Merge pull request #894 from touwaeriol/pr/startup-concurrency-cleanup

feat: cleanup stale concurrency slots on startup

backend/internal/service/concurrency_service.go

@@ -43,6 +43,9 @@ type ConcurrencyCache interface {
 
 	// 清理过期槽位（后台任务）
 	CleanupExpiredAccountSlots(ctx context.Context, accountID int64) error
+
+	// 启动时清理旧进程遗留槽位与等待计数
+	CleanupStaleProcessSlots(ctx context.Context, activeRequestPrefix string) error
 }
 
 var (
@@ -59,13 +62,22 @@ func initRequestIDPrefix() string {
 	return "r" + strconv.FormatUint(fallback, 36)
 }
 
-// generateRequestID generates a unique request ID for concurrency slot tracking.
-// Format: {process_random_prefix}-{base36_counter}
+func RequestIDPrefix() string {
+	return requestIDPrefix
+}
+
 func generateRequestID() string {
 	seq := requestIDCounter.Add(1)
 	return requestIDPrefix + "-" + strconv.FormatUint(seq, 36)
 }
 
+func (s *ConcurrencyService) CleanupStaleProcessSlots(ctx context.Context) error {
+	if s == nil || s.cache == nil {
+		return nil
+	}
+	return s.cache.CleanupStaleProcessSlots(ctx, RequestIDPrefix())
+}
+
 const (
 	// Default extra wait slots beyond concurrency limit
 	defaultExtraWaitSlots = 20

backend/internal/service/concurrency_service_test.go

@@ -91,6 +91,32 @@ func (c *stubConcurrencyCacheForTest) CleanupExpiredAccountSlots(_ context.Conte
 	return c.cleanupErr
 }
 
+func (c *stubConcurrencyCacheForTest) CleanupStaleProcessSlots(_ context.Context, _ string) error {
+	return c.cleanupErr
+}
+
+type trackingConcurrencyCache struct {
+	stubConcurrencyCacheForTest
+	cleanupPrefix string
+}
+
+func (c *trackingConcurrencyCache) CleanupStaleProcessSlots(_ context.Context, prefix string) error {
+	c.cleanupPrefix = prefix
+	return c.cleanupErr
+}
+
+func TestCleanupStaleProcessSlots_NilCache(t *testing.T) {
+	svc := &ConcurrencyService{cache: nil}
+	require.NoError(t, svc.CleanupStaleProcessSlots(context.Background()))
+}
+
+func TestCleanupStaleProcessSlots_DelegatesPrefix(t *testing.T) {
+	cache := &trackingConcurrencyCache{}
+	svc := NewConcurrencyService(cache)
+	require.NoError(t, svc.CleanupStaleProcessSlots(context.Background()))
+	require.Equal(t, RequestIDPrefix(), cache.cleanupPrefix)
+}
+
 func TestAcquireAccountSlot_Success(t *testing.T) {
 	cache := &stubConcurrencyCacheForTest{acquireResult: true}
 	svc := NewConcurrencyService(cache)

backend/internal/service/gateway_multiplatform_test.go

@@ -1986,6 +1986,10 @@ func (m *mockConcurrencyCache) CleanupExpiredAccountSlots(ctx context.Context, a
 	return nil
 }
 
+func (m *mockConcurrencyCache) CleanupStaleProcessSlots(ctx context.Context, activeRequestPrefix string) error {
+	return nil
+}
+
 func (m *mockConcurrencyCache) GetUsersLoadBatch(ctx context.Context, users []UserWithConcurrency) (map[int64]*UserLoadInfo, error) {
 	result := make(map[int64]*UserLoadInfo, len(users))
 	for _, user := range users {

backend/internal/service/wire.go

@@ -105,6 +105,9 @@ func ProvideDeferredService(accountRepo AccountRepository, timingWheel *TimingWh
 // ProvideConcurrencyService creates ConcurrencyService and starts slot cleanup worker.
 func ProvideConcurrencyService(cache ConcurrencyCache, accountRepo AccountRepository, cfg *config.Config) *ConcurrencyService {
 	svc := NewConcurrencyService(cache)
+	if err := svc.CleanupStaleProcessSlots(context.Background()); err != nil {
+		logger.LegacyPrintf("service.concurrency", "Warning: startup cleanup stale process slots failed: %v", err)
+	}
 	if cfg != nil {
 		svc.StartSlotCleanupWorker(accountRepo, cfg.Gateway.Scheduling.SlotCleanupInterval)
 	}