76 lines
2.7 KiB
YAML
76 lines
2.7 KiB
YAML
# AI Agent API 的 Deployment：滚动更新、三种探针、资源限制、非 root 运行、优雅退出
|
|
apiVersion: apps/v1
|
|
kind: Deployment
|
|
metadata:
|
|
name: agent-api
|
|
labels:
|
|
app.kubernetes.io/name: agent-api
|
|
spec:
|
|
replicas: 3
|
|
revisionHistoryLimit: 5
|
|
selector:
|
|
matchLabels:
|
|
app.kubernetes.io/name: agent-api
|
|
strategy:
|
|
type: RollingUpdate
|
|
rollingUpdate:
|
|
maxSurge: 1 # 更新时最多多出 1 个 Pod
|
|
maxUnavailable: 0 # 更新过程中可用 Pod 数不减少
|
|
template:
|
|
metadata:
|
|
labels:
|
|
app.kubernetes.io/name: agent-api
|
|
spec:
|
|
terminationGracePeriodSeconds: 90 # 留时间让正在进行的流式回答结束
|
|
securityContext:
|
|
runAsNonRoot: true
|
|
runAsUser: 10001
|
|
containers:
|
|
- name: api
|
|
image: registry.example.com/agent-api:1.4.2 # 使用固定版本，不用 latest
|
|
ports:
|
|
- name: http
|
|
containerPort: 8000
|
|
envFrom:
|
|
- configMapRef:
|
|
name: agent-api-config
|
|
env:
|
|
- name: LLM_API_KEY
|
|
valueFrom:
|
|
secretKeyRef:
|
|
name: agent-api-secrets # 由运维或密钥管理系统创建，不在仓库中
|
|
key: llm-api-key
|
|
resources:
|
|
requests:
|
|
cpu: "250m"
|
|
memory: "256Mi"
|
|
limits:
|
|
memory: "512Mi" # 内存设上限防止拖垮节点；CPU 不设上限避免被限流（按团队规范）
|
|
startupProbe: # 启动慢（加载模型配置、预热连接）时，避免被存活探针误杀
|
|
httpGet:
|
|
path: /healthz
|
|
port: http
|
|
periodSeconds: 5
|
|
failureThreshold: 24
|
|
readinessProbe: # 未就绪时不接收流量（例如依赖的 Redis 不可用）
|
|
httpGet:
|
|
path: /readyz
|
|
port: http
|
|
periodSeconds: 5
|
|
failureThreshold: 3
|
|
livenessProbe: # 进程卡死时重启；不要检查外部依赖，否则依赖故障会引发全体重启
|
|
httpGet:
|
|
path: /healthz
|
|
port: http
|
|
periodSeconds: 10
|
|
failureThreshold: 3
|
|
lifecycle:
|
|
preStop: # 先等负载均衡摘除，再收到 SIGTERM。sleep 动作需要较新的 Kubernetes（1.30+，以官方文档为准），旧版本用 exec sleep
|
|
sleep:
|
|
seconds: 5
|
|
securityContext:
|
|
allowPrivilegeEscalation: false
|
|
readOnlyRootFilesystem: true
|
|
capabilities:
|
|
drop: ["ALL"]
|