telemetry-airflow/airflow.cfg

[core]
# 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 = utc

hide_sensitive_var_conn_fields = True
sensitive_var_conn_names = 'cred,CRED,secret,SECRET,pass,PASS,password,Password,PASSWORD,private,PRIVATE,key,KEY,cert,CERT,token,TOKEN,AKIA'

# This setting would not have any effect in an existing deployment where the default_pool already exists.
default_pool_task_slot_count = 50

# The folder where your airflow pipelines live, most likely a
# subfolder in a code repository
dags_folder = $AIRFLOW_HOME/dags

# The executor class that airflow should use. Choices include
# SequentialExecutor, LocalExecutor, CeleryExecutor
executor = CeleryExecutor

# 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 = 16

# The number of task instances allowed to run concurrently by the scheduler
max_active_tasks_per_dag = 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 = 5

# 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

# Should tasks be executed via forking of the parent process ("False",
# the speedier option) or by spawning a new python process ("True" slow,
# but means plugin changes picked up by tasks straight away)
execute_tasks_new_python_interpreter = False

# Secret key to save connection passwords in the db
# Setting this to $AIRFLOW_FERNET_KEY is broken in 1.9 for initdb.  Set $AIRFLOW__CORE__FERNET_KEY instead
# fernet_key =

# Whether to disable pickling dags
donot_pickle = False

# How long before timing out a python file import while filling the DagBag
dagbag_import_timeout = 30.0

# Should a traceback be shown in the UI for dagbag import errors,
# instead of just the exception message
dagbag_import_error_tracebacks = True

# If tracebacks are shown, how many entries from the traceback should be shown
dagbag_import_error_traceback_depth = 2

# 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.
# Choices include StandardTaskRunner, CgroupTaskRunner or the full import path to the class
# when using a custom task runner.
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 =

# Turn unit test mode on (overwrites many configuration options with test
# values at runtime)
unit_test_mode = False

# Whether to enable pickling for xcom (note that this is insecure and allows for
# RCE exploits).
enable_xcom_pickling = False

# 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 = True

# When discovering DAGs, ignore any files that don't contain the strings ``DAG`` and ``airflow``.
dag_discovery_safe_mode = False

# The pattern syntax used in the ".airflowignore" files in the DAG directories. Valid values are
# ``regexp`` or ``glob``.
dag_ignore_file_syntax = regexp

# The number of retries each task is going to have by default. Can be overridden at dag or task level.
default_task_retries = 0

# The weighting method used for the effective total priority weight of the task
default_task_weight_rule = downstream

# The default task execution_timeout value for the operators. Expected an integer value to
# be passed into timedelta as seconds. If not specified, then the value is considered as None,
# meaning that the operators are never timed out by default.
default_task_execution_timeout =

# We will override the next 2 intervals in prod via env vars.
# Updating serialized DAG can not be faster than a minimum interval to reduce database write rate.
# This flag sets the minimum interval (in seconds) after which the serialized DAGs in the DB should be updated.
# This helps in reducing database write rate.
min_serialized_dag_update_interval = 10

# If True, serialized DAGs are compressed before writing to DB.
# Note: this will disable the DAG dependencies view
compress_serialized_dags = False

# Fetching serialized DAG can not be faster than a minimum interval to reduce database
# read rate. This config controls when your DAGs are updated in the Webserver
min_serialized_dag_fetch_interval = 5

# Whether to persist DAG files code in DB.
# If set to True, Webserver reads file contents from DB instead of
# trying to access files in a DAG folder.
# (Default is ``True``)
# Example: store_dag_code = True
# store_dag_code =

# Maximum number of Rendered Task Instance Fields (Template Fields) per task to store
# in the Database.
# All the template_fields for each of Task Instance are stored in the Database.
# Keeping this number small may cause an error when you try to view ``Rendered`` tab in
# TaskInstance view for older tasks.
max_num_rendered_ti_fields_per_task = 30

# On each dagrun check against defined SLAs
check_slas = True

# Path to custom XCom class that will be used to store and resolve operators results
# Example: xcom_backend = path.to.CustomXCom
xcom_backend = airflow.models.xcom.BaseXCom

# By default Airflow plugins are lazily-loaded (only loaded when required). Set it to ``False``,
# if you want to load plugins whenever 'airflow' is invoked via cli or loaded from module.
lazy_load_plugins = True

