diff --git a/README.md b/README.md index dc1b531..7fa5cb2 100644 --- a/README.md +++ b/README.md @@ -78,6 +78,15 @@ PawMark is a platform for big data and AI. It is based on Apache Spark and Kuber +
+Server + +[![Build Docker - Server](https://github.com/xuwenyihust/PawMark/actions/workflows/build-docker-server.yml/badge.svg)](https://github.com/xuwenyihust/PawMark/actions/workflows/build-docker-server.yml) + +- [Dockerfile](./server/Dockerfile) + +
+
Spark diff --git a/docker/airflow/Dockerfile b/docker/airflow/Dockerfile index ad78e3e..8b32cd6 100644 --- a/docker/airflow/Dockerfile +++ b/docker/airflow/Dockerfile @@ -18,3 +18,6 @@ RUN python3 -m ipykernel install --user --name python3 --display-name "Python 3" # Set JAVA_HOME environment variable ENV JAVA_HOME /usr/lib/jvm/java-17-openjdk-amd64 +COPY webserver_config.py /opt/airflow/webserver_config.py +COPY airflow.cfg /opt/airflow/airflow.cfg + diff --git a/docker/airflow/airflow.cfg b/docker/airflow/airflow.cfg new file mode 100644 index 0000000..d36de39 --- /dev/null +++ b/docker/airflow/airflow.cfg @@ -0,0 +1,3016 @@ +[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 +# +dags_folder = /opt/airflow/dags + +# 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() - see 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 +# with argument as: `(file_path: str, zip_file: zipfile.ZipFile | None = None)` +# return True if it has dags otherwise False +# If this is not provided, Airflow uses its own heuristic rules. +# +# 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 timezone string (e.g. Europe/Amsterdam) +# +# Variable: AIRFLOW__CORE__DEFAULT_TIMEZONE +# +default_timezone = utc + +# The executor class that airflow should use. Choices include +# ``SequentialExecutor``, ``LocalExecutor``, ``CeleryExecutor``, +# ``KubernetesExecutor``, ``CeleryKubernetesExecutor``, ``LocalKubernetesExecutor`` or the +# full import path to the class when using a custom executor. +# +# Variable: AIRFLOW__CORE__EXECUTOR +# +executor = SequentialExecutor + +# The auth manager class that airflow should use. Full import path to the auth manager class. +# +# Variable: AIRFLOW__CORE__AUTH_MANAGER +# +auth_manager = airflow.providers.fab.auth_manager.fab_auth_manager.FabAuthManager + +# 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. +# +# Variable: AIRFLOW__CORE__PARALLELISM +# +parallelism = 32 + +# The maximum number of task instances allowed to run concurrently in each DAG. To calculate +# the number of tasks that is running concurrently for a DAG, add up the number of running +# tasks for all DAG runs of the DAG. This is configurable at the DAG level with ``max_active_tasks``, +# which is defaulted as ``max_active_tasks_per_dag``. +# +# An example scenario when this would be useful is when you want to stop a new dag 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 ``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 ``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 + +# The name of the method used in order to start Python processes via the multiprocessing module. +# This corresponds directly with the options available in the Python docs: +# https://docs.python.org/3/library/multiprocessing.html#multiprocessing.set_start_method. +# Must be one of the values returned by: +# https://docs.python.org/3/library/multiprocessing.html#multiprocessing.get_all_start_methods. +# +# Example: mp_start_method = fork +# +# Variable: AIRFLOW__CORE__MP_START_METHOD +# +# mp_start_method = + +# 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 +# +# Variable: AIRFLOW__CORE__LOAD_EXAMPLES +# +load_examples = True + +# Path to the folder containing Airflow plugins +# +# Variable: AIRFLOW__CORE__PLUGINS_FOLDER +# +plugins_folder = /opt/airflow/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) +# +# 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 = + +# Whether to disable pickling dags +# +# Variable: AIRFLOW__CORE__DONOT_PICKLE +# +donot_pickle = True + +# 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 + +# How long before timing out a DagFileProcessor, which processes a dag file +# +# Variable: AIRFLOW__CORE__DAG_FILE_PROCESSOR_TIMEOUT +# +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. +# +# Variable: AIRFLOW__CORE__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 +# +# 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 + +# Whether to enable pickling for xcom (note that this is insecure and allows for +# RCE exploits). +# +# Variable: AIRFLOW__CORE__ENABLE_XCOM_PICKLING +# +enable_xcom_pickling = False + +# What classes can be imported during deserialization. This is a multi line value. +# The individual items will be parsed as a pattern to a glob function. +# Python built-in classes (like dict) are always allowed. +# +# Variable: AIRFLOW__CORE__ALLOWED_DESERIALIZATION_CLASSES +# +allowed_deserialization_classes = airflow.* + +# What classes can be imported during deserialization. This is a multi line value. +# The individual items will be parsed as regexp patterns. +# This is a secondary option to ``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" files in the DAG directories. Valid values are +# ``regexp`` or ``glob``. +# +# Variable: AIRFLOW__CORE__DAG_IGNORE_FILE_SYNTAX +# +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. +# +# 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 + +# 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 + +# 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 +# +# Variable: AIRFLOW__CORE__MIN_SERIALIZED_DAG_FETCH_INTERVAL +# +min_serialized_dag_fetch_interval = 10 + +# 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. +# +# Variable: AIRFLOW__CORE__MAX_NUM_RENDERED_TI_FIELDS_PER_TASK +# +max_num_rendered_ti_fields_per_task = 30 + +# On each dagrun check against defined SLAs +# +# Variable: AIRFLOW__CORE__CHECK_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 +# +# Variable: AIRFLOW__CORE__XCOM_BACKEND +# +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. +# +# 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 +# +# (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 dataset manager. +# +# Example: dataset_manager_class = airflow.datasets.manager.DatasetManager +# +# Variable: AIRFLOW__CORE__DATASET_MANAGER_CLASS +# +# dataset_manager_class = + +# Kwargs to supply to dataset manager. +# +# Example: dataset_manager_kwargs = {"some_param": "some_value"} +# +# Variable: AIRFLOW__CORE__DATASET_MANAGER_KWARGS +# +# dataset_manager_kwargs = + +# (experimental) Whether components should use Airflow Internal API for DB connectivity. +# +# Variable: AIRFLOW__CORE__DATABASE_ACCESS_ISOLATION +# +database_access_isolation = False + +# (experimental) Airflow Internal API url. Only used if [core] database_access_isolation is True. +# +# Example: internal_api_url = http://localhost:8080 +# +# Variable: AIRFLOW__CORE__INTERNAL_API_URL +# +# internal_api_url = + +# 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. For more information on capabilities of users, see the documentation: +# https://airflow.apache.org/docs/apache-airflow/stable/security/security_model.html#capabilities-of-authenticated-ui-users +# +# Variable: AIRFLOW__CORE__TEST_CONNECTION +# +test_connection = Disabled + +# 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 + +[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. +# More information here: +# http://airflow.apache.org/docs/apache-airflow/stable/howto/set-up-database.html#database-uri +# +# Variable: AIRFLOW__DATABASE__SQL_ALCHEMY_CONN +# +sql_alchemy_conn = sqlite:////opt/airflow/airflow.db + +# 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 https://github.com/apache/airflow/pull/17603#issuecomment-901121618). +# +# 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". +# More information here: +# https://docs.sqlalchemy.org/en/14/core/pooling.html#disconnect-handling-pessimistic +# +# 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 connection see +# 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 +# +# Example: sql_alchemy_connect_args = airflow_local_settings.connect_args +# +# Variable: AIRFLOW__DATABASE__SQL_ALCHEMY_CONNECT_ARGS +# +# sql_alchemy_connect_args = + +# Whether to load the default connections that ship with Airflow when ``airflow db init`` is called. +# It's good to get started, but you probably want to set this to ``False`` in a production environment. +# +# Variable: AIRFLOW__DATABASE__LOAD_DEFAULT_CONNECTIONS +# +load_default_connections = True + +# 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 + +[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 dag_processor_manager_log_location and +# child_process_log_directory settings as well. +# +# Variable: AIRFLOW__LOGGING__BASE_LOG_FOLDER +# +base_log_folder = /opt/airflow/logs + +# 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 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 +# `__ 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 __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. +# +# Supported values: ``CRITICAL``, ``ERROR``, ``WARNING``, ``INFO``, ``DEBUG``. +# +# Variable: AIRFLOW__LOGGING__LOGGING_LEVEL +# +logging_level = INFO + +# 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 + +# 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 + +# Log format for when Colored logs is enabled +# +# Variable: AIRFLOW__LOGGING__COLORED_LOG_FORMAT +# +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 + +# Specifies the class utilized by Airflow to implement colored logging +# +# Variable: AIRFLOW__LOGGING__COLORED_FORMATTER_CLASS +# +colored_formatter_class = airflow.utils.log.colored_log.CustomTTYColoredFormatter + +# Format of Log line +# +# Variable: AIRFLOW__LOGGING__LOG_FORMAT +# +log_format = [%%(asctime)s] {%%(filename)s:%%(lineno)d} %%(levelname)s - %%(message)s + +# 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 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 +# +# Variable: AIRFLOW__LOGGING__LOG_FORMATTER_CLASS +# +log_formatter_class = airflow.utils.log.timezone_aware.TimezoneAware + +# An import path to a function to add adaptations of each secret added with +# `airflow.utils.log.