Advertisement
Not a member of Pastebin yet?
Sign Up,
it unlocks many cool features!
- [core]
- # The home folder for airflow, default is ~/airflow
- airflow_home = /airflow
- # The folder where your airflow pipelines live, most likely a
- # subfolder in a code repository
- # This path must be absolute
- dags_folder = /airflow/dags
- # The folder where airflow should store its log files
- # This path must be absolute
- base_log_folder = /airflow/logs
- # Airflow can store logs remotely in AWS S3 or Google Cloud Storage. Users
- # must supply an Airflow connection id that provides access to the storage
- # location.
- remote_log_conn_id =
- encrypt_s3_logs = False
- # Logging level
- logging_level = INFO
- # 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
- log_format = [%%(asctime)s] {%%(filename)s:%%(lineno)d} %%(levelname)s - %%(message)s
- simple_log_format = %%(asctime)s %%(levelname)s - %%(message)s
- # The executor class that airflow should use. Choices include
- # SequentialExecutor, LocalExecutor, CeleryExecutor, DaskExecutor
- 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/airflow.db
- # The SqlAlchemy pool size is the maximum number of database connections
- # in the pool.
- sql_alchemy_pool_size = 5
- # 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.
- sql_alchemy_pool_recycle = 3600
- # 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 = 64
- # The number of task instances allowed to run concurrently by the scheduler
- dag_concurrency = 32
- # Are DAGs paused by default at creation
- dags_are_paused_at_creation = True
- # When not using pools, tasks are run in the "default pool",
- # whose size is guided by this config element
- non_pooled_task_slot_count = 128
- # 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/plugins
- # Secret key to save connection passwords in the db
- fernet_key = gX7DpsHZ9dBnMnzVPvD_WeaCM9FE8DXtncwEZBNT_j0=
- # Whether to disable pickling dags
- donot_pickle = False
- # How long before timing out a python file import while filling the DagBag
- dagbag_import_timeout = 30
- # The class to use for running task instances in a subprocess
- task_runner = BashTaskRunner
- # 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 =
- # 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 file task handler.
- logging_config_class = log_config.LOGGING_CONFIG
- task_log_reader = gcs.task
- remote_log_conn_id=datalake_gcp_connection
- # 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
- [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.json_client
- endpoint_url = http://0.0.0.0:443
- [api]
- # How to authenticate users of the API
- auth_backend = airflow.api.auth.backend.default
- [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
- [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:443
- authenticate = False
- auth_backend = airflow.contrib.auth.backends.password_auth
- # 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 = 443
- # 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 = /home/certs/rootCA.pem
- web_server_ssl_key = /home/certs/rootCA.key
- # 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
- secret_key = temporary_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
- # Set to true to turn on authentication:
- # http://pythonhosted.org/airflow/security.html#web-authentication
- #authenticate = False
- # Filter the list of dags by owner name (requires authentication to be enabled)
- filter_by_owner = False
- # Filtering mode. Choices include user (default) and ldapgroup.
- # Ldap group filtering requires using the ldap backend
- #
- # Note that the ldap server needs the "memberOf" overlay to be set up
- # in order to user the ldapgroup mode.
- owner_mode = user
- # Default DAG view. Valid values are:
- # tree, graph, duration, gantt, landing_times
- dag_default_view = graph
- # 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 = True
- # Consistent page size across all listing views in the UI
- page_size = 100
- [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
- [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
- celeryd_concurrency = 16
- # 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.
- broker_url = sqla+mysql://airflow:airflow@localhost:3306/airflow
- # Another key Celery setting
- celery_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
- # This defines the port that Celery Flower runs on
- flower_port = 5555
- # Default queue that tasks get assigned to and that worker listen on.
- default_queue = default
- # Import path for celery configuration options
- celery_config_options = airflow.config_templates.default_celery.DEFAULT_CELERY_CONFIG
- [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
- [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
- # after how much time should the scheduler terminate in seconds
- # -1 indicates to run continuously (see also num_runs)
- run_duration = -1
- # after how much time a new DAGs should be picked up from the filesystem
- min_file_process_interval = 0
- dag_dir_list_interval = 300
- # How often should stats be printed to the logs
- print_stats_interval = 30
- child_process_log_directory = /airflow/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.
- # This depends on query length limits and how long you are willing to hold locks.
- # 0 for no limit
- max_tis_per_query = 0
- # Statsd (https://github.com/etsy/statsd) integration settings
- statsd_on = False
- statsd_host = localhost
- statsd_port = 8125
- statsd_prefix = airflow
- # The scheduler can run multiple threads in parallel to schedule dags.
- # This defines how many threads will run.
- max_threads = 2
- authenticate = False
- [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
- [mesos]
- # Mesos master address which MesosExecutor will connect to.
- master = localhost:5050
- # The framework name which Airflow scheduler will register itself as on mesos
- framework_name = Airflow
- # Number of cpu cores required for running one task instance using
- # 'airflow run <dag_id> <task_id> <execution_date> --local -p <pickle_id>'
- # command on a mesos slave
- task_cpu = 1
- # Memory in MB required for running one task instance using
- # 'airflow run <dag_id> <task_id> <execution_date> --local -p <pickle_id>'
- # command on a mesos slave
- task_memory = 256
- # Enable framework checkpointing for mesos
- # See http://mesos.apache.org/documentation/latest/slave-recovery/
- checkpoint = False
- # Failover timeout in milliseconds.
- # When checkpointing is enabled and this option is set, Mesos waits
- # until the configured timeout for
- # the MesosExecutor framework to re-register after a failover. Mesos
- # shuts down running tasks if the
- # MesosExecutor framework fails to re-register within this timeframe.
- # failover_timeout = 604800
- # Enable framework authentication for mesos
- # See http://mesos.apache.org/documentation/latest/configuration/
- authenticate = False
- # Mesos credentials, if authentication is enabled
- # default_principal = admin
- # default_secret = admin
- [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
Advertisement
Add Comment
Please, Sign In to add comment
Advertisement