python监控子程序运行状态_Python写的服务监控程序实例

前言:

Redhat下安装Python2.7

rhel6.4自带的是2.6， 发现有的机器是python2.4。 到python网站下载源代码，解压到Redhat上，然后运行下面的命令：

# ./configure --prefix=/usr/local/python27

# make

# make install

这样安装之后默认不会启用Python2.7，需要使用/usr/local/python27/bin/python2.7调用新版本的python。

而下面的安装方式会直接接管现有的python

# ./configure

# make

# make install

开始：

服务子进程被监控主进程创建并监控，当子进程异常关闭，主进程可以再次启动之。使用了python的subprocess模块。就这个简单的代码，居然互联网上没有现成可用的例子。没办法，我写好了贡献出来吧。

首先是主进程代码：service_mgr.py

#!/usr/bin/python

#-*- coding: UTF-8 -*-

# cheungmine

# stdin、stdout和stderr分别表示子程序的标准输入、标准输出和标准错误。

#

# 可选的值有:

#   subprocess.PIPE - 表示需要创建一个新的管道.

#   一个有效的文件描述符(其实是个正整数)

#   一个文件对象

#   None - 不会做任何重定向工作，子进程的文件描述符会继承父进程的.

#

# stderr的值还可以是STDOUT, 表示子进程的标准错误也输出到标准输出.

#

# subprocess.PIPE

# 一个可以被用于Popen的stdin、stdout和stderr 3个参数的特输值，表示需要创建一个新的管道.

#

# subprocess.STDOUT

# 一个可以被用于Popen的stderr参数的特输值，表示子程序的标准错误汇合到标准输出.

################################################################################

import os

import sys

import getopt

import time

import datetime

import codecs

import optparse

import ConfigParser

import signal

import subprocess

import select

# logging

# require python2.6.6 and later

import logging

from logging.handlers import RotatingFileHandler

## log settings: SHOULD BE CONFIGURED BY config

LOG_PATH_FILE = "./my_service_mgr.log"

LOG_MODE = 'a'

LOG_MAX_SIZE = 4*1024*1024 # 4M per file

LOG_MAX_FILES = 4          # 4 Files: my_service_mgr.log.1, printmy_service_mgrlog.2, ...

LOG_LEVEL = logging.DEBUG

LOG_FORMAT = "%(asctime)s %(levelname)-10s[%(filename)s:%(lineno)d(%(funcName)s)] %(message)s"

handler = RotatingFileHandler(LOG_PATH_FILE, LOG_MODE, LOG_MAX_SIZE, LOG_MAX_FILES)

formatter = logging.Formatter(LOG_FORMAT)

handler.setFormatter(formatter)

Logger = logging.getLogger()

Logger.setLevel(LOG_LEVEL)

Logger.addHandler(handler)

# color output

#

pid = os.getpid()

def print_error(s):

print '\033[31m[%d: ERROR] %s\033[31;m' % (pid, s)

def print_info(s):

print '\033[32m[%d: INFO] %s\033[32;m' % (pid, s)

def print_warning(s):

print '\033[33m[%d: WARNING] %s\033[33;m' % (pid, s)

def start_child_proc(command, merged):

try:

if command is None:

raise OSError, "Invalid command"

child = None

if merged is True:

# merge stdout and stderr

child = subprocess.Popen(command,

stderr=subprocess.STDOUT, # 表示子进程的标准错误也输出到标准输出

stdout=subprocess.PIPE    # 表示需要创建一个新的管道

)

else:

# DO NOT merge stdout and stderr

child = subprocess.Popen(command,

stderr=subprocess.PIPE,

stdout=subprocess.PIPE)

return child

except subprocess.CalledProcessError:

pass # handle errors in the called executable

except OSError:

pass # executable not found

raise OSError, "Failed to run command!"

def run_forever(command):

print_info("start child process with command: " + ' '.join(command))

Logger.info("start child process with command: " + ' '.join(command))

merged = False

child = start_child_proc(command, merged)

line = ''

errln = ''

failover = 0

while True:

while child.poll() != None:

failover = failover + 1

print_warning("child process shutdown with return code: " + str(child.returncode))

Logger.critical("child process shutdown with return code: " + str(child.returncode))

print_warning("restart child process again, times=%d" % failover)

Logger.info("restart child process again, times=%d" % failover)

child = start_child_proc(command, merged)

# read child process stdout and log it

ch = child.stdout.read(1)

if ch != '' and ch != '\n':

line += ch

if ch == '\n':

print_info(line)

line = ''

if merged is not True:

# read child process stderr and log it

ch = child.stderr.read(1)

if ch != '' and ch != '\n':

errln += ch

if ch == '\n':

Logger.info(errln)

print_error(errln)

errln = ''

Logger.exception("!!!should never run to this!!!")

if __name__ == "__main__":

run_forever(["python", "./testpipe.py"])

然后是子进程代码：testpipe.py

#!/usr/bin/python

#-*- coding: UTF-8 -*-

# cheungmine

# 模拟一个woker进程,10秒挂掉

import os

import sys

import time

import random

cnt = 10

while cnt >= 0:

time.sleep(0.5)

sys.stdout.write("OUT: %s\n" % str(random.randint(1, 100000)))

sys.stdout.flush()

time.sleep(0.5)

sys.stderr.write("ERR: %s\n" % str(random.randint(1, 100000)))

sys.stderr.flush()

#print str(cnt)

#sys.stdout.flush()

cnt = cnt - 1

sys.exit(-1)

Linux上运行很简单：

$ python service_mgr.py

Windows上以后台进程运行：

> start pythonw service_mgr.py

代码中需要修改：

run_forever(["python", "testpipe.py"])