Python并行任务技巧

示例

标准线程多进程,生产者/消费者示例:

Worker越多,问题越大

# -*- coding: utf8 -*-

import os
import time
import Queue
import threading
from PIL import Image

def create_thumbnail(filename, size=(128, 128)):
    try:
        fp, fmt = filename.rsplit('.', 1)
        im = Image.open(filename)
        im.thumbnail(size, Image.ANTIALIAS)
        im.save((fp + '_'+'x'.join(str(i) for i in size) + '.'+fmt), im.format)
        return '%s thumbnail success!' % filename
    except Exception:
        return '%s thumbnail failed!' % filename


def get_image_paths(folder):
    return [os.path.join(folder, f) for f in os.listdir(folder) if 'png' in f]


class Consumer(threading.Thread):
    def __init__(self, queue):
        threading.Thread.__init__(self)
        self._queue = queue

    def run(self):
        while True:
            content = self._queue.get()
            if isinstance(content, str) and content == 'quit':
                break
            respone = create_thumbnail(content)
        print 'Bye bye!'


def Producer():
    filenames = get_image_paths('images')
    queue = Queue.Queue()
    worker_threads = build_worker_pool(queue, 4)
    start_time = time.time()

    for filename in filenames:
        queue.put(filename)
    for worker in worker_threads:
        queue.put('quit')
    for worker in worker_threads:
        worker.join()

    print time.time() - start_time


def build_worker_pool(queue, size):
    workers = []
    for _ in range(size):
        worker = Consumer(queue)
        worker.start()
        workers.append(worker)
    return workers


if __name__ == '__main__':
    Producer()

map

Map能够处理集合按顺序遍历,最终将调用产生的结果保存在一个简单的集合当中。

map.png

# -*- coding: utf8 -*-

import os
import time
from multiprocessing import Pool
from PIL import Image

def create_thumbnail(filename, size=(128, 128)):
    try:
        fp, fmt = filename.rsplit('.', 1)
        im = Image.open(filename)
        im.thumbnail(size, Image.ANTIALIAS)
        im.save((fp + '_'+'x'.join(str(i) for i in size) + '.'+fmt), im.format)
        return '%s thumbnail success!' % filename
    except Exception:
        return '%s thumbnail failed!' % filename


def get_image_paths(folder):
    return [os.path.join(folder, f) for f in os.listdir(folder) if 'png' in f]


def main():
    filenames = get_image_paths('images')
    start_time = time.time()
    
    pool = Pool(4)
    pool.map(create_thumbnail, filenames)
    pool.close()
    pool.join()

    print time.time() - start_time


if __name__ == '__main__':
    main()