搜索到
211
篇与
默认分类
的结果
-
Centos9网卡配置 Centos9 网卡配置文件已修改，如下[root@bogon ~]# cat /etc/NetworkManager/system-connections/ens18.nmconnection [connection] id=ens18 uuid=8d1ece55-d999-3c97-866b-d2e23832a324 type=ethernet autoconnect-priority=-999 interface-name=ens18 permissions= timestamp=1639473429 [ethernet] mac-address-blacklist= [ipv4] address1=192.168.1.92/24,192.168.1.1 dns=8.8.8.8; dns-search= method=manual [ipv6] addr-gen-mode=eui64 dns-search= method=auto [proxy] [root@bogon ~]#命令语法：# nmcli connection modify <interface_name> ipv4.address <ip/prefix>复制代码注意: 为了简化语句，在 nmcli 命令中，我们通常用 con 关键字替换 connection，并用 mod 关键字替换 modify。将 IPv4 地址 (192.168.1.91) 分配给 ens18网卡上， [root@chenby ~]# nmcli con mod ens18 ipv4.addresses 192.168.1.91/24; 复制代码使用下面的 nmcli 命令设置网关， [root@chenby ~]# nmcli con mod ens18 ipv4.gateway 192.168.1.1; 复制代码设置手动配置（从 dhcp 到 static）， [root@chenby ~]# nmcli con mod ens18 ipv4.method manual; 复制代码设置 DNS 值为 “8.8.8.8”， [root@chen'b'y ~]# nmcli con mod ens18 ipv4.dns "8.8.8.8"; 复制代码要保存上述更改并重新加载，请执行如下 nmcli 命令， [root@chenby ~]# nmcli con up ens18合成一句话为：nmcli con mod ens18 ipv4.addresses 192.168.1.91/24; nmcli con mod ens18 ipv4.gateway 192.168.1.1; nmcli con mod ens18 ipv4.method manual; nmcli con mod ens18 ipv4.dns "8.8.8.8"; nmcli con up ens18远程修改IP为：ssh root@192.168.1.197 "nmcli con mod ens18 ipv4.addresses 192.168.1.91/24; nmcli con mod ens18 ipv4.gateway 192.168.1.1; nmcli con mod ens18 ipv4.method manual; nmcli con mod ens18 ipv4.dns "8.8.8.8"; nmcli con up ens18"Linux运维交流社区Linux运维交流社区，互联网新闻以及技术交流。69篇原创内容公众号 https://blog.csdn.net/qq_33921750https://my.oschina.net/u/3981543https://www.zhihu.com/people/chen-bu-yun-2https://segmentfault.com/u/hppyvyv6/articleshttps://juejin.cn/user/3315782802482007https://space.bilibili.com/352476552/articlehttps://cloud.tencent.com/developer/column/93230知乎、CSDN、开源中国、思否、掘金、哔哩哔哩、腾讯云本文使用 文章同步助手 同步v -
kubernetes核心实战（八）--- service 13、service四层网络负载创建[root@k8s-master-node1 ~/yaml/test]# [root@k8s-master-node1 ~/yaml/test]# vim my-app.yaml [root@k8s-master-node1 ~/yaml/test]# cat my-app.yaml apiVersion: apps/v1 kind: Deployment metadata: labels: app: my-dep name: my-dep spec: replicas: 3 selector: matchLabels: app: my-dep template: metadata: labels: app: my-dep spec: containers: - image: nginx name: nginx [root@k8s-master-node1 ~/yaml/test]# kubectl apply -f my-app.yaml deployment.apps/my-dep created [root@k8s-master-node1 ~/yaml/test]# [root@k8s-master-node1 ~/yaml/test]# kubectl get deployments.apps NAME READY UP-TO-DATE AVAILABLE AGE ingress-demo-app 2/2 2 2 155m my-dep 3/3 3 3 71s nfs-client-provisioner 1/1 1 1 140m [root@k8s-master-node1 ~/yaml/test]# 使用标签查找[root@k8s-master-node1 ~/yaml/test]# kubectl get pod --show-labels NAME READY STATUS RESTARTS AGE LABELS hello-27285682--1-q2p6x 0/1 Completed 0 3m15s controller-uid=5e700c2e-29b3-4099-be17-b005d8077284,job-name=hello-27285682 hello-27285683--1-b2qgn 0/1 Completed 0 2m15s controller-uid=d7455e28-bd37-4fdf-bf47-de7ae6b4b7bb,job-name=hello-27285683 hello-27285684--1-glsmp 0/1 Completed 0 75s controller-uid=9cc7f28d-e780-49fb-a23a-ab725413ea8a,job-name=hello-27285684 hello-27285685--1-s7ws5 0/1 ContainerCreating 0 15s controller-uid=169e3631-6981-4df8-bfee-6a4f4632b713,job-name=hello-27285685 ingress-demo-app-694bf5d965-8rh7f 1/1 Running 0 157m app=ingress-demo-app,pod-template-hash=694bf5d965 ingress-demo-app-694bf5d965-swkpb 1/1 Running 0 157m app=ingress-demo-app,pod-template-hash=694bf5d965 my-dep-5b7868d854-kzflw 1/1 Running 0 2m34s app=my-dep,pod-template-hash=5b7868d854 my-dep-5b7868d854-pfhps 1/1 Running 0 2m34s app=my-dep,pod-template-hash=5b7868d854 my-dep-5b7868d854-v67ll 1/1 Running 0 2m34s app=my-dep,pod-template-hash=5b7868d854 nfs-client-provisioner-dc5789f74-5bznq 1/1 Running 0 141m app=nfs-client-provisioner,pod-template-hash=dc5789f74 