I am writing an application in Flask, which works really well except that WSGI is synchronous and blocking. I have one task in particular which calls out to a third party API and that task can take several minutes to complete. I would like to make that call (it's actually a series of calls) and let it run. while control is returned to Flask.
My view looks like:
#app.route('/render/<id>', methods=['POST'])
def render_script(id=None):
...
data = json.loads(request.data)
text_list = data.get('text_list')
final_file = audio_class.render_audio(data=text_list)
# do stuff
return Response(
mimetype='application/json',
status=200
)
Now, what I want to do is have the line
final_file = audio_class.render_audio()
run and provide a callback to be executed when the method returns, whilst Flask can continue to process requests. This is the only task which I need Flask to run asynchronously, and I would like some advice on how best to implement this.
I have looked at Twisted and Klein, but I'm not sure they are overkill, as maybe Threading would suffice. Or maybe Celery is a good choice for this?
I would use Celery to handle the asynchronous task for you. You'll need to install a broker to serve as your task queue (RabbitMQ and Redis are recommended).
app.py:
from flask import Flask
from celery import Celery
broker_url = 'amqp://guest#localhost' # Broker URL for RabbitMQ task queue
app = Flask(__name__)
celery = Celery(app.name, broker=broker_url)
celery.config_from_object('celeryconfig') # Your celery configurations in a celeryconfig.py
#celery.task(bind=True)
def some_long_task(self, x, y):
# Do some long task
...
#app.route('/render/<id>', methods=['POST'])
def render_script(id=None):
...
data = json.loads(request.data)
text_list = data.get('text_list')
final_file = audio_class.render_audio(data=text_list)
some_long_task.delay(x, y) # Call your async task and pass whatever necessary variables
return Response(
mimetype='application/json',
status=200
)
Run your Flask app, and start another process to run your celery worker.
$ celery worker -A app.celery --loglevel=debug
I would also refer to Miguel Gringberg's write up for a more in depth guide to using Celery with Flask.
Threading is another possible solution. Although the Celery based solution is better for applications at scale, if you are not expecting too much traffic on the endpoint in question, threading is a viable alternative.
This solution is based on Miguel Grinberg's PyCon 2016 Flask at Scale presentation, specifically slide 41 in his slide deck. His code is also available on github for those interested in the original source.
From a user perspective the code works as follows:
You make a call to the endpoint that performs the long running task.
This endpoint returns 202 Accepted with a link to check on the task status.
Calls to the status link returns 202 while the taks is still running, and returns 200 (and the result) when the task is complete.
To convert an api call to a background task, simply add the #async_api decorator.
Here is a fully contained example:
from flask import Flask, g, abort, current_app, request, url_for
from werkzeug.exceptions import HTTPException, InternalServerError
from flask_restful import Resource, Api
from datetime import datetime
from functools import wraps
import threading
import time
import uuid
tasks = {}
app = Flask(__name__)
api = Api(app)
#app.before_first_request
def before_first_request():
"""Start a background thread that cleans up old tasks."""
def clean_old_tasks():
"""
This function cleans up old tasks from our in-memory data structure.
"""
global tasks
while True:
# Only keep tasks that are running or that finished less than 5
# minutes ago.
five_min_ago = datetime.timestamp(datetime.utcnow()) - 5 * 60
tasks = {task_id: task for task_id, task in tasks.items()
if 'completion_timestamp' not in task or task['completion_timestamp'] > five_min_ago}
time.sleep(60)
if not current_app.config['TESTING']:
thread = threading.Thread(target=clean_old_tasks)
thread.start()
def async_api(wrapped_function):
#wraps(wrapped_function)
def new_function(*args, **kwargs):
def task_call(flask_app, environ):
# Create a request context similar to that of the original request
# so that the task can have access to flask.g, flask.request, etc.
with flask_app.request_context(environ):
try:
tasks[task_id]['return_value'] = wrapped_function(*args, **kwargs)
except HTTPException as e:
tasks[task_id]['return_value'] = current_app.handle_http_exception(e)
except Exception as e:
# The function raised an exception, so we set a 500 error
tasks[task_id]['return_value'] = InternalServerError()
if current_app.debug:
# We want to find out if something happened so reraise
raise
finally:
# We record the time of the response, to help in garbage
# collecting old tasks
tasks[task_id]['completion_timestamp'] = datetime.timestamp(datetime.utcnow())
# close the database session (if any)
# Assign an id to the asynchronous task
task_id = uuid.uuid4().hex
# Record the task, and then launch it
tasks[task_id] = {'task_thread': threading.Thread(
target=task_call, args=(current_app._get_current_object(),
request.environ))}
tasks[task_id]['task_thread'].start()
# Return a 202 response, with a link that the client can use to
# obtain task status
print(url_for('gettaskstatus', task_id=task_id))
return 'accepted', 202, {'Location': url_for('gettaskstatus', task_id=task_id)}
return new_function
class GetTaskStatus(Resource):
def get(self, task_id):
"""
Return status about an asynchronous task. If this request returns a 202
status code, it means that task hasn't finished yet. Else, the response
from the task is returned.
"""
task = tasks.get(task_id)
if task is None:
abort(404)
if 'return_value' not in task:
return '', 202, {'Location': url_for('gettaskstatus', task_id=task_id)}
return task['return_value']
class CatchAll(Resource):
#async_api
def get(self, path=''):
# perform some intensive processing
print("starting processing task, path: '%s'" % path)
time.sleep(10)
print("completed processing task, path: '%s'" % path)
return f'The answer is: {path}'
api.add_resource(CatchAll, '/<path:path>', '/')
api.add_resource(GetTaskStatus, '/status/<task_id>')
if __name__ == '__main__':
app.run(debug=True)
You can also try using multiprocessing.Process with daemon=True; the process.start() method does not block and you can return a response/status immediately to the caller while your expensive function executes in the background.
I experienced similar problem while working with falcon framework and using daemon process helped.
You'd need to do the following:
from multiprocessing import Process
#app.route('/render/<id>', methods=['POST'])
def render_script(id=None):
...
heavy_process = Process( # Create a daemonic process with heavy "my_func"
target=my_func,
daemon=True
)
heavy_process.start()
return Response(
mimetype='application/json',
status=200
)
# Define some heavy function
def my_func():
time.sleep(10)
print("Process finished")
You should get a response immediately and, after 10s you should see a printed message in the console.
NOTE: Keep in mind that daemonic processes are not allowed to spawn any child processes.
Flask 2.0
Flask 2.0 supports async routes now. You can use the httpx library and use the asyncio coroutines for that. You can change your code a bit like below
#app.route('/render/<id>', methods=['POST'])
async def render_script(id=None):
...
data = json.loads(request.data)
text_list = data.get('text_list')
final_file = await asyncio.gather(
audio_class.render_audio(data=text_list),
do_other_stuff_function()
)
# Just make sure that the coroutine should not having any blocking calls inside it.
return Response(
mimetype='application/json',
status=200
)
The above one is just a pseudo code, but you can checkout how asyncio works with flask 2.0 and for HTTP calls you can use httpx. And also make sure the coroutines are only doing some I/O tasks only.