# By default Airflow providers are lazily-discovered (discovery and imports happen only when required).
# Set it to False, if you want to discover providers whenever 'airflow' is invoked via cli or
# loaded from module.
lazy_discover_providers = True

# The maximum list/dict length an XCom can push to trigger task mapping. If the pushed list/dict has a
# length exceeding this value, the task pushing the XCom will be failed automatically to prevent the
# mapped tasks from clogging the scheduler.
max_map_length = 1024

[database]
# Whether to load the default connections that ship with Airflow. It's good to
# get started, but you probably want to set this to ``False`` in a production
# environment
# We have configured google_cloud_default, so hopefully this wont remove it.
load_default_connections = False

# The SqlAlchemy connection string to the metadata database.
# SqlAlchemy supports many different database engine, more information
# their website
sql_alchemy_conn = $AIRFLOW_DATABASE_URL

# 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

# Number of times the code should be retried in case of DB Operational Errors.
# Not all transactions will be retried as it can cause undesired state.
# Currently it is only used in ``DagFileProcessor.process_file`` to retry ``dagbag.sync_to_db``.
max_db_retries = 3

# Collation for ``dag_id``, ``task_id``, ``key`` columns in case they have different encoding.
# By default this collation is the same as the database collation, however for ``mysql`` and ``mariadb``
# the default is ``utf8mb3_general_ci`` so that the index sizes of our index keys will not exceed
# the maximum size of allowed index when collation is set to ``utf8mb4`` variant
# (see https://github.com/apache/airflow/pull/17603#issuecomment-901121618).
# and https://github.com/apache/airflow/pull/17729/
# sql_engine_collation_for_ids =


[logging]
# The folder where airflow should store its log files. This location
base_log_folder = $AIRFLOW_HOME/logs

# Logging level.
#
# Supported values: ``CRITICAL``, ``ERROR``, ``WARNING``, ``INFO``, ``DEBUG``.
logging_level = INFO

# Logging level for celery. If not set, it uses the value of logging_level
#
# Supported values: ``CRITICAL``, ``ERROR``, ``WARNING``, ``INFO``, ``DEBUG``.
# celery_logging_level =

# Logging level for Flask-appbuilder UI.
#
# Supported values: ``CRITICAL``, ``ERROR``, ``WARNING``, ``INFO``, ``DEBUG``.
fab_logging_level = WARNING

# 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

# Logging class
# Specify the class that will specify the logging configuration
# This class has to be on the python classpath
# Example: logging_config_class = my.path.default_local_settings.LOGGING_CONFIG
# logging_config_class =

# Flag to enable/disable Colored logs in Console
# Colour the logs when the controlling terminal is a TTY.
colored_console_log = True

# Log format for when Colored logs is enabled
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

# Format of Log line
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
# Example: task_log_prefix_template = {{ti.dag_id}}-{{ti.task_id}}-{{execution_date}}-{{try_number}}
# task_log_prefix_template =

# Formatting for how airflow generates file names/paths for each task run.
log_filename_template = {{ ti.dag_id }}/{{ ti.task_id }}/{{ execution_date.strftime("%%Y-%%m-%%dT%%H:%%M:%%S") }}/{{ try_number }}.log

# Formatting for how airflow generates file names for log
log_processor_filename_template = {{ filename }}.log

# full path of dag_processor_manager logfile
dag_processor_manager_log_location = $AIRFLOW_HOME/logs/dag_processor_manager/dag_processor_manager.log

# Name of handler to read task instance logs.
# Defaults to use ``task`` handler.
task_log_reader = task

# A comma\-separated list of third-party logger names that will be configured to print messages to
# consoles\.
# Example: extra_logger_names = connexion,sqlalchemy
# extra_logger_names =


[webserver]
# The base url of your website as airflow cannot guess what domain or
# cname you are using. This is use in automated emails that
# airflow sends to point links to the right web server
base_url = $URL

# Default timezone to display all dates in the UI, can be UTC, system, or
# any IANA timezone string (e.g. Europe/Amsterdam). If left empty the
# default value of core/default_timezone will be used
# Example: default_ui_timezone = America/New_York
default_ui_timezone = UTC

# 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 = $PORT

# Secret key used to run your flask app
secret_key = $AIRFLOW_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 = gevent

# Set to true to turn on authentication : http://pythonhosted.org/airflow/installation.html#web-authentication
auth_backend = $AIRFLOW_AUTH_BACKEND

