oadmin/sub2api
1
0
Fork 0
Code Issues Pull Requests 1 Actions Packages Projects Releases Wiki Activity

Revert "feat(gateway): 实现负载感知的账号调度优化 (#114)" (#117)

Browse Source 
This reverts commit 8d252303fc.
This commit is contained in:
Wesley Liddick
2025-12-31 21:45:42 -05:00
committed by GitHub
parent 8d252303fc
commit c5c12d4c8b
29 changed files with 133 additions and 2671 deletions
Download Patch File Download Diff File Expand all files Collapse all files

57
backend/internal/config/config.go
View File

@@ -3,7 +3,6 @@ package config
import (
"fmt"
"strings"
"time"
"github.com/spf13/viper"
)
@@ -120,37 +119,6 @@ type GatewayConfig struct {
// ConcurrencySlotTTLMinutes: 并发槽位过期时间（分钟）
// 应大于最长 LLM 请求时间，防止请求完成前槽位过期
ConcurrencySlotTTLMinutes int `mapstructure:"concurrency_slot_ttl_minutes"`
// 是否记录上游错误响应体摘要（避免输出请求内容）
LogUpstreamErrorBody bool `mapstructure:"log_upstream_error_body"`
// 上游错误响应体记录最大字节数（超过会截断）
LogUpstreamErrorBodyMaxBytes int `mapstructure:"log_upstream_error_body_max_bytes"`
// API-key 账号在客户端未提供 anthropic-beta 时，是否按需自动补齐（默认关闭以保持兼容）
InjectBetaForApiKey bool `mapstructure:"inject_beta_for_apikey"`
// 是否允许对部分 400 错误触发 failover（默认关闭以避免改变语义）
FailoverOn400 bool `mapstructure:"failover_on_400"`
// Scheduling: 账号调度相关配置
Scheduling GatewaySchedulingConfig `mapstructure:"scheduling"`
}
// GatewaySchedulingConfig accounts scheduling configuration.
type GatewaySchedulingConfig struct {
// 粘性会话排队配置
StickySessionMaxWaiting int `mapstructure:"sticky_session_max_waiting"`
StickySessionWaitTimeout time.Duration `mapstructure:"sticky_session_wait_timeout"`
// 兜底排队配置
FallbackWaitTimeout time.Duration `mapstructure:"fallback_wait_timeout"`
FallbackMaxWaiting int `mapstructure:"fallback_max_waiting"`
// 负载计算
LoadBatchEnabled bool `mapstructure:"load_batch_enabled"`
// 过期槽位清理周期（0 表示禁用）
SlotCleanupInterval time.Duration `mapstructure:"slot_cleanup_interval"`
}
func (s *ServerConfig) Address() string {
@@ -345,10 +313,6 @@ func setDefaults() {
// Gateway
viper.SetDefault("gateway.response_header_timeout", 300) // 300秒(5分钟)等待上游响应头，LLM高负载时可能排队较久
viper.SetDefault("gateway.log_upstream_error_body", false)
viper.SetDefault("gateway.log_upstream_error_body_max_bytes", 2048)
viper.SetDefault("gateway.inject_beta_for_apikey", false)
viper.SetDefault("gateway.failover_on_400", false)
viper.SetDefault("gateway.max_body_size", int64(100*1024*1024))
viper.SetDefault("gateway.connection_pool_isolation", ConnectionPoolIsolationAccountProxy)
// HTTP 上游连接池配置（针对 5000+ 并发用户优化）
@@ -359,12 +323,6 @@ func setDefaults() {
viper.SetDefault("gateway.max_upstream_clients", 5000)
viper.SetDefault("gateway.client_idle_ttl_seconds", 900)
viper.SetDefault("gateway.concurrency_slot_ttl_minutes", 15) // 并发槽位过期时间（支持超长请求）
viper.SetDefault("gateway.scheduling.sticky_session_max_waiting", 3)
viper.SetDefault("gateway.scheduling.sticky_session_wait_timeout", 45*time.Second)
viper.SetDefault("gateway.scheduling.fallback_wait_timeout", 30*time.Second)
viper.SetDefault("gateway.scheduling.fallback_max_waiting", 100)
viper.SetDefault("gateway.scheduling.load_batch_enabled", true)
viper.SetDefault("gateway.scheduling.slot_cleanup_interval", 30*time.Second)
// TokenRefresh
viper.SetDefault("token_refresh.enabled", true)
@@ -453,21 +411,6 @@ func (c *Config) Validate() error {
if c.Gateway.ConcurrencySlotTTLMinutes <= 0 {
return fmt.Errorf("gateway.concurrency_slot_ttl_minutes must be positive")
}
if c.Gateway.Scheduling.StickySessionMaxWaiting <= 0 {
return fmt.Errorf("gateway.scheduling.sticky_session_max_waiting must be positive")
}
if c.Gateway.Scheduling.StickySessionWaitTimeout <= 0 {
return fmt.Errorf("gateway.scheduling.sticky_session_wait_timeout must be positive")
}
if c.Gateway.Scheduling.FallbackWaitTimeout <= 0 {
return fmt.Errorf("gateway.scheduling.fallback_wait_timeout must be positive")
}
if c.Gateway.Scheduling.FallbackMaxWaiting <= 0 {
return fmt.Errorf("gateway.scheduling.fallback_max_waiting must be positive")
}
if c.Gateway.Scheduling.SlotCleanupInterval < 0 {
return fmt.Errorf("gateway.scheduling.slot_cleanup_interval must be non-negative")
}
return nil
}

