ansible-devops/scripts
joy ff5c3e036a 123
123
2025-12-02 16:20:38 +08:00
..
README.md 123 2025-11-20 11:21:36 +08:00
all-install.sh 123 2025-12-02 16:08:16 +08:00
auto_ssh_auth_setup.sh 更新 scripts/auto_ssh_auth_setup.sh 2025-10-30 20:51:33 +08:00
calico.yaml 上传文件至 scripts 2025-11-02 20:23:06 +08:00
clonezilla_config.sh 添加 scripts/clonezilla_config.sh 2025-10-15 12:37:14 +08:00
containerd.sh 更新 scripts/containerd.sh 2025-10-31 09:20:04 +08:00
cuda.sh 123 2025-12-02 16:20:38 +08:00
dcgm-exporter.sh 更新 scripts/dcgm-exporter.sh 2025-10-24 10:16:05 +08:00
dcgm_diag_bg_log.sh 更新 scripts/dcgm_diag_bg_log.sh 2025-10-31 16:29:16 +08:00
deploy_gpu_monitor.sh 更新 scripts/deploy_gpu_monitor.sh 2025-10-31 12:50:22 +08:00
disable_acs.sh 更新 scripts/disable_acs.sh 2025-07-15 17:32:06 +08:00
docker.sh 添加 scripts/docker.sh 2025-09-24 09:32:17 +08:00
get-gpu-ib-sn.sh aaa 2025-10-31 16:57:24 +08:00
gitlab.sh 123 2025-11-20 11:20:43 +08:00
gpu-manager.sh aa 2025-07-05 18:22:07 +08:00
gpu-test.tgz dsd 2025-11-05 13:08:45 +08:00
gpu_bench_auto.sh 更新 scripts/gpu_bench_auto.sh 2025-11-07 14:58:16 +08:00
gpu_metrics.sh 更新 scripts/gpu_metrics.sh 2025-10-31 12:11:13 +08:00
gpu_metrics.sh_back 更新 scripts/gpu_metrics.sh_back 2025-09-09 08:34:15 +08:00
haproxy.sh 更新 scripts/haproxy.sh 2025-11-02 19:13:37 +08:00
ib-drive.sh 更新 scripts/ib-drive.sh 2025-07-19 23:10:24 +08:00
ib-sn-check.sh aaa 2025-07-14 13:13:47 +08:00
ib.sh 添加 scripts/ib.sh 2025-10-14 09:45:40 +08:00
ingress.yaml qw 2025-11-10 09:58:41 +08:00
install-checker.sh 添加 scripts/install-checker.sh 2025-07-15 18:09:02 +08:00
install-nfs-storageclass-pro.sh 123 2025-11-10 08:56:38 +08:00
jenkins-install.sh asdf 2025-11-10 14:38:20 +08:00
k8s-base-setup.sh 更新 scripts/k8s-base-setup.sh 2025-10-31 09:46:34 +08:00
k8s-cluster-deploy.sh 更新 scripts/k8s-cluster-deploy.sh 2025-11-08 12:23:55 +08:00
k8s-config-deploy.sh 12 2025-11-05 17:21:01 +08:00
k8s-ubuntu-init.sh 12 2025-11-10 08:46:09 +08:00
keepalived.sh 更新 scripts/keepalived.sh 2025-11-02 19:11:35 +08:00
kubeadm-conf.yaml 更新 scripts/kubeadm-conf.yaml 2025-10-31 00:15:59 +08:00
linux_security_hardening.sh adsf 2025-07-05 15:49:53 +08:00
local_allreduce_gpu.sh asdf 2025-11-19 10:10:28 +08:00
mellanox-fwupdate.sh aaa 2025-07-14 13:13:47 +08:00
metrics-server.yaml 1233 2025-11-10 09:40:52 +08:00
mpi_allreduce_perf_test.sh aa 2025-10-31 16:10:59 +08:00
nfs-subdir-external-provisioner.tgz asdf 2025-11-08 16:18:32 +08:00
nfs.sh sdfsaf 2025-11-08 14:11:18 +08:00
node-exporter.sh 更新 scripts/node-exporter.sh 2025-07-28 17:00:56 +08:00
nvidia-container-toolkit.sh 添加 scripts/nvidia-container-toolkit.sh 2025-09-24 10:03:14 +08:00
nvidia-dcgm.sh aa 2025-07-11 08:52:20 +08:00
nvidia-driver.sh aa 2025-07-11 18:30:14 +08:00
nvidia-fabricmanager.sh 更新 scripts/nvidia-fabricmanager.sh 2025-07-20 00:07:40 +08:00
prometheus-monitor.tgz 122 2025-11-07 17:28:12 +08:00
redis.sh 123 2025-11-20 10:41:39 +08:00
rename_mlx.sh 添加 scripts/rename_mlx.sh 2025-08-19 17:09:10 +08:00
set_ip.sh 更新 scripts/set_ip.sh 2025-10-16 09:43:23 +08:00
ssh.sh 123 2025-11-20 10:41:39 +08:00
system_optimize.sh 更新 scripts/system_optimize.sh 2025-10-20 13:46:46 +08:00

