云平台服务运行情况检测脚本V0.1

Posted 2020-10-04 黄海的编程知识世界

tags:

篇首语：本文由小常识网(cha138.com)小编为大家整理，主要介绍了云平台服务运行情况检测脚本V0.1相关的知识，希望对你有一定的参考价值。

1、准备Python3环境

yum groupinstall "Development tools" -y
yum install zlib-devel bzip2-devel openssl-devel ncurses-devel sqlite-devel readline-devel tk-devel gdbm-devel db4-devel libpcap-devel xz-devel -y
cd /usr/local/software && wget https://www.python.org/ftp/python/3.6.2/Python-3.6.2.tgz
tar xf Python-3.6.2.tgz
cd Python-3.6.2
./configure -prefix=/usr/local/python -enable-shared
make && make install
ln -s /usr/local/python/bin/python3 /usr/bin/python3

3、在运行Python之前需要配置库：

echo /usr/local/python/lib >> /etc/ld.so.conf.d/local.conf && ldconfig

4、运行演示：
python3 -V
Python 3.6.2

5、升级一下pip
pip3 install --upgrade pip

2、脚本内容 /usr/local/checkall.py

执行方式：

cd /usr/local/

python3 checkall.py

import subprocess as t
import time
import os, sys
import socket
import requests
import redis

# ===============================================================================================================
# pip3 install requests
# pip3 install redis
# ===============================================================================================================
# 地区名称
Area_Name = ‘199测试服务器‘

# 是否需要检查Tomcat2
NeedCheckTomcat2 = False

# 数据库所在的IP
DB_IP = ‘127.0.0.1‘

# WEB所在的IP
WEB_IP = ‘127.0.0.1‘

RedisPort = 6379
NeedCheckPort = {‘mysql服务‘: 22066, ‘REDIS服务‘: RedisPort, ‘SSDB服务‘: 8888, ‘nginx服务‘: 80, ‘ICOMET服务‘: 8000,
                 ‘RABBITMQ服务‘: 4369}

SphinxList = [‘/usr/local/sphinx/etc/csft.conf‘,
              ‘/usr/local/sphinx/etc/csft_member.conf‘,
              ‘/usr/local/sphinx/etc/csft_paper.conf‘,
              ‘/usr/local/sphinx/etc/csft_tk.conf‘,
              ‘/usr/local/sphinx/etc/csft_tk_my.conf‘,
              ‘/usr/local/sphinx/etc/csft_group.conf‘,
              ‘/usr/local/sphinx/etc/csft_my.conf‘,
              ‘/usr/local/sphinx/etc/csft_paper_my.conf‘,
              ‘/usr/local/sphinx/etc/csft_cloud.conf‘,
              ‘/usr/local/sphinx/etc/csft_wkds.conf‘,
              ‘/usr/local/sphinx/etc/csft_publish.conf‘,
              ‘/usr/local/sphinx/etc/csft_publish_resource.conf‘,
              ‘/usr/local/sphinx/etc/csft_publish_paper.conf‘,
              ‘/usr/local/sphinx/etc/csft_publish_wk.conf‘,
              ‘/usr/local/sphinx/etc/csft_zy.conf‘,
              ‘/usr/local/sphinx/etc/csft_news.conf‘,
              ‘/usr/local/sphinx/etc/csft_kyyj.conf‘,
              ‘/usr/local/sphinx/etc/csft_xzt.conf‘,
              ‘/usr/local/sphinx/etc/csft_hd.conf‘,
              ‘/usr/local/sphinx/etc/csft_allpublish.conf‘,
              ‘/usr/local/sphinx/etc/csft_wktostudent.conf‘,
              ‘/usr/local/sphinx/etc/csft_bbs_topic.conf‘,
              ‘/usr/local/sphinx/etc/csft_bbs_post.conf‘,
              ‘/usr/local/sphinx/etc/csft_notice.conf‘,
              ‘/usr/local/sphinx/etc/csft_blog_article.conf‘,
              ‘/usr/local/sphinx/etc/csft_supervise.conf‘,
              ‘/usr/local/sphinx/etc/csft_seach.conf‘
              ]


# ===============================================================================================================
# 检查指定IP的服务端口
def check_port(address, port):
    s = socket.socket(socket.AF_INET, socket.SOCK_STREAM)
    s.settimeout(3)
    try:
        s.connect((address, port))
        s.close()
        return True
    except Exception as e:
        s.close()
        return False


