Python对mdadm组建的RAID软列阵定时检测异常自动短信/电话通知
基于mysubmail接口发送短信、电话语音通知。创建脚本后可以通过crontab -e每小时或半小时运行一次,例如:
/30 * python /etc/weed/checkRAID.py
可以在raid出现异常状态时快速获知及时处理,避免故障扩大。
# -*- coding: utf-8 -*-
#!/usr/bin/python
import os
import requests
node = '香港vps-nvmenode-1'
error = 0
def get_status(value):
try:
status = value.split(": ")
return status[1].strip()
except:
return False
def send_warning():
global node
# 语音通知
voice_url = 'http://api.mysubmail.com/voice/send.json'
voice_params = { 'appid': '*****',
'to': '13200000000',
'content': '紧急事态:'+node+'硬盘状态异常,请立即检查',
'signature': '**************'
}
#voice_res = requests.post(voice_url, data=voice_params)
# print voice_res.text
# 短信通知
message_url = 'http://api.mysubmail.com/message/send.json'
message_params = { 'appid': '*****',
'to': '13200000000',
'content': '【XXX】紧急事态:'+node+'硬盘状态异常,请立即检查',
'signature': '**************'
}
message_res = requests.post(message_url, data=message_params)
# print(message_res.text)
# 检查RAID状态,注意/dev/md10是变动参数,自行fdisk -l查看你的软列阵磁盘名称,如raid1则为/dev/md1
raidinfos = os.popen('mdadm -D /dev/md10').readlines()
for raidinfo in raidinfos:
raidinfo = raidinfo.strip('\n')
print(raidinfo)
if "State : " in raidinfo:
status = get_status(raidinfo)
if status != 'active' and status != 'active, checking':
error = 1
if "Failed Devices : " in raidinfo:
status = get_status(raidinfo)
if status != '0':
error = 1
if "Active Devices : " in raidinfo:
status = get_status(raidinfo)
if status != '2':
error = 1
# 发送通知
if error == 1:
send_warning()