Repository navigation
Expand file tree
/
Copy pathairflow.cfg
More file actions
4061 lines (3567 loc) · 137 KB
/
Copy pathairflow.cfg
File metadata and controls
4061 lines (3567 loc) · 137 KB
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
[core]
# The folder where your airflow pipelines live, most likely a
# subfolder in a code repository. This path must be absolute.
#
# Variable: AIRFLOW__CORE__DAGS_FOLDER
#
# Hostname by providing a path to a callable, which will resolve the hostname.
# The format is "package.function".
#
# For example, default value ``airflow.utils.net.getfqdn`` means that result from patched
# version of `socket.getfqdn() <https://docs.python.org/3/library/socket.html#socket.getfqdn>`__,
# see related `CPython Issue <https://github.com/python/cpython/issues/49254>`__.
#
# 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``
#
# Variable: AIRFLOW__CORE__HOSTNAME_CALLABLE
#
hostname_callable = airflow.utils.net.getfqdn
# A callable to check if a python file has airflow dags defined or not and should
# return ``True`` if it has dags otherwise ``False``.
# If this is not provided, Airflow uses its own heuristic rules.
#
# The function should have the following signature
#
# .. code-block:: python
#
# def func_name(file_path: str, zip_file: zipfile.ZipFile | None = None) -> bool: ...
#
# Variable: AIRFLOW__CORE__MIGHT_CONTAIN_DAG_CALLABLE
#
might_contain_dag_callable = airflow.utils.file.might_contain_dag_via_default_heuristic
# Default timezone in case supplied date times are naive
# can be `UTC` (default), `system`, or any `IANA <https://www.iana.org/time-zones>`
# timezone string (e.g. Europe/Amsterdam)
#
# Variable: AIRFLOW__CORE__DEFAULT_TIMEZONE
#
default_timezone = utc
# The executor class that airflow should use. Choices include
# ``LocalExecutor``, ``CeleryExecutor``,
# ``KubernetesExecutor`` or the full import path to the class when using a custom executor.
#
# Variable: AIRFLOW__CORE__EXECUTOR
#
executor = LocalExecutor
# The auth manager class that airflow should use. Full import path to the auth manager class.
#
# Variable: AIRFLOW__CORE__AUTH_MANAGER
#
auth_manager = airflow.api_fastapi.auth.managers.simple.simple_auth_manager.SimpleAuthManager
