I am coding for python >3.5.
I am using Websockets 6.0 library that is here:
https://github.com/aaugustin/websockets
I have been call them the asyncio Websockets since they are based on asyncio.
In my search there were a lot of "lost connections", but I am looking at how to cancel a current ws.recv().
A call to the .start() creates a helper thread to start the asynico event loop. Then the receive function start and calls the connect function and websocket ws is instanced. Then the receive functions works fall messages. When I am ready to stop, a .stop() is called. I was expecting the stop funciton to stop the awaited ws.recv(). Then with the keep_running flag set to false and running a ws.close(), I would expect the ws.recv() to end and the when keep_running loop to end. That is not what is happening. I see all three stops, but never the receive stop.
command is: stop
Do command is stopped
Stop 1
Stop 2
Stop 3
^CException ignored in: <module 'threading' from '/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/threading.py'>
Traceback (most recent call last):
File "/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/threading.py", line 1294, in _shutdown
t.join()
File "/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/threading.py", line 1056, in join
self._wait_for_tstate_lock()
File "/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/threading.py", line 1072, in _wait_for_tstate_lock
elif lock.acquire(block, timeout):
KeyboardInterrupt
(pyalmondplus) Pauls-MBP:pyalmondplus paulenright$
Code for reference:
import threading
import asyncio
import websockets
import json
class PyAlmondPlus:
def __init__(self, api_url, event_callback=None):
self.api_url = api_url
self.ws = None
self.loop = asyncio.get_event_loop()
self.receive_task = None
self.event_callback = event_callback
self.keep_running = False
async def connect(self):
print("connecting")
if self.ws is None:
print("opening socket")
self.ws = await websockets.connect(self.api_url)
print(self.ws)
async def disconnect(self):
pass
async def send(self, message):
pass
async def receive(self):
print("receive started")
while self.keep_running:
if self.ws is None:
await self.connect()
recv_data = await self.ws.recv()
print(recv_data)
print("receive ended")
def start(self):
self.keep_running = True
print("Start 1")
print("Start 2")
t = threading.Thread(target=self.start_loop, args=())
print("Start 3")
t.start()
print("Receiver running")
def start_loop(self):
print("Loop helper 1")
policy = asyncio.get_event_loop_policy()
policy.set_event_loop(policy.new_event_loop())
self.loop = asyncio.get_event_loop()
self.loop.set_debug(True)
asyncio.set_event_loop(self.loop)
self.loop.run_until_complete(self.receive())
print("Loop helper 2")
def stop(self):
print("Stop 1")
self.keep_running = False
print("Stop 2")
self.ws.close()
print("Stop 3")
I am looking at how to cancel a current ws.recv() [...] I see all three stops, but never the receive stop.
Your receive coroutine is likely suspended waiting for some data to arrive, so it's not in a position to check the keep_running flag.
The easy and robust way to stop a running coroutine is to cancel the asyncio Task that drives it. That will immediately un-suspend the coroutine and make whatever it was waiting for raise a CancelledError. When using cancel you don't need a keep_running flag at all, the exception will terminate the loop automatically.
A call to the .start() creates a helper thread to start the asynico event loop.
This works, but you don't really need a new thread and a whole new event loop for each instance of PyAlmondPlus. Asyncio is designed to run inside a single thread, so one event loop instance can host any number of coroutines.
Here is a possible design that implements both ideas (not tested with actual web sockets):
# pre-start a single thread that runs the asyncio event loop
bgloop = asyncio.new_event_loop()
_thread = threading.Thread(target=bgloop.run_forever)
_thread.daemon = True
_thread.start()
class PyAlmondPlus:
def __init__(self, api_url):
self.api_url = api_url
self.ws = None
async def connect(self):
if self.ws is None:
self.ws = await websockets.connect(self.api_url)
async def receive(self):
# keep_running is not needed - cancel the task instead
while True:
if self.ws is None:
await self.connect()
recv_data = await self.ws.recv()
async def init_receive_task(self):
self.receive_task = bgloop.create_task(self.receive())
def start(self):
# use run_coroutine_threadsafe to safely submit a coroutine
# to the event loop running in a different thread
init_done = asyncio.run_coroutine_threadsafe(
self.init_receive_task(), bgloop)
# wait for the init coroutine to actually finish
init_done.result()
def stop(self):
# Cancel the running task. Since the event loop is in a
# background thread, request cancellation with
# call_soon_threadsafe.
bgloop.call_soon_threadsafe(self.receive_task.cancel)
Related
I need an asynchronous parent process to handover function calls to a process pool.
