Refactor: Optimize the request rate limiting for ModelRequestRateLimitCount.
Reason: The original steps 1 and 3 in the redisRateLimitHandler method were not atomic, leading to poor precision under high concurrent requests. For example, with a rate limit set to 60, sending 200 concurrent requests would result in none being blocked, whereas theoretically around 140 should be intercepted. Solution: I chose not to merge steps 1 and 3 into a single Lua script because a single atomic operation involving read, write, and delete operations could suffer from performance issues under high concurrency. Instead, I implemented a token bucket algorithm to optimize this, reducing the atomic operation to just read and write steps while significantly decreasing the memory footprint.
This commit is contained in:
94
common/limiter/limiter.go
Normal file
94
common/limiter/limiter.go
Normal file
@@ -0,0 +1,94 @@
|
||||
package limiter
|
||||
|
||||
import (
|
||||
"context"
|
||||
_ "embed"
|
||||
"fmt"
|
||||
"github.com/go-redis/redis/v8"
|
||||
"sync"
|
||||
)
|
||||
|
||||
//go:embed lua/rate_limit.lua
|
||||
var rateLimitScript string
|
||||
|
||||
type RedisLimiter struct {
|
||||
client *redis.Client
|
||||
limitScriptSHA string
|
||||
}
|
||||
|
||||
var (
|
||||
instance *RedisLimiter
|
||||
once sync.Once
|
||||
)
|
||||
|
||||
func New(ctx context.Context, r *redis.Client) *RedisLimiter {
|
||||
once.Do(func() {
|
||||
client := r
|
||||
_, err := client.Ping(ctx).Result()
|
||||
if err != nil {
|
||||
panic(err) // 或者处理连接错误
|
||||
}
|
||||
// 预加载脚本
|
||||
limitSHA, err := client.ScriptLoad(ctx, rateLimitScript).Result()
|
||||
if err != nil {
|
||||
fmt.Println(err)
|
||||
}
|
||||
|
||||
instance = &RedisLimiter{
|
||||
client: client,
|
||||
limitScriptSHA: limitSHA,
|
||||
}
|
||||
})
|
||||
|
||||
return instance
|
||||
}
|
||||
|
||||
func (rl *RedisLimiter) Allow(ctx context.Context, key string, opts ...Option) (bool, error) {
|
||||
// 默认配置
|
||||
config := &Config{
|
||||
Capacity: 10,
|
||||
Rate: 1,
|
||||
Requested: 1,
|
||||
}
|
||||
|
||||
// 应用选项模式
|
||||
for _, opt := range opts {
|
||||
opt(config)
|
||||
}
|
||||
|
||||
// 执行限流
|
||||
result, err := rl.client.EvalSha(
|
||||
ctx,
|
||||
rl.limitScriptSHA,
|
||||
[]string{key},
|
||||
config.Requested,
|
||||
config.Rate,
|
||||
config.Capacity,
|
||||
).Int()
|
||||
|
||||
if err != nil {
|
||||
return false, fmt.Errorf("rate limit failed: %w", err)
|
||||
}
|
||||
return result == 1, nil
|
||||
}
|
||||
|
||||
// Config 配置选项模式
|
||||
type Config struct {
|
||||
Capacity int64
|
||||
Rate int64
|
||||
Requested int64
|
||||
}
|
||||
|
||||
type Option func(*Config)
|
||||
|
||||
func WithCapacity(c int64) Option {
|
||||
return func(cfg *Config) { cfg.Capacity = c }
|
||||
}
|
||||
|
||||
func WithRate(r int64) Option {
|
||||
return func(cfg *Config) { cfg.Rate = r }
|
||||
}
|
||||
|
||||
func WithRequested(n int64) Option {
|
||||
return func(cfg *Config) { cfg.Requested = n }
|
||||
}
|
||||
Reference in New Issue
Block a user