I have attempted to follow guidance given here: Handling long running tasks in pika / RabbitMQ and here: https://github.com/pika/pika/issues/753#issuecomment-318124510 on how to run long tasks in a separate thread to avoid interrupting the connection heartbeat. I'm a beginner to threading and still struggling to understand this solution.
For my final use case, I need to make function calls that are several minutes long, represented in the example code below by the long_function(). I've found that if the sleep call in long_function() exceeds the length of the heartbeat timeout, I lose connection (presumably because this function is blocking thread #2 from receiving/acknowledging the heartbeat messages from thread #1) and I get this message in the logs: ERROR: Unexpected connection close detected: StreamLostError: ("Stream connection lost: RxEndOfFile(-1, 'End of input stream (EOF)')",). A sleep call of the same length in the target function of thread #2 does not lead to a StreamLostError.
What's the proper solution for overcoming the StreamLostError here? Do I launch all subsequent function calls in their own threads to avoid blocking thread #2? Do I increase the heartbeat to be longer than long_function()? If this is the solution, what was the point of running my long task in a separate thread? Why not just make the heartbeat timeout in the main thread long enough to accommodate the whole message being processed? Thanks!
import functools
import logging
import pika
import threading
import time
import os
import ssl
from common_utils.rabbitmq_utils import send_message_to_queue, initialize_rabbitmq_channel
import json
import traceback
logging.basicConfig(format='%(asctime)s %(levelname)s: %(message)s',
level=logging.INFO,
datefmt='%Y-%m-%d %H:%M:%S')
def send_message_to_queue(channel, queue_name, body):
channel.basic_publish(exchange='',
routing_key=queue_name,
body=json.dumps(body),
properties=pika.BasicProperties(delivery_mode=2)
)
logging.info("RabbitMQ publish to queue {} confirmed".format(queue_name))
def initialize_rabbitmq_channel(timeout=5*60):
credentials = pika.PlainCredentials(os.environ.get("RABBITMQ_USER"), os.environ.get("RABBITMQ_PASSWORD"))
context = ssl.SSLContext(ssl.PROTOCOL_TLSv1_2)
params = pika.ConnectionParameters(port=5671, host=os.environ.get("RABBITMQ_HOST"), credentials=credentials,
ssl_options=pika.SSLOptions(context), virtual_host="/", heartbeat=timeout)
connection = pika.BlockingConnection(params)
return connection.channel(), connection
def long_function():
logging.info("Long function starting...")
time.sleep(5)
logging.info("Long function finished.")
def ack_message(channel, delivery_tag):
"""
Note that `channel` must be the same pika channel instance via which
the message being ACKed was retrieved (AMQP protocol constraint).
"""
if channel.is_open:
channel.basic_ack(delivery_tag)
logging.info("Message {} acknowledged".format(delivery_tag))
else:
logging.error("Channel is closed and message acknowledgement will fail")
pass
def do_work(connection, channel, delivery_tag, body):
thread_id = threading.get_ident()
fmt1 = 'Thread id: {} Delivery tag: {} Message body: {}'
logging.info(fmt1.format(thread_id, delivery_tag, body))
# Simulating work including a call to another function that exceeds heartbeat timeout
time.sleep(5)
long_function()
send_message_to_queue(channel, "test_inactive", json.loads(body))
cb = functools.partial(ack_message, channel, delivery_tag)
connection.add_callback_threadsafe(cb)
def on_message(connection, channel, method, property, body):
t = threading.Thread(target=do_work, args=(connection, channel, method.delivery_tag, body))
t.start()
t.join()
if __name__ == "__main__":
channel, connection = initialize_rabbitmq_channel(timeout=3)
channel.basic_qos(prefetch_count=1)
channel.basic_consume(queue="test_queue",
auto_ack=False,
on_message_callback=lambda channel, method, property, body: on_message(connection, channel, method, property, body)
)
channel.start_consuming()
Related
We have several tasks that we consume from a message queue. The runtimes of those tasks are dependent on fetching some data from a database. Therefore we would like to work with Gevent to not block the program if some database requests take a long time. We are trying to couple it with the Pika client, which has some asynchronous adapters, one of them for gevent: pika.adapters.gevent_connection.GeventConnection.