The imports are to time consuming to spawn a new worker/process every time. So I thought to put tasks in an asyncio.queue and have a consumer listen to it and hand them off to the workers. (Sort of like how Gunicorn works but I don't want to run a webserver in order to make the calls).
However the function call seems to only be executed if I call res.get() on the response of pool.apply_async() but then it just runs as if I would call a normal synchronous for-loop.
This is my code:
#!/usr/bin/env python
import os
import time
import multiprocessing as mp
import asyncio
def f(x: list) -> int:
print(f'the pid of this process is: {os.getpid()}')
time.sleep(1)
return len(x)
def callback_func(x):
print(f'this is the callback function')
print(x)
async def consumer(queue):
with mp.Pool(processes=4) as pool:
while True:
x = await queue.get()
if x == 'stop':
break
# this makes it seem to run synchronous:
res = pool.apply_async(f, (x,))
print(res.get(), x, os.getpid())
# if I run this instead, both f() and callback_func
# are not executed.
#res = pool.apply_async(f, (x,), callback_func)
#print(x, os.getpid())
queue.task_done()
print(f'consumed')
async def producer(queue):
for i in range(20):
await queue.put([i,i+1,i+2])
# await asyncio.sleep(0.5)
await queue.put('stop')
async def main():
queue = asyncio.Queue()
input_coroutines = [consumer(queue), producer(queue)]
for f in asyncio.as_completed(input_coroutines):
try:
result = await f
print(result)
except Exception as e:
print('caught exception')
print(e)
if __name__ == "__main__":
asyncio.run(main())
What am I doing wrong?
I'm using tornado with threads.
In short, each time the websocket handler receives a requests, it start to execute a task, which might take a few minutes.
However, once a client is connected, no other client can be connected, until the first one disconnects.
Any ideas?
I've attached a minimal example that uses time.sleep to simulate long running tasks.
import tornado.web
import tornado.websocket
import tornado.httpserver
import tornado.ioloop
import time
import json
import threading
class TaskHandler(tornado.websocket.WebSocketHandler):
def open(self):
pass
def check_origin(self, origin):
return True
def on_message(self, message):
try:
print 'received: ', message
self.write_message(json.dumps({'status': 'running'}))
def worker_A(kwargs):
time.sleep(100)
pass
def worker_B(kwargs):
time.sleep(100)
pass
threads = []
for target in [worker_A, worker_B]:
t = threading.Thread(target = target, args = ({'xxx': 'yyy'}, ))
t.daemon = True
t.start()
threads.append(t)
for t in threads:
t.join()
except Exception, e:
print 'TaskHandler: exception: ', e
pass
self.write_message(json.dumps({'status': 'done'}))
def on_close(self):
pass
class Server(tornado.web.Application):
def __init__(self):
handlers = [
('/task', TaskHandler),
]
tornado.web.Application.__init__(self, handlers)
if __name__ == '__main__':
server = tornado.httpserver.HTTPServer(Server())
server.listen(8765, address = '127.0.0.1')
tornado.ioloop.IOLoop.instance().start()
You block the whole Tornado event loop for 100 seconds in t.join. Unless you have a yield statement or schedule a callback and exit a function, then your function is not asynchronous. Notice how your function "on_message" begins two threads and then calls t.join on each -- how can Tornado's event loop accomplish any other work while your function is waiting for t.join?