pi--1-k5cbq 0/1 Completed 0 25m controller-uid=2ecfcafd-f848-403b-b37f-9c145a0dc8cc,job-name=pi redis-app-86g4q 1/1 Running 0 27m controller-revision-hash=77c8899f5d,name=fluentd-redis,pod-template-generation=1 redis-app-rt92n 1/1 Running 0 27m controller-revision-hash=77c8899f5d,name=fluentd-redis,pod-template-generation=1 redis-app-vkzft 1/1 Running 0 27m controller-revision-hash=77c8899f5d,name=fluentd-redis,pod-template-generation=1 web-0 1/1 Running 0 91m app=nginx,controller-revision-hash=web-57c5cc66df,statefulset.kubernetes.io/pod-name=web-0 web-1 1/1 Running 0 91m app=nginx,controller-revision-hash=web-57c5cc66df,statefulset.kubernetes.io/pod-name=web-1 web-2 1/1 Running 0 90m app=nginx,controller-revision-hash=web-57c5cc66df,statefulset.kubernetes.io/pod-name=web-2 [root@k8s-master-node1 ~/yaml/test]# [root@k8s-master-node1 ~/yaml/test]# [root@k8s-master-node1 ~/yaml/test]# [root@k8s-master-node1 ~/yaml/test]# kubectl get pod -l app=my-dep NAME READY STATUS RESTARTS AGE my-dep-5b7868d854-kzflw 1/1 Running 0 2m42s my-dep-5b7868d854-pfhps 1/1 Running 0 2m42s my-dep-5b7868d854-v67ll 1/1 Running 0 2m42s [root@k8s-master-node1 ~/yaml/test]#命令行暴露端口[root@k8s-master-node1 ~/yaml/test]# kubectl expose deployment my-dep --port=8000 --target-port=80 service/my-dep exposed [root@k8s-master-node1 ~/yaml/test]# [root@k8s-master-node1 ~/yaml/test]# kubectl get service NAME TYPE CLUSTER-IP EXTERNAL-IP PORT(S) AGE ingress-demo-app ClusterIP 10.96.145.40 <none> 80/TCP 158m kubernetes ClusterIP 10.96.0.1 <none> 443/TCP 160m my-dep ClusterIP 10.96.241.162 <none> 8000/TCP 11s nginx ClusterIP None <none> 80/TCP 92m [root@k8s-master-node1 ~/yaml/test]#yaml文件暴露端口apiVersion: v1 kind: Service metadata: labels: app: my-dep name: my-dep spec: selector: app: my-dep ports: - port: 8000 protocol: TCP targetPort: 80ClusterIP方式暴露命令行kubectl expose deployment my-dep --port=8000 --target-port=80 --type=ClusterIPyaml方式apiVersion: v1 kind: Service metadata: labels: app: my-dep name: my-dep spec: ports: - port: 8000 protocol: TCP targetPort: 80 selector: app: my-dep type: ClusterIP访问测试[root@k8s-master-node1 ~/yaml/test]# curl -I 10.96.241.162:8000 HTTP/1.1 200 OK Server: nginx/1.21.4 Date: Wed, 17 Nov 2021 09:30:27 GMT Content-Type: text/html Content-Length: 615 Last-Modified: Tue, 02 Nov 2021 14:49:22 GMT Connection: keep-alive ETag: "61814ff2-267" Accept-Ranges: bytes [root@k8s-master-node1 ~/yaml/test]#NodePort方式暴露命令行kubectl expose deployment my-dep --port=8000 --target-port=80 --type=NodePortyaml方式apiVersion: v1 kind: Service metadata: labels: app: my-dep name: my-dep spec: ports: - port: 8000 protocol: TCP targetPort: 80 selector: app: my-dep type: NodePort查看service[root@k8s-master-node1 ~/yaml/test]# kubectl get service NAME TYPE CLUSTER-IP EXTERNAL-IP PORT(S) AGE ingress-demo-app ClusterIP 10.96.145.40 <none> 80/TCP 165m kubernetes ClusterIP 10.96.0.1 <none> 443/TCP 167m my-dep NodePort 10.96.241.162 <none> 8000:32306/TCP 7m13s nginx ClusterIP None <none> 80/TCP 99m [root@k8s-master-node1 ~/yaml/test]#访问测试使用kubernetes任何node的ip都可以访问[root@k8s-master-node1 ~/yaml/test]# curl -I 192.168.1.62:32306 HTTP/1.1 200 OK Server: nginx/1.21.4 Date: Wed, 17 Nov 2021 09:36:50 GMT Content-Type: text/html Content-Length: 615 Last-Modified: Tue, 02 Nov 2021 14:49:22 GMT Connection: keep-alive ETag: "61814ff2-267" Accept-Ranges: bytes [root@k8s-master-node1 ~/yaml/test]# curl -I 192.168.1.61:32306 HTTP/1.1 200 OK Server: nginx/1.21.4 Date: Wed, 17 Nov 2021 09:36:53 GMT Content-Type: text/html Content-Length: 615 Last-Modified: Tue, 02 Nov 2021 14:49:22 GMT Connection: keep-alive ETag: "61814ff2-267" Accept-Ranges: bytes [root@k8s-master-node1 ~/yaml/test]# curl -I 192.168.1.63:32306 HTTP/1.1 200 OK Server: nginx/1.21.4 Date: Wed, 17 Nov 2021 09:36:56 GMT Content-Type: text/html Content-Length: 615 Last-Modified: Tue, 02 Nov 2021 14:49:22 GMT Connection: keep-alive ETag: "61814ff2-267" Accept-Ranges: bytes [root@k8s-master-node1 ~/yaml/test]# https://blog.csdn.net/qq_33921750https://my.oschina.net/u/3981543https://www.zhihu.com/people/chen-bu-yun-2https://segmentfault.com/u/hppyvyv6/articleshttps://juejin.cn/user/3315782802482007https://space.bilibili.com/352476552/articlehttps://cloud.tencent.com/developer/column/93230知乎、CSDN、开源中国、思否、掘金、哔哩哔哩、腾讯云本文使用 文章同步助手 同步