If you are using redis, you can use Pubsub event to handle background tasks.
See more: https://redis.com/ebook/part-2-core-concepts/chapter-3-commands-in-redis/3-6-publishsubscribe/
Related
I have some code that needs to execute after Flask returns a response. I don't think it's complex enough to set up a task queue like Celery for it. The key requirement is that Flask must return the response to the client before running this function. It can't wait for the function to execute.
There are some existing questions about this, but none of the answers seem to address running a task after the response is sent to the client, they still execute synchronously and then the response is returned.
Python Flask sending response immediately
Need to execute a function after returning the response in Flask
Flask end response and continue processing
The long story short is that Flask does not provide any special capabilities to accomplish this. For simple one-off tasks, consider Python's multithreading as shown below. For more complex configurations, use a task queue like RQ or Celery.
Why?
It's important to understand the functions Flask provides and why they do not accomplish the intended goal. All of these are useful in other cases and are good reading, but don't help with background tasks.
Flask's after_request handler
Flask's after_request handler, as detailed in this pattern for deferred request callbacks and this snippet on attaching different functions per request, will pass the request to the callback function. The intended use case is to modify the request, such as to attach a cookie.
Thus the request will wait around for these handlers to finish executing because the expectation is that the request itself will change as a result.
Flask's teardown_request handler
This is similar to after_request, but teardown_request doesn't receive the request object. So that means it won't wait for the request, right?
This seems like the solution, as this answer to a similar Stack Overflow question suggests. And since Flask's documentation explains that teardown callbacks are independent of the actual request and do not receive the request context, you'd have good reason to believe this.
Unfortunately, teardown_request is still synchronous, it just happens at a later part of Flask's request handling when the request is no longer modifiable. Flask will still wait for teardown functions to complete before returning the response, as this list of Flask callbacks and errors dictates.
Flask's streaming responses
Flask can stream responses by passing a generator to Response(), as this Stack Overflow answer to a similar question suggests.
With streaming, the client does begin receiving the response before the request concludes. However, the request still runs synchronously, so the worker handling the request is busy until the stream is finished.
This Flask pattern for streaming includes some documentation on using stream_with_context(), which is necessary to include the request context.
So what's the solution?
Flask doesn't offer a solution to run functions in the background because this isn't Flask's responsibility.
In most cases, the best way to solve this problem is to use a task queue such as RQ or Celery. These manage tricky things like configuration, scheduling, and distributing workers for you.This is the most common answer to this type of question because it is the most correct, and forces you to set things up in a way where you consider context, etc. correctly.
If you need to run a function in the background and don't want to set up a queue to manage this, you can use Python's built in threading or multiprocessing to spawn a background worker.
You can't access request or others of Flask's thread locals from background tasks, since the request will not be active there. Instead, pass the data you need from the view to the background thread when you create it.
#app.route('/start_task')
def start_task():
def do_work(value):
# do something that takes a long time
import time
time.sleep(value)
thread = Thread(target=do_work, kwargs={'value': request.args.get('value', 20)})
thread.start()
return 'started'
Flask is a WSGI app and as a result it fundamentally cannot handle anything after the response. This is why no such handler exists, the WSGI app itself is responsible only for constructing the response iterator object to the WSGI server.
A WSGI server however (like gunicorn) can very easily provide this functionality, but tying the application to the server is a very bad idea for a number of reasons.
For this exact reason, WSGI provides a spec for Middleware, and Werkzeug provides a number of helpers to simplify common Middleware functionality. Among them is a ClosingIterator class which allows you to hook methods up to the close method of the response iterator which is executed after the request is closed.
Here's an example of a naive after_response implementation done as a Flask extension:
import traceback
from werkzeug.wsgi import ClosingIterator
class AfterResponse:
def __init__(self, app=None):
self.callbacks = []
if app:
self.init_app(app)
def __call__(self, callback):
self.callbacks.append(callback)
return callback
def init_app(self, app):
# install extension
app.after_response = self
# install middleware
app.wsgi_app = AfterResponseMiddleware(app.wsgi_app, self)
def flush(self):
for fn in self.callbacks:
try:
fn()
except Exception:
traceback.print_exc()
class AfterResponseMiddleware:
def __init__(self, application, after_response_ext):
self.application = application
self.after_response_ext = after_response_ext
def __call__(self, environ, after_response):
iterator = self.application(environ, after_response)
try:
return ClosingIterator(iterator, [self.after_response_ext.flush])
except Exception:
traceback.print_exc()
return iterator
You can use this extension like this:
import flask
app = flask.Flask("after_response")
AfterResponse(app)
#app.after_response
def say_hi():
print("hi")
#app.route("/")
def home():
return "Success!\n"
When you curl "/" you'll see the following in your logs:
127.0.0.1 - - [24/Jun/2018 19:30:48] "GET / HTTP/1.1" 200 -
hi
This solves the issue simply without introducing either threads (GIL??) or having to install and manage a task queue and client software.
Flask now supports (via Werkzeug) a call_on_close callback decorator on response objects. Here is how you use it:
#app.after_request
def response_processor(response):
# Prepare all the local variables you need since the request context
# will be gone in the callback function
#response.call_on_close
def process_after_request():
# Do whatever is necessary here
pass
return response
Advantages:
call_on_close sets up functions for being called after the response is returned, using the WSGI spec for the close method.
No threads, no background jobs, no complicated setup. It runs in the same thread without blocking the request from returning.
Disadvantages:
No request context or app context. You have to save the variables you need, to pass into the closure.
No local stack as all that is being torn down. You have to make your own app context if you need it.
Flask-SQLAlchemy will fail silently if you're attempting to write to the database (I haven't figured out why, but likely due to the context shutting down). (It works, but if you have an existing object, it must be added to the new session using session.add or session.merge; not a disadvantage!)
There are 3 ways to do this, all work:
1. Thread
#app.route('/inner')
def foo():
for i in range(10):
sleep(1)
print(i)
return
#app.route('/inner', methods=['POST'])
def run_jobs():
try:
thread = Thread(target=foo)
thread.start()
return render_template("index_inner.html", img_path=DIR_OF_PHOTOS, video_path=UPLOAD_VIDEOS_FOLDER)
2. AfterResponse decorator
app = Flask(__name__)
AfterResponse(app)
#app.route('/inner', methods=['POST'])
def save_data():
pass
#app.after_response
def foo():
for i in range(10):
sleep(1)
print(i)
return
3. call_on_close
from time import sleep
from flask import Flask, Response, request
app = Flask('hello')
#app.route('/')
def hello():
response = Response('hello')
#response.call_on_close
def on_close():
for i in range(10):
sleep(1)
print(i)
return response
if __name__ == '__main__':
app.run()
Middleware Solution for Flask Blueprints
This is the same solution proposed by Matthew Story (which is the perfect solution IMHO - thanks Matthew), adapted for Flask Blueprints. The secret sauce here is to get hold of the app context using the current_app proxy. Read up here for more information (http://flask.pocoo.org/docs/1.0/appcontext/)
Let's assume the AfterThisResponse & AfterThisResponseMiddleware classes are placed in a module at .utils.after_this_response.py
Then where the Flask object creation occurs, you might have, eg...