I set up some toy code, which consumes from a MQ tasks that consists of integers and publishes them on another queue, while sleeping for 4 seconds for each odd number:
# from gevent import monkey
# # Monkeypatch core python libraries to support asynchronous operations.
# monkey.patch_time()
import pika
from pika.adapters.gevent_connection import GeventConnection
from datetime import datetime
import time
def handle_delivery(unused_channel, method, header, body):
"""Called when we receive a message from RabbitMQ"""
print(f"Received: {body} at {datetime.now()}")
channel.basic_ack(method.delivery_tag)
num = int(body)
print(num)
if num % 2 != 0:
time.sleep(4)
channel.basic_publish(
exchange='my_test_exchange2',
routing_key='my_test_queue2',
body=body
)
print("Finished processing")
def on_connected(connection):
"""Called when we are fully connected to RabbitMQ"""
# Open a channel
connection.channel(on_open_callback=on_channel_open)
def on_channel_open(new_channel):
"""Called when our channel has opened"""
global channel
channel = new_channel
channel.basic_qos(prefetch_count=1)
channel.queue_declare(queue="my_queue_gevent5")
channel.exchange_declare("my_test_exchange2")
channel.queue_declare(queue="my_test_queue2")
channel.queue_bind(exchange="my_test_exchange2", queue="my_test_queue2")
channel.basic_consume("my_queue_gevent5", handle_delivery)
def start_loop(i):
conn = GeventConnection(pika.ConnectionParameters('localhost'), on_open_callback=on_connected)
conn.ioloop.start()
start_loop(1)
If I run it without the monkey.patch_time() call it works OK and it publishes results on the my_test_queue2, but it works sequentially. The expected behaviour after adding monkey.patch_time() patch would be that it still works but concurrently. However, the code gets stuck (nothing happens anymore) after it comes to the call time.sleep(4). It processes and publishes the first integer, which is 0, and then gets stuck at 1, when the if clause gets triggered. What am I doing wrong?
With the help of ChatGPT I managed to make it work. There was a gevent.spawn() call missing:
def handle_delivery(unused_channel, method, header, body):
print("Handling delivery")
gevent.spawn(process_message, method, body)
def process_message(method, body):
print(f"Received: {body} at {datetime.now()}")
channel.basic_ack(method.delivery_tag)
num = int(body)
print(num)
if num % 2 != 0:
time.sleep(4)
channel.basic_publish(
exchange='my_test_exchange2',
routing_key='my_test_queue2',
body=body
)
print("Finished processing")
With the RabbitMQ Python client running subscriber.py:
import pika, time
credentials = pika.PlainCredentials('user', 'pass')
parameters = pika.ConnectionParameters(host='localhost', port=6672, credentials=credentials)
connection = pika.BlockingConnection(parameters)
channel = connection.channel()
channel.basic_qos(prefetch_count=1)
channel.queue_declare(queue='my_queue')
def callback(ch, method, properties, body):
ch.basic_ack(delivery_tag=method.delivery_tag)
time.sleep(600)
print ('process completed')
channel.basic_consume(queue='my_queue', on_message_callback=callback)
channel.start_consuming()
the connection breaks after the callback function is completed.
It appears it always happens on 60th second. It seems the channel.basic_consume() method doesn't want to wait for the main thread to complete the callback function. Is there a way to make sure the connection doesn't drop after 60th second?
Your time.sleep call is blocking Pika's I/O loop which prevents heartbeats from being processed. Don't block the I/O loop!!!
Instead, you should do your long-running work in a separate thread and acknowledge the message correctly from that thread. Fortunately, I have an example right here: link
NOTE: the RabbitMQ team monitors the rabbitmq-users mailing list and only sometimes answers questions on StackOverflow.
