diff --git a/config/airflow.cfg b/config/airflow.cfg new file mode 100644 index 0000000000000000000000000000000000000000..bbaed40f4a001703480ad33e8c26626fe8cc532b --- /dev/null +++ b/config/airflow.cfg @@ -0,0 +1,992 @@ +[core] +# The folder where your airflow pipelines live, most likely a +# subfolder in a code repository. This path must be absolute. +dags_folder = /opt/airflow/dags + +# The folder where airflow should store its log files +# This path must be absolute +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. +remote_logging = False + +# Users must supply an Airflow connection id that provides access to the storage +# location. +remote_log_conn_id = +remote_base_log_folder = +encrypt_s3_logs = False + +# Logging level +logging_level = INFO + +# Logging level for Flask-appbuilder UI +fab_logging_level = WARN + +# 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 +logging_config_class = + +# Flag to enable/disable Colored logs in Console +# Colour the logs when the controlling terminal is a TTY. +colored_console_log = True + +# Log format for when Colored logs is enabled +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 +colored_formatter_class = airflow.utils.log.colored_log.CustomTTYColoredFormatter + +# Format of Log line +log_format = [%%(asctime)s] {{%%(filename)s:%%(lineno)d}} %%(levelname)s - %%(message)s +simple_log_format = %%(asctime)s %%(levelname)s - %%(message)s + +# Log filename format +log_filename_template = {{ ti.dag_id }}/{{ ti.task_id }}/{{ ts }}/{{ try_number }}.log +log_processor_filename_template = {{ filename }}.log +dag_processor_manager_log_location = /opt/airflow/logs/dag_processor_manager/dag_processor_manager.log + +# Name of handler to read task instance logs. +# Default to use task handler. +task_log_reader = task + +# Hostname by providing a path to a callable, which will resolve the hostname. +# The format is "package:function". +# +# For example, default value "socket:getfqdn" means that result from getfqdn() of "socket" +# package will be used as hostname. +# +# 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`` +hostname_callable = socket:getfqdn + +# Default timezone in case supplied date times are naive +# can be utc (default), system, or any IANA timezone string (e.g. Europe/Amsterdam) +default_timezone = utc + +# The executor class that airflow should use. Choices include +# SequentialExecutor, LocalExecutor, CeleryExecutor, DaskExecutor, KubernetesExecutor +executor = SequentialExecutor + +# The SqlAlchemy connection string to the metadata database. +# SqlAlchemy supports many different database engine, more information +# their website +# sql_alchemy_conn = sqlite:////tmp/airflow.db + +# The encoding for the databases +sql_engine_encoding = utf-8 + +# If SqlAlchemy should pool database connections. +sql_alchemy_pool_enabled = True + +# The SqlAlchemy pool size is the maximum number of database connections +# in the pool. 0 indicates no limit. +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. +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. +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/13/core/pooling.html#disconnect-handling-pessimistic +sql_alchemy_pool_pre_ping = True + +# The schema to use for the metadata database. +# SqlAlchemy supports databases with the concept of multiple schemas. +sql_alchemy_schema = + +# The amount of parallelism as a setting to the executor. This defines +# the max number of task instances that should run simultaneously +# on this airflow installation +parallelism = 32 + +# The number of task instances allowed to run concurrently by the scheduler +dag_concurrency = 16 + +# Are DAGs paused by default at creation +dags_are_paused_at_creation = True + +# The maximum number of active DAG runs per DAG +max_active_runs_per_dag = 16 + +# Whether to load the examples that ship with Airflow. It's good to +# get started, but you probably want to set this to False in a production +# environment +load_examples = True + +# Where your Airflow plugins are stored +plugins_folder = /opt/airflow/plugins + +# Secret key to save connection passwords in the db +fernet_key = $FERNET_KEY + +# Whether to disable pickling dags +donot_pickle = False + +# How long before timing out a python file import +dagbag_import_timeout = 30 + +# How long before timing out a DagFileProcessor, which