Go语言中HTTP包剖析（服务器端）

Go自带一个HTTP包，可以满足Web开发中的一部分需求。但没有ORM、SESSION处理、缓存等。通过源码也发现该包的路由也很简单。但可以自定义路由。

问题：

1. 如何根据请求路径找到对于的handler
2. 路由如何处理
3. 服务器从接收请求到处理请求的整个过程

一个简单的例子：

package main

import (
    "io"
    "net/http"
    "log"
)

func handler(w http.ResponseWriter, req *http.Request) {
    io.WriteString(w, "hello, world!\n")
}

func main() {
    http.HandleFunc("/", handler)
    log.Fatal(http.ListenAndServe(":8080", nil))
}

从net/http分析源码，ListenAndServe创建一个Server实例，调用其ListenAndServe方法。

func ListenAndServe(addr string, handler Handler) error {
    server := &Server{Addr: addr, Handler: handler}
    return server.ListenAndServe()
}

Handler是一个接口：

type Handler interface {
    ServeHTTP(ResponseWriter, *Request)
}

Server.ListenAndServe代码如下：

func (srv *Server) ListenAndServe() error {
    addr := srv.Addr
    if addr == "" {
        addr = ":http"
    }
    ln, err := net.Listen("tcp", addr)
    if err != nil {
        return err
    }
    return srv.Serve(tcpKeepAliveListener{ln.(*net.TCPListener)})
}

它监听TCP请求，使用Server.Serve接口处理TCP连接。tcpKeepAliveListener是一个结构体，用于保持TCP长连接。

type tcpKeepAliveListener struct {
    *net.TCPListener
}

func (ln tcpKeepAliveListener) Accept() (net.Conn, error) {
    tc, err := ln.AcceptTCP()
    if err != nil {
        return nil, err
    }
    tc.SetKeepAlive(true)
    tc.SetKeepAlivePeriod(3 * time.Minute)
    return tc, nil
}

从Accept方法可以看到，长连接时间为三分钟。

再看看Server.Serve的实现

func (srv *Server) Serve(l net.Listener) error {
    defer l.Close()
    if fn := testHookServerServe; fn != nil {
        fn(srv, l)
    }
    var tempDelay time.Duration // how long to sleep on accept failure

    if err := srv.setupHTTP2_Serve(); err != nil {
        return err
    }

    srv.trackListener(l, true)
    defer srv.trackListener(l, false)

    baseCtx := context.Background() // base is always background, per Issue 16220
    ctx := context.WithValue(baseCtx, ServerContextKey, srv)
    for {
        rw, e := l.Accept()
        if e != nil {
            select {
            case <-srv.getDoneChan():
                return ErrServerClosed
            default:
            }
            if ne, ok := e.(net.Error); ok && ne.Temporary() {
                if tempDelay == 0 {
                    tempDelay = 5 * time.Millisecond
                } else {
                    tempDelay *= 2
                }
                if max := 1 * time.Second; tempDelay > max {
                    tempDelay = max
                }
                srv.logf("http: Accept error: %v; retrying in %v", e, tempDelay)
                time.Sleep(tempDelay)
                continue
            }
            return e
        }
        tempDelay = 0
        c := srv.newConn(rw)
        c.setState(c.rwc, StateNew) // before Serve can return
        go c.serve(ctx)
    }
}

newConn代码如下，rwc是底层网络连接对象。

func (srv *Server) newConn(rwc net.Conn) *conn {
    c := &conn{
        server: srv,
        rwc:    rwc,
    }
    if debugServerConnections {
        c.rwc = newLoggingConn("server", c.rwc)
    }
    return c
}

忽略控制流程的细节代码，for循环部分在等待连接的到来，c := srv.newConn(rw)代码把TCP连接转化成用conn结构包装的对象。该结构代表服务器端的HTTP连接。因此，这里可以理解为把TCP连接包装成HTTP连接。该结构如下（列举部分元素）：

type conn struct {
    // server is the server on which the connection arrived.
    // Immutable; never nil.
    server *Server

    // cancelCtx cancels the connection-level context.
    cancelCtx context.CancelFunc

    // rwc is the underlying network connection.
    // This is never wrapped by other types and is the value given out
    // to CloseNotifier callers. It is usually of type *net.TCPConn or
    // *tls.Conn.
    rwc net.Conn

    // remoteAddr is rwc.RemoteAddr().String(). It is not populated synchronously
    // inside the Listener's Accept goroutine, as some implementations block.
    // It is populated immediately inside the (*conn).serve goroutine.
    // This is the value of a Handler's (*Request).RemoteAddr.
    remoteAddr string
}

conn.serve方法用于处理一个HTTP连接。这个方法有上百行代码，这里不全列出来。具体的方法签名如下：func (c *conn) serve(ctx context.Context)。

func (c *conn) serve(ctx context.Context) {
    c.remoteAddr = c.rwc.RemoteAddr().String()

    // ignore code here

    for {
        w, err := c.readRequest(ctx)

