ipconfig  /flushdns

sudo systemctl restart nscd 

sudo killall -HUP mDNSResponder

[ R8 root ~]#ss -antulp | grep 80
tcp   LISTEN 0      2048         0.0.0.0:80        0.0.0.0:*    users:(("docker-proxy",pid=1501,fd=4))
tcp   LISTEN 0      2048            [::]:80           [::]:*    users:(("docker-proxy",pid=1507,fd=4))
[ R8 root ~]#

[ R8 root ~]#netstat -antulp | grep docker
tcp        0      0 0.0.0.0:80              0.0.0.0:*               LISTEN      1501/docker-proxy   
tcp6       0      0 :::80                   :::*                    LISTEN      1507/docker-proxy   
[ R8 root ~]#

[ R8 root ~]#sudo dnf -y install nc             #from   nmap-ncat  appstream
[ R8 root ~]#sudo apt install netcat


### 要检查特定端口是否开放，可以使用 nc 命令尝试连接到该端口
[ R8 root ~]#nc -zv 127.0.0.1 23
Ncat: Version 7.92 ( https://nmap.org/ncat )
Ncat: Connection refused.
[ R8 root ~]#nc -zv 127.0.0.1 80
Ncat: Version 7.92 ( https://nmap.org/ncat )
Ncat: Connected to 127.0.0.1:80.
Ncat: 0 bytes sent, 0 bytes received in 0.01 seconds.
[ R8 root ~]#

docker run -d --gpus=all -v ollama:/root/.ollama -p 11434:11434 --name ollama ollama/ollama

#基于Debain系列服务器
curl -fsSL https://nvidia.github.io/libnvidia-container/gpgkey \
    | sudo gpg --dearmor -o /usr/share/keyrings/nvidia-container-toolkit-keyring.gpg
curl -s -L https://nvidia.github.io/libnvidia-container/stable/deb/nvidia-container-toolkit.list \
    | sed 's#deb https://#deb [signed-by=/usr/share/keyrings/nvidia-container-toolkit-keyring.gpg] https://#g' \
    | sudo tee /etc/apt/sources.list.d/nvidia-container-toolkit.list
sudo apt-get update
sudo apt-get install -y nvidia-container-toolkit




#基于RedHat系列服务器
curl -s -L https://nvidia.github.io/libnvidia-container/stable/rpm/nvidia-container-toolkit.repo \
    | sudo tee /etc/yum.repos.d/nvidia-container-toolkit.repo
sudo yum install -y nvidia-container-toolkit
sudo nvidia-ctk runtime configure --runtime=docker
sudo systemctl restart docker

kubectl label node gpu=a100


apiVersion: apps/v1
kind: StatefulSet
metadata:
  name: ollama
  namespace: llama
spec:
  serviceName: "ollama"
  replicas: 1
  selector:
    matchLabels:
      app: ollama
  template:
    metadata:
      labels:
        app: ollama
    spec:
      nodeSelector:
        gpu: a100
      containers:
        - name: ollama
          image: ollama/ollama:latest
          ports:
            - containerPort: 11434
          resources:
            requests:
              cpu: "6000m"
              memory: "6Gi"
              nvidia.com/gpu: "6"
            limits:
              cpu: "30000m"
              memory: "30Gi"
          volumeMounts:
            - name: ollama-volume
              mountPath: /root/.ollama
          tty: true
  volumeClaimTemplates:
    - metadata:
        name: ollama-volume
      spec:
        accessModes: ["ReadWriteOnce"]
        resources:
          requests:
            storage: 2000Gi