安装zabbix agent
sudo apt-get install -y zabbix-agent
修改配置文件
vi /etc/zabbix/zabbix_agentd.conf
server:zabbix服务器192.168.x.x
Hostname:zabbix服务器计算机名字
添加:
UserParameter=gpu.number,/usr/bin/nvidia-smi -L | /bin/grep GeForce | /usr/bin/wc -l
UserParameter=gpu.discovery,/etc/zabbix/scripts/get_gpus_info.sh
UserParameter=gpu.fanspeed[],nvidia-smi --query-gpu=fan.speed --format=csv,noheader,nounits -i 0 | tr -d \n
UserParameter=gpu.power[],nvidia-smi --query-gpu=power.draw --format=csv,noheader,nounits -i 1 | tr -d \n
UserParameter=gpu.utilization[],nvidia-smi --query-gpu=utilization.gpu --format=csv,noheader,nounits -i 1 | tr -d \n
UserParameter=gpu.memused[],nvidia-smi --query-gpu=memory.used --format=csv,noheader,nounits -i 1 | tr -d \n
脚本:
get_gpus_info.sh
!/bin/bash
result=$(/usr/bin/nvidia-smi -L)
first=1
echo "{"
echo ""data":["
while IFS= read -r line
do
if (( "(echo -n (echo -n index"", "{#GPUUUID}"":"first" == "1" ))
then
echo ,
first=0
fi
done < <(printf '%s\n' "$result")
echo
echo "]"
echo "}"
启动zabbix,并配置开机启动
service zabbix-agent start
service zabbix-agent status
update-rc.d zabbix-agent enable
zabbix server端效果