README.md

GPU 环境标 准化部署脚本使用说明:

code size ofed NVIDIA fabricmanager CUDA
Author


一、脚本概述

该脚本旨在简化 GPU 相关应用的安装流程,适用于需要快速部署 GPU 环境的场景。

  • 核心功能
    脚本可批量完成网卡驱动、显卡驱动、fabricmanager互联管理器、CUDA 工具包、Nvidia-dcgm、DCGM-EXporter、Node-EXporter 核心组件的安装与卸载操作 
    
  • 配置说明
    用户管理:若需删除 ubuntu 用户,需手动执行相关用户删除命令,并妥善处理该用户关联的数据与权限。​
    磁盘管理:磁盘分区扩容需通过磁盘管理工具,根据实际需求对磁盘进行分区调整与扩容操作,以满足应用存储需求。​
    网络配置:网卡重命名需手动修改网络配置文件,根据实际网络环境对网卡名称进行重新定义,确保网络连接正常。
    
  • 使用建议
    新系统推荐使用一键自动安装脚本,可快速、全面地完成 GPU 相关应用的部署,具体使用方法详见文章末尾说明。​若系统之前已存在相关安装内容,或需要对各组件进行独立、定制化部署,建议使用单独部署脚本安装。
    

二、使用说明

1系统初始化

cd /opt/ && wget -qO- http://116.205.97.109/scripts/system_optimize.sh|bash

#磁盘扩容(初始化脚本已集成无须重新执行)
#lvresize --extents +100%FREE --resizefs /dev/mapper/ubuntu--vg-ubuntu--lv

#修改主机名(初始化脚本已集成无须重新执行)
#IP=$(ip addr | awk '/^[0-9]+: / {}; /inet.*global/ {print gensub(/(.*)\/(.*)/, "\\1", "g", $2)}' | grep `ip route | grep default | awk '{print $3}' | awk -F. '{print $1"."$2}' | head -1` | head -1 | sed 's/\./-/g') 
#hostnamectl set-hostname $IP
#bash

#内核锁定(初始化脚本已集成无须重新执行)
#apt-mark hold  $(dpkg -l | grep -E "linux-(headers|image|unsigned|modules|modules-extra)" | grep "6.8.0-53" | awk '{print $2}') 
#dpkg --get-selections | grep hold  #查看

2MLNX_OFED 网络套件安装/卸载

#支持版本[23.10-1.1.9.0]
cd /opt/ && wget -qO- http://116.205.97.109/scripts/ib-drive.sh|bash -s --  --install  --version "24.10-2.1.8.0" --distro "ubuntu24.04"