# The list of users and their associated role in simple auth manager. If the simple auth manager is
# used in your environment, this list controls who can access the environment.
#
# List of user-role delimited with a comma. Each user-role is a colon delimited couple of username and
# role. Roles are predefined in simple auth managers: viewer, user, op, admin.
#
# You can also associate users to teams by appending the list of teams (separated by "|") as third item
# in the user-role definition. Example: ``bob:admin:marketing|hr``.
# This can only be used if ``[core] multi_team`` is set to True.
#
# Example: simple_auth_manager_users = bob:admin,peter:viewer
#
# Variable: AIRFLOW__CORE__SIMPLE_AUTH_MANAGER_USERS
#
simple_auth_manager_users = admin:admin
# Whether to disable authentication and allow everyone as admin in the environment.
#
# Variable: AIRFLOW__CORE__SIMPLE_AUTH_MANAGER_ALL_ADMINS
#
simple_auth_manager_all_admins = False
# The json file where the simple auth manager stores passwords for the configured users.
# By default this is ``AIRFLOW_HOME/simple_auth_manager_passwords.json.generated``.
#
# Example: simple_auth_manager_passwords_file = /path/to/passwords.json
#
# Variable: AIRFLOW__CORE__SIMPLE_AUTH_MANAGER_PASSWORDS_FILE
#
# simple_auth_manager_passwords_file =
# This defines the maximum number of task instances that can run concurrently per scheduler in
# Airflow, regardless of the worker count. Generally this value, multiplied by the number of
# schedulers in your cluster, is the maximum number of task instances with the running
# state in the metadata database. The value must be larger or equal 1.
#
# Variable: AIRFLOW__CORE__PARALLELISM
#
parallelism = 32
# The maximum number of task instances allowed to run concurrently in each dag run.
# This is also configurable per-dag with ``max_active_tasks``,
# which is defaulted as ``[core] max_active_tasks_per_dag``.
#
# An example scenario when this would be useful is when you want to stop a new dag run with an early
# start date from stealing all the executor slots in a cluster.
#
# Variable: AIRFLOW__CORE__MAX_ACTIVE_TASKS_PER_DAG
#
max_active_tasks_per_dag = 16
# Are DAGs paused by default at creation
#
# Variable: AIRFLOW__CORE__DAGS_ARE_PAUSED_AT_CREATION
#
dags_are_paused_at_creation = True
# The maximum number of active DAG runs per DAG. The scheduler will not create more DAG runs
# if it reaches the limit. This is configurable at the DAG level with ``max_active_runs``,
# which is defaulted as ``[core] max_active_runs_per_dag``.
#
# Variable: AIRFLOW__CORE__MAX_ACTIVE_RUNS_PER_DAG
#
max_active_runs_per_dag = 16
# (experimental) The maximum number of consecutive DAG failures before DAG is automatically paused.
# This is also configurable per DAG level with ``max_consecutive_failed_dag_runs``,
# which is defaulted as ``[core] max_consecutive_failed_dag_runs_per_dag``.
# If not specified, then the value is considered as 0,
# meaning that the dags are never paused out by default.
#
# Variable: AIRFLOW__CORE__MAX_CONSECUTIVE_FAILED_DAG_RUNS_PER_DAG
#
max_consecutive_failed_dag_runs_per_dag = 0
# Whether to load the Dag examples that ship with Airflow. It's good to
# get started, but you probably want to set this to ``False`` in a production
# environment
#
# .. note::
#
# If you are using the Official Airflow Docker Image, this value is set to ``False`` by default
# via the environment variable ``AIRFLOW__CORE__LOAD_EXAMPLES``. To enable example Dags when
# using the official image, you must explicitly set ``AIRFLOW__CORE__LOAD_EXAMPLES=True`` in your
# environment.
#
# Variable: AIRFLOW__CORE__LOAD_EXAMPLES
#
load_examples = True
# Path to the folder containing Airflow plugins
#
# Variable: AIRFLOW__CORE__PLUGINS_FOLDER
#
# Should tasks be executed via forking of the parent process
#
# * ``False``: Execute via forking of the parent process
# * ``True``: Spawning a new python process, slower than fork, but means plugin changes picked
# up by tasks straight away
#
# Variable: AIRFLOW__CORE__EXECUTE_TASKS_NEW_PYTHON_INTERPRETER
#
execute_tasks_new_python_interpreter = False
# Secret key to save connection passwords in the db
#
# Variable: AIRFLOW__CORE__FERNET_KEY
#
fernet_key = ukA6E-P_hSDgyOpAtM64519BOEIDkabAaqsY4eZyz7Q=
# How long before timing out a python file import
#
# Variable: AIRFLOW__CORE__DAGBAG_IMPORT_TIMEOUT
#
dagbag_import_timeout = 30.0
# Should a traceback be shown in the UI for dagbag import errors,
# instead of just the exception message
#
# Variable: AIRFLOW__CORE__DAGBAG_IMPORT_ERROR_TRACEBACKS
#
dagbag_import_error_tracebacks = True
# If tracebacks are shown, how many entries from the traceback should be shown
#
# Variable: AIRFLOW__CORE__DAGBAG_IMPORT_ERROR_TRACEBACK_DEPTH
#
dagbag_import_error_traceback_depth = 2
# 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
#
# Variable: AIRFLOW__CORE__DEFAULT_IMPERSONATION
#
default_impersonation =
# What security module to use (for example kerberos)
#
# Variable: AIRFLOW__CORE__SECURITY
#
security =
# Turn unit test mode on (overwrites many configuration options with test
# values at runtime)
#
# Variable: AIRFLOW__CORE__UNIT_TEST_MODE
#
unit_test_mode = False
# Space-separated list of classes that may be imported during deserialization. Items can be glob
# expressions. Python built-in classes (like dict) are always allowed.
#
# Example: allowed_deserialization_classes = airflow.* my_mod.my_other_mod.TheseClasses*
#
# Variable: AIRFLOW__CORE__ALLOWED_DESERIALIZATION_CLASSES
#
allowed_deserialization_classes = airflow.*
# Space-separated list of classes that may be imported during deserialization. Items are processed
# as regex expressions. Python built-in classes (like dict) are always allowed.
# This is a secondary option to ``[core] allowed_deserialization_classes``.
#
# Variable: AIRFLOW__CORE__ALLOWED_DESERIALIZATION_CLASSES_REGEXP
#
allowed_deserialization_classes_regexp =
# 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
#
# Variable: AIRFLOW__CORE__KILLED_TASK_CLEANUP_TIME
#
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.
