一、ServerStatus 介绍

ServerStatus 是一个酷炫高逼格的云探针、云监控、服务器云监控、多服务器探针~。 ServerStatus开源地址：https://github.com/cppla/ServerStatus ### 特性 + 使用 Rust 完全重写 Server、Client，单个执行文件部署 + 支持上下线和简单自定义规则告警 (Telegram、 Wechat、 Email、 Webhook) + 支持 http 协议上报，可以方便部署到各免费容器服务和配合 cf 等优化上报链路 + 支持 vnstat 统计月流量，重启不丢流量数据 + 支持 Railway 快速部署 + 支持 Systemd 开机自启

ServerStatus一个酷炫的云监控神器 - 图1

二、检查宿主机系统版本

  1. cat /etc/os-release

三、检查本地 Docker 环境

检查 Docker 服务状态 
  1. // 1) 低版本 Docker 安装
  2. yum install docker -y
  4. ----
  5. // < '推荐' >
  6. // 2) 高版本 Docker 安装
  7. curl -fsSL https://get.docker.com/ | sh
  9. ----
  10. // 关闭防火墙
  11. systemctl disable --now firewalld
  12. setenforce 0
  14. // 启用 Docker
  15. systemctl enable --now docker
检查 Docker 配置信息 
  1. docker info
开启 IPv4 forwarding 
  1. echo "net.ipv4.ip_forward=1" >>  /etc/sysctl.conf
  2. systemctl restart network
  3. sysctl net.ipv4.ip_forward

四、安装 Docker-compose

下载 Docker-compose 二进制包 
  1. curl -L https://github.com/docker/compose/releases/download/v2.2.2/docker-compose-linux-x86_64 -o /usr/local/bin/docker-compose
给文件增加执行权限 
  1. chmod +x /usr/local/bin/docker-compose
检查 Docker-compose 版本 
  1. docker-compose -v

五、下载 ServerStatus 镜像

  1. docker pull stilleshan/serverstatus

六、使用 Docker-cli 部署

  1. mkdir /docker/ServerStatus/server -p && cd /docker/ServerStatus/server
  1. ( 省略 )
  2. docker run -d --name=serverstatus --restart=always \
  3.   -p 8888:80 \
  4.   -p 35601:35601 \
  5.   -v /docker/ServerStatus/server/config.json:/ServerStatus/server/config.json \
  6.   stilleshan/serverstatus

七、下载 ServerStatus 安装文件

创建数据目录 
  1. mkdir /docker/ServerStatus/server -p && cd /docker/ServerStatus/server
下载安装文件 
  1. yum install git -y
  1. git clone https://github.com/stilleshan/ServerStatus.git
  1. [root@localhost ServerStatus]# ls
  2. config.json  docker-compose.yml  Dockerfile  README.md  screenshot.jpg  status.sh  web
查看 Docker-compose.yaml 文件 
  1. [root@localhost ServerStatus]# vim docker-compose.yml
  2. version: "3"
  3. services:
  4.   serverstatus:
  5.     image: stilleshan/serverstatus
  6.     container_name: serverstatus
  7.     ports:
  8.       - 8888:80
  9.       - 35601:35601
  10.     volumes:
  11.       # - ./web:/usr/share/nginx/html
  12.       - ./config.json:/ServerStatus/server/config.json
  13.     environment:
  14.       TZ: Asia/Shanghai
  15.     restart: always
创建 ServerStatus 容器 
  1. docker-compose up -d
查看 ServerStatus 容器状态 
  1. docker ps