# 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 =

# 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_key =

# The type of backend used to store web session data, can be 'database' or 'securecookie'
# Example: session_backend = securecookie
# session_backend = database

# Number of seconds the webserver waits before killing gunicorn master that doesn't respond
web_server_master_timeout = 300

# Number of seconds the gunicorn webserver waits before timing out on a worker
web_server_worker_timeout = 300

# 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 = 6000

# If set to True, Airflow will track files in plugins_folder directory. When it detects changes,
# then reload the gunicorn.
# We set this to True for local development, and override it with ENV var in prod
# False in prod so that changes pushed to plugins folder do not kill currently running backfills
reload_on_plugin_change = True

# Log files for the gunicorn webserver. '-' means log to stderr.
access_logfile = -

# Log files for the gunicorn webserver. '-' means log to stderr.
error_logfile = -

# Access log format for gunicorn webserver.
# default format is %%(h)s %%(l)s %%(u)s %%(t)s "%%(r)s" %%(s)s %%(b)s "%%(f)s" "%%(a)s"
# documentation - https://docs.gunicorn.org/en/stable/settings.html#access-log-format
# access_logformat =

# Expose the configuration file in the web server
expose_config = True

# Expose hostname in the web server
expose_hostname = True

# Expose stacktrace in the web server
expose_stacktrace = True

# Default DAG view. Valid values are: ``tree``, ``graph``, ``duration``, ``gantt``, ``landing_times``
dag_default_view = grid

# Default DAG orientation. Valid values are:
# ``LR`` (Left->Right), ``TB`` (Top->Bottom), ``RL`` (Right->Left), ``BT`` (Bottom->Top)
dag_orientation = LR

# The amount of time (in secs) webserver will wait for initial handshake
# while fetching logs from other worker machine
log_fetch_timeout_sec = 5

# Time interval (in secs) to wait before next log fetching.
log_fetch_delay_sec = 2

# Distance away from page bottom to enable auto tailing.
log_auto_tailing_offset = 30

# Animation speed for auto tailing log display.
log_animation_speed = 1000

# 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 = #fff

# Default dagrun to show in UI
default_dag_run_display_number = 25

# Enable werkzeug ``ProxyFix`` middleware for reverse proxy
enable_proxy_fix = False

# Number of values to trust for ``X-Forwarded-For``.
# More info: https://werkzeug.palletsprojects.com/en/0.16.x/middleware/proxy_fix/
proxy_fix_x_for = 1

# Number of values to trust for ``X-Forwarded-Proto``
proxy_fix_x_proto = 1

# Number of values to trust for ``X-Forwarded-Host``
proxy_fix_x_host = 1

# Number of values to trust for ``X-Forwarded-Port``
proxy_fix_x_port = 1

# Number of values to trust for ``X-Forwarded-Prefix``
proxy_fix_x_prefix = 1

# Set secure flag on session cookie
cookie_secure = False

# Set samesite policy on session cookie
cookie_samesite = Lax

# Default setting for wrap toggle on DAG code and TI log views.
default_wrap = False

# Allow the UI to be rendered in a frame
x_frame_enabled = True

# Send anonymous user activity to your analytics tool
# choose from google_analytics, segment, or metarouter
# analytics_tool =

# Unique ID of your account in the analytics tool
# analytics_id =

# 'Recent Tasks' stats will show for old DagRuns if set
show_recent_stats_for_completed_runs = True

# Update FAB permissions and sync security manager roles
# on webserver startup
update_fab_perms = True

# The UI cookie lifetime in minutes. User will be logged out from UI after
# ``session_lifetime_minutes`` of non-activity
session_lifetime_minutes = 43200

# Sets a custom page title for the DAGs overview page and site title for all pages
# instance_name =

# Whether the custom page title for the DAGs overview page contains any Markup language
instance_name_has_markup = False

# How frequently, in seconds, the DAG data will auto-refresh in graph or grid view
# when auto-refresh is turned on
auto_refresh_interval = 3

# Boolean for displaying warning for publicly viewable deployment
warn_deployment_exposure = True

# Comma separated string of view events to exclude from dag audit view.
# All other events will be added minus the ones passed here.
# The audit logs in the db will not be affected by this parameter.
audit_view_excluded_events = gantt,landing_times,tries,duration,calendar,graph,grid,tree,tree_data