#
# Variable: AIRFLOW__CORE__DAG_RUN_CONF_OVERRIDES_PARAMS
#
dag_run_conf_overrides_params = True
# If enabled, Airflow will only scan files containing both ``DAG`` and ``airflow`` (case-insensitive).
#
# Variable: AIRFLOW__CORE__DAG_DISCOVERY_SAFE_MODE
#
dag_discovery_safe_mode = True
# The pattern syntax used in the
# `.airflowignore
# <https://airflow.apache.org/docs/apache-airflow/stable/core-concepts/dags.html#airflowignore>`__
# files in the DAG directories. Valid values are ``regexp`` or ``glob``.
#
# Variable: AIRFLOW__CORE__DAG_IGNORE_FILE_SYNTAX
#
dag_ignore_file_syntax = glob
# The number of retries each task is going to have by default. Can be overridden at dag or task level.
#
# Variable: AIRFLOW__CORE__DEFAULT_TASK_RETRIES
#
default_task_retries = 0
# The number of seconds each task is going to wait by default between retries. Can be overridden at
# dag or task level.
#
# Variable: AIRFLOW__CORE__DEFAULT_TASK_RETRY_DELAY
#
default_task_retry_delay = 300
# The maximum delay (in seconds) each task is going to wait by default between retries.
# This is a global setting and cannot be overridden at task or DAG level.
#
# Variable: AIRFLOW__CORE__MAX_TASK_RETRY_DELAY
#
max_task_retry_delay = 86400
# The weighting method used for the effective total priority weight of the task
#
# Variable: AIRFLOW__CORE__DEFAULT_TASK_WEIGHT_RULE
#
default_task_weight_rule = downstream
# Maximum possible time (in seconds) that task will have for execution of auxiliary processes
# (like listeners, mini scheduler...) after task is marked as success..
#
# Variable: AIRFLOW__CORE__TASK_SUCCESS_OVERTIME
#
task_success_overtime = 20
# 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.
#
# Variable: AIRFLOW__CORE__DEFAULT_TASK_EXECUTION_TIMEOUT
#
default_task_execution_timeout =
# Updating serialized DAG can not be faster than a minimum interval to reduce database write rate.
#
# Variable: AIRFLOW__CORE__MIN_SERIALIZED_DAG_UPDATE_INTERVAL
#
min_serialized_dag_update_interval = 30
# If ``True``, serialized DAGs are compressed before writing to DB.
#
# .. note::
#
# This will disable the DAG dependencies view
#
# Variable: AIRFLOW__CORE__COMPRESS_SERIALIZED_DAGS
#
compress_serialized_dags = False
# Number of recent dag runs for which Rendered Task Instance Fields are retained.
# Records from older runs are deleted during task execution.
# Keeping this number small may cause an error when you try to view ``Rendered`` tab in
# TaskInstance view for older tasks.
#
# Variable: AIRFLOW__CORE__NUM_DAG_RUNS_TO_RETAIN_RENDERED_FIELDS
#
num_dag_runs_to_retain_rendered_fields = 30
# Path to custom XCom class that will be used to store and resolve operators results
#
# Example: xcom_backend = path.to.CustomXCom
#
# Variable: AIRFLOW__CORE__XCOM_BACKEND
#
xcom_backend = airflow.sdk.execution_time.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.
#
# Variable: AIRFLOW__CORE__LAZY_LOAD_PLUGINS
#
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.
