I want to run multiple threads in parallel. Each thread picks up a task from a task queue and executes that task.
from threading import Thread
from Queue import Queue
import time
class link(object):
def __init__(self, i):
self.name = str(i)
def run_jobs_in_parallel(consumer_func, jobs, results, thread_count,
async_run=False):
def consume_from_queue(jobs, results):
while not jobs.empty():
job = jobs.get()
try:
results.append(consumer_func(job))
except Exception as e:
print str(e)
results.append(False)
finally:
jobs.task_done()
#start worker threads
if jobs.qsize() < thread_count:
thread_count = jobs.qsize()
for tc in range(1,thread_count+1):
worker = Thread(
target=consume_from_queue,
name="worker_{0}".format(str(tc)),
args=(jobs,results,))
worker.start()
if not async_run:
jobs.join()
def create_link(link):
print str(link.name)
time.sleep(10)
return True
def consumer_func(link):
return create_link(link)
# create_link takes a while to execute
jobs = Queue()
results = list()
for i in range(0,10):
jobs.put(link(i))
run_jobs_in_parallel(consumer_func, jobs, results, 25, async_run=False)
Now what is happening is, let say we have 10 link objects in jobs queue, while the threads are running in parallel, multiple threads are executing same task. How can I prevent this from happening?
Note - the above sample code does not have the problem describe above, but i have exactly same code except create_link method does some complex stuff.
I think what you need is a lock object (docs,tutorial+examples). If you create an instance of such an object you can 'lock' some parts of your code, ensuring that only one thread executes this part at a time.
I guess in your case you want to lock the line job = jobs.get().
First you have to create the lock in a scope where all threads have access to it. (You don't want a lock for every thread but a single lock for all your threads. That means creating the lock within your thread just before acquiring it won't work)
import threading
lock = threading.Lock()
then you can use it on your line like:
lock.acquire()
job = jobs.get()
lock.release()
or
with lock:
job = jobs.get()
The first thread to reach acquire() will lock the lock. other threads that try to acquire() the lock will pause until the lock gets unlocked again by calling release().
Related
I am building a watchdog timer that runs another Python program, and if it fails to find a check-in from any of the threads, shuts down the whole program. This is so it will, eventually, be able to take control of needed communication ports. The code for the timer is as follows:
from multiprocessing import Process, Queue
from time import sleep
from copy import deepcopy
PATH_TO_FILE = r'.\test_program.py'
WATCHDOG_TIMEOUT = 2
class Watchdog:
def __init__(self, filepath, timeout):
self.filepath = filepath
self.timeout = timeout
self.threadIdQ = Queue()
self.knownThreads = {}
def start(self):
threadIdQ = self.threadIdQ
process = Process(target = self._executeFile)
process.start()
try:
while True:
unaccountedThreads = deepcopy(self.knownThreads)
# Empty queue since last wake. Add new thread IDs to knownThreads, and account for all known thread IDs
# in queue
while not threadIdQ.empty():
threadId = threadIdQ.get()
if threadId in self.knownThreads:
unaccountedThreads.pop(threadId, None)
else:
print('New threadId < {} > discovered'.format(threadId))
self.knownThreads[threadId] = False
# If there is a known thread that is unaccounted for, then it has either hung or crashed.
# Shut everything down.
if len(unaccountedThreads) > 0:
print('The following threads are unaccounted for:\n')
for threadId in unaccountedThreads:
print(threadId)
print('\nShutting down!!!')
break
else:
print('No unaccounted threads...')
sleep(self.timeout)
# Account for any exceptions thrown in the watchdog timer itself
except:
process.terminate()
raise
process.terminate()
def _executeFile(self):
with open(self.filepath, 'r') as f:
exec(f.read(), {'wdQueue' : self.threadIdQ})
if __name__ == '__main__':
wd = Watchdog(PATH_TO_FILE, WATCHDOG_TIMEOUT)
wd.start()
I also have a small program to test the watchdog functionality
from time import sleep
from threading import Thread
from queue import SimpleQueue
Q_TO_Q_DELAY = 0.013
class QToQ:
def __init__(self, processQueue, threadQueue):
self.processQueue = processQueue
self.threadQueue = threadQueue
Thread(name='queueToQueue', target=self._run).start()
def _run(self):
pQ = self.processQueue
tQ = self.threadQueue
while True:
while not tQ.empty():
sleep(Q_TO_Q_DELAY)
pQ.put(tQ.get())
def fastThread(q):
while True:
print('Fast thread, checking in!')