3IB 网卡排序

#支持版本[23.10-1.1.9.0]
cd /opt/ && wget -qO- http://116.205.97.109/scripts/ib.sh|bash -s --  --install

4Nvidia 显卡驱动安装/卸载

#支持版本[565.57.01]  [570.124.06]
cd /opt/ && wget -qO- http://116.205.97.109/scripts/nvidia-driver.sh | bash -s -- --install --version '565.57.01'
cd /opt/ && wget -qO- http://116.205.97.109/scripts/nvidia-driver.sh | bash -s -- --install --version '570.124.06'

5GPU 互联管理器安装/卸载

#支持版本[565_565.57.01-1]  [570_570.124.06-1]
cd /opt/ && wget -qO- http://116.205.97.109/scripts/nvidia-fabricmanager.sh|bash -s -- --install --distro ubuntu22.04 --version 565_565.57.01-1
cd /opt/ && wget -qO- http://116.205.97.109/scripts/nvidia-fabricmanager.sh|bash -s -- --install --distro ubuntu24.04 --version 570_570.124.06-1

6NVIDIA CUDA 工具包部署/卸载

#支持版本[12.6.3_560.35.05]  [12.8.1_570.124.06]
cd /opt/ && wget -qO- http://116.205.97.109/scripts/cuda.sh | bash -s -- --install --version '12.6.3_560.35.05'
cd /opt/ && wget -qO- http://116.205.97.109/scripts/cuda.sh | bash -s -- --install --version '12.8.1_570.124.06'

7dcgm/node exporter 部署/卸载

cd /opt/ && wget -qO- http://116.205.97.109/scripts/nvidia-dcgm.sh   | bash -s -- --install 
cd /opt/ && wget -qO- http://116.205.97.109/scripts/dcgm-exporter.sh | bash -s -- --install
cd /opt/ && wget -qO- http://116.205.97.109/scripts/node-exporter.sh | bash -s -- --install
cd /opt/ && wget -qO- http://116.205.97.109/scripts/deploy_gpu_monitor.sh | bash -s -- --install #针对dcgm-exporter 进行自定义扩展后期集成到dcgm中

cd /opt/ && wget -qO- http://116.205.97.109/scripts/nvidia-dcgm.sh   | bash -s -- --uninstall 
cd /opt/ && wget -qO- http://116.205.97.109/scripts/dcgm-exporter.sh | bash -s -- --uninstall
cd /opt/ && wget -qO- http://116.205.97.109/scripts/node-exporter.sh | bash -s -- --uninstall
cd /opt/ && wget -qO- http://116.205.97.109/scripts/deploy_gpu_monitor.sh | bash -s -- --uninstall

8Docker 安装/卸载

#支持版本[5:28.4.0-1~ubuntu.24.04~noble]
cd /opt/ && wget -qO- http://116.205.97.109/scripts/docker.sh | bash -s -- --install --version '5:28.4.0-1~ubuntu.24.04~noble'
cd /opt/ && wget -qO- http://116.205.97.109/scripts/docker.sh | bash -s -- --uninstall --version '5:28.4.0-1~ubuntu.24.04~noble'

9nvidia-container-toolkit 安装/卸载

#支持版本[1.17.6-1,1.17.7-1,1.17.8-1.....]
cd /opt/ && wget -qO- http://116.205.97.109/scripts/nvidia-container-toolkit.sh | bash -s -- --install --version '1.17.6-1'
cd /opt/ && wget -qO- http://116.205.97.109/scripts/nvidia-container-toolkit.sh | bash -s -- --uninstall --version '1.17.6-1'
#查看版本nvidia-container-runtime --version|head -1

10nfs 安装/卸载

cd /opt/ && wget -qO- http://116.205.97.109/scripts/nfs.sh | bash -s -- --install --share-dirs=/opt/data
cd /opt/ && wget -qO- http://116.205.97.109/scripts/nfs.sh | bash -s -- --install --share-dirs=/opt/data

