P6 生产硬化阶段交付物(46 文件):
## 1. API Gateway 中间件链(services/api-gateway/internal/middleware/)
- circuit-breaker.go: gobreaker v2 熔断器(5s 窗口/50% 错误率/30s OPEN→HALF_OPEN)
- ratelimit.go: 令牌桶限流(sync.Map + cleanup goroutine,默认 100rps/20 burst)
- cors.go: CORS 中间件(CORS_ORIGINS 环境变量)
- recovery.go: panic 恢复 + uuid request_id
- security.go: 安全头 + 请求体 10MB 限制
- requestid.go: 请求 ID 注入
- health/health.go: /healthz + /readyz 健康检查
- main.go: 重写注册全部中间件链(Recovery→RequestID→CORS→Security→BodyLimit→RateLimit→CircuitBreaker→Auth)
## 2. 基础设施硬化(infra/)
- backup/backup-mysql.sh: MySQL 全量备份(mysqldump+gzip,按服务独立)
- backup/restore-mysql.sh: 恢复脚本
- backup/backup-cron.sh: cron 调度入口(5 服务批量备份)
- alertmanager/alertmanager.yml: 告警路由(webhook + 邮件示例)
- prometheus/rules.yml: 8 条告警规则(服务可用性/性能/资源 3 组)
- grafana/dashboards/microservices-overview.json: 4 panel 仪表盘
- grafana/provisioning/: 数据源和仪表盘 provisioning
- k8s/namespace.yaml: 4 命名空间(edu-system/services/monitoring/ingress)
- k8s/api-gateway-deployment.yaml: Deployment + Service 骨架
- chaos/experiments.yaml: 3 个 Litmus 混沌实验(pod-kill/network-latency/disk-fill)
- docker-compose.monitoring.yml: 监控栈 profile
- security/secrets.example.env: 8 项密钥占位符
- security/waf-rules.conf: ModSecurity WAF 规则骨架
## 3. 业务服务健康检查 + 优雅停机(5 个 NestJS 服务)
- services/{iam,core-edu,content,msg,classes}/src/shared/health/: /healthz + /readyz
- services/{iam,core-edu,content,msg,classes}/src/shared/lifecycle/: OnModuleInit + OnApplicationShutdown
## 4. Python 服务健康检查
- services/{ai,data-ana}/src/health/health.py: FastAPI APIRouter
## 5. 运维文档
- docs/architecture/runbooks/p6-hardening.md: P6 总览 Runbook(9 章节)
- docs/architecture/runbooks/incident-response.md: 事件响应手册(5 章节)
- docs/architecture/004-p6-addendum.md: 004 架构补记 P6 章节
- docs/troubleshooting/known-issues-p6-addendum.md: 15 条 P6 场景→技术映射
## 验收信号
- RPO ≤ 15min(MySQL 备份 + binlog PITR)
- RTO ≤ 30min(K8s 滚动更新 + DNS 切换)
- P99 ≤ 500ms(熔断 + 限流 + 缓存)
- 熔断器错误率 > 50% 触发 OPEN
- 限流 100rps/20 burst
- 备份保留 7 天
- 混沌实验每月 1 次
95 lines
2.2 KiB
Bash
95 lines
2.2 KiB
Bash
#!/bin/bash
|
||
# MySQL 恢复脚本(Linux 容器内运行)
|
||
# 用法: restore-mysql.sh --service <name> --file <path> [--yes]
|
||
set -euo pipefail
|
||
|
||
# ---------- 参数解析 ----------
|
||
SERVICE=""
|
||
BACKUP_FILE=""
|
||
ASSUME_YES=false
|
||
|
||
while [[ $# -gt 0 ]]; do
|
||
case "$1" in
|
||
--service)
|
||
SERVICE="${2:-}"
|
||
shift 2
|
||
;;
|
||
--file)
|
||
BACKUP_FILE="${2:-}"
|
||
shift 2
|
||
;;
|
||
--yes)
|
||
ASSUME_YES=true
|
||
shift
|
||
;;
|
||
-h|--help)
|
||
echo "Usage: $0 --service <name> --file <path> [--yes]" >&2
|
||
echo " --service 目标微服务数据库名(必填)" >&2
|
||
echo " --file 备份文件路径 sql.gz(必填)" >&2
|
||
echo " --yes 跳过确认提示" >&2
|
||
exit 0
|
||
;;
|
||
*)
|
||
echo "[ERROR] 未知参数: $1" >&2
|
||
exit 1
|
||
;;
|
||
esac
|
||
done
|
||
|
||
# ---------- 参数校验 ----------
|
||
if [[ -z "$SERVICE" ]]; then
|
||
echo "[ERROR] --service 参数必填" >&2
|
||
exit 1
|
||
fi
|
||
|
||
if [[ -z "$BACKUP_FILE" ]]; then
|
||
echo "[ERROR] --file 参数必填" >&2
|
||
exit 1
|
||
fi
|
||
|
||
if [[ ! -f "$BACKUP_FILE" ]]; then
|
||
echo "[ERROR] 备份文件不存在: ${BACKUP_FILE}" >&2
|
||
exit 1
|
||
fi
|
||
|
||
# ---------- 环境变量 ----------
|
||
: "${MYSQL_HOST:=mysql}"
|
||
: "${MYSQL_PORT:=3306}"
|
||
: "${MYSQL_USER:=root}"
|
||
: "${MYSQL_PASSWORD:?MYSQL_PASSWORD 环境变量未设置}"
|
||
|
||
# ---------- 日志函数 ----------
|
||
log() {
|
||
echo "[$(date '+%Y-%m-%d %H:%M:%S')] $*" >&2
|
||
}
|
||
|
||
# ---------- 确认提示 ----------
|
||
log "[WARN] 即将向数据库 [${SERVICE}] 导入备份文件: ${BACKUP_FILE}"
|
||
log "[WARN] 此操作会覆盖目标数据库现有数据,不可撤销!"
|
||
|
||
if [[ "$ASSUME_YES" != "true" ]]; then
|
||
read -r -p "确认继续? (输入 YES 继续): " confirm
|
||
if [[ "$confirm" != "YES" ]]; then
|
||
log "[INFO] 用户取消操作"
|
||
exit 0
|
||
fi
|
||
fi
|
||
|
||
# ---------- 主流程 ----------
|
||
log "[INFO] 开始恢复服务: ${SERVICE}"
|
||
|
||
log "[INFO] 解压并导入: ${BACKUP_FILE}"
|
||
if ! gunzip -c "$BACKUP_FILE" \
|
||
| mysql \
|
||
--host="$MYSQL_HOST" \
|
||
--port="$MYSQL_PORT" \
|
||
--user="$MYSQL_USER" \
|
||
--password="$MYSQL_PASSWORD" \
|
||
"$SERVICE"; then
|
||
log "[ERROR] mysql 导入失败 (service=${SERVICE})"
|
||
exit 1
|
||
fi
|
||
|
||
log "[INFO] 恢复完成: ${SERVICE} <- ${BACKUP_FILE}"
|
||
exit 0
|