All checks were successful
构建并部署到测试环境(无 SSH) / build-and-deploy (push) Successful in 9m46s
【核心变更】
1. 停复机逻辑统一(StopResumeService)
- 新增 EvaluateAndAct 统一入口,封装三条件停复机判断
- 停机条件:无套餐(no_package) / 流量耗尽(traffic_exhausted) / 未实名(not_realname)
- 复机条件:stop_reason 合规 + 有套餐且未耗尽 + 已实名或行业卡
- 修复设备套餐 Bug:hasValidPackage 按 device_id 查套餐,而非仅 iot_card_id
- 设备维度停复机加幂等锁(Redis SetNX,TTL 30s),防止多卡并发重复调 Gateway
2. Redis 分片队列(PollingQueueManager)
- 新建 queue_manager.go,封装所有轮询 Redis 操作
- 16 分片 Sorted Set,Key 格式:polling:shard:{shardID}:queue:{taskType}
- Lua 脚本原子出队(ZRANGEBYSCORE + 分批 ZREM),消除竞态窗口
- 新增背压检测:队列深度超 50 万时 Scheduler 跳过该分片
- RemoveFromAllQueues 覆盖 4 种任务类型(含 protect)
3. Handler 拆分(polling_handler.go 1360行 → 5个专注文件)
- polling_base.go:共享基类(并发控制/卡缓存/重入队)
- polling_realname_handler.go:实名采集,实名 0→1 时立即触发复机
- polling_carddata_handler.go:流量采集,保留跨月边界检测逻辑
- polling_package_handler.go:套餐采集,委托 EvaluateAndAct 决策
- polling_protect_handler.go:保护期一致性检查,保护期内强制修正
4. 配置管理(PollingConfigManager)
- 新建 config_manager.go,从 scheduler.go 提取配置职责
- 内存缓存 + 5 分钟定时刷新,刷新失败保留原缓存
- 修复 getCardCondition:停机卡返回 suspended,不再错配 activated 配置
5. 渐进式初始化(CardInitializer)
- 新建 initializer.go,分批加载(每批 10 万),批次间 sleep 500ms
- 过滤 enable_polling=false 的卡,初始化完成前 Scheduler 不出队
6. 卡生命周期服务(PollingLifecycleService)
- 新建 lifecycle_service.go,替代已删除的 callbacks.go 和 api_callback.go
- OnCardCreated/OnCardEnabled/OnCardStatusChanged 入队前检查 enable_polling
7. Scheduler 精简(1000+行 → 227行)
- 保留纯调度循环:scheduleLoop + processShardSchedule + enqueueBatch
- 保留每 10 秒触发套餐过期检测和流量重置
- 移除所有 DB 操作、配置加载、卡初始化逻辑
8. 轮询管控 API(enable_polling)
- 新增 PUT /api/admin/assets/:id/polling-status 接口
- 支持对设备/卡维度开关轮询,关闭后从所有分片队列移除
9. 数据库迁移
- 000103:tb_device 新增 enable_polling 字段(boolean, NOT NULL, DEFAULT true)
- 000104:新增 suspended 轮询配置,为 activated 配置补全 protect_check_interval
【文件统计】
- 新增:19 个文件(handler × 5、polling 组件 × 4、迁移 × 3 等)
- 修改:20 个文件(bootstrap 注入、store 接口、monitoring 适配分片等)
- 删除:3 个文件(polling_handler.go、callbacks.go、api_callback.go)
Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)
Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
152 lines
6.1 KiB
Go
152 lines
6.1 KiB
Go
package task
|
||
|
||
import (
|
||
"context"
|
||
"time"
|
||
|
||
"github.com/hibiken/asynq"
|
||
"go.uber.org/zap"
|
||
|
||
"github.com/break/junhong_cmp_fiber/internal/gateway"
|
||
iot_card_svc "github.com/break/junhong_cmp_fiber/internal/service/iot_card"
|
||
"github.com/break/junhong_cmp_fiber/internal/store/postgres"
|
||
"github.com/break/junhong_cmp_fiber/pkg/constants"
|
||
)
|
||
|
||
// PollingProtectHandler 保护期一致性检查任务处理器
|
||
// 保护期内:直接调 Gateway 强制停/复机(绕过 EvaluateAndAct 三条件判断)
|
||
// 保护期结束:调 EvaluateAndAct 重新评估正常停复机条件
|
||
// 两种路径不可混淆:保护期内=强制修正;保护期结束=重新评估
|
||
