Go-深入理解HTTP

package main

import (
	"io"
	"net/http"
)

func HanldeHello(w http.ResponseWriter, r *http.Request) {
	io.WriteString(w, "ok\n")
}

func main() {
	http.HandleFunc("/", HanldeHello, http.MethodPost)
	http.ListenAndServe("0.0.0.0:8080", nil)
}

type ServeMux struct {
	mu    sync.RWMutex
	m     map[string]muxEntry  // 存储Path=>muxEntry
	es    []muxEntry // 按照muxEntry的path从最长到最短排序slice
	hosts bool       // whether any patterns contain hostnames
}

type muxEntry struct {
    // type Handler interface {
	//     ServeHTTP(ResponseWriter, *Request)
    // }
	h       Handler  // handler  
	pattern string   // 路由路径
}

type Server struct {
	Addr    string  // TCP address to listen on, ":http" if empty
	Handler Handler // handler to invoke, http.DefaultServeMux if nil

	// TLSConfig optionally provides a TLS configuration for use
	// by ServeTLS and ListenAndServeTLS. Note that this value is
	// cloned by ServeTLS and ListenAndServeTLS, so it's not
	// possible to modify the configuration with methods like
	// tls.Config.SetSessionTicketKeys. To use
	// SetSessionTicketKeys, use Server.Serve with a TLS Listener
	// instead.
	TLSConfig *tls.Config

	// ReadTimeout is the maximum duration for reading the entire
	// request, including the body.
	//
	// Because ReadTimeout does not let Handlers make per-request
	// decisions on each request body's acceptable deadline or
	// upload rate, most users will prefer to use
	// ReadHeaderTimeout. It is valid to use them both.
	ReadTimeout time.Duration

	// ReadHeaderTimeout is the amount of time allowed to read
	// request headers. The connection's read deadline is reset
	// after reading the headers and the Handler can decide what
	// is considered too slow for the body.
	ReadHeaderTimeout time.Duration

	// WriteTimeout is the maximum duration before timing out
	// writes of the response. It is reset whenever a new
	// request's header is read. Like ReadTimeout, it does not
	// let Handlers make decisions on a per-request basis.
	WriteTimeout time.Duration

	// IdleTimeout is the maximum amount of time to wait for the
	// next request when keep-alives are enabled. If IdleTimeout
	// is zero, the value of ReadTimeout is used. If both are
	// zero, ReadHeaderTimeout is used.
	IdleTimeout time.Duration

	// MaxHeaderBytes controls the maximum number of bytes the
	// server will read parsing the request header's keys and
	// values, including the request line. It does not limit the
	// size of the request body.
	// If zero, DefaultMaxHeaderBytes is used.
	MaxHeaderBytes int

	// TLSNextProto optionally specifies a function to take over
	// ownership of the provided TLS connection when an NPN/ALPN
	// protocol upgrade has occurred. The map key is the protocol
	// name negotiated. The Handler argument should be used to
	// handle HTTP requests and will initialize the Request's TLS
	// and RemoteAddr if not already set. The connection is
	// automatically closed when the function returns.
	// If TLSNextProto is not nil, HTTP/2 support is not enabled
	// automatically.
	TLSNextProto map[string]func(*Server, *tls.Conn, Handler)

	// ConnState specifies an optional callback function that is
	// called when a client connection changes state. See the
	// ConnState type and associated constants for details.
	ConnState func(net.Conn, ConnState)

	// ErrorLog specifies an optional logger for errors accepting
	// connections, unexpected behavior from handlers, and
	// underlying FileSystem errors.
	// If nil, logging is done via the log package's standard logger.
	ErrorLog *log.Logger

	disableKeepAlives int32     // accessed atomically.
	inShutdown        int32     // accessed atomically (non-zero means we're in Shutdown)
	nextProtoOnce     sync.Once // guards setupHTTP2_* init
	nextProtoErr      error     // result of http2.ConfigureServer if used

	mu         sync.Mutex
	listeners  map[*net.Listener]struct{}
	activeConn map[*conn]struct{}   // 活动的连接
	doneChan   chan struct{}
	onShutdown []func()
}

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

    // 检查参数
	if pattern == "" {
		panic("http: invalid pattern")
	}
	if handler == nil {
		panic("http: nil handler")
    }
    
