🚀 CI/CD 自动部署模块运维手册

# Master 节点初始化
kubeadm init \
  --pod-network-cidr=10.244.0.0/16 \
  --service-cidr=10.96.0.0/12 \
  --apiserver-advertise-address=192.168.1.10

# 配置 kubectl
mkdir -p $HOME/.kube
cp -i /etc/kubernetes/admin.conf $HOME/.kube/config
chown $(id -u):$(id -g) $HOME/.kube/config

# Worker 节点加入
kubeadm join 192.168.1.10:6443 \
  --token <token> \
  --discovery-token-ca-cert-hash sha256:<hash>

# 添加 Jenkins Helm 仓库
helm repo add jenkins https://charts.jenkins.io
helm repo update

# 创建命名空间
kubectl create namespace jenkins

# 安装 Jenkins
helm install jenkins jenkins/jenkins \
  -n jenkins \
  -f jenkins-values.yaml

# 下载 Harbor 安装包
wget https://github.com/goharbor/harbor/releases/download/v2.9.0/harbor-offline-installer-v2.9.0.tgz
tar xvf harbor-offline-installer-v2.9.0.tgz
cd harbor

# 编辑 harbor.yml 并安装
./install.sh

# 启动顺序
kubectl apply -f /opt/auto-research/core-services/
kubectl get pods -n auto-research-system
kubectl apply -f /opt/auto-research/applications/

# 停止顺序
kubectl delete -f /opt/auto-research/applications/
kubectl delete -f /opt/auto-research/core-services/

# 更新镜像版本
kubectl set image deployment/myapp \
  myapp=harbor.example.com/myapp:v1.2.0 \
  -n auto-research-prod

# 查看部署状态
kubectl rollout status deployment/myapp -n auto-research-prod

# 回滚
kubectl rollout undo deployment/myapp -n auto-research-prod

# 查看历史
kubectl rollout history deployment/myapp -n auto-research-prod

# 查看 Pod 日志
kubectl logs myapp-5d8c9f7b6-x2k4m -n auto-research-prod

# 实时跟踪日志
kubectl logs -f myapp-5d8c9f7b6-x2k4m -n auto-research-prod

# 搜索错误日志
kubectl logs myapp-pod -n auto-research-prod | grep "ERROR"

# 手动扩缩容
kubectl scale deployment myapp --replicas=10 -n auto-research-prod

# 查看 HPA 状态
kubectl get hpa -n auto-research-prod

# 编辑 HPA
kubectl edit hpa myapp-hpa -n auto-research-prod

groups:
- name: auto-research-alerts
  rules:
  - alert: HighCPUUsage
    expr: 100 - (avg by(instance) (irate(node_cpu_seconds_total{mode="idle"}[5m])) * 100) > 80
    for: 5m
    labels:
      severity: warning
    annotations:
      summary: "节点 {{ $labels.instance }} CPU 使用率过高"
      description: "CPU 使用率：{{ $value }}%"
  
  - alert: PodCrashLooping
    expr: rate(kube_pod_container_status_restarts_total[15m]) * 60 * 5 > 0
    for: 15m
    labels:
      severity: critical
    annotations:
      summary: "Pod {{ $labels.namespace }}/{{ $labels.pod }} 频繁重启"

# 1. 查看 Pod 状态
kubectl get pod <pod-name> -n <namespace>

# 2. 查看详情
kubectl describe pod <pod-name> -n <namespace>

# 3. 查看日志
kubectl logs <pod-name> -n <namespace>

# 4. 进入容器调试
kubectl exec -it <pod-name> -n <namespace> -- /bin/sh

# 检查 Service 和 Endpoints
kubectl get svc <service-name> -n <namespace>
kubectl get endpoints <service-name> -n <namespace>

# 检查 Pod 标签匹配
kubectl get pods -n <namespace> --show-labels

# 测试连通性
kubectl run -it --rm debug --image=busybox --restart=Never -n <namespace> -- \
  nslookup <service-name>.<namespace>.svc.cluster.local