_a,secret_b
+image_pull_secrets =
+
+# GCP Service Account Keys to be provided to tasks run on Kubernetes Executors
+# Should be supplied in the format: key-name-1:key-path-1,key-name-2:key-path-2
+gcp_service_account_keys =
+
+# Use the service account kubernetes gives to pods to connect to kubernetes cluster.
+# It's intended for clients that expect to be running inside a pod running on kubernetes.
+# It will raise an exception if called from a process not running in a kubernetes environment.
+in_cluster = True
+
+# When running with in_cluster=False change the default cluster_context or config_file
+# options to Kubernetes client. Leave blank these to use default behaviour like `kubectl` has.
+# cluster_context =
+# config_file =
+
+
+# Affinity configuration as a single line formatted JSON object.
+# See the affinity model for top-level key names (e.g. `nodeAffinity`, etc.):
+#   https://kubernetes.io/docs/reference/generated/kubernetes-api/v1.12/#affinity-v1-core
+affinity =
+
+# A list of toleration objects as a single line formatted JSON array
+# See:
+#   https://kubernetes.io/docs/reference/generated/kubernetes-api/v1.12/#toleration-v1-core
+tolerations =
+
+# **kwargs parameters to pass while calling a kubernetes client core_v1_api methods from Kubernetes Executor
+# provided as a single line formatted JSON dictionary string.
+# List of supported params in **kwargs are similar for all core_v1_apis, hence a single config variable for all apis
+# See:
+#   https://raw.githubusercontent.com/kubernetes-client/python/master/kubernetes/client/apis/core_v1_api.py
+kube_client_request_args =
+
+# Worker pods security context options
+# See:
+#   https://kubernetes.io/docs/tasks/configure-pod-container/security-context/
+
+# Specifies the uid to run the first process of the worker pods containers as
+run_as_user =
+
+# Specifies a gid to associate with all containers in the worker pods
+# if using a git_ssh_key_secret_name use an fs_group
+# that allows for the key to be read, e.g. 65533
+fs_group =
+
+# Annotations configuration as a single line formatted JSON object.
+# See the naming convention in:
+#   https://kubernetes.io/docs/concepts/overview/working-with-objects/annotations/
+worker_annotations =
+
+
+[kubernetes_node_selectors]
+# The Key-value pairs to be given to worker pods.
+# The worker pods will be scheduled to the nodes of the specified key-value pairs.
+# Should be supplied in the format: key = value
+
+[kubernetes_environment_variables]
+# The scheduler sets the following environment variables into your workers. You may define as
+# many environment variables as needed and the kubernetes launcher will set them in the launched workers.
+# Environment variables in this section are defined as follows
+#     <environment_variable_key> = <environment_variable_value>
+#
+# For example if you wanted to set an environment variable with value `prod` and key
+# `ENVIRONMENT` you would follow the following format:
+#     ENVIRONMENT = prod
+#
+# Additionally you may override worker airflow settings with the AIRFLOW__<SECTION>__<KEY>
+# formatting as supported by airflow normally.
+
+[kubernetes_secrets]
+# The scheduler mounts the following secrets into your workers as they are launched by the
+# scheduler. You may define as many secrets as needed and the kubernetes launcher will parse the
+# defined secrets and mount them as secret environment variables in the launched workers.
+# Secrets in this section are defined as follows
+#     <environment_variable_mount> = <kubernetes_secret_object>=<kubernetes_secret_key>
+#
+# For example if you wanted to mount a kubernetes secret key named `postgres_password` from the
+# kubernetes secret object `airflow-secret` as the environment variable `POSTGRES_PASSWORD` into
+# your workers you would follow the following format:
+#     POSTGRES_PASSWORD = airflow-secret=postgres_credentials
+#
+# Additionally you may override worker airflow settings with the AIRFLOW__<SECTION>__<KEY>
+# formatting as supported by airflow normally.
+
+[kubernetes_labels]
+# The Key-value pairs to be given to worker pods.
+# The worker pods will be given these static labels, as well as some additional dynamic labels
+# to identify the task.
+# Should be supplied in the format: key = value
diff --git a/airflow/data/logs/.gitkeep b/airflow/data/logs/.gitkeep
new file mode 100644
index 0000000..e69de29
diff --git a/airflow/data/plugins/.gitkeep b/airflow/data/plugins/.gitkeep
new file mode 100644
index 0000000..e69de29
diff --git a/airflow/docker-compose-master.yml b/airflow/deprecated/docker-compose-master.yml
similarity index 100%
rename from airflow/docker-compose-master.yml
rename to airflow/deprecated/docker-compose-master.yml
diff --git a/airflow/docker-compose-worker.yml b/airflow/deprecated/docker-compose-worker.yml
similarity index 100%
rename from airflow/docker-compose-worker.yml
rename to airflow/deprecated/docker-compose-worker.yml
diff --git a/airflow/docker-stack.yaml b/airflow/docker-stack.yaml
new file mode 100644
index 0000000..4e080f3
--- /dev/null
+++ b/airflow/docker-stack.yaml
@@ -0,0 +1,110 @@
+version: "3.7"
+
+services:
+
+  redis:
+    image: redis:alpine
+    command: --save 900 1
+    ports:
+      - "6379:6379"
+    volumes:
+      - /data/redis:/data
+    deploy:
+      replicas: 1
+      placement:
+        constraints:
+          - node.role == manager
+      restart_policy:
+        condition: on-failure
+  
+  postgres:
+    image: postgres:alpine
+    ports:
+      - "5432:5432"
+    volumes:
+      - /data/postgres:/var/lib/postgresql/data
+    environment:
+      - POSTGRES_USER=airflow
+      - POSTGRES_PASSWORD=airflow
+      - POSTGRES_DB=airflow
+    deploy:
+      replicas: 1
+      placement:
+        constraints:
+          - node.role == manager
+      restart_policy:
+        condition: on-failure
+
+  webserver:
+    image: vimagick/airflow
+    command: webserver
+    ports:
+      - "8080:8080"
+    volumes:
+      - airflow_data:/opt/airflow
+    deploy:
+      replicas: 1
+      placement:
+        constraints:
+          - node.role == manager
+      restart_policy:
+        condition: on-failure
+    depends_on:
+      - postgres
+      - redis
+
+  scheduler:
+    image: vimagick/airflow
+    command: scheduler
+    volumes:
+      - airflow_data:/opt/airflow
+    deploy:
+      replicas: 1
+      placement:
+        constraints:
+          - node.role == manager
+      restart_policy:
+        condition: on-failure
+    depends_on:
+      - webserver
+
+  flower:
+    image: vimagick/airflow
+    command: flower
+    ports:
+      - "5555:5555"
+    volumes:
+      - airflow_data:/opt/airflow
+    deploy:
+      replicas: 1
+      placement:
+        constraints:
+          - node.role == manager
+      restart_policy:
+        condition: on-failure
+    depends_on:
+      - webserver
+
+  worker:
+    image: vimagick/airflow
+    command: worker
+    volumes:
+      - airflow_data:/opt/airflow
+    deploy:
+      replicas: 0
+      placement:
+        constraints:
+          - node.role == worker
+      restart_policy:
+        condition: on-failure
+    depends_on:
+      - webserver
+
+volumes:
+
+  airflow_data:
+    driver: local
+    driver_opts:
+      type: nfs
+      o: "addr=10.0.0.1,nolock,soft,rw"
+      device: ":/export/airflow"