    // 检查是否存在
	if _, exist := mux.m[pattern]; exist {
		panic("http: multiple registrations for " + pattern)
	}

	if mux.m == nil {
		mux.m = make(map[string]muxEntry)
	}
	e := muxEntry{h: handler, pattern: pattern}
    mux.m[pattern] = e
    // 如果pattern的最后一位是/，将其加入mux.es
	if pattern[len(pattern)-1] == '/' {
		mux.es = appendSorted(mux.es, e)
	}

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

func appendSorted(es []muxEntry, e muxEntry) []muxEntry {
    n := len(es)
    // 二分查找
	i := sort.Search(n, func(i int) bool {
		return len(es[i].pattern) < len(e.pattern)
	})
	if i == n {
		return append(es, e)
	}
	// we now know that i points at where we want to insert
	es = append(es, muxEntry{}) // try to grow the slice in place, any entry works.
	copy(es[i+1:], es[i:])      // Move shorter entries down
	es[i] = e
	return es
}

func (srv *Server) ListenAndServe() error {
    // 判断状态
	if srv.shuttingDown() {
		return ErrServerClosed
	}
	addr := srv.Addr
	if addr == "" {
		addr = ":http"
	}
	ln, err := net.Listen("tcp", addr)
	if err != nil {
		return err
    }
    // tcpKeepAliveListener会在Accept连接后，设置KeepAlive，周期是3分钟
	return srv.Serve(tcpKeepAliveListener{ln.(*net.TCPListener)})
}

func (srv *Server) Serve(l net.Listener) error {
	if fn := testHookServerServe; fn != nil {
		fn(srv, l) // call hook with unwrapped listener
	}

	l = &onceCloseListener{Listener: l}
	defer l.Close()

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

	if !srv.trackListener(&l, true) {
		return ErrServerClosed
	}
	defer srv.trackListener(&l, false)

    // accept失败后的休眠时间
	var tempDelay time.Duration     // how long to sleep on accept failure
	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() {
                // 失败后的休眠处理
				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
        }
        // 重置休眠时间
        tempDelay = 0
        // 新建conn
		c := srv.newConn(rw)
        c.setState(c.rwc, StateNew) // before Serve can return
        // 处理请求
		go c.serve(ctx)
	}
}

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

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

	// tlsState is the TLS connection state when using TLS.
	// nil means not TLS.
	tlsState *tls.ConnectionState

	// werr is set to the first write error to rwc.
	// It is set via checkConnErrorWriter{w}, where bufw writes.
	werr error

	// r is bufr's read source. It's a wrapper around rwc that provides
	// io.LimitedReader-style limiting (while reading request headers)
	// and functionality to support CloseNotifier. See *connReader docs.
	r *connReader

	// bufr reads from r.
	bufr *bufio.Reader

	// bufw writes to checkConnErrorWriter{c}, which populates werr on error.
	bufw *bufio.Writer

	// lastMethod is the method of the most recent request
	// on this connection, if any.
	lastMethod string

	curReq atomic.Value // of *response (which has a Request in it)

	curState struct{ atomic uint64 } // packed (unixtime<<8|uint8(ConnState))

	// mu guards hijackedv
	mu sync.Mutex

	// hijackedv is whether this connection has been hijacked
	// by a Handler with the Hijacker interface.
	// It is guarded by mu.
	hijackedv bool
}

func (c *conn) serve(ctx context.Context) {
	// 省略...

	// HTTP/1.x from here on.

	ctx, cancelCtx := context.WithCancel(ctx)
	c.cancelCtx = cancelCtx
	defer cancelCtx()

	c.r = &connReader{conn: c}
	c.bufr = newBufioReader(c.r)
	c.bufw = newBufioWriterSize(checkConnErrorWriter{c}, 4<<10)

	for {
        // 从连接里读取请求
		w, err := c.readRequest(ctx)
		if c.r.remain != c.server.initialReadLimitSize() {
			// If we read any bytes off the wire, we're active.
			c.setState(c.rwc, StateActive)
		}
		if err != nil {
			const errorHeaders = "\r\nContent-Type: text/plain; charset=utf-8\r\nConnection: close\r\n\r\n"

			if err == errTooLarge {
				// Their HTTP client may or may not be
				// able to read this if we're
				// responding to them and hanging up
				// while they're still writing their
				// request. Undefined behavior.
				const publicErr = "431 Request Header Fields Too Large"
				fmt.Fprintf(c.rwc, "HTTP/1.1 "+publicErr+errorHeaders+publicErr)
				c.closeWriteAndWait()
				return
			}
			if isCommonNetReadError(err) {
				return // don't reply
			}

			publicErr := "400 Bad Request"
			if v, ok := err.(badRequestError); ok {
				publicErr = publicErr + ": " + string(v)
			}

			fmt.Fprintf(c.rwc, "HTTP/1.1 "+publicErr+errorHeaders+publicErr)
			return
		}

		// 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
		}

		c.curReq.Store(w)

		if requestBodyRemains(req.Body) {
			registerOnHitEOF(req.Body, w.conn.r.startBackgroundRead)
		} else {
			w.conn.r.startBackgroundRead()
		}

