我刚刚写了一个我自己的日志处理程序，它只是通过管道将所有内容提供给父进程。我只测试了十分钟，但它似乎工作得很好。

(注意:这是硬编码到RotatingFileHandler，这是我自己的用例。)

更新:@javier现在将这种方法作为Pypi上可用的包来维护-参见Pypi上的multiprocessing-logging, github上的https://github.com/jruere/multiprocessing-logging

更新:实现!

现在它使用队列来正确地处理并发，并正确地从错误中恢复。现在，我已经在生产中使用了几个月了，下面的当前版本工作起来没有问题。

from logging.handlers import RotatingFileHandler
import multiprocessing, threading, logging, sys, traceback

class MultiProcessingLog(logging.Handler):
    def __init__(self, name, mode, maxsize, rotate):
        logging.Handler.__init__(self)

        self._handler = RotatingFileHandler(name, mode, maxsize, rotate)
        self.queue = multiprocessing.Queue(-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):
        while True:
            try:
                record = self.queue.get()
                self._handler.emit(record)
            except (KeyboardInterrupt, SystemExit):
                raise
            except EOFError:
                break
            except:
                traceback.print_exc(file=sys.stderr)

    def send(self, s):
        self.queue.put_nowait(s)

    def _format_record(self, record):
        # ensure that exc_info and args
        # have been stringified.  Removes any chance of
        # unpickleable things inside and possibly reduces
        # message size sent over the pipe
        if record.args:
            record.msg = record.msg % record.args
            record.args = None
        if record.exc_info:
            dummy = self.format(record)
            record.exc_info = None

        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):
        self._handler.close()
        logging.Handler.close(self)

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

如何将所有日志记录委托给另一个进程，从队列中读取所有日志条目?

LOG_QUEUE = multiprocessing.JoinableQueue()

class CentralLogger(multiprocessing.Process):
    def __init__(self, queue):
        multiprocessing.Process.__init__(self)
        self.queue = queue
        self.log = logger.getLogger('some_config')
        self.log.info("Started Central Logging process")

    def run(self):
        while True:
            log_level, message = self.queue.get()
            if log_level is None:
                self.log.info("Shutting down Central Logging process")
                break
            else:
                self.log.log(log_level, message)

central_logger_process = CentralLogger(LOG_QUEUE)
central_logger_process.start()

只需通过任何多进程机制甚至继承共享LOG_QUEUE，就可以很好地工作!

concurrent-log-handler似乎完美地完成了这项工作。在Windows上测试。还支持POSIX系统。

主要思想

使用返回记录器的函数创建一个单独的文件。记录器必须为每个进程拥有ConcurrentRotatingFileHandler的新实例。示例函数get_logger()如下所示。 创建记录器是在流程初始化时完成的。对于多处理。进程的子类，它将意味着run()方法的开始。

详细说明

在这个例子中，我将使用下面的文件结构

.
│-- child.py        <-- For a child process
│-- logs.py         <-- For setting up the logs for the app
│-- main.py         <-- For a main process
│-- myapp.py        <-- For starting the app
│-- somemodule.py   <-- For an example, a "3rd party module using standard logging"

Code

子进程

# child.py 

import multiprocessing as mp
import time
from somemodule import do_something


class ChildProcess(mp.Process):
    def __init__(self):
        self.logger = None
        super().__init__()

    def run(self):
        from logs import get_logger
        self.logger = get_logger()


        while True:
            time.sleep(1)
            self.logger.info("Child process")
            do_something()

Simple child process that inherits multiprocessing.Process and simply logs to file text "Child process" Important: The get_logger() is called inside the run(), or elsewhere inside the child process (not module level or in __init__().) This is required as get_logger() creates ConcurrentRotatingFileHandler instance, and new instance is needed for each process. The do_something is used just to demonstrate that this works with 3rd party library code which does not have any clue that you are using concurrent-log-handler.

主要过程

# main.py

import logging
import multiprocessing as mp
import time

from child import ChildProcess
from somemodule import do_something


class MainProcess(mp.Process):
    def __init__(self):
        self.logger = logging.getLogger()
        super().__init__()

    def run(self):
        from logs import get_logger

        self.logger = get_logger()
        self.child = ChildProcess()
        self.child.daemon = True
        self.child.start()

        while True:
            time.sleep(0.5)
            self.logger.critical("Main process")
            do_something()

主进程，在第二个“主进程”中两次登录到文件。同样继承自multiprocessing.Process。 get_logger()和do_something()的注释与子进程相同。

日志设置

# logs.py

import logging
import os

from concurrent_log_handler import ConcurrentRotatingFileHandler

LOGLEVEL = logging.DEBUG


def get_logger():
    logger = logging.getLogger()

    if logger.handlers:
        return logger

    # Use an absolute path to prevent file rotation trouble.
    logfile = os.path.abspath("mylog.log")

    logger.setLevel(LOGLEVEL)

    # Rotate log after reaching 512K, keep 5 old copies.
    filehandler = ConcurrentRotatingFileHandler(
        logfile, mode="a", maxBytes=512 * 1024, backupCount=5, encoding="utf-8"
    )
    filehandler.setLevel(LOGLEVEL)

    # create also handler for displaying output in the stdout
    ch = logging.StreamHandler()
    ch.setLevel(LOGLEVEL)

    formatter = logging.Formatter(
        "%(asctime)s - %(module)s - %(levelname)s - %(message)s [Process: %(process)d, %(filename)s:%(funcName)s(%(lineno)d)]"
    )

    # add formatter to ch
    ch.setFormatter(formatter)
    filehandler.setFormatter(formatter)

    logger.addHandler(ch)
    logger.addHandler(filehandler)

    return logger

这使用了concurrent-log-handler包中的ConcurrentRotatingFileHandler。每个进程都需要一个新的ConcurrentRotatingFileHandler实例。 注意，ConcurrentRotatingFileHandler的所有参数在每个进程中都应该是相同的。

示例应用程序

# myapp.py 

if __name__ == "__main__":
    from main import MainProcess

    p = MainProcess()
    p.start()

这只是一个关于如何启动多进程应用程序的简单示例

第三方模块使用标准日志记录的例子

# somemodule.py 

import logging

logger = logging.getLogger("somemodule")

def do_something():
    logging.info("doing something")

只是一个简单的例子来测试来自第三方代码的记录器是否正常工作。

示例输出

2021-04-19 19:02:29,425 - main - CRITICAL - Main process [Process: 103348, main.py:run(23)]
2021-04-19 19:02:29,427 - somemodule - INFO - doing something [Process: 103348, somemodule.py:do_something(7)]
2021-04-19 19:02:29,929 - main - CRITICAL - Main process [Process: 103348, main.py:run(23)]
2021-04-19 19:02:29,931 - somemodule - INFO - doing something [Process: 103348, somemodule.py:do_something(7)]
2021-04-19 19:02:30,133 - child - INFO - Child process [Process: 76700, child.py:run(18)]
2021-04-19 19:02:30,137 - somemodule - INFO - doing something [Process: 76700, somemodule.py:do_something(7)]
2021-04-19 19:02:30,436 - main - CRITICAL - Main process [Process: 103348, main.py:run(23)]
2021-04-19 19:02:30,439 - somemodule - INFO - doing something [Process: 103348, somemodule.py:do_something(7)]
2021-04-19 19:02:30,944 - main - CRITICAL - Main process [Process: 103348, main.py:run(23)]
2021-04-19 19:02:30,946 - somemodule - INFO - doing something [Process: 103348, somemodule.py:do_something(7)]
2021-04-19 19:02:31,142 - child - INFO - Child process [Process: 76700, child.py:run(18)]
2021-04-19 19:02:31,145 - somemodule - INFO - doing something [Process: 76700, somemodule.py:do_something(7)]
2021-04-19 19:02:31,449 - main - CRITICAL - Main process [Process: 103348, main.py:run(23)]
2021-04-19 19:02:31,451 - somemodule - INFO - doing something [Process: 103348, somemodule.py:do_something(7)]

我喜欢zzzeek的回答。我只会用管道代替队列，因为如果多个线程/进程使用相同的管道端来生成日志消息，它们将被混淆。

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)