Go如何实现HTTP请求限流示例

在开发高并发系统时有三把利器用来保护系统：缓存、降级和限流!为了保证在业务高峰期，线上系统也能保证一定的弹性和稳定性，最有效的方案就是进行服务降级了，而限流就是降级系统最常采用的方案之一。

这里为大家推荐一个开源库 但是，如果您想要一些简单的、轻量级的或者只是想要学习的东西，实现自己的中间件来处理速率限制并不困难。今天我们就来聊聊如何实现自己的一个限流中间件

首先我们需要安装一个提供了 token bucket (令牌桶算法)的依赖包，上面提到的toolbooth 的实现也是基于它实现的

$ go get golang.org/x/time/rate

好了我们先看demo代码的实现：

limit.go

package main

import (
  "net/http"

  "golang.org/x/time/rate"
)

var limiter = rate.newlimiter(2, 5)

func limit(next http.handler) http.handler {
  return http.handlerfunc(func(w http.responsewriter, r *http.request) {
    if limiter.allow() == false {
      http.error(w, http.statustext(429), http.statustoomanyrequests)
      return
    }

    next.servehttp(w, r)
  })
}

main.go

package main

import (
  "net/http"
)

func main() {
  mux := http.newservemux()
  mux.handlefunc("/", okhandler)

  // wrap the servemux with the limit middleware.
  http.listenandserve(":4000", limit(mux))
}

func okhandler(w http.responsewriter, r *http.request) {
  w.write([]byte("ok"))
}

我们看看 rate.newlimiter的源码：

// copyright 2015 the go authors. all rights reserved.
// use of this source code is governed by a bsd-style
// license that can be found in the license file.

// package rate provides a rate limiter.
package rate

import (
 "fmt"
 "math"
 "sync"
 "time"

 "golang.org/x/net/context"
)

// limit defines the maximum frequency of some events.
// limit is represented as number of events per second.
// a zero limit allows no events.
type limit float64

// inf is the infinite rate limit; it allows all events (even if burst is zero).
const inf = limit(math.maxfloat64)

// every converts a minimum time interval between events to a limit.
func every(interval time.duration) limit {
 if interval <= 0 {
  return inf
 }
 return 1 / limit(interval.seconds())
}

// a limiter controls how frequently events are allowed to happen.
// it implements a "token bucket" of size b, initially full and refilled
// at rate r tokens per second.
// informally, in any large enough time interval, the limiter limits the
// rate to r tokens per second, with a maximum burst size of b events.
// as a special case, if r == inf (the infinite rate), b is ignored.
// see https://en.wikipedia.org/wiki/token_bucket for more about token buckets.
//
// the zero value is a valid limiter, but it will reject all events.
// use newlimiter to create non-zero limiters.
//
// limiter has three main methods, allow, reserve, and wait.
// most callers should use wait.
//
// each of the three methods consumes a single token.
// they differ in their behavior when no token is available.
// if no token is available, allow returns false.
// if no token is available, reserve returns a reservation for a future token
// and the amount of time the caller must wait before using it.
// if no token is available, wait blocks until one can be obtained
// or its associated context.context is canceled.
//
// the methods allown, reserven, and waitn consume n tokens.
type limiter struct {
 limit limit
 burst int

 mu   sync.mutex
 tokens float64
 // last is the last time the limiter's tokens field was updated
 last time.time
 // lastevent is the latest time of a rate-limited event (past or future)
 lastevent time.time
}

// limit returns the maximum overall event rate.
func (lim *limiter) limit() limit {
 lim.mu.lock()
 defer lim.mu.unlock()
 return lim.limit
}

// burst returns the maximum burst size. burst is the maximum number of tokens
// that can be consumed in a single call to allow, reserve, or wait, so higher
// burst values allow more events to happen at once.
// a zero burst allows no events, unless limit == inf.
func (lim *limiter) burst() int {
 return lim.burst
}

// newlimiter returns a new limiter that allows events up to rate r and permits
// bursts of at most b tokens.
func newlimiter(r limit, b int) *limiter {
 return &limiter{
  limit: r,
  burst: b,
 }
}

// allow is shorthand for allown(time.now(), 1).
func (lim *limiter) allow() bool {
 return lim.allown(time.now(), 1)
}

// allown reports whether n events may happen at time now.
// use this method if you intend to drop / skip events that exceed the rate limit.
// otherwise use reserve or wait.
func (lim *limiter) allown(now time.time, n int) bool {
 return lim.reserven(now, n, 0).ok
}

// a reservation holds information about events that are permitted by a limiter to happen after a delay.
// a reservation may be canceled, which may enable the limiter to permit additional events.
type reservation struct {
 ok    bool
 lim    *limiter
 tokens  int
 timetoact time.time
 // this is the limit at reservation time, it can change later.
 limit limit
}

// ok returns whether the limiter can provide the requested number of tokens
// within the maximum wait time. if ok is false, delay returns infduration, and
// cancel does nothing.
func (r *reservation) ok() bool {
 return r.ok
}

