added celeryexecutor docker-compose

Dockerfile

@@ -1,4 +1,4 @@
 FROM puckel/docker-airflow:1.10.3
 RUN pip install --user psycopg2-binary
-ENV AIRFLOW_HOME=/usr/local/airflow
 COPY ./airflow.cfg /usr/local/airflow/airflow.cfg
+# or ./airflow_celeryexecutor.cfg /usr/local/airflow/airflow.cfg if you need .cfg with CeleryExecutor

airflow_celeryexecutor.cfg

@@ -0,0 +1,594 @@
+[core]
+# The home folder for airflow, default is ~/airflow
+
+# The folder where your airflow pipelines live, most likely a
+# subfolder in a code repository
+# This path must be absolute
+dags_folder = /usr/local/airflow/dags
+
+# The folder where airflow should store its log files
+# This path must be absolute
+base_log_folder = /usr/local/airflow/logs
+
+# Airflow can store logs remotely in AWS S3, Google Cloud Storage or Elastic Search.
+# Users must supply an Airflow connection id that provides access to the storage
+# location. If remote_logging is set to true, see UPDATING.md for additional
+# configuration requirements.
+remote_logging = False
+remote_log_conn_id =
+remote_base_log_folder =
+encrypt_s3_logs = False
+
+# Logging level
+logging_level = INFO
+fab_logging_level = WARN
+
+# Logging class
+# Specify the class that will specify the logging configuration
+# This class has to be on the python classpath
+# logging_config_class = my.path.default_local_settings.LOGGING_CONFIG
+logging_config_class =
+
+# Log format
+# we need to escape the curly braces by adding an additional curly brace
+log_format = [%%(asctime)s] {%%(filename)s:%%(lineno)d} %%(levelname)s - %%(message)s
+simple_log_format = %%(asctime)s %%(levelname)s - %%(message)s
+
+# Log filename format
+# we need to escape the curly braces by adding an additional curly brace
+log_filename_template = {{ ti.dag_id }}/{{ ti.task_id }}/{{ ts }}/{{ try_number }}.log
+log_processor_filename_template = {{ filename }}.log
+
+# Hostname by providing a path to a callable, which will resolve the hostname
+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
+executor = CeleryExecutor
+
+# The SqlAlchemy connection string to the metadata database.
+# SqlAlchemy supports many different database engine, more information
+# their website
+sql_alchemy_conn = postgresql+psycopg2://airflow:airflow@postgres:5432/airflow
+
+# 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 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
+
+# How many seconds to retry re-establishing a DB connection after
+# disconnects. Setting this to 0 disables retries.
+sql_alchemy_reconnect_timeout = 300
+
+# 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
+
+# When not using pools, tasks are run in the "default pool",
+# whose size is guided by this config element
+non_pooled_task_slot_count = 128
+
+# 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 = False
+
+# Where your Airflow plugins are stored
+plugins_folder = /usr/local/airflow/plugins
+
+# Secret key to save connection passwords in the db
+fernet_key = cryptography_not_found_storing_passwords_in_plain_text
+
+# Whether to disable pickling dags
+donot_pickle = False
+
+# How long before timing out a python file import while filling the DagBag
+dagbag_import_timeout = 30
+
+# 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 = True
+
+# Turn unit test mode on (overwrites many configuration options with test
+# values at runtime)
+unit_test_mode = False
+
+# Name of handler to read task instance logs.
+# Default to use task handler.
+task_log_reader = task
+
+# 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 backfill -c` or
+# `airflow trigger_dag -c`, the key-value pairs will override the existing ones in params.
+dag_run_conf_overrides_params = False
+
+[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
+
+[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 =
+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
+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 = -
+error_logfile = -
+
+# Expose the configuration file in the web server
+expose_config = True
+
+# Set to true to turn on authentication:
+# https://airflow.incubator.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
+
+# 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
+
+
+[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
+# Uncomment and set the user/pass settings if you want to use SMTP AUTH
+# smtp_user = airflow
+# smtp_password = airflow
+smtp_port = 25
+smtp_mail_from = airflow@example.com
+
+
+[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 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
+
+# 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:6379/0
+
+# 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
+# http://docs.celeryproject.org/en/latest/userguide/configuration.html#task-result-backend-settings
+result_backend =  db+postgresql://airflow:airflow@postgres:5432/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 = flower
+
+# The root URL for Flower
+# Ex: flower_url_prefix = /flower
+flower_url_prefix =
+
+# This defines the port that Celery Flower runs on
+flower_port = 5555
+
+# Default queue that tasks get assigned to and that worker listen on.
+default_queue = default
+
+# 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_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
+
+visibility_timeout = 21600
+
+[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
+
+# after how much time a new DAGs should be picked up from the filesystem
+min_file_process_interval = 0
+
+# How many seconds to wait between file-parsing loops to prevent the logs from being spammed.
+min_file_parsing_loop_time = 1
+
+dag_dir_list_interval = 300
+
+# How often should stats be printed to the logs
+print_stats_interval = 30
+
+child_process_log_directory = ~/airflow_tutorial/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
+
+# The scheduler can run multiple threads in parallel to schedule dags.
+# This defines how many threads will run.
+max_threads = 2
+
+authenticate = 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
+
+[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.
+# failover_timeout = 604800
+
+# Enable framework authentication for mesos
+# See http://mesos.apache.org/documentation/latest/configuration/
+authenticate = False
+
+# Mesos credentials, if authentication is enabled
+# default_principal = admin
+# default_secret = admin
+
+# 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.
+# docker_image_slave = puckel/docker-airflow
+
+[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 =
+# we need to escape the curly braces by adding an additional curly brace
+elasticsearch_log_id_template = {dag_id}-{task_id}-{execution_date}-{try_number}
+elasticsearch_end_of_log_mark = end_of_log
+
+[kubernetes]
+# The repository and tag of the Kubernetes Image for the Worker to Run
+worker_container_repository =
+worker_container_tag =
+
+# If True (default), worker pods will be deleted upon termination
+delete_worker_pods = True
+
+# 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)
+airflow_configmap =
+
+# 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 volume claim)
+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 =
+
+# Git credentials and repository for DAGs mounted via Git (mutually exclusive with volume claim)
+git_repo =
+git_branch =
+git_user =
+git_password =
+git_subpath =
+
+# For cloning DAGs from git repositories into volumes: https://github.com/kubernetes/git-sync
+git_sync_container_repository = gcr.io/google-containers/git-sync-amd64
+git_sync_container_tag = v2.0.5
+git_sync_init_container_name = git-sync-clone
+
+# 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
+
+[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.

