feat(gateway): 实现负载感知的账号调度优化

- 新增调度配置:粘性会话排队、兜底排队、负载计算、槽位清理
- 实现账号级等待队列和批量负载查询(Redis Lua 脚本)
- 三层选择策略:粘性会话优先 → 负载感知选择 → 兜底排队
- 后台定期清理过期槽位,防止资源泄漏
- 集成到所有网关处理器(Claude/Gemini/OpenAI)
This commit is contained in:
IanShaw027
2026-01-01 04:01:51 +08:00
parent 2ccdc2b8ef
commit 592d2d0978
16 changed files with 1342 additions and 47 deletions

View File

@@ -197,13 +197,17 @@ func (h *GatewayHandler) GeminiV1BetaModels(c *gin.Context) {
// 3) select account (sticky session based on request body)
parsedReq, _ := service.ParseGatewayRequest(body)
sessionHash := h.gatewayService.GenerateSessionHash(parsedReq)
sessionKey := sessionHash
if sessionHash != "" {
sessionKey = "gemini:" + sessionHash
}
const maxAccountSwitches = 3
switchCount := 0
failedAccountIDs := make(map[int64]struct{})
lastFailoverStatus := 0
for {
account, err := h.geminiCompatService.SelectAccountForModelWithExclusions(c.Request.Context(), apiKey.GroupID, sessionHash, modelName, failedAccountIDs)
selection, err := h.gatewayService.SelectAccountWithLoadAwareness(c.Request.Context(), apiKey.GroupID, sessionKey, modelName, failedAccountIDs)
if err != nil {
if len(failedAccountIDs) == 0 {
googleError(c, http.StatusServiceUnavailable, "No available Gemini accounts: "+err.Error())
@@ -212,12 +216,46 @@ func (h *GatewayHandler) GeminiV1BetaModels(c *gin.Context) {
handleGeminiFailoverExhausted(c, lastFailoverStatus)
return
}
account := selection.Account
// 4) account concurrency slot
accountReleaseFunc, err := geminiConcurrency.AcquireAccountSlotWithWait(c, account.ID, account.Concurrency, stream, &streamStarted)
if err != nil {
googleError(c, http.StatusTooManyRequests, err.Error())
return
accountReleaseFunc := selection.ReleaseFunc
var accountWaitRelease func()
if !selection.Acquired {
if selection.WaitPlan == nil {
googleError(c, http.StatusServiceUnavailable, "No available Gemini accounts")
return
}
canWait, err := geminiConcurrency.IncrementAccountWaitCount(c.Request.Context(), account.ID, selection.WaitPlan.MaxWaiting)
if err != nil {
log.Printf("Increment account wait count failed: %v", err)
} else if !canWait {
log.Printf("Account wait queue full: account=%d", account.ID)
googleError(c, http.StatusTooManyRequests, "Too many pending requests, please retry later")
return
}
accountWaitRelease = func() {
geminiConcurrency.DecrementAccountWaitCount(c.Request.Context(), account.ID)
}
accountReleaseFunc, err = geminiConcurrency.AcquireAccountSlotWithWaitTimeout(
c,
account.ID,
selection.WaitPlan.MaxConcurrency,
selection.WaitPlan.Timeout,
stream,
&streamStarted,
)
if err != nil {
if accountWaitRelease != nil {
accountWaitRelease()
}
googleError(c, http.StatusTooManyRequests, err.Error())
return
}
if err := h.gatewayService.BindStickySession(c.Request.Context(), sessionKey, account.ID); err != nil {
log.Printf("Bind sticky session failed: %v", err)
}
}
// 5) forward (根据平台分流)
@@ -230,6 +268,9 @@ func (h *GatewayHandler) GeminiV1BetaModels(c *gin.Context) {
if accountReleaseFunc != nil {
accountReleaseFunc()
}
if accountWaitRelease != nil {
accountWaitRelease()
}
if err != nil {
var failoverErr *service.UpstreamFailoverError
if errors.As(err, &failoverErr) {