__init__.py
from api.routes import my_blueprint
from .utils.after_this_response import AfterThisResponse
app = Flask( __name__ )
AfterThisResponse( app )
app.register_blueprint( my_blueprint.mod )
And then in your blueprint module...
a_blueprint.py
from flask import Blueprint, current_app
mod = Blueprint( 'a_blueprint', __name__, url_prefix=URL_PREFIX )
#mod.route( "/some_resource", methods=['GET', 'POST'] )
def some_resource():
# do some stuff here if you want
#current_app.after_this_response
def post_process():
# this will occur after you finish processing the route & return (below):
time.sleep(2)
print("after_response")
# do more stuff here if you like & then return like so:
return "Success!\n"
In addition to the other solutions, you can do route specific actions by combining after_this_request and response.call_on_close:
#app.route('/')
def index():
# Do your pre-response work here
msg = 'Hello World!'
#flask.after_this_request
def add_close_action(response):
#response.call_on_close
def process_after_request():
# Do your post-response work here
time.sleep(3.0)
print('Delayed: ' + msg)
return response
return msg
Thanks to Matthew Story and Paul Brackin, but I needed to change their proposals.
So the working solution is:
.
├── __init__.py
├── blueprint.py
└── library.py
# __init__.py
from flask import Flask
from .blueprint import bp
from .library import AfterResponse
app = Flask(__name__)
with app.app_context():
app.register_blueprint(bp, url_prefix='/')
AfterResponse(app)
# blueprint.py
from flask import Blueprint, request, current_app as app
from time import sleep
bp = Blueprint('app', __name__)
#bp.route('/')
def root():
body = request.json
#app.after_response
def worker():
print(body)
sleep(5)
print('finished_after_processing')
print('returned')
return 'finished_fast', 200
# library.py
from werkzeug.wsgi import ClosingIterator
from traceback import print_exc
class AfterResponse:
def __init__(self, application=None):
self.functions = list()
if application:
self.init_app(application)
def __call__(self, function):
self.functions.append(function)
def init_app(self, application):
application.after_response = self
application.wsgi_app = AfterResponseMiddleware(application.wsgi_app, self)
def flush(self):
while self.functions:
try:
self.functions.pop()()
except Exception:
print_exc()
class AfterResponseMiddleware:
def __init__(self, application, after_response_ext):
self.application = application
self.after_response_ext = after_response_ext
def __call__(self, environ, after_response):
iterator = self.application(environ, after_response)
try:
return ClosingIterator(iterator, [self.after_response_ext.flush])
except Exception:
print_exc()
return iterator
The source code can be found here
The signal request_finished receives a Response instance as parameter. Any after-processing can be done by connecting to that signal.
From https://flask-doc.readthedocs.io/en/latest/signals.html:
def log_response(sender, response, **extra):
sender.logger.debug('Request context is about to close down. '
'Response: %s', response)
from flask import request_finished
request_finished.connect(log_response, app)
Obs: In case of error, the signal got_request_exception can be used instead.
After read many topics.
I found the solution for me, if use Blueprint, it is worked for python 3.8 and SQLAlchemy
init.py
from flask import Flask
from flask_sqlalchemy import SQLAlchemy
from flask_login import LoginManager
import dir
import time
from flask_mail import Mail
from flask_cors import CORS
import flask_excel as excel
# init SQLAlchemy so we can use it later in our models
dbb = SQLAlchemy()
def create_app():
app = Flask(__name__)
from .bp_route_1 import auth as bp_route_1_blueprint
app.register_blueprint(bp_route_1_blueprint)
CORS(app)
return app
bp_route_1.py
from flask import Blueprint, request, redirect, Response, url_for, abort, flash, render_template, \
copy_current_request_context
from . import dbb
from .models import #Import Models
from threading import Thread
bp_route_1 = Blueprint('bp_route_1', __name__)
#bp_route_1.route('/wehooks', methods=['POST'])
def route_1_wehooks_post():
#copy_current_request_context #to copy request
def foo_main():
# insert your code here
do_long_time_webhook(request)
Thread(target=foo_main).start()
print("do Webhook by Thread")
return Response(status=200)
def do_long_time_webhook(request):
try:
data = request.get_data()
print(data)
#do long tim function for webhook data
except Exception as e:
print('Dont do webhook', e)
To expand upon Kiran's response, I've added the call_on_close decorator to the copy_current_request_context decorator along with their imports.
I can confirm this works as expected.
from flask import Response, copy_current_request_context
#app.route('/example-route')
def response():
# Prepare response
#response.call_on_close
#copy_current_request_context
def post_processing():
# Process after response
pass
return response
You can use this code i have tried it.It works.
this code will print the string "message". after the 3 second ,from the scheduling time. You can change the time your self according to you requirement.
import time, traceback
import threading
def every(delay,message, task):
next_time = time.time() + delay
time.sleep(max(0, next_time - time.time()))
task(message)
def foo(message):
print(message+" :foo", time.time())
def main(message):
threading.Thread(target=lambda: every(3,message, foo)).start()
main("message")
I am writing an application in Flask, which works really well except that WSGI is synchronous and blocking. I have one task in particular which calls out to a third party API and that task can take several minutes to complete. I would like to make that call (it's actually a series of calls) and let it run. while control is returned to Flask.
My view looks like:
#app.route('/render/<id>', methods=['POST'])
def render_script(id=None):
...
data = json.loads(request.data)
text_list = data.get('text_list')
final_file = audio_class.render_audio(data=text_list)
# do stuff
return Response(
mimetype='application/json',
status=200
)
Now, what I want to do is have the line
final_file = audio_class.render_audio()
run and provide a callback to be executed when the method returns, whilst Flask can continue to process requests. This is the only task which I need Flask to run asynchronously, and I would like some advice on how best to implement this.
I have looked at Twisted and Klein, but I'm not sure they are overkill, as maybe Threading would suffice. Or maybe Celery is a good choice for this?
I would use Celery to handle the asynchronous task for you. You'll need to install a broker to serve as your task queue (RabbitMQ and Redis are recommended).
app.py:
from flask import Flask
from celery import Celery
broker_url = 'amqp://guest#localhost' # Broker URL for RabbitMQ task queue
app = Flask(__name__)
celery = Celery(app.name, broker=broker_url)
celery.config_from_object('celeryconfig') # Your celery configurations in a celeryconfig.py
#celery.task(bind=True)
def some_long_task(self, x, y):
# Do some long task
...
#app.route('/render/<id>', methods=['POST'])
def render_script(id=None):
...
data = json.loads(request.data)
text_list = data.get('text_list')
final_file = audio_class.render_audio(data=text_list)
some_long_task.delay(x, y) # Call your async task and pass whatever necessary variables
return Response(
mimetype='application/json',
status=200
)
Run your Flask app, and start another process to run your celery worker.