#
# Variable: AIRFLOW__CORE__LAZY_DISCOVER_PROVIDERS
#
lazy_discover_providers = True
# Hide sensitive **Variables** or **Connection extra json keys** from UI
# and task logs when set to ``True``
#
# .. note::
#
# Connection passwords are always hidden in logs
#
# Variable: AIRFLOW__CORE__HIDE_SENSITIVE_VAR_CONN_FIELDS
#
hide_sensitive_var_conn_fields = True
# A comma-separated list of extra sensitive keywords to look for in variables names or connection's
# extra JSON.
#
# Variable: AIRFLOW__CORE__SENSITIVE_VAR_CONN_NAMES
#
sensitive_var_conn_names =
# Task Slot counts for ``default_pool``. This setting would not have any effect in an existing
# deployment where the ``default_pool`` is already created. For existing deployments, users can
# change the number of slots using Webserver, API or the CLI
#
# Variable: AIRFLOW__CORE__DEFAULT_POOL_TASK_SLOT_COUNT
#
default_pool_task_slot_count = 128
# 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.
#
# Variable: AIRFLOW__CORE__MAX_MAP_LENGTH
#
max_map_length = 1024
# The default umask to use for process when run in daemon mode (scheduler, worker, etc.)
#
# This controls the file-creation mode mask which determines the initial value of file permission bits
# for newly created files.
#
# This value is treated as an octal-integer.
#
# Variable: AIRFLOW__CORE__DAEMON_UMASK
#
daemon_umask = 0o077
# Class to use as asset manager.
#
# Example: asset_manager_class = airflow.assets.manager.AssetManager
#
# Variable: AIRFLOW__CORE__ASSET_MANAGER_CLASS
#
# asset_manager_class =
# Kwargs to supply to asset manager.
#
# Example: asset_manager_kwargs = {"some_param": "some_value"}
#
# Variable: AIRFLOW__CORE__ASSET_MANAGER_KWARGS
#
# asset_manager_kwargs =
# The ability to allow testing connections across Airflow UI, API and CLI.
# Supported options: ``Disabled``, ``Enabled``, ``Hidden``. Default: Disabled
# Disabled - Disables the test connection functionality and disables the Test Connection button in UI.
# Enabled - Enables the test connection functionality and shows the Test Connection button in UI.
# Hidden - Disables the test connection functionality and hides the Test Connection button in UI.
# Before setting this to Enabled, make sure that you review the users who are able to add/edit
# connections and ensure they are trusted. Connection testing can be done maliciously leading to
# undesired and insecure outcomes.
# See `Airflow Security Model: Capabilities of authenticated UI users
# <https://airflow.apache.org/docs/apache-airflow/stable/security/security_model.html#capabilities-of-authenticated-ui-users>`__
# for more details.
#
# Variable: AIRFLOW__CORE__TEST_CONNECTION
#
test_connection = Enabled
# The maximum length of the rendered template field. If the value to be stored in the
# rendered template field exceeds this size, it's redacted.
#
# Variable: AIRFLOW__CORE__MAX_TEMPLATED_FIELD_LENGTH
#
max_templated_field_length = 4096
# The url of the execution api server. Default is ``{BASE_URL}/execution/``
# where ``{BASE_URL}`` is the base url of the API Server. If ``{BASE_URL}`` is not set,
# it will use ``http://localhost:8080`` as the default base url.
#
# Variable: AIRFLOW__CORE__EXECUTION_API_SERVER_URL
#
# execution_api_server_url =
# Whether to run the Airflow environment in multi-team mode.
# In this mode, different teams can have scoped access to their own resources while still sharing the
# same underlying deployment.
#
# Variable: AIRFLOW__CORE__MULTI_TEAM
#
multi_team = False
[database]
# Path to the ``alembic.ini`` file. You can either provide the file path relative
# to the Airflow home directory or the absolute path if it is located elsewhere.
#
# Variable: AIRFLOW__DATABASE__ALEMBIC_INI_FILE_PATH
#
alembic_ini_file_path = alembic.ini
# The SQLAlchemy connection string to the metadata database.
# SQLAlchemy supports many different database engines.
# See: `Set up a Database Backend: Database URI
# <https://airflow.apache.org/docs/apache-airflow/stable/howto/set-up-database.html#database-uri>`__
# for more details.
#
# Variable: AIRFLOW__DATABASE__SQL_ALCHEMY_CONN
#
# The SQLAlchemy connection string to the metadata database used for async connections.
# If this is not set, Airflow automatically derives a string by converting ``sql_alchemy_conn``.
# Unfortunately, this conversion logic does not always work due to various incompatibilities
# between sync and async db driver implementations. This sets the connection string directly
# without any conversion instead.
#
# Example: sql_alchemy_conn_async = postgresql+asyncpg://postgres:airflow@postgres/airflow
#
# Variable: AIRFLOW__DATABASE__SQL_ALCHEMY_CONN_ASYNC
#
# sql_alchemy_conn_async =
# Extra engine specific keyword args passed to SQLAlchemy's create_engine, as a JSON-encoded value
#
# Example: sql_alchemy_engine_args = {"arg1": true}
#
# Variable: AIRFLOW__DATABASE__SQL_ALCHEMY_ENGINE_ARGS
#
# sql_alchemy_engine_args =
# The encoding for the databases
#
# Variable: AIRFLOW__DATABASE__SQL_ENGINE_ENCODING
#
sql_engine_encoding = utf-8
# Collation for ``dag_id``, ``task_id``, ``key``, ``external_executor_id`` 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_bin`` 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
# `GitHub Issue Comment <https://github.com/apache/airflow/pull/17603#issuecomment-901121618>`__
# for more details.
#
# Variable: AIRFLOW__DATABASE__SQL_ENGINE_COLLATION_FOR_IDS
#
# sql_engine_collation_for_ids =
# If SQLAlchemy should pool database connections.
#
# Variable: AIRFLOW__DATABASE__SQL_ALCHEMY_POOL_ENABLED
#
sql_alchemy_pool_enabled = True
# The SQLAlchemy pool size is the maximum number of database connections
# in the pool. 0 indicates no limit.
#
# Variable: AIRFLOW__DATABASE__SQL_ALCHEMY_POOL_SIZE
#
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``.
#
# Variable: AIRFLOW__DATABASE__SQL_ALCHEMY_MAX_OVERFLOW
#
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.