-
kubernetes核心实战（九） --- Ingress 14、Ingress检查是否有安装[root@k8s-master-node1 ~/yaml/test]# kubectl get pod,svc -n ingress-nginx NAME READY STATUS RESTARTS AGE pod/ingress-nginx-admission-create--1-74mtg 0/1 Completed 0 172m pod/ingress-nginx-admission-patch--1-5qrct 0/1 Completed 0 172m pod/ingress-nginx-controller-f97bd58b5-vr8c2 1/1 Running 0 172m NAME TYPE CLUSTER-IP EXTERNAL-IP PORT(S) AGE service/ingress-nginx-controller NodePort 10.96.109.80 <none> 80:30127/TCP,443:36903/TCP 172m service/ingress-nginx-controller-admission ClusterIP 10.96.215.201 <none> 443/TCP 172m [root@k8s-master-node1 ~/yaml/test]#若未安装可以查看官网文档：https://kubernetes.github.io/ingress-nginx/deploy/创建环境：[root@k8s-master-node1 ~/yaml/test]# vim ingress.yaml [root@k8s-master-node1 ~/yaml/test]# [root@k8s-master-node1 ~/yaml/test]# cat ingress.yaml apiVersion: apps/v1 kind: Deployment metadata: name: hello-server spec: replicas: 2 selector: matchLabels: app: hello-server template: metadata: labels: app: hello-server spec: containers: - name: hello-server image: registry.cn-hangzhou.aliyuncs.com/lfy_k8s_images/hello-server ports: - containerPort: 9000 --- apiVersion: apps/v1 kind: Deployment metadata: labels: app: nginx-demo name: nginx-demo spec: replicas: 2 selector: matchLabels: app: nginx-demo template: metadata: labels: app: nginx-demo spec: containers: - image: nginx name: nginx --- apiVersion: v1 kind: Service metadata: labels: app: nginx-demo name: nginx-demo spec: selector: app: nginx-demo ports: - port: 8000 protocol: TCP targetPort: 80 --- apiVersion: v1 kind: Service metadata: labels: app: hello-server name: hello-server spec: selector: app: hello-server ports: - port: 8000 protocol: TCP targetPort: 9000 [root@k8s-master-node1 ~/yaml/test]# [root@k8s-master-node1 ~/yaml/test]# kubectl apply -f ingress.yaml deployment.apps/hello-server created deployment.apps/nginx-demo created service/nginx-demo created service/hello-server created [root@k8s-master-node1 ~/yaml/test]#查看四层负载并测试[root@k8s-master-node1 ~/yaml/test]# kubectl get service NAME TYPE CLUSTER-IP EXTERNAL-IP PORT(S) AGE hello-server ClusterIP 10.96.246.46 <none> 8000/TCP 21s ingress-demo-app ClusterIP 10.96.145.40 <none> 80/TCP 3h1m kubernetes ClusterIP 10.96.0.1 <none> 443/TCP 3h3m my-dep NodePort 10.96.241.162 <none> 8000:32306/TCP 23m nginx ClusterIP None <none> 80/TCP 115m nginx-demo ClusterIP 10.96.162.193 <none> 8000/TCP 21s [root@k8s-master-node1 ~/yaml/test]# [root@k8s-master-node1 ~/yaml/test]# [root@k8s-master-node1 ~/yaml/test]# curl -I 10.96.162.193:8000 HTTP/1.1 200 OK Server: nginx/1.21.4 Date: Wed, 17 Nov 2021 09:49:40 GMT Content-Type: text/html Content-Length: 615 Last-Modified: Tue, 02 Nov 2021 14:49:22 GMT Connection: keep-alive ETag: "61814ff2-267" Accept-Ranges: bytes [root@k8s-master-node1 ~/yaml/test]# curl -I 10.96.246.46:8000 HTTP/1.1 200 OK Date: Wed, 17 Nov 2021 09:49:52 GMT Content-Length: 12 Content-Type: text/plain; charset=utf-8 [root@k8s-master-node1 ~/yaml/test]#创建七层[root@k8s-master-node1 ~/yaml/test]# vim ingress-7.yaml [root@k8s-master-node1 ~/yaml/test]# [root@k8s-master-node1 ~/yaml/test]# [root@k8s-master-node1 ~/yaml/test]# cat ingress-7.yaml apiVersion: networking.k8s.io/v1 kind: Ingress metadata: name: ingress-host-bar spec: ingressClassName: nginx rules: - host: "hello.chenby.cn" http: paths: - pathType: Prefix path: "/" backend: service: name: hello-server port: number: 8000 - host: "demo.chenby.cn" http: paths: - pathType: Prefix path: "/nginx" # 把请求会转给下面的服务，下面的服务一定要能处理这个路径，不能处理就是404 backend: service: name: nginx-demo ## java，比如使用路径重写，去掉前缀nginx port: number: 8000 [root@k8s-master-node1 ~/yaml/test]# [root@k8s-master-node1 ~/yaml/test]# kubectl apply -f ingress-7.yaml ingress.networking.k8s.io/ingress-host-bar created [root@k8s-master-node1 ~/yaml/test]# [root@k8s-master-node1 ~/yaml/test]# [root@k8s-master-node1 ~/yaml/test]# kubectl get ingress NAME CLASS HOSTS ADDRESS PORTS AGE ingress-demo-app <none> app.demo.com 192.168.1.62 80 3h14m ingress-host-bar nginx hello.chenby.cn,demo.chenby.cn 192.168.1.62 80 9m50s [root@k8s-master-node1 ~/yaml/test]# [root@k8s-master-node1 ~/yaml/test]# kubectl describe ingress ingress-host-bar Name: ingress-host-bar Namespace: default Address: 192.168.1.62 Default backend: default-http-backend:80 (10.244.2.7:8080) Rules: Host Path Backends ---- ---- -------- hello.chenby.cn / hello-server:8000 (10.244.2.47:9000,10.244.2.48:9000) demo.chenby.cn /nginx nginx-demo:8000 (10.244.0.13:80,10.244.1.34:80) Annotations: <none> Events: Type Reason Age From Message ---- ------ ---- ---- ------- Normal Sync 6m26s (x2 over 6m50s) nginx-ingress-controller Scheduled for sync [root@k8s-master-node1 ~/yaml/test]#电脑上写死hosts[root@k8s-master-node1 ~/yaml/test]# kubectl get service ingress-demo-app NAME TYPE CLUSTER-IP EXTERNAL-IP PORT(S) AGE ingress-demo-app ClusterIP 10.96.145.40 <none> 80/TCP 3h15m [root@k8s-master-node1 ~/yaml/test]# 10.96.145.40 hello.chenby.cn 10.96.145.40 demo.chenby.cn测试访问[root@k8s-master-node1 ~/yaml/test]# curl hello.chenby.cn Hostname: ingress-demo-app-694bf5d965-8rh7f IP: 127.0.0.1 IP: 10.244.1.6 RemoteAddr: 192.168.1.61:49809 GET / HTTP/1.1 Host: hello.chenby.cn User-Agent: curl/7.68.0 Accept: */* [root@k8s-master-node1 ~/yaml/test]# [root@k8s-master-node1 ~/yaml/test]# curl demo.chenby.cn Hostname: ingress-demo-app-694bf5d965-swkpb IP: 127.0.0.1 IP: 10.244.2.4 RemoteAddr: 192.168.1.61:57797 GET / HTTP/1.1 Host: demo.chenby.cn User-Agent: curl/7.68.0 Accept: */* [root@k8s-master-node1 ~/yaml/test]#url 重写[root@k8s-master-node1 ~/yaml/test]# vim ingress-url [root@k8s-master-node1 ~/yaml/test]# cat ingress-url.yaml apiVersion: networking.k8s.io/v1 kind: Ingress metadata: annotations: nginx.ingress.kubernetes.io/rewrite-target: /$2 name: ingress-host-bar spec: ingressClassName: nginx rules: - host: "hello.chenby.cn" http: paths: - pathType: Prefix path: "/" backend: service: name: hello-server port: number: 8000 - host: "demo.chenby.cn" http: paths: - pathType: Prefix path: "/nginx(/|$)(.*)" # 把请求会转给下面的服务，下面的服务一定要能处理这个路径，不能处理就是404 backend: service: name: nginx-demo ## java，比如使用路径重写，去掉前缀nginx port: number: 8000 [root@k8s-master-node1 ~/yaml/test]# kubectl apply -f ingress-url.yaml ingress.networking.k8s.io/ingress-host-bar created [root@k8s-master-node1 ~/yaml/test]# [root@k8s-master-node1 ~/yaml/test]# curl hello.chenby.cn Hostname: ingress-demo-app-694bf5d965-8rh7f IP: 127.0.0.1 IP: 10.244.1.6 RemoteAddr: 192.168.1.61:42303 GET / HTTP/1.1 Host: hello.chenby.cn User-Agent: curl/7.68.0 Accept: */* [root@k8s-master-node1 ~/yaml/test]# curl demo.chenby.cn Hostname: ingress-demo-app-694bf5d965-swkpb IP: 127.0.0.1 IP: 10.244.2.4 RemoteAddr: 192.168.1.61:1108 GET / HTTP/1.1 Host: demo.chenby.cn User-Agent: curl/7.68.0 Accept: */* [root@k8s-master-node1 ~/yaml/test]#流量限制[root@k8s-master-node1 ~/yaml/test]# vim ingress-limit [root@k8s-master-node1 ~/yaml/test]# cat ingress-limit.yaml apiVersion: networking.k8s.io/v1 kind: Ingress metadata: name: ingress-limit-rate annotations: nginx.ingress.kubernetes.io/limit-rps: "1" spec: ingressClassName: nginx rules: - host: "haha.chenby.cn" http: paths: - pathType: Exact path: "/" backend: service: name: nginx-demo port: number: 8000 [root@k8s-master-node1 ~/yaml/test]# [root@k8s-master-node1 ~/yaml/test]# kubectl apply -f ingress-limit.yaml ingress.networking.k8s.io/ingress-limit-rate created [root@k8s-master-node1 ~/yaml/test]# [root@k8s-master-node1 ~/yaml/test]# vim /etc/hosts [root@k8s-master-node1 ~/yaml/test]# [root@k8s-master-node1 ~/yaml/test]# [root@k8s-master-node1 ~/yaml/test]# curl haha.chenby.cn Hostname: ingress-demo-app-694bf5d965-8rh7f IP: 127.0.0.1 IP: 10.244.1.6 RemoteAddr: 192.168.1.61:1676 GET / HTTP/1.1 Host: haha.chenby.cn User-Agent: curl/7.68.0 Accept: */* [root@k8s-master-node1 ~/yaml/test]#注：可以将server 改为nodeport 即可在外部访问，将 type 改为 NodePort[root@k8s-master-node1 ~/yaml/test]# kubectl get service ingress-demo-app NAME TYPE CLUSTER-IP EXTERNAL-IP PORT(S) AGE ingress-demo-app ClusterIP 10.96.145.40 <none> 80/TCP 6h27m [root@k8s-master-node1 ~/yaml/test]# kubectl edit service ingress-demo-app service/ingress-demo-app edited [root@k8s-master-node1 ~/yaml/test]# [root@k8s-master-node1 ~/yaml/test]# [root@k8s-master-node1 ~/yaml/test]# kubectl get service ingress-demo-app NAME TYPE CLUSTER-IP EXTERNAL-IP PORT(S) AGE ingress-demo-app NodePort 10.96.145.40 <none> 80:30975/TCP 6h28m [root@k8s-master-node1 ~/yaml/test]#https://blog.csdn.net/qq_33921750https://my.oschina.net/u/3981543https://www.zhihu.com/people/chen-bu-yun-2https://segmentfault.com/u/hppyvyv6/articleshttps://juejin.cn/user/3315782802482007https://space.bilibili.com/352476552/articlehttps://cloud.tencent.com/developer/column/93230知乎、CSDN、开源中国、思否、掘金、哔哩哔哩、腾讯云本文使用 文章同步助手 同步
-
Docker容器中使用GPU 背景容器封装了应用程序的依赖项，以提供可重复和可靠的应用程序和服务执行，而无需整个虚拟机的开销。如果您曾经花了一天的时间为一个科学或 深度学习 应用程序提供一个包含大量软件包的服务器，或者已经花费数周的时间来确保您的应用程序可以在多个 linux 环境中构建和部署，那么 Docker 容器非常值得您花费时间。安装添加docker源[root@localhost ~]# sudo yum-config-manager --add-repo=https://download.docker.com/linux/centos/docker-ce.repo Loaded plugins: fastestmirror, langpacks adding repo from: https://download.docker.com/linux/centos/docker-ce.repo grabbing file https://download.docker.com/linux/centos/docker-ce.repo to /etc/yum.repos.d/docker-ce.repo repo saved to /etc/yum.repos.d/docker-ce.repo [root@localhost ~]# [root@localhost ~]# cat /etc/yum.repos.d/docker-ce.repo [docker-ce-stable] name=Docker CE Stable - $basearch baseurl=https://download.docker.com/linux/centos/$releasever/$basearch/stable enabled=1 gpgcheck=1 gpgkey=https://download.docker.com/linux/centos/gpg [docker-ce-stable-debuginfo] name=Docker CE Stable - Debuginfo $basearch baseurl=https://download.docker.com/linux/centos/$releasever/debug-$basearch/stable enabled=0 gpgcheck=1 gpgkey=https://download.docker.com/linux/centos/gpg [docker-ce-stable-source] name=Docker CE Stable - Sources baseurl=https://download.docker.com/linux/centos/$releasever/source/stable enabled=0 gpgcheck=1 gpgkey=https://download.docker.com/linux/centos/gpg [docker-ce-test] name=Docker CE Test - $basearch baseurl=https://download.docker.com/linux/centos/$releasever/$basearch/test enabled=0 gpgcheck=1 gpgkey=https://download.docker.com/linux/centos/gpg [docker-ce-test-debuginfo] name=Docker CE Test - Debuginfo $basearch baseurl=https://download.docker.com/linux/centos/$releasever/debug-$basearch/test enabled=0 gpgcheck=1 gpgkey=https://download.docker.com/linux/centos/gpg [docker-ce-test-source] name=Docker CE Test - Sources baseurl=https://download.docker.com/linux/centos/$releasever/source/test enabled=0 gpgcheck=1 gpgkey=https://download.docker.com/linux/centos/gpg [docker-ce-nightly] name=Docker CE Nightly - $basearch baseurl=https://download.docker.com/linux/centos/$releasever/$basearch/nightly enabled=0 gpgcheck=1 