搭建dell服务器的zabbix硬件监控

1 在每一台被监控的客户端上安装omsa （查看我另一篇文章关于omsa安装的）

 (27条消息) dell服务器硬件监控omsa部署_m0_61626354的博客-CSDN博客

2 cd /etc/zabbix/ #进入zabbix目录下

3 vim /etc/zabbix/zabbix_agent.d/userparameter_hardwarecheck.conf

#到配置文件下写zabbix的参数，这边思路主要是通过/opt下面的脚本去执行omsa命令去获取服务器硬件的状态，如果有故障就输出1，没有就是0

UserParameter=hardware_memory_health, sh /opt/hardware_check.sh memory

UserParameter=hardware_cpu, sh /opt/hardware_check.sh cpu

UserParameter=hardware_physics_health, sh /opt/hardware_check.sh pdisk

UserParameter=hardware_virtual_health, sh /opt/hardware_check.sh vdisk

UserParameter=hardware_raid_health, sh /opt/hardware_check.sh raidcard

4 vim /opt/hardware_check.sh  #到opt下创建脚本

#!/bin/sh

raid_card_exist() {
        /bin/omreport storage controller  > /dev/null
        if [ $? -eq 0 ];then
            /bin/omreport storage controller | grep "^Status "|egrep -v "Ok|Non-Critical"  > /dev/null
            if [ $? -eq 0 ];then
                echo 1
            else
                echo 0
            fi
        else
                echo 2
        fi

}

check_physical_disk() {
        /bin/omreport storage pdisk controller=0|grep "^State "|egrep -v "Online|Ready|Non-Critical" > /dev/null
        if [ $? -eq 0 ];then
                echo 1
        else
                echo 0
        fi
}

check_virtual_disk() {
        /bin/omreport storage vdisk controller=0|grep "^Status "|egrep -v "Ok|Non-Critical" > /dev/null
        if [ $? -eq 0 ];then
                echo 1
        else
                echo 0
        fi
}

check_memory() {
        /bin/omreport chassis memory |grep "^Health"|grep -v "Ok" > /dev/null
        if [ $? -eq 0 ];then
                echo 1
        else
                echo 0
        fi
}
check_cpu() {
       /bin/omreport  chassis processors |grep "^Health "|egrep -v "Ok"  > /dev/null
       if [ $? -eq 0 ];then
                echo 1
        else
                echo 0
        fi
}

if [ -z $1 ];then
    echo "Usage: $0 [pdisk|vdisk|memory|cpu|raidcard]"
else
#       raid_card_exist
#       if [ $? -ne 0 ];then
        #       echo 2
         #       exit
        #fi

        case "$1" in
                pdisk)
                check_physical_disk
                ;;
                vdisk)
                check_virtual_disk
                ;;
                memory)
                check_memory
                ;;
                cpu)
                check_cpu
                ;;
                raidcard)
                raid_card_exist
                ;;
        esac
fi

保存后 sh执行对照参数核对下状态

5 重启zabbix客户端并查看状态

systemctl restart zabbix-agent
systemctl status zabbix-agent

6 在服务端上自己写硬件监控模板

对照上面的参数创建触发器

{Template Hardware Monitor:hardware_cpu.last()}=1

{Template Hardware Monitor:hardware_raid_health.last()}=2

{Template Hardware Monitor:hardware_raid_health.last()}=1

{Template Hardware Monitor:hardware_memory_health.last()}=1

{Template Hardware Monitor:hardware_physics_health.last()}<>0

{Template Hardware Monitor:hardware_virtual_health.last()}=1