Zabbix自定义监控

监控指标

• 系统指标（内存、CPU、硬盘）
• 文件监控
• 网络监控
• 硬件监控（硬盘温度、电源是否异常、CPU温度），通过IPMI实现
• 业务监控

自定义监控流程：

1. 开启自定义监控的功能：

   在agentd.conf中设置，

   ​ UnsafeUserParameters=1

   ​ UserParameters=key,command

2. 写脚本

3. 网页上配置监控项、触发器

 

自定义监控进程

注意事项

• 脚本放哪里
• 脚本让谁执行
• 规范化

写脚本+开启自定义监控功能

[root@cxx ~]# mkdir /scripts
//编写监控脚本
[root@cxx ~]# vim /scripts/check_process.sh

#!/bin/bash

count=$(ps -ef | grep -Ev "grep|$0" | grep -c "$1")
if [ $count -eq 0 ];then
                echo "1"
        else
                        echo "0"
                fi

[root@cxx ~]# chmod +x /scripts/check_process.sh
//开启httpd测试
[root@cxx ~]# systemctl start httpd
[root@cxx ~]# ss -antl
State      Recv-Q      Send-Q            Local Address:Port            Peer Address:Port     
LISTEN     0           128                     0.0.0.0:22                   0.0.0.0:*        
LISTEN     0           128                     0.0.0.0:10050                0.0.0.0:*        
LISTEN     0           128                        [::]:22                      [::]:*        
LISTEN     0           128                           *:80                         *:*        
[root@cxx ~]# /scripts/check_process.sh httpd
0
//关闭httpd测试
[root@cxx ~]# systemctl stop httpd
[root@cxx ~]# ss -antl
State      Recv-Q      Send-Q            Local Address:Port            Peer Address:Port     
LISTEN     0           128                     0.0.0.0:22                   0.0.0.0:*        
LISTEN     0           128                     0.0.0.0:10050                0.0.0.0:*        
LISTEN     0           128                        [::]:22                      [::]:*        
[root@cxx ~]# /scripts/check_process.sh httpd
1
//在文件最后面加入两行代码
[root@cxx ~]# vim /usr/local/etc/zabbix_agentd.conf
UnsafeUserParameters=1
UserParameter=check_apache,/scripts/check_process.sh /usr/local/apache/bin/httpd
[root@cxx ~]# pkill zabbix
[root@cxx ~]# zabbix_agentd 
[root@cxx ~]# ss -antl
State      Recv-Q      Send-Q            Local Address:Port            Peer Address:Port     
LISTEN     0           128                     0.0.0.0:22                   0.0.0.0:*        
LISTEN     0           128                     0.0.0.0:10050                0.0.0.0:*        
LISTEN     0           128                        [::]:22                      [::]:*   
//使用服务端测试是否能获取客户端的指标
[root@zabbix ~]# zabbix_get -s 192.168.100.2 -k check_apache
1

 

 

 

 

 

 

 

 

 

 

 

 

 

 

配置监控日志流程

[root@zabbix ~]# cd /scripts/
[root@zabbix scripts]# dnf -y install python36
[root@zabbix scripts]# vim log.py 

#!/usr/bin/env python3
import sys
import re

def prePos(seekfile):
    global curpos
    try:
        cf = open(seekfile)
    except IOError:
        curpos = 0
        return curpos
    except FileNotFoundError:
        curpos = 0
        return curpos
    else:
        try:
            curpos = int(cf.readline().strip())
        except ValueError:
            curpos = 0
            cf.close()
            return curpos
        cf.close()
    return curpos

def lastPos(filename):
    with open(filename) as lfile:
        if lfile.readline():
            lfile.seek(0,2)
        else:
            return 0
        lastPos = lfile.tell()
    return lastPos

def getSeekFile():
    try:
        seekfile = sys.argv[2]
    except IndexError:
        seekfile = '/tmp/logseek'
    return seekfile

def getKey():
    try:
        tagKey = str(sys.argv[3])
    except IndexError:
        tagKey = 'Error'
    return tagKey

def getResult(filename,seekfile,tagkey):
    destPos = prePos(seekfile)
    curPos = lastPos(filename)

    if curPos < destPos:
        curpos = 0

    try:
        f = open(filename)
    except IOError:
        print('Could not open file: %s' % filename)
    except FileNotFoundError:
        print('Could not open file: %s' % filename)
    else:
        f.seek(destPos)

        while curPos != 0 and f.tell() < curPos:
            rresult = f.readline().strip()
            global result
            if re.search(tagkey, rresult):
                result = 1
                break
            else:
                result = 0

        with open(seekfile,'w') as sf:
            sf.write(str(curPos))
    finally:
        f.close()
    return result

if __name__ == "__main__":
    result = 0
    curpos = 0
    tagkey = getKey()
    seekfile = getSeekFile()
    result = getResult(sys.argv[1],seekfile,tagkey)
    print(result)

[root@zabbix scripts]# chmod +x log.py 
[root@zabbix scripts]# touch /usr/local/apache/logs/error.log
//在文件最后添加
[root@zabbix scripts]# vim /usr/local/etc/zabbix_agentd.conf
UserParameter=check_logs[*],/scripts/log.py $1 $2 $3

[root@zabbix scripts]# pkill zabbix
[root@zabbix scripts]# zabbix_agentd

 

 

 

 

 

 

 

 

监控客户端的mysql主从状态

[root@zabbix scripts]# vim check_mysql_repl.sh

#!/bin/bash
  
count=$(mysql -uroot -e 'show slave status\G'|grep ' Running:'|awk '{print $2}'|grep -c 'Yes')
if [ $count -ne 2 ];then
                echo '1'
        else
                        echo '0'
                fi
                
[root@zabbix scripts]# vim /usr/local/etc/zabbix_agentd.conf
UserParameter=check_mysql_repl,/scripts/check_mysql_repl.sh

[root@zabbix scripts]# pkill zabbix
[root@zabbix scripts]# zabbix_agentd