        // Expect 100 Continue support
        req := w.req
        if req.expectsContinue() {
            if req.ProtoAtLeast(1, 1) && req.ContentLength != 0 {
                // Wrap the Body reader with one that replies on the connection
                req.Body = &expectContinueReader{readCloser: req.Body, resp: w}
            }
        } else if req.Header.get("Expect") != "" {
            w.sendExpectationFailed()
            return
        }

        serverHandler{c.server}.ServeHTTP(w, w.req)
        w.cancelCtx()
        if c.hijacked() {
            return
        }
        w.finishRequest()
    }
}

for循环下c.readRequest获取具体的请求对象，然后根据HTTP语义处理。具体的路由和serverHandler结构有关。看看该结构的定义和其ServeHTTP代码：

type serverHandler struct {
    srv *Server
}

func (sh serverHandler) ServeHTTP(rw ResponseWriter, req *Request) {
    handler := sh.srv.Handler
    if handler == nil {
        handler = DefaultServeMux
    }
    if req.RequestURI == "*" && req.Method == "OPTIONS" {
        handler = globalOptionsHandler{}
    }
    handler.ServeHTTP(rw, req)
}

默认使用DefaultServeMux处理路由，它是ServeMux结构的实例。

type ServeMux struct {
    mu    sync.RWMutex
    m     map[string]muxEntry
    hosts bool // whether any patterns contain hostnames
}

type muxEntry struct {
    h       Handler
    pattern string
}

由此可见，Golang标准库net/http对路由的处理也很简单。

func (mux *ServeMux) ServeHTTP(w ResponseWriter, r *Request) {
    if r.RequestURI == "*" {
        if r.ProtoAtLeast(1, 1) {
            w.Header().Set("Connection", "close")
        }
        w.WriteHeader(StatusBadRequest)
        return
    }
    h, _ := mux.Handler(r)
    h.ServeHTTP(w, r)
}

ServeMux中的ServeHTTP方法根据Handler方法找到处理该路由的函数，然后调用该Handler的ServeHTTP，即h.ServeHTTP(w, r)处理该请求。下面我们看看具体的路由查找过程。

func (mux *ServeMux) Handler(r *Request) (h Handler, pattern string) {

    // CONNECT requests are not canonicalized.
    if r.Method == "CONNECT" {
        // If r.URL.Path is /tree and its handler is not registered,
        // the /tree -> /tree/ redirect applies to CONNECT requests
        // but the path canonicalization does not.
        if u, ok := mux.redirectToPathSlash(r.URL.Path, r.URL); ok {
            return RedirectHandler(u.String(), StatusMovedPermanently), u.Path
        }

        return mux.handler(r.Host, r.URL.Path)
    }

    // All other requests have any port stripped and path cleaned
    // before passing to mux.handler.
    host := stripHostPort(r.Host)
    path := cleanPath(r.URL.Path)

    // If the given path is /tree and its handler is not registered,
    // redirect for /tree/.
    if u, ok := mux.redirectToPathSlash(path, r.URL); ok {
        return RedirectHandler(u.String(), StatusMovedPermanently), u.Path
    }

    if path != r.URL.Path {
        _, pattern = mux.handler(host, path)
        url := *r.URL
        url.Path = path
        return RedirectHandler(url.String(), StatusMovedPermanently), pattern
    }

    return mux.handler(host, r.URL.Path)
}

func (mux *ServeMux) handler(host, path string) (h Handler, pattern string) {
    mux.mu.RLock()
    defer mux.mu.RUnlock()

    // Host-specific pattern takes precedence over generic ones
    if mux.hosts {
        h, pattern = mux.match(host + path)
    }
    if h == nil {
        h, pattern = mux.match(path)
    }
    if h == nil {
        h, pattern = NotFoundHandler(), ""
    }
    return
}

函数最终根据host和path变量找到对应的路由。而match方法就简单粗暴直接使用map查找。

func (mux *ServeMux) match(path string) (h Handler, pattern string) {
    // Check for exact match first.
    v, ok := mux.m[path]
    if ok {
        return v.h, v.pattern
    }

    // Check for longest valid match.
    var n = 0
    for k, v := range mux.m {
        if !pathMatch(k, path) {
            continue
        }
        if h == nil || len(k) > n {
            n = len(k)
            h = v.h
            pattern = v.pattern
        }
    }
    return
}

根据路由找到具体的处理函数后，调用ServeHTTP处理。

type HandlerFunc func(ResponseWriter, *Request)

// ServeHTTP calls f(w, r).
func (f HandlerFunc) ServeHTTP(w ResponseWriter, r *Request) {
    f(w, r)
}

而，注册路由的代码如下，本质上是把路径和对应的处理函数添加到map数据结构上。

func (mux *ServeMux) Handle(pattern string, handler Handler) {
    mux.mu.Lock()
    defer mux.mu.Unlock()

    if pattern == "" {
        panic("http: invalid pattern")
    }
    if handler == nil {
        panic("http: nil handler")
    }
    if _, exist := mux.m[pattern]; exist {
        panic("http: multiple registrations for " + pattern)
    }

    if mux.m == nil {
        mux.m = make(map[string]muxEntry)
    }
    mux.m[pattern] = muxEntry{h: handler, pattern: pattern}

    if pattern[0] != '/' {
        mux.hosts = true
    }
}

// HandleFunc registers the handler function for the given pattern.
func (mux *ServeMux) HandleFunc(pattern string, handler func(ResponseWriter, *Request)) {
    mux.Handle(pattern, HandlerFunc(handler))
}

// Handle registers the handler for the given pattern
// in the DefaultServeMux.
// The documentation for ServeMux explains how patterns are matched.
func Handle(pattern string, handler Handler) { DefaultServeMux.Handle(pattern, handler) }

// HandleFunc registers the handler function for the given pattern
// in the DefaultServeMux.
// The documentation for ServeMux explains how patterns are matched.
func HandleFunc(pattern string, handler func(ResponseWriter, *Request)) {
    DefaultServeMux.HandleFunc(pattern, handler)
}

完。