Remove dead code/constants from settings.py (#59822)

Author: jscheffl

airflow-core/docs/administration-and-deployment/dag-serialization.rst

@@ -74,15 +74,11 @@ Add the following settings in ``airflow.cfg``:
 
     # You can also update the following default configurations based on your needs
     min_serialized_dag_update_interval = 30
-    min_serialized_dag_fetch_interval = 10
     max_num_rendered_ti_fields_per_task = 30
     compress_serialized_dags = False
 
 *   ``min_serialized_dag_update_interval``: 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_fetch_interval``: This option controls how often the Serialized Dag will be re-fetched
-    from the DB when it is already loaded in the DagBag in the Webserver. Setting this higher will reduce
-    load on the DB, but at the expense of displaying a possibly stale cached version of the Dag.
 *   ``max_num_rendered_ti_fields_per_task``: This option controls the maximum number of Rendered Task Instance
     Fields (Template Fields) per task to store in the Database.
 *   ``compress_serialized_dags``: This option controls whether to compress the Serialized Dag to the Database.

airflow-core/src/airflow/config_templates/config.yml

@@ -367,14 +367,6 @@ core:
       type: boolean
       example: ~
       default: "False"
-    min_serialized_dag_fetch_interval:
-      description: |
-        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
-      version_added: 1.10.12
-      type: integer
-      example: ~
-      default: "10"
     max_num_rendered_ti_fields_per_task:
       description: |
         Maximum number of Rendered Task Instance Fields (Template Fields) per task to store

airflow-core/src/airflow/settings.py

@@ -109,16 +109,12 @@
 
 LOGGING_LEVEL = logging.INFO
 
-# the prefix to append to gunicorn worker processes after init
-GUNICORN_WORKER_READY_PREFIX = "[ready] "
-
 LOG_FORMAT = conf.get("logging", "log_format")
 SIMPLE_LOG_FORMAT = conf.get("logging", "simple_log_format")
 
 SQL_ALCHEMY_CONN: str | None = None
 SQL_ALCHEMY_CONN_ASYNC: str | None = None
 PLUGINS_FOLDER: str | None = None
-DONOT_MODIFY_HANDLERS: bool | None = None
 DAGS_FOLDER: str = os.path.expanduser(conf.get_mandatory_value("core", "DAGS_FOLDER"))
 
 AIO_LIBS_MAPPING = {"sqlite": "aiosqlite", "postgresql": "asyncpg", "mysql": "aiomysql"}
@@ -264,7 +260,6 @@ def configure_vars():
     global SQL_ALCHEMY_CONN_ASYNC
     global DAGS_FOLDER
     global PLUGINS_FOLDER
-    global DONOT_MODIFY_HANDLERS
 
     SQL_ALCHEMY_CONN = conf.get("database", "sql_alchemy_conn")
     if conf.has_option("database", "sql_alchemy_conn_async"):
@@ -276,13 +271,6 @@ def configure_vars():
 
     PLUGINS_FOLDER = conf.get("core", "plugins_folder", fallback=os.path.join(AIRFLOW_HOME, "plugins"))
 
-    # If donot_modify_handlers=True, we do not modify logging handlers in task_run command
-    # If the flag is set to False, we remove all handlers from the root logger
-    # and add all handlers from 'airflow.task' logger to the root Logger. This is done
-    # to get all the logs from the print & log statements in the DAG files before a task is run
-    # The handlers are restored after the task completes execution.
-    DONOT_MODIFY_HANDLERS = conf.getboolean("logging", "donot_modify_handlers", fallback=False)
-
 
 def _run_openlineage_runtime_check():
     """
@@ -340,10 +328,6 @@ def get_bind(
 
 
 AIRFLOW_PATH = os.path.dirname(os.path.dirname(__file__))
-AIRFLOW_TESTS_PATH = os.path.join(AIRFLOW_PATH, "tests")
-AIRFLOW_SETTINGS_PATH = os.path.join(AIRFLOW_PATH, "airflow", "settings.py")
-AIRFLOW_UTILS_SESSION_PATH = os.path.join(AIRFLOW_PATH, "airflow", "utils", "session.py")
-AIRFLOW_MODELS_BASEOPERATOR_PATH = os.path.join(AIRFLOW_PATH, "airflow", "models", "baseoperator.py")
 
 
 def _is_sqlite_db_path_relative(sqla_conn_str: str) -> bool:
@@ -753,9 +737,6 @@ def initialize():
 
 
 # Const stuff
-
-KILOBYTE = 1024
-MEGABYTE = KILOBYTE * KILOBYTE
 WEB_COLORS = {"LIGHTBLUE": "#4d9de0", "LIGHTORANGE": "#FF9933"}
 
 # Updating serialized DAG can not be faster than a minimum interval to reduce database
@@ -765,10 +746,6 @@ def initialize():
 # If set to True, serialized DAGs is compressed before writing to DB,
 COMPRESS_SERIALIZED_DAGS = conf.getboolean("core", "compress_serialized_dags", fallback=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 = conf.getint("core", "min_serialized_dag_fetch_interval", fallback=10)
-
 CAN_FORK = hasattr(os, "fork")
 
 EXECUTE_TASKS_NEW_PYTHON_INTERPRETER = not CAN_FORK or conf.getboolean(

airflow-core/tests/unit/jobs/test_scheduler_job.py

@@ -8112,12 +8112,11 @@ def test_execute_queries_count_with_harvested_dags(
                 {
                     ("scheduler", "use_job_schedule"): "True",
                     ("core", "load_examples"): "False",
-                    # For longer running tests under heavy load, the min_serialized_dag_fetch_interval
-                    # and min_serialized_dag_update_interval might kick-in and re-retrieve the record.
+                    # For longer running tests under heavy load, the min_serialized_dag_update_interval
+                    # might kick-in and re-retrieve the record.
                     # This will increase the count of serliazied_dag.py.get() count.
                     # That's why we keep the values high
                     ("core", "min_serialized_dag_update_interval"): "100",
-                    ("core", "min_serialized_dag_fetch_interval"): "100",
                 }
             ),
         ):
@@ -8204,12 +8203,11 @@ def test_process_dags_queries_count(
             conf_vars(
                 {
                     ("scheduler", "use_job_schedule"): "True",
-                    # For longer running tests under heavy load, the min_serialized_dag_fetch_interval
-                    # and min_serialized_dag_update_interval might kick-in and re-retrieve the record.
+                    # For longer running tests under heavy load, the min_serialized_dag_update_interval
+                    # might kick-in and re-retrieve the record.
                     # This will increase the count of serliazied_dag.py.get() count.
                     # That's why we keep the values high
                     ("core", "min_serialized_dag_update_interval"): "100",
-                    ("core", "min_serialized_dag_fetch_interval"): "100",
                 }
             ),
         ):