Signal the end of a Queue? - python

Python 2.7 here.
In the Queue example, the threads run indefinitely:
def worker():
while True:
item = q.get()
do_work(item)
q.task_done()
q = Queue()
for i in range(num_worker_threads):
t = Thread(target=worker)
t.daemon = True
t.start()
for item in source():
q.put(item)
q.join() # block until all tasks are done
Is there an "official" or recommended way to tell the threads to exit after q.join() without using a global variable or subclassing Thread?
Currently, I am doing something like:
class MyThread(Thread, object):
...
def run(self):
...
while True:
try:
item = self.q.get_nowait()
except Queue.Empty:
if self.is_queue_empty:
break
else:
...
...
threads = [MyThread(q, target) for _ in range(num_threads)]
...
q.join()
for thread in threads:
thread.is_queue_empty = True
It works, but it seems kind of hacky. I would also like to avoid making a list of threads, if possible.

Related

Kill all "workers" on "listener" error (multiprocessing, manager and queue set-up)

I'm using multiprocessing to run workers on different files in parallel. Worker's results are put into queue. A listener gets the results from the queue and writes them to the file.
Sometimes listener might run into errors (of various origins). In this case, the listener silently dies, but all other processes continue running (rather surprisingly, worker errors causes all processes to terminate).
I would like to stop all processes (workers, listener, e.t.c.) when listener catches an error. How this can be done?
The scheme of my code is as follows:
def worker(file_path, q):
## do something
q.put(1.)
return True
def listener(q):
while True:
m = q.get()
if m == 'kill':
break
else:
try:
# do something and write to file
except Exception as err:
# raise error
tb = sys.exc_info()[2]
raise err.with_traceback(tb)
def main():
manager = mp.Manager()
q = manager.Queue(maxsize=3)
with mp.Pool(5) as pool:
watcher = pool.apply_async(listener, (q,))
files = ['path_1','path_2','path_3']
jobs = [ pool.apply_async(worker, (p,q,)) for p in files ]
# fire off workers
for job in jobs:
job.get()
# kill the listener when done
q.put('kill')
# run
if __name__ == "__main__":
main()
I tried introducing event = manager.Event() and using it as a flag in main():
## inside the pool, after starting workers
while True:
if event.is_set():
for job in jobs:
job.terminate()
No success. Calling os._exit(1) in listener exception block rises broken pipe error, but processes are not killed.
I also tried setting daemon = True,
for job in jobs:
job.daemon = True
Did not help.
In fact, to handle listener exceptions, I'm using a callable, as required by apply_async (so that they are not entirely silenced). This complicates the situation, but not much.
Thank you in advance.
As always there are many ways to accomplish what you're after, but I would probably suggest using an Event to signal that the processes should quit. I also would not use a Pool in this instance, as it only really simplifies things for simple cases where you need something like map. More complicated use cases quickly make it easier to just build you own "pool" with the functionality you need.
from multiprocessing import Process, Queue, Event
from random import random
def might_fail(a):
assert(a > .001)
def worker(args_q: Queue, result_q: Queue, do_quit: Event):
try:
while not do_quit.is_set():
args = args_q.get()
if args is None:
break
else:
# do something
result_q.put(random())
finally: #signal that worker is exiting even if exception is raised
result_q.put(None) #signal listener that worker is exiting
def listener(result_q: Queue, do_quit: Event, n_workers: int):
n_completed = 0
while n_workers > 0:
res = result_q.get()
if res is None:
n_workers -= 1
else:
n_completed += 1
try:
might_fail(res)
except:
do_quit.set() #let main continue
print(n_completed)
raise #reraise error after we signal others to stop
do_quit.set() #let main continue
print(n_completed)
if __name__ == "__main__":
args_q = Queue()
result_q = Queue()
do_quit = Event()
n_workers = 4
listener_p = Process(target=listener, args=(result_q, do_quit, n_workers))
listener_p.start()
for _ in range(n_workers):
worker_p = Process(target=worker, args=(args_q, result_q, do_quit))
worker_p.start()
for _ in range(1000):
args_q.put("some/file.txt")
for _ in range(n_workers):
args_q.put(None)
do_quit.wait()
print('done')

Python multiprocessing program possible deadlock?

Could some explain to me why this hangs sometimes? (This is just for learning purposes, I wouldn't sum a list like that)
import multiprocessing as mp
q = mp.JoinableQueue()
def worker():
S = 0
while not q.empty():
S += q.get()
q.task_done()
print(S)
procs = []
for i in range(1000):
q.put(i)
for i in range(2):
t = mp.Process(target=worker)
t.start()
procs.append(t)
q.join()
for t in procs:
t.join()