		// HTTP cannot have multiple simultaneous active requests.[*]
		// Until the server replies to this request, it can't read another,
		// so we might as well run the handler in this goroutine.
		// [*] Not strictly true: HTTP pipelining. We could let them all process
		// in parallel even if their responses need to be serialized.
		// But we're not going to implement HTTP pipelining because it
        // was never deployed in the wild and the answer is HTTP/2.
        // 由于HTTP/1.x 一个连接只能处理一个请求，也就是说serverHandler只有在执行完回复，这个连接才能被复用
        // serverHandler是否能用Goroutine来运行，这个也不完全可行，这里并不打算实现HTTP pipelining，所以如果有需求可以选择HTTP/2

        // 调用ServeHTTP去执行Handler
		serverHandler{c.server}.ServeHTTP(w, w.req)
		w.cancelCtx()
		if c.hijacked() {
			return
		}
        w.finishRequest()
        // 判断连接是重用
		if !w.shouldReuseConnection() {
			if w.requestBodyLimitHit || w.closedRequestBodyEarly() {
				c.closeWriteAndWait()
			}
			return
		}
		c.setState(c.rwc, StateIdle)
		c.curReq.Store((*response)(nil))

		if !w.conn.server.doKeepAlives() {
			// We're in shutdown mode. We might've replied
			// to the user without "Connection: close" and
			// they might think they can send another
			// request, but such is life with HTTP/1.1.
			return
		}

		if d := c.server.idleTimeout(); d != 0 {
			c.rwc.SetReadDeadline(time.Now().Add(d))
			if _, err := c.bufr.Peek(4); err != nil {
				return
			}
		}
		c.rwc.SetReadDeadline(time.Time{})
	}
}

func (c *conn) readRequest(ctx context.Context) (w *response, err error) {
	if c.hijacked() {
		return nil, ErrHijacked
	}

	var (
		wholeReqDeadline time.Time // or zero if none
		hdrDeadline      time.Time // or zero if none
    )
    // 设置读取超时时间
	t0 := time.Now()
	if d := c.server.readHeaderTimeout(); d != 0 {
		hdrDeadline = t0.Add(d)
	}
	if d := c.server.ReadTimeout; d != 0 {
		wholeReqDeadline = t0.Add(d)
	}
	c.rwc.SetReadDeadline(hdrDeadline)
	if d := c.server.WriteTimeout; d != 0 {
		defer func() {
			c.rwc.SetWriteDeadline(time.Now().Add(d))
		}()
	}

	c.r.setReadLimit(c.server.initialReadLimitSize())
	if c.lastMethod == "POST" {
		// RFC 7230 section 3 tolerance for old buggy clients.
		peek, _ := c.bufr.Peek(4) // ReadRequest will get err below
		c.bufr.Discard(numLeadingCRorLF(peek))
	}
	req, err := readRequest(c.bufr, keepHostHeader)
	if err != nil {
		if c.r.hitReadLimit() {
			return nil, errTooLarge
		}
		return nil, err
	}

	if !http1ServerSupportsRequest(req) {
		return nil, badRequestError("unsupported protocol version")
	}

	c.lastMethod = req.Method
	c.r.setInfiniteReadLimit()

	hosts, haveHost := req.Header["Host"]
	isH2Upgrade := req.isH2Upgrade()
	if req.ProtoAtLeast(1, 1) && (!haveHost || len(hosts) == 0) && !isH2Upgrade && req.Method != "CONNECT" {
		return nil, badRequestError("missing required Host header")
	}
	if len(hosts) > 1 {
		return nil, badRequestError("too many Host headers")
	}
	if len(hosts) == 1 && !httpguts.ValidHostHeader(hosts[0]) {
		return nil, badRequestError("malformed Host header")
	}
	for k, vv := range req.Header {
		if !httpguts.ValidHeaderFieldName(k) {
			return nil, badRequestError("invalid header name")
		}
		for _, v := range vv {
			if !httpguts.ValidHeaderFieldValue(v) {
				return nil, badRequestError("invalid header value")
			}
		}
	}
	delete(req.Header, "Host")

	ctx, cancelCtx := context.WithCancel(ctx)
	req.ctx = ctx
	req.RemoteAddr = c.remoteAddr
	req.TLS = c.tlsState
	if body, ok := req.Body.(*body); ok {
		body.doEarlyClose = true
	}

