I want to do a infinite loop function.
Here is my code
def do_request():
# my code here
print(result)
while True:
do_request()
When use while True to do this, it's a little slow, so I want to use a thread pool to concurrently execute the function do_request(). How to do this ?
Just like use ab (Apache Bench) to test HTTP server.
Finally, I've solved this problem. I use a variable to limit the thread number.
Here is my final code, solved my problem.
import threading
import time
thread_num = 0
lock = threading.Lock()
def do_request():
global thread_num
# -------------
# my code here
# -------------
with lock:
thread_num -= 1
while True:
if thread_num <= 50:
with lock:
thread_num += 1
t = threading.Thread(target=do_request)
t.start()
else:
time.sleep(0.01)
Thanks for all replies.
You can use threading in Python to implement this.
Can be something similar to this (when using two extra threads only):
import threading
# define threads
task1 = threading.Thread(target = do_request)
task2 = threading.Thread(target = do_request)
# start both threads
task1.start()
task2.start()
# wait for threads to complete
task1.join()
task2.join()
Basically, you start as many threads as you need (make sure you don't get too many, so your system can handle it), then you .join() them to wait for tasks to complete.
Or you can get fancier with multiprocessing Python module.
Try the following code:
import multiprocessing as mp
import time
def do_request():
while(True):
print('I\'m making requests')
time.sleep(0.5)
p = mp.Process(target=do_request)
p.start()
for ii in range(10):
print 'I\'m also doing other things though'
time.sleep(0.7)
print 'Now it is time to kill the service thread'
p.terminate()
The main thread stars a service thread that does the request and goes on until it has to, and then it finishes up the service thread.
Maybe you can use the concurrent.futures.ThreadPoolExecutor
from concurrent.futures import ThreadPoolExecutor
import time
def wait_on_b(hello):
time.sleep(1)
print(hello) # b will never complete because it is waiting on a.
return 5
def wait_on_a():
time.sleep(1)
print(a.result()) # a will never complete because it is waiting on b.
return 6
executor = ThreadPoolExecutor(max_workers=2)
a = executor.submit(wait_on_b, 3)
b = executor.submit(wait_on_a)
How about this?
from threading import Thread, Event
class WorkerThread(Thread):
def __init__(self, logger, func):
Thread.__init__(self)
self.stop_event = Event()
self.logger = logger
self.func = func
def run(self):
self.logger("Going to start the infinite loop...")
#Your code
self.func()
concur_task = WorkerThread(logger, func = do_request)
concur_task.start()
To end this thread...
concur_task.stop_event.set()
concur_task.join(10) #or any value you like
Related
I need to open multiple chrome drivers with selenium, then execute my script by threading in them.
How to make it wait until first threading is finished and then start second threading.
time.sleep(x) wont work for me, as I do not know how much time would first threading take and I need second threading to start as soon as first one is finished.
import time
import threading
from selenium import webdriver
mydrivers=[]
tabs = []
class ActivePool(object):
def __init__(self):
super(ActivePool, self).__init__()
self.active = []
self.lock = threading.Lock()
def makeActive(self, name):
with self.lock:
self.active.append(name)
def makeInactive(self, name):
with self.lock:
self.active.remove(name)
def main_worker(s):
#Driver State
global tabs
global mydrivers
mydrivers.append(webdriver.Chrome())
tabs.append(False)
def worker(s, pool):
with s:
global tabs
global mydrivers
name = threading.currentThread().getName()
pool.makeActive(name)
x = tabs.index(False)
tabs[x] = True
mydrivers[x].get("https://stackoverflow.com")
time.sleep(15)
pool.makeInactive(name)
tabs[x]= False
for k in range(5):
t = threading.Thread(target=main_worker, args=(k,))
t.start()
# How to make it wait until above threading is finished and then start below threading
pool = ActivePool()
s = threading.Semaphore(5)
for j in range(100):
t = threading.Thread(target=worker, name=j, args=(s, pool))
t.start()
thds = []
for k in range(5):
thds.append( threading.Thread(target=main_worker, args=(k,)))
for t in thds:
t.start()
for t in thds:
t.join()
Or, even:
thds = [threading.Thread(target=main_worker, args=(k,)) for k in range(5)]
for t in thds:
t.start()
for t in thds:
t.join()
To wait for a thread to finish you should use the thread.join function. Eg...
from threading import Thread
import time
def wait_sec():
time.sleep(2)
my_thread = Thread(target=wait_sec)
my_thread.start()
# after starting the thread join it to wait for end of target
my_thread.join()
print("You have waited 2 seconds")
I want to limit the number of active threads. What i have seen is, that a finished thread stays alive and does not exit itself, so the number of active threads keep growing until an error occours.