# 检查磁盘
def check_disk():
    # 检查是不是存在指定的MOUNT盘
    var = t.getoutput("df -h | cat -n ")
    success = False
    for line in var.split("\n"):
        if ‘/usr/local/tomcat7/webapps/dsideal_yy/html/down‘ in line:
            success = True
    if not success:
        return False
    # 尝试写入文件，是不是正常
    try:
        testFile = ‘/usr/local/tomcat7/webapps/dsideal_yy/html/down/test.txt‘
        with open(testFile, ‘w‘) as data:
            print(time.strftime(‘%Y-%m-%d %H:%M:%S‘, time.localtime(time.time())), file=data)  # 输出默认为sys.stdout
            success = True
        os.remove(testFile)
    except IOError as err:
        success = False
    return success


# 检查服务端口
def check_serviceport():
    for (k, v) in NeedCheckPort.items():
        success = check_port(DB_IP, NeedCheckPort[k])
        if not success:
            return k


# 检查 Tomcat
def check_Tomcat():
    var = t.getoutput("ps -ef | grep tomcat")
    success = False
    for line in var.split("\n"):
        if ‘/usr/local/tomcat7/conf/logging.properties‘ in line:
            success = True

    if not success:
        return False

    # 判断是不是 Tomcat僵死掉
    try:
        requests.get("http://" + WEB_IP + "/dsideal_yy/adminlogin/captchaText", timeout=1)
    except requests.exceptions.ConnectTimeout:
        return False
    except requests.exceptions.Timeout:
        return False

    # 判断验证码是不是能正常生成？
    r = requests.get("http://" + WEB_IP + "/dsideal_yy/adminlogin/captchaText")
    if r.status_code != 200:
        return False
    else:
        # 下载图片
        try:
            r = requests.get("http://" + WEB_IP + "/dsideal_yy/adminlogin/captchaImage?text=" + r.json()[‘text‘])
            with open(‘/usr/local/software/picture.jpg‘, ‘wb‘) as file:
                file.write(r.content)
            # 用完就删除了吧
            os.remove(‘/usr/local/software/picture.jpg‘)
            return True
        except Exception as err:
            print(‘Tomcat检查发现异常：‘ + str(err))
            return False


# 判断 Tomcat2
def check_Tomcat2():
    var = t.getoutput("ps -ef | grep tomcat")
    success = False
    for line in var.split("\n"):
        if ‘/usr/local/tomcat7_2/conf/logging.properties‘ in line:
            success = True
    return success


# 检查是否存在检查挂盘定时任务
def check_disk_crontab():
    file = open(‘/etc/crontab‘)
    success = False
    for line in file:
        # 每分钟进行检查
        if ‘* * * * * root  /usr/local/checkdisk.sh > /dev/null 2>&1‘ in line:
            success = True
    file.close()
    return success


# 检查磁盘的定时脚本是不是与启动脚本中的挂载方式一致
def check_diskShAndRcLocal():
    typeA = ‘‘
    file = open(‘/usr/local/checkdisk.sh‘)
    for line in file:
        if ‘sshfs -o nonempty,allow_other,reconnect‘ in line:
            typeA = ‘ssh‘
        if ‘mount -t cifs -o‘ in line:
            typeA = ‘samba‘
    file.close()

    typeB = ‘‘
    file = open(‘/etc/rc.d/rc.local‘)
    for line in file:
        if ‘sshfs -o nonempty,allow_other,reconnect‘ in line:
            typeB = ‘ssh‘
        if ‘mount -t cifs -o‘ in line:
            typeB = ‘samba‘
    file.close()

    if typeA == ‘ssh‘:
        print("########################################################################################")
        print(‘########发现现在在使用sshfs方式挂盘，如果可能 ，还是建议使用samba的方式进行挂盘!########‘)
        print("########################################################################################")
    if typeA == typeB and typeA != ‘‘:
        return True
    else:
        return False


# 检查处理程序的状态
def checkWinFormExist():
    try:
        r = redis.Redis(host=DB_IP, port=RedisPort, db=0)
        # r.set(‘WinForm_GetSwf‘,11111)
        ret = r.get(‘WinForm_GetSwf‘)
        if ret is None:
            return False
        else:
            return True
    except Exception as err:
        print(‘Redis访问异常：‘ + str(err))
        return False