type PollingProtectHandler struct {
|
||
base *PollingBase
|
||
gateway *gateway.Client
|
||
iotCardStore *postgres.IotCardStore
|
||
deviceSimBindingStore *postgres.DeviceSimBindingStore
|
||
stopResumeSvc iot_card_svc.StopResumeServiceInterface
|
||
}
|
||
|
||
// NewPollingProtectHandler 创建保护期一致性检查任务处理器
|
||
func NewPollingProtectHandler(
|
||
base *PollingBase,
|
||
gw *gateway.Client,
|
||
iotCardStore *postgres.IotCardStore,
|
||
deviceSimBindingStore *postgres.DeviceSimBindingStore,
|
||
stopResumeSvc iot_card_svc.StopResumeServiceInterface,
|
||
) *PollingProtectHandler {
|
||
return &PollingProtectHandler{
|
||
base: base,
|
||
gateway: gw,
|
||
iotCardStore: iotCardStore,
|
||
deviceSimBindingStore: deviceSimBindingStore,
|
||
stopResumeSvc: stopResumeSvc,
|
||
}
|
||
}
|
||
|
||
// Handle 处理保护期一致性检查任务
|
||
func (h *PollingProtectHandler) Handle(ctx context.Context, t *asynq.Task) error {
|
||
startTime := time.Now()
|
||
|
||
cardID, ok := parseTaskPayload(t.Payload(), h.base.logger)
|
||
if !ok {
|
||
return nil
|
||
}
|
||
|
||
if !h.base.acquireConcurrency(ctx, constants.TaskTypePollingProtect) {
|
||
h.base.logger.Debug("并发已满,重新入队", zap.Uint("card_id", cardID))
|
||
return h.base.requeueCard(ctx, cardID, constants.TaskTypePollingProtect)
|
||
}
|
||
defer h.base.releaseConcurrency(ctx, constants.TaskTypePollingProtect)
|
||
|
||
card, err := h.iotCardStore.GetByID(ctx, cardID)
|
||
if err != nil {
|
||
if isNotFound(err) {
|
||
return nil
|
||
}
|
||
h.base.logger.Error("查询卡信息失败", zap.Uint("card_id", cardID), zap.Error(err))
|
||
return h.base.requeueCard(ctx, cardID, constants.TaskTypePollingProtect)
|
||
}
|
||
|
||
// 独立卡(未绑设备)跳过保护期检查
|
||
if card.IsStandalone {
|
||
return h.base.requeueCard(ctx, cardID, constants.TaskTypePollingProtect)
|
||
}
|
||
|
||
// 未实名卡跳过保护期检查
|
||
if card.RealNameStatus != constants.RealNameStatusVerified {
|
||
return h.base.requeueCard(ctx, cardID, constants.TaskTypePollingProtect)
|
||
}
|
||
|
||
binding, err := h.deviceSimBindingStore.GetActiveBindingByCardID(ctx, card.ID)
|
||
if err != nil || binding == nil {
|
||
return h.base.requeueCard(ctx, cardID, constants.TaskTypePollingProtect)
|
||
}
|
||
deviceID := binding.DeviceID
|
||
|
||
stopProtect := h.base.redis.Exists(ctx, constants.RedisDeviceProtectKey(deviceID, "stop")).Val() > 0
|
||
startProtect := h.base.redis.Exists(ctx, constants.RedisDeviceProtectKey(deviceID, "start")).Val() > 0
|
||
|
||
switch {
|
||
case stopProtect && card.NetworkStatus == constants.NetworkStatusOnline:
|
||
// 保护期内:停机保护期发现开机卡 → 强制停机(绕过 EvaluateAndAct)
|
||
h.base.logger.Info("保护期一致性:停机保护期内发现开机卡,强制停机",
|
||
zap.Uint("card_id", card.ID), zap.Uint("device_id", deviceID))
|
