监控服务器资源利用率的客户端脚本

麦辣鸡腿堡 2023-01-22 528

描述

客户端脚本：

端脚本：

- - coding:utf-8 - -

import io

import os

import sys

import time

import datetime

import socket

import commands

import logging

from logging import handlers

import psutil

import struct

import fcntl

if sys.getdefaultencoding() != 'utf-8':

reload(sys)

sys.setdefaultencoding('utf-8')

class Logger(object):

level_relations = {

'debug': logging.DEBUG,

'info': logging.INFO,

'warning': logging.WARNING,

'error': logging.ERROR,

'crit': logging.CRITICAL

} # 日志级别关系映射

def init (self,logname, level='info', when='D', backCount=10, fmt='%(asctime)s - %(pathname)s[line:%(lineno)d] - %(levelname)s: %(message)s'):

CURRENT_DIR = os.path.dirname(file)

LOG_FILE = os.path.abspath(os.path.join(CURRENT_DIR, logname))

self.logger = logging.getLogger(LOG_FILE)

format_str = logging.Formatter(fmt) # 设置日志格式

self.logger.setLevel(self.level_relations.get(level)) # 设置日志级别

sh = logging.StreamHandler() # 往屏幕上输出

sh.setFormatter(format_str) # 设置屏幕上显示的格式

th = handlers.TimedRotatingFileHandler(

filename=LOG_FILE, when=when, backupCount=backCount, encoding='utf-8') # 往文件里写入#指定间隔时间自动生成文件的处理器

#实例化TimedRotatingFileHandler

#interval是时间间隔，backupCount是备份文件的个数，如果超过这个个数，就会自动删除，when是间隔的时间单位，单位有以下几种：

S 秒

M 分

H 小时、

D 天、

W 每星期（interval==0时代表星期一）

midnight 每天凌晨

th.setFormatter(format_str) # 设置文件里写入的格式

#self.logger.addHandler(sh) # 把对象加到logger里

if not self.logger.handlers:

self.logger.addHandler(th)

class clientMonitor(object):

#获取指定网卡ip

def getIpAddress(self,dev):

s = socket.socket(socket.AF_INET, socket.SOCK_DGRAM)

a = s.fileno()

b = 0x8915

c = struct.pack('256s', dev[:15])

res = fcntl.ioctl(a, b, c)[20:24]

return socket.inet_ntoa(res)

#获取网络的使用情况 ,取的是eth0的发送和收取的总字节数

#readNetInfo('eth0')

def readNetInfo(self,dev):

f = open('/proc/net/dev')

lines = f.readlines()

f.close()

res = {'in':0, 'out':0}

for line in lines:

if line.lstrip().startswith(dev):

for centos

line = line.replace(':', ' ')

items = line.split()

res['in'] = long(items[1])#/1024

res['out'] = long(items[len(items)/2 + 1])#/1024

return res

def readNetInfo_new(self,dev):

res = {'in':0, 'out':0}

res['in'] = psutil.net_io_counters(pernic=True).get(dev).bytes_recv

res['out'] = psutil.net_io_counters(pernic=True).get(dev).bytes_sent

return res

#磁盘使用率，path：磁盘路径

def disk_stat(self,path):

hd={}

disk = os.statvfs(path)

percent = (disk.f_blocks - disk.f_bfree) * 100 / (disk.f_blocks -disk.f_bfree + disk.f_bavail) + 1

return percent

def net_loop(self,dev):

#end = {'in':0, 'out':0}

res = self.readNetInfo_new(dev)

#推迟执行的秒数

time.sleep(2)

#new_recv,new_send = get_net_data()

new_res = self.readNetInfo_new(dev)

recv_data = (new_res['in']-res['in'])/1024/1024

send_data = (new_res['out']-res['out'])/1024/1024

print ("recv_data: %s M, send_data: %s M"%(recv_data, send_data))

return recv_data,send_data

def processcheck(self,cmd):

