airflow-scheduler.conf

[program:airflow-scheduler]
process_name=%(program_name)s
directory=/home/airflow
environment=PATH="/usr/local/bin:/bin:/usr/bin:/usr/local/sbin:/usr/sbin:/sbin:$PATH",AIRFLOW_HOME=/home/airflow/airflow
command=/usr/local/bin/airflow scheduler
autostart=true
autorestart=true
user=airflow
redirect_stderr=true
stdout_logfile=/var/log/airflow/%(program_name)s.log
stdout_logfile_maxbytes=10MB
stdout_logfile_backups=5
stopasgroup=true

airflow-webserver.conf

[program:airflow-webserver]
process_name=%(program_name)s
directory=/home/airflow
environment=PATH="/usr/local/bin:/bin:/usr/bin:/usr/local/sbin:/usr/sbin:/sbin:$PATH",AIRFLOW_HOME=/home/airflow/airflow
command=/usr/local/bin/airflow webserver
autostart=true
autorestart=true
user=airflow
redirect_stderr=true
stdout_logfile=/var/log/airflow/%(program_name)s.log
stdout_logfile_maxbytes=10MB
stdout_logfile_backups=5
stopasgroup=true

airflow-worker.conf

[program:airflow-worker]
process_name=%(program_name)s
directory=/home/airflow
environment=PATH="/usr/local/bin:/bin:/usr/bin:/usr/local/sbin:/usr/sbin:/sbin:$PATH",AIRFLOW_HOME=/home/airflow/airflow
command=/usr/local/bin/airflow worker
autostart=true
autorestart=true
user=airflow
redirect_stderr=true
stdout_logfile=/var/log/airflow/%(program_name)s.log
stdout_logfile_maxbytes=10MB
stdout_logfile_backups=5
stopasgroup=true

airflow.cfg

[core]
# The home folder for airflow, default is ~/airflow
airflow_home = /home/airflow/airflow

# The folder where your airflow pipelines live, most likely a
# subfolder in a code repository
dags_folder = /home/airflow/airflow/dags

# The folder where airflow should store its log files. This location
base_log_folder = /home/airflow/airflow/logs
# An S3 location can be provided for log backups
# For S3, use the full URL to the base folder (starting with "s3://...")
s3_log_folder = None

# The executor class that airflow should use. Choices include
# SequentialExecutor, LocalExecutor, CeleryExecutor
executor = LocalExecutor
#executor = CeleryExecutor

# The SqlAlchemy connection string to the metadata database.
# SqlAlchemy supports many different database engine, more information
# their website
sql_alchemy_conn = sqlite:////home/airflow/airflow/airflow.db

# 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 = 8

# The number of task instances allowed to run concurrently by the scheduler
dag_concurrency = 4

# The maximum number of active DAG runs per DAG
max_active_runs_per_dag = 4

# 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 = /home/airflow/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

[webserver]
# The base url of your website as airflow cannot guess what domain or
# cname you are using. This is use 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

# Secret key used to run your flask app
secret_key = temporary_key

# Number of workers to run the Gunicorn web server
workers = 2

# The worker class gunicorn should use. Choices include
# sync (default), eventlet, gevent
worker_class = sync

# Expose the configuration file in the web server
expose_config = true

# Set to true to turn on authentication : http://pythonhosted.org/airflow/installation.html#web-authentication
authenticate = False

# Filter the list of dags by owner name (requires authentication to be enabled)
filter_by_owner = False

[smtp]
# If you want airflow to send emails on retries, failure, and you want to
# the airflow.utils.send_email function, you have to configure an smtp
# server here
smtp_host = localhost
smtp_starttls = True
smtp_user = airflow
smtp_port = 25
smtp_password = airflow
smtp_mail_from = [email protected]

[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
celeryd_concurrency = 4

# 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.
broker_url = sqla+mysql://airflow:airflow@localhost:3306/airflow

# Another key Celery setting
celery_result_backend = db+mysql://airflow:airflow@localhost:3306/airflow

# Celery Flower is a sweet UI for Celery. Airflow has a shortcut to start
# it `airflow flower`. 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

[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

# Statsd (https://github.com/etsy/statsd) integration settings
# statsd_on =  False
# statsd_host =  localhost
# statsd_port =  8125
# statsd_prefix = airflow

[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

init.d_supervisord

#!/bin/bash
#
# supervisord   This scripts turns supervisord on
#
# Author:       Mike McGrath <[email protected]> (based off yumupdatesd)
#               Jason Koppe <[email protected]> adjusted to read sysconfig,
#                   use supervisord tools to start/stop, conditionally wait
#                   for child processes to shutdown, and startup later
#
# chkconfig:    345 83 04
#
# description:  supervisor is a process control utility.  It has a web based
#               xmlrpc interface as well as a few other nifty features.
# processname:  supervisord
# config: /etc/supervisord.conf
# pidfile: /var/run/supervisord.pid
#

# Treat unset variables as error
#set -o nounset

# source function library
. /etc/rc.d/init.d/functions

# source system settings
[ -e /etc/sysconfig/supervisord ] && . /etc/sysconfig/supervisord

RETVAL=0

start() {
    echo "Starting supervisord: "
	if [ -e $PIDFILE ]; then 
		echo "ALREADY STARTED"
		return 1
	fi

	# start supervisord with options from sysconfig (stuff like -c)
    /usr/local/bin/supervisord $OPTIONS
	
	# show initial startup status
	/usr/local/bin/supervisorctl $OPTIONS status
	
	# only create the subsyslock if we created the PIDFILE
    [ -e $PIDFILE ] && touch /var/lock/subsys/supervisord
}

stop() {
    echo -n "Stopping supervisord: "
    /usr/local/bin/supervisorctl $OPTIONS shutdown
	if [ -n "$WAIT_FOR_SUBPROCESSES" ]; then 
        echo "Waiting roughly 60 seconds for $PIDFILE to be removed after child processes exit"
        for sleep in  2 2 2 2 4 4 4 4 8 8 8 8 last; do
            if [ ! -e $PIDFILE ] ; then
                echo "Supervisord exited as expected in under $total_sleep seconds"
                break
            else
                if [[ $sleep -eq "last" ]] ; then
                    echo "Supervisord still working on shutting down. We've waited roughly 60 seconds, we'll let it do its thing from here"
                    return 1
                else
                    sleep $sleep
                    total_sleep=$(( $total_sleep + $sleep ))
                fi

            fi
        done
    fi

    # always remove the subsys.  we might have waited a while, but just remove it at this point.
    rm -f /var/lock/subsys/supervisord
}

restart() {
        stop
        start
}

case "$1" in
    start)
        start
        RETVAL=$?
        ;;
    stop)
        stop
        RETVAL=$?
        ;;
    restart|force-reload)
        restart
        RETVAL=$?
        ;;
    reload)
        /usr/local/bin/supervisorctl $OPTIONS reload
        RETVAL=$?
        ;;
    condrestart)
        [ -f /var/lock/subsys/supervisord ] && restart
        RETVAL=$?
        ;;
    status)
        /usr/local/bin/supervisorctl $OPTIONS status
        RETVAL=$?
        ;;
    *)
        echo $"Usage: $0 {start|stop|status|restart|reload|force-reload|condrestart}"
        exit 1
esac

exit $RETVAL

supervisord.conf

; Sample supervisor config file.
;
; For more information on the config file, please see:
; http://supervisord.org/configuration.html
;
; Notes:
;  - Shell expansion ("~" or "$HOME") is not supported.  Environment
;    variables can be expanded using this syntax: "%(ENV_HOME)s".
;  - Comments must have a leading space: "a=b ;comment" not "a=b;comment".