||
if h.gateway == nil {
|
||
break
|
||
}
|
||
if err := h.gateway.StopCard(ctx, &gateway.CardOperationReq{CardNo: card.ICCID}); err != nil {
|
||
h.base.logger.Error("保护期强制停机失败",
|
||
zap.Uint("card_id", card.ID), zap.Error(err))
|
||
h.base.updateStats(ctx, constants.TaskTypePollingProtect, false, time.Since(startTime))
|
||
return h.base.requeueCard(ctx, cardID, constants.TaskTypePollingProtect)
|
||
}
|
||
if updateErr := h.iotCardStore.UpdateFields(ctx, cardID, map[string]any{
|
||
"network_status": constants.NetworkStatusOffline,
|
||
"stopped_at": time.Now(),
|
||
"stop_reason": constants.StopReasonProtectPeriod,
|
||
}); updateErr != nil {
|
||
h.base.logger.Warn("保护期停机 DB 更新失败", zap.Uint("card_id", cardID), zap.Error(updateErr))
|
||
}
|
||
h.base.updateCardCache(ctx, cardID, map[string]any{"network_status": constants.NetworkStatusOffline})
|
||
|
||
case startProtect && card.NetworkStatus == constants.NetworkStatusOffline:
|
||
// 保护期内:复机保护期发现停机卡 → 强制复机(绕过 EvaluateAndAct)
|
||
h.base.logger.Info("保护期一致性:复机保护期内发现停机卡,强制复机",
|
||
zap.Uint("card_id", card.ID), zap.Uint("device_id", deviceID))
|
||
if h.gateway == nil {
|
||
break
|
||
}
|
||
if err := h.gateway.StartCard(ctx, &gateway.CardOperationReq{CardNo: card.ICCID}); err != nil {
|
||
h.base.logger.Error("保护期强制复机失败",
|
||
zap.Uint("card_id", card.ID), zap.Error(err))
|
||
h.base.updateStats(ctx, constants.TaskTypePollingProtect, false, time.Since(startTime))
|
||
return h.base.requeueCard(ctx, cardID, constants.TaskTypePollingProtect)
|
||
}
|
||
if updateErr := h.iotCardStore.UpdateFields(ctx, cardID, map[string]any{
|
||
"network_status": constants.NetworkStatusOnline,
|
||
"resumed_at": time.Now(),
|
||
"stop_reason": "",
|
||
}); updateErr != nil {
|
||
h.base.logger.Warn("保护期复机 DB 更新失败", zap.Uint("card_id", cardID), zap.Error(updateErr))
|
||
}
|
||
h.base.updateCardCache(ctx, cardID, map[string]any{"network_status": constants.NetworkStatusOnline})
|
||
|
||
case !stopProtect && !startProtect:
|
||
// 保护期结束:调 EvaluateAndAct 重新评估正常停复机条件
|
||
if h.stopResumeSvc != nil {
|
||
if evalErr := h.stopResumeSvc.EvaluateAndAct(ctx, card); evalErr != nil {
|
||
h.base.logger.Warn("保护期结束后停复机评估失败",
|
||
zap.Uint("card_id", cardID), zap.Error(evalErr))
|
||
}
|
||
}
|
||
}
|
||
|
||
if updateErr := h.iotCardStore.UpdateFields(ctx, cardID, map[string]any{
|
||
"last_protect_check_at": time.Now(),
|
||
}); updateErr != nil {
|
||
h.base.logger.Warn("更新保护期检查时间失败", zap.Uint("card_id", cardID), zap.Error(updateErr))
|
||
}
|
||
|
||
h.base.updateStats(ctx, constants.TaskTypePollingProtect, true, time.Since(startTime))
|
||
return h.base.requeueCard(ctx, cardID, constants.TaskTypePollingProtect)
|
||
}
|