$ celery worker -A app.celery --loglevel=debug
I would also refer to Miguel Gringberg's write up for a more in depth guide to using Celery with Flask.
Threading is another possible solution. Although the Celery based solution is better for applications at scale, if you are not expecting too much traffic on the endpoint in question, threading is a viable alternative.
This solution is based on Miguel Grinberg's PyCon 2016 Flask at Scale presentation, specifically slide 41 in his slide deck. His code is also available on github for those interested in the original source.
From a user perspective the code works as follows:
You make a call to the endpoint that performs the long running task.
This endpoint returns 202 Accepted with a link to check on the task status.
Calls to the status link returns 202 while the taks is still running, and returns 200 (and the result) when the task is complete.
To convert an api call to a background task, simply add the #async_api decorator.
Here is a fully contained example:
from flask import Flask, g, abort, current_app, request, url_for
from werkzeug.exceptions import HTTPException, InternalServerError
from flask_restful import Resource, Api
from datetime import datetime
from functools import wraps
import threading
import time
import uuid
tasks = {}
app = Flask(__name__)
api = Api(app)
#app.before_first_request
def before_first_request():
"""Start a background thread that cleans up old tasks."""
def clean_old_tasks():
"""
This function cleans up old tasks from our in-memory data structure.
"""
global tasks
while True:
# Only keep tasks that are running or that finished less than 5
# minutes ago.
five_min_ago = datetime.timestamp(datetime.utcnow()) - 5 * 60
tasks = {task_id: task for task_id, task in tasks.items()
if 'completion_timestamp' not in task or task['completion_timestamp'] > five_min_ago}
time.sleep(60)
if not current_app.config['TESTING']:
thread = threading.Thread(target=clean_old_tasks)
thread.start()
def async_api(wrapped_function):
#wraps(wrapped_function)
def new_function(*args, **kwargs):
def task_call(flask_app, environ):
# Create a request context similar to that of the original request
# so that the task can have access to flask.g, flask.request, etc.
with flask_app.request_context(environ):
try:
tasks[task_id]['return_value'] = wrapped_function(*args, **kwargs)
except HTTPException as e:
tasks[task_id]['return_value'] = current_app.handle_http_exception(e)
except Exception as e:
# The function raised an exception, so we set a 500 error
tasks[task_id]['return_value'] = InternalServerError()
if current_app.debug:
# We want to find out if something happened so reraise
raise
finally:
# We record the time of the response, to help in garbage
# collecting old tasks
tasks[task_id]['completion_timestamp'] = datetime.timestamp(datetime.utcnow())
# close the database session (if any)
# Assign an id to the asynchronous task
task_id = uuid.uuid4().hex
# Record the task, and then launch it
tasks[task_id] = {'task_thread': threading.Thread(
target=task_call, args=(current_app._get_current_object(),
request.environ))}
tasks[task_id]['task_thread'].start()
# Return a 202 response, with a link that the client can use to
# obtain task status
print(url_for('gettaskstatus', task_id=task_id))
return 'accepted', 202, {'Location': url_for('gettaskstatus', task_id=task_id)}
return new_function
class GetTaskStatus(Resource):
def get(self, task_id):
"""
Return status about an asynchronous task. If this request returns a 202
status code, it means that task hasn't finished yet. Else, the response
from the task is returned.
"""
task = tasks.get(task_id)
if task is None:
abort(404)
if 'return_value' not in task:
return '', 202, {'Location': url_for('gettaskstatus', task_id=task_id)}
return task['return_value']
class CatchAll(Resource):
#async_api
def get(self, path=''):
# perform some intensive processing
print("starting processing task, path: '%s'" % path)
time.sleep(10)
print("completed processing task, path: '%s'" % path)
return f'The answer is: {path}'
api.add_resource(CatchAll, '/<path:path>', '/')
api.add_resource(GetTaskStatus, '/status/<task_id>')
if __name__ == '__main__':
app.run(debug=True)
You can also try using multiprocessing.Process with daemon=True; the process.start() method does not block and you can return a response/status immediately to the caller while your expensive function executes in the background.
I experienced similar problem while working with falcon framework and using daemon process helped.
You'd need to do the following:
from multiprocessing import Process
#app.route('/render/<id>', methods=['POST'])
def render_script(id=None):
...
heavy_process = Process( # Create a daemonic process with heavy "my_func"
target=my_func,
daemon=True
)
heavy_process.start()
return Response(
mimetype='application/json',
status=200
)
# Define some heavy function
def my_func():
time.sleep(10)
print("Process finished")
You should get a response immediately and, after 10s you should see a printed message in the console.
NOTE: Keep in mind that daemonic processes are not allowed to spawn any child processes.
Flask 2.0
Flask 2.0 supports async routes now. You can use the httpx library and use the asyncio coroutines for that. You can change your code a bit like below
#app.route('/render/<id>', methods=['POST'])
async def render_script(id=None):
...
data = json.loads(request.data)
text_list = data.get('text_list')
final_file = await asyncio.gather(
audio_class.render_audio(data=text_list),
do_other_stuff_function()
)
# Just make sure that the coroutine should not having any blocking calls inside it.
return Response(
mimetype='application/json',
status=200
)
The above one is just a pseudo code, but you can checkout how asyncio works with flask 2.0 and for HTTP calls you can use httpx. And also make sure the coroutines are only doing some I/O tasks only.
If you are using redis, you can use Pubsub event to handle background tasks.
See more: https://redis.com/ebook/part-2-core-concepts/chapter-3-commands-in-redis/3-6-publishsubscribe/
I have some code that needs to execute after Flask returns a response. I don't think it's complex enough to set up a task queue like Celery for it. The key requirement is that Flask must return the response to the client before running this function. It can't wait for the function to execute.
There are some existing questions about this, but none of the answers seem to address running a task after the response is sent to the client, they still execute synchronously and then the response is returned.
Python Flask sending response immediately
Need to execute a function after returning the response in Flask
Flask end response and continue processing
The long story short is that Flask does not provide any special capabilities to accomplish this. For simple one-off tasks, consider Python's multithreading as shown below. For more complex configurations, use a task queue like RQ or Celery.
Why?
It's important to understand the functions Flask provides and why they do not accomplish the intended goal. All of these are useful in other cases and are good reading, but don't help with background tasks.
Flask's after_request handler
Flask's after_request handler, as detailed in this pattern for deferred request callbacks and this snippet on attaching different functions per request, will pass the request to the callback function. The intended use case is to modify the request, such as to attach a cookie.
Thus the request will wait around for these handlers to finish executing because the expectation is that the request itself will change as a result.
Flask's teardown_request handler
This is similar to after_request, but teardown_request doesn't receive the request object. So that means it won't wait for the request, right?
This seems like the solution, as this answer to a similar Stack Overflow question suggests. And since Flask's documentation explains that teardown callbacks are independent of the actual request and do not receive the request context, you'd have good reason to believe this.