// delay is shorthand for delayfrom(time.now()).
func (r *reservation) delay() time.duration {
 return r.delayfrom(time.now())
}

// infduration is the duration returned by delay when a reservation is not ok.
const infduration = time.duration(1<<63 - 1)

// delayfrom returns the duration for which the reservation holder must wait
// before taking the reserved action. zero duration means act immediately.
// infduration means the limiter cannot grant the tokens requested in this
// reservation within the maximum wait time.
func (r *reservation) delayfrom(now time.time) time.duration {
 if !r.ok {
  return infduration
 }
 delay := r.timetoact.sub(now)
 if delay < 0 {
  return 0
 }
 return delay
}

// cancel is shorthand for cancelat(time.now()).
func (r *reservation) cancel() {
 r.cancelat(time.now())
 return
}

// cancelat indicates that the reservation holder will not perform the reserved action
// and reverses the effects of this reservation on the rate limit as much as possible,
// considering that other reservations may have already been made.
func (r *reservation) cancelat(now time.time) {
 if !r.ok {
  return
 }

 r.lim.mu.lock()
 defer r.lim.mu.unlock()

 if r.lim.limit == inf || r.tokens == 0 || r.timetoact.before(now) {
  return
 }

 // calculate tokens to restore
 // the duration between lim.lastevent and r.timetoact tells us how many tokens were reserved
 // after r was obtained. these tokens should not be restored.
 restoretokens := float64(r.tokens) - r.limit.tokensfromduration(r.lim.lastevent.sub(r.timetoact))
 if restoretokens <= 0 {
  return
 }
 // advance time to now
 now, _, tokens := r.lim.advance(now)
 // calculate new number of tokens
 tokens += restoretokens
 if burst := float64(r.lim.burst); tokens > burst {
  tokens = burst
 }
 // update state
 r.lim.last = now
 r.lim.tokens = tokens
 if r.timetoact == r.lim.lastevent {
  prevevent := r.timetoact.add(r.limit.durationfromtokens(float64(-r.tokens)))
  if !prevevent.before(now) {
   r.lim.lastevent = prevevent
  }
 }

 return
}

// reserve is shorthand for reserven(time.now(), 1).
func (lim *limiter) reserve() *reservation {
 return lim.reserven(time.now(), 1)
}

// reserven returns a reservation that indicates how long the caller must wait before n events happen.
// the limiter takes this reservation into account when allowing future events.
// reserven returns false if n exceeds the limiter's burst size.
// usage example:
//  r, ok := lim.reserven(time.now(), 1)
//  if !ok {
//   // not allowed to act! did you remember to set lim.burst to be > 0 ?
//  }
//  time.sleep(r.delay())
//  act()
// use this method if you wish to wait and slow down in accordance with the rate limit without dropping events.
// if you need to respect a deadline or cancel the delay, use wait instead.
// to drop or skip events exceeding rate limit, use allow instead.
func (lim *limiter) reserven(now time.time, n int) *reservation {
 r := lim.reserven(now, n, infduration)
 return &r
}

// wait is shorthand for waitn(ctx, 1).
func (lim *limiter) wait(ctx context.context) (err error) {
 return lim.waitn(ctx, 1)
}

// waitn blocks until lim permits n events to happen.
// it returns an error if n exceeds the limiter's burst size, the context is
// canceled, or the expected wait time exceeds the context's deadline.
func (lim *limiter) waitn(ctx context.context, n int) (err error) {
 if n > lim.burst {
  return fmt.errorf("rate: wait(n=%d) exceeds limiter's burst %d", n, lim.burst)
 }
 // check if ctx is already cancelled
 select {
 case <-ctx.done():
  return ctx.err()
 default:
 }
 // determine wait limit
 now := time.now()
 waitlimit := infduration
 if deadline, ok := ctx.deadline(); ok {
  waitlimit = deadline.sub(now)
 }
 // reserve
 r := lim.reserven(now, n, waitlimit)
 if !r.ok {
  return fmt.errorf("rate: wait(n=%d) would exceed context deadline", n)
 }
 // wait
 t := time.newtimer(r.delayfrom(now))
 defer t.stop()
 select {
 case <-t.c:
  // we can proceed.
  return nil
 case <-ctx.done():
  // context was canceled before we could proceed. cancel the
  // reservation, which may permit other events to proceed sooner.
  r.cancel()
  return ctx.err()
 }
}

// setlimit is shorthand for setlimitat(time.now(), newlimit).
func (lim *limiter) setlimit(newlimit limit) {
 lim.setlimitat(time.now(), newlimit)
}

// setlimitat sets a new limit for the limiter. the new limit, and burst, may be violated
// or underutilized by those which reserved (using reserve or wait) but did not yet act
// before setlimitat was called.
func (lim *limiter) setlimitat(now time.time, newlimit limit) {
 lim.mu.lock()
 defer lim.mu.unlock()

 now, _, tokens := lim.advance(now)

 lim.last = now
 lim.tokens = tokens
 lim.limit = newlimit
}

// reserven is a helper method for allown, reserven, and waitn.
// maxfuturereserve specifies the maximum reservation wait duration allowed.
// reserven returns reservation, not *reservation, to avoid allocation in allown and waitn.
func (lim *limiter) reserven(now time.time, n int, maxfuturereserve time.duration) reservation {
 lim.mu.lock()
 defer lim.mu.unlock()

 if lim.limit == inf {
  return reservation{
   ok:    true,
   lim:    lim,
   tokens:  n,
   timetoact: now,
  }
 }

 now, last, tokens := lim.advance(now)