The following code starts only 8 threads at a time but they stay alive even when they finished. So the number keeps growing:
class ThreadEx(threading.Thread):
__thread_limiter = None
__max_threads = 2
#classmethod
def max_threads(cls, thread_max):
ThreadEx.__max_threads = thread_max
ThreadEx.__thread_limiter = threading.BoundedSemaphore(value=ThreadEx.__max_threads)
def __init__(self, target=None, args:tuple=()):
super().__init__(target=target, args=args)
if not ThreadEx.__thread_limiter:
ThreadEx.__thread_limiter = threading.BoundedSemaphore(value=ThreadEx.__max_threads)
def run(self):
ThreadEx.__thread_limiter.acquire()
try:
#success = self._target(*self._args)
#if success: return True
super().run()
except:
pass
finally:
ThreadEx.__thread_limiter.release()
def call_me(test1, test2):
print(test1 + test2)
time.sleep(1)
ThreadEx.max_threads(8)
for i in range(0, 99):
t = ThreadEx(target=call_me, args=("Thread count: ", str(threading.active_count())))
t.start()
Due to the for loop, the number of threads keep growing to 99.
I know that a thread has done its work because call_me has been executed and threading.active_count() was printed.
Does somebody know how i make sure, a finished thread does not stay alive?
This may be a silly answer but to me it looks you are trying to reinvent ThreadPool.
from multiprocessing.pool import ThreadPool
from time import sleep
p = ThreadPool(8)
def call_me(test1):
print(test1)
sleep(1)
for i in range(0, 99):
p.apply_async(call_me, args=(i,))
p.close()
p.join()
This will ensure only 8 concurrent threads are running your function at any point of time. And if you want a bit more performance, you can import Pool from multiprocessing and use that. The interface is exactly the same but your pool will now be subprocesses instead of threads, which usually gives a performance boost as GIL does not come in the way.
I have changed the class according to the help of Hannu.
I post it for reference, maybe it's useful for others that come across this post:
import threading
from multiprocessing.pool import ThreadPool
import time
class MultiThread():
__thread_pool = None
#classmethod
def begin(cls, max_threads):
MultiThread.__thread_pool = ThreadPool(max_threads)
#classmethod
def end(cls):
MultiThread.__thread_pool.close()
MultiThread.__thread_pool.join()
def __init__(self, target=None, args:tuple=()):
self.__target = target
self.__args = args
def run(self):
try:
result = MultiThread.__thread_pool.apply_async(self.__target, args=self.__args)
return result.get()
except:
pass
def call_me(test1, test2):
print(test1 + test2)
time.sleep(1)
return 0
MultiThread.begin(8)
for i in range(0, 99):
t = MultiThread(target=call_me, args=("Thread count: ", str(threading.active_count())))
t.run()
MultiThread.end()
The maximum of threads is 8 at any given time determined by the method begin.
And also the method run returns the result of your passed function if it returns something.
Hope that helps.
I've started programming in Python a few weeks ago and was trying to use Semaphores to synchronize two simple threads, for learning purposes. Here is what I've got:
import threading
sem = threading.Semaphore()
def fun1():
while True:
sem.acquire()
print(1)
sem.release()
def fun2():
while True:
sem.acquire()
print(2)
sem.release()
t = threading.Thread(target = fun1)
t.start()
t2 = threading.Thread(target = fun2)
t2.start()
But it keeps printing just 1's. How can I intercale the prints?
It is working fine, its just that its printing too fast for you to see . Try putting a time.sleep() in both functions (a small amount) to sleep the thread for that much amount of time, to actually be able to see both 1 as well as 2.
Example -
import threading
import time
sem = threading.Semaphore()
def fun1():
while True:
sem.acquire()
print(1)
sem.release()
time.sleep(0.25)
def fun2():
while True:
sem.acquire()
print(2)
sem.release()
time.sleep(0.25)
t = threading.Thread(target = fun1)
t.start()
t2 = threading.Thread(target = fun2)
t2.start()
Also, you can use Lock/mutex method as follows:
import threading
import time
mutex = threading.Lock() # is equal to threading.Semaphore(1)
def fun1():
while True:
mutex.acquire()
print(1)
mutex.release()
time.sleep(.5)
def fun2():
while True:
mutex.acquire()
print(2)
mutex.release()
time.sleep(.5)
t1 = threading.Thread(target=fun1).start()
t2 = threading.Thread(target=fun2).start()
Simpler style using "with":
import threading
import time
mutex = threading.Lock() # is equal to threading.Semaphore(1)
def fun1():
while True:
with mutex:
print(1)
time.sleep(.5)
def fun2():
while True:
with mutex:
print(2)
time.sleep(.5)
t1 = threading.Thread(target=fun1).start()
t2 = threading.Thread(target=fun2).start()
[NOTE]:
The difference between mutex, semaphore, and lock
In fact, I want to find asyncio.Semaphores, not threading.Semaphore,
and I believe someone may want it too.