Unfortunately, teardown_request is still synchronous, it just happens at a later part of Flask's request handling when the request is no longer modifiable. Flask will still wait for teardown functions to complete before returning the response, as this list of Flask callbacks and errors dictates.
Flask's streaming responses
Flask can stream responses by passing a generator to Response(), as this Stack Overflow answer to a similar question suggests.
With streaming, the client does begin receiving the response before the request concludes. However, the request still runs synchronously, so the worker handling the request is busy until the stream is finished.
This Flask pattern for streaming includes some documentation on using stream_with_context(), which is necessary to include the request context.
So what's the solution?
Flask doesn't offer a solution to run functions in the background because this isn't Flask's responsibility.
In most cases, the best way to solve this problem is to use a task queue such as RQ or Celery. These manage tricky things like configuration, scheduling, and distributing workers for you.This is the most common answer to this type of question because it is the most correct, and forces you to set things up in a way where you consider context, etc. correctly.
If you need to run a function in the background and don't want to set up a queue to manage this, you can use Python's built in threading or multiprocessing to spawn a background worker.
You can't access request or others of Flask's thread locals from background tasks, since the request will not be active there. Instead, pass the data you need from the view to the background thread when you create it.
#app.route('/start_task')
def start_task():
def do_work(value):
# do something that takes a long time
import time
time.sleep(value)
thread = Thread(target=do_work, kwargs={'value': request.args.get('value', 20)})
thread.start()
return 'started'
Flask is a WSGI app and as a result it fundamentally cannot handle anything after the response. This is why no such handler exists, the WSGI app itself is responsible only for constructing the response iterator object to the WSGI server.
A WSGI server however (like gunicorn) can very easily provide this functionality, but tying the application to the server is a very bad idea for a number of reasons.
For this exact reason, WSGI provides a spec for Middleware, and Werkzeug provides a number of helpers to simplify common Middleware functionality. Among them is a ClosingIterator class which allows you to hook methods up to the close method of the response iterator which is executed after the request is closed.
Here's an example of a naive after_response implementation done as a Flask extension:
import traceback
from werkzeug.wsgi import ClosingIterator
class AfterResponse:
def __init__(self, app=None):
self.callbacks = []
if app:
self.init_app(app)
def __call__(self, callback):
self.callbacks.append(callback)
return callback
def init_app(self, app):
# install extension
app.after_response = self
# install middleware
app.wsgi_app = AfterResponseMiddleware(app.wsgi_app, self)
def flush(self):
for fn in self.callbacks:
try:
fn()
except Exception:
traceback.print_exc()
class AfterResponseMiddleware:
def __init__(self, application, after_response_ext):
self.application = application
self.after_response_ext = after_response_ext
def __call__(self, environ, after_response):
iterator = self.application(environ, after_response)
try:
return ClosingIterator(iterator, [self.after_response_ext.flush])
except Exception:
traceback.print_exc()
return iterator
You can use this extension like this:
import flask
app = flask.Flask("after_response")
AfterResponse(app)
#app.after_response
def say_hi():
print("hi")
#app.route("/")
def home():
return "Success!\n"
When you curl "/" you'll see the following in your logs:
127.0.0.1 - - [24/Jun/2018 19:30:48] "GET / HTTP/1.1" 200 -
hi
This solves the issue simply without introducing either threads (GIL??) or having to install and manage a task queue and client software.
Flask now supports (via Werkzeug) a call_on_close callback decorator on response objects. Here is how you use it:
#app.after_request
def response_processor(response):
# Prepare all the local variables you need since the request context
# will be gone in the callback function
#response.call_on_close
def process_after_request():
# Do whatever is necessary here
pass
return response
Advantages:
call_on_close sets up functions for being called after the response is returned, using the WSGI spec for the close method.
No threads, no background jobs, no complicated setup. It runs in the same thread without blocking the request from returning.
Disadvantages:
No request context or app context. You have to save the variables you need, to pass into the closure.
No local stack as all that is being torn down. You have to make your own app context if you need it.
Flask-SQLAlchemy will fail silently if you're attempting to write to the database (I haven't figured out why, but likely due to the context shutting down). (It works, but if you have an existing object, it must be added to the new session using session.add or session.merge; not a disadvantage!)
There are 3 ways to do this, all work:
1. Thread
#app.route('/inner')
def foo():
for i in range(10):
sleep(1)
print(i)
return
#app.route('/inner', methods=['POST'])
def run_jobs():
try:
thread = Thread(target=foo)
thread.start()
return render_template("index_inner.html", img_path=DIR_OF_PHOTOS, video_path=UPLOAD_VIDEOS_FOLDER)
2. AfterResponse decorator
app = Flask(__name__)
AfterResponse(app)
#app.route('/inner', methods=['POST'])
def save_data():
pass
#app.after_response
def foo():
for i in range(10):
sleep(1)
print(i)
return
3. call_on_close
from time import sleep
from flask import Flask, Response, request
app = Flask('hello')
#app.route('/')
def hello():
response = Response('hello')
#response.call_on_close
def on_close():
for i in range(10):
sleep(1)
print(i)
return response
if __name__ == '__main__':
app.run()
Middleware Solution for Flask Blueprints
This is the same solution proposed by Matthew Story (which is the perfect solution IMHO - thanks Matthew), adapted for Flask Blueprints. The secret sauce here is to get hold of the app context using the current_app proxy. Read up here for more information (http://flask.pocoo.org/docs/1.0/appcontext/)
Let's assume the AfterThisResponse & AfterThisResponseMiddleware classes are placed in a module at .utils.after_this_response.py
Then where the Flask object creation occurs, you might have, eg...
__init__.py
from api.routes import my_blueprint
from .utils.after_this_response import AfterThisResponse
app = Flask( __name__ )
AfterThisResponse( app )
app.register_blueprint( my_blueprint.mod )
And then in your blueprint module...
a_blueprint.py
from flask import Blueprint, current_app
mod = Blueprint( 'a_blueprint', __name__, url_prefix=URL_PREFIX )
#mod.route( "/some_resource", methods=['GET', 'POST'] )
def some_resource():
# do some stuff here if you want
#current_app.after_this_response
def post_process():
# this will occur after you finish processing the route & return (below):
time.sleep(2)
print("after_response")
# do more stuff here if you like & then return like so:
return "Success!\n"
In addition to the other solutions, you can do route specific actions by combining after_this_request and response.call_on_close:
#app.route('/')
def index():
# Do your pre-response work here
msg = 'Hello World!'
#flask.after_this_request
def add_close_action(response):
#response.call_on_close
def process_after_request():
# Do your post-response work here
time.sleep(3.0)
print('Delayed: ' + msg)
return response
return msg
Thanks to Matthew Story and Paul Brackin, but I needed to change their proposals.
So the working solution is:
.