[unix_http_server]
file=/tmp/supervisor.sock   ; (the path to the socket file)
;chmod=0700                 ; socket file mode (default 0700)
;chown=nobody:nogroup       ; socket file uid:gid owner
;username=user              ; (default is no username (open server))
;password=123               ; (default is no password (open server))

[inet_http_server]          ; inet (TCP) server disabled by default
port=*:9001                 ; (ip_address:port specifier, *:port for all iface)
;username=user              ; (default is no username (open server))
;password=123               ; (default is no password (open server))

[supervisord]
logfile=/var/log/supervisord.log ; (main log file;default $CWD/supervisord.log)
logfile_maxbytes=10MB            ; (max main logfile bytes b4 rotation;default 50MB)
logfile_backups=5                ; (num of main logfile rotation backups;default 10)
loglevel=info                    ; (log level;default info; others: debug,warn,trace)
pidfile=/var/run/supervisord.pid ; (supervisord pidfile;default supervisord.pid)
nodaemon=false                   ; (start in foreground if true;default false)
minfds=1024                      ; (min. avail startup file descriptors;default 1024)
minprocs=200                     ; (min. avail process descriptors;default 200)
;umask=022                       ; (process file creation umask;default 022)
;user=chrism                     ; (default is current user, required if root)
;identifier=supervisor           ; (supervisord identifier, default is 'supervisor')
;directory=/tmp                  ; (default is not to cd during start)
;nocleanup=true                  ; (don't clean up tempfiles at start;default false)
;childlogdir=/tmp                ; ('AUTO' child log dir, default $TEMP)
;environment=KEY="value"         ; (key value pairs to add to environment)
;strip_ansi=false                ; (strip ansi escape codes in logs; def. false)

; the below section must remain in the config file for RPC
; (supervisorctl/web interface) to work, additional interfaces may be
; added by defining them in separate rpcinterface: sections
[rpcinterface:supervisor]
supervisor.rpcinterface_factory = supervisor.rpcinterface:make_main_rpcinterface

[supervisorctl]
serverurl=unix:///tmp/supervisor.sock ; use a unix:// URL  for a unix socket
serverurl=http://127.0.0.1:9001       ; use an http:// url to specify an inet socket
;username=chris                       ; should be same as http_username if set
;password=123                         ; should be same as http_password if set
;prompt=mysupervisor                  ; cmd line prompt (default "supervisor")
;history_file=~/.sc_history           ; use readline history if available

; The below sample program section shows all possible program subsection values,
; create one or more 'real' program: sections to be able to control them under
; supervisor.

;[program:theprogramname]
;command=/bin/cat              ; the program (relative uses PATH, can take args)
;process_name=%(program_name)s ; process_name expr (default %(program_name)s)
;numprocs=1                    ; number of processes copies to start (def 1)
;directory=/tmp                ; directory to cwd to before exec (def no cwd)
;umask=022                     ; umask for process (default None)
;priority=999                  ; the relative start priority (default 999)
;autostart=true                ; start at supervisord start (default: true)
;startsecs=1                   ; # of secs prog must stay up to be running (def. 1)
;startretries=3                ; max # of serial start failures when starting (default 3)
;autorestart=unexpected        ; when to restart if exited after running (def: unexpected)
;exitcodes=0,2                 ; 'expected' exit codes used with autorestart (default 0,2)
;stopsignal=QUIT               ; signal used to kill process (default TERM)
;stopwaitsecs=10               ; max num secs to wait b4 SIGKILL (default 10)
;stopasgroup=false             ; send stop signal to the UNIX process group (default false)
;killasgroup=false             ; SIGKILL the UNIX process group (def false)
;user=chrism                   ; setuid to this UNIX account to run the program
;redirect_stderr=true          ; redirect proc stderr to stdout (default false)
;stdout_logfile=/a/path        ; stdout log path, NONE for none; default AUTO
;stdout_logfile_maxbytes=1MB   ; max # logfile bytes b4 rotation (default 50MB)
;stdout_logfile_backups=10     ; # of stdout logfile backups (default 10)
;stdout_capture_maxbytes=1MB   ; number of bytes in 'capturemode' (default 0)
;stdout_events_enabled=false   ; emit events on stdout writes (default false)
;stderr_logfile=/a/path        ; stderr log path, NONE for none; default AUTO
;stderr_logfile_maxbytes=1MB   ; max # logfile bytes b4 rotation (default 50MB)
;stderr_logfile_backups=10     ; # of stderr logfile backups (default 10)
;stderr_capture_maxbytes=1MB   ; number of bytes in 'capturemode' (default 0)
;stderr_events_enabled=false   ; emit events on stderr writes (default false)
;environment=A="1",B="2"       ; process environment additions (def no adds)
;serverurl=AUTO                ; override serverurl computation (childutils)