ServerStatus一个酷炫的云监控神器 - 图2

八、访问 ServerStatus 服务端

ServerStatus一个酷炫的云监控神器 - 图3

九、客户端安装

修改 status-client.py 
  1. [root@node01 ~] vim status-client.py 
  2. # -*- coding: utf-8 -*-
  4. SERVER = "192.168.80.8"    # 填写服务器地址
  5. PORT = 35601
  6. USER = "admin"             # 设置账号 ( 待会需要在服务端填写 )
  7. PASSWORD = "admin"        # 设置密码 ( 待会需要在服务端填写 )
  8. INTERVAL = 1             # 更新间隔, 单位: 秒
  11. import socket
  12. import time
  13. import string
  14. import math
  15. import re
  16. import os
  17. import json
  18. import subprocess
  19. import collections
  20. import platform
  22. def get_uptime():
  23.     f = open('/proc/uptime', 'r')
  24.     uptime = f.readline()
  25.     f.close()
  26.     uptime = uptime.split('.', 2)
  27.     time = int(uptime[0])
  28.     return int(time)
  30. def get_memory():
  31.     re_parser = re.compile(r'^(?P<key>\S*):\s*(?P<value>\d*)\s*kB')
  32.     result = dict()
  33.     for line in open('/proc/meminfo'):
  34.         match = re_parser.match(line)
  35.         if not match:
  36.             continue;
  37.         key, value = match.groups(['key', 'value'])
  38.         result[key] = int(value)
  40.     MemTotal = float(result['MemTotal'])
  41.     MemFree = float(result['MemFree'])
  42.     Cached = float(result['Cached'])
  43.     MemUsed = MemTotal - (Cached + MemFree)
  44.     SwapTotal = float(result['SwapTotal'])
  45.     SwapFree = float(result['SwapFree'])
  46.     return int(MemTotal), int(MemUsed), int(SwapTotal), int(SwapFree)
  48. def get_hdd():
  49.     p = subprocess.check_output(['df', '-Tlm', '--total', '-t', 'ext4', '-t', 'ext3', '-t', 'ext2', '-t', 'reiserfs', '-t', 'jfs', '-t', 'ntfs', '-t', 'fat32', '-t', 'btrfs', '-t', 'fuseblk', '-t', 'zfs', '-t', 'simfs', '-t', 'xfs']).decode("Utf-8")
  50.     total = p.splitlines()[-1]
  51.     used = total.split()[3]
  52.     size = total.split()[2]
  53.     return int(size), int(used)
  55. def get_load():
  56.     system = platform.linux_distribution()
  57.     if system[0][:6] == "CentOS":
  58.         if system[1][0] == "6":
  59.             tmp_load = os.popen("netstat -anp |grep ESTABLISHED |grep tcp |grep '::ffff:' |awk '{print $5}' |awk -F ':' '{print $4}' |sort -u |grep -E -o '([0-9]{1,3}[\.]){3}[0-9]{1,3}' |wc -l").read()
  60.         else:
  61.             tmp_load = os.popen("netstat -anp |grep ESTABLISHED |grep tcp6 |awk '{print $5}' |awk -F ':' '{print $1}' |sort -u |grep -E -o '([0-9]{1,3}[\.]){3}[0-9]{1,3}' |wc -l").read()
  62.     else:
  63.         tmp_load = os.popen("netstat -anp |grep ESTABLISHED |grep tcp6 |awk '{print $5}' |awk -F ':' '{print $1}' |sort -u |grep -E -o '([0-9]{1,3}[\.]){3}[0-9]{1,3}' |wc -l").read()
  65.     return float(tmp_load)
  66. #return os.getloadavg()[0]
  68. def get_time():
  69.     stat_file = file("/proc/stat", "r")
  70.     time_list = stat_file.readline().split(' ')[2:6]
  71.     stat_file.close()
  72.     for i in range(len(time_list))  :
  73.         time_list[i] = int(time_list[i])
  74.     return time_list
  75. def delta_time():
  76.     x = get_time()
  77.     time.sleep(INTERVAL)
  78.     y = get_time()
  79.     for i in range(len(x)):
  80.         y[i]-=x[i]
  81.     return y
  82. def get_cpu():
  83.     t = delta_time()
  84.     st = sum(t)
  85.     if st == 0:
  86.         st = 1
  87.     result = 100-(t[len(t)-1]*100.00/st)
  88.     return round(result)
  90. class Traffic:
  91.     def __init__(self):
  92.         self.rx = collections.deque(maxlen=10)
  93.         self.tx = collections.deque(maxlen=10)
  94.     def get(self):
  95.         f = open('/proc/net/dev', 'r')
  96.         net_dev = f.readlines()
  97.         f.close()
  98.         avgrx = 0; avgtx = 0
  100.         for dev in net_dev[2:]:
  101.             dev = dev.split(':')
  102.             if dev[0].strip() == "lo" or dev[0].find("tun") > -1:
  103.                 continue
  104.             dev = dev[1].split()
  105.             avgrx += int(dev[0])
  106.             avgtx += int(dev[8])
  108.         self.rx.append(avgrx)
  109.         self.tx.append(avgtx)
  110.         avgrx = 0; avgtx = 0
  112.         l = len(self.rx)
  113.         for x in range(l - 1):
  114.             avgrx += self.rx[x+1] - self.rx[x]
  115.             avgtx += self.tx[x+1] - self.tx[x]
  117.         avgrx = int(avgrx / l / INTERVAL)
  118.         avgtx = int(avgtx / l / INTERVAL)
  120.         return avgrx, avgtx
  122. def liuliang():
  123.     NET_IN = 0
  124.     NET_OUT = 0
  125.     with open('/proc/net/dev') as f:
  126.         for line in f.readlines():
  127.             netinfo = re.findall('([^\s]+):[\s]{0,}(\d+)\s+(\d+)\s+(\d+)\s+(\d+)\s+(\d+)\s+(\d+)\s+(\d+)\s+(\d+)\s+(\d+)\s+(\d+)\s+(\d+)', line)