#
# Variable: AIRFLOW__DATABASE__SQL_ALCHEMY_POOL_RECYCLE
#
sql_alchemy_pool_recycle = 1800
# Check connection at the start of each connection pool checkout.
# Typically, this is a simple statement like "SELECT 1".
# See `SQLAlchemy Pooling: Disconnect Handling - Pessimistic
# <https://docs.sqlalchemy.org/en/14/core/pooling.html#disconnect-handling-pessimistic>`__
# for more details.
#
# Variable: AIRFLOW__DATABASE__SQL_ALCHEMY_POOL_PRE_PING
#
sql_alchemy_pool_pre_ping = True
# The schema to use for the metadata database.
# SQLAlchemy supports databases with the concept of multiple schemas.
#
# Variable: AIRFLOW__DATABASE__SQL_ALCHEMY_SCHEMA
#
sql_alchemy_schema =
# Import path for connect args in SQLAlchemy. Defaults to an empty dict.
# This is useful when you want to configure db engine args that SQLAlchemy won't parse
# in connection string. This can be set by passing a dictionary containing the create engine parameters.
# For more details about passing create engine parameters (keepalives variables, timeout etc)
# in Postgres DB Backend see `Setting up a PostgreSQL Database
# <https://airflow.apache.org/docs/apache-airflow/stable/howto/set-up-database.html#setting-up-a-postgresql-database>`__
# e.g ``connect_args={"timeout":30}`` can be defined in ``airflow_local_settings.py`` and
# can be imported as shown below
#
# *Changed in 3.1.0*: This configuration is only applied to synchronous engines, such as psycopg2.
# See ``sql_alchemy_connect_args_async``.
#
# Example: sql_alchemy_connect_args = airflow_local_settings.connect_args
#
# Variable: AIRFLOW__DATABASE__SQL_ALCHEMY_CONNECT_ARGS
#
# sql_alchemy_connect_args =
# Import path for connect args in SQLAlchemy. Defaults to an empty dict.
# This is similar to ``sql_alchemy_connect_args``, but only for async connections.
#
# This configuration is only applied to async engines, such as asyncpg.
#
# Example: sql_alchemy_connect_args_async = airflow_local_settings.connect_args_async
#
# Variable: AIRFLOW__DATABASE__SQL_ALCHEMY_CONNECT_ARGS_ASYNC
#
# sql_alchemy_connect_args_async =
# Important Warning: Use of sql_alchemy_session_maker Highly Discouraged
# Import path for function which returns 'sqlalchemy.orm.sessionmaker'.
# Improper configuration of sql_alchemy_session_maker can lead to serious issues,
# including data corruption, unrecoverable application crashes. Please review the SQLAlchemy
# documentation for detailed guidance on proper configuration and best practices.
#
# Example: sql_alchemy_session_maker = airflow_local_settings._sessionmaker
#
# Variable: AIRFLOW__DATABASE__SQL_ALCHEMY_SESSION_MAKER
#
# sql_alchemy_session_maker =
# 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``.
#
# Variable: AIRFLOW__DATABASE__MAX_DB_RETRIES
#
max_db_retries = 3
# Whether to run alembic migrations during Airflow start up. Sometimes this operation can be expensive,
# and the users can assert the correct version through other means (e.g. through a Helm chart).
# Accepts ``True`` or ``False``.
#
# Variable: AIRFLOW__DATABASE__CHECK_MIGRATIONS
#
check_migrations = True
# Additional DB managers to include when migrating external tables in the Airflow
# database, beyond those automatically discovered from installed providers.
# The managers must inherit from BaseDBManager.
#
# Example: external_db_managers = airflow.providers.fab.auth_manager.models.db.FABDBManager
#
# Variable: AIRFLOW__DATABASE__EXTERNAL_DB_MANAGERS
#
# external_db_managers =
# The number of rows to process in each batch when performing a migration.
# This is useful for large tables to avoid locking and failure due to query timeouts.
#
# Variable: AIRFLOW__DATABASE__MIGRATION_BATCH_SIZE
#
migration_batch_size = 10000
[logging]