q.put('fastID')
sleep(0.5)
def slowThread(q):
while True:
print('Slow thread, checking in...')
q.put('slowID')
sleep(1.5)
def hangThread(q):
print('Hanging thread, checked in')
q.put('hangID')
while True:
pass
print('Hello! I am a program that spawns threads!\n\n')
threadQ = SimpleQueue()
Thread(name='fastThread', target=fastThread, args=(threadQ,)).start()
Thread(name='slowThread', target=slowThread, args=(threadQ,)).start()
Thread(name='hangThread', target=hangThread, args=(threadQ,)).start()
QToQ(wdQueue, threadQ)
As you can see, I need to have the threads put into a queue.Queue, while a separate object slowly feeds the output of the queue.Queue into the multiprocessing queue. If instead I have the threads put directly into the multiprocessing queue, or do not have the QToQ object sleep in between puts, the multiprocessing queue will lock up, and will appear to always be empty on the watchdog side.
Now, as the multiprocessing queue is supposed to be thread and process safe, I can only assume I have messed something up in the implementation. My solution seems to work, but also feels hacky enough that I feel I should fix it.
I am using Python 3.7.2, if it matters.
I suspect that test_program.py exits.
I changed the last few lines to this:
tq = threadQ
# tq = wdQueue # option to send messages direct to WD
t1 = Thread(name='fastThread', target=fastThread, args=(tq,))
t2 = Thread(name='slowThread', target=slowThread, args=(tq,))
t3 = Thread(name='hangThread', target=hangThread, args=(tq,))
t1.start()
t2.start()
t3.start()
QToQ(wdQueue, threadQ)
print('Joining with threads...')
t1.join()
t2.join()
t3.join()
print('test_program exit')
The calls to join() means that the test program never exits all by itself since none of the threads ever exit.
So, as is, t3 hangs and the watchdog program detects this and detects the unaccounted for thread and stops the test program.
If t3 is removed from the above program, then the other two threads are well behaved and the watchdog program allows the test program to continue indefinitely.
I'm making remote API calls using threads, using no join so that the program could make the next API call without waiting for the last to complete.
Like so:
def run_single_thread_no_join(function, args):
thread = Thread(target=function, args=(args,))
thread.start()
return
The problem was I needed to know when all API calls were completed. So I moved to code that's using a cue & join.
Threads seem to run in serial now.
I can't seem to figure out how to get the join to work so that threads execute in parallel.
What am I doing wrong?
def run_que_block(methods_list, num_worker_threads=10):
'''
Runs methods on threads. Stores method returns in a list. Then outputs that list
after all methods in the list have been completed.
:param methods_list: example ((method name, args), (method_2, args), (method_3, args)
:param num_worker_threads: The number of threads to use in the block.
:return: The full list of returns from each method.
'''
method_returns = []
# log = StandardLogger(logger_name='run_que_block')
# lock to serialize console output
lock = threading.Lock()
def _output(item):
# Make sure the whole print completes or threads can mix up output in one line.
with lock:
if item:
print(item)
msg = threading.current_thread().name, item
# log.log_debug(msg)
return
# The worker thread pulls an item from the queue and processes it
def _worker():
while True:
item = q.get()
if item is None:
break
method_returns.append(item)
_output(item)
q.task_done()
# Create the queue and thread pool.
q = Queue()
threads = []
# starts worker threads.
for i in range(num_worker_threads):
t = threading.Thread(target=_worker)
t.daemon = True # thread dies when main thread (only non-daemon thread) exits.
t.start()
threads.append(t)
for method in methods_list:
q.put(method[0](*method[1]))
# block until all tasks are done
q.join()
# stop workers
for i in range(num_worker_threads):
q.put(None)
for t in threads:
t.join()
return method_returns
You're doing all the work in the main thread:
for method in methods_list:
q.put(method[0](*method[1]))
Assuming each entry in methods_list is a callable and a sequence of arguments for it, you did all the work in the main thread, then put the result from each function call in the queue, which doesn't allow any parallelization aside from printing (which is generally not a big enough cost to justify thread/queue overhead).