So, I decided to share the asyncio.Semaphores, hope you don't mind.
from asyncio import (
Task,
Semaphore,
)
import asyncio
from typing import List
async def shopping(sem: Semaphore):
while True:
async with sem:
print(shopping.__name__)
await asyncio.sleep(0.25) # Transfer control to the loop, and it will assign another job (is idle) to run.
async def coding(sem: Semaphore):
while True:
async with sem:
print(coding.__name__)
await asyncio.sleep(0.25)
async def main():
sem = Semaphore(value=1)
list_task: List[Task] = [asyncio.create_task(_coroutine(sem)) for _coroutine in (shopping, coding)]
"""
# Normally, we will wait until all the task has done, but that is impossible in your case.
for task in list_task:
await task
"""
await asyncio.sleep(2) # So, I let the main loop wait for 2 seconds, then close the program.
asyncio.run(main())
output
shopping
coding
shopping
coding
shopping
coding
shopping
coding
shopping
coding
shopping
coding
shopping
coding
shopping
coding
16*0.25 = 2
I used this code to demonstrate how 1 thread can use a Semaphore and the other thread will wait (non-blocking) until the Sempahore is available.
This was written using Python3.6; Not tested on any other version.
This will only work is the synchronization is being done from the same thread, IPC from separate processes will fail using this mechanism.
import threading
from time import sleep
sem = threading.Semaphore()
def fun1():
print("fun1 starting")
sem.acquire()
for loop in range(1,5):
print("Fun1 Working {}".format(loop))
sleep(1)
sem.release()
print("fun1 finished")
def fun2():
print("fun2 starting")
while not sem.acquire(blocking=False):
print("Fun2 No Semaphore available")
sleep(1)
else:
print("Got Semphore")
for loop in range(1, 5):
print("Fun2 Working {}".format(loop))
sleep(1)
sem.release()
t1 = threading.Thread(target = fun1)
t2 = threading.Thread(target = fun2)
t1.start()
t2.start()
t1.join()
t2.join()
print("All Threads done Exiting")
When I run this - I get the following output.
fun1 starting
Fun1 Working 1
fun2 starting
Fun2 No Semaphore available
Fun1 Working 2
Fun2 No Semaphore available
Fun1 Working 3
Fun2 No Semaphore available
Fun1 Working 4
Fun2 No Semaphore available
fun1 finished
Got Semphore
Fun2 Working 1
Fun2 Working 2
Fun2 Working 3
Fun2 Working 4
All Threads done Exiting
Existing answers are wastefully sleeping
I noticed that almost all answers use some form of time.sleep or asyncio.sleep, which blocks the thread. This should be avoided in real software, because blocking your thread for 0.25, 0.5 or 1 second is unnecessary/wasteful - you could be doing more processing, especially if your application is IO bound - it already blocks when it does IO AND you are introducing arbitrary delays (latency) in your processing time. If all your threads are sleeping, your app isn't doing anything. Also, these variables are quite arbitrary, which is why each answer has a different value they sleep (block the thread for).
The answers are using it as a way to get Python's bytecode interpreter to pre-empt the thread after each print line, so that it alternates deterministically between running the 2 threads. By default, the interpreter pre-empts a thread every 5ms (sys.getswitchinterval() returns 0.005), and remember that these threads never run in parallel, because of Python's GIL
Solution to problem
How can I intercale the prints?
So my answer would be, you do not want to use semaphores to print (or process) something in a certain order reliably, because you cannot rely on thread prioritization in Python. See Controlling scheduling priority of python threads? for more. time.sleep(arbitrarilyLargeEnoughNumber) doesn't really work when you have more than 2 concurrent pieces of code, since you don't know which one will run next - see * below. If the order matters, use a queue, and worker threads:
from threading import Thread
import queue
q = queue.Queue()
def enqueue():
while True:
q.put(1)
q.put(2)
def reader():
while True:
value = q.get()
print(value)
enqueuer_thread = Thread(target = enqueue)
reader_thread_1 = Thread(target = reader)
reader_thread_2 = Thread(target = reader)
reader_thread_3 = Thread(target = reader)
enqueuer_thread.start()
reader_thread_1.start()
reader_thread_2.start()
reader_thread_3.start()
...
Unfortunately in this problem, you don't get to use Semaphore.
*An extra check for you
If you try a modification of the top voted answer but with an extra function/thread to print(3), you'll get:
1
2
3
1
3
2
1
3
...
Within a few prints, the ordering is broken - it's 1-3-2.
You need to use 2 semaphores to do what you want to do, and you need to initialize them at 0.
import threading
SEM_FUN1 = threading.Semaphore(0)
SEM_FUN2 = threading.Semaphore(0)
def fun1() -> None:
for _ in range(5):
SEM_FUN1.acquire()
print(1)
SEM_FUN2.release()
def fun2() -> None:
for _ in range(5):
SEM_FUN2.acquire()
print(2)
SEM_FUN1.release()
threading.Thread(target=fun1).start()
threading.Thread(target=fun2).start()
SEM_FUN1.release() # Trigger fun1
Output:
I created two threads each running different functions.
What i tryed to achieve is if first thread ends then the second should also end ( i tryed achieving it using global variable)
Once both the threads end the same procedure should continue.
The script is not working as expected.
I am using Linux - Centos and python 2.7
#!/usr/bin/python
import threading
import time
import subprocess
import datetime
import os
import thread
command= "strace -o /root/Desktop/a.txt -c ./server"
final_dir = "/root/Desktop/"
exitflag = 0
# Define a function for the thread
def print_time(*args):
os.chdir(final_dir)
print "IN first thread"
proc = subprocess.Popen(command,shell=True,stdout=subprocess.PIPE, stderr=subprocess.PIPE)
proc.wait(70)
exitflag=1
def print_time1(*args):
print "In second thread"
global exitflag
while exitflag:
thread.exit()
#proc = subprocess.Popen(command1,shell=True,stdout=subprocess.PIPE, sterr=subprocess.PIPE)
# Create two threads as follows
while (1):
t1=threading.Thread(target=print_time)
t1.start()
t2=threading.Thread(target=print_time1)
t2=start()
time.sleep(80)
z = t1.isAlive()
z1 = t2.isAlive()
if z:
z.exit()
if z1:
z1.exit()
threading.Thread(target=print_time1).start()
threading.Thread(target=print_time1).start()
print "In try"
Where am i going wrong?
You could create an object to share state, and have the dependent thread check that state. Something like:
import threading
import time
import datetime
class Worker1( threading.Thread ):
def __init__(self, state):
super(Worker1, self).__init__()
self.state = state
def run(self):
print_time_helper("Worker1 Start")
time.sleep(4)
print_time_helper("Worker1 End")
self.state.keepOnRunning = False
class Worker2( threading.Thread ):
def __init__(self, state):
super(Worker2, self).__init__()
self.state = state
def run(self):
while self.state.keepOnRunning:
print_time_helper("Worker2")
time.sleep(1)
class State( object ):
def __init__(self):
self.keepOnRunning = True
def main():
state = State()
thread1 = Worker1(state)
thread2 = Worker2(state)
thread1.start()
thread2.start()
thread1.join()
thread2.join()
def print_time_helper(name):
print "{0}: {1}".format(name, datetime.datetime.now().time().strftime("%S"))
which will output something like this (numbers show current time seconds):
Worker1 Start: 39
Worker2: 39
Worker2: 40
Worker2: 41
Worker2: 42
Worker1 End: 43
However, this is a bit simplistic for most situations. You might be better off using message queues - this is a good intro.
Use a threading.Event instead of an int and wait for it to be set.
Also your logic appears to be wrong in print_time1 because your while loop will never run since exitflag is initially 0, but even if it was 1 it would still just exit immediately. It's not actually waiting on anything.
I don't know why I'm having such a problem with this, basically, I want to have a Queue that is constantly running during the program called "Worker" this then works, however, every 10 seconds or so.. Another method called "Process" comes in and processes the data. Let's assume the following, data is captured every 10 seconds.. (0, 1, 2, 3, ..... n) and then the "Proces" function receives this, processes the data, ends, and then the "Worker" goes back to work and does their job until the program has ended.
I have the following code:
import multiprocessing as mp
import time
DELAY_SIZE = 10
def Worker(q):
print "I'm working..."
def Process(q):
print "I'm processing.."
queue = mp.Queue(maxsize=DELAY_SIZE)
p = mp.Process(target=Worker, args=(queue,))
p.start()
while True:
d = queue.get()
time.sleep(10)
Process()
In this example, it would look like the following:
I'm working...
I'm working...
I'm working...
...
...
...
I'm working...
I'm processing...
I'm processing...
I'm processing...
...
...
I'm working..
I'm working..
Any ideas?
Here is an alternative way using threads:
import threading
import Queue
import time
class Worker(threading.Thread):
def __init__(self, q):
threading.Thread.__init__(self)
self._q = q
def run(self):
# here, worker does its job
# results are pushed to the shared queue
while True:
print 'I am working'
time.sleep(1)
result = time.time() # just an example
self._q.put(result)
def process(q):
while True:
if q.empty():
time.sleep(10)
print 'I am processing'
worker_result = q.get()
# do whatever you want with the result...
print " ", worker_result
if __name__ == '__main__':
shared_queue = Queue.Queue()
worker = Worker(shared_queue)
worker.start()
process(shared_queue)