# The folder where airflow should store its log files.
# This path must be absolute.
# There are a few existing configurations that assume this is set to the default.
# If you choose to override this you may need to update the
# ``[logging] dag_processor_manager_log_location`` and
# ``[logging] dag_processor_child_process_log_directory settings`` as well.
#
# Variable: AIRFLOW__LOGGING__BASE_LOG_FOLDER
#
# Airflow can store logs remotely in AWS S3, Google Cloud Storage or Elastic Search.
# Set this to ``True`` if you want to enable remote logging.
#
# Variable: AIRFLOW__LOGGING__REMOTE_LOGGING
#
remote_logging = False
# Users must supply an Airflow connection id that provides access to the storage
# location. Depending on your remote logging service, this may only be used for
# reading logs, not writing them.
#
# Variable: AIRFLOW__LOGGING__REMOTE_LOG_CONN_ID
#
remote_log_conn_id =
# Whether the local log files for GCS, S3, WASB, HDFS and OSS remote logging should be deleted after
# they are uploaded to the remote location.
#
# Variable: AIRFLOW__LOGGING__DELETE_LOCAL_LOGS
#
delete_local_logs = False
# Path to Google Credential JSON file. If omitted, authorization based on `the Application Default
# Credentials
# <https://cloud.google.com/docs/authentication/application-default-credentials>`__ will
# be used.
#
# Variable: AIRFLOW__LOGGING__GOOGLE_KEY_PATH
#
google_key_path =
# Storage bucket URL for remote logging
# S3 buckets should start with **s3://**
# Cloudwatch log groups should start with **cloudwatch://**
# GCS buckets should start with **gs://**
# WASB buckets should start with **wasb** just to help Airflow select correct handler
# Stackdriver logs should start with **stackdriver://**
#
# Variable: AIRFLOW__LOGGING__REMOTE_BASE_LOG_FOLDER
#
remote_base_log_folder =
# The remote_task_handler_kwargs param is loaded into a dictionary and passed to the ``__init__``
# of remote task handler and it overrides the values provided by Airflow config. For example if you set
# ``delete_local_logs=False`` and you provide ``{"delete_local_copy": true}``, then the local
# log files will be deleted after they are uploaded to remote location.
#
# Example: remote_task_handler_kwargs = {"delete_local_copy": true}
#
# Variable: AIRFLOW__LOGGING__REMOTE_TASK_HANDLER_KWARGS
#
remote_task_handler_kwargs =
# Use server-side encryption for logs stored in S3
#
# Variable: AIRFLOW__LOGGING__ENCRYPT_S3_LOGS
#
encrypt_s3_logs = False
# Logging level.
#
# Individual loggers can be set at a different level with the :ref:`config:logging__namespace_levels`
# option.
#
# Supported values: ``CRITICAL``, ``ERROR``, ``WARNING``, ``INFO``, ``DEBUG``.
#
# Variable: AIRFLOW__LOGGING__LOGGING_LEVEL
#
logging_level = INFO
# Set the log level for individual named loggers.
#
# A very common convention in Python is to use the module name as the name of the logger from which log
# messages originate. This config option gives us the ability to set log levels for those loggers
# easily.
#
# The format of this variable is a series of ``<logger>=<level>`` pairs, separated by whitespace or
# commas.
#
# Each level is one of the possible values to ``logging_level``.
#
# The logger names are viewable in task logs (as the "source" attribute), or in server components by
# including ``%(name)s`` in your format string, or in the between ``[]`` after the message in the
# default format.
#
# Example: namespace_levels = sqlalchemy=INFO sqlalchemy.engine=DEBUG, botocor
#
# Variable: AIRFLOW__LOGGING__NAMESPACE_LEVELS
#
# namespace_levels =
# Logging level for celery. If not set, it uses the value of logging_level
#
# Supported values: ``CRITICAL``, ``ERROR``, ``WARNING``, ``INFO``, ``DEBUG``.
#
# Variable: AIRFLOW__LOGGING__CELERY_LOGGING_LEVEL
#
celery_logging_level =
# Logging level for Flask-appbuilder UI.
#
# Supported values: ``CRITICAL``, ``ERROR``, ``WARNING``, ``INFO``, ``DEBUG``.
#
# Variable: AIRFLOW__LOGGING__FAB_LOGGING_LEVEL
#
fab_logging_level = WARNING
# Enable JSON-structured logging for all output. When ``True``, every log line emitted by
# the process is a single-line JSON object (including HTTP access logs from the API server).
# Recommended for production / cloud-native deployments where logs are collected by a log
# aggregator.
#
# Example: json_logs = True
#
# Variable: AIRFLOW__LOGGING__JSON_LOGS
#
json_logs = False
# Logging level for uvicorn (API server and serve-logs).
#
# Supported values: ``CRITICAL``, ``ERROR``, ``WARNING``, ``INFO``, ``DEBUG``.
#
# Variable: AIRFLOW__LOGGING__UVICORN_LOGGING_LEVEL
#
uvicorn_logging_level = INFO