11jenkinsdocker版本-后续优化)

cd /opt/ && wget -qO- http://116.205.97.109/scripts/jenkins-install.sh | bash

10Clonezilla 母机增强配置

#在再生龙克隆系统前,对目标母机系统进行增强配置,实现克隆还原后系统 “开箱即用”无需手动修改主机名、带内IP、修复udev规则文件丢失问题等。
cd /opt/ && wget -qO- http://116.205.97.109/scripts/clonezilla_config.sh | bash

#=注意:配置 IP 映射关系
脚本执行完成后,需在母机的 /opt/ip.txt 文件中,按格式填写还原后主机的带内 IP带外 IP 对应关系(后续克隆到目标机后,系统会自动匹配配置)如:
cat /opt/ip.txt
#第一列:带内IP,第二列子网掩码第三列带内网关第四列带外IP
172.51.4.1     26      172.51.4.126    172.51.2.50
172.51.4.2     26      172.51.4.126    172.51.2.50
.......

11k8s集群部署

配置免密:
#注ip.txt
cat > /opt/ip.txt << EOF
192.168.61.131
192.168.61.132
192.168.61.133
192.168.61.134
EOF

cd /opt/ && wget -qO- http://116.205.97.109/scripts/auto_ssh_auth_setup.sh |bash -s -- --file=/opt/ip.txt --user=root --passwd=xxxx
cd /opt/ && wget -qO- http://116.205.97.109/scripts/k8s-ubuntu-init.sh | bash #系统初始化
cd /opt/ && wget -qO- http://116.205.97.109/scripts/containerd.sh |bash -s -- --install --version '1.7.28-1'   #containerd 安装(所有节点执行)
cd /opt/ && wget -qO- http://116.205.97.109/scripts/k8s-base-setup.sh |bash -s -- --install --version '1.30.5' #k8s基础组件所有节点执行
cd /opt/ && wget -qO- http://116.205.97.109/scripts/haproxy.sh |bash -s -- --install --backend  192.168.61.131:6443,192.168.61.132:6443,192.168.61.133:6443 --port 36443

#master 节点3,5,7...
cd /opt/ && wget -qO- http://116.205.97.109/scripts/keepalived.sh |bash -s -- --install --vip 192.168.61.200/24 --priority 150 #主节点执行
cd /opt/ && wget -qO- http://116.205.97.109/scripts/keepalived.sh |bash -s -- --install --vip 192.168.61.200/24 --priority 140 #备节点执行
cd /opt/ && wget -qO- http://116.205.97.109/scripts/keepalived.sh |bash -s -- --install --vip 192.168.61.200/24 --priority 130 #备节点执行

#配置分发kubeadm配置文件
cd /opt/ && wget -qO- http://116.205.97.109/scripts/k8s-config-deploy.sh  |bash -s -- --local-ip=192.168.61.131   --hostname=master-01   --k8s-version=1.30.5 --cluster-vip=192.168.61.200   --cluster-port=36443   --master1-ip=192.168.61.131 --master2-ip=192.168.61.132 --master3-ip=192.168.61.133 #master01

cd /opt/ && wget -qO- http://116.205.97.109/scripts/k8s-config-deploy.sh  |bash -s -- --local-ip=192.168.61.132   --hostname=master-02   --k8s-version=1.30.5 --cluster-vip=192.168.61.200   --cluster-port=36443   --master1-ip=192.168.61.131 --master2-ip=192.168.61.132 --master3-ip=192.168.61.133 #master02

cd /opt/ && wget -qO- http://116.205.97.109/scripts/k8s-config-deploy.sh  |bash -s -- --local-ip=192.168.61.133   --hostname=master-03   --k8s-version=1.30.5 --cluster-vip=192.168.61.200   --cluster-port=36443   --master1-ip=192.168.61.131 --master2-ip=192.168.61.132 --master3-ip=192.168.61.133 #master03