# 检查sphinx服务状态
def checkSphinx():
    for c in SphinxList:
        var = t.getoutput(‘ps -ef | grep ‘ + c + ‘ | grep -v grep‘)
        n = 0
        for line in var.split("\n"):
            n = n + 1

        if n == 0:
            print(‘Sphinx检查失败：‘ + c)
            return c


# 检查sphinx 定时增量索引的配置是否正确
def checkSphinxInc():
    SphinxShList = []
    for c in SphinxList:
        a = c.replace(‘.conf‘, ‘.sh‘).replace(‘/usr/local/sphinx/etc/‘, ‘/usr/local/sphinx_sh/‘)
        SphinxShList.append(a)

    for c in SphinxShList:
        Found = False
        with open(‘/etc/crontab‘, ‘r‘) as f:
            for line in f:
                if c in line:
                    Found = True
                    break
                else:
                    Found = False
            if not Found:
                return c


# 检查sphinx 在自启动脚本中是不是存在
def checkSphinxRcLocal():
    for c in SphinxList:
        with open(‘/etc/rc.d/rc.local‘, ‘r‘) as f:
            Found = False
            for line in f:
                if c in line:
                    Found = True
                    break
                else:
                    Found = False
            if not Found:
                return c


if __name__ == "__main__":
    # 检查磁盘
    if not check_disk():
        print(‘1、磁盘检查失败，请马上处理！‘)
        sys.exit()
    else:
        print(‘1、磁盘检查成功！‘)

    # 检查Tomcat
    if not check_Tomcat():
        print(‘2、Tomcat检查失败，请马上处理！‘)
        sys.exit()
    else:
        print(‘2、Tomcat检查成功！‘)

    # 检查Tomcat2,各地区不一样，有的需要进行检查
    if NeedCheckTomcat2:
        if not check_Tomcat2():
            print(‘3、Tomcat_2检查失败，请马上处理！‘)
            sys.exit()
        else:
            print(‘3、Tomcat_2检查成功！‘)

    # 检查端口
    ret = check_serviceport()
    if ret != None:
        print(‘4、‘ + ret + ‘端口检查失败，请马上处理！‘)
        sys.exit()
    else:
        print(‘4、端口检查成功！‘)

    # 检查定时磁盘检查
    if not check_disk_crontab():
        print(‘5、磁盘定时探测服务检查失败，请马上处理！‘)
        sys.exit()
    else:
        print(‘5、磁盘定时探测服务检查成功！‘)

    # 检查磁盘探测程序是不是与启动脚本中的挂载磁盘方式一致？
    if not check_diskShAndRcLocal():
        print(‘6、磁盘挂载方式不一致，请马上处理！‘)
        sys.exit()
    else:
        print(‘6、磁盘挂载方式一致性检查成功！‘)

    # 检查处理程序的状态
    if not checkWinFormExist():
        print(‘7、处理程序没有正确开启，请马上处理！‘)
        sys.exit()
    else:
        print(‘7、处理程序检查成功！‘)

    # 检查Sphinx服务状态
    ret = checkSphinx()
    if ret != None:
        print(‘8、检查Sphinx失败，‘ + ret + ‘,请马上处理！‘)
        sys.exit()
    else:
        print(‘8、检查Sphinx成功完成！‘)

    # 检查Sphinx增量脚本的编写
    ret = checkSphinxInc()
    if ret != None:
        print(‘9、检查Sphinx增量索引失败，‘ + ret + ‘,请马上处理！‘)
        sys.exit()
    else:
        print(‘9、检查Sphinx增量索引完成！‘)

        # 检查Sphinx自启动脚本的编写
        ret = checkSphinxRcLocal()
        if ret != None:
            print(‘10、检查Sphinx自启动脚本失败，‘ + ret + ‘,请马上处理！文件位置：/etc/crontab‘)
            sys.exit()
        else:
            print(‘10、检查Sphinx自启动脚本完成！‘)

    print(‘恭喜，所有检查成功完成！没有发现异常！‘)

以上是关于云平台服务运行情况检测脚本V0.1的主要内容，如果未能解决你的问题，请参考以下文章

通过云服务器租用GPU进行基于YOLOV5的人体检测模型训练

检测 VM 中的云类型