# 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
#
# Variable: AIRFLOW__LOGGING__LOGGING_CONFIG_CLASS
#
logging_config_class =
# Flag to enable/disable Colored logs in Console
# Colour the logs when the controlling terminal is a TTY.
#
# Variable: AIRFLOW__LOGGING__COLORED_CONSOLE_LOG
#
colored_console_log = True
# Format of Log line
#
# *Changed in 3.1.0*: This can now contain color escape sequences ``%(blue)s`` etc which will only
# result in colours if :ref:`config:logging__colored_console_log` is true.
#
# Example: log_format = [%%(asctime)s] {{%%(filename)s:%%(lineno)d}} %%(levelname)s - %%(message)s
#
# Variable: AIRFLOW__LOGGING__LOG_FORMAT
#
log_format =
# A comma separated list of information about the callsite (such as line number of filename etc) of
# logger calls to include in each message.
#
# See :class:`structlog.processors.CallsiteParameter` for the possible values.The values should be the
# constant names (``FUNC_NAME``) or the values (``func_name``)
#
# Including these in a log message adds a lot to the usability to the logs, but collecting these has a
# (tiny) cost -- if you are super concerned with eking out every last ounce of performance you could
# turn these off (by setting this value to an empty string)
#
# Variable: AIRFLOW__LOGGING__CALLSITE_PARAMETERS
#
callsite_parameters = filename,lineno
# Defines the format of log messages for simple logging configuration
#
# Variable: AIRFLOW__LOGGING__SIMPLE_LOG_FORMAT
#
simple_log_format = %%(asctime)s %%(levelname)s - %%(message)s
# Where to send dag parser logs. If "file", logs are sent to log files defined by child_process_log_directory.
#
# Variable: AIRFLOW__LOGGING__DAG_PROCESSOR_LOG_TARGET
#
dag_processor_log_target = file
# Format of Dag Processor Log line
#
# Variable: AIRFLOW__LOGGING__DAG_PROCESSOR_LOG_FORMAT
#
dag_processor_log_format = [%%(asctime)s] [SOURCE:DAG_PROCESSOR] {%%(filename)s:%%(lineno)d} %%(levelname)s - %%(message)s
# Determines the directory where logs for the child processes of the dag processor will be stored
#
# Variable: AIRFLOW__LOGGING__DAG_PROCESSOR_CHILD_PROCESS_LOG_DIRECTORY
#
# Determines the formatter class used by Airflow for structuring its log messages
# The default formatter class is timezone-aware, which means that timestamps attached to log entries
# will be adjusted to reflect the local timezone of the Airflow instance.
# Note: This setting does NOT affect component logs (scheduler, api-server, triggerer, etc.) since
# those use structlog directly. Use ``log_timestamp_format`` to control timestamps for those logs.
#
# Variable: AIRFLOW__LOGGING__LOG_FORMATTER_CLASS
#
log_formatter_class = airflow.utils.log.timezone_aware.TimezoneAware
# Timestamp format for component logs (scheduler, api-server, triggerer, etc.).
# Use ``iso`` for ISO 8601 format (default), or a Python strftime format string
# such as ``%Y-%m-%d %H:%M:%S``.
# Note: This setting only applies to component logs rendered via structlog.
# Task/DAG logs use ``log_format`` instead.
#
# Example: log_timestamp_format = %Y-%m-%d %H:%M:%S
#
# Variable: AIRFLOW__LOGGING__LOG_TIMESTAMP_FORMAT
#
log_timestamp_format = iso
# An import path to a function to add adaptations of each secret added with
# ``airflow.sdk.execution_time.secrets_masker.mask_secret`` to be masked in log messages.
# The given function is expected to require a single parameter: the secret to be adapted.
# It may return a single adaptation of the secret or an iterable of adaptations to each be
# masked as secrets. The original secret will be masked as well as any adaptations returned.
#
# Example: secret_mask_adapter = urllib.parse.quote
#
# Variable: AIRFLOW__LOGGING__SECRET_MASK_ADAPTER
#
secret_mask_adapter =
# The minimum length of a secret to be masked in log messages.
# Secrets shorter than this length will not be masked.
#
# Variable: AIRFLOW__LOGGING__MIN_LENGTH_MASKED_SECRET
#
min_length_masked_secret = 5
# Specify prefix pattern like mentioned below with stream handler ``TaskHandlerWithCustomFormatter``
#
# Example: task_log_prefix_template = {{ti.dag_id}}-{{ti.task_id}}-{{logical_date}}-{{ti.try_number}}
#
# Variable: AIRFLOW__LOGGING__TASK_LOG_PREFIX_TEMPLATE
#
task_log_prefix_template =
# Formatting for how airflow generates file names/paths for each task run.
#
# Variable: AIRFLOW__LOGGING__LOG_FILENAME_TEMPLATE
#
log_filename_template = dag_id={{ ti.dag_id }}/run_id={{ ti.run_id }}/task_id={{ ti.task_id }}/{%% if ti.map_index >= 0 %%}map_index={{ ti.map_index }}/{%% endif %%}attempt={{ try_number|default(ti.try_number) }}.log