#初始化集群,在这个地方拍摄快照调试代码
#k8s-master 初始化集群
cd /opt/ && wget -qO- http://116.205.97.109/scripts/k8s-cluster-deploy.sh |bash -s --  --master-ips=192.168.61.132,192.168.61.133   --node-ips=192.168.61.134
#脚本存在bug 请手动执行初始化kubeadm init --config kubeadm-init.yaml --upload-certs


#常用工具组件安装helm 工具安装
curl https://raw.githubusercontent.com/helm/helm/main/scripts/get-helm-3 | bash

#安装nfs存储类
# 依赖环境所有节点必须安装nfs客户端apt install -y nfs-common
# 若没有node节点,可取消master污点让其可调度kubectl taint nodes master-03 node-role.kubernetes.io/control-plane:NoSchedule-
cd /opt/ && wget -qO- http://116.205.97.109/scripts/nfs.sh | bash -s -- --install --share-dirs=/opt/data #安装nfs
cd /opt/ && wget -qO- http://116.205.97.109/scripts/install-nfs-storageclass-pro.sh | bash -s -- --nfs-server 192.168.61.131 --share-dirs /opt/data #指定nfs信息

#安装Metrics Server组件
cd /opt/k8s-install-conf/ && wget http://116.205.97.109/scripts/metrics-server.yaml && kubectl apply -f /opt/k8s-install-conf/metrics-server.yaml
#测试 kubectl top node


#安装ingress-nginx组件
cd /opt/k8s-install-conf/ && wget http://116.205.97.109/scripts/ingress.yaml && kubectl apply -f /opt/k8s-install-conf/ingress.yaml

#安装网络插件
#wget -q -c -O /opt/k8s-install-conf/calico.yaml http://116.205.97.109/scripts/calico.yaml --show-progress && kubectl apply -f /opt/k8s-install-conf/calico.yaml


#static pod 安装 kuboard-UI
在 Kubernetes master 节点上,执行如下两行指令,即可在根据提示完成 kuboard 安装。默认用户名/密码: admin/Kuboard123
cd /opt/k8s-install-conf && curl -fsSL https://addons.kuboard.cn/kuboard/kuboard-static-pod.sh -o kuboard.sh
sed -i 's#eipwork/kuboard:v3#swr.cn-east-2.myhuaweicloud.com/kuboard/kuboard:v3#g' kuboard.sh
sh kuboard.sh



#Argocd部署【集群内部部署-dev环境】- K8S集群内部署
kubectl create namespace argocd && cd /opt/k8s-install-conf && wget https://raw.githubusercontent.com/argoproj/argo-cd/stable/manifests/install.yaml
kubectl apply -n argocd -f install.yaml
#获取密码kubectl -n argocd get secret argocd-initial-admin-secret -o jsonpath="{.data.password}" | base64 -d


# Jenkins 独立于K8S集群之外部署(docker 部署)
cd /opt/ && wget -qO- http://116.205.97.109/scripts/jenkins-install.sh | bash


#Gitlab
cd /opt/ && wget -qO- http://116.205.97.109/scripts/gitlab.sh |bash -s -- --install        #安装
cd /opt/ && wget -qO- http://116.205.97.109/scripts/gitlab.sh |bash -s -- --uninstall      #卸载

#elk


#Prometheus


#ceph


#mysql


#kafka


#redis【哨兵集群模式】
cat > /opt/ip.txt << EOF
192.168.61.131
192.168.61.132
192.168.61.133
EOF
cd /opt/ && wget -qO- http://116.205.97.109/scripts/ssh.sh |bash -s -- --file=/opt/ip.txt --user=root --passwd=XXXXXX         #免密
cd /opt/ && wget -qO- http://116.205.97.109/scripts/redis.sh |bash -s -- --install --ip=IP1(),IP2,IP3 --passwd=XXXXXX       #安装
cd /opt/ && wget -qO- http://116.205.97.109/scripts/redis.sh |bash -s -- --uninstall -ip=IP1(),IP2,IP3 --passwd=XXXXXX      #卸载
#harbor