I think the "heartbeat" parameter solves this problem. Just set the time in seconds:
import pika, time
credentials = pika.PlainCredentials('user', 'pass')
parameters = pika.ConnectionParameters(host='localhost', port=6672, credentials=credentials, heartbeat=36000)
connection = pika.BlockingConnection(parameters)
channel = connection.channel()
channel.basic_qos(prefetch_count=1)
channel.queue_declare(queue='my_queue')
def callback(ch, method, properties, body):
ch.basic_ack(delivery_tag=method.delivery_tag)
time.sleep(600)
print ('process completed')
channel.basic_consume(queue='my_queue', on_message_callback=callback)
channel.start_consuming()
TL;DR: Calling future.set_result doesn't immediately resolve loop.run_until_complete. Instead it blocks for an additional 5 seconds.
Full context:
In my project, I'm using autobahn and asyncio to send and receive messages with a websocket server. For my use case, I need a 2nd thread for websocket communication, since I have arbitrary blocking code that will be running in the main thread. The main thread also needs to be able to schedule messages for the communication thread to send back and forth with the server. My current goal is to send a message originating from the main thread and block until the response comes back, using the communication thread for all message passing.
Here is a snippet of my code:
import asyncio
import threading
from autobahn.asyncio.websocket import WebSocketClientFactory, WebSocketClientProtocol
CLIENT = None
class MyWebSocketClientProtocol(WebSocketClientProtocol):
# -------------- Boilerplate --------------
is_connected = False
msg_queue = []
msg_listeners = []
def onOpen(self):
self.is_connected = True
for msg in self.msg_queue[::]:
self.publish(msg)
def onClose(self, wasClean, code, reason):
is_connected = False
def onMessage(self, payload, isBinary):
for listener in self.msg_listeners:
listener(payload)
def publish(self, msg):
if not self.is_connected:
self.msg_queue.append(msg)
else:
self.sendMessage(msg.encode('utf-8'))
# /----------------------------------------
def send_and_wait(self):
future = asyncio.get_event_loop().create_future()
def listener(msg):
print('set result')
future.set_result(123)
self.msg_listeners.append(listener)
self.publish('hello')
return future
def worker(loop, ready):
asyncio.set_event_loop(loop)
factory = WebSocketClientFactory('ws://127.0.0.1:9000')
factory.protocol = MyWebSocketClientProtocol
transport, protocol = loop.run_until_complete(loop.create_connection(factory, '127.0.0.1', 9000))
global CLIENT
CLIENT = protocol
ready.set()
loop.run_forever()
if __name__ == '__main__':
# Set up communication thread to talk to the server
threaded_loop = asyncio.new_event_loop()
thread_is_ready = threading.Event()
thread = threading.Thread(target=worker, args=(threaded_loop, thread_is_ready))
thread.start()
thread_is_ready.wait()
# Send a message and wait for response
print('starting')
loop = asyncio.get_event_loop()
result = loop.run_until_complete(CLIENT.send_and_wait())
print('done') # this line gets called 5 seconds after it should
I'm using the autobahn echo server example to respond to my messages.
Problem: The WebSocketClientProtocol receives the response to its outgoing message and calls set_result on its pending future, but loop.run_until_complete blocks an additional ~4.9 seconds until eventually resolving.
I understand that run_until_complete also processes other pending events on the event loop. Is it possible that the main thread has somehow queued up a bunch of events that have to now get processed once I start the loop? Also, if I move run_until_complete into the communications thread or move the create_connection into the main thread, then the event loop doesn't block me.
Lastly, I tried to recreate this problem without using autobahn, but I couldn't cause the extra delay. I'm curious if maybe this is an issue with the nature of autobahn's callback timing (onMessage for example).
For server automation, we're trying to develop a tool, which can handle and execute a lot of tasks on different servers. We send the task and the server hostname into a queue. The queue is then consumed from a requester, which give the information to the ansible api. To achieve that we can execute more then one task at once, we're using threading.
Now we're stuck with the acknowledge of the message...
What we have done so far:
The requester.py consumes the queue and starts then a thread, in which the ansible task is running. The result is then sended into another queue. So each new messages creates a new thread. Is the task finished, the thread dies.
But now comes difficult part. We have to made the messages persistent, in case our server dies. So each message should be acknowledged after the result from ansible was sended back.