gpgkey=https://download.docker.com/linux/centos/gpg [docker-ce-nightly-debuginfo] name=Docker CE Nightly - Debuginfo $basearch baseurl=https://download.docker.com/linux/centos/$releasever/debug-$basearch/nightly enabled=0 gpgcheck=1 gpgkey=https://download.docker.com/linux/centos/gpg [docker-ce-nightly-source] name=Docker CE Nightly - Sources baseurl=https://download.docker.com/linux/centos/$releasever/source/nightly enabled=0 gpgcheck=1 gpgkey=https://download.docker.com/linux/centos/gpg [root@localhost ~]#下载安装包[root@localhost ~]# cd docker [root@localhost docker]# [root@localhost docker]# repotrack docker-ce安装docker 并设置开机自启[root@localhost docker]# yum install ./* [root@localhost docker]# systemctl start docker [root@localhost docker]# [root@localhost docker]# systemctl enable docker Created symlink from /etc/systemd/system/multi-user.target.wants/docker.service to /usr/lib/systemd/system/docker.service. [root@localhost docker]#配置nvidia-docker的源[root@localhost docker]# distribution=$(. /etc/os-release;echo $ID$VERSION_ID) \ > && curl -s -L https://nvidia.github.io/nvidia-docker/$distribution/nvidia-docker.repo | sudo tee /etc/yum.repos.d/nvidia-docker.repo [root@localhost docker]# cat /etc/yum.repos.d/nvidia-docker.repo [libnvidia-container] name=libnvidia-container baseurl=https://nvidia.github.io/libnvidia-container/stable/centos7/$basearch repo_gpgcheck=1 gpgcheck=0 enabled=1 gpgkey=https://nvidia.github.io/libnvidia-container/gpgkey sslverify=1 sslcacert=/etc/pki/tls/certs/ca-bundle.crt [libnvidia-container-experimental] name=libnvidia-container-experimental baseurl=https://nvidia.github.io/libnvidia-container/experimental/centos7/$basearch repo_gpgcheck=1 gpgcheck=0 enabled=0 gpgkey=https://nvidia.github.io/libnvidia-container/gpgkey sslverify=1 sslcacert=/etc/pki/tls/certs/ca-bundle.crt [nvidia-container-runtime] name=nvidia-container-runtime baseurl=https://nvidia.github.io/nvidia-container-runtime/stable/centos7/$basearch repo_gpgcheck=1 gpgcheck=0 enabled=1 gpgkey=https://nvidia.github.io/nvidia-container-runtime/gpgkey sslverify=1 sslcacert=/etc/pki/tls/certs/ca-bundle.crt [nvidia-container-runtime-experimental] name=nvidia-container-runtime-experimental baseurl=https://nvidia.github.io/nvidia-container-runtime/experimental/centos7/$basearch repo_gpgcheck=1 gpgcheck=0 enabled=0 gpgkey=https://nvidia.github.io/nvidia-container-runtime/gpgkey sslverify=1 sslcacert=/etc/pki/tls/certs/ca-bundle.crt [nvidia-docker] name=nvidia-docker baseurl=https://nvidia.github.io/nvidia-docker/centos7/$basearch repo_gpgcheck=1 gpgcheck=0 enabled=1 gpgkey=https://nvidia.github.io/nvidia-docker/gpgkey sslverify=1 sslcacert=/etc/pki/tls/certs/ca-bundle.crt [root@localhost docker]#安装下载nvidia-docker[root@localhost ~]# mkdir nvidia-docker2 [root@localhost ~]# cd nvidia-docker2 [root@localhost nvidia-docker2]# yum update -y [root@localhost nvidia-docker2]# repotrack nvidia-docker2 [root@localhost nvidia-docker2]# yum install ./* [root@localhost ~]# mkdir nvidia-container-toolkit [root@localhost ~]# cd nvidia-container-toolkit [root@localhost nvidia-container-toolkit]# repotrack nvidia-container-toolkit [root@ai-rd nvidia-container-toolkit]# yum install ./*下载镜像，并保存[root@localhost ~]# docker pull nvidia/cuda:11.0-base 11.0-base: Pulling from nvidia/cuda 54ee1f796a1e: Pull complete f7bfea53ad12: Pull complete 46d371e02073: Pull complete b66c17bbf772: Pull complete 3642f1a6dfb3: Pull complete e5ce55b8b4b9: Pull complete 155bc0332b0a: Pull complete Digest: sha256:774ca3d612de15213102c2dbbba55df44dc5cf9870ca2be6c6e9c627fa63d67a Status: Downloaded newer image for nvidia/cuda:11.0-base docker.io/nvidia/cuda:11.0-base [root@localhost ~]# [root@localhost ~]# docker images REPOSITORY TAG IMAGE ID CREATED SIZE nvidia/cuda 11.0-base 2ec708416bb8 15 months ago 122MB [root@localhost ~]# [root@localhost ~]# docker save -o cuda-11.0.tar nvidia/cuda:11.0-base [root@localhost ~]# [root@localhost ~]# ls cuda-11.0.tar cuda-11.0.tar [root@localhost ~]#在要测试的服务器上导入镜像[root@ai-rd cby]# docker load -i cuda-11.0.tar 2ce3c188c38d: Loading layer [==================================================>] 75.23MB/75.23MB ad44aa179b33: Loading layer [==================================================>] 1.011MB/1.011MB 35a91a75d24b: Loading layer [==================================================>] 15.36kB/15.36kB a4399aeb9a0e: Loading layer [==================================================>] 3.072kB/3.072kB fa39d0e9f3dc: Loading layer [==================================================>] 18.84MB/18.84MB 232fb43df6ad: Loading layer [==================================================>] 30.08MB/30.08MB 0da51e35db05: Loading layer [==================================================>] 22.53kB/22.53kB Loaded image: nvidia/cuda:11.0-base [root@ai-rd cby]# [root@ai-rd cby]# docker images | grep cuda nvidia/cuda 11.0-base 2ec708416bb8 15 months ago 122MB [root@ai-rd cby]#安装升级内核[root@ai-rd cby]# yum install kernel-headers [root@ai-rd cby]# yum install kernel-devel [root@ai-rd cby]# yum update kernel*禁用模块，并升级boot[root@ai-rd cby]# vim /etc/modprobe.d/blacklist-nouveau.conf [root@ai-rd cby]# cat /etc/modprobe.d/blacklist-nouveau.conf blacklist nouveau options nouveau modeset=0 [root@ai-rd cby]# [root@ai-rd cby]# mv /boot/initramfs-$(uname -r).img /boot/initramfs-$(uname -r).img.bak [root@ai-rd cby]# sudo dracut -v /boot/initramfs-$(uname -r).img $(uname -r)下载驱动并安装[root@localhost ~]# wget https://cn.download.nvidia.cn/tesla/450.156.00/NVIDIA-Linux-x86_64-450.156.00.run [root@ai-rd cby]# chmod +x NVIDIA-Linux-x86_64-450.156.00.run [root@ai-rd cby]# ./NVIDIA-Linux-x86_64-450.156.00.run配置docker[root@ai-rd ~]# vim /etc/docker/daemon.json [root@ai-rd ~]# cat /etc/docker/daemon.json { "runtimes": { "nvidia": { "path": "nvidia-container-runtime", "runtimeArgs": [] } } } [root@ai-rd ~]# [root@ai-rd ~]# systemctl daemon-reload [root@ai-rd ~]# [root@ai-rd ~]# [root@ai-rd ~]# [root@ai-rd ~]# systemctl restart docker [root@ai-rd ~]#测试docker中的调用情况[root@ai-rd ~]# [root@ai-rd ~]# sudo docker run --rm --gpus all nvidia/cuda:11.0-base nvidia-smi Tue Nov 23 06:03:04 2021 +-----------------------------------------------------------------------------+ | NVIDIA-SMI 450.156.00 Driver Version: 450.156.00 CUDA Version: 11.0 | |-------------------------------+----------------------+----------------------+ | GPU Name Persistence-M| Bus-Id Disp.A | Volatile Uncorr. ECC | | Fan Temp Perf Pwr:Usage/Cap| Memory-Usage | GPU-Util Compute M. | | | | MIG M. | |===============================+======================+======================| | 0 Tesla T4 Off | 00000000:86:00.0 Off | 0 | | N/A 90C P0 34W / 70W | 0MiB / 15109MiB | 6% Default | | | | N/A | +-------------------------------+----------------------+----------------------+ +-----------------------------------------------------------------------------+ | Processes: | | GPU GI CI PID Type Process name GPU Memory | | ID ID Usage | |=============================================================================| | No running processes found | +-----------------------------------------------------------------------------+ [root@ai-rd ~]# https://blog.csdn.net/qq_33921750https://my.oschina.net/u/3981543https://www.zhihu.com/people/chen-bu-yun-2https://segmentfault.com/u/hppyvyv6/articleshttps://juejin.cn/user/3315782802482007https://space.bilibili.com/352476552/articlehttps://cloud.tencent.com/developer/column/93230知乎、CSDN、开源中国、思否、掘金、哔哩哔哩、腾讯云本文使用 文章同步助手 同步
-