# Name of handler to read task instance logs.
# Defaults to use ``task`` handler.
#
# Variable: AIRFLOW__LOGGING__TASK_LOG_READER
#
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 = fastapi,sqlalchemy
#
# Variable: AIRFLOW__LOGGING__EXTRA_LOGGER_NAMES
#
extra_logger_names =
# 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.
#
# Variable: AIRFLOW__LOGGING__WORKER_LOG_SERVER_PORT
#
worker_log_server_port = 8793
# Port to serve logs from for triggerer.
# See ``[logging] worker_log_server_port`` description for more info.
#
# Variable: AIRFLOW__LOGGING__TRIGGER_LOG_SERVER_PORT
#
trigger_log_server_port = 8794
# We must parse timestamps to interleave logs between trigger and task. To do so,
# we need to parse timestamps in log files. In case your log format is non-standard,
# you may provide import path to callable which takes a string log line and returns
# the timestamp (datetime.datetime compatible).
#
# Example: interleave_timestamp_parser = path.to.my_func
#
# Variable: AIRFLOW__LOGGING__INTERLEAVE_TIMESTAMP_PARSER
#
# interleave_timestamp_parser =
# Permissions in the form or of octal string as understood by chmod. The permissions are important
# when you use impersonation, when logs are written by a different user than airflow. The most secure
# way of configuring it in this case is to add both users to the same group and make it the default
# group of both users. Group-writeable logs are default in airflow, but you might decide that you are
# OK with having the logs other-writeable, in which case you should set it to ``0o777``. You might
# decide to add more security if you do not use impersonation and change it to ``0o755`` to make it
# only owner-writeable. You can also make it just readable only for owner by changing it to ``0o700``
# if all the access (read/write) for your logs happens from the same user.
#
# Example: file_task_handler_new_folder_permissions = 0o775
#
# Variable: AIRFLOW__LOGGING__FILE_TASK_HANDLER_NEW_FOLDER_PERMISSIONS
#
file_task_handler_new_folder_permissions = 0o775
# Permissions in the form or of octal string as understood by chmod. The permissions are important
# when you use impersonation, when logs are written by a different user than airflow. The most secure
# way of configuring it in this case is to add both users to the same group and make it the default
# group of both users. Group-writeable logs are default in airflow, but you might decide that you are
# OK with having the logs other-writeable, in which case you should set it to ``0o666``. You might
# decide to add more security if you do not use impersonation and change it to ``0o644`` to make it
# only owner-writeable. You can also make it just readable only for owner by changing it to ``0o600``
# if all the access (read/write) for your logs happens from the same user.
#
# Example: file_task_handler_new_file_permissions = 0o664
#
# Variable: AIRFLOW__LOGGING__FILE_TASK_HANDLER_NEW_FILE_PERMISSIONS
#
file_task_handler_new_file_permissions = 0o664
# By default Celery sends all logs into stderr.
# If enabled any previous logging handlers will get *removed*.
# With this option AirFlow will create new handlers
# and send low level logs like INFO and WARNING to stdout,
# while sending higher severity logs to stderr.
#
# Variable: AIRFLOW__LOGGING__CELERY_STDOUT_STDERR_SEPARATION
#
celery_stdout_stderr_separation = False
# A comma separated list of keywords related to errors whose presence should display the line in red
# color in UI
#
# Variable: AIRFLOW__LOGGING__COLOR_LOG_ERROR_KEYWORDS
#
color_log_error_keywords = error,exception
# A comma separated list of keywords related to warning whose presence should display the line in yellow
# color in UI
#
# Variable: AIRFLOW__LOGGING__COLOR_LOG_WARNING_KEYWORDS
#
color_log_warning_keywords = warn
[metrics]
# `StatsD <https://github.com/statsd/statsd>`__ integration settings.
# Configure an allow list (comma separated regex patterns to match) to send only certain metrics.
#
# Example: metrics_allow_list = "scheduler,executor,dagrun,pool,triggerer,celery" or "^scheduler,^executor,heartbeat|timeout"
#
# Variable: AIRFLOW__METRICS__METRICS_ALLOW_LIST
#
metrics_allow_list =
# Configure a block list (comma separated regex patterns to match) to block certain metrics
# from being emitted.
# If ``[metrics] metrics_allow_list`` and ``[metrics] metrics_block_list`` are both configured,
# ``[metrics] metrics_block_list`` is ignored.
#
# Example: metrics_block_list = "scheduler,executor,dagrun,pool,triggerer,celery" or "^scheduler,^executor,heartbeat|timeout"
#
# Variable: AIRFLOW__METRICS__METRICS_BLOCK_LIST
#