#cmd='ps -aux | sort -k3nr | head -1'

(status,output) = commands.getstatusoutput(cmd)

#Pid= output.split(' ')[6]

log.logger.info('资源占用top:\\n'+output)

#查看占用内存最高的进程的PID

#ps aux|head -1;ps aux|grep -v PID|sort -rn -k +4|head

#ps -aux | sort -k4nr | head -1 ,-k3 cpu占用最高，-k4 内存占用最高

#root 14668 1.9 0.0 90504 3256 ? Ss 4月23 2811:48 /sbin/rngd -f

#索引：-k3 b.split(' ')[6] 28进程路径（/sbin/rngd）

#索引：-k4 b.split(' ')[4]

if name == " main ":

#10分钟执行一次，数据上报到服务端，服务端负责报警

#需要修改的参数：custom,deviceType,netName

custom ='test'

deviceType ='客户端服务器'

#网卡名称

netName = 'ens3f0'

log = Logger('socketclient.logs')

log.logger.info("----start----")

info=clientMonitor()

locatIp = info.getIpAddress(netName)

recv_data,send_data = info.net_loop(netName)

cpuinfo = psutil.cpu_percent(1)

#svmem(total=67268558848, available=32022245376, percent=52.4, used=34601009152, free=29655695360, active=17274105856, inactive=2927910912, buffers=10100736, cached=3001753600, shared=298610688, slab=11243315200)

svmem = psutil.virtual_memory()

meminfo = svmem[2]

disk_root = info.disk_stat('/')

disk_appslog = info.disk_stat('/appslog')

disk_bigdata = info.disk_stat('/bigdata')

#如果CPU或内存的占用率大于80%，将占用CPU或内存资源最多的进程找出来

issendmsg =1

if(cpuinfo>80 or meminfo>80 or disk_root>80 or disk_appslog>80 or disk_bigdata>80 or recv_data>3000 or send_data>3000):

#发送预警邮件

sendmsg=locatIp +' 服务器资源占用高！请检查！\\n'

sendmsg += "CPU占用："+str(cpuinfo)+'\\n'

sendmsg += "内存占用："+str(meminfo)+'\\n'

sendmsg += "/目录占用："+str(disk_root)+'\\n'

sendmsg += "/appslog目录占用："+str(disk_appslog)+'\\n'

sendmsg += "/bigdata目录占用："+str(disk_bigdata)+'\\n'

sendmsg += "网卡接收流量："+str(recv_data)+'M,发送流量 '+str(send_data)+'M \\n'

#sendmsg += "网卡10秒发送流量："+str(send_data)+'\\n'

log.logger.info(sendmsg)

if cpuinfo>80 :

info.processcheck('ps -aux | sort -k3nr | head -10')

if meminfo>80 :

info.processcheck('ps -aux | sort -k4nr | head -10')

issendmsg = 1

else:

#log.logger.info(locatIp+" 正常")

log.logger.info("CPU使用率："+str(cpuinfo))

log.logger.info("内存使用率："+str(meminfo))

log.logger.info("/目录使用率："+str(disk_root))

log.logger.info("/appslog使用率："+str(disk_appslog))

log.logger.info("/bigdata使用率："+str(disk_bigdata))

log.logger.info("网卡接收和发送情况：接收"+str(recv_data) +"M，发送 "+str(send_data)+"M")

#Id,custom,deviceType,IP,cpu,mem,disk_root,disk_appslog,disk_bigdata,networkRecv,networkSend,uploadTime,temp2,temp3,temp4

if issendmsg ==1:

ip_port = ('IP',port)

sk = socket.socket()

sk.connect(ip_port)

sk.sendall(msg)

data = sk.recv(1024)

if data=='1':

log.logger.info("本地预警信息传输成功！")

else:

log.logger.info("本地预警信息传输失败！")

sk.sendall('exit')

sk.close()

原文链接：https://blog.csdn.net/eagle89/article/details/128579002

打开APP阅读更多精彩内容