processes a dag file +dag_file_processor_timeout = 50 + +# The class to use for running task instances in a subprocess +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 +default_impersonation = + +# What security module to use (for example kerberos) +security = + +# If set to False enables some unsecure features like Charts and Ad Hoc Queries. +# In 2.0 will default to True. +secure_mode = False + +# Turn unit test mode on (overwrites many configuration options with test +# values at runtime) +unit_test_mode = False + +# Whether to enable pickling for xcom (note that this is insecure and allows for +# RCE exploits). This will be deprecated in Airflow 2.0 (be forced to False). +enable_xcom_pickling = True + +# 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 +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. +dag_run_conf_overrides_params = False + +# Worker initialisation check to validate Metadata Database connection +worker_precheck = False + +# When discovering DAGs, ignore any files that don't contain the strings ``DAG`` and ``airflow``. +dag_discovery_safe_mode = True + +# The number of retries each task is going to have by default. Can be overridden at dag or task level. +default_task_retries = 0 + +# Whether to serialises DAGs and persist them in DB. +# If set to True, Webserver reads from DB instead of parsing DAG files +# More details: https://airflow.apache.org/docs/stable/dag-serialization.html +store_serialized_dags = False + +# Updating serialized DAG can not be faster than a minimum interval to reduce database write rate. +min_serialized_dag_update_interval = 30 + +# On each dagrun check against defined SLAs +check_slas = True + +[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 +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/...`` +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. +fail_fast = False + +[api] +# How to authenticate users of the API +auth_backend = airflow.api.auth.backend.default + +[lineage] +# what lineage backend to use +backend = + +[atlas] +sasl_enabled = False +host = +port = 21000 +username = +password = + +[operators] +# The default owner assigned to each new operator, unless +# provided explicitly or passed via ``default_args`` +default_owner = airflow +default_cpus = 1 +default_ram = 512 +default_disk = 512 +default_gpus = 0 + +[hive] +# Default mapreduce queue for HiveOperator tasks +default_hive_mapred_queue = + +[webserver] +# The base url of your website as airflow cannot guess what domain or +# cname you are using. This is used in automated emails that +# airflow sends to point links to the right web server +base_url = http://localhost:8080 + +# The ip specified when starting the web server +web_server_host = 0.0.0.0 + +# The port on which to run the web server +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. +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. +web_server_ssl_key = + +# Number of seconds the webserver waits before killing gunicorn master that doesn't respond +web_server_master_timeout = 120 + +# Number of seconds the gunicorn webserver waits before timing out on a worker +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. +worker_refresh_batch_size = 1 + +# Number of seconds to wait before refreshing a batch of workers. +worker_refresh_interval = 30 + +# Secret key used to run your flask app +# It should be as random as possible +secret_key = temporary_key + +# Number of workers to run the Gunicorn web server +workers = 4 + +# The worker class gunicorn should use. Choices include +# sync (default), eventlet, gevent +worker_class = sync + +# Log files for the gunicorn webserver. '-' means log to stderr. +access_logfile = - + +# Log files for the gunicorn webserver. '-' means log to stderr. +error_logfile = - + +# Expose the configuration file in the web server +expose_config = True + +# Expose hostname in the web server +expose_hostname = True + +# Expose stacktrace in the web server +expose_stacktrace = True + +# Set to true to turn on authentication: +# https://airflow.apache.org/security.html#web-authentication +authenticate = False + +# Filter the list of dags by owner name (requires authentication to be enabled) +filter_by_owner = False + +# Filtering mode. Choices include user (default) and ldapgroup. +# Ldap group filtering requires using the