# Comma separated string of view events to include in dag audit view.
# If passed, only these events will populate the dag audit view.
# The audit logs in the db will not be affected by this parameter.
# Example: audit_view_included_events = dagrun_cleared,failed
# audit_view_included_events =

[email]
email_backend = $AIRFLOW_EMAIL_BACKEND

# Email connection to use
# email_conn_id = smtp_default

# Whether email alerts should be sent when a task is retried
default_email_on_retry = True

# Whether email alerts should be sent when a task failed
default_email_on_failure = True

# File that will be used as the template for Email subject (which will be rendered using Jinja2).
# If not set, Airflow uses a base template.
# Example: subject_template = /path/to/my_subject_template_file
# subject_template =

# File that will be used as the template for Email content (which will be rendered using Jinja2).
# If not set, Airflow uses a base template.
# Example: html_content_template = /path/to/my_html_content_template_file
# html_content_template =


[smtp]
# If you want airflow to send emails on retries, failure, and you want to
# the airflow.utils.send_email function, you have to configure an smtp
# server here
smtp_starttls = True
smtp_ssl = False
smtp_host = $AIRFLOW_SMTP_HOST
smtp_port = 587
smtp_user = $AIRFLOW_SMTP_USER
smtp_password = $AIRFLOW_SMTP_PASSWORD
smtp_mail_from = $AIRFLOW_SMTP_FROM
# smtp_timeout = 30
# smtp_retry_limit = 5


[sentry]
# Sentry (https://docs.sentry.io) integration. Here you can supply
# additional configuration options based on the Python platform. See:
# https://docs.sentry.io/error-reporting/configuration/?platform=python.
# Unsupported options: ``integrations``, ``in_app_include``, ``in_app_exclude``,
# ``ignore_errors``, ``before_breadcrumb``, ``before_send``, ``transport``.
# Enable error reporting to Sentry
# sentry_on = false
# sentry_dsn =


[celery_kubernetes_executor]
# This section only applies if you are using the ``CeleryKubernetesExecutor`` in
# ``[core]`` section above
# Define when to send a task to ``KubernetesExecutor`` when using ``CeleryKubernetesExecutor``.
# When the queue of a task is the value of ``kubernetes_queue`` (default ``kubernetes``),
# the task is executed via ``KubernetesExecutor``,
# otherwise via ``CeleryExecutor``
# kubernetes_queue = kubernetes


[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 = 32

# The maximum and minimum concurrency that will be used when starting workers with the
# ``airflow celery 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
# Example: worker_autoscale = 16,12
# worker_autoscale =

# Used to increase the number of tasks that a worker prefetches which can improve performance.
# The number of processes multiplied by worker_prefetch_multiplier is the number of tasks
# that are prefetched by a worker. A value greater than 1 can result in tasks being unnecessarily
# blocked if there are multiple workers and one worker prefetches tasks that sit behind long
# running tasks while another worker has unutilized processes that are unable to process the already
# claimed blocked tasks.
# https://docs.celeryproject.org/en/stable/userguide/optimizing.html#prefetch-limits
# Example: worker_prefetch_multiplier = 1
# worker_prefetch_multiplier =

# Specify if remote control of the workers is enabled.
# When using Amazon SQS as the broker, Celery creates lots of ``.*reply-celery-pidbox`` queues. You can
# prevent this by setting this to false. However, with this disabled Flower won't work.
# worker_enable_remote_control = true

# Umask that will be used when starting workers with the ``airflow celery worker``
# in daemon mode. This control the file-creation mode mask which determines the initial
# value of file permission bits for newly created files.
# worker_umask = 0o077

# The Celery broker URL. Celery supports RabbitMQ, Redis and experimentally
# a sqlalchemy database. Refer to the Celery documentation for more
# information.
broker_url = $AIRFLOW_BROKER_URL

# Another key Celery setting
result_backend = $AIRFLOW_RESULT_URL

# Celery Flower is a sweet UI for Celery. Airflow has a shortcut to start
# it ``airflow celery flower``. This defines the IP that Celery Flower runs on
flower_host = 0.0.0.0

# The root URL for Flower
# Example: flower_url_prefix = /flower
# flower_url_prefix =

# Celery Flower is a sweet UI for Celery. Airflow has a shortcut to start
# it `airflow flower`. This defines the port that Celery Flower runs on
flower_port = $AIRFLOW_FLOWER_PORT