├── __init__.py
├── blueprint.py
└── library.py
# __init__.py
from flask import Flask
from .blueprint import bp
from .library import AfterResponse
app = Flask(__name__)
with app.app_context():
app.register_blueprint(bp, url_prefix='/')
AfterResponse(app)
# blueprint.py
from flask import Blueprint, request, current_app as app
from time import sleep
bp = Blueprint('app', __name__)
#bp.route('/')
def root():
body = request.json
#app.after_response
def worker():
print(body)
sleep(5)
print('finished_after_processing')
print('returned')
return 'finished_fast', 200
# library.py
from werkzeug.wsgi import ClosingIterator
from traceback import print_exc
class AfterResponse:
def __init__(self, application=None):
self.functions = list()
if application:
self.init_app(application)
def __call__(self, function):
self.functions.append(function)
def init_app(self, application):
application.after_response = self
application.wsgi_app = AfterResponseMiddleware(application.wsgi_app, self)
def flush(self):
while self.functions:
try:
self.functions.pop()()
except Exception:
print_exc()
class AfterResponseMiddleware:
def __init__(self, application, after_response_ext):
self.application = application
self.after_response_ext = after_response_ext
def __call__(self, environ, after_response):
iterator = self.application(environ, after_response)
try:
return ClosingIterator(iterator, [self.after_response_ext.flush])
except Exception:
print_exc()
return iterator
The source code can be found here
The signal request_finished receives a Response instance as parameter. Any after-processing can be done by connecting to that signal.
From https://flask-doc.readthedocs.io/en/latest/signals.html:
def log_response(sender, response, **extra):
sender.logger.debug('Request context is about to close down. '
'Response: %s', response)
from flask import request_finished
request_finished.connect(log_response, app)
Obs: In case of error, the signal got_request_exception can be used instead.
After read many topics.
I found the solution for me, if use Blueprint, it is worked for python 3.8 and SQLAlchemy
init.py
from flask import Flask
from flask_sqlalchemy import SQLAlchemy
from flask_login import LoginManager
import dir
import time
from flask_mail import Mail
from flask_cors import CORS
import flask_excel as excel
# init SQLAlchemy so we can use it later in our models
dbb = SQLAlchemy()
def create_app():
app = Flask(__name__)
from .bp_route_1 import auth as bp_route_1_blueprint
app.register_blueprint(bp_route_1_blueprint)
CORS(app)
return app
bp_route_1.py
from flask import Blueprint, request, redirect, Response, url_for, abort, flash, render_template, \
copy_current_request_context
from . import dbb
from .models import #Import Models
from threading import Thread
bp_route_1 = Blueprint('bp_route_1', __name__)
#bp_route_1.route('/wehooks', methods=['POST'])
def route_1_wehooks_post():
#copy_current_request_context #to copy request
def foo_main():
# insert your code here
do_long_time_webhook(request)
Thread(target=foo_main).start()
print("do Webhook by Thread")
return Response(status=200)
def do_long_time_webhook(request):
try:
data = request.get_data()
print(data)
#do long tim function for webhook data
except Exception as e:
print('Dont do webhook', e)
To expand upon Kiran's response, I've added the call_on_close decorator to the copy_current_request_context decorator along with their imports.
I can confirm this works as expected.
from flask import Response, copy_current_request_context
#app.route('/example-route')
def response():
# Prepare response
#response.call_on_close
#copy_current_request_context
def post_processing():
# Process after response
pass
return response
You can use this code i have tried it.It works.
this code will print the string "message". after the 3 second ,from the scheduling time. You can change the time your self according to you requirement.
import time, traceback
import threading
def every(delay,message, task):
next_time = time.time() + delay
time.sleep(max(0, next_time - time.time()))
task(message)
def foo(message):
print(message+" :foo", time.time())
def main(message):
threading.Thread(target=lambda: every(3,message, foo)).start()
main("message")
I have some code that needs to execute after Flask returns a response. I don't think it's complex enough to set up a task queue like Celery for it. The key requirement is that Flask must return the response to the client before running this function. It can't wait for the function to execute.
There are some existing questions about this, but none of the answers seem to address running a task after the response is sent to the client, they still execute synchronously and then the response is returned.
Python Flask sending response immediately
Need to execute a function after returning the response in Flask
Flask end response and continue processing
The long story short is that Flask does not provide any special capabilities to accomplish this. For simple one-off tasks, consider Python's multithreading as shown below. For more complex configurations, use a task queue like RQ or Celery.
Why?
It's important to understand the functions Flask provides and why they do not accomplish the intended goal. All of these are useful in other cases and are good reading, but don't help with background tasks.
Flask's after_request handler
Flask's after_request handler, as detailed in this pattern for deferred request callbacks and this snippet on attaching different functions per request, will pass the request to the callback function. The intended use case is to modify the request, such as to attach a cookie.
Thus the request will wait around for these handlers to finish executing because the expectation is that the request itself will change as a result.
Flask's teardown_request handler
This is similar to after_request, but teardown_request doesn't receive the request object. So that means it won't wait for the request, right?
This seems like the solution, as this answer to a similar Stack Overflow question suggests. And since Flask's documentation explains that teardown callbacks are independent of the actual request and do not receive the request context, you'd have good reason to believe this.
Unfortunately, teardown_request is still synchronous, it just happens at a later part of Flask's request handling when the request is no longer modifiable. Flask will still wait for teardown functions to complete before returning the response, as this list of Flask callbacks and errors dictates.
Flask's streaming responses
Flask can stream responses by passing a generator to Response(), as this Stack Overflow answer to a similar question suggests.
With streaming, the client does begin receiving the response before the request concludes. However, the request still runs synchronously, so the worker handling the request is busy until the stream is finished.
This Flask pattern for streaming includes some documentation on using stream_with_context(), which is necessary to include the request context.
So what's the solution?
Flask doesn't offer a solution to run functions in the background because this isn't Flask's responsibility.
In most cases, the best way to solve this problem is to use a task queue such as RQ or Celery. These manage tricky things like configuration, scheduling, and distributing workers for you.This is the most common answer to this type of question because it is the most correct, and forces you to set things up in a way where you consider context, etc. correctly.
If you need to run a function in the background and don't want to set up a queue to manage this, you can use Python's built in threading or multiprocessing to spawn a background worker.
You can't access request or others of Flask's thread locals from background tasks, since the request will not be active there. Instead, pass the data you need from the view to the background thread when you create it.
#app.route('/start_task')
def start_task():
def do_work(value):
# do something that takes a long time
import time
time.sleep(value)
thread = Thread(target=do_work, kwargs={'value': request.args.get('value', 20)})
thread.start()
return 'started'
Flask is a WSGI app and as a result it fundamentally cannot handle anything after the response. This is why no such handler exists, the WSGI app itself is responsible only for constructing the response iterator object to the WSGI server.
A WSGI server however (like gunicorn) can very easily provide this functionality, but tying the application to the server is a very bad idea for a number of reasons.
For this exact reason, WSGI provides a spec for Middleware, and Werkzeug provides a number of helpers to simplify common Middleware functionality. Among them is a ClosingIterator class which allows you to hook methods up to the close method of the response iterator which is executed after the request is closed.