 // calculate the remaining number of tokens resulting from the request.
 tokens -= float64(n)

 // calculate the wait duration
 var waitduration time.duration
 if tokens < 0 {
  waitduration = lim.limit.durationfromtokens(-tokens)
 }

 // decide result
 ok := n <= lim.burst && waitduration <= maxfuturereserve

 // prepare reservation
 r := reservation{
  ok:  ok,
  lim:  lim,
  limit: lim.limit,
 }
 if ok {
  r.tokens = n
  r.timetoact = now.add(waitduration)
 }

 // update state
 if ok {
  lim.last = now
  lim.tokens = tokens
  lim.lastevent = r.timetoact
 } else {
  lim.last = last
 }

 return r
}

// advance calculates and returns an updated state for lim resulting from the passage of time.
// lim is not changed.
func (lim *limiter) advance(now time.time) (newnow time.time, newlast time.time, newtokens float64) {
 last := lim.last
 if now.before(last) {
  last = now
 }

 // avoid making delta overflow below when last is very old.
 maxelapsed := lim.limit.durationfromtokens(float64(lim.burst) - lim.tokens)
 elapsed := now.sub(last)
 if elapsed > maxelapsed {
  elapsed = maxelapsed
 }

 // calculate the new number of tokens, due to time that passed.
 delta := lim.limit.tokensfromduration(elapsed)
 tokens := lim.tokens + delta
 if burst := float64(lim.burst); tokens > burst {
  tokens = burst
 }

 return now, last, tokens
}

// durationfromtokens is a unit conversion function from the number of tokens to the duration
// of time it takes to accumulate them at a rate of limit tokens per second.
func (limit limit) durationfromtokens(tokens float64) time.duration {
 seconds := tokens / float64(limit)
 return time.nanosecond * time.duration(1e9*seconds)
}

// tokensfromduration is a unit conversion function from a time duration to the number of tokens
// which could be accumulated during that duration at a rate of limit tokens per second.
func (limit limit) tokensfromduration(d time.duration) float64 {
 return d.seconds() * float64(limit)
}

算法描述：

用户配置的平均发送速率为r，则每隔1/r秒一个令牌被加入到桶中（每秒会有r个令牌放入桶中），桶中最多可以存放b个令牌。如果令牌到达时令牌桶已经满了，那么这个令牌会被丢弃；

实现用户粒度的限流

虽然在某些情况下使用单个全局速率限制器非常有用，但另一种常见情况是基于ip地址或api密钥等标识符为每个用户实施速率限制器。我们将使用ip地址作为标识符。简单实现代码如下：

package main
import (
  "net/http"
  "sync"
  "time"

  "golang.org/x/time/rate"
)

// create a custom visitor struct which holds the rate limiter for each
// visitor and the last time that the visitor was seen.
type visitor struct {
  limiter *rate.limiter
  lastseen time.time
}

// change the the map to hold values of the type visitor.
var visitors = make(map[string]*visitor)
var mtx sync.mutex
// run a background goroutine to remove old entries from the visitors map.
func init() {
  go cleanupvisitors()
}

func addvisitor(ip string) *rate.limiter {
  limiter := rate.newlimiter(2, 5)
  mtx.lock()
  // include the current time when creating a new visitor.
  visitors[ip] = &visitor{limiter, time.now()}
  mtx.unlock()
  return limiter
}

func getvisitor(ip string) *rate.limiter {
  mtx.lock()
  v, exists := visitors[ip]
  if !exists {
    mtx.unlock()
    return addvisitor(ip)
  }
  // update the last seen time for the visitor.
  v.lastseen = time.now()
  mtx.unlock()
  return v.limiter
}

// every minute check the map for visitors that haven't been seen for
// more than 3 minutes and delete the entries.
func cleanupvisitors() {
  for {
    time.sleep(time.minute)
    mtx.lock()
    for ip, v := range visitors {
      if time.now().sub(v.lastseen) > 3*time.minute {
        delete(visitors, ip)
      }
    }
    mtx.unlock()
  }
}

func limit(next http.handler) http.handler {
  return http.handlerfunc(func(w http.responsewriter, r *http.request) {
    limiter := getvisitor(r.remoteaddr)
    if limiter.allow() == false {
      http.error(w, http.statustext(429), http.statustoomanyrequests)
      return
    }
    next.servehttp(w, r)
  })
}

当然这只是一个简单的实现方案，如果我们要在微服务的api-gateway中去实现限流还是要考虑很多东西的。建议大家可以看看 的源码。

以上就是本文的全部内容，希望对大家的学习有所帮助，也希望大家多多支持。