Instead, use a ThreadPoolExecutor something like this:
thread_pool = ThreadPoolExecutor(4)
class TaskHandler(tornado.websocket.WebSocketHandler):
# Make this an asynchronous coroutine
#gen.coroutine
def on_message_coroutine(self, message):
print 'received: ', message
self.write_message(json.dumps({'status': 'running'}))
def worker_A(kwargs):
time.sleep(100)
pass
def worker_B(kwargs):
time.sleep(100)
pass
futures = []
for target in [worker_A, worker_B]:
f = thread_pool.submit(target, {'xxx': 'yyy'})
futures.append(future)
# Now the event loop can do other things
yield futures
def on_message(self, message):
IOLoop.current().spawn_callback(self.on_message_coroutine,
message)
I'm currently doing my first steps with asyncio in Python 3.5 and there is one problem that's bugging me. Obviously I haven't fully understood coroutines...
Here is a simplified version of what I'm doing.
In my class I have an open() method that creates a new thread. Within that thread I create a new event loop and a socket connection to some host. Then I let the loop run forever.
def open(self):
# create thread
self.thread = threading.Thread(target=self._thread)
self.thread.start()
# wait for connection
while self.protocol is None:
time.sleep(0.1)
def _thread(self):
# create loop, connection and run forever
self.loop = asyncio.new_event_loop()
coro = self.loop.create_connection(lambda: MyProtocol(self.loop),
'somehost.com', 1234)
self.loop.run_until_complete(coro)
self.loop.run_forever()
Stopping the connection is now quite simple, I just stop the loop from the main thread:
loop.call_soon_threadsafe(loop.stop)
Unfortunately I need to do some cleanup, especially I need to empty a queue before disconnecting from the server. So I tried something like this stop() method in MyProtocol:
class MyProtocol(asyncio.Protocol):
def __init__(self, loop):
self._loop = loop
self._queue = []
async def stop(self):
# wait for all queues to empty
while self._queue:
await asyncio.sleep(0.1)
# disconnect
self.close()
self._loop.stop()
The queue gets emptied from within the protocol's data_received() method, so I just want to wait for that to happen using the while loop with the asyncio.sleep() call. Afterwards I close the connection and stop the loop.
But how do I call this method from the main thread and wait for it?
I tried the following, but none of them seem to work (protocol is the currently used instance of MyProtocol):
loop.call_soon_threadsafe(protocol.stop)
loop.call_soon_threadsafe(functools.partial(asyncio.ensure_future, protocol.stop(), loop=loop))
asyncio.ensure_future(protocol.stop(), loop=loop)
Can anyone please help me here? Thanks!
Basically you want to schedule coroutine on loop of different thread. You could use run_coroutine_threadsafe:
future = asyncio.run_coroutine_threadsafe(protocol.stop, loop=loop)
future.result() # wait for results
Or the old style async like in https://stackoverflow.com/a/32084907/681044
import asyncio
from threading import Thread
loop = asyncio.new_event_loop()
def f(loop):
asyncio.set_event_loop(loop)
loop.run_forever()
t = Thread(target=f, args=(loop,))
t.start()
#asyncio.coroutine
def g():
yield from asyncio.sleep(1)
print('Hello, world!')
loop.call_soon_threadsafe(asyncio.async, g())
This is the relevant code of my python program:
import discord
import asyncio
class Bot(discord.Client):
def __init__(self):
super().__init__()
#asyncio.coroutine
def my_background_task(self):
yield from self.wait_until_ready()
while not self.is_closed:
yield from asyncio.sleep(3600*24) # <- This is line 76 where it fails
doSomething()
bot = Bot()
loop = asyncio.get_event_loop()
try:
loop.create_task(bot.my_background_task())
loop.run_until_complete(bot.login('username', 'password'))
loop.run_until_complete(bot.connect())
except Exception:
loop.run_until_complete(bot.close())
finally:
loop.close()
The program occasionally quits (on its own, while it should not) with no other errors or warning other than
Task was destroyed but it is pending!
task: <Task pending coro=<my_background_task() running at bin/discordBot.py:76> wait_for=<Future pending cb=[Task._wakeup()]>>
How to ensure the program won't randomly quit? I have Python 3.4.3+ on Xubuntu 15.10.