Here's an example of a naive after_response implementation done as a Flask extension:
import traceback
from werkzeug.wsgi import ClosingIterator
class AfterResponse:
def __init__(self, app=None):
self.callbacks = []
if app:
self.init_app(app)
def __call__(self, callback):
self.callbacks.append(callback)
return callback
def init_app(self, app):
# install extension
app.after_response = self
# install middleware
app.wsgi_app = AfterResponseMiddleware(app.wsgi_app, self)
def flush(self):
for fn in self.callbacks:
try:
fn()
except Exception:
traceback.print_exc()
class AfterResponseMiddleware:
def __init__(self, application, after_response_ext):
self.application = application
self.after_response_ext = after_response_ext
def __call__(self, environ, after_response):
iterator = self.application(environ, after_response)
try:
return ClosingIterator(iterator, [self.after_response_ext.flush])
except Exception:
traceback.print_exc()
return iterator
You can use this extension like this:
import flask
app = flask.Flask("after_response")
AfterResponse(app)
#app.after_response
def say_hi():
print("hi")
#app.route("/")
def home():
return "Success!\n"
When you curl "/" you'll see the following in your logs:
127.0.0.1 - - [24/Jun/2018 19:30:48] "GET / HTTP/1.1" 200 -
hi
This solves the issue simply without introducing either threads (GIL??) or having to install and manage a task queue and client software.
Flask now supports (via Werkzeug) a call_on_close callback decorator on response objects. Here is how you use it:
#app.after_request
def response_processor(response):
# Prepare all the local variables you need since the request context
# will be gone in the callback function
#response.call_on_close
def process_after_request():
# Do whatever is necessary here
pass
return response
Advantages:
call_on_close sets up functions for being called after the response is returned, using the WSGI spec for the close method.
No threads, no background jobs, no complicated setup. It runs in the same thread without blocking the request from returning.
Disadvantages:
No request context or app context. You have to save the variables you need, to pass into the closure.
No local stack as all that is being torn down. You have to make your own app context if you need it.
Flask-SQLAlchemy will fail silently if you're attempting to write to the database (I haven't figured out why, but likely due to the context shutting down). (It works, but if you have an existing object, it must be added to the new session using session.add or session.merge; not a disadvantage!)
There are 3 ways to do this, all work:
1. Thread
#app.route('/inner')
def foo():
for i in range(10):
sleep(1)
print(i)
return
#app.route('/inner', methods=['POST'])
def run_jobs():
try:
thread = Thread(target=foo)
thread.start()
return render_template("index_inner.html", img_path=DIR_OF_PHOTOS, video_path=UPLOAD_VIDEOS_FOLDER)
2. AfterResponse decorator
app = Flask(__name__)
AfterResponse(app)
#app.route('/inner', methods=['POST'])
def save_data():
pass
#app.after_response
def foo():
for i in range(10):
sleep(1)
print(i)
return
3. call_on_close
from time import sleep
from flask import Flask, Response, request
app = Flask('hello')
#app.route('/')
def hello():
response = Response('hello')
#response.call_on_close
def on_close():
for i in range(10):
sleep(1)
print(i)
return response
if __name__ == '__main__':
app.run()
Middleware Solution for Flask Blueprints
This is the same solution proposed by Matthew Story (which is the perfect solution IMHO - thanks Matthew), adapted for Flask Blueprints. The secret sauce here is to get hold of the app context using the current_app proxy. Read up here for more information (http://flask.pocoo.org/docs/1.0/appcontext/)
Let's assume the AfterThisResponse & AfterThisResponseMiddleware classes are placed in a module at .utils.after_this_response.py
Then where the Flask object creation occurs, you might have, eg...
__init__.py
from api.routes import my_blueprint
from .utils.after_this_response import AfterThisResponse
app = Flask( __name__ )
AfterThisResponse( app )
app.register_blueprint( my_blueprint.mod )
And then in your blueprint module...
a_blueprint.py
from flask import Blueprint, current_app
mod = Blueprint( 'a_blueprint', __name__, url_prefix=URL_PREFIX )
#mod.route( "/some_resource", methods=['GET', 'POST'] )
def some_resource():
# do some stuff here if you want
#current_app.after_this_response
def post_process():
# this will occur after you finish processing the route & return (below):
time.sleep(2)
print("after_response")
# do more stuff here if you like & then return like so:
return "Success!\n"
In addition to the other solutions, you can do route specific actions by combining after_this_request and response.call_on_close:
#app.route('/')
def index():
# Do your pre-response work here
msg = 'Hello World!'
#flask.after_this_request
def add_close_action(response):
#response.call_on_close
def process_after_request():
# Do your post-response work here
time.sleep(3.0)
print('Delayed: ' + msg)
return response
return msg
Thanks to Matthew Story and Paul Brackin, but I needed to change their proposals.
So the working solution is:
.
├── __init__.py
├── blueprint.py
└── library.py
# __init__.py
from flask import Flask
from .blueprint import bp
from .library import AfterResponse
app = Flask(__name__)
with app.app_context():
app.register_blueprint(bp, url_prefix='/')
AfterResponse(app)
# blueprint.py
from flask import Blueprint, request, current_app as app
from time import sleep
bp = Blueprint('app', __name__)
#bp.route('/')
def root():
body = request.json
#app.after_response
def worker():
print(body)
sleep(5)
print('finished_after_processing')
print('returned')
return 'finished_fast', 200
# library.py
from werkzeug.wsgi import ClosingIterator
from traceback import print_exc
class AfterResponse:
def __init__(self, application=None):
self.functions = list()
if application:
self.init_app(application)
def __call__(self, function):
self.functions.append(function)
def init_app(self, application):
application.after_response = self
application.wsgi_app = AfterResponseMiddleware(application.wsgi_app, self)
def flush(self):
while self.functions:
try:
self.functions.pop()()
except Exception:
print_exc()
class AfterResponseMiddleware:
def __init__(self, application, after_response_ext):
self.application = application
self.after_response_ext = after_response_ext
def __call__(self, environ, after_response):
iterator = self.application(environ, after_response)
try:
return ClosingIterator(iterator, [self.after_response_ext.flush])
except Exception:
print_exc()
return iterator
The source code can be found here
The signal request_finished receives a Response instance as parameter. Any after-processing can be done by connecting to that signal.
From https://flask-doc.readthedocs.io/en/latest/signals.html:
def log_response(sender, response, **extra):
sender.logger.debug('Request context is about to close down. '
'Response: %s', response)
from flask import request_finished
request_finished.connect(log_response, app)
Obs: In case of error, the signal got_request_exception can be used instead.
After read many topics.