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 = + +# 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} +# +# 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 }}.log + +# Formatting for how airflow generates file names for log +# +# Variable: AIRFLOW__LOGGING__LOG_PROCESSOR_FILENAME_TEMPLATE +# +log_processor_filename_template = {{ filename }}.log + +# Full path of dag_processor_manager logfile. +# +# Variable: AIRFLOW__LOGGING__DAG_PROCESSOR_MANAGER_LOG_LOCATION +# +dag_processor_manager_log_location = /opt/airflow/logs/dag_processor_manager/dag_processor_manager.log + +# Whether DAG processor manager will write logs to stdout +# +# Variable: AIRFLOW__LOGGING__DAG_PROCESSOR_MANAGER_LOG_STDOUT +# +dag_processor_manager_log_stdout = False + +# 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 = connexion,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 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 + +# If enabled, Airflow may ship messages to task logs from outside the task run context, e.g. from +# the scheduler, executor, or callback execution context. This can help in circumstances such as +# when there's something blocking the execution of the task and ordinarily there may be no task +# logs at all. +# This is set to True by default. If you encounter issues with this feature +# (e.g. scheduler performance issues) it can be disabled. +# +# Variable: AIRFLOW__LOGGING__ENABLE_TASK_CONTEXT_LOGGER +# +enable_task_context_logger = True + +[metrics] +# StatsD (https://github.com/etsy/statsd) integration settings. + +# If true, metrics_allow_list and metrics_block_list will use regex pattern matching +# anywhere within the metric name instead of only prefix matching at the start of the name. +# +# Variable: AIRFLOW__METRICS__METRICS_USE_PATTERN_MATCH +# +metrics_use_pattern_match = False + +# Configure an allow list (comma separated string) to send only certain metrics. +# If metrics_use_pattern_match is false, match only the exact metric name prefix. +# If metrics_use_pattern_match is true, provide regex patterns to match. +# +# Example: metrics_allow_list = "scheduler,executor,dagrun" or "^scheduler,^executor,heartbeat|timeout" +# +# Variable: AIRFLOW__METRICS__METRICS_ALLOW_LIST +# +metrics_allow_list = + +# Configure a block list (comma separated string) to block certain metrics from being emitted. +# If metrics_allow_list and metrics_block_list are both configured, metrics_block_list is ignored. +# If metrics_use_pattern_match is false, match only the exact metric name prefix. +# If metrics_use_pattern_match is true, provide regex patterns to match. +# +# Example: metrics_block_list = "scheduler,executor,dagrun" or "^scheduler,^executor,heartbeat|timeout" +# +# Variable: AIRFLOW__METRICS__METRICS_BLOCK_LIST +# +metrics_block_list = + +# Enables sending metrics to StatsD. +# +# Variable: AIRFLOW__METRICS__STATSD_ON +# +statsd_on = False + +# Specifies the host address where the StatsD daemon (or server) is running +# +# Variable: AIRFLOW__METRICS__STATSD_HOST +# +statsd_host = localhost + +# Specifies the port on which the StatsD daemon (or server) is listening to +# +# Variable: AIRFLOW__METRICS__STATSD_PORT +# +statsd_port = 8125 + +# Defines the namespace for all metrics sent from Airflow to StatsD +# +# Variable: AIRFLOW__METRICS__STATSD_PREFIX +# +statsd_prefix = airflow + +# A function that validate the StatsD stat name, apply changes to the stat name if necessary and return +# the transformed stat name. +# +# The function should have the following signature: +# def func_name(stat_name: str) -> str: +# +# Variable: AIRFLOW__METRICS__STAT_NAME_HANDLER +# +stat_name_handler = + +# To enable datadog integration to send airflow metrics. +# +# Variable: AIRFLOW__METRICS__STATSD_DATADOG_ENABLED +# +statsd_datadog_enabled = False + +# List of datadog tags attached to all metrics(e.g: key1:value1,key2:value2) +# +# Variable: AIRFLOW__METRICS__STATSD_DATADOG_TAGS +# +statsd_datadog_tags = + +# Set to False to disable metadata tags for some of the emitted metrics +# +# Variable: AIRFLOW__METRICS__STATSD_DATADOG_METRICS_TAGS +# +statsd_datadog_metrics_tags = True + +# If you want to utilise your own custom StatsD client set the relevant +# module path below. +# Note: The module path must exist on your PYTHONPATH for Airflow to pick it up +# +# Variable: AIRFLOW__METRICS__STATSD_CUSTOM_CLIENT_PATH +# +# statsd_custom_client_path = + +# If you want to avoid sending all the available metrics tags to StatsD, +# you can configure a block list of prefixes (comma separated) to filter out metric tags +# that start with the elements of the list (e.g: "job_id,run_id") +# +# Example: statsd_disabled_tags = job_id,run_id,dag_id,task_id +# +# Variable: AIRFLOW__METRICS__STATSD_DISABLED_TAGS +# +statsd_disabled_tags = job_id,run_id + +# To enable sending Airflow metrics with StatsD-Influxdb tagging convention. +# +# Variable: AIRFLOW__METRICS__STATSD_INFLUXDB_ENABLED +# +statsd_influxdb_enabled = False + +# Enables sending metrics to OpenTelemetry. +# +# Variable: AIRFLOW__METRICS__OTEL_ON +# +otel_on = False + +# Specifies the hostname or IP address of the OpenTelemetry Collector to which Airflow sends +# metrics and traces. +# +# Variable: AIRFLOW__METRICS__OTEL_HOST +# +otel_host = localhost + +# Specifies the port of the OpenTelemetry Collector that is listening to. +# +# Variable: AIRFLOW__METRICS__OTEL_PORT +# +otel_port = 8889 + +# The prefix for the Airflow metrics. +# +# Variable: AIRFLOW__METRICS__OTEL_PREFIX +# +otel_prefix = airflow + +# Defines the interval, in milliseconds, at which Airflow sends batches of metrics and traces +# to the configured OpenTelemetry Collector. +# +# Variable: AIRFLOW__METRICS__OTEL_INTERVAL_MILLISECONDS +# +otel_interval_milliseconds = 60000 + +# If True, all metrics are also emitted to the console. Defaults to False. +# +# Variable: AIRFLOW__METRICS__OTEL_DEBUGGING_ON +# +otel_debugging_on = False + +# If True, SSL will be enabled. Defaults to False. +# To establish an HTTPS connection to the OpenTelemetry collector, +# you need to configure the SSL certificate and key within the OpenTelemetry collector's +# config.yml file. +# +# Variable: AIRFLOW__METRICS__OTEL_SSL_ACTIVE +# +otel_ssl_active = False + +[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 +# +# Variable: AIRFLOW__SECRETS__BACKEND +# +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"}`` +# +# Variable: AIRFLOW__SECRETS__BACKEND_KWARGS +# +backend_kwargs = + +# .. note:: |experimental| +# +# Enables local caching of Variables, when parsing DAGs only. +# Using this option can make dag parsing faster if Variables are used in top level code, at the expense +# of longer propagation time for changes. +# Please note that this cache concerns only the DAG parsing step. There is no caching in place when DAG +# tasks are run. +# +# Variable: AIRFLOW__SECRETS__USE_CACHE +# +use_cache = False + +# .. note:: |experimental| +# +# When the cache is enabled, this is the duration for which we consider an entry in the cache to be +# valid. Entries are refreshed if they are older than this many seconds. +# It means that when the cache is enabled, this is the maximum amount of time you need to wait to see a +# Variable change take effect. +# +# Variable: AIRFLOW__SECRETS__CACHE_TTL_SECONDS +# +cache_ttl_seconds = 900 + +[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 +# +# Variable: AIRFLOW__CLI__API_CLIENT +# +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/...`` +# +# Variable: AIRFLOW__CLI__ENDPOINT_URL +# +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. +# +# Variable: AIRFLOW__DEBUG__FAIL_FAST +# +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 `__ is +# deprecated since version 2.0. Please consider using +# `the Stable REST API `__. +# For more information on migration, see +# `RELEASE_NOTES.rst `_ +# +# Variable: AIRFLOW__API__ENABLE_EXPERIMENTAL_API +# +enable_experimental_api = False + +# Comma separated list of auth backends to authenticate users of the API. See +# https://airflow.apache.org/docs/apache-airflow/stable/security/api.html for possible values. +# ("airflow.api.auth.backend.default" allows all requests for historic reasons) +# +# Variable: AIRFLOW__API__AUTH_BACKENDS +# +auth_backends = airflow.api.auth.backend.session + +# Used to set the maximum page limit for API requests. If limit passed as param +# is greater than maximum page limit, it will be ignored and maximum page limit value +# will be set as the limit +# +# Variable: AIRFLOW__API__MAXIMUM_PAGE_LIMIT +# +maximum_page_limit = 100 + +# Used to set the default page limit when limit param is zero or not provided in API +# requests. Otherwise if positive integer is passed in the API requests as limit, the +# smallest number of user given limit or maximum page limit is taken as limit. +# +# Variable: AIRFLOW__API__FALLBACK_PAGE_LIMIT +# +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 +# +# Variable: AIRFLOW__API__GOOGLE_OAUTH2_AUDIENCE +# +google_oauth2_audience = + +# Path to Google Cloud Service Account key file (JSON). If omitted, authorization based on +# `the Application Default Credentials +# `__ will +# be used. +# +# Example: google_key_path = /files/service-account-json +# +# Variable: AIRFLOW__API__GOOGLE_KEY_PATH +# +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. +# +# Variable: AIRFLOW__API__ACCESS_CONTROL_ALLOW_HEADERS +# +access_control_allow_headers = + +# Specifies the method or methods allowed when accessing the resource. +# +# Variable: AIRFLOW__API__ACCESS_CONTROL_ALLOW_METHODS +# +access_control_allow_methods = + +# Indicates whether the response can be shared with requesting code from the given origins. +# Separate URLs with space. +# +# Variable: AIRFLOW__API__ACCESS_CONTROL_ALLOW_ORIGINS +# +access_control_allow_origins = + +# Indicates whether the *xcomEntries* endpoint supports the *deserialize* +# flag. If set to False, setting this flag in a request would result in a +# 400 Bad Request error. +# +# Variable: AIRFLOW__API__ENABLE_XCOM_DESERIALIZE_SUPPORT +# +enable_xcom_deserialize_support = False + +[lineage] +# what lineage backend to use +# +# Variable: AIRFLOW__LINEAGE__BACKEND +# +backend = + +[operators] +# The default owner assigned to each new operator, unless +# provided explicitly or passed via ``default_args`` +# +# Variable: AIRFLOW__OPERATORS__DEFAULT_OWNER +# +default_owner = airflow + +# The default value of attribute "deferrable" in operators and sensors. +# +# Variable: AIRFLOW__OPERATORS__DEFAULT_DEFERRABLE +# +default_deferrable = false + +# Indicates the default number of CPU units allocated to each operator when no specific CPU request +# is specified in the operator's configuration +# +# Variable: AIRFLOW__OPERATORS__DEFAULT_CPUS +# +default_cpus = 1 + +# Indicates the default number of RAM allocated to each operator when no specific RAM request +# is specified in the operator's configuration +# +# Variable: AIRFLOW__OPERATORS__DEFAULT_RAM +# +default_ram = 512 + +# Indicates the default number of