#nacos


#

(12) AL多租户平台 GPU资源基准测试

cd /opt/ && wget -qO- http://116.205.97.109/scripts/gpu_bench_auto.sh|bash -s -- --tests=bandwidthTest,deviceQuery,gpu_burn,p2pBandwidthLatencyTest #gpu基准测试
cd /opt/ && wget -qO- http://116.205.97.109/scripts/dcgm_diag_bg_log.sh | bash #默认后台压测压测级别4预计时间2-3小时。
cd /opt/ && wget -qO- http://116.205.97.109/scripts/local_allreduce_gpu.sh | bash #单节点allreduce测试
cd /opt/ && wget -qO- http://116.205.97.109/scripts/mpi_allreduce_perf_test.sh|bash -s -- --host=node01-ip:8,node02-ip:8 # allreduce 测试

(13) docker实现监控快速搭建

#环境依赖docker,docker-compose 
#promtheus配置1.支持【dcgm-exporter,node-exporter】consul 自动发现和file_sd自动发现。2.支持【ipmi-exporter】file_sd自动发现。
#自动部署服务ipmi-exporter,prometheus, alertmanager,consul,grafana,prometheus,prometheus-alert 
wget -O - http://116.205.97.109/scripts/prometheus-monitor.tgz | tar -xvz && cd prometheus-monitor && docker-compose up -d
#以下命令可通过ansible 批量执行或在任意节点发起PUT请求批量循环注册。
bash /opt/prometheus-monitor/dcgm-consul.sh --register/deregister     #dcgm-exporter->consul注册/注销
bash /opt/prometheus-monitor/node-consul.sh --register/deregister     #node-exporter->consul 注册/注销

13批量安装/卸载

Static Badge Static Badge Static Badge Static Badge Static Badge

Static Badge

#安装/卸载服务(安装或卸载时间较长,建议放后台执行。)
#组合[1]-----------------------------------------------------------------------------------------------------------------------------------
screen -dmS install_script bash -c  "cd /opt/ && wget -qO- http://116.205.97.109/scripts/gpu-manager.sh|bash -s -- --install --version 1 --include=exporter  2>&1 > /opt/gpu-manager.log";
tail -f /opt/gpu-manager.log

screen -dmS uninstall_script bash -c "cd /opt/ && wget -qO- http://116.205.97.109/scripts/gpu-manager.sh|bash -s -- --uninstall --version 1 --include=exporter  2>&1 > /opt/gpu-manager.log";
tail -f /opt/gpu-manager.log

#组合[2]-----------------------------------------------------------------------------------------------------------------------------------
screen -dmS install_script bash -c  "cd /opt/ && wget -qO- http://116.205.97.109/scripts/gpu-manager.sh|bash -s -- --install --version 2 --include=exporter  2>&1 > /opt/gpu-manager.log";
tail -f /opt/gpu-manager.log

screen -dmS uninstall_script bash -c "cd /opt/ && wget -qO- http://116.205.97.109/scripts/gpu-manager.sh|bash -s -- --uninstall --version 2 --include=exporter  2>&1 > /opt/gpu-manager.log";
tail -f /opt/gpu-manager.log

#说明:
#version 1 表示安装/卸载七.[1]组件版本mlnx_ofed-23.10.1.1.9.0+nvidia_drive-565.57.01 +cuda-12.6.3.560.35.05 +fabricmanager-565_565.57.01.1
#version 2 表示安装/卸载七.[2]组件版本mlnx_ofed-23.10.1.1.9.0+nvidia_drive-570.124.06+cuda-12.8.1.570.124.06+fabricmanager-570.124.06.1
#--include=exporter 指定该参数,脚本将安装/卸载exporter组件中的相关服务[dcgm-exporter,node-exporter,nvidia-dcgm],默认不安装/卸载。

