对于可能需要这个的人，我为multiprocessing_logging包写了一个装饰器，它将当前进程名添加到日志中，这样就可以清楚地看到谁记录了什么。

它还运行install_mp_handler()，因此在创建池之前运行它是没有用的。

这让我可以看到哪个工作人员创建了哪些日志消息。

下面是蓝图和示例:

import sys
import logging
from functools import wraps
import multiprocessing
import multiprocessing_logging

# Setup basic console logger as 'logger'
logger = logging.getLogger()
console_handler = logging.StreamHandler(sys.stdout)
console_handler.setFormatter(logging.Formatter(u'%(asctime)s :: %(levelname)s :: %(message)s'))
logger.setLevel(logging.DEBUG)
logger.addHandler(console_handler)


# Create a decorator for functions that are called via multiprocessing pools
def logs_mp_process_names(fn):
    class MultiProcessLogFilter(logging.Filter):
        def filter(self, record):
            try:
                process_name = multiprocessing.current_process().name
            except BaseException:
                process_name = __name__
            record.msg = f'{process_name} :: {record.msg}'
            return True

    multiprocessing_logging.install_mp_handler()
    f = MultiProcessLogFilter()

    # Wraps is needed here so apply / apply_async know the function name
    @wraps(fn)
    def wrapper(*args, **kwargs):
        logger.removeFilter(f)
        logger.addFilter(f)
        return fn(*args, **kwargs)

    return wrapper


# Create a test function and decorate it
@logs_mp_process_names
def test(argument):
    logger.info(f'test function called via: {argument}')


# You can also redefine undecored functions
def undecorated_function():
    logger.info('I am not decorated')


@logs_mp_process_names
def redecorated(*args, **kwargs):
    return undecorated_function(*args, **kwargs)


# Enjoy
if __name__ == '__main__':
    with multiprocessing.Pool() as mp_pool:
        # Also works with apply_async
        mp_pool.apply(test, ('mp pool',))
        mp_pool.apply(redecorated)
        logger.info('some main logs')
        test('main program')

QueueHandler在Python 3.2+中是原生的，并且正是这样做的。它很容易在以前的版本中复制。

Python文档有两个完整的示例:从多个进程记录到单个文件

对于那些使用Python < 3.2的人，只需将QueueHandler从https://gist.github.com/vsajip/591589复制到自己的代码中，或者导入logutils。

每个进程(包括父进程)将其日志记录放在Queue上，然后监听线程或进程(为每个进程提供了一个示例)拾取这些日志并将它们全部写入一个文件—没有损坏或乱码的风险。

然而，另一种选择可能是日志包中各种非基于文件的日志处理程序:

套接字处理程序 数据报处理程序 系统日志处理程序

(和其他人)

通过这种方式，您可以轻松地在某个地方创建一个日志守护进程，以便安全地对其进行写入并正确地处理结果。(例如，一个简单的套接字服务器，它只是解pickle消息并将其发送到自己的旋转文件处理程序。)

SyslogHandler也会为您处理这个问题。当然，您可以使用自己的syslog实例，而不是系统实例。

下面是一个可以在Windows环境下使用的类，需要ActivePython。 您还可以继承其他日志处理程序(StreamHandler等)。

class SyncronizedFileHandler(logging.FileHandler):
    MUTEX_NAME = 'logging_mutex'

    def __init__(self , *args , **kwargs):

        self.mutex = win32event.CreateMutex(None , False , self.MUTEX_NAME)
        return super(SyncronizedFileHandler , self ).__init__(*args , **kwargs)

    def emit(self, *args , **kwargs):
        try:
            win32event.WaitForSingleObject(self.mutex , win32event.INFINITE)
            ret = super(SyncronizedFileHandler , self ).emit(*args , **kwargs)
        finally:
            win32event.ReleaseMutex(self.mutex)
        return ret

下面是一个演示用法的例子:

import logging
import random , time , os , sys , datetime
from string import letters
import win32api , win32event
from multiprocessing import Pool

def f(i):
    time.sleep(random.randint(0,10) * 0.1)
    ch = random.choice(letters)
    logging.info( ch * 30)


def init_logging():
    '''
    initilize the loggers
    '''
    formatter = logging.Formatter("%(levelname)s - %(process)d - %(asctime)s - %(filename)s - %(lineno)d - %(message)s")
    logger = logging.getLogger()
    logger.setLevel(logging.INFO)

    file_handler = SyncronizedFileHandler(sys.argv[1])
    file_handler.setLevel(logging.INFO)
    file_handler.setFormatter(formatter)
    logger.addHandler(file_handler)

#must be called in the parent and in every worker process
init_logging() 

if __name__ == '__main__':
    #multiprocessing stuff
    pool = Pool(processes=10)
    imap_result = pool.imap(f , range(30))
    for i , _ in enumerate(imap_result):
        pass

我也喜欢zzzeek的回答，但Andre是正确的，需要一个队列来防止乱码。我的运气还不错，但确实看到了乱码，这是意料之中的。实现它比我想象的要难，特别是在Windows上运行，在Windows上有一些关于全局变量和其他东西的额外限制(参见:如何在Windows上实现Python Multiprocessing ?)