python threading with sync queue

I have a script that follows the same logic in this sample.
Basically I insert items into a global queue and spawn threads with a while loop that gets and item from the queue and the calls task_done.
I can get the threads to join if my while loop is checking that the queue is not empty, but I wanted to try and incorporate a flag that I could set myself to exit the loop. When I try to do this, joining the thread blocks forever.
Here is the non-working sample that doesnt join the threads:
import threading
import queue
class Mythread(threading.Thread):
def __init__(self):
super().__init__()
self.signal = False
def run(self):
global queue
while not self.signal:
item = q.get()
print(item)
q.task_done()
def stop(self):
self.signal = True
q = queue.Queue
for i in range(5000):
q.put(i)
threads = []
for i in range(2):
t = Mythread()
threads.append(t)
for t in threads:
t.start()
q.join()
for t in threads:
print(t.signal) <---- False
t.stop()
print(t.signal) <---- True
t.join() <---- Blocks forever
Here is the one that works using queue empty
import threading
import queue
class Mythread(threading.Thread):
def __init__(self):
super().__init__()
def run(self):
global queue
while not q.empty():
item = q.get()
print(item)
q.task_done()
q = queue.Queue
for i in range(5000):
q.put(i)
threads = []
for i in range(2):
t = Mythread()
threads.append(t)
for t in threads:
t.start()
q.join()
for t in threads:
t.join() <---- Works fine
print(t.is_alive()) <--- returns False
Any ideas?
q.get blocks so it won't reach your while condition

python can't start a new thread

I am building a multi threading application.
I have setup a threadPool.
[ A Queue of size N and N Workers that get data from the queue]
When all tasks are done I use
tasks.join()
where tasks is the queue .
The application seems to run smoothly until suddently at some point (after 20 minutes in example) it terminates with the error
thread.error: can't start new thread
Any ideas?
Edit: The threads are daemon Threads and the code is like:
while True:
t0 = time.time()
keyword_statuses = DBSession.query(KeywordStatus).filter(KeywordStatus.status==0).options(joinedload(KeywordStatus.keyword)).with_lockmode("update").limit(100)
if keyword_statuses.count() == 0:
DBSession.commit()
break
for kw_status in keyword_statuses:
kw_status.status = 1
DBSession.commit()
t0 = time.time()
w = SWorker(threads_no=32, network_server='http://192.168.1.242:8180/', keywords=keyword_statuses, cities=cities, saver=MySqlRawSave(DBSession), loglevel='debug')
w.work()
print 'finished'
When the daemon threads are killed?
When the application finishes or when the work() finishes?
Look at the thread pool and the worker (it's from a recipe )
from Queue import Queue
from threading import Thread, Event, current_thread
import time
event = Event()
class Worker(Thread):
"""Thread executing tasks from a given tasks queue"""
def __init__(self, tasks):
Thread.__init__(self)
self.tasks = tasks
self.daemon = True
self.start()
def run(self):
'''Start processing tasks from the queue'''
while True:
event.wait()
#time.sleep(0.1)
try:
func, args, callback = self.tasks.get()
except Exception, e:
print str(e)
return
else:
if callback is None:
func(args)
else:
callback(func(args))
self.tasks.task_done()
class ThreadPool:
"""Pool of threads consuming tasks from a queue"""
def __init__(self, num_threads):
self.tasks = Queue(num_threads)
for _ in range(num_threads): Worker(self.tasks)
def add_task(self, func, args=None, callback=None):
''''Add a task to the queue'''
self.tasks.put((func, args, callback))
def wait_completion(self):
'''Wait for completion of all the tasks in the queue'''
self.tasks.join()
def broadcast_block_event(self):
'''blocks running threads'''
event.clear()
def broadcast_unblock_event(self):
'''unblocks running threads'''
event.set()
def get_event(self):
'''returns the event object'''
return event
ALSo maybe the problem it's because I create SWorker objects in a loop?
What happens with the old SWorker (garbage collection ?) ?
There is still not enough code for localize the problem, but I'm sure that this is because you don't utilize the threads and start too much of them. Did you see canonical example from Queue python documentation http://docs.python.org/library/queue.html (bottom of the page)?
I can reproduce your problem with the following code:
import threading
import Queue
q = Queue.Queue()
def worker():
item = q.get(block=True) # sleeps forever for now
do_work(item)
q.task_done()
# create infinite number of workers threads and fails
# after some time with "error: can't start new thread"
while True:
t = threading.Thread(target=worker)
t.start()
q.join() # newer reached this
Instead you must create the poll of threads with known number of threads and put your data to queue like:
q = Queue()
def worker():
while True:
item = q.get()
do_work(item)
q.task_done()
for i in range(num_worker_threads):
t = Thread(target=worker)
t.daemon = True
t.start()
for item in source():
q.put(item)
q.join() # block until all tasks are done
UPD: In case you need to stop some thread, you can add a flag to it or send a special mark means "stop" for break while loop:
class Worker(Thread):
break_msg = object() # just uniq mark sign
def __init__(self):
self.continue = True
def run():
while self.continue: # can stop and destroy thread, (var 1)
msg = queue.get(block=True)
if msg == self.break_msg:
return # will stop and destroy thread (var 2)
do_work()
queue.task_done()
workers = [Worker() for _ in xrange(num_workers)]
for w in workers:
w.start()
for task in tasks:
queue.put(task)
for _ in xrange(num_workers):
queue.put(Worker.break_msg) # stop thread after all tasks done. Need as many messages as many threads you have
OR
queue.join() # wait until all tasks done
for w in workers:
w.continue = False
w.put(None)