Our problem is now, when we try to acknowledged the message in the thread itselfs, there is no more "simultaneously" work done, because the consume of pika waits for the acknowledge. So how we can achieve, that the consume consumes messages and dont wait for the acknowledge? Or how we can work around or improve our little programm?
requester.py
#!/bin/python
from worker import *
import ansible.inventory
import ansible.runner
import threading
class Requester(Worker):
def __init__(self):
Worker.__init__(self)
self.connection(self.selfhost, self.from_db)
self.receive(self.from_db)
def send(self, result, ch, method):
self.channel.basic_publish(exchange='',
routing_key=self.to_db,
body=result,
properties=pika.BasicProperties(
delivery_mode=2,
))
print "[x] Sent \n" + result
ch.basic_ack(delivery_tag = method.delivery_tag)
def callAnsible(self, cmd, ch, method):
#call ansible api pre 2.0
result = json.dumps(result, sort_keys=True, indent=4, separators=(',', ': '))
self.send(result, ch, method)
def callback(self, ch, method, properties, body):
print(" [x] Received by requester %r" % body)
t = threading.Thread(target=self.callAnsible, args=(body,ch,method,))
t.start()
worker.py
import pika
import ConfigParser
import json
import os
class Worker(object):
def __init__(self):
#read some config files
def callback(self, ch, method, properties, body):
raise Exception("Call method in subclass")
def receive(self, queue):
self.channel.basic_qos(prefetch_count=1)
self.channel.basic_consume(self.callback,queue=queue)
self.channel.start_consuming()
def connection(self,server,queue):
self.connection = pika.BlockingConnection(pika.ConnectionParameters(
host=server,
credentials=self.credentials))
self.channel = self.connection.channel()
self.channel.queue_declare(queue=queue, durable=True)
We're working with Python 2.7 and pika 0.10.0.
And yes, we noticed in the pika FAQ: http://pika.readthedocs.io/en/0.10.0/faq.html
that pika is not thread safe.
Disable auto-acknowledge and set the prefetch count to something bigger then 1, depending on how many messages would you like your consumer to take.
Here is how to set prefetch
channel.basic_qos(prefetch_count=1), found here.
I have this piece of code, basically it run channel.start_consuming().
I want it to stop after a while.
I think that channel.stop_consuming() is the right method:
def stop_consuming(self, consumer_tag=None):
""" Cancels all consumers, signalling the `start_consuming` loop to
exit.
But it doesn't work: start_consuming() never ends (execution doesn't exit from this call, "end" is never printed).
import unittest
import pika
import threading
import time
_url = "amqp://user:password#xxx.rabbitserver.com/aaa"
class Consumer_test(unittest.TestCase):
def test_startConsuming(self):
def callback(channel, method, properties, body):
print("callback")
print(body)
def connectionTimeoutCallback():
print("connecionClosedCallback")
def _closeChannel(channel_):
print("_closeChannel")
time.sleep(1)
print("close")
if channel_.is_open:
channel_.stop_consuming()
print("stop_cosuming")
else:
print("channel is closed")
#channel_.close()
params = pika.URLParameters(_url)
params.socket_timeout = 5
connection = pika.BlockingConnection(params)
#connection.add_timeout(2, connectionTimeoutCallback)
channel = connection.channel()
channel.basic_consume(callback,
queue='test',
no_ack=True)
t = threading.Thread(target=_closeChannel, args=[channel])
t.start()
print("start_consuming")
channel.start_consuming() # start consuming (loop never ends)
connection.close()
print("end")
connection.add_timeout solve my problem, maybe call basic_cancel too, but I want to use the right method.
Thanks
Note:
I can't respond or add comment to this (pika, stop_consuming does not work) due to my low reputation points.
Note 2:
I think that I'm not sharing channel or connection across threads (Pika doesn't support this) because I use "channel_" passed as parameter and not "channel" instance of the class (Am I wrong?).
I was having the same problem; as pika is not thread safe. i.e. connections and channels can't be safely shared across threads.
So I used a separate connection to send a shutdown message; then stopped consuming the original channel from the callback function.