@@ -39,6 +39,7 @@ simple_log_format = %%(asctime)s %%(levelname)s - %%(message)s
3939# we need to escape the curly braces by adding an additional curly brace
4040log_filename_template = {{ ti.dag_id }}/{{ ti.task_id }}/{{ ts }}/{{ try_number }}.log
4141log_processor_filename_template = {{ filename }}.log
42+ dag_processor_manager_log_location = /usr/local/airflow/logs/dag_processor_manager/dag_processor_manager.log
4243
4344# Hostname by providing a path to a callable, which will resolve the hostname
4445hostname_callable = socket:getfqdn
@@ -59,6 +60,9 @@ executor = SequentialExecutor
5960# If SqlAlchemy should pool database connections.
6061sql_alchemy_pool_enabled = True
6162
63+ # The encoding for the databases
64+ sql_engine_encoding = utf-8
65+
6266# The SqlAlchemy pool size is the maximum number of database connections
6367# in the pool. 0 indicates no limit.
6468sql_alchemy_pool_size = 5
@@ -73,6 +77,10 @@ sql_alchemy_pool_recycle = 1800
7377# disconnects. Setting this to 0 disables retries.
7478sql_alchemy_reconnect_timeout = 300
7579
80+ # The schema to use for the metadata database
81+ # SqlAlchemy supports databases with the concept of multiple schemas.
82+ sql_alchemy_schema =
83+
7684# The amount of parallelism as a setting to the executor. This defines
7785# the max number of task instances that should run simultaneously
7886# on this airflow installation
@@ -142,6 +150,9 @@ killed_task_cleanup_time = 60
142150# `airflow trigger_dag -c`, the key-value pairs will override the existing ones in params.
143151dag_run_conf_overrides_params = False
144152
153+ # Worker initialisation check to validate Metadata Database connection
154+ worker_precheck = False
155+
145156[cli]
146157# In what way should the cli access the API. The LocalClient will use the
147158# database directly, while the json_client will use the api running on the
@@ -180,6 +191,9 @@ default_gpus = 0
180191[hive]
181192# Default mapreduce queue for HiveOperator tasks
182193default_hive_mapred_queue =
194+ # Template for mapred_job_name in HiveOperator, supports the following named parameters:
195+ # hostname, dag_id, task_id, execution_date
196+ mapred_job_name_template = Airflow HiveOperator task for {hostname}.{dag_id}.{task_id}.{execution_date}
183197
184198[webserver]
185199# The base url of your website as airflow cannot guess what domain or
@@ -227,7 +241,10 @@ access_logfile = -
227241error_logfile = -
228242
229243# Expose the configuration file in the web server
230- expose_config = False
244+ # This is only applicable for the flask-admin based web UI (non FAB-based).
245+ # In the FAB-based web UI with RBAC feature,
246+ # access to configuration is controlled by role permissions.
247+ expose_config = True
231248
232249# Set to true to turn on authentication:
233250# https://airflow.incubator.apache.org/security.html#web-authentication
@@ -387,9 +404,7 @@ run_duration = -1
387404# after how much time a new DAGs should be picked up from the filesystem
388405min_file_process_interval = 0
389406
390- # How many seconds to wait between file-parsing loops to prevent the logs from being spammed.
391- min_file_parsing_loop_time = 1
392-
407+ # How often (in seconds) to scan the DAGs directory for new files. Default to 5 minutes.
393408dag_dir_list_interval = 300
394409
395410# How often should stats be printed to the logs
@@ -427,6 +442,10 @@ max_threads = 2
427442
428443authenticate = False
429444
445+ # Turn off scheduler use of cron intervals by setting this to False.
446+ # DAGs submitted manually in the web UI or with trigger_dag will still run.
447+ use_job_schedule = True
448+
430449[ldap]
431450# set this to ldaps://<your.ldap.server>:<port>
432451uri =
@@ -491,7 +510,6 @@ reinit_frequency = 3600
491510kinit_path = kinit
492511keytab = airflow.keytab
493512
494-
495513[github_enterprise]
496514api_rev = v3
497515
@@ -506,9 +524,11 @@ elasticsearch_log_id_template = {dag_id}-{task_id}-{execution_date}-{try_number}
506524elasticsearch_end_of_log_mark = end_of_log
507525
508526[kubernetes]
509- # The repository and tag of the Kubernetes Image for the Worker to Run
527+ # The repository, tag and imagePullPolicy of the Kubernetes Image for the Worker to Run
510528worker_container_repository =
511529worker_container_tag =
530+ worker_container_image_pull_policy = IfNotPresent
531+ worker_dags_folder =
512532
513533# If True (default), worker pods will be deleted upon termination
514534delete_worker_pods = True
@@ -562,6 +582,11 @@ gcp_service_account_keys =
562582# It will raise an exception if called from a process not running in a kubernetes environment.
563583in_cluster = True
564584
585+ [kubernetes_node_selectors]
586+ # The Key-value pairs to be given to worker pods.
587+ # The worker pods will be scheduled to the nodes of the specified key-value pairs.
588+ # Should be supplied in the format: key = value
589+
565590[kubernetes_secrets]
566591# The scheduler mounts the following secrets into your workers as they are launched by the
567592# scheduler. You may define as many secrets as needed and the kubernetes launcher will parse the
0 commit comments