Multiprocessing Queue in Python

I'm trying to use a queue with the multiprocessing library in Python. After executing the code below (the print statements work), but the processes do not quit after I call join on the Queue and there are still alive. How can I terminate the remaining processes?
Thanks!
def MultiprocessTest(self):
print "Starting multiprocess."
print "Number of CPUs",multiprocessing.cpu_count()
num_procs = 4
def do_work(message):
print "work",message ,"completed"
def worker():
while True:
item = q.get()
do_work(item)
q.task_done()
q = multiprocessing.JoinableQueue()
for i in range(num_procs):
p = multiprocessing.Process(target=worker)
p.daemon = True
p.start()
source = ['hi','there','how','are','you','doing']
for item in source:
q.put(item)
print "q close"
q.join()
#q.close()
print "Finished everything...."
print "num active children:",multiprocessing.active_children()
try this:
import multiprocessing
num_procs = 4
def do_work(message):
print "work",message ,"completed"
def worker():
for item in iter( q.get, None ):
do_work(item)
q.task_done()
q.task_done()
q = multiprocessing.JoinableQueue()
procs = []
for i in range(num_procs):
procs.append( multiprocessing.Process(target=worker) )
procs[-1].daemon = True
procs[-1].start()
source = ['hi','there','how','are','you','doing']
for item in source:
q.put(item)
q.join()
for p in procs:
q.put( None )
q.join()
for p in procs:
p.join()
print "Finished everything...."
print "num active children:", multiprocessing.active_children()
Your workers need a sentinel to terminate, or they will just sit on the blocking reads. Note that using sleep on the Q instead of join on the P lets you display status information etc.
My preferred template is:
def worker(q,nameStr):
print 'Worker %s started' %nameStr
while True:
item = q.get()
if item is None: # detect sentinel
break
print '%s processed %s' % (nameStr,item) # do something useful
q.task_done()
print 'Worker %s Finished' % nameStr
q.task_done()
q = multiprocessing.JoinableQueue()
procs = []
for i in range(num_procs):
nameStr = 'Worker_'+str(i)
p = multiprocessing.Process(target=worker, args=(q,nameStr))
p.daemon = True
p.start()
procs.append(p)
source = ['hi','there','how','are','you','doing']
for item in source:
q.put(item)
for i in range(num_procs):
q.put(None) # send termination sentinel, one for each process
while not q.empty(): # wait for processing to finish
sleep(1) # manage timeouts and status updates etc.
Here is a sentinel-free method for the relatively simple case where you put a number of tasks on a JoinableQueue, then launch worker processes that consume the tasks and exit once they read the queue "dry". The trick is to use JoinableQueue.get_nowait() instead of get(). get_nowait(), as the name implies, tries to get a value from the queue in a non-blocking manner and if there's nothing to be gotten then a queue.Empty exception is raised. The worker handles this exception by exiting.
Rudimentary code to illustrate the principle:
import multiprocessing as mp
from queue import Empty
def worker(q):
while True:
try:
work = q.get_nowait()
# ... do something with `work`
q.task_done()
except Empty:
break # completely done
# main
worknum = 4
jq = mp.JoinableQueue()
# fill up the task queue
# let's assume `tasks` contains some sort of data
# that your workers know how to process
for task in tasks:
jq.put(task)
procs = [ mp.Process(target=worker, args=(jq,)) for _ in range(worknum) ]
for p in procs:
p.start()
for p in procs:
p.join()
The advantage is that you do not need to put the "poison pills" on the queue so the code is a bit shorter.
IMPORTANT : in more complex situations where producers and consumers use the same queue in an "interleaved" manner and the workers may have to wait for new tasks to come along, the "poison pill" approach should be used. My suggestion above is for simple cases where the workers "know" that if the task queue is empty, then there's no point hanging around any more.
You have to clear the queue before joining the process, but q.empty() is unreliable.
The best way to clear the queue is to count the number of successful gets or loop until you receive a sentinel value, just like a socket with a reliable network.
The code below may not be very relevant but I post it for your comments/feedbacks so we can learn together. Thank you!
import multiprocessing
def boss(q,nameStr):
source = range(1024)
for item in source:
q.put(nameStr+' '+str(item))
q.put(None) # send termination sentinel, one for each process
def worker(q,nameStr):
while True:
item = q.get()
if item is None: # detect sentinel
break
print '%s processed %s' % (nameStr,item) # do something useful
q = multiprocessing.Queue()
procs = []
num_procs = 4
for i in range(num_procs):
nameStr = 'ID_'+str(i)
p = multiprocessing.Process(target=worker, args=(q,nameStr))
procs.append(p)
p = multiprocessing.Process(target=boss, args=(q,nameStr))
procs.append(p)
for j in procs:
j.start()
for j in procs:
j.join()

Categories

Resources