python 日志滚动多进程导致日志丢失

      最近遇到生产环境某个应用的日志丢失，但是其他应用的日志却没丢失，通过查看日志库及其源码，发现，日志在滚动删除时，并不是线程安全的，如果多个进程或者线程，并发进行滚动时，可能导致后一个执行的把之前执行的滚动给删除了。

源码：

class TimedRotatingFileHandler(baseRotatingHandler):

    def doRollover(self):
        """
        do a rollover; in this case, a date/time stamp is appended to the filename
        when the rollover happens.  However, you want the file to be named for the
        start of the interval, not the current time.  If there is a backup count,
        then we have to get a list of matching filenames, sort them and remove
        the one with the oldest suffix.
        """
        if self.stream:
            self.stream.close()
            self.stream = None
        # get the time that this sequence started at and make it a TimeTuple
        currentTime = int(time.time())
        dstNow = time.localtime(currentTime)[-1]
        t = self.rolloverAt - self.interval
        if self.utc:
            timeTuple = time.gmtime(t)
        else:
            timeTuple = time.localtime(t)
            dstThen = timeTuple[-1]
            if dstNow != dstThen:
                if dstNow:
                    addend = 3600
                else:
                    addend = -3600
                timeTuple = time.localtime(t + addend)
        dfn = self.rotation_filename(self.baseFilename + "." +
                                     time.strftime(self.suffix, timeTuple))
        if os.path.exists(dfn):
            os.remove(dfn)
        self.rotate(self.baseFilename, dfn)
        if self.backupCount > 0:
            for s in self.getFilesToDelete():
                os.remove(s)
        if not self.delay:
            self.stream = self._open()
        newRolloverAt = self.computeRollover(currentTime)
        while newRolloverAt <= currentTime:
            newRolloverAt = newRolloverAt + self.interval
        #If DST changes and midnight or weekly rollover, adjust for this.
        if (self.when == 'MIDNIGHT' or self.when.startswith('W')) and not self.utc:
            dstAtRollover = time.localtime(newRolloverAt)[-1]
            if dstNow != dstAtRollover:
                if not dstNow:  # DST kicks in before next rollover, so we need to deduct an hour
                    addend = -3600
                else:           # DST bows out before next rollover, so we need to add an hour
                    addend = 3600
                newRolloverAt += addend
        self.rolloverAt = newRolloverAt

修改后的源码：

import fcntl
import os
import time
from logging.handlers import TimedRotatingFileHandler


class ConcurrentTimedRotatingFileHandler(TimedRotatingFileHandler):
    def doRollover(self):
        """
        do a rollover; in this case, a date/time stamp is appended to the filename
        when the rollover happens.  However, you want the file to be named for the
        start of the interval, not the current time.  If there is a backup count,
        then we have to get a list of matching filenames, sort them and remove
        the one with the oldest suffix.
        """
        if self.stream:
            self.stream.close()
            self.stream = None
        # get the time that this sequence started at and make it a TimeTuple
        currentTime = int(time.time())
        dstNow = time.localtime(currentTime)[-1]
        t = self.rolloverAt - self.interval
        if self.utc:
            timeTuple = time.gmtime(t)
        else:
            timeTuple = time.localtime(t)
            dstThen = timeTuple[-1]
            if dstNow != dstThen:
                if dstNow:
                    addend = 3600
                else:
                    addend = -3600
                timeTuple = time.localtime(t + addend)
        dfn = self.rotation_filename(self.baseFilename + "." +
                                     time.strftime(self.suffix, timeTuple))
        # 兼容多进程并发 LOG_ROTATE
        if not os.path.exists(dfn):
            f = open(self.baseFilename, 'a')
            fcntl.lockf(f.fileno(), fcntl.LOCK_EX)
            if not os.path.exists(dfn):
                os.rename(self.baseFilename, dfn)
            # 释放锁 释放老 log 句柄
            f.close()
        self.rotate(self.baseFilename, dfn)
        if self.backupCount > 0:
            for s in self.getFilesToDelete():
                os.remove(s)
        if not self.delay:
            self.stream = self._open()
        newRolloverAt = self.computeRollover(currentTime)
        while newRolloverAt <= currentTime:
            newRolloverAt = newRolloverAt + self.interval
        # If DST changes and midnight or weekly rollover, adjust for this.
        if (self.when == 'MIDNIGHT' or self.when.startswith('W')) and not self.utc:
            dstAtRollover = time.localtime(newRolloverAt)[-1]
            if dstNow != dstAtRollover:
                if not dstNow:  # DST kicks in before next rollover, so we need to deduct an hour
                    addend = -3600
                else:  # DST bows out before next rollover, so we need to add an hour
                    addend = 3600
                newRolloverAt += addend
        self.rolloverAt = newRolloverAt