; The below sample eventlistener section shows all possible
; eventlistener subsection values, create one or more 'real'
; eventlistener: sections to be able to handle event notifications
; sent by supervisor.

;[eventlistener:theeventlistenername]
;command=/bin/eventlistener    ; the program (relative uses PATH, can take args)
;process_name=%(program_name)s ; process_name expr (default %(program_name)s)
;numprocs=1                    ; number of processes copies to start (def 1)
;events=EVENT                  ; event notif. types to subscribe to (req'd)
;buffer_size=10                ; event buffer queue size (default 10)
;directory=/tmp                ; directory to cwd to before exec (def no cwd)
;umask=022                     ; umask for process (default None)
;priority=-1                   ; the relative start priority (default -1)
;autostart=true                ; start at supervisord start (default: true)
;startsecs=1                   ; # of secs prog must stay up to be running (def. 1)
;startretries=3                ; max # of serial start failures when starting (default 3)
;autorestart=unexpected        ; autorestart if exited after running (def: unexpected)
;exitcodes=0,2                 ; 'expected' exit codes used with autorestart (default 0,2)
;stopsignal=QUIT               ; signal used to kill process (default TERM)
;stopwaitsecs=10               ; max num secs to wait b4 SIGKILL (default 10)
;stopasgroup=false             ; send stop signal to the UNIX process group (default false)
;killasgroup=false             ; SIGKILL the UNIX process group (def false)
;user=chrism                   ; setuid to this UNIX account to run the program
;redirect_stderr=false         ; redirect_stderr=true is not allowed for eventlisteners
;stdout_logfile=/a/path        ; stdout log path, NONE for none; default AUTO
;stdout_logfile_maxbytes=1MB   ; max # logfile bytes b4 rotation (default 50MB)
;stdout_logfile_backups=10     ; # of stdout logfile backups (default 10)
;stdout_events_enabled=false   ; emit events on stdout writes (default false)
;stderr_logfile=/a/path        ; stderr log path, NONE for none; default AUTO
;stderr_logfile_maxbytes=1MB   ; max # logfile bytes b4 rotation (default 50MB)
;stderr_logfile_backups=10     ; # of stderr logfile backups (default 10)
;stderr_events_enabled=false   ; emit events on stderr writes (default false)
;environment=A="1",B="2"       ; process environment additions
;serverurl=AUTO                ; override serverurl computation (childutils)

; The below sample group section shows all possible group values,
; create one or more 'real' group: sections to create "heterogeneous"
; process groups.

;[group:thegroupname]
;programs=progname1,progname2  ; each refers to 'x' in [program:x] definitions
;priority=999                  ; the relative start priority (default 999)

; The [include] section can just contain the "files" setting.  This
; setting can list multiple files (separated by whitespace or
; newlines).  It can also contain wildcards.  The filenames are
; interpreted as relative to this file.  Included files *cannot*
; include files themselves.

[include]
files=/etc/supervisord.d/*.conf

sysconfig_supervisord

# this is sourced by the supervisord init script
# written by jkoppe

set -a 

# should probably put both of these options as runtime arguments 
OPTIONS="-c /etc/supervisord.conf"
PIDFILE=/var/run/supervisord.pid

# unset this variable if you don't care to wait for child processes to shutdown before removing the /var/lock/subsys/supervisord lock
WAIT_FOR_SUBPROCESSES=yes

# remove this if you manage number of open files in some other fashion
ulimit -n 96000