Presumably, you want the threads to do the work for each function, so change that loop to:
for method in methods_list:
q.put(method) # Don't call it, queue it to be called in worker
and change the _worker function so it calls the function that does the work in the thread:
def _worker():
while True:
method, args = q.get() # Extract and unpack callable and arguments
item = method(*args) # Call callable with provided args and store result
if item is None:
break
method_returns.append(item)
_output(item)
q.task_done()
When I have an error in my code, I'd like my processes to exit, but I have some strange behavior that I don't know how to work around.
This code errors out and closes the processes as expected:
from multiprocessing import Queue, Pool
def worker(queue):
raise error
task_queue = Queue(10)
the_pool = Pool(1, worker, (task_queue,))
But this one spins off an infinite number of new processes which all error out (but followed up by yet new processes):
from multiprocessing import Queue, Pool
def worker(queue):
raise error
task_queue = Queue(10)
the_pool = Pool(1, worker, (task_queue,))
while True: # <-- added this
pass
How can I effectively stop the second from spinning off infinite new processes?
I know that the termination notice is made available via the meta-data url and that I can do something similar to
if requests.get("http://169.254.169.254/latest/meta-data/spot/termination-time").status_code == 200
in order to determine if the notice has been posted. I run a Python service on my Spot Instances that:
Loops over long polling SQS Queues
If it gets a message, it pauses polling and works on the payload.
Working on the payload can take 5-50 minutes.
Working on the payload will involve spawning a threadpool of up to 50 threads to handle parallel uploading of files to S3, this is the majority of the time spent working on the payload.
Finally, remove the message from the queue, rinse, repeat.
The work is idempotent, so if the same payload runs multiple times, I'm out the processing time/costs, but will not negatively impact the application workflow.
I'm searching for an elegant way to now also poll for the termination notice every five seconds in the background. As soon as the termination notice appears, I'd like to immediately release the message back to the SQS queue in order for another instance to pick it up as quickly as possible.
As a bonus, I'd like to shutdown the work, kill off the threadpool, and have the service enter a stasis state. If I terminate the service, supervisord will simply start it back up again.
Even bigger bonus! Is there not a python module available that simplifies this and just works?
I wrote this code to demonstrate how a thread can be used to poll for the Spot instance termination. It first starts up a polling thread, which would be responsible for checking the http endpoint.
Then we create pool of fake workers (mimicking real work to be done) and starts running the pool. Eventually the polling thread will kick in (about 10 seconds into execution as implemented) and kill the whole thing.
To prevent the script from continuing to work after Supervisor restarts it, we would simply put a check at the beginning of the __main__ and if the termination notice is there we sleep for 2.5 minutes, which is longer than that notice lasts before the instance is shutdown.
#!/usr/bin/env python
import threading
import Queue
import random
import time
import sys
import os
class Instance_Termination_Poll(threading.Thread):
"""
Sleep for 5 seconds and eventually pretend that we then recieve the
termination event
if requests.get("http://169.254.169.254/latest/meta-data/spot/termination-time").status_code == 200
"""
def run(self):
print("Polling for termination")
while True:
for i in range(30):
time.sleep(5)
if i==2:
print("Recieve Termination Poll!")
print("Pretend we returned the message to the queue.")
print("Now Kill the entire program.")
os._exit(1)
print("Well now, this is embarassing!")
class ThreadPool:
"""
Pool of threads consuming tasks from a queue
"""
def __init__(self, num_threads):
self.num_threads = num_threads
self.errors = Queue.Queue()
self.tasks = Queue.Queue(self.num_threads)
for _ in range(num_threads):
Worker(self.tasks, self.errors)
def add_task(self, func, *args, **kargs):
"""
Add a task to the queue
"""
self.tasks.put((func, args, kargs))
def wait_completion(self):
"""
Wait for completion of all the tasks in the queue
"""
try:
while True:
if self.tasks.empty() == False:
time.sleep(10)
else:
break
except KeyboardInterrupt:
print "Ctrl-c received! Kill it all with Prejudice..."
os._exit(1)
self.tasks.join()
class Worker(threading.Thread):
"""
Thread executing tasks from a given tasks queue
"""
def __init__(self, tasks, error_queue):
threading.Thread.__init__(self)
self.tasks = tasks
self.daemon = True
self.errors = error_queue
self.start()
def run(self):
while True:
func, args, kargs = self.tasks.get()
try:
func(*args, **kargs)
except Exception, e:
print("Exception " + str(e))
error = {'exception': e}
self.errors.put(error)
self.tasks.task_done()
def do_work(n):
"""
Sleeps a random ammount of time, then creates a little CPU usage to
mimic some work taking place.