  128.             if netinfo:
  129.                 if netinfo[0][0] == 'lo' or 'tun' in netinfo[0][0] or netinfo[0][1]=='0' or netinfo[0][9]=='0':
  130.                     continue
  131.                 else:
  132.                     NET_IN += int(netinfo[0][1])
  133.                     NET_OUT += int(netinfo[0][9])
  134.     return NET_IN, NET_OUT
  136. def get_network(ip_version):
  137.     if(ip_version == 4):
  138.         HOST = "192.168.80.18"        # 客户端地址
  139.     elif(ip_version == 6):
  140.         HOST = "ipv6.google.com"
  141.     try:
  142.         s = socket.create_connection((HOST, 80), 2)
  143.         return True
  144.     except:
  145.         pass
  146.     return False
  148. if __name__ == '__main__':
  149.     socket.setdefaulttimeout(30)
  150.     while 1:
  151.         try:
  152.             print("Connecting...")
  153.             s = socket.socket(socket.AF_INET, socket.SOCK_STREAM)
  154.             s.connect((SERVER, PORT))
  155.             data = s.recv(1024)
  156.             if data.find("Authentication required") > -1:
  157.                 s.send(USER + ':' + PASSWORD + '\n')
  158.                 data = s.recv(1024)
  159.                 if data.find("Authentication successful") < 0:
  160.                     print(data)
  161.                     raise socket.error
  162.             else:
  163.                 print(data)
  164.                 raise socket.error
  166.             print(data)
  167.             data = s.recv(1024)
  168.             print(data)
  170.             timer = 0
  171.             check_ip = 0
  172.             if data.find("IPv4") > -1:
  173.                 check_ip = 6
  174.             elif data.find("IPv6") > -1:
  175.                 check_ip = 4
  176.             else:
  177.                 print(data)
  178.                 raise socket.error
  180.             traffic = Traffic()
  181.             traffic.get()
  182.             while 1:
  183.                 CPU = get_cpu()
  184.                 NetRx, NetTx = traffic.get()
  185.                 NET_IN, NET_OUT = liuliang()
  186.                 Uptime = get_uptime()
  187.                 Load = get_load()
  188.                 MemoryTotal, MemoryUsed, SwapTotal, SwapFree = get_memory()
  189.                 HDDTotal, HDDUsed = get_hdd()
  191.                 array = {}
  192.                 if not timer:
  193.                     array['online' + str(check_ip)] = get_network(check_ip)
  194.                     timer = 10
  195.                 else:
  196.                     timer -= 1*INTERVAL
  198.                 array['uptime'] = Uptime
  199.                 array['load'] = Load
  200.                 array['memory_total'] = MemoryTotal
  201.                 array['memory_used'] = MemoryUsed
  202.                 array['swap_total'] = SwapTotal
  203.                 array['swap_used'] = SwapTotal - SwapFree
  204.                 array['hdd_total'] = HDDTotal
  205.                 array['hdd_used'] = HDDUsed
  206.                 array['cpu'] = CPU
  207.                 array['network_rx'] = NetRx
  208.                 array['network_tx'] = NetTx
  209.                 array['network_in'] = NET_IN
  210.                 array['network_out'] = NET_OUT
  212.                 s.send("update " + json.dumps(array) + "\n")
  213.         except KeyboardInterrupt:
  214.             raise
  215.         except socket.error:
  216.             print("Disconnected...")
  217.             # keep on trying after a disconnect
  218.             s.close()
  219.             time.sleep(3)
  220.         except Exception as e:
  221.             print("Caught Exception:", e)
  222.             s.close()
  223.             time.sleep(3)
在客户端运行 status-client.py 脚本 
  1. [root@node01 ~] python status-client.py &
  2. [1] 105194
服务端配置 修改 config.json 文件，必须配置项为 username/password/host 
  1. [root@server ServerStatus] vim config.json 
  2. {"servers":
  3.  [
  4.   {
  5.    "username": "admin",     # 客户端账号
  6.    "password": "admin",     # 客户端密码
  7.    "name": "腾讯云-上海",
  8.    "type": "KVM",
  9.    "host": "192.168.80.18",   # 填写客户端 IP 地址
  10.    "location": "CN",
  11.    "disabled": false
  12.   },
  13.   {
  14.    "username": "2",
  15.    "password": "xxx",
  16.    "name": "阿里云-香港",
  17.    "type": "KVM",
  18.    "host": "None",
  19.    "location": "HK",
  20.    "disabled": false
  21.   },
  22.   {
  23.    "username": "3",
  24.    "password": "xxxx",
  25.    "name": "谷歌云-日本",
  26.    "type": "KVM",
  27.    "host": "None",
  28.    "location": "JP",
  29.    "disabled": false
  30.   }
  31.  ]
  32. }
在 Web 监控页查看效果

ServerStatus一个酷炫的云监控神器 - 图4

大功告成~