在Kubernetes（k8s）中使用GPU 介绍Kubernetes 支持对节点上的 AMD 和 NVIDIA GPU （图形处理单元）进行管理，目前处于实验状态。修改docker配置文件root@hello:~# cat /etc/docker/daemon.json { "default-runtime": "nvidia", "runtimes": { "nvidia": { "path": "/usr/bin/nvidia-container-runtime", "runtimeArgs": [] } }, "data-root": "/var/lib/docker", "exec-opts": ["native.cgroupdriver=systemd"], "registry-mirrors": [ "https://docker.mirrors.ustc.edu.cn", "http://hub-mirror.c.163.com" ], "insecure-registries": ["127.0.0.1/8"], "max-concurrent-downloads": 10, "live-restore": true, "log-driver": "json-file", "log-level": "warn", "log-opts": { "max-size": "50m", "max-file": "1" }, "storage-driver": "overlay2" } root@hello:~# root@hello:~# systemctl daemon-reload root@hello:~# systemctl start docker添加标签root@hello:~# kubectl label nodes 192.168.1.56 nvidia.com/gpu.present=true root@hello:~# kubectl get nodes -L nvidia.com/gpu.present NAME STATUS ROLES AGE VERSION GPU.PRESENT 192.168.1.55 Ready,SchedulingDisabled master 128m v1.22.2 192.168.1.56 Ready node 127m v1.22.2 true root@hello:~#安装helm仓库root@hello:~# curl https://baltocdn.com/helm/signing.asc | sudo apt-key add - root@hello:~# sudo apt-get install apt-transport-https --yes root@hello:~# echo "deb https://baltocdn.com/helm/stable/debian/ all main" | sudo tee /etc/apt/sources.list.d/helm-stable-debian.list root@hello:~# sudo apt-get update root@hello:~# sudo apt-get install helm helm install \ --version=0.10.0 \ --generate-name \ nvdp/nvidia-device-plugin查看是否有nvidiaroot@hello:~# kubectl describe node 192.168.1.56 | grep nv nvidia.com/gpu.present=true nvidia.com/gpu: 1 nvidia.com/gpu: 1 kube-system nvidia-device-plugin-1637728448-fgg2d 0 (0%) 0 (0%) 0 (0%) 0 (0%) 50s nvidia.com/gpu 0 0 root@hello:~#下载镜像root@hello:~# docker pull registry.cn-beijing.aliyuncs.com/ai-samples/tensorflow:1.5.0-devel-gpu root@hello:~# docker save -o tensorflow-gpu.tar registry.cn-beijing.aliyuncs.com/ai-samples/tensorflow:1.5.0-devel-gpu root@hello:~# docker load -i tensorflow-gpu.tar创建tensorflow测试podroot@hello:~# vim gpu-test.yaml root@hello:~# cat gpu-test.yaml apiVersion: v1 kind: Pod metadata: name: test-gpu labels: test-gpu: "true" spec: containers: - name: training image: registry.cn-beijing.aliyuncs.com/ai-samples/tensorflow:1.5.0-devel-gpu command: - python - tensorflow-sample-code/tfjob/docker/mnist/main.py - --max_steps=300 - --data_dir=tensorflow-sample-code/data resources: limits: nvidia.com/gpu: 1 tolerations: - effect: NoSchedule operator: Exists root@hello:~# root@hello:~# kubectl apply -f gpu-test.yaml pod/test-gpu created root@hello:~#查看日志root@hello:~# kubectl logs test-gpu WARNING:tensorflow:From tensorflow-sample-code/tfjob/docker/mnist/main.py:120: softmax_cross_entropy_with_logits (from tensorflow.python.ops.nn_ops) is deprecated and will be removed in a future version. Instructions for updating: Future major versions of TensorFlow will allow gradients to flow into the labels input on backprop by default. See tf.nn.softmax_cross_entropy_with_logits_v2. 2021-11-24 04:38:50.846973: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:895] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero 2021-11-24 04:38:50.847698: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1105] Found device 0 with properties: name: Tesla T4 major: 7 minor: 5 memoryClockRate(GHz): 1.59 pciBusID: 0000:00:10.0 totalMemory: 14.75GiB freeMemory: 14.66GiB 2021-11-24 04:38:50.847759: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1195] Creating TensorFlow device (/device:GPU:0) -> (device: 0, name: Tesla T4, pci bus id: 0000:00:10.0, compute capability: 7.5) root@hello:~# https://blog.csdn.net/qq_33921750https://my.oschina.net/u/3981543https://www.zhihu.com/people/chen-bu-yun-2https://segmentfault.com/u/hppyvyv6/articleshttps://juejin.cn/user/3315782802482007https://space.bilibili.com/352476552/articlehttps://cloud.tencent.com/developer/column/93230知乎、CSDN、开源中国、思否、掘金、哔哩哔哩、腾讯云本文使用 文章同步助手 同步