最近部署的web程序，在服务器上出现不少
time_wait的连接状态，会占用tcp端口，费了几天时间排查。
之前我有结论：HTTP keep-alive 是在应用层对TCP连接的滑动续约复用，如果客户端、服务器稳定续约，就成了名副其实的长连接。
目前所有的HTTP网络库(不论是客户端、服务端)都默认开启了HTTP Keep-Alive，通过Request/Response的Connection标头来协商复用连接。
非常规做法导致的短连接
我手上有个项目，由于历史原因，客户端禁用了Keep-Alive，服务端默认开启了Keep-Alive，如此一来协商复用连接失败， 客户端每次请求会使用新的TCP连接， 也就是回退为短连接。
客户端强制禁用Keep-Alive
package main
import (
"fmt"
"io/ioutil"
"log"
"net/http"
"time"
)
func main() {
tr := http.Transport{
DisableKeepAlives: true,
}
client := &http.Client{
Timeout: 10 * time.Second,
Transport: &tr,
}
for {
requestWithClose(client)
time.Sleep(time.Second * 1)
}
}
func requestWithClose(client *http.Client) {
resp, