@@ -39,6 +39,7 @@ simple_log_format = %%(asctime)s %%(levelname)s - %%(message)s
39
39
# we need to escape the curly braces by adding an additional curly brace
40
40
log_filename_template = {{ ti.dag_id }}/{{ ti.task_id }}/{{ ts }}/{{ try_number }}.log
41
41
log_processor_filename_template = {{ filename }}.log
42
+ dag_processor_manager_log_location = /usr/local/airflow/logs/dag_processor_manager/dag_processor_manager.log
42
43
43
44
# Hostname by providing a path to a callable, which will resolve the hostname
44
45
hostname_callable = socket:getfqdn
@@ -59,6 +60,9 @@ executor = SequentialExecutor
59
60
# If SqlAlchemy should pool database connections.
60
61
sql_alchemy_pool_enabled = True
61
62
63
+ # The encoding for the databases
64
+ sql_engine_encoding = utf-8
65
+
62
66
# The SqlAlchemy pool size is the maximum number of database connections
63
67
# in the pool. 0 indicates no limit.
64
68
sql_alchemy_pool_size = 5
@@ -73,6 +77,10 @@ sql_alchemy_pool_recycle = 1800
73
77
# disconnects. Setting this to 0 disables retries.
74
78
sql_alchemy_reconnect_timeout = 300
75
79
80
+ # The schema to use for the metadata database
81
+ # SqlAlchemy supports databases with the concept of multiple schemas.
82
+ sql_alchemy_schema =
83
+
76
84
# The amount of parallelism as a setting to the executor. This defines
77
85
# the max number of task instances that should run simultaneously
78
86
# on this airflow installation
@@ -142,6 +150,9 @@ killed_task_cleanup_time = 60
142
150
# `airflow trigger_dag -c`, the key-value pairs will override the existing ones in params.
143
151
dag_run_conf_overrides_params = False
144
152
153
+ # Worker initialisation check to validate Metadata Database connection
154
+ worker_precheck = False
155
+
145
156
[cli]
146
157
# In what way should the cli access the API. The LocalClient will use the
147
158
# database directly, while the json_client will use the api running on the
@@ -180,6 +191,9 @@ default_gpus = 0
180
191
[hive]
181
192
# Default mapreduce queue for HiveOperator tasks
182
193
default_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}
183
197
184
198
[webserver]
185
199
# The base url of your website as airflow cannot guess what domain or
@@ -227,7 +241,10 @@ access_logfile = -
227
241
error_logfile = -
228
242
229
243
# 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
231
248
232
249
# Set to true to turn on authentication:
233
250
# https://airflow.incubator.apache.org/security.html#web-authentication
@@ -387,9 +404,7 @@ run_duration = -1
387
404
# after how much time a new DAGs should be picked up from the filesystem
388
405
min_file_process_interval = 0
389
406
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.
393
408
dag_dir_list_interval = 300
394
409
395
410
# How often should stats be printed to the logs
@@ -427,6 +442,10 @@ max_threads = 2
427
442
428
443
authenticate = False
429
444
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
+
430
449
[ldap]
431
450
# set this to ldaps://<your.ldap.server>:<port>
432
451
uri =
@@ -491,7 +510,6 @@ reinit_frequency = 3600
491
510
kinit_path = kinit
492
511
keytab = airflow.keytab
493
512
494
-
495
513
[github_enterprise]
496
514
api_rev = v3
497
515
@@ -506,9 +524,11 @@ elasticsearch_log_id_template = {dag_id}-{task_id}-{execution_date}-{try_number}
506
524
elasticsearch_end_of_log_mark = end_of_log
507
525
508
526
[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
510
528
worker_container_repository =
511
529
worker_container_tag =
530
+ worker_container_image_pull_policy = IfNotPresent
531
+ worker_dags_folder =
512
532
513
533
# If True (default), worker pods will be deleted upon termination
514
534
delete_worker_pods = True
@@ -562,6 +582,11 @@ gcp_service_account_keys =
562
582
# It will raise an exception if called from a process not running in a kubernetes environment.
563
583
in_cluster = True
564
584
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
+
565
590
[kubernetes_secrets]
566
591
# The scheduler mounts the following secrets into your workers as they are launched by the
567
592
# scheduler. You may define as many secrets as needed and the kubernetes launcher will parse the
0 commit comments