"""
for z in range(100):
time.sleep(random.randint(3,10))
print "Thread ID: {} working.".format(threading.current_thread())
for x in range(30000):
x*n
print "Thread ID: {} done, sleeping.".format(threading.current_thread())
if __name__ == '__main__':
num_threads = 30
# Start up the termination polling thread
term_poll = Instance_Termination_Poll()
term_poll.start()
# Create our threadpool
pool = ThreadPool(num_threads)
for y in range(num_threads*2):
pool.add_task(do_work, n=y)
# Wait for the threadpool to complete
pool.wait_completion()
I'm using Python Python Multiprocessing for a RabbitMQ Consumers.
On Application Start I create 4 WorkerProcesses.
def start_workers(num=4):
for i in xrange(num):
process = WorkerProcess()
process.start()
Below you find my WorkerClass.
The Logic works so far, I create 4 parallel Consumer Processes.
But the Problem is after a Process got killed. I want to create a new Process. The Problem in the Logic below is that the new Process is created as child process from the old one and after a while the memory runs out of space.
Is there any possibility with Python Multiprocessing to start a new process and kill the old one correctly?
class WorkerProcess(multiprocessing.Process):
def ___init__(self):
app.logger.info('%s: Starting new Thread!', self.name)
super(multiprocessing.Process, self).__init__()
def shutdown(self):
process = WorkerProcess()
process.start()
return True
def kill(self):
start_workers(1)
self.terminate()
def run(self):
try:
# Connect to RabbitMQ
credentials = pika.PlainCredentials(app.config.get('RABBIT_USER'), app.config.get('RABBIT_PASS'))
connection = pika.BlockingConnection(
pika.ConnectionParameters(host=app.config.get('RABBITMQ_SERVER'), port=5672, credentials=credentials))
channel = connection.channel()
# Declare the Queue
channel.queue_declare(queue='screenshotlayer',
auto_delete=False,
durable=True)
app.logger.info('%s: Start to consume from RabbitMQ.', self.name)
channel.basic_qos(prefetch_count=1)
channel.basic_consume(callback, queue='screenshotlayer')
channel.start_consuming()
app.logger.info('%s: Thread is going to sleep!', self.name)
# do what channel.start_consuming() does but with stoppping signal
#while self.stop_working.is_set():
# channel.transport.connection.process_data_events()
channel.stop_consuming()
connection.close()
except Exception as e:
self.shutdown()
return 0
Thank You
In the main process, keep track of your subprocesses (in a list) and loop over them with .join(timeout=50) (https://docs.python.org/2/library/multiprocessing.html#multiprocessing.Process.join).
Then check is he is alive (https://docs.python.org/2/library/multiprocessing.html#multiprocessing.Process.is_alive).
If he is not, replace him with a fresh one.
def start_workers(n):
wks = []
for _ in range(n):
wks.append(WorkerProcess())
wks[-1].start()
while True:
#Remove all terminated process
wks = [p for p in wks if p.is_alive()]
#Start new process
for i in range(n-len(wks)):
wks.append(WorkerProcess())
wks[-1].start()
I would not handle the process pool management myself. Instead, I would use the ProcessPoolExecutor from the concurrent.future module.
No need to inherit the WorkerProcess to inherit the Process class. Just write your actual code in the class and then submit it to a process pool executor. The executor would have a pool of processes always ready to execute your tasks.
This way you can keep things simple and less headache for you.
You can read more about in my blog post here: http://masnun.com/2016/03/29/python-a-quick-introduction-to-the-concurrent-futures-module.html
Example Code:
from concurrent.futures import ProcessPoolExecutor
from time import sleep
def return_after_5_secs(message):
sleep(5)
return message
pool = ProcessPoolExecutor(3)
future = pool.submit(return_after_5_secs, ("hello"))
print(future.done())
sleep(5)
print(future.done())
print("Result: " + future.result())