但是，我终于让它工作了。这个例子可能并不完美，所以欢迎评论和建议。它也不支持设置格式化程序或根日志记录器以外的任何内容。基本上，您必须在每个池进程中用队列重新配置记录器，并在记录器上设置其他属性。

同样，欢迎提出任何关于如何使代码更好的建议。我当然还不知道所有的Python技巧:-)

import multiprocessing, logging, sys, re, os, StringIO, threading, time, Queue

class MultiProcessingLogHandler(logging.Handler):
    def __init__(self, handler, queue, child=False):
        logging.Handler.__init__(self)

        self._handler = handler
        self.queue = queue

        # we only want one of the loggers to be pulling from the queue.
        # If there is a way to do this without needing to be passed this
        # information, that would be great!
        if child == False:
            self.shutdown = False
            self.polltime = 1
            t = threading.Thread(target=self.receive)
            t.daemon = True
            t.start()

    def setFormatter(self, fmt):
        logging.Handler.setFormatter(self, fmt)
        self._handler.setFormatter(fmt)

    def receive(self):
        #print "receive on"
        while (self.shutdown == False) or (self.queue.empty() == False):
            # so we block for a short period of time so that we can
            # check for the shutdown cases.
            try:
                record = self.queue.get(True, self.polltime)
                self._handler.emit(record)
            except Queue.Empty, e:
                pass

    def send(self, s):
        # send just puts it in the queue for the server to retrieve
        self.queue.put(s)

    def _format_record(self, record):
        ei = record.exc_info
        if ei:
            dummy = self.format(record) # just to get traceback text into record.exc_text
            record.exc_info = None  # to avoid Unpickleable error

        return record

    def emit(self, record):
        try:
            s = self._format_record(record)
            self.send(s)
        except (KeyboardInterrupt, SystemExit):
            raise
        except:
            self.handleError(record)

    def close(self):
        time.sleep(self.polltime+1) # give some time for messages to enter the queue.
        self.shutdown = True
        time.sleep(self.polltime+1) # give some time for the server to time out and see the shutdown

    def __del__(self):
        self.close() # hopefully this aids in orderly shutdown when things are going poorly.

def f(x):
    # just a logging command...
    logging.critical('function number: ' + str(x))
    # to make some calls take longer than others, so the output is "jumbled" as real MP programs are.
    time.sleep(x % 3)

def initPool(queue, level):
    """
    This causes the logging module to be initialized with the necessary info
    in pool threads to work correctly.
    """
    logging.getLogger('').addHandler(MultiProcessingLogHandler(logging.StreamHandler(), queue, child=True))
    logging.getLogger('').setLevel(level)

if __name__ == '__main__':
    stream = StringIO.StringIO()
    logQueue = multiprocessing.Queue(100)
    handler= MultiProcessingLogHandler(logging.StreamHandler(stream), logQueue)
    logging.getLogger('').addHandler(handler)
    logging.getLogger('').setLevel(logging.DEBUG)

    logging.debug('starting main')

    # when bulding the pool on a Windows machine we also have to init the logger in all the instances with the queue and the level of logging.
    pool = multiprocessing.Pool(processes=10, initializer=initPool, initargs=[logQueue, logging.getLogger('').getEffectiveLevel()] ) # start worker processes
    pool.map(f, range(0,50))
    pool.close()

    logging.debug('done')
    logging.shutdown()
    print "stream output is:"
    print stream.getvalue()

下面是我简单的破解/变通方法…不是最全面的，但很容易修改，比我在写这篇文章之前找到的任何其他答案都更容易阅读和理解:

import logging
import multiprocessing

class FakeLogger(object):
    def __init__(self, q):
        self.q = q
    def info(self, item):
        self.q.put('INFO - {}'.format(item))
    def debug(self, item):
        self.q.put('DEBUG - {}'.format(item))
    def critical(self, item):
        self.q.put('CRITICAL - {}'.format(item))
    def warning(self, item):
        self.q.put('WARNING - {}'.format(item))

def some_other_func_that_gets_logger_and_logs(num):
    # notice the name get's discarded
    # of course you can easily add this to your FakeLogger class
    local_logger = logging.getLogger('local')
    local_logger.info('Hey I am logging this: {} and working on it to make this {}!'.format(num, num*2))
    local_logger.debug('hmm, something may need debugging here')
    return num*2

def func_to_parallelize(data_chunk):
    # unpack our args
    the_num, logger_q = data_chunk
    # since we're now in a new process, let's monkeypatch the logging module
    logging.getLogger = lambda name=None: FakeLogger(logger_q)
    # now do the actual work that happens to log stuff too
    new_num = some_other_func_that_gets_logger_and_logs(the_num)
    return (the_num, new_num)

if __name__ == '__main__':
    multiprocessing.freeze_support()
    m = multiprocessing.Manager()
    logger_q = m.Queue()
    # we have to pass our data to be parallel-processed
    # we also need to pass the Queue object so we can retrieve the logs
    parallelable_data = [(1, logger_q), (2, logger_q)]
    # set up a pool of processes so we can take advantage of multiple CPU cores
    pool_size = multiprocessing.cpu_count() * 2
    pool = multiprocessing.Pool(processes=pool_size, maxtasksperchild=4)
    worker_output = pool.map(func_to_parallelize, parallelable_data)
    pool.close() # no more tasks
    pool.join()  # wrap up current tasks
    # get the contents of our FakeLogger object
    while not logger_q.empty():
        print logger_q.get()
    print 'worker output contained: {}'.format(worker_output)