python - 任务中的 celery 任务

Question

我在我的应用程序中结合了 dropbox 和 celery，如果用户连接了 dropbox，我将允许他们存储自己的照片。

我写了一段代码，但我担心这可能会导致死循环，从而杀死系统。

我正在使用的 API 一次只允许 60 张照片，然后它会为您提供分页。

这是我的 tasks.py 文件的副本 - 这实际上工作正常，但我想检查我做的事情是否正确并且不会对系统造成太大影响。

class DropboxUsers(PeriodicTask):
    run_every = timedelta(hours=4)

    def run(self, **kwargs):
        logger = self.get_logger(**kwargs)
        logger.info("Collecting Dropbox users")

        dropbox_users = UserSocialAuth.objects.filter(provider='dropbox')
        for db in dropbox_users:
            ...
            ...
            ...
            sync_images.delay(first, second, third_argument)
        return True


@task(ignore_result=True)
def sync_images(token, secret, username):
    """docstring for sync_images"""
    logger = sync_images.get_logger()
    logger.info("Syncing images for %s" % username)
    ...
    ...
    ...
    ...
    feed = api.user_recent_media(user_id='self', count=60)
    images = feed[0]
    pagination = feed[1]
    for obj in images:
        ### STORE TO DROPBOX
        ...
        ...
        ...
        response = dropbox.put_file(f, my_picture, overwrite=True)
    ### CLOSE DB SESSION
    sess.unlink()
    if pagination:
        store_images.delay(first, second, third, fourth_argument)

@task(ignore_result=True)
def store_images(token, secret, username, max_id):
    """docstring for sync_images"""
    logger = store_images.get_logger()
    logger.info("Storing images for %s" % username)
    ...
    ...
    ...
    ...
    feed = api.user_recent_media(user_id='self', count=60, max_id=max_id)
    images = feed[0]
    try:
        pagination = feed[1]
    except:
        pagination = None
    for obj in images:
        ### STORE TO DROPBOX
        ...
        ...
        ...
        response = dropbox.put_file(f, my_picture, overwrite=True)
    ### CLOSE DB SESSION
    sess.unlink()
    if pagination:
        ### BASICALLY RESTART THE TASK WITH NEW ARGS
        store_images.delay(first, second, third, fourth_argument)

    return True

非常感谢您的专业知识。

Answer 1

我没有发现任何重大问题。我还实现了一个任务启动另一个任务的系统。

有一段时间，我在服务器重启时遇到 celery 复制任务的问题。我写了一个装饰器来包装一个使用缓存后端的任务，以确保具有相同参数的相同任务不会运行得太频繁。可能对您有用，可以防止无限循环。

from django.core.cache import cache as _djcache
from django.utils.functional import wraps

class cache_task(object):

    """ Makes sure that a task is only run once over the course of a configurable
    number of seconds. Useful for tasks that get queued multiple times by accident,
    or on service restart, etc. Uses django's cache (memcache) to keep track."""

    def __init__(self, seconds=120, minutes=0, hours=0):
        self.cache_timeout_seconds = seconds + 60 * minutes + 60 * 60 * hours

    def __call__(self, task):
        task.unsynchronized_run = task.run
        @wraps(task.unsynchronized_run)
        def wrapper(*args, **kwargs):
            key = sha1(str(task.__module__) + str(task.__name__) + str(args) + str(kwargs)).hexdigest()
            is_cached = _djcache.get(key)
            if not is_cached:
                # store the cache BEFORE to cut down on race conditions caused by long tasks
                if self.cache_timeout_seconds:
                    _djcache.set(key, True, self.cache_timeout_seconds)
                task.unsynchronized_run(*args, **kwargs)
        task.run = wrapper
        return task

用法:

@cache_task(hours=2)
@task(ignore_result=True)
def store_images(token, secret, username, max_id):
   ...