# Securing Flower with Basic Authentication
# Accepts user:password pairs separated by a comma
# Example: flower_basic_auth = user1:password1,user2:password2
# flower_basic_auth =

# 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
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

# The number of seconds to wait before timing out ``send_task_to_executor`` or
# ``fetch_celery_task_state`` operations.
operation_timeout = 3.0

# Celery task will report its status as 'started' when the task is executed by a worker.
# This is used in Airflow to keep track of the running tasks and if a Scheduler is restarted
# or run in HA mode, it can adopt the orphan tasks launched by previous SchedulerJob.
task_track_started = True

# Time in seconds after which Adopted tasks are cleared by CeleryExecutor. This is helpful to clear
# stalled tasks.
task_adoption_timeout = 600

# The Maximum number of retries for publishing task messages to the broker when failing
# due to ``AirflowTaskTimeout`` error before giving up and marking Task as failed.
task_publish_max_retries = 3

# Worker initialisation check to validate Metadata Database connection
worker_precheck = False


# [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 =


[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
# Example: visibility_timeout = 21600
# visibility_timeout =


[operators]
# Default queue that tasks get assigned to and that worker listen on.
default_queue = default

# 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

# Is allowed to pass additional/unused arguments (args, kwargs) to the BaseOperator operator.
# If set to False, an exception will be thrown, otherwise only the console message will be displayed.
allow_illegal_arguments = False


[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
# Deprecated since version 2.2.0: The option has been moved to scheduler.scheduler_idle_sleep_time
scheduler_idle_sleep_time = 1

# Number of seconds after which a DAG file is parsed. The DAG file is parsed every
# ``min_file_process_interval`` number of seconds. Updates to DAGs are reflected after
# this interval. Keeping this number low will increase CPU usage.
min_file_process_interval = 60

# How often (in seconds) to check for stale DAGs (DAGs which are no longer present in
# the expected files) which should be deactivated.
deactivate_stale_dags_interval = 120

# How often (in seconds) to scan the DAGs directory for new files. Default to 5 minutes.
# This is set via env var to 300 in prod, but 30 for local testing
dag_dir_list_interval = 30

# How often should stats be printed to the logs. Setting to 0 will disable printing stats
print_stats_interval = 30

# How often (in seconds) should pool usage stats be sent to statsd (if statsd_on is enabled)
pool_metrics_interval = 20.0

# 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

# How often (in seconds) should the scheduler check for orphaned tasks and SchedulerJobs
orphaned_tasks_check_interval = 300.0
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

# How often (in seconds) should the scheduler check for zombie tasks.
zombie_detection_interval = 60.0

# 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 = False

# Setting this to True will make first task instance of a task
# ignore depends_on_past setting. A task instance will be considered
# as the first task instance of a task when there is no task instance
# in the DB with an execution_date earlier than it., i.e. no manual marking
# success will be needed for a newly added task to be scheduled.
ignore_first_depends_on_past_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

# Should the scheduler issue ``SELECT ... FOR UPDATE`` in relevant queries.
# If this is set to False then you should not run more than a single
# scheduler at once
use_row_level_locking = True

# Max number of DAGs to create DagRuns for per scheduler loop
#
# Default: 10
# max_dagruns_to_create_per_loop =

# How many DagRuns should a scheduler examine (and lock) when scheduling
# and queuing tasks.
#
# Default: 20
# max_dagruns_per_loop_to_schedule =

# Should the Task supervisor process perform a "mini scheduler" to attempt to schedule more tasks of the
# same DAG. Leaving this on will mean tasks in the same DAG execute quicker, but might starve out other
# dags in some circumstances
#
# Default: True
# schedule_after_task_execution =

# The scheduler can run multiple processes in parallel to parse dags.
# This defines how many processes will run.
parsing_processes = 2

# One of ``modified_time``, ``random_seeded_by_host`` and ``alphabetical``.
# The scheduler will list and sort the dag files to decide the parsing order.
#
# * ``modified_time``: Sort by modified time of the files. This is useful on large scale to parse the
#   recently modified DAGs first.
# * ``random_seeded_by_host``: Sort randomly across multiple Schedulers but with same order on the
#   same host. This is useful when running with Scheduler in HA mode where each scheduler can
#   parse different DAG files.
# * ``alphabetical``: Sort by filename
file_parsing_sort_mode = modified_time