This is because the discord client module needs control once every minute or so.
This means that any function that steals control for more than a certain time causes discord's client to enter an invalid state (which will manifest itself as an exception some point later, perhaps upon next method call of client).
To ensure that the discord module client can ping the discord server, you should use a true multi-threading solution.
One solution is to offload all heavy processing onto a separate process (a separate thread will not do, because Python has a global interpreter lock) and use the discord bot as a thin layer whose responsibility is to populate work queues.
Related reading:
https://discordpy.readthedocs.io/en/latest/faq.html#what-does-blocking-mean
Example solution... this is WAY beyond the scope of the problem, but I already had the code mostly written. If I had more time, I would write a shorter solution :)
2 parts, discord interaction and processing server:
This is the discord listener.
import discord
import re
import asyncio
import traceback
import websockets
import json
# Call a function on other server
async def call(methodName, *args, **kwargs):
async with websockets.connect('ws://localhost:9001/meow') as websocket:
payload = json.dumps( {"method":methodName, "args":args, "kwargs": kwargs})
await websocket.send(payload)
#...
resp = await websocket.recv()
#...
return resp
client = discord.Client()
tok = open("token.dat").read()
#client.event
async def on_ready():
print('Logged in as')
print(client.user.name)
print(client.user.id)
print('------')
#client.event
async def on_error(event, *args, **kwargs):
print("Error?")
#client.event
async def on_message(message):
try:
if message.author.id == client.user.id:
return
m = re.match("(\w+) for (\d+).*?", message.content)
if m:
g = m.groups(1)
methodName = g[0]
someNumber = int(g[1])
response = await call(methodName, someNumber)
if response:
await client.send_message(message.channel, response[0:2000])
except Exception as e:
print (e)
print (traceback.format_exc())
client.run(tok)
This is the worker server for processing heavy requests. You can make this part sync or async.
I chose to use some magic called a websocket to send data from one python process to another one. But you can use anything you want. You could make one script write files into a dir, and the other script could read the files out and process them, for example.
import tornado
import tornado.websocket
import tornado.httpserver
import json
import asyncio
import inspect
import time
class Handler:
def __init__(self, *args, **kwargs):
super().__init__(*args, **kwargs)
def consume(self, text):
return "You said {0} and I say hiya".format(text)
async def sweeps(self, len):
await asyncio.sleep(len)
return "Slept for {0} seconds asynchronously!".format(len)
def sleeps(self, len):
time.sleep(len)
return "Slept for {0} seconds synchronously!".format(len)
class MyService(Handler, tornado.websocket.WebSocketHandler):
def __init__(self, *args, **kwargs):
super().__init__(*args, **kwargs)
def stop(self):
Handler.server.stop()
def open(self):
print("WebSocket opened")
def on_message(self, message):
print (message)
j = json.loads(message)
methodName = j["method"]
args = j.get("args", ())
method = getattr(self, methodName)
if inspect.iscoroutinefunction(method):
loop = asyncio.get_event_loop()
task = loop.create_task(method(*args))
task.add_done_callback( lambda res: self.write_message(res.result()))
future = asyncio.ensure_future(task)
elif method:
resp = method(*args)
self.write_message(resp)
def on_close(self):
print("WebSocket closed")
application = tornado.web.Application([
(r'/meow', MyService),
])
if __name__ == "__main__":
from tornado.platform.asyncio import AsyncIOMainLoop
AsyncIOMainLoop().install()
http_server = tornado.httpserver.HTTPServer(application)
Handler.server = http_server
http_server.listen(9001)
asyncio.get_event_loop().run_forever()
Now, if you run both processes in separate python scripts, and tell your bot "sleep for 100", it will sleep for 100 seconds happily!
The asyncio stuff functions as a make-shift work queue, and you can properly separate the listener from the backend processing by running them as separate python scripts.
Now, no matter how long your functions run in the 'server' part, the client part will never be prevented from pinging the discord server.