ldap backend +# +# Note that the ldap server needs the "memberOf" overlay to be set up +# in order to user the ldapgroup mode. +owner_mode = user + +# Default DAG view. Valid values are: +# tree, graph, duration, gantt, landing_times +dag_default_view = tree + +# "Default DAG orientation. Valid values are:" +# LR (Left->Right), TB (Top->Bottom), RL (Right->Left), BT (Bottom->Top) +dag_orientation = LR + +# Puts the webserver in demonstration mode; blurs the names of Operators for +# privacy. +demo_mode = False + +# The amount of time (in secs) webserver will wait for initial handshake +# while fetching logs from other worker machine +log_fetch_timeout_sec = 5 + +# Time interval (in secs) to wait before next log fetching. +log_fetch_delay_sec = 2 + +# Distance away from page bottom to enable auto tailing. +log_auto_tailing_offset = 30 + +# Animation speed for auto tailing log display. +log_animation_speed = 1000 + +# By default, the webserver shows paused DAGs. Flip this to hide paused +# DAGs by default +hide_paused_dags_by_default = False + +# Consistent page size across all listing views in the UI +page_size = 100 + +# Use FAB-based webserver with RBAC feature +rbac = False + +# Define the color of navigation bar +navbar_color = #007A87 + +# Default dagrun to show in UI +default_dag_run_display_number = 25 + +# Enable werkzeug ``ProxyFix`` middleware for reverse proxy +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/ +proxy_fix_x_for = 1 + +# Number of values to trust for ``X-Forwarded-Proto`` +proxy_fix_x_proto = 1 + +# Number of values to trust for ``X-Forwarded-Host`` +proxy_fix_x_host = 1 + +# Number of values to trust for ``X-Forwarded-Port`` +proxy_fix_x_port = 1 + +# Number of values to trust for ``X-Forwarded-Prefix`` +proxy_fix_x_prefix = 1 + +# Set secure flag on session cookie +cookie_secure = False + +# Set samesite policy on session cookie +cookie_samesite = + +# Default setting for wrap toggle on DAG code and TI log views. +default_wrap = False + +# Allow the UI to be rendered in a frame +x_frame_enabled = True + +# Send anonymous user activity to your analytics tool +# choose from google_analytics, segment, or metarouter +# analytics_tool = + +# Unique ID of your account in the analytics tool +# analytics_id = + +# Update FAB permissions and sync security manager roles +# on webserver startup +update_fab_perms = True + +# Minutes of non-activity before logged out from UI +# 0 means never get forcibly logged out +force_log_out_after = 0 + +# The UI cookie lifetime in days +session_lifetime_days = 30 + +instance_name = "eFlows4HPC Pipelines" + +[email] +email_backend = airflow.utils.email.send_email_smtp + +[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 +smtp_host = localhost +smtp_starttls = True +smtp_ssl = False +# Example: smtp_user = airflow +# smtp_user = +# Example: smtp_password = airflow +# smtp_password = +smtp_port = 25 +smtp_mail_from = airflow@example.com + +[sentry] + +# Sentry (https://docs.sentry.io) integration +sentry_dsn = + +[celery] + +# This section only applies if you are using the CeleryExecutor in +# ``[core]`` section above +# The app name that will be used by celery +celery_app_name = airflow.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 +worker_concurrency = 16 + +# The maximum and minimum concurrency that will be used when starting workers with the +# ``airflow celery worker`` command (always keep minimum processes, but grow +# to maximum if necessary). Note the value should be max_concurrency,min_concurrency +# 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. +# http://docs.celeryproject.org/en/latest/reference/celery.bin.worker.html#cmdoption-celery-worker-autoscale +# Example: worker_autoscale = 16,12 +worker_autoscale = 16,12 + +# 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. +worker_log_server_port = 8793 + +# The Celery broker URL. Celery supports RabbitMQ, Redis and experimentally +# a sqlalchemy database. Refer to the Celery documentation for more +# information. +# http://docs.celeryproject.org/en/latest/userguide/configuration.html#broker-settings +broker_url = redis://redis:6379/1 + +# 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 +# http://docs.celeryproject.org/en/latest/userguide/configuration.html#task-result-backend-settings +result_backend = db+postgresql://airflow:airflow@postgres/airflow + +# Celery Flower is a sweet UI for Celery. Airflow has a shortcut to start +# it ``airflow flower``. This defines the IP that Celery Flower runs on +flower_host = 0.0.0.0 + +# The root URL for Flower +# Example: flower_url_prefix = /flower +flower_url_prefix = + +# This defines the port that Celery Flower runs on +flower_port = 5555 + +# Securing Flower with Basic Authentication +# Accepts user:password pairs separated by a comma +# Example: flower_basic_auth = user1:password1,user2:password2 +flower_basic_auth = + +# Default queue that tasks get assigned to and that worker listen on. +default_queue = default + +# How many processes CeleryExecutor uses to sync task state. +# 0 means to use max(1, number of cores - 1) processes. +sync_parallelism = 0 + +# Import path for celery configuration options +celery_config_options = airflow.config_templates.default_celery.DEFAULT_CELERY_CONFIG + +# In case of using SSL +ssl_active = False +ssl_key = +ssl_cert = +ssl_cacert = + +# Celery Pool implementation. +# Choices include: prefork (default), eventlet, gevent or solo. +# See: +# https://docs.celeryproject.org/en/latest/userguide/workers.html#concurrency +# https://docs.celeryproject.org/en/latest/userguide/concurrency/eventlet.html +pool = prefork + +# The number of seconds to wait before timing out ``send_task_to_executor`` or +# ``fetch_celery_task_state`` operations. +operation_timeout = 2 + +[celery_broker_transport_options] + +# This section is for specifying options which can be passed to the +# underlying celery broker transport. See: +# http://docs.celeryproject.org/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: +# http://docs.celeryproject.org/en/master/userguide/configuration.html#std:setting-broker_transport_options +# Example: visibility_timeout = 21600 +# visibility_timeout = + +[dask] + +# This section only applies if you are using the DaskExecutor in +# [core] section above +# The IP address and port of the Dask cluster's scheduler. +cluster_address = 127.0.0.1:8786 + +# TLS/ SSL settings to access a secured Dask scheduler. +tls_ca = +tls_cert = +tls_key = + +[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). +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). +scheduler_heartbeat_sec = 5 + +# After how much time should the scheduler terminate in seconds +# -1 indicates to run continuously (see also num_runs) +run_duration = -1 + +# The number of times to try to schedule each DAG file +# -1 indicates unlimited number +num_runs = -1 + +# The number of seconds to wait between consecutive DAG file processing +processor_poll_interval = 1 + +# after how much time (seconds) a new DAGs should be picked up from the filesystem +min_file_process_interval = 0 + +# How often (in seconds) to scan the DAGs directory for new files. Default to 5 minutes. +dag_dir_list_interval = 300 + +# How often should stats be printed to the logs. Setting to 0 will disable printing stats +print_stats_interval = 30 + +# 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 +scheduler_health_check_threshold = 30 +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. +scheduler_zombie_task_threshold = 300 + +# 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) +catchup_by_default = True + +# This changes the batch size of queries in the scheduling main loop. +# If this is too high, SQL query performance may be impacted by one +# or more of the following: +# - reversion to full table scan +# - complexity of query predicate +# - excessive locking +# Additionally, you may hit the maximum allowable query length for your db. +# Set this to 0 for no limit (not advised) +max_tis_per_query = 512 + +# Statsd (https://github.com/etsy/statsd) integration settings +statsd_on = False +statsd_host = localhost +statsd_port = 8125 +statsd_prefix = airflow + +# If you want to avoid send all the available metrics to StatsD, +# you can configure an allow list of prefixes to send only the metrics that +# start with the elements of the list (e.g: scheduler,executor,dagrun) +statsd_allow_list = + +# The scheduler can run multiple threads in parallel to schedule dags. +# This defines how many threads will run. +max_threads = 2 +authenticate = False + +# 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. +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 +allow_trigger_in_future = False + +[ldap] +# set this to ldaps://<your.ldap.server>:<port> +uri = +user_filter = objectClass=* +user_name_attr = uid +group_member_attr = memberOf +superuser_filter = +data_profiler_filter = +bind_user = cn=Manager,dc=example,dc=com +bind_password = insecure +basedn = dc=example,dc=com +cacert = /etc/ca/ldap_ca.crt +search_scope = LEVEL + +# This setting allows the use of LDAP servers that either return a +# broken schema, or do not return a schema. +ignore_malformed_schema = False + +[mesos] +# Mesos master address which MesosExecutor will connect to. +master = localhost:5050 + +# The framework name which Airflow scheduler will register itself as on mesos +framework_name = Airflow + +# Number of cpu cores required for running one task instance using +# 'airflow run <dag_id> <task_id> <execution_date> --local -p <pickle_id>' +# command on a mesos slave +task_cpu = 1 + +# Memory in MB required for running one task instance using +# 'airflow run <dag_id> <task_id> <execution_date> --local -p <pickle_id>' +# command on a mesos slave +task_memory = 256 + +# Enable framework checkpointing for mesos +# See http://mesos.apache.org/documentation/latest/slave-recovery/ +checkpoint = False + +# Failover timeout in milliseconds. +# When checkpointing is enabled and this option is set, Mesos waits +# until the configured timeout for +# the MesosExecutor framework to re-register after a failover. Mesos +# shuts down running tasks if the +# MesosExecutor framework fails to re-register within this timeframe. +# Example: failover_timeout = 604800 +# failover_timeout = + +# Enable framework authentication for mesos +# See http://mesos.apache.org/documentation/latest/configuration/ +authenticate = False + +# Mesos credentials, if authentication is enabled +# Example: default_principal = admin +# default_principal = +# Example: default_secret = admin +# default_secret = + +# Optional Docker Image to run on slave before running the command +# This image should be accessible from mesos slave i.e mesos slave +# should be able to pull this docker image before executing the command. +# Example: docker_image_slave = puckel/docker-airflow +# docker_image_slave = + +[kerberos] +ccache = /tmp/airflow_krb5_ccache + +# gets augmented with fqdn +principal = airflow +reinit_frequency = 3600 +kinit_path = kinit +keytab = airflow.keytab + +[github_enterprise] +api_rev = v3 + +[admin] +# UI to hide sensitive variable fields when set to True +hide_sensitive_variable_fields = True + +[elasticsearch] +# Elasticsearch host +host = + +# Format of the log_id, which is used to query for a given tasks logs +log_id_template = {{dag_id}}-{{task_id}}-{{execution_date}}-{{try_number}} + +# Used to mark the end of a log stream for a task +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: The code will prefix the https:// automatically, don't include that here. +frontend = + +# Write the task logs to the stdout of the worker, rather than the default files +write_stdout = False + +# Instead of the default log formatter, write the log lines as JSON +json_format = False + +# Log fields to also attach to the json output, if enabled +json_fields = asctime, filename, lineno, levelname, message + +[elasticsearch_configs] +use_ssl = False +verify_certs = True + +[kubernetes] +# The repository, tag and imagePullPolicy of the Kubernetes Image for the Worker to Run +worker_container_repository = +worker_container_tag = +worker_container_image_pull_policy = IfNotPresent + +# If True (default), worker pods will be deleted upon termination +delete_worker_pods = True + +# Number of Kubernetes Worker Pod creation calls per scheduler loop +worker_pods_creation_batch_size = 1 + +# The Kubernetes namespace where airflow workers should be created. Defaults to ``default`` +namespace = default + +# The name of the Kubernetes ConfigMap containing the Airflow Configuration (this file) +# Example: airflow_configmap = airflow-configmap +airflow_configmap = + +# The name of the Kubernetes ConfigMap containing ``airflow_local_settings.py`` file. +# +# For example: +# +# ``airflow_local_settings_configmap = "airflow-configmap"`` if you have the following ConfigMap. +# +# ``airflow-configmap.yaml``: +# +# .. code-block:: yaml +# +# --- +# apiVersion: v1 +# kind: ConfigMap +# metadata: +# name: airflow-configmap +# data: +# airflow_local_settings.py: | +# def pod_mutation_hook(pod): +# ... +# airflow.cfg: | +# ... +# Example: airflow_local_settings_configmap = airflow-configmap +airflow_local_settings_configmap = + +# For docker image already contains DAGs, this is set to ``True``, and the worker will +# search for dags in dags_folder, +# otherwise use git sync or dags volume claim to mount DAGs +dags_in_image = False + +# For either git sync or volume mounted DAGs, the worker will look in this subpath for DAGs +dags_volume_subpath = + +# For DAGs mounted via a volume claim (mutually exclusive with git-sync and host path) +dags_volume_claim = + +# For volume mounted logs, the worker will look in this subpath for logs +logs_volume_subpath = + +# A shared volume claim for the logs +logs_volume_claim = + +# For DAGs mounted via a hostPath volume (mutually exclusive with volume claim and git-sync) +# Useful in local environment, discouraged in production +dags_volume_host = + +# A hostPath volume for the logs +# Useful in local environment, discouraged in production +logs_volume_host = + +# A list of configMapsRefs to envFrom. If more than one configMap is +# specified, provide a comma separated list: configmap_a,configmap_b +env_from_configmap_ref = + +# A list of secretRefs to envFrom. If more than one secret is +# specified, provide a comma separated list: secret_a,secret_b +env_from_secret_ref = + +# Git credentials and repository for DAGs mounted via Git (mutually exclusive with volume claim) +git_repo = +git_branch = +git_subpath = + +# The specific rev or hash the git_sync init container will checkout +# This becomes GIT_SYNC_REV environment variable in the git_sync init container for worker pods +git_sync_rev = + +# Use git_user and git_password for user authentication or git_ssh_key_secret_name +# and git_ssh_key_secret_key for SSH authentication +git_user = +git_password = +git_sync_root = /git +git_sync_dest = repo + +# Mount point of the volume if git-sync is being used. +# i.e./opt/airflow/dags +git_dags_folder_mount_point = + +# To get Git-sync SSH authentication set up follow this format +# +# ``airflow-secrets.yaml``: +# +# .. code-block:: yaml +# +# --- +# apiVersion: v1 +# kind: Secret +# metadata: +# name: airflow-secrets +# data: +# # key needs to be gitSshKey +# gitSshKey: <base64_encoded_data> +# Example: git_ssh_key_secret_name = airflow-secrets +git_ssh_key_secret_name = + +# To get Git-sync SSH authentication set up follow this format +# +# ``airflow-configmap.yaml``: +# +# .. code-block:: yaml +# +# --- +# apiVersion: v1 +# kind: ConfigMap +# metadata: +# name: airflow-configmap +# data: +# known_hosts: | +# github.com ssh-rsa <...> +# airflow.cfg: | +# ... +# Example: git_ssh_known_hosts_configmap_name = airflow-configmap +git_ssh_known_hosts_configmap_name = + +# To give the git_sync init container credentials via a secret, create a secret +# with two fields: GIT_SYNC_USERNAME and GIT_SYNC_PASSWORD (example below) and +# add ``git_sync_credentials_secret = <secret_name>`` to your airflow config under the +# ``kubernetes`` section +# +# Secret Example: +# +# .. code-block:: yaml +# +# --- +# apiVersion: v1 +# kind: Secret +# metadata: +# name: git-credentials +# data: +# GIT_SYNC_USERNAME: <base64_encoded_git_username> +# GIT_SYNC_PASSWORD: <base64_encoded_git_password> +git_sync_credentials_secret = + +# For cloning DAGs from git repositories into volumes: https://github.com/kubernetes/git-sync +git_sync_container_repository = k8s.gcr.io/git-sync +git_sync_container_tag = v3.1.1 +git_sync_init_container_name = git-sync-clone +git_sync_run_as_user = 65533 + +# The name of the Kubernetes service account to be associated with airflow workers, if any. +# Service accounts are required for workers that require access to secrets or cluster resources. +# See the Kubernetes RBAC documentation for more: +# https://kubernetes.io/docs/admin/authorization/rbac/ +worker_service_account_name = + +# Any image pull secrets to be given to worker pods, If more than one secret is +# required, provide a comma separated list: secret_a,secret_b +image_pull_secrets = + +# GCP Service Account Keys to be provided to tasks run on Kubernetes Executors +# Should be supplied in the format: key-name-1:key-path-1,key-name-2:key-path-2 +gcp_service_account_keys = + +# 