# Whether the dag processor is running as a standalone process or it is a subprocess of a scheduler
# job.
standalone_dag_processor = False

# Only applicable if `[scheduler]standalone_dag_processor` is true and  callbacks are stored
# in database. Contains maximum number of callbacks that are fetched during a single loop.
max_callbacks_per_loop = 20

# 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

# Allow externally triggered DagRuns for Execution Dates in the future
# Only has effect if schedule_interval is set to None in DAG
allow_trigger_in_future = False

# DAG dependency detector class to use
dependency_detector = airflow.serialization.serialized_objects.DependencyDetector

# How often to check for expired trigger requests that have not run yet.
trigger_timeout_check_interval = 15

[triggerer]
# How many triggers a single Triggerer will run at once, by default.
default_capacity = 1000

[metrics]
# Statsd (https://github.com/etsy/statsd) integration settings
# statsd_on =  False
# statsd_host =  localhost
# statsd_port =  8125
# statsd_prefix = airflow

# To enable datadog integration to send airflow metrics.
statsd_datadog_enabled = False

# List of datadog tags attached to all metrics(e.g: key1:value1,key2:value2)
# statsd_datadog_tags =


# [secrets]
# Full class name of secrets backend to enable (will precede env vars and metastore in search path)
# Example: backend = airflow.providers.amazon.aws.secrets.systems_manager.SystemsManagerParameterStoreBackend
# backend =

# The backend_kwargs param is loaded into a dictionary and passed to __init__ of secrets backend class.
# See documentation for the secrets backend you are using. JSON is expected.
# Example for AWS Systems Manager ParameterStore:
# ``{{"connections_prefix": "/airflow/connections", "profile_name": "default"}}``
# backend_kwargs =

# [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


[debug]
# Used only with ``DebugExecutor``. If set to ``True`` DAG will fail with first
# failed task. Helpful for debugging purposes.
fail_fast = False


[api]
# Enables the deprecated experimental API. Please note that these APIs do not have access control.
# The authenticated user has full access.
#
# .. warning::
#
#   This `Experimental REST API <https://airflow.readthedocs.io/en/latest/rest-api-ref.html>`__ is
#   deprecated since version 2.0. Please consider using
#   `the Stable REST API <https://airflow.readthedocs.io/en/latest/stable-rest-api-ref.html>`__.
#   For more information on migration, see
#   `UPDATING.md <https://github.com/apache/airflow/blob/master/UPDATING.md>`_
enable_experimental_api = False

# How to authenticate users of the API. See
# https://airflow.apache.org/docs/apache-airflow/stable/security.html for possible values.
# ("airflow.api.auth.backend.default" allows all requests for historic reasons)
auth_backends = airflow.api.auth.backend.session

# Used to set the maximum page limit for API requests
maximum_page_limit = 100

# Used to set the default page limit when limit is zero. A default limit
# of 100 is set on OpenApi spec. However, this particular default limit
# only work when limit is set equal to zero(0) from API requests.
# If no limit is supplied, the OpenApi spec default is used.
fallback_page_limit = 100

# The intended audience for JWT token credentials used for authorization. This value must match on the client and server sides. If empty, audience will not be tested.
# Example: google_oauth2_audience = project-id-random-value.apps.googleusercontent.com
# google_oauth2_audience =

# Path to Google Cloud Service Account key file (JSON). If omitted, authorization based on
# `the Application Default Credentials
# <https://cloud.google.com/docs/authentication/production#finding_credentials_automatically>`__ will
# be used.
# Example: google_key_path = /files/service-account-json
# google_key_path =

# Used in response to a preflight request to indicate which HTTP
# headers can be used when making the actual request. This header is
# the server side response to the browser's
# Access-Control-Request-Headers header.
# access_control_allow_headers =

# Specifies the method or methods allowed when accessing the resource.
# access_control_allow_methods =

# Indicates whether the response can be shared with requesting code from the given origin.
# access_control_allow_origin =

[lineage]
# what lineage backend to use
# backend =

[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


# [lineage]
# what lineage backend to use
# backend =

# [atlas]
# sasl_enabled = False
# host =
# port = 21000
# username =
# password =

# [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 =

# [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

[sensors]
# A sensor will immediately fail without retrying if timeout is reached
# Set to 3 days, default is 7 days or 604800
default_timeout = 259200