I found the solution for me, if use Blueprint, it is worked for python 3.8 and SQLAlchemy
init.py
from flask import Flask
from flask_sqlalchemy import SQLAlchemy
from flask_login import LoginManager
import dir
import time
from flask_mail import Mail
from flask_cors import CORS
import flask_excel as excel
# init SQLAlchemy so we can use it later in our models
dbb = SQLAlchemy()
def create_app():
app = Flask(__name__)
from .bp_route_1 import auth as bp_route_1_blueprint
app.register_blueprint(bp_route_1_blueprint)
CORS(app)
return app
bp_route_1.py
from flask import Blueprint, request, redirect, Response, url_for, abort, flash, render_template, \
copy_current_request_context
from . import dbb
from .models import #Import Models
from threading import Thread
bp_route_1 = Blueprint('bp_route_1', __name__)
#bp_route_1.route('/wehooks', methods=['POST'])
def route_1_wehooks_post():
#copy_current_request_context #to copy request
def foo_main():
# insert your code here
do_long_time_webhook(request)
Thread(target=foo_main).start()
print("do Webhook by Thread")
return Response(status=200)
def do_long_time_webhook(request):
try:
data = request.get_data()
print(data)
#do long tim function for webhook data
except Exception as e:
print('Dont do webhook', e)
To expand upon Kiran's response, I've added the call_on_close decorator to the copy_current_request_context decorator along with their imports.
I can confirm this works as expected.
from flask import Response, copy_current_request_context
#app.route('/example-route')
def response():
# Prepare response
#response.call_on_close
#copy_current_request_context
def post_processing():
# Process after response
pass
return response
You can use this code i have tried it.It works.
this code will print the string "message". after the 3 second ,from the scheduling time. You can change the time your self according to you requirement.
import time, traceback
import threading
def every(delay,message, task):
next_time = time.time() + delay
time.sleep(max(0, next_time - time.time()))
task(message)
def foo(message):
print(message+" :foo", time.time())
def main(message):
threading.Thread(target=lambda: every(3,message, foo)).start()
main("message")
I am writing a web application which would do some heavy work. With that in mind I thought of making the tasks as background tasks(non blocking) so that other requests are not blocked by the previous ones.
I went with demonizing the thread so that it doesn't exit once the main thread (since I am using threaded=True) is finished, Now if a user sends a request my code will immediately tell them that their request is in progress, it'll be running in the background, and the application is ready to serve other requests.
My current application code looks something like this:
from flask import Flask
from flask import request
import threading
class threadClass:
def __init__(self):
thread = threading.Thread(target=self.run, args=())
thread.daemon = True # Daemonize thread
thread.start() # Start the execution
def run(self):
#
# This might take several minutes to complete
someHeavyFunction()
app = Flask(__name__)
#app.route('/start', methods=['POST'])
try:
begin = threadClass()
except:
abort(500)
return "Task is in progress"
def main():
"""
Main entry point into program execution
PARAMETERS: none
"""
app.run(host='0.0.0.0',threaded=True)
main()
I just want it to be able to handle a few concurrent requests (it's not gonna be used in production)
Could I have done this better? Did I miss anything? I was going through python's multi-threading package and found this
multiprocessing is a package that supports spawning processes using an
API similar to the threading module. The multiprocessing package
offers both local and remote concurrency, effectively side-stepping
the Global Interpreter Lock by using subprocesses instead of threads.
Due to this, the multiprocessing module allows the programmer to fully
leverage multiple processors on a given machine. It runs on both Unix
and Windows.
Can I demonize a process using multi-processing? How can I achieve better than what I have with threading module?
##EDIT
I went through the multi-processing package of python, it is similar to threading.
from flask import Flask
from flask import request
from multiprocessing import Process
class processClass:
def __init__(self):
p = Process(target=self.run, args=())
p.daemon = True # Daemonize it
p.start() # Start the execution
def run(self):
#
# This might take several minutes to complete
someHeavyFunction()
app = Flask(__name__)
#app.route('/start', methods=['POST'])
try:
begin = processClass()
except:
abort(500)
return "Task is in progress"
def main():
"""
Main entry point into program execution
PARAMETERS: none
"""
app.run(host='0.0.0.0',threaded=True)
main()
Does the above approach looks good?
Best practice
The best way to implement background tasks in flask is with Celery as explained in this SO post. A good starting point is the official Flask documentation and the Celery documentation.
Crazy way: Build your own decorator
As #MrLeeh pointed out in a comment, Miguel Grinberg presented a solution in his Pycon 2016 talk by implementing a decorator. I want to emphasize that I have the highest respect for his solution; he called it a "crazy solution" himself. The below code is a minor adaptation of his solution.
Warning!!!
Don't use this in production! The main reason is that this app has a memory leak by using the global tasks dictionary. Even if you fix the memory leak issue, maintaining this sort of code is hard. If you just want to play around or use this in a private project, read on.
Minimal example
Assume you have a long running function call in your /foo endpoint. I mock this with a 10 second sleep timer. If you call the enpoint three times, it will take 30 seconds to finish.
Miguel Grinbergs decorator solution is implemented in flask_async. It runs a new thread in a Flask context which is identical to the current Flask context. Each thread is issued a new task_id. The result is saved in a global dictionary tasks[task_id]['result'].
With the decorator in place you only need to decorate the endpoint with #flask_async and the endpoint is asynchronous - just like that!
import threading
import time
import uuid
from functools import wraps
from flask import Flask, current_app, request, abort
from werkzeug.exceptions import HTTPException, InternalServerError
app = Flask(__name__)
tasks = {}
def flask_async(f):
"""
This decorator transforms a sync route to asynchronous by running it in a background thread.
"""
#wraps(f)
def wrapped(*args, **kwargs):
def task(app, environ):
# Create a request context similar to that of the original request
with app.request_context(environ):
try:
# Run the route function and record the response
tasks[task_id]['result'] = f(*args, **kwargs)
except HTTPException as e:
tasks[task_id]['result'] = current_app.handle_http_exception(e)
except Exception as e:
# The function raised an exception, so we set a 500 error
tasks[task_id]['result'] = InternalServerError()
if current_app.debug:
# We want to find out if something happened so reraise
raise
# Assign an id to the asynchronous task
task_id = uuid.uuid4().hex
# Record the task, and then launch it
tasks[task_id] = {'task': threading.Thread(
target=task, args=(current_app._get_current_object(), request.environ))}
tasks[task_id]['task'].start()
# Return a 202 response, with an id that the client can use to obtain task status
return {'TaskId': task_id}, 202
return wrapped
#app.route('/foo')
#flask_async
def foo():
time.sleep(10)
return {'Result': True}
#app.route('/foo/<task_id>', methods=['GET'])
def foo_results(task_id):
"""
Return results of asynchronous task.
If this request returns a 202 status code, it means that task hasn't finished yet.
"""
task = tasks.get(task_id)
if task is None:
abort(404)
if 'result' not in task:
return {'TaskID': task_id}, 202
return task['result']
if __name__ == '__main__':
app.run(debug=True)
However, you need a little trick to get your results. The endpoint /foo will only return the HTTP code 202 and the task id, but not the result. You need another endpoint /foo/<task_id> to get the result. Here is an example for localhost:
import time
import requests
task_ids = [requests.get('http://127.0.0.1:5000/foo').json().get('TaskId')
for _ in range(2)]
time.sleep(11)
results = [requests.get(f'http://127.0.0.1:5000/foo/{task_id}').json()
for task_id in task_ids]
# [{'Result': True}, {'Result': True}]