在生产环境中,有客户架构为阿里云线上环境及线下IDC须要内网互通,互联采用阿里云使用第三方深信服云产品与线下IDC侧Cisco防火墙ipsec打通实现,主要用于定时阿里云文件及数据备份至IDC,在生产应用中无端隧道会不定时中断,联系深信服及思科售后排查均没有结果,可是进行手动的重启阿里云上深信服设备隧道当即恢复,在两边网络工程师排查无果后,想到去编写监控脚本,若是隧道终端去利用python重启深信服设备,从而恢复隧道,数据传输延迟timeout及使用断点续传,当网络层面异常没法解决时,换另外一种思路来解决问题。前端
2.1 编写隧道监控脚本
因为线上阿里云侧为公有云,且为配置EIP及NAT网关,ecs均采用前端公网SLB负责业务请求接入,其内部没法出公网,隧道监控脚本想告警出来发送至微信及后续的去操做深信服须要公网连通,所以在线下IDC侧放置检查及重启脚本。python
2.2 深信服重启
- 利用Python编写去操做深信服,web页面模拟登陆,主要利用到了selenium模块,logging来记录日志。
- 利用阿里云ECS API来操做重启深信服设备。
检测隧道连通性,若是隧道终端告警至微信及钉钉,其次触发深信服重启脚本。linux
#!/bin/bash #检测内网地址 IP=10.10.10.2 dir="/sangfor/Shscripts/pdc/" if [ ! -d ${dir} ];then mkdir -p ${dir} fi echo 1 > ${dir}pdcping.lock while true do #日志分割归档 Time=`date +%F` TIME="${Time} 23:59" if [ "${data}" == "${TIME}" ];then mkdir ${dir}${Time} && mv ${dir}pdcping.log ${dir}${Time}-pingpdc.log mv ${dir}${Time}-pingpdc.log ${dir}${Time} fi find ${dir} -mtime +7 -type d -exec rm -rf {} \; find ${dir} -mtime +7 -name "*-pingpdc.log" -exec rm -rf {} \; data=`date +%F' '%H:%M` data1=`date +%F' '%H:%M:%S` echo "------------${data1}---------------">>${dir}pingpdc.log ping -c 10 ${IP} >>${dir}pingpdc.log if [ $? -eq 1 ];then STAT=`cat ${dir}pdcping.lock` if [ ${STAT} -eq 1 ];then /usr/local/python34/bin/python3 /sangfor/Pysangfor/sangfor_public.py echo 0 > ${dir}pdcping.lock else continue fi else STAT=`cat ${dir}pdcping.lock` if [ ${STAT} -eq 0 ];then echo 1 > ${dir}pdcping.lock else continue fi fi done
为防止隧道检测脚本异常,另外编写监控监测脚本的脚本配合定时任务来定时监控,若是异常,从新拉起。c++
#!/bin/bash num=$(ps -ef |grep pdc.sh|wc -l) cmd="/usr/bin/nohup /bin/bash /sangfor/Shscripts/pdc/pdc.sh &" if [ ${num} -lt 2 ];then ${cmd} fi
配合定时任务git
* * * * * /bin/bash /sangfor/Shscripts/pdc/checkpdc.sh
yum -y install zlib-devel zlib readline-devel openssl-devel wget gcc-c++ Xvfb lrzsz firefox cd /tmp wget -c https://www.python.org/ftp/python/3.4.5/Python-3.4.5.tgz tar -zxvf Python-3.4.5.tgz cd Python-3.4.5 ./configure --prefix=/usr/local/python34 make && make install echo "export PATH=$PATH:/usr/local/python34/bin" >/etc/profile.d/python34.sh source /etc/profile.d/python34.sh
cd /tmp wget https://bootstrap.pypa.io/get-pip.py python3 get-pip.py
pip3 install selenium pip3 install pyvirtualdisplay pip3 install xvfbwrapper
cd /tmp wget -c https://github.com/mozilla/geckodriver/releases/download/v0.16.1/geckodriver-v0.16.1-linux64.tar.gz tar zxvf geckodriver-v0.16.1-linux64.tar.gz cp geckodriver /usr/bin/
github地址
模拟web登陆操做深信服github
cat > /sangfor/Pysangfor/sangfor_public.py<<EOF #!/bin/env python3 # -*- coding:UTF-8 -*- # _author:kaliarch #导入模块 from pyvirtualdisplay import Display from selenium import webdriver import time import os import logging #定义深信服重启类 class Glp_SangFor: def __init__(self,logger): self.logger = logger self.logger.info("--------------start log----------------") self.display = Display(visible=0, size=(800, 600)) self.display.start() self.browser = webdriver.Firefox() self.logger.info("start browser successfuly") self.sangfor_url = "深信服公网url" self.username = '深信服登陆用户名' self.password = '深信服登陆密码' def login(self): self.browser.get(self.sangfor_url) self.browser.implicitly_wait(5) self.browser.find_element_by_name('user').send_keys(self.username) self.browser.find_element_by_name('password').send_keys(self.password) self.browser.find_element_by_class_name('buttons').click() self.browser.implicitly_wait(5) self.logger.info("loggin sangfor successfuly") def client_reboot(self): self.browser.find_element_by_id("ext-gen111").click() print(self.browser.find_element_by_id("ext-gen111").text) self.browser.implicitly_wait(15) time.sleep(60) self.logger.info("switch mainiframe start") try: print(self.browser.find_element_by_link_text("重启/重启服务/关机").text) self.browser.find_element_by_link_text("重启/重启服务/关机").click() self.browser.implicitly_wait(3) self.browser.switch_to_frame("mainiframe") self.browser.implicitly_wait(8) time.sleep(10) self.browser.find_element_by_xpath("//button[@id='ext-gen19']").click() print(self.browser.find_element_by_xpath("//button[@id='ext-gen19']").text) self.browser.implicitly_wait(10) #self.browser.find_element_by_xpath("//button[@id='ext-gen42']").click() print(self.browser.find_element_by_xpath("//button[@id='ext-gen42']").text) except