disk storage allocated to each operator when no specific disk request +# is specified in the operator's configuration +# +# Variable: AIRFLOW__OPERATORS__DEFAULT_DISK +# +default_disk = 512 + +# Indicates the default number of GPUs allocated to each operator when no specific GPUs request +# is specified in the operator's configuration +# +# Variable: AIRFLOW__OPERATORS__DEFAULT_GPUS +# +default_gpus = 0 + +# Default queue that tasks get assigned to and that worker listen on. +# +# Variable: AIRFLOW__OPERATORS__DEFAULT_QUEUE +# +default_queue = default + +# 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. +# +# Variable: AIRFLOW__OPERATORS__ALLOW_ILLEGAL_ARGUMENTS +# +allow_illegal_arguments = False + +[webserver] +rbac = False +authenticate = False + +# The message displayed when a user attempts to execute actions beyond their authorised privileges. +# +# Variable: AIRFLOW__WEBSERVER__ACCESS_DENIED_MESSAGE +# +access_denied_message = Access is Denied + +# Path of webserver config file used for configuring the webserver parameters +# +# Variable: AIRFLOW__WEBSERVER__CONFIG_FILE +# +config_file = /opt/airflow/webserver_config.py + +# The base url of your website: Airflow cannot guess what domain or CNAME you are using. +# This is used to create links in the Log Url column in the Browse - Task Instances menu, +# as well as in any automated emails sent by Airflow that contain links to your webserver. +# +# Variable: AIRFLOW__WEBSERVER__BASE_URL +# +base_url = http://localhost:8080 + +# 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 +# +# Variable: AIRFLOW__WEBSERVER__DEFAULT_UI_TIMEZONE +# +default_ui_timezone = UTC + +# The ip specified when starting the web server +# +# Variable: AIRFLOW__WEBSERVER__WEB_SERVER_HOST +# +web_server_host = 0.0.0.0 + +# The port on which to run the web server +# +# Variable: AIRFLOW__WEBSERVER__WEB_SERVER_PORT +# +web_server_port = 8080 + +# 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. +# +# Variable: AIRFLOW__WEBSERVER__WEB_SERVER_SSL_CERT +# +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. +# +# Variable: AIRFLOW__WEBSERVER__WEB_SERVER_SSL_KEY +# +web_server_ssl_key = + +# The type of backend used to store web session data, can be `database` or `securecookie`. For the +# `database` backend, sessions are store in the database (in `session` table) and they can be +# managed there (for example when you reset password of the user, all sessions for that user are +# deleted). For the `securecookie` backend, sessions are stored in encrypted cookies on the client +# side. The `securecookie` mechanism is 'lighter' than database backend, but sessions are not deleted +# when you reset password of the user, which means that other than waiting for expiry time, the only +# way to invalidate all sessions for a user is to change secret_key and restart webserver (which +# also invalidates and logs out all other user's sessions). +# +# When you are using `database` backend, make sure to keep your database session table small +# by periodically running `airflow db clean --table session` command, especially if you have +# automated API calls that will create a new session for each call rather than reuse the sessions +# stored in browser cookies. +# +# Example: session_backend = securecookie +# +# Variable: AIRFLOW__WEBSERVER__SESSION_BACKEND +# +session_backend = database + +# Number of seconds the webserver waits before killing gunicorn master that doesn't respond +# +# Variable: AIRFLOW__WEBSERVER__WEB_SERVER_MASTER_TIMEOUT +# +web_server_master_timeout = 120 + +# Number of seconds the gunicorn webserver waits before timing out on a worker +# +# Variable: AIRFLOW__WEBSERVER__WEB_SERVER_WORKER_TIMEOUT +# +web_server_worker_timeout = 120 + +# 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. +# +# Variable: AIRFLOW__WEBSERVER__WORKER_REFRESH_BATCH_SIZE +# +worker_refresh_batch_size = 1 + +# Number of seconds to wait before refreshing a batch of workers. +# +# Variable: AIRFLOW__WEBSERVER__WORKER_REFRESH_INTERVAL +# +worker_refresh_interval = 6000 + +# If set to True, Airflow will track files in plugins_folder directory. When it detects changes, +# then reload the gunicorn. If set to True, gunicorn starts without preloading, which is slower, uses +# more memory, and may cause race conditions. Avoid setting this to True in production. +# +# Variable: AIRFLOW__WEBSERVER__RELOAD_ON_PLUGIN_CHANGE +# +reload_on_plugin_change = False + +# Secret key used to run your flask app. It should be as random as possible. However, when running +# more than 1 instances of webserver, make sure all of them use the same ``secret_key`` otherwise +# one of them will error with "CSRF session token is missing". +# The webserver key is also used to authorize requests to Celery workers when logs are retrieved. +# The token generated using the secret key has a short expiry time though - make sure that time on +# ALL the machines that you run airflow components on is synchronized (for example using ntpd) +# otherwise you might get "forbidden" errors when the logs are accessed. +# +# Variable: AIRFLOW__WEBSERVER__SECRET_KEY +# +secret_key = 4gEP/cauV3wbhzcaNpS3gw== + +# Number of workers to run the Gunicorn web server +# +# Variable: AIRFLOW__WEBSERVER__WORKERS +# +workers = 4 + +# The worker class gunicorn should use. Choices include +# sync (default), eventlet, gevent. Note when using gevent you might also want to set the +# "_AIRFLOW_PATCH_GEVENT" environment variable to "1" to make sure gevent patching is done as +# early as possible. +# +# Variable: AIRFLOW__WEBSERVER__WORKER_CLASS +# +worker_class = sync + +# Log files for the gunicorn webserver. '-' means log to stderr. +# +# Variable: AIRFLOW__WEBSERVER__ACCESS_LOGFILE +# +access_logfile = - + +# Log files for the gunicorn webserver. '-' means log to stderr. +# +# Variable: AIRFLOW__WEBSERVER__ERROR_LOGFILE +# +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 +# +# Variable: AIRFLOW__WEBSERVER__ACCESS_LOGFORMAT +# +access_logformat = + +# Expose the configuration file in the web server. Set to "non-sensitive-only" to show all values +# except those that have security implications. "True" shows all values. "False" hides the +# configuration completely. +# +# Variable: AIRFLOW__WEBSERVER__EXPOSE_CONFIG +# +expose_config = False + +# Expose hostname in the web server +# +# Variable: AIRFLOW__WEBSERVER__EXPOSE_HOSTNAME +# +expose_hostname = False + +# Expose stacktrace in the web server +# +# Variable: AIRFLOW__WEBSERVER__EXPOSE_STACKTRACE +# +expose_stacktrace = False + +# Default DAG view. Valid values are: ``grid``, ``graph``, ``duration``, ``gantt``, ``landing_times`` +# +# Variable: AIRFLOW__WEBSERVER__DAG_DEFAULT_VIEW +# +dag_default_view = grid + +# Default DAG orientation. Valid values are: +# ``LR`` (Left->Right), ``TB`` (Top->Bottom), ``RL`` (Right->Left), ``BT`` (Bottom->Top) +# +# Variable: AIRFLOW__WEBSERVER__DAG_ORIENTATION +# +dag_orientation = LR + +# Sorting order in grid view. Valid values are: ``topological``, ``hierarchical_alphabetical`` +# +# Variable: AIRFLOW__WEBSERVER__GRID_VIEW_SORTING_ORDER +# +grid_view_sorting_order = topological + +# The amount of time (in secs) webserver will wait for initial handshake +# while fetching logs from other worker machine +# +# Variable: AIRFLOW__WEBSERVER__LOG_FETCH_TIMEOUT_SEC +# +log_fetch_timeout_sec = 5 + +# Time interval (in secs) to wait before next log fetching. +# +# Variable: AIRFLOW__WEBSERVER__LOG_FETCH_DELAY_SEC +# +log_fetch_delay_sec = 2 + +# Distance away from page bottom to enable auto tailing. +# +# Variable: AIRFLOW__WEBSERVER__LOG_AUTO_TAILING_OFFSET +# +log_auto_tailing_offset = 30 + +# Animation speed for auto tailing log display. +# +# Variable: AIRFLOW__WEBSERVER__LOG_ANIMATION_SPEED +# +log_animation_speed = 1000 + +# By default, the webserver shows paused DAGs. Flip this to hide paused +# DAGs by default +# +# Variable: AIRFLOW__WEBSERVER__HIDE_PAUSED_DAGS_BY_DEFAULT +# +hide_paused_dags_by_default = False + +# Consistent page size across all listing views in the UI +# +# Variable: AIRFLOW__WEBSERVER__PAGE_SIZE +# +page_size = 100 + +# Define the color of navigation bar +# +# Variable: AIRFLOW__WEBSERVER__NAVBAR_COLOR +# +navbar_color = #fff + +# Define the color of text in the navigation bar +# +# Variable: AIRFLOW__WEBSERVER__NAVBAR_TEXT_COLOR +# +navbar_text_color = #51504f + +# Define the color of navigation bar links when hovered +# +# Variable: AIRFLOW__WEBSERVER__NAVBAR_HOVER_COLOR +# +navbar_hover_color = #eee + +# Define the color of text in the navigation bar when hovered +# +# Variable: AIRFLOW__WEBSERVER__NAVBAR_TEXT_HOVER_COLOR +# +navbar_text_hover_color = #51504f + +# Define the color of the logo text +# +# Variable: AIRFLOW__WEBSERVER__NAVBAR_LOGO_TEXT_COLOR +# +navbar_logo_text_color = #51504f + +# Default dagrun to show in UI +# +# Variable: AIRFLOW__WEBSERVER__DEFAULT_DAG_RUN_DISPLAY_NUMBER +# +default_dag_run_display_number = 25 + +# Enable werkzeug ``ProxyFix`` middleware for reverse proxy +# +# Variable: AIRFLOW__WEBSERVER__ENABLE_PROXY_FIX +# +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/ +# +# Variable: AIRFLOW__WEBSERVER__PROXY_FIX_X_FOR +# +proxy_fix_x_for = 1 + +# Number of values to trust for ``X-Forwarded-Proto`` +# +# Variable: AIRFLOW__WEBSERVER__PROXY_FIX_X_PROTO +# +proxy_fix_x_proto = 1 + +# Number of values to trust for ``X-Forwarded-Host`` +# +# Variable: AIRFLOW__WEBSERVER__PROXY_FIX_X_HOST +# +proxy_fix_x_host = 1 + +# Number of values to trust for ``X-Forwarded-Port`` +# +# Variable: AIRFLOW__WEBSERVER__PROXY_FIX_X_PORT +# +proxy_fix_x_port = 1 + +# Number of values to trust for ``X-Forwarded-Prefix`` +# +# Variable: AIRFLOW__WEBSERVER__PROXY_FIX_X_PREFIX +# +proxy_fix_x_prefix = 1 + +# Set secure flag on session cookie +# +# Variable: AIRFLOW__WEBSERVER__COOKIE_SECURE +# +cookie_secure = False + +# Set samesite policy on session cookie +# +# Variable: AIRFLOW__WEBSERVER__COOKIE_SAMESITE +# +cookie_samesite = Lax + +# Default setting for wrap toggle on DAG code and TI log views. +# +# Variable: AIRFLOW__WEBSERVER__DEFAULT_WRAP +# +default_wrap = False + +# Allow the UI to be rendered in a frame +# +# Variable: AIRFLOW__WEBSERVER__X_FRAME_ENABLED +# +x_frame_enabled = True + +# Send anonymous user activity to your analytics tool +# choose from google_analytics, segment, metarouter, or matomo +# +# Variable: AIRFLOW__WEBSERVER__ANALYTICS_TOOL +# +# analytics_tool = + +# Unique ID of your account in the analytics tool +# +# Variable: AIRFLOW__WEBSERVER__ANALYTICS_ID +# +# analytics_id = + +# Your instances url, only applicable to