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. +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. +# cluster_context = +# config_file = + +# Affinity configuration as a single line formatted JSON object. +# See the affinity model for top-level key names (e.g. ``nodeAffinity``, etc.): +# https://kubernetes.io/docs/reference/generated/kubernetes-api/v1.12/#affinity-v1-core +affinity = + +# A list of toleration objects as a single line formatted JSON array +# See: +# https://kubernetes.io/docs/reference/generated/kubernetes-api/v1.12/#toleration-v1-core +tolerations = + +# 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/master/kubernetes/client/apis/core_v1_api.py +# Note that if no _request_timeout is specified, the kubernetes client will wait indefinitely +# for kubernetes api responses, which will cause the scheduler to hang. +# The timeout is specified as [connect timeout, read timeout] +kube_client_request_args = {{"_request_timeout" : [60,60] }} + +# Specifies the uid to run the first process of the worker pods containers as +run_as_user = + +# Specifies a gid to associate with all containers in the worker pods +# if using a git_ssh_key_secret_name use an fs_group +# that allows for the key to be read, e.g. 65533 +fs_group = + +[kubernetes_node_selectors] + +# The Key-value pairs to be given to worker pods. +# The worker pods will be scheduled to the nodes of the specified key-value pairs. +# Should be supplied in the format: key = value + +[kubernetes_annotations] + +# The Key-value annotations pairs to be given to worker pods. +# Should be supplied in the format: key = value + +[kubernetes_environment_variables] + +# The scheduler sets the following environment variables into your workers. You may define as +# many environment variables as needed and the kubernetes launcher will set them in the launched workers. +# Environment variables in this section are defined as follows +# ``<environment_variable_key> = <environment_variable_value>`` +# +# For example if you wanted to set an environment variable with value `prod` and key +# ``ENVIRONMENT`` you would follow the following format: +# ENVIRONMENT = prod +# +# Additionally you may override worker airflow settings with the ``AIRFLOW__<SECTION>__<KEY>`` +# formatting as supported by airflow normally. + +[kubernetes_secrets] + +# The scheduler mounts the following secrets into your workers as they are launched by the +# scheduler. You may define as many secrets as needed and the kubernetes launcher will parse the +# defined secrets and mount them as secret environment variables in the launched workers. +# Secrets in this section are defined as follows +# ``<environment_variable_mount> = <kubernetes_secret_object>=<kubernetes_secret_key>`` +# +# For example if you wanted to mount a kubernetes secret key named ``postgres_password`` from the +# kubernetes secret object ``airflow-secret`` as the environment variable ``POSTGRES_PASSWORD`` into +# your workers you would follow the following format: +# ``POSTGRES_PASSWORD = airflow-secret=postgres_credentials`` +# +# Additionally you may override worker airflow settings with the ``AIRFLOW__<SECTION>__<KEY>`` +# formatting as supported by airflow normally. + +[kubernetes_labels] + +# The Key-value pairs to be given to worker pods. +# The worker pods will be given these static labels, as well as some additional dynamic labels +# to identify the task. +# Should be supplied in the format: ``key = value`` diff --git a/dockers/docker-compose.yaml b/dockers/docker-compose.yaml index eee098e53fe651f4558b91d75199bb751a955c94..0c36e660776c05ca81e9313cfbfaf8525f3ba562 100644 --- a/dockers/docker-compose.yaml +++ b/dockers/docker-compose.yaml @@ -47,6 +47,8 @@ x-airflow-common: image: ${AIRFLOW_IMAGE_NAME:-apache/airflow:2.1.2} environment: &airflow-common-env + AIRFLOW_HOME: /opt/airflow + AIRFLOW__CORE_dags_folder: /opt/airflow/dags AIRFLOW__CORE__EXECUTOR: CeleryExecutor AIRFLOW__CORE__SQL_ALCHEMY_CONN: postgresql+psycopg2://airflow:airflow@postgres/airflow AIRFLOW__CELERY__RESULT_BACKEND: db+postgresql://airflow:airflow@postgres/airflow @@ -60,6 +62,7 @@ x-airflow-common: - ./dags:/opt/airflow/dags - ./logs:/opt/airflow/logs - ./plugins:/opt/airflow/plugins + - ./config/airflow.cfg:/opt/airflow/airflow.cfg user: "${AIRFLOW_UID:-50000}:${AIRFLOW_GID:-50000}" depends_on: redis: