有一个很棒的套餐

包: https://pypi.python.org/pypi/multiprocessing-logging/

代码: https://github.com/jruere/multiprocessing-logging

安装:

pip install multiprocessing-logging

然后添加:

import multiprocessing_logging

# This enables logs inside process
multiprocessing_logging.install_mp_handler()

如果在日志模块中的锁、线程和fork的组合中出现死锁，则在错误报告6721中报告(另见相关SO问题)。

有一个小的解决方案张贴在这里。

但是，这只会修复日志记录中任何潜在的死锁。这并不能解决问题，事情可能会变得混乱。请参阅此处提供的其他答案。

到2020年，似乎有一种更简单的多处理日志记录方式。

这个函数将创建记录器。你可以在这里设置格式和你想要输出的位置(文件，stdout):

def create_logger():
    import multiprocessing, logging
    logger = multiprocessing.get_logger()
    logger.setLevel(logging.INFO)
    formatter = logging.Formatter(\
        '[%(asctime)s| %(levelname)s| %(processName)s] %(message)s')
    handler = logging.FileHandler('logs/your_file_name.log')
    handler.setFormatter(formatter)

    # this bit will make sure you won't have 
    # duplicated messages in the output
    if not len(logger.handlers): 
        logger.addHandler(handler)
    return logger

在init中实例化记录器:

if __name__ == '__main__': 
    from multiprocessing import Pool
    logger = create_logger()
    logger.info('Starting pooling')
    p = Pool()
    # rest of the code

现在，你只需要在每个需要记录日志的函数中添加这个引用:

logger = create_logger()

并输出消息:

logger.info(f'My message from {something}')

希望这能有所帮助。

其他线程的变体，它将日志记录和队列线程分开。

"""sample code for logging in subprocesses using multiprocessing

* Little handler magic - The main process uses loggers and handlers as normal.
* Only a simple handler is needed in the subprocess that feeds the queue.
* Original logger name from subprocess is preserved when logged in main
  process.
* As in the other implementations, a thread reads the queue and calls the
  handlers. Except in this implementation, the thread is defined outside of a
  handler, which makes the logger definitions simpler.
* Works with multiple handlers.  If the logger in the main process defines
  multiple handlers, they will all be fed records generated by the
  subprocesses loggers.

tested with Python 2.5 and 2.6 on Linux and Windows

"""

import os
import sys
import time
import traceback
import multiprocessing, threading, logging, sys

DEFAULT_LEVEL = logging.DEBUG

formatter = logging.Formatter("%(levelname)s: %(asctime)s - %(name)s - %(process)s - %(message)s")

class SubProcessLogHandler(logging.Handler):
    """handler used by subprocesses

    It simply puts items on a Queue for the main process to log.

    """

    def __init__(self, queue):
        logging.Handler.__init__(self)
        self.queue = queue

    def emit(self, record):
        self.queue.put(record)

class LogQueueReader(threading.Thread):
    """thread to write subprocesses log records to main process log

    This thread reads the records written by subprocesses and writes them to
    the handlers defined in the main process's handlers.

    """

    def __init__(self, queue):
        threading.Thread.__init__(self)
        self.queue = queue
        self.daemon = True

    def run(self):
        """read from the queue and write to the log handlers

        The logging documentation says logging is thread safe, so there
        shouldn't be contention between normal logging (from the main
        process) and this thread.

        Note that we're using the name of the original logger.

        """
        # Thanks Mike for the error checking code.
        while True:
            try:
                record = self.queue.get()
                # get the logger for this record
                logger = logging.getLogger(record.name)
                logger.callHandlers(record)
            except (KeyboardInterrupt, SystemExit):
                raise
            except EOFError:
                break
            except:
                traceback.print_exc(file=sys.stderr)

class LoggingProcess(multiprocessing.Process):

    def __init__(self, queue):
        multiprocessing.Process.__init__(self)
        self.queue = queue

    def _setupLogger(self):
        # create the logger to use.
        logger = logging.getLogger('test.subprocess')
        # The only handler desired is the SubProcessLogHandler.  If any others
        # exist, remove them. In this case, on Unix and Linux the StreamHandler
        # will be inherited.

        for handler in logger.handlers:
            # just a check for my sanity
            assert not isinstance(handler, SubProcessLogHandler)
            logger.removeHandler(handler)
        # add the handler
        handler = SubProcessLogHandler(self.queue)
        handler.setFormatter(formatter)
        logger.addHandler(handler)

        # On Windows, the level will not be inherited.  Also, we could just
        # set the level to log everything here and filter it in the main
        # process handlers.  For now, just set it from the global default.
        logger.setLevel(DEFAULT_LEVEL)
        self.logger = logger

    def run(self):
        self._setupLogger()
        logger = self.logger
        # and here goes the logging
        p = multiprocessing.current_process()
        logger.info('hello from process %s with pid %s' % (p.name, p.pid))


if __name__ == '__main__':
    # queue used by the subprocess loggers
    queue = multiprocessing.Queue()
    # Just a normal logger
    logger = logging.getLogger('test')
    handler = logging.StreamHandler()
    handler.setFormatter(formatter)
    logger.addHandler(handler)
    logger.setLevel(DEFAULT_LEVEL)
    logger.info('hello from the main process')
    # This thread will read from the subprocesses and write to the main log's
    # handlers.
    log_queue_reader = LogQueueReader(queue)
    log_queue_reader.start()
    # create the processes.
    for i in range(10):
        p = LoggingProcess(queue)
        p.start()
    # The way I read the multiprocessing warning about Queue, joining a
    # process before it has finished feeding the Queue can cause a deadlock.
    # Also, Queue.empty() is not realiable, so just make sure all processes
    # are finished.
    # active_children joins subprocesses when they're finished.
    while multiprocessing.active_children():
        time.sleep(.1)

通过使用处理程序，当前所有解决方案都与日志记录配置过于耦合。我的解决方案具有以下架构和功能:

您可以使用任何想要的日志记录配置 日志记录在守护进程线程中完成 使用上下文管理器安全关闭守护进程 与日志线程的通信是由多进程完成的。队列 在子进程中，日志记录。Logger(和已经定义的实例)被打补丁以将所有记录发送到队列 新:在发送到队列之前格式化回溯和消息，以防止pickle错误

带有使用示例和输出的代码可以在以下Gist中找到:https://gist.github.com/schlamar/7003737

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')