Image failed to upload, but... anyway, this is how to tell the bot to sleep and reply... note that the sleep is synchronous.
http://i.imgur.com/N4ZPPbB.png
I don't think problem happens while asyncio.sleep. Anyway you shouldn't suppress exception you got:
bot = Bot()
loop = asyncio.get_event_loop()
try:
# ...
except Exception as e:
loop.run_until_complete(bot.close())
raise e # <--- reraise exception you got while execution to see it (or log it here)
finally:
# ...
You have to manually stop your task on exit:
import discord
import asyncio
class Bot(discord.Client):
def __init__(self):
super().__init__()
#asyncio.coroutine
def my_background_task(self):
yield from self.wait_until_ready()
while not self.is_closed:
yield from asyncio.sleep(3600*24) # <- This is line 76 where it fails
doSomething()
bot = Bot()
loop = asyncio.get_event_loop()
try:
task = loop.create_task(bot.my_background_task())
loop.run_until_complete(bot.login('username', 'password'))
loop.run_until_complete(bot.connect())
except Exception:
loop.run_until_complete(bot.close())
finally:
task.cancel()
try:
loop.run_until_complete(task)
except Exception:
pass
loop.close()
I have a python 3.4.3, postgreSQL 9.4, aiopg-0.7.0. An example of multi-threaded applications, was taken from this site. How to use the pool? The thread hangs when the operation of the select.
import time
import asyncio
import aiopg
import functools
from threading import Thread, current_thread, Event
from concurrent.futures import Future
class B(Thread):
def __init__(self, start_event):
Thread.__init__(self)
self.loop = None
self.tid = None
self.event = start_event
def run(self):
self.loop = asyncio.new_event_loop()
asyncio.set_event_loop(self.loop)
self.tid = current_thread()
self.loop.call_soon(self.event.set)
self.loop.run_forever()
def stop(self):
self.loop.call_soon_threadsafe(self.loop.stop)
def add_task(self, coro):
"""this method should return a task object, that I
can cancel, not a handle"""
def _async_add(func, fut):
try:
ret = func()
fut.set_result(ret)
except Exception as e:
fut.set_exception(e)
f = functools.partial(asyncio.async, coro, loop=self.loop)
if current_thread() == self.tid:
return f() # We can call directly if we're not going between threads.
else:
# We're in a non-event loop thread so we use a Future
# to get the task from the event loop thread once
# it's ready.
fut = Future()
self.loop.call_soon_threadsafe(_async_add, f, fut)
return fut.result()
def cancel_task(self, task):
self.loop.call_soon_threadsafe(task.cancel)
#asyncio.coroutine
def test(pool, name_task):
while True:
print(name_task, 'running')
with (yield from pool.cursor()) as cur:
print(name_task, " select. ")
yield from cur.execute("SELECT count(*) FROM test")
count = yield from cur.fetchone()
print(name_task, ' Result: ', count)
yield from asyncio.sleep(3)
#asyncio.coroutine
def connect_db():
dsn = 'dbname=%s user=%s password=%s host=%s' % ('testdb', 'user', 'passw', '127.0.0.1')
pool = yield from aiopg.create_pool(dsn)
print('create pool type =', type(pool))
# future.set_result(pool)
return (pool)
event = Event()
b = B(event)
b.start()
event.wait() # Let the loop's thread signal us, rather than sleeping
loop_db = asyncio.get_event_loop()
pool = loop_db.run_until_complete(connect_db())
time.sleep(2)
t = b.add_task(test(pool, 'Task1')) # This is a real task
t = b.add_task(test(pool, 'Task2'))
while True:
time.sleep(10)
b.stop()
Not return result in 'yield from cur.execute("SELECT count(*) FROM test")'
Long story short: you cannot share aiopg pool object from different event loops.
Every aiopg.Pool is coupled to event loop. If you don't specify loop parameter explicitly it is taken from asyncio.get_event_loop() call.
So it your example you have a pool coupled to event loop from main thread.
When you execute db query from separate thread you trying to accomplish it by executing thread's loop, not the main one. It doesn't work.