特别提醒

GPU:B200系列
  1B200系列安装fabricmanager 时需要安装nvlsm,否则faricmanager无法启动。
       wget https://developer.download.nvidia.com/compute/cuda/repos/ubuntu2404/x86_64/nvlsm_2025.03.1-1_amd64.deb
       dpkg -i nvlsm_2025.03.1-1_amd64.deb
超威机型:
  1超威机型需要在:/etc/default/grub文件下添加GRUB_CMDLINE_LINUX="quiet splash nokaslr"参数否则CUDA初始化失败。
  2超威机型需要在:/etc/default/grub文件下添加GRUB_CMDLINE_LINUX_DEFAULT="intel_iommu=off" #正确关闭iommu
   (3) 超威机型挂载镜像: http协议:file_server:http://10.51.151.201  镜像路径:/iso/ubu22043.iso

再生龙镜像还原:
  1华擎B200:再生龙镜像NFS10.102.35.99/nfs/clone.iso  备份路径:/nfs/2025-05-26-09-B200-960g-img #华擎机型对再生龙引导镜像版本无要求。
  2超威B200:再生龙镜像:10.102.35.99/nfs/clone.iso   备份路径: /nfs/chaowei-B200-1.7T-img #注意超威机型对再生龙引导镜像对版本有要求,最新版本无法引导。
   (3) 技嘉A100:再生龙镜像:10.101.0.86:/nfs/  备份路径: /nfs/2025-07-15-03-Jijia-A100-960G-img #技嘉A100-磁盘960G-CX7

ubuntu2404:(临时)

cd /opt/ 
wget https://content.mellanox.com/ofed/MLNX_OFED-24.10-2.1.8.0/MLNX_OFED_LINUX-24.10-2.1.8.0-ubuntu24.04-x86_64.tgz #[ubuntu24.04]
wget https://developer.download.nvidia.cn/compute/cuda/repos/ubuntu2404/x86_64/nvidia-fabricmanager-570_570.124.06-1_amd64.deb #[ubuntu24.04]
wget https://cn.download.nvidia.com/tesla/570.124.06/NVIDIA-Linux-x86_64-570.124.06.run #[无版本要求]
wget https://developer.download.nvidia.com/compute/cuda/12.8.1/local_installers/cuda_12.8.1_570.124.06_linux.run #[无版本要求]
cd /opt/ && git clone http://116.205.97.109:3000/yindun/ansible-devops.git
cd /opt/ansible-devops/scripts/

#-----临时替换适配ubuntu24.04
sed -i -e 's/5.8-6.0.4.2/24.10-2.1.8.0/g' -e 's/22.04/24.04/g' ib-drive.sh && sed -i 's/2204/2404/g' nvidia-fabricmanager.sh
bash system_optimize.sh --install
bash ib-drive.sh --install --version "24.10-2.1.8.0"
bash nvidia-driver.sh --install --version '570.124.06'
bash nvidia-fabricmanager.sh --install --version "570_570.124.06-1"
bash cuda.sh --install --version "12.8.1_570.124.06"

#安装exporter
cd /opt/ && wget -qO- http://116.205.97.109/scripts/nvidia-dcgm.sh | bash -s -- --install 
cd /opt/ && wget -qO- http://116.205.97.109/scripts/dcgm-exporter.sh | bash -s -- --install
cd /opt/ && wget -qO- http://116.205.97.109/scripts/node-exporter.sh | bash -s -- --install
cd /opt/ && wget -qO- http://116.205.97.109/scripts/deploy_gpu_monitor.sh | bash -s -- --install #针对dcgm-exporter 进行自定义扩展后期集成到dcgm中

#修改主机名,内核版本锁定,根分区扩容已集成在初始化脚本中无须重复执行。

# 平湖引导镜像10.101.0.34  /nfs/iso/gpu550.iso