Matomo. +# +# Example: analytics_url = https://your.matomo.instance.com/ +# +# Variable: AIRFLOW__WEBSERVER__ANALYTICS_URL +# +# analytics_url = + +# 'Recent Tasks' stats will show for old DagRuns if set +# +# Variable: AIRFLOW__WEBSERVER__SHOW_RECENT_STATS_FOR_COMPLETED_RUNS +# +show_recent_stats_for_completed_runs = True + +# Update FAB permissions and sync security manager roles +# on webserver startup +# +# Variable: AIRFLOW__WEBSERVER__UPDATE_FAB_PERMS +# +update_fab_perms = True + +# The UI cookie lifetime in minutes. User will be logged out from UI after +# ``session_lifetime_minutes`` of non-activity +# +# Variable: AIRFLOW__WEBSERVER__SESSION_LIFETIME_MINUTES +# +session_lifetime_minutes = 43200 + +# Sets a custom page title for the DAGs overview page and site title for all pages +# +# Variable: AIRFLOW__WEBSERVER__INSTANCE_NAME +# +# instance_name = + +# Whether the custom page title for the DAGs overview page contains any Markup language +# +# Variable: AIRFLOW__WEBSERVER__INSTANCE_NAME_HAS_MARKUP +# +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 +# +# Variable: AIRFLOW__WEBSERVER__AUTO_REFRESH_INTERVAL +# +auto_refresh_interval = 3 + +# Boolean for displaying warning for publicly viewable deployment +# +# Variable: AIRFLOW__WEBSERVER__WARN_DEPLOYMENT_EXPOSURE +# +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. +# +# Example: audit_view_excluded_events = cli_task_run,running,success +# +# Variable: AIRFLOW__WEBSERVER__AUDIT_VIEW_EXCLUDED_EVENTS +# +# audit_view_excluded_events = + +# 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 +# +# Variable: AIRFLOW__WEBSERVER__AUDIT_VIEW_INCLUDED_EVENTS +# +# audit_view_included_events = + +# Boolean for running SwaggerUI in the webserver. +# +# Variable: AIRFLOW__WEBSERVER__ENABLE_SWAGGER_UI +# +enable_swagger_ui = True + +# Boolean for running Internal API in the webserver. +# +# Variable: AIRFLOW__WEBSERVER__RUN_INTERNAL_API +# +run_internal_api = False + +# Boolean for enabling rate limiting on authentication endpoints. +# +# Variable: AIRFLOW__WEBSERVER__AUTH_RATE_LIMITED +# +auth_rate_limited = True + +# Rate limit for authentication endpoints. +# +# Variable: AIRFLOW__WEBSERVER__AUTH_RATE_LIMIT +# +auth_rate_limit = 5 per 40 second + +# The caching algorithm used by the webserver. Must be a valid hashlib function name. +# +# Example: caching_hash_method = sha256 +# +# Variable: AIRFLOW__WEBSERVER__CACHING_HASH_METHOD +# +caching_hash_method = md5 + +# Behavior of the trigger DAG run button for DAGs without params. False to skip and trigger +# without displaying a form to add a dag_run.conf, True to always display the form. +# The form is displayed always if parameters are defined. +# +# Variable: AIRFLOW__WEBSERVER__SHOW_TRIGGER_FORM_IF_NO_PARAMS +# +show_trigger_form_if_no_params = False + +# Number of recent DAG run configurations in the selector on the trigger web form. +# +# Example: num_recent_configurations_for_trigger = 10 +# +# Variable: AIRFLOW__WEBSERVER__NUM_RECENT_CONFIGURATIONS_FOR_TRIGGER +# +num_recent_configurations_for_trigger = 5 + +# A DAG author is able to provide any raw HTML into ``doc_md`` or params description in +# ``description_md`` for text formatting. This is including potentially unsafe javascript. +# Displaying the DAG or trigger form in web UI provides the DAG author the potential to +# inject malicious code into clients browsers. To ensure the web UI is safe by default, +# raw HTML is disabled by default. If you trust your DAG authors, you can enable HTML +# support in markdown by setting this option to True. +# +# This parameter also enables the deprecated fields ``description_html`` and +# ``custom_html_form`` in DAG params until the feature is removed in a future version. +# +# Example: allow_raw_html_descriptions = False +# +# Variable: AIRFLOW__WEBSERVER__ALLOW_RAW_HTML_DESCRIPTIONS +# +allow_raw_html_descriptions = False + +# The maximum size of the request payload (in MB) that can be sent. +# +# Variable: AIRFLOW__WEBSERVER__ALLOWED_PAYLOAD_SIZE +# +allowed_payload_size = 1.0 + +# Require confirmation when changing a DAG in the web UI. This is to prevent accidental changes +# to a DAG that may be running on sensitive environments like production. +# When set to True, confirmation dialog will be shown when a user tries to Pause/Unpause, Trigger a DAG +# +# Variable: AIRFLOW__WEBSERVER__REQUIRE_CONFIRMATION_DAG_CHANGE +# +require_confirmation_dag_change = False + +[email] +# Configuration email backend and whether to +# send email alerts on retry or failure + +# Email backend to use +# +# Variable: AIRFLOW__EMAIL__EMAIL_BACKEND +# +email_backend = airflow.utils.email.send_email_smtp + +# Email connection to use +# +# Variable: AIRFLOW__EMAIL__EMAIL_CONN_ID +# +email_conn_id = smtp_default + +# Whether email alerts should be sent when a task is retried +# +# Variable: AIRFLOW__EMAIL__DEFAULT_EMAIL_ON_RETRY +# +default_email_on_retry = True + +# Whether email alerts should be sent when a task failed +# +# Variable: AIRFLOW__EMAIL__DEFAULT_EMAIL_ON_FAILURE +# +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 +# +# Variable: AIRFLOW__EMAIL__SUBJECT_TEMPLATE +# +# 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 +# +# Variable: AIRFLOW__EMAIL__HTML_CONTENT_TEMPLATE +# +# html_content_template = + +# Email address that will be used as sender address. +# It can either be raw email or the complete address in a format ``Sender Name `` +# +# Example: from_email = Airflow +# +# Variable: AIRFLOW__EMAIL__FROM_EMAIL +# +# from_email = + +# ssl context to use when using SMTP and IMAP SSL connections. By default, the context is "default" +# which sets it to ``ssl.create_default_context()`` which provides the right balance between +# compatibility and security, it however requires that certificates in your operating system are +# updated and that SMTP/IMAP servers of yours have valid certificates that have corresponding public +# keys installed on your machines. You can switch it to "none" if you want to disable checking +# of the certificates, but it is not recommended as it allows MITM (man-in-the-middle) attacks +# if your infrastructure is not sufficiently secured. It should only be set temporarily while you +# are fixing your certificate configuration. This can be typically done by upgrading to newer +# version of the operating system you run Airflow components on,by upgrading/refreshing proper +# certificates in the OS or by updating certificates for your mail servers. +# +# Example: ssl_context = default +# +# Variable: AIRFLOW__EMAIL__SSL_CONTEXT +# +ssl_context = default + +[smtp] +# If you want airflow to send emails on retries, failure, and you want to use +# the airflow.utils.email.send_email_smtp function, you have to configure an +# smtp server here + +# Specifies the host server address used by Airflow when sending out email notifications via SMTP. +# +# Variable: AIRFLOW__SMTP__SMTP_HOST +# +smtp_host = localhost + +# Determines whether to use the STARTTLS command when connecting to the SMTP server. +# +# Variable: AIRFLOW__SMTP__SMTP_STARTTLS +# +smtp_starttls = True + +# Determines whether to use an SSL connection when talking to the SMTP server. +# +# Variable: AIRFLOW__SMTP__SMTP_SSL +# +smtp_ssl = False + +# Username to authenticate when connecting to smtp server. +# +# Example: smtp_user = airflow +# +# Variable: AIRFLOW__SMTP__SMTP_USER +# +# smtp_user = + +# Password to authenticate when connecting to smtp server. +# +# Example: smtp_password = airflow +# +# Variable: AIRFLOW__SMTP__SMTP_PASSWORD +# +# smtp_password = + +# Defines the port number on which Airflow connects to the SMTP server to send email notifications. +# +# Variable: AIRFLOW__SMTP__SMTP_PORT +# +smtp_port = 25 + +# Specifies the default "from" email address used when Airflow sends email notifications. +# +# Variable: AIRFLOW__SMTP__SMTP_MAIL_FROM +# +smtp_mail_from = airflow@example.com + +# Determines the maximum time (in seconds) the Apache Airflow system will wait for a +# connection to the SMTP server to be established. +# +# Variable: AIRFLOW__SMTP__SMTP_TIMEOUT +# +smtp_timeout = 30 + +# Defines the maximum number of times Airflow will attempt to connect to the SMTP server. +# +# Variable: AIRFLOW__SMTP__SMTP_RETRY_LIMIT +# +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``, ``transport``. + +# Enable error reporting to Sentry +# +# Variable: AIRFLOW__SENTRY__SENTRY_ON +# +sentry_on = false + +# +# Variable: AIRFLOW__SENTRY__SENTRY_DSN +# +sentry_dsn = + +# Dotted path to a before_send function that the sentry SDK should be configured to use. +# +# Variable: AIRFLOW__SENTRY__BEFORE_SEND +# +# before_send = + +[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). +# +# Variable: AIRFLOW__SCHEDULER__JOB_HEARTBEAT_SEC +# +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). +# +# Variable: AIRFLOW__SCHEDULER__SCHEDULER_HEARTBEAT_SEC +# +scheduler_heartbeat_sec = 5 + +# The frequency (in seconds) at which the LocalTaskJob should send heartbeat signals to the +# scheduler to notify it's still alive. If this value is set to 0, the heartbeat interval will default +# to the value of scheduler_zombie_task_threshold. +# +# Variable: AIRFLOW__SCHEDULER__LOCAL_TASK_JOB_HEARTBEAT_SEC +# +local_task_job_heartbeat_sec = 0 + +# The number of times to try to schedule each DAG file +# -1 indicates unlimited number +# +# Variable: AIRFLOW__SCHEDULER__NUM_RUNS +# +num_runs = -1 + +# Controls how long the scheduler will sleep between loops, but if there was nothing to do +# in the loop. i.e. if it scheduled something then it will start the next loop +# iteration straight away. +# +# Variable: AIRFLOW__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. +# +# Variable: AIRFLOW__SCHEDULER__MIN_FILE_PROCESS_INTERVAL +# +min_file_process_interval = 30 + +# How often (in seconds) to check for stale DAGs (DAGs which are no longer present in +# the expected files) which should be deactivated, as well as datasets that are no longer +# referenced and should be marked as orphaned. +# +# Variable: AIRFLOW__SCHEDULER__PARSING_CLEANUP_INTERVAL +# +parsing_cleanup_interval = 60 + +# How long (in seconds) to wait after we have re-parsed a DAG file before deactivating stale +# DAGs (DAGs which are no longer present in the expected files). The reason why we need +# this threshold is to account for the time between when the file is parsed and when the +# DAG is loaded. The absolute maximum that this could take is `dag_file_processor_timeout`, +# but when you have a long timeout configured, it results in a significant delay in the +# deactivation of stale dags. +# +# Variable: AIRFLOW__SCHEDULER__STALE_DAG_THRESHOLD +# +stale_dag_threshold = 50 + +# How often (in seconds) to scan the DAGs directory for new files. Default to 5 minutes. +# +# Variable: AIRFLOW__SCHEDULER__DAG_DIR_LIST_INTERVAL +# +dag_dir_list_interval = 300 + +# How often should stats be printed to the logs. Setting to 0 will disable printing stats +# +# Variable: AIRFLOW__SCHEDULER__PRINT_STATS_INTERVAL +# +print_stats_interval = 30 + +# How often (in seconds) should pool usage stats be sent to StatsD (if statsd_on is enabled) +# +# Variable: AIRFLOW__SCHEDULER__POOL_METRICS_INTERVAL +# +pool_metrics_interval = 5.0 + +# 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 and in `airflow jobs check` CLI +# for SchedulerJob. +# +# Variable: AIRFLOW__SCHEDULER__SCHEDULER_HEALTH_CHECK_THRESHOLD +# +scheduler_health_check_threshold = 30 + +# When you start a scheduler, airflow starts a tiny web server +# subprocess to serve a health check if this is set to True +# +# Variable: AIRFLOW__SCHEDULER__ENABLE_HEALTH_CHECK +# +enable_health_check = False + +# When you start a scheduler, airflow starts a tiny web server +# subprocess to serve a health check on this host +# +# Variable: AIRFLOW__SCHEDULER__SCHEDULER_HEALTH_CHECK_SERVER_HOST +# +scheduler_health_check_server_host = 0.0.0.0 + +# When you start a scheduler, airflow starts a tiny web server +# subprocess to serve a health check on this port +# +# Variable: AIRFLOW__SCHEDULER__SCHEDULER_HEALTH_CHECK_SERVER_PORT +# +scheduler_health_check_server_port = 8974 + +# How often (in seconds) should the scheduler check for orphaned tasks and SchedulerJobs +# +# Variable: AIRFLOW__SCHEDULER__ORPHANED_TASKS_CHECK_INTERVAL +# +orphaned_tasks_check_interval = 300.0 + +# Determines the directory where logs for the child processes of the scheduler will be stored +# +# Variable: AIRFLOW__SCHEDULER__CHILD_PROCESS_LOG_DIRECTORY +# +child_process_log_directory = /opt/airflow/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. +# +# Variable: AIRFLOW__SCHEDULER__SCHEDULER_ZOMBIE_TASK_THRESHOLD +# +scheduler_zombie_task_threshold = 300 + +# How often (in seconds) should the scheduler check for zombie tasks. +# +# Variable: AIRFLOW__SCHEDULER__ZOMBIE_DETECTION_INTERVAL +# +zombie_detection_interval = 10.0 + +# 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) +# +# Variable: AIRFLOW__SCHEDULER__CATCHUP_BY_DEFAULT +# +catchup_by_default = True + +# 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. +# +# Variable: AIRFLOW__SCHEDULER__IGNORE_FIRST_DEPENDS_ON_PAST_BY_DEFAULT +# +ignore_first_depends_on_past_by_default = True + +# This changes the batch size of queries in the scheduling main loop. +# This should not be greater than ``core.parallelism``. +# If this is too high, SQL query performance may be impacted by +# complexity of query predicate, and/or excessive locking. +# Additionally, you may hit the maximum allowable query length for your db. +# Set this to 0 to use the value of ``core.parallelism`` +# +# Variable: AIRFLOW__SCHEDULER__MAX_TIS_PER_QUERY +# +max_tis_per_query = 16 + +# 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 +# +# Variable: AIRFLOW__SCHEDULER__USE_ROW_LEVEL_LOCKING +# +use_row_level_locking = True + +# Max number of DAGs to create DagRuns for per scheduler loop. +# +# Variable: AIRFLOW__SCHEDULER__MAX_DAGRUNS_TO_CREATE_PER_LOOP +# +max_dagruns_to_create_per_loop = 10 + +# How many DagRuns should a scheduler examine (and lock) when scheduling +# and queuing tasks. +# +# Variable: AIRFLOW__SCHEDULER__MAX_DAGRUNS_PER_LOOP_TO_SCHEDULE +# +max_dagruns_per_loop_to_schedule = 20 + +# 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 +# +# Variable: AIRFLOW__SCHEDULER__SCHEDULE_AFTER_TASK_EXECUTION +# +schedule_after_task_execution = True + +# The scheduler reads dag files to extract the airflow modules that are going to be used, +# and imports them ahead of time to avoid having to re-do it for each parsing process. +# This flag can be set to False to disable this behavior in case an airflow module needs to be freshly +# imported each time (at the cost of increased DAG parsing time). +# +# Variable: AIRFLOW__SCHEDULER__PARSING_PRE_IMPORT_MODULES +# +parsing_pre_import_modules = True + +# The scheduler can run multiple processes in parallel to parse dags. +# This defines how many processes will run. +# +# Variable: AIRFLOW__SCHEDULER__PARSING_PROCESSES +# +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 +# +# Variable: AIRFLOW__SCHEDULER__FILE_PARSING_SORT_MODE +# +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. +# +# Variable: AIRFLOW__SCHEDULER__STANDALONE_DAG_PROCESSOR +# +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. +# +# Variable: AIRFLOW__SCHEDULER__MAX_CALLBACKS_PER_LOOP +# +max_callbacks_per_loop = 20 + +# Only applicable if `[scheduler]standalone_dag_processor` is true. +# Time in seconds after which dags, which were not updated by Dag Processor are deactivated. +# +# Variable: AIRFLOW__SCHEDULER__DAG_STALE_NOT_SEEN_DURATION +# +dag_stale_not_seen_duration = 600 + +# 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. +# +# Variable: AIRFLOW__SCHEDULER__USE_JOB_SCHEDULE +# +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 +# +# Variable: AIRFLOW__SCHEDULER__ALLOW_TRIGGER_IN_FUTURE +# +allow_trigger_in_future = False + +# How often to check for expired trigger requests that have not run yet. +# +# Variable: AIRFLOW__SCHEDULER__TRIGGER_TIMEOUT_CHECK_INTERVAL +# +trigger_timeout_check_interval = 15 + +# Amount of time a task can be in the queued state before being retried or set to failed. +# +# Variable: AIRFLOW__SCHEDULER__TASK_QUEUED_TIMEOUT +# +task_queued_timeout = 600.0 + +# How often to check for tasks that have been in the queued state for +# longer than `[scheduler] task_queued_timeout`. +# +# Variable: AIRFLOW__SCHEDULER__TASK_QUEUED_TIMEOUT_CHECK_INTERVAL +# +task_queued_timeout_check_interval = 120.0 + +# The run_id pattern used to verify the validity of user input to the run_id parameter when +# triggering a DAG. This pattern cannot change the pattern used by scheduler to generate run_id +# for scheduled DAG runs or DAG runs triggered without changing the run_id parameter. +# +# Variable: AIRFLOW__SCHEDULER__ALLOWED_RUN_ID_PATTERN +# +allowed_run_id_pattern = ^[A-Za-z0-9_.~:+-]+$ + +# Whether to create DAG runs that span an interval or one single point in time for cron schedules, when +# a cron string is provided to `schedule` argument of a DAG. If True, +# CronDataIntervalTimetable is used, which is the legacy Airflow behavior suitable +# for DAGs with well-defined data_interval you get contiguous intervals from the end of the previous +# interval up to the scheduled datetime. If False, CronTriggerTimetable is used, +# which is closer to the behavior of cron itself. +# +# Notably, for CronTriggerTimetable, the logical_date is the same as the time the DAG Run will try to +# schedule, while for CronDataIntervalTimetable, the logical_date is the beginning of the data interval, +# but the DAG Run will try to schedule at the end of the data interval. For more differences +# between the two Timetables, see +# https://airflow.apache.org/docs/apache-airflow/stable/authoring-and-scheduling/timetable.html#differences-between-the-two-cron-timetables +# +# Variable: AIRFLOW__SCHEDULER__CREATE_CRON_DATA_INTERVALS +# +create_cron_data_intervals = True + +[triggerer] +# How many triggers a single Triggerer will run at once, by default. +# +# Variable: AIRFLOW__TRIGGERER__DEFAULT_CAPACITY +# +default_capacity = 1000 + +# How often to heartbeat the Triggerer job to ensure it hasn't been killed. +# +# Variable: AIRFLOW__TRIGGERER__JOB_HEARTBEAT_SEC +# +job_heartbeat_sec = 5 + +# If the last triggerer heartbeat happened more than triggerer_health_check_threshold +# ago (in seconds), triggerer is considered unhealthy. +# This is used by the health check in the "/health" endpoint and in `airflow jobs check` CLI +# for TriggererJob. +# +# Variable: AIRFLOW__TRIGGERER__TRIGGERER_HEALTH_CHECK_THRESHOLD +# +triggerer_health_check_threshold = 30 + +[kerberos] +# Location of your ccache file once kinit has been performed. +# +# Variable: AIRFLOW__KERBEROS__CCACHE +# +ccache = /tmp/airflow_krb5_ccache + +# gets augmented with fqdn +# +# Variable: AIRFLOW__KERBEROS__PRINCIPAL +# +principal = airflow + +# Determines the frequency at which initialization or re-initialization processes occur. +# +# Variable: AIRFLOW__KERBEROS__REINIT_FREQUENCY +# +reinit_frequency = 3600 + +# Path to the kinit executable +# +# Variable: AIRFLOW__KERBEROS__KINIT_PATH +# +kinit_path = kinit + +# Designates the path to the Kerberos keytab file for the Airflow user +# +# Variable: AIRFLOW__KERBEROS__KEYTAB +# +keytab = airflow.keytab + +# Allow to disable ticket forwardability. +# +# Variable: AIRFLOW__KERBEROS__FORWARDABLE +# +forwardable = True + +# Allow to remove source IP from token, useful when using token behind NATted Docker host. +# +# Variable: AIRFLOW__KERBEROS__INCLUDE_IP +# +include_ip = True + +[sensors] +# Sensor default timeout, 7 days by default (7 * 24 * 60 * 60). +# +# Variable: AIRFLOW__SENSORS__DEFAULT_TIMEOUT +# +default_timeout = 604800 + +[aws] +# This section contains settings for Amazon Web Services (AWS) integration. + +# session_factory = +cloudwatch_task_handler_json_serializer = airflow.providers.amazon.aws.log.cloudwatch_task_handler.json_serialize_legacy + +[aws_batch_executor] +# This section only applies if you are using the AwsBatchExecutor in +# Airflow's ``[core]`` configuration. +# For more information on any of these execution parameters, see the link below: +# https://boto3.amazonaws.com/v1/documentation/api/latest/reference/services/batch.html#Batch.Client.submit_job +# For boto3 credential management, see +# https://boto3.amazonaws.com/v1/documentation/api/latest/guide/configuration.html + +conn_id = aws_default +# region_name = +max_submit_job_attempts = 3 +check_health_on_startup = True +# job_name = +# job_queue = +# job_definition = +# submit_job_kwargs = + +[aws_ecs_executor] +# This section only applies if you are using the AwsEcsExecutor in +# Airflow's ``[core]`` configuration. +# For more information on any of these execution parameters, see the link below: +# https://boto3.amazonaws.com/v1/documentation/api/latest/reference/services/ecs/client/run_task.html +# For boto3 credential management, see +# https://boto3.amazonaws.com/v1/documentation/api/latest/guide/configuration.html + +conn_id = aws_default +# region_name = +assign_public_ip = False +# cluster = +# capacity_provider_strategy = +# container_name = +# launch_type = +platform_version = LATEST +# security_groups = +# subnets = +# task_definition = +max_run_task_attempts = 3 +# run_task_kwargs = +check_health_on_startup = True + +[aws_auth_manager] +# This section only applies if you are using the AwsAuthManager. In other words, if you set +# ``[core] auth_manager = airflow.providers.amazon.aws.auth_manager.aws_auth_manager.AwsAuthManager`` in +# Airflow's configuration. + +enable = False +conn_id = aws_default +# region_name = +# saml_metadata_url = +# avp_policy_store_id = + +[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`` +# +# Variable: AIRFLOW__CELERY_KUBERNETES_EXECUTOR__KUBERNETES_QUEUE +# +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 +# +# Variable: AIRFLOW__CELERY__CELERY_APP_NAME +# +celery_app_name = airflow.providers.celery.executors.celery_executor + +# The concurrency that will be used when starting workers with the +# ``airflow celery 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 +# +# Variable: AIRFLOW__CELERY__WORKER_CONCURRENCY +# +worker_concurrency = 16 + +# The maximum and minimum number of pool processes that will be used to dynamically resize +# the pool based on load.Enable autoscaling by providing max_concurrency,min_concurrency +# with the ``airflow celery worker`` command (always keep minimum processes, +# but grow to maximum if necessary). +# 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. +# https://docs.celeryq.dev/en/latest/reference/celery.bin.worker.html#cmdoption-celery-worker-autoscale +# +# Example: worker_autoscale = 16,12 +# +# Variable: AIRFLOW__CELERY__WORKER_AUTOSCALE +# +# 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.celeryq.dev/en/stable/userguide/optimizing.html#prefetch-limits +# +# Variable: AIRFLOW__CELERY__WORKER_PREFETCH_MULTIPLIER +# +worker_prefetch_multiplier = 1 + +# Specify if remote control of the workers is enabled. +# In some cases when the broker does not support remote control, 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. +# https://docs.celeryq.dev/en/stable/getting-started/backends-and-brokers/index.html#broker-overview +# +# Variable: AIRFLOW__CELERY__WORKER_ENABLE_REMOTE_CONTROL +# +worker_enable_remote_control = true + +# The Celery broker URL. Celery supports RabbitMQ, Redis and experimentally +# a sqlalchemy database. Refer to the Celery documentation for more information. +# +# Variable: AIRFLOW__CELERY__BROKER_URL +# +broker_url = redis://redis:6379/0 + +# The Celery result_backend. When a job finishes, it needs to update the +# metadata of the job. Therefore it will post a message on a message bus, +# or insert it into a database (depending of the backend) +# This status is used by the scheduler to update the state of the task +# The use of a database is highly recommended +# When not specified, sql_alchemy_conn with a db+ scheme prefix will be used +# https://docs.celeryq.dev/en/latest/userguide/configuration.html#task-result-backend-settings +# +# Example: result_backend = db+postgresql://postgres:airflow@postgres/airflow +# +# Variable: AIRFLOW__CELERY__RESULT_BACKEND +# +# result_backend = + +# Optional configuration dictionary to pass to the Celery result backend SQLAlchemy engine. +# +# Example: result_backend_sqlalchemy_engine_options = {"pool_recycle": 1800} +# +# Variable: AIRFLOW__CELERY__RESULT_BACKEND_SQLALCHEMY_ENGINE_OPTIONS +# +result_backend_sqlalchemy_engine_options = + +# 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 +# +# Variable: AIRFLOW__CELERY__FLOWER_HOST +# +flower_host = 0.0.0.0 + +# The root URL for Flower +# +# Example: flower_url_prefix = /flower +# +# Variable: AIRFLOW__CELERY__FLOWER_URL_PREFIX +# +flower_url_prefix = + +# This defines the port that Celery Flower runs on +# +# Variable: AIRFLOW__CELERY__FLOWER_PORT +# +flower_port = 5555 + +# Securing Flower with Basic Authentication +# Accepts user:password pairs separated by a comma +# +# Example: flower_basic_auth = user1:password1,user2:password2 +# +# Variable: AIRFLOW__CELERY__FLOWER_BASIC_AUTH +# +flower_basic_auth = + +# How many processes CeleryExecutor uses to sync task state. +# 0 means to use max(1, number of cores - 1) processes. +# +# Variable: AIRFLOW__CELERY__SYNC_PARALLELISM +# +sync_parallelism = 0 + +# Import path for celery configuration options +# +# Variable: AIRFLOW__CELERY__CELERY_CONFIG_OPTIONS +# +celery_config_options = airflow.providers.celery.executors.default_celery.DEFAULT_CELERY_CONFIG + +# +# Variable: AIRFLOW__CELERY__SSL_ACTIVE +# +ssl_active = False + +# Path to the client key. +# +# Variable: AIRFLOW__CELERY__SSL_KEY +# +ssl_key = + +# Path to the client certificate. +# +# Variable: AIRFLOW__CELERY__SSL_CERT +# +ssl_cert = + +# Path to the CA certificate. +# +# Variable: AIRFLOW__CELERY__SSL_CACERT +# +ssl_cacert = + +# Celery Pool implementation. +# Choices include: ``prefork`` (default), ``eventlet``, ``gevent`` or ``solo``. +# See: +# https://docs.celeryq.dev/en/latest/userguide/workers.html#concurrency +# https://docs.celeryq.dev/en/latest/userguide/concurrency/eventlet.html +# +# Variable: AIRFLOW__CELERY__POOL +# +pool = prefork + +# The number of seconds to wait before timing out ``send_task_to_executor`` or +# ``fetch_celery_task_state`` operations. +# +# Variable: AIRFLOW__CELERY__OPERATION_TIMEOUT +# +operation_timeout = 1.0 + +task_acks_late = True +# 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. +# +# Variable: AIRFLOW__CELERY__TASK_TRACK_STARTED +# +task_track_started = True + +# 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. +# +# Variable: AIRFLOW__CELERY__TASK_PUBLISH_MAX_RETRIES +# +task_publish_max_retries = 3 + +# Worker initialisation check to validate Metadata Database connection +# +# Variable: AIRFLOW__CELERY__WORKER_PRECHECK +# +worker_precheck = False + +[celery_broker_transport_options] +# This section is for specifying options which can be passed to the +# underlying celery broker transport. See: +# https://docs.celeryq.dev/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: +# https://docs.celeryq.dev/en/stable/getting-started/backends-and-brokers/redis.html#visibility-timeout +# +# Example: visibility_timeout = 21600 +# +# Variable: AIRFLOW__CELERY_BROKER_TRANSPORT_OPTIONS__VISIBILITY_TIMEOUT +# +# visibility_timeout = + +# The sentinel_kwargs parameter allows passing additional options to the Sentinel client. +# In a typical scenario where Redis Sentinel is used as the broker and Redis servers are +# password-protected, the password needs to be passed through this parameter. Although its +# type is string, it is required to pass a string that conforms to the dictionary format. +# See: +# https://docs.celeryq.dev/en/stable/getting-started/backends-and-brokers/redis.html#configuration +# +# Example: sentinel_kwargs = {"password": "password_for_redis_server"} +# +# Variable: AIRFLOW__CELERY_BROKER_TRANSPORT_OPTIONS__SENTINEL_KWARGS +# +# sentinel_kwargs = + +[local_kubernetes_executor] +# This section only applies if you are using the ``LocalKubernetesExecutor`` in +# ``[core]`` section above + +# Define when to send a task to ``KubernetesExecutor`` when using ``LocalKubernetesExecutor``. +# When the queue of a task is the value of ``kubernetes_queue`` (default ``kubernetes``), +# the task is executed via ``KubernetesExecutor``, +# otherwise via ``LocalExecutor`` +# +# Variable: AIRFLOW__LOCAL_KUBERNETES_EXECUTOR__KUBERNETES_QUEUE +# +kubernetes_queue = kubernetes + +[kubernetes_executor] +# Kwargs to override the default urllib3 Retry used in the kubernetes API client +# +# Example: api_client_retry_configuration = { "total": 3, "backoff_factor": 0.5 } +# +# Variable: AIRFLOW__KUBERNETES_EXECUTOR__API_CLIENT_RETRY_CONFIGURATION +# +api_client_retry_configuration = + +# Flag to control the information added to kubernetes executor logs for better traceability +# +# Variable: AIRFLOW__KUBERNETES_EXECUTOR__LOGS_TASK_METADATA +# +logs_task_metadata = False + +# Path to the YAML pod file that forms the basis for KubernetesExecutor workers. +# +# Variable: AIRFLOW__KUBERNETES_EXECUTOR__POD_TEMPLATE_FILE +# +pod_template_file = + +# The repository of the Kubernetes Image for the Worker to Run +# +# Variable: AIRFLOW__KUBERNETES_EXECUTOR__WORKER_CONTAINER_REPOSITORY +# +worker_container_repository = + +# The tag of the Kubernetes Image for the Worker to Run +# +# Variable: AIRFLOW__KUBERNETES_EXECUTOR__WORKER_CONTAINER_TAG +# +worker_container_tag = + +# The Kubernetes namespace where airflow workers should be created. Defaults to ``default`` +# +# Variable: AIRFLOW__KUBERNETES_EXECUTOR__NAMESPACE +# +namespace = default + +# If True, all worker pods will be deleted upon termination +# +# Variable: AIRFLOW__KUBERNETES_EXECUTOR__DELETE_WORKER_PODS +# +delete_worker_pods = True + +# If False (and delete_worker_pods is True), +# failed worker pods will not be deleted so users can investigate them. +# This only prevents removal of worker pods where the worker itself failed, +# not when the task it ran failed. +# +# Variable: AIRFLOW__KUBERNETES_EXECUTOR__DELETE_WORKER_PODS_ON_FAILURE +# +delete_worker_pods_on_failure = False + +worker_pod_pending_fatal_container_state_reasons = CreateContainerConfigError,ErrImagePull,CreateContainerError,ImageInspectError, InvalidImageName +# Number of Kubernetes Worker Pod creation calls per scheduler loop. +# Note that the current default of "1" will only launch a single pod +# per-heartbeat. It is HIGHLY recommended that users increase this +# number to match the tolerance of their kubernetes cluster for +# better performance. +# +# Variable: AIRFLOW__KUBERNETES_EXECUTOR__WORKER_PODS_CREATION_BATCH_SIZE +# +worker_pods_creation_batch_size = 1 + +# Allows users to launch pods in multiple namespaces. +# Will require creating a cluster-role for the scheduler, +# or use multi_namespace_mode_namespace_list configuration. +# +# Variable: AIRFLOW__KUBERNETES_EXECUTOR__MULTI_NAMESPACE_MODE +# +multi_namespace_mode = False + +# If multi_namespace_mode is True while scheduler does not have a cluster-role, +# give the list of namespaces where the scheduler will schedule jobs +# Scheduler needs to have the necessary permissions in these namespaces. +# +# Variable: AIRFLOW__KUBERNETES_EXECUTOR__MULTI_NAMESPACE_MODE_NAMESPACE_LIST +# +multi_namespace_mode_namespace_list = + +# Use the service account kubernetes gives to pods to connect to kubernetes cluster. +# It's intended for clients that expect to be running inside a pod running on kubernetes. +# It will raise an exception if called from a process not running in a kubernetes environment. +# +# Variable: AIRFLOW__KUBERNETES_EXECUTOR__IN_CLUSTER +# +in_cluster = True + +# When running with in_cluster=False change the default cluster_context or config_file +# options to Kubernetes client. Leave blank these to use default behaviour like ``kubectl`` has. +# +# Variable: AIRFLOW__KUBERNETES_EXECUTOR__CLUSTER_CONTEXT +# +# cluster_context = + +# Path to the kubernetes configfile to be used when ``in_cluster`` is set to False +# +# Variable: AIRFLOW__KUBERNETES_EXECUTOR__CONFIG_FILE +# +# config_file = + +# Keyword parameters to pass while calling a kubernetes client core_v1_api methods +# from Kubernetes Executor provided as a single line formatted JSON dictionary string. +# List of supported params are similar for all core_v1_apis, hence a single config +# variable for all apis. See: +# https://raw.githubusercontent.com/kubernetes-client/python/41f11a09995efcd0142e25946adc7591431bfb2f/kubernetes/client/api/core_v1_api.py +# +# Variable: AIRFLOW__KUBERNETES_EXECUTOR__KUBE_CLIENT_REQUEST_ARGS +# +kube_client_request_args = + +# Optional keyword arguments to pass to the ``delete_namespaced_pod`` kubernetes client +# ``core_v1_api`` method when using the Kubernetes Executor. +# This should be an object and can contain any of the options listed in the ``v1DeleteOptions`` +# class defined here: +# https://github.com/kubernetes-client/python/blob/41f11a09995efcd0142e25946adc7591431bfb2f/kubernetes/client/models/v1_delete_options.py#L19 +# +# Example: delete_option_kwargs = {"grace_period_seconds": 10} +# +# Variable: AIRFLOW__KUBERNETES_EXECUTOR__DELETE_OPTION_KWARGS +# +delete_option_kwargs = + +# Enables TCP keepalive mechanism. This prevents Kubernetes API requests to hang indefinitely +# when idle connection is time-outed on services like cloud load balancers or firewalls. +# +# Variable: AIRFLOW__KUBERNETES_EXECUTOR__ENABLE_TCP_KEEPALIVE +# +enable_tcp_keepalive = True + +# When the `enable_tcp_keepalive` option is enabled, TCP probes a connection that has +# been idle for `tcp_keep_idle` seconds. +# +# Variable: AIRFLOW__KUBERNETES_EXECUTOR__TCP_KEEP_IDLE +# +tcp_keep_idle = 120 + +# When the `enable_tcp_keepalive` option is enabled, if Kubernetes API does not respond +# to a keepalive probe, TCP retransmits the probe after `tcp_keep_intvl` seconds. +# +# Variable: AIRFLOW__KUBERNETES_EXECUTOR__TCP_KEEP_INTVL +# +tcp_keep_intvl = 30 + +# When the `enable_tcp_keepalive` option is enabled, if Kubernetes API does not respond +# to a keepalive probe, TCP retransmits the probe `tcp_keep_cnt number` of times before +# a connection is considered to be broken. +# +# Variable: AIRFLOW__KUBERNETES_EXECUTOR__TCP_KEEP_CNT +# +tcp_keep_cnt = 6 + +# Set this to false to skip verifying SSL certificate of Kubernetes python client. +# +# Variable: AIRFLOW__KUBERNETES_EXECUTOR__VERIFY_SSL +# +verify_ssl = True + +# How often in seconds to check for task instances stuck in "queued" status without a pod +# +# Variable: AIRFLOW__KUBERNETES_EXECUTOR__WORKER_PODS_QUEUED_CHECK_INTERVAL +# +worker_pods_queued_check_interval = 60 + +# Path to a CA certificate to be used by the Kubernetes client to verify the server's SSL certificate. +# +# Variable: AIRFLOW__KUBERNETES_EXECUTOR__SSL_CA_CERT +# +ssl_ca_cert = + +# The Maximum number of retries for queuing the task to the kubernetes scheduler when +# failing due to Kube API exceeded quota errors before giving up and marking task as failed. +# -1 for unlimited times. +# +# Variable: AIRFLOW__KUBERNETES_EXECUTOR__TASK_PUBLISH_MAX_RETRIES +# +task_publish_max_retries = 0 + +[common.io] +# Common IO configuration section + +# Path to a location on object storage where XComs can be stored in url format. +# +# Example: xcom_objectstorage_path = s3://conn_id@bucket/path +# +# Variable: AIRFLOW__COMMON.IO__XCOM_OBJECTSTORAGE_PATH +# +xcom_objectstorage_path = + +# Threshold in bytes for storing XComs in object storage. -1 means always store in the +# database. 0 means always store in object storage. Any positive number means +# it will be stored in object storage if the size of the value is greater than the threshold. +# +# Example: xcom_objectstorage_threshold = 1000000 +# +# Variable: AIRFLOW__COMMON.IO__XCOM_OBJECTSTORAGE_THRESHOLD +# +xcom_objectstorage_threshold = -1 + +# Compression algorithm to use when storing XComs in object storage. Supported algorithms +# are a.o.: snappy, zip, gzip, bz2, and lzma. If not specified, no compression will be used. +# Note that the compression algorithm must be available in the Python installation (e.g. +# python-snappy for snappy). Zip, gz, bz2 are available by default. +# +# Example: xcom_objectstorage_compression = gz +# +# Variable: AIRFLOW__COMMON.IO__XCOM_OBJECTSTORAGE_COMPRESSION +# +xcom_objectstorage_compression = + +[elasticsearch] +# Elasticsearch host +# +# Variable: AIRFLOW__ELASTICSEARCH__HOST +# +host = + +# Format of the log_id, which is used to query for a given tasks logs +# +# Variable: AIRFLOW__ELASTICSEARCH__LOG_ID_TEMPLATE +# +log_id_template = {dag_id}-{task_id}-{run_id}-{map_index}-{try_number} + +# Used to mark the end of a log stream for a task +# +# Variable: AIRFLOW__ELASTICSEARCH__END_OF_LOG_MARK +# +end_of_log_mark = end_of_log + +# Qualified URL for an elasticsearch frontend (like Kibana) with a template argument for log_id +# Code will construct log_id using the log_id template from the argument above. +# NOTE: scheme will default to https if one is not provided +# +# Example: frontend = http://localhost:5601/app/kibana#/discover?_a=(columns:!(message),query:(language:kuery,query:'log_id: "{log_id}"'),sort:!(log.offset,asc)) +# +# Variable: AIRFLOW__ELASTICSEARCH__FRONTEND +# +frontend = + +# Write the task logs to the stdout of the worker, rather than the default files +# +# Variable: AIRFLOW__ELASTICSEARCH__WRITE_STDOUT +# +write_stdout = False + +# Instead of the default log formatter, write the log lines as JSON +# +# Variable: AIRFLOW__ELASTICSEARCH__JSON_FORMAT +# +json_format = False + +# Log fields to also attach to the json output, if enabled +# +# Variable: AIRFLOW__ELASTICSEARCH__JSON_FIELDS +# +json_fields = asctime, filename, lineno, levelname, message + +# The field where host name is stored (normally either `host` or `host.name`) +# +# Variable: AIRFLOW__ELASTICSEARCH__HOST_FIELD +# +host_field = host + +# The field where offset is stored (normally either `offset` or `log.offset`) +# +# Variable: AIRFLOW__ELASTICSEARCH__OFFSET_FIELD +# +offset_field = offset + +# Comma separated list of index patterns to use when searching for logs (default: `_all`). +# +# Example: index_patterns = something-* +# +# Variable: AIRFLOW__ELASTICSEARCH__INDEX_PATTERNS +# +index_patterns = _all + +[elasticsearch_configs] +# +# Variable: AIRFLOW__ELASTICSEARCH_CONFIGS__HTTP_COMPRESS +# +http_compress = False + +# +# Variable: AIRFLOW__ELASTICSEARCH_CONFIGS__VERIFY_CERTS +# +verify_certs = True + +[fab] +# This section contains configs specific to FAB provider. + +# Boolean for enabling rate limiting on authentication endpoints. +# +# Variable: AIRFLOW__FAB__AUTH_RATE_LIMITED +# +auth_rate_limited = True + +# Rate limit for authentication endpoints. +# +# Variable: AIRFLOW__FAB__AUTH_RATE_LIMIT +# +auth_rate_limit = 5 per 40 second + +# Update FAB permissions and sync security manager roles +# on webserver startup +# +# Variable: AIRFLOW__FAB__UPDATE_FAB_PERMS +# +update_fab_perms = True + +[imap] +# Options for IMAP provider. + +# ssl_context = + +[azure_remote_logging] +# Configuration that needs to be set for enable remote logging in Azure Blob Storage + +remote_wasb_log_container = airflow-logs + +[openlineage] +# This section applies settings for OpenLineage integration. +# More about configuration and it's precedence can be found at +# https://airflow.apache.org/docs/apache-airflow-providers-openlineage/stable/guides/user.html#transport-setup + +# Disable sending events without uninstalling the OpenLineage Provider by setting this to true. +# +# Variable: AIRFLOW__OPENLINEAGE__DISABLED +# +disabled = False + +# Exclude some Operators from emitting OpenLineage events by passing a string of semicolon separated +# full import paths of Operators to disable. +# +# Example: disabled_for_operators = airflow.operators.bash.BashOperator;airflow.operators.python.PythonOperator +# +# Variable: AIRFLOW__OPENLINEAGE__DISABLED_FOR_OPERATORS +# +disabled_for_operators = + +# If this setting is enabled, OpenLineage integration won't collect and emit metadata, +# unless you explicitly enable it per `DAG` or `Task` using `enable_lineage` method. +# +# Variable: AIRFLOW__OPENLINEAGE__SELECTIVE_ENABLE +# +selective_enable = False + +# Set namespace that the lineage data belongs to, so that if you use multiple OpenLineage producers, +# events coming from them will be logically separated. +# +# Example: namespace = my_airflow_instance_1 +# +# Variable: AIRFLOW__OPENLINEAGE__NAMESPACE +# +# namespace = + +# Register custom OpenLineage Extractors by passing a string of semicolon separated full import paths. +# +# Example: extractors = full.path.to.ExtractorClass;full.path.to.AnotherExtractorClass +# +# Variable: AIRFLOW__OPENLINEAGE__EXTRACTORS +# +# extractors = + +# Specify the path to the YAML configuration file. +# This ensures backwards compatibility with passing config through the `openlineage.yml` file. +# +# Example: config_path = full/path/to/openlineage.yml +# +# Variable: AIRFLOW__OPENLINEAGE__CONFIG_PATH +# +config_path = + +# Pass OpenLineage Client transport configuration as JSON string. It should contain type of the +# transport and additional options (different for each transport type). For more details see: +# https://openlineage.io/docs/client/python/#built-in-transport-types +# +# Currently supported types are: +# +# * HTTP +# * Kafka +# * Console +# * File +# +# Example: transport = {"type": "http", "url": "http://localhost:5000", "endpoint": "api/v1/lineage"} +# +# Variable: AIRFLOW__OPENLINEAGE__TRANSPORT +# +transport = + +# Disable the inclusion of source code in OpenLineage events by setting this to `true`. +# By default, several Operators (e.g. Python, Bash) will include their source code in the events +# unless disabled. +# +# Variable: AIRFLOW__OPENLINEAGE__DISABLE_SOURCE_CODE +# +# disable_source_code = + +[smtp_provider] +# Options for SMTP provider. + +# ssl context to use when using SMTP and IMAP SSL connections. By default, the context is "default" +# which sets it to ``ssl.create_default_context()`` which provides the right balance between +# compatibility and security, it however requires that certificates in your operating system are +# updated and that SMTP/IMAP servers of yours