docker-compose-celery-executor.yml

@@ -0,0 +1,99 @@
+version: "3"
+services:
+  postgres:
+    image: "postgres:9.6"
+    container_name: "postgres"
+    environment:
+      - POSTGRES_USER=airflow
+      - POSTGRES_PASSWORD=airflow
+      - POSTGRES_DB=airflow
+    ports:
+      - "5432:5432"
+    volumes:
+      - ./data/postgres:/var/lib/postgresql/data
+  webserver:
+    build: .
+    restart: always
+    depends_on:
+      - postgres
+    volumes:
+      - ./airflow/dags:/usr/local/airflow/dags
+    ports:
+      - "8080:8080"
+    entrypoint: airflow webserver
+    healthcheck:
+      test: ["CMD-SHELL", "[ -f /usr/local/airflow/airflow-webserver.pid ]"]
+      interval: 30s
+      timeout: 30s
+      retries: 3
+
+  scheduler:
+    build: .
+    restart: always
+    depends_on:
+      - postgres
+      - webserver
+    volumes:
+      - ./airflow/dags:/usr/local/airflow/dags
+    entrypoint: airflow scheduler
+    healthcheck:
+      test: ["CMD-SHELL", "[ -f /usr/local/airflow/airflow-scheduler.pid ]"]
+      interval: 30s
+      timeout: 30s
+      retries: 3
+  redis:
+    image: redis:5.0.5
+  worker_1:
+    build: .
+    restart: always
+    depends_on:
+      - postgres
+    volumes:
+      - ./airflow/dags:/usr/local/airflow/dags
+    entrypoint: airflow worker -cn worker_1
+    healthcheck:
+      test: ["CMD-SHELL", "[ -f /usr/local/airflow/airflow-worker.pid ]"]
+      interval: 30s
+      timeout: 30s
+      retries: 3
+  worker_2:
+    build: .
+    restart: always
+    depends_on:
+      - postgres
+    volumes:
+      - ./airflow/dags:/usr/local/airflow/dags
+    entrypoint: airflow worker -cn worker_2
+    healthcheck:
+      test: ["CMD-SHELL", "[ -f /usr/local/airflow/airflow-worker.pid ]"]
+      interval: 30s
+      timeout: 30s
+      retries: 3
+  worker_3:
+    build: .
+    restart: always
+    depends_on:
+      - postgres
+    volumes:
+      - ./airflow/dags:/usr/local/airflow/dags
+    entrypoint: airflow worker -cn worker_3
+    healthcheck:
+      test: ["CMD-SHELL", "[ -f /usr/local/airflow/airflow-worker.pid ]"]
+      interval: 30s
+      timeout: 30s
+      retries: 3
+  flower:
+    build: .
+    restart: always
+    depends_on:
+      - postgres
+    volumes:
+      - ./airflow/dags:/usr/local/airflow/dags
+    entrypoint: airflow flower
+    healthcheck:
+      test: ["CMD-SHELL", "[ -f /usr/local/airflow/airflow-flower.pid ]"]
+      interval: 30s
+      timeout: 30s
+      retries: 3
+    ports:
+      - "5555:5555"

docker-compose.yml

@@ -16,14 +16,11 @@ services:
     restart: always
     depends_on:
       - postgres
-    environment:
-      - LOAD_EX=n
-      - EXECUTOR=Local
     volumes:
       - ./airflow/dags:/usr/local/airflow/dags
     ports:
       - "8080:8080"
-    command: webserver
+    entrypoint: airflow webserver
     healthcheck:
       test: ["CMD-SHELL", "[ -f /usr/local/airflow/airflow-webserver.pid ]"]
       interval: 30s
@@ -34,9 +31,10 @@ services:
     restart: always
     depends_on:
       - postgres
+      - webserver
     volumes:
       - ./airflow/dags:/usr/local/airflow/dags
-    command: scheduler
+    entrypoint: airflow scheduler
     healthcheck:
       test: ["CMD-SHELL", "[ -f /usr/local/airflow/airflow-scheduler.pid ]"]
       interval: 30s