嗨，在Python中使用线程池，你可以使用这个库:

from multiprocessing.dummy import Pool as ThreadPool

为了使用，这个库是这样的:

pool = ThreadPool(threads)
results = pool.map(service, tasks)
pool.close()
pool.join()
return results

线程是您想要的线程数，任务是大多数映射到服务的任务列表。

这是我最终使用的结果。它是dgorissen上面的类的修改版本。

文件:threadpool.py

from queue import Queue, Empty
import threading
from threading import Thread


class Worker(Thread):
    _TIMEOUT = 2
    """ Thread executing tasks from a given tasks queue. Thread is signalable, 
        to exit
    """
    def __init__(self, tasks, th_num):
        Thread.__init__(self)
        self.tasks = tasks
        self.daemon, self.th_num = True, th_num
        self.done = threading.Event()
        self.start()

    def run(self):       
        while not self.done.is_set():
            try:
                func, args, kwargs = self.tasks.get(block=True,
                                                   timeout=self._TIMEOUT)
                try:
                    func(*args, **kwargs)
                except Exception as e:
                    print(e)
                finally:
                    self.tasks.task_done()
            except Empty as e:
                pass
        return

    def signal_exit(self):
        """ Signal to thread to exit """
        self.done.set()


class ThreadPool:
    """Pool of threads consuming tasks from a queue"""
    def __init__(self, num_threads, tasks=[]):
        self.tasks = Queue(num_threads)
        self.workers = []
        self.done = False
        self._init_workers(num_threads)
        for task in tasks:
            self.tasks.put(task)

    def _init_workers(self, num_threads):
        for i in range(num_threads):
            self.workers.append(Worker(self.tasks, i))

    def add_task(self, func, *args, **kwargs):
        """Add a task to the queue"""
        self.tasks.put((func, args, kwargs))

    def _close_all_threads(self):
        """ Signal all threads to exit and lose the references to them """
        for workr in self.workers:
            workr.signal_exit()
        self.workers = []

    def wait_completion(self):
        """Wait for completion of all the tasks in the queue"""
        self.tasks.join()

    def __del__(self):
        self._close_all_threads()


def create_task(func, *args, **kwargs):
    return (func, args, kwargs)

使用泳池

from random import randrange
from time import sleep

delays = [randrange(1, 10) for i in range(30)]

def wait_delay(d):
    print('sleeping for (%d)sec' % d)
    sleep(d)

pool = ThreadPool(20)
for i, d in enumerate(delays):
    pool.add_task(wait_delay, d)
pool.wait_completion()

没有内置的基于线程的池。但是，使用queue类实现生产者/消费者队列可以非常快。

来自: https://docs.python.org/2/library/queue.html

from threading import Thread
from Queue import Queue
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

是的，有一个线程池类似于多处理池，但是，它有些隐藏，没有适当的文档。您可以通过以下方式导入:-

from multiprocessing.pool import ThreadPool

我举个简单的例子

def test_multithread_stringio_read_csv(self):
        # see gh-11786
        max_row_range = 10000
        num_files = 100

        bytes_to_df = [
            '\n'.join(
                ['%d,%d,%d' % (i, i, i) for i in range(max_row_range)]
            ).encode() for j in range(num_files)]
        files = [BytesIO(b) for b in bytes_to_df]

        # read all files in many threads
        pool = ThreadPool(8)
        results = pool.map(self.read_csv, files)
        first_result = results[0]

        for result in results:
            tm.assert_frame_equal(first_result, result) 

创建新进程的开销是最小的，特别是当只有4个进程时。我怀疑这是您的应用程序的性能热点。保持简单，优化你必须做的和分析结果指向的地方。

另一种方法是将进程添加到线程队列池中

import concurrent.futures
with concurrent.futures.ThreadPoolExecutor(max_workers=cpus) as executor:
    for i in range(10):
        a = executor.submit(arg1, arg2,....)