	// Adjust the read deadline if necessary.
	if !hdrDeadline.Equal(wholeReqDeadline) {
		c.rwc.SetReadDeadline(wholeReqDeadline)
	}

	w = &response{
		conn:          c,
		cancelCtx:     cancelCtx,
		req:           req,
		reqBody:       req.Body,
		handlerHeader: make(Header),
		contentLength: -1,
		closeNotifyCh: make(chan bool, 1),

		// We populate these ahead of time so we're not
		// reading from req.Header after their Handler starts
		// and maybe mutates it (Issue 14940)
		wants10KeepAlive: req.wantsHttp10KeepAlive(),
		wantsClose:       req.wantsClose(),
	}
	if isH2Upgrade {
		w.closeAfterReply = true
	}
	w.cw.res = w
	w.w = newBufioWriterSize(&w.cw, bufferBeforeChunkingSize)
	return w, nil
}

func readRequest(b *bufio.Reader, deleteHostHeader bool) (req *Request, err error) {
	tp := newTextprotoReader(b)
	req = new(Request)

	// First line: GET /index.html HTTP/1.0
	var s string
	if s, err = tp.ReadLine(); err != nil {
		return nil, err
	}
	defer func() {
		putTextprotoReader(tp)
		if err == io.EOF {
			err = io.ErrUnexpectedEOF
		}
	}()

	var ok bool
	req.Method, req.RequestURI, req.Proto, ok = parseRequestLine(s)
	if !ok {
		return nil, &badStringError{"malformed HTTP request", s}
	}
	if !validMethod(req.Method) {
		return nil, &badStringError{"invalid method", req.Method}
	}
	rawurl := req.RequestURI
	if req.ProtoMajor, req.ProtoMinor, ok = ParseHTTPVersion(req.Proto); !ok {
		return nil, &badStringError{"malformed HTTP version", req.Proto}
	}

	// CONNECT requests are used two different ways, and neither uses a full URL:
	// The standard use is to tunnel HTTPS through an HTTP proxy.
	// It looks like "CONNECT www.google.com:443 HTTP/1.1", and the parameter is
	// just the authority section of a URL. This information should go in req.URL.Host.
	//
	// The net/rpc package also uses CONNECT, but there the parameter is a path
	// that starts with a slash. It can be parsed with the regular URL parser,
	// and the path will end up in req.URL.Path, where it needs to be in order for
	// RPC to work.
	justAuthority := req.Method == "CONNECT" && !strings.HasPrefix(rawurl, "/")
	if justAuthority {
		rawurl = "http://" + rawurl
	}

	if req.URL, err = url.ParseRequestURI(rawurl); err != nil {
		return nil, err
	}

	if justAuthority {
		// Strip the bogus "http://" back off.
		req.URL.Scheme = ""
	}

	// Subsequent lines: Key: value.
	mimeHeader, err := tp.ReadMIMEHeader()
	if err != nil {
		return nil, err
	}
	req.Header = Header(mimeHeader)

	// RFC 7230, section 5.3: Must treat
	//	GET /index.html HTTP/1.1
	//	Host: www.google.com
	// and
	//	GET http://www.google.com/index.html HTTP/1.1
	//	Host: doesntmatter
	// the same. In the second case, any Host line is ignored.
	req.Host = req.URL.Host
	if req.Host == "" {
		req.Host = req.Header.get("Host")
	}
	if deleteHostHeader {
		delete(req.Header, "Host")
	}

	fixPragmaCacheControl(req.Header)

    // 根据Header和HTTP协议判断是否需要关闭
	req.Close = shouldClose(req.ProtoMajor, req.ProtoMinor, req.Header, false)

    // 读取header、body等其他信息
	err = readTransfer(req, b)
	if err != nil {
		return nil, err
	}

	if req.isH2Upgrade() {
		// Because it's neither chunked, nor declared:
		req.ContentLength = -1