49
backend/internal/config/config_test.go
View File

@@ -1,11 +1,6 @@
package config
import (
"testing"
"time"
"github.com/spf13/viper"
)
import "testing"
func TestNormalizeRunMode(t *testing.T) {
tests := []struct {
@@ -26,45 +21,3 @@ func TestNormalizeRunMode(t *testing.T) {
}
}
}
func TestLoadDefaultSchedulingConfig(t *testing.T) {
viper.Reset()
cfg, err := Load()
if err != nil {
t.Fatalf("Load() error: %v", err)
}
if cfg.Gateway.Scheduling.StickySessionMaxWaiting != 3 {
t.Fatalf("StickySessionMaxWaiting = %d, want 3", cfg.Gateway.Scheduling.StickySessionMaxWaiting)
}
if cfg.Gateway.Scheduling.StickySessionWaitTimeout != 45*time.Second {
t.Fatalf("StickySessionWaitTimeout = %v, want 45s", cfg.Gateway.Scheduling.StickySessionWaitTimeout)
}
if cfg.Gateway.Scheduling.FallbackWaitTimeout != 30*time.Second {
t.Fatalf("FallbackWaitTimeout = %v, want 30s", cfg.Gateway.Scheduling.FallbackWaitTimeout)
}
if cfg.Gateway.Scheduling.FallbackMaxWaiting != 100 {
t.Fatalf("FallbackMaxWaiting = %d, want 100", cfg.Gateway.Scheduling.FallbackMaxWaiting)
}
if !cfg.Gateway.Scheduling.LoadBatchEnabled {
t.Fatalf("LoadBatchEnabled = false, want true")
}
if cfg.Gateway.Scheduling.SlotCleanupInterval != 30*time.Second {
t.Fatalf("SlotCleanupInterval = %v, want 30s", cfg.Gateway.Scheduling.SlotCleanupInterval)
}
}
func TestLoadSchedulingConfigFromEnv(t *testing.T) {
viper.Reset()
t.Setenv("GATEWAY_SCHEDULING_STICKY_SESSION_MAX_WAITING", "5")
cfg, err := Load()
if err != nil {
t.Fatalf("Load() error: %v", err)
}
if cfg.Gateway.Scheduling.StickySessionMaxWaiting != 5 {
t.Fatalf("StickySessionMaxWaiting = %d, want 5", cfg.Gateway.Scheduling.StickySessionMaxWaiting)
}
}