have valid certificates that have corresponding public +# keys installed on your machines. You can switch it to "none" if you want to disable checking +# of the certificates, but it is not recommended as it allows MITM (man-in-the-middle) attacks +# if your infrastructure is not sufficiently secured. It should only be set temporarily while you +# are fixing your certificate configuration. This can be typically done by upgrading to newer +# version of the operating system you run Airflow components on,by upgrading/refreshing proper +# certificates in the OS or by updating certificates for your mail servers. +# +# If you do not set this option explicitly, it will use Airflow "email.ssl_context" configuration, +# but if this configuration is not present, it will use "default" value. +# +# Example: ssl_context = default +# +# Variable: AIRFLOW__SMTP_PROVIDER__SSL_CONTEXT +# +# ssl_context = + +# Allows overriding of the standard templated email subject line when the SmtpNotifier is used. +# Must provide a path to the template. +# +# Example: templated_email_subject_path = path/to/override/email_subject.html +# +# Variable: AIRFLOW__SMTP_PROVIDER__TEMPLATED_EMAIL_SUBJECT_PATH +# +# templated_email_subject_path = + +# Allows overriding of the standard templated email path when the SmtpNotifier is used. Must provide +# a path to the template. +# +# Example: templated_html_content_path = path/to/override/email.html +# +# Variable: AIRFLOW__SMTP_PROVIDER__TEMPLATED_HTML_CONTENT_PATH +# +# templated_html_content_path = + diff --git a/docker/airflow/webserver_config.py b/docker/airflow/webserver_config.py new file mode 100644 index 0000000..78fae49 --- /dev/null +++ b/docker/airflow/webserver_config.py @@ -0,0 +1,133 @@ +# +# Licensed to the Apache Software Foundation (ASF) under one +# or more contributor license agreements. See the NOTICE file +# distributed with this work for additional information +# regarding copyright ownership. The ASF licenses this file +# to you under the Apache License, Version 2.0 (the +# "License"); you may not use this file except in compliance +# with the License. You may obtain a copy of the License at +# +# http://www.apache.org/licenses/LICENSE-2.0 +# +# Unless required by applicable law or agreed to in writing, +# software distributed under the License is distributed on an +# "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY +# KIND, either express or implied. See the License for the +# specific language governing permissions and limitations +# under the License. +"""Default configuration for the Airflow webserver.""" + +from __future__ import annotations + +import os + +from flask_appbuilder.const import AUTH_DB + +# from airflow.www.fab_security.manager import AUTH_LDAP +# from airflow.www.fab_security.manager import AUTH_OAUTH +# from airflow.www.fab_security.manager import AUTH_OID +# from airflow.www.fab_security.manager import AUTH_REMOTE_USER + + +basedir = os.path.abspath(os.path.dirname(__file__)) + +# Flask-WTF flag for CSRF +WTF_CSRF_ENABLED = True +WTF_CSRF_TIME_LIMIT = None + +# ---------------------------------------------------- +# AUTHENTICATION CONFIG +# ---------------------------------------------------- +# For details on how to set up each of the following authentication, see +# http://flask-appbuilder.readthedocs.io/en/latest/security.html# authentication-methods +# for details. + +# The authentication type +# AUTH_OID : Is for OpenID +# AUTH_DB : Is for database +# AUTH_LDAP : Is for LDAP +# AUTH_REMOTE_USER : Is for using REMOTE_USER from web server +# AUTH_OAUTH : Is for OAuth +AUTH_TYPE = AUTH_DB + +# Uncomment to setup Full admin role name +# AUTH_ROLE_ADMIN = 'Admin' + +# Uncomment and set to desired role to enable access without authentication +# AUTH_ROLE_PUBLIC = 'Viewer' +AUTH_ROLE_PUBLIC = 'Admin' + +# Will allow user self registration +# AUTH_USER_REGISTRATION = True + +# The recaptcha it's automatically enabled for user self registration is active and the keys are necessary +# RECAPTCHA_PRIVATE_KEY = PRIVATE_KEY +# RECAPTCHA_PUBLIC_KEY = PUBLIC_KEY + +# Config for Flask-Mail necessary for user self registration +# MAIL_SERVER = 'smtp.gmail.com' +# MAIL_USE_TLS = True +# MAIL_USERNAME = 'yourappemail@gmail.com' +# MAIL_PASSWORD = 'passwordformail' +# MAIL_DEFAULT_SENDER = 'sender@gmail.com' + +# The default user self registration role +# AUTH_USER_REGISTRATION_ROLE = "Public" + +# When using OAuth Auth, uncomment to setup provider(s) info +# Google OAuth example: +# OAUTH_PROVIDERS = [{ +# 'name':'google', +# 'token_key':'access_token', +# 'icon':'fa-google', +# 'remote_app': { +# 'api_base_url':'https://www.googleapis.com/oauth2/v2/', +# 'client_kwargs':{ +# 'scope': 'email profile' +# }, +# 'access_token_url':'https://accounts.google.com/o/oauth2/token', +# 'authorize_url':'https://accounts.google.com/o/oauth2/auth', +# 'request_token_url': None, +# 'client_id': GOOGLE_KEY, +# 'client_secret': GOOGLE_SECRET_KEY, +# } +# }] + +# When using LDAP Auth, setup the ldap server +# AUTH_LDAP_SERVER = "ldap://ldapserver.new" + +# When using OpenID Auth, uncomment to setup OpenID providers. +# example for OpenID authentication +# OPENID_PROVIDERS = [ +# { 'name': 'Yahoo', 'url': 'https://me.yahoo.com' }, +# { 'name': 'AOL', 'url': 'http://openid.aol.com/' }, +# { 'name': 'Flickr', 'url': 'http://www.flickr.com/' }, +# { 'name': 'MyOpenID', 'url': 'https://www.myopenid.com' }] + +# ---------------------------------------------------- +# Theme CONFIG +# ---------------------------------------------------- +# Flask App Builder comes up with a number of predefined themes +# that you can use for Apache Airflow. +# http://flask-appbuilder.readthedocs.io/en/latest/customizing.html#changing-themes +# Please make sure to remove "navbar_color" configuration from airflow.cfg +# in order to fully utilize the theme. (or use that property in conjunction with theme) +# APP_THEME = "bootstrap-theme.css" # default bootstrap +# APP_THEME = "amelia.css" +# APP_THEME = "cerulean.css" +# APP_THEME = "cosmo.css" +# APP_THEME = "cyborg.css" +# APP_THEME = "darkly.css" +# APP_THEME = "flatly.css" +# APP_THEME = "journal.css" +# APP_THEME = "lumen.css" +# APP_THEME = "paper.css" +# APP_THEME = "readable.css" +# APP_THEME = "sandstone.css" +# APP_THEME = "simplex.css" +# APP_THEME = "slate.css" +# APP_THEME = "solar.css" +# APP_THEME = "spacelab.css" +# APP_THEME = "superhero.css" +# APP_THEME = "united.css" +# APP_THEME = "yeti.css" diff --git a/docker/nginx/nginx.conf b/docker/nginx/nginx.conf index 5c75883..5e7218e 100644 --- a/docker/nginx/nginx.conf +++ b/docker/nginx/nginx.conf @@ -8,7 +8,7 @@ http { proxy_pass http://history-server:18080; proxy_hide_header X-Frame-Options; add_header X-Frame-Options "ALLOW-FROM http://localhost:3000" always; # Add the new header - add_header X-Frame-Options "ALLOW-FROM http://localhost:5001" always; # Add the new header + add_header X-Frame-Options "ALLOW-FROM http://webapp:5001" always; # Add the new header } } } diff --git a/webapp/.env.dev b/webapp/.env.dev index 61f2985..0c1de63 100644 --- a/webapp/.env.dev +++ b/webapp/.env.dev @@ -1,3 +1,4 @@ REACT_APP_SERVER_BASE_URL=http://localhost:5002 REACT_APP_JUPYTER_BASE_URL=http://localhost:8888 -REACT_APP_SPARK_UI_BASE_URL=http://localhost:18081 \ No newline at end of file +REACT_APP_SPARK_UI_BASE_URL=http://localhost:18081 +REACT_APP_AIRFLOW_BASE_URL=http://localhost:8090 \ No newline at end of file diff --git a/webapp/.env.test b/webapp/.env.test new file mode 100644 index 0000000..c284b85 --- /dev/null +++ b/webapp/.env.test @@ -0,0 +1,4 @@ +REACT_APP_SERVER_BASE_URL=server:5002 +REACT_APP_JUPYTER_BASE_URL=notebook:8888 +REACT_APP_SPARK_UI_BASE_URL=history-server:18080 +REACT_APP_AIRFLOW_BASE_URL=airflow-webserver:8080 \ No newline at end of file diff --git a/webapp/public/env.template.js b/webapp/public/env.template.js index ff6a579..82d5f78 100644 --- a/webapp/public/env.template.js +++ b/webapp/public/env.template.js @@ -1,4 +1,6 @@ window._env_ = { REACT_APP_JUPYTER_BASE_URL: "$REACT_APP_JUPYTER_BASE_URL", REACT_APP_SERVER_BASE_URL: "$REACT_APP_SERVER_BASE_URL", + REACT_APP_SPARK_UI_BASE_URL: "$REACT_APP_SPARK_UI_BASE_URL", + REACT_APP_AIRFLOW_BASE_URL: "$REACT_APP_AIRFLOW_BASE_URL", }; diff --git a/webapp/src/App.js b/webapp/src/App.js index 6a371a4..e07fc55 100644 --- a/webapp/src/App.js +++ b/webapp/src/App.js @@ -2,6 +2,7 @@ import React, { useState, useEffect } from 'react'; import Sidebar from './components/sidebar/Sidebar'; import Notebook from './components/notebook/Notebook'; import HistoryServer from './components/HistoryServer'; +import Scheduler from './components/Scheduler'; import { createTheme, ThemeProvider } from '@mui/material/styles'; import config from './config'; import NotebookModel from './models/NotebookModel'; @@ -34,6 +35,7 @@ const App = () => { const baseUrl = `${config.jupyterBaseUrl}/api/contents/` const [showHistoryServer, setShowHistoryServer] = useState(false); + const [showScheduler, setShowScheduler] = useState(false); const [showNotebook, setShowNotebook] = useState(false); const [notebook, setNotebook] = useState({}); @@ -80,6 +82,7 @@ const App = () => { NotebookModel.fetchNotebook(notebookPath).then((data) => { setNotebook(data); setShowHistoryServer(false); + setShowScheduler(false); setShowNotebook(true); }).catch((error) => { console.error('Failed to fetch newly created notebook:', error); @@ -97,6 +100,7 @@ const App = () => { console.log('Fetched notebook:', data); setNotebook(data); setShowHistoryServer(false); + setShowScheduler(false); setShowNotebook(true); }).catch((error) => { console.error('Failed to fetch notebook:', error); @@ -118,16 +122,29 @@ const App = () => { const handleHistoryServerClick = () => { if (handleUnsavedChanges()) { setShowNotebook(false); + setShowScheduler(false); setShowHistoryServer(true); } }; + // Scheduler + const handleSchedulerClick = () => { + console.log(config.airflowBaseUrl) + console.log('Scheduler clicked'); + if (handleUnsavedChanges()) { + setShowNotebook(false); + setShowHistoryServer(false); + setShowScheduler(true); + } + }; + return ( { setIsNotebookModified={setIsNotebookModified} handleDeleteNotebook={handleDeleteNotebook} /> + ); }; diff --git a/webapp/src/components/Scheduler.js b/webapp/src/components/Scheduler.js new file mode 100644 index 0000000..a18d7d0 --- /dev/null +++ b/webapp/src/components/Scheduler.js @@ -0,0 +1,20 @@ +import React from 'react'; +import config from '../config'; + +function Scheduler({ showScheduler }) { + return ( +
{/* Adjust marginLeft based on your sidebar width */} + {showScheduler && ( +