Exception as e: self.logger.exception("reboot successful") return 1 self.browser.close() self.logger.info("browser close successful") self.logger.info("--------------end log----------------") return 0 #定义日志记录 class Glp_Log: def __init__(self,filename): self.filename = filename def createDir(self): _LOGDIR = os.path.join(os.path.dirname(__file__), 'publiclog') print(_LOGDIR) _TIME = time.strftime('%Y-%m-%d', time.gmtime()) + '-' _LOGNAME = _TIME + self.filename print(_LOGNAME) LOGFILENAME = os.path.join(_LOGDIR, _LOGNAME) print(LOGFILENAME) if not os.path.exists(_LOGDIR): os.mkdir(_LOGDIR) return LOGFILENAME print(LOGFILENAME) def createlogger(self,logfilename): logger= logging.getLogger() logger.setLevel(logging.INFO) handler = logging.FileHandler(logfilename) handler.setLevel(logging.INFO) formater = logging.Formatter('%(asctime)s - %(name)s - %(levelname)s - %(message)s') handler.setFormatter(formater) logger.addHandler(handler) return logger #主函数调用 if __name__ == '__main__': os.system("pkill firefox") os.system("pkill Xvfb") glploger = Glp_Log('public-***.log') logfilename = glploger.createDir() logger = glploger.createlogger(logfilename) sangfor_oper = Glp_SangFor(logger) sangfor_oper.login() sangfor_oper.client_reboot() EOF
经过阿里云ECS API操做深信服设备web
#!/bin/env python3 # -*- coding:UTF-8 -*- # _author:kaliarch from aliyunsdkcore import client from aliyunsdkecs.request.v20140526 import RebootInstanceRequest,StartInstanceRequest,StopInstanceRequest import time import os import logging class ecsOper(): def __init__(self,logger): self.clentoper = client.AcsClient('<accessKeyId>', '<accessSecret>', 'cn-hangzhou') self.logger = logger self.logger.info("------------------------start reboot *** ecs of API log-------------") def reboot_instance(self): # 设置参数 request = RebootInstanceRequest.RebootInstanceRequest() request.set_accept_format('json') request.add_query_param('InstanceId', 'i-bpxxzx1rlsgvclq79au') # 发起请求 response = self.clentoper.do_action_with_exception(request) self.logger.info("public ecs *** reboot successful!") self.logger.info(response) print(response) def start_instance(self): request = StartInstanceRequest.StartInstanceRequest() request.set_accept_format('json') request.add_query_param('InstanceId', 'i-bpxxzx1rlsgvclq79au') # 发起请求 response = self.clentoper.do_action_with_exception(request) self.logger.info("public ecs *** start successful!") self.logger.info(response) print(response) def stop_instance(self): request = StopInstanceRequest.StopInstanceRequest() request.set_accept_format('json') request.add_query_param('InstanceId', 'i-bp1djzd1rlsgvclq79au') request.add_query_param('ForceStop', 'false') # 发起请求 response = self.clentoper.do_action_with_exception(request) request.add_query_param('InstanceId', 'i-bpxxzxd1rlsgvclq79au') self.logger.info(response) print(response) def testlog(self): self.logger.info("public test log") class Glp_Log: def __init__(self,filename): self.filename = filename def createDir(self): _LOGDIR = os.path.join(os.path.dirname(__file__), 'publiclog') print(_LOGDIR) _TIME = time.strftime('%Y-%m-%d', time.gmtime()) + '-' _LOGNAME = _TIME + self.filename print(_LOGNAME) LOGFILENAME = os.path.join(_LOGDIR, _LOGNAME) print(LOGFILENAME) if not os.path.exists(_LOGDIR): os.mkdir(_LOGDIR) return LOGFILENAME print(LOGFILENAME) def createlogger(self,logfilename): logger= logging.getLogger() logger.setLevel(logging.INFO) handler = logging.FileHandler(logfilename) handler.setLevel(logging.INFO) formater = logging.Formatter('%(asctime)s - %(name)s - %(levelname)s - %(message)s') handler.setFormatter(formater) logger.addHandler(handler) return logger if __name__ == "__main__": glploger = Glp_Log('public-***.log') logfilename = glploger.createDir() logger = glploger.createlogger(logfilename) app = ecsOper(logger) app.reboot_instance()
查看检查脚本日志已经进行了切割,且保留7天的日志,防止日志过大占用过多磁盘空间
微信告警信息
钉钉告警信息
查看python脚本深信服重启日志json
其简单的实现了故障自愈,利用其思路客户配合不少业务,例如简单的应用重启等。bootstrap