		// We want to give handlers a chance to hijack the
		// connection, but we need to prevent the Server from
		// dealing with the connection further if it's not
		// hijacked. Set Close to ensure that:
		req.Close = true
	}
	return req, nil
}

msg 是*Request或者*Response.
func readTransfer(msg interface{}, r *bufio.Reader) (err error) {
	t := &transferReader{RequestMethod: "GET"}

	// Unify input
	isResponse := false
	switch rr := msg.(type) {
	case *Response:
		t.Header = rr.Header
		t.StatusCode = rr.StatusCode
		t.ProtoMajor = rr.ProtoMajor
		t.ProtoMinor = rr.ProtoMinor
		t.Close = shouldClose(t.ProtoMajor, t.ProtoMinor, t.Header, true)
		isResponse = true
		if rr.Request != nil {
			t.RequestMethod = rr.Request.Method
		}
	case *Request:
		t.Header = rr.Header
		t.RequestMethod = rr.Method
		t.ProtoMajor = rr.ProtoMajor
		t.ProtoMinor = rr.ProtoMinor
		// Transfer semantics for Requests are exactly like those for
		// Responses with status code 200, responding to a GET method
		t.StatusCode = 200
		t.Close = rr.Close
	default:
		panic("unexpected type")
	}

	// Default to HTTP/1.1
	if t.ProtoMajor == 0 && t.ProtoMinor == 0 {
		t.ProtoMajor, t.ProtoMinor = 1, 1
	}

	// Transfer encoding, content length
	err = t.fixTransferEncoding()
	if err != nil {
		return err
	}

	realLength, err := fixLength(isResponse, t.StatusCode, t.RequestMethod, t.Header, t.TransferEncoding)
	if err != nil {
		return err
	}
	if isResponse && t.RequestMethod == "HEAD" {
		if n, err := parseContentLength(t.Header.get("Content-Length")); err != nil {
			return err
		} else {
			t.ContentLength = n
		}
	} else {
		t.ContentLength = realLength
	}

	// Trailer
	t.Trailer, err = fixTrailer(t.Header, t.TransferEncoding)
	if err != nil {
		return err
	}

	// If there is no Content-Length or chunked Transfer-Encoding on a *Response
	// and the status is not 1xx, 204 or 304, then the body is unbounded.
	// See RFC 7230, section 3.3.
	switch msg.(type) {
	case *Response:
		if realLength == -1 &&
			!chunked(t.TransferEncoding) &&
			bodyAllowedForStatus(t.StatusCode) {
			// Unbounded body.
			t.Close = true
		}
	}

	// Prepare body reader. ContentLength < 0 means chunked encoding
	// or close connection when finished, since multipart is not supported yet
	switch {
	case chunked(t.TransferEncoding):
		if noResponseBodyExpected(t.RequestMethod) || !bodyAllowedForStatus(t.StatusCode) {
			t.Body = NoBody
		} else {
			t.Body = &body{src: internal.NewChunkedReader(r), hdr: msg, r: r, closing: t.Close}
		}
	case realLength == 0:
		t.Body = NoBody
	case realLength > 0:
		t.Body = &body{src: io.LimitReader(r, realLength), closing: t.Close}
	default:
		// realLength < 0, i.e. "Content-Length" not mentioned in header
		if t.Close {
			// Close semantics (i.e. HTTP/1.0)
			t.Body = &body{src: r, closing: t.Close}
		} else {
			// Persistent connection (i.e. HTTP/1.1)
			t.Body = NoBody
		}
	}

	// Unify output
	switch rr := msg.(type) {
	case *Request:
		rr.Body = t.Body
		rr.ContentLength = t.ContentLength
		rr.TransferEncoding = t.TransferEncoding
		rr.Close = t.Close
		rr.Trailer = t.Trailer
	case *Response:
		rr.Body = t.Body
		rr.ContentLength = t.ContentLength
		rr.TransferEncoding = t.TransferEncoding
		rr.Close = t.Close
		rr.Trailer = t.Trailer
	}

	return nil
}

type body struct {
	src          io.Reader
	hdr          interface{}   // non-nil (Response or Request) value means read trailer
	r            *bufio.Reader // underlying wire-format reader for the trailer
	closing      bool          // is the connection to be closed after reading body?
	doEarlyClose bool          // whether Close should stop early

	mu         sync.Mutex // guards following, and calls to Read and Close
	sawEOF     bool
	closed     bool
	earlyClose bool   // Close called and we didn't read to the end of src
	onHitEOF   func() // if non-nil, func to call when EOF is Read
}