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

@@ -3,6 +3,7 @@ package config
import (
"fmt"
"strings"
"time"
"github.com/spf13/viper"
)
@@ -119,6 +120,26 @@ 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"`
// 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 {
@@ -323,6 +344,12 @@ 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)
@@ -411,6 +438,21 @@ 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
}

View File

@@ -1,6 +1,11 @@
package config
import "testing"
import (
"testing"
"time"
"github.com/spf13/viper"
)
func TestNormalizeRunMode(t *testing.T) {
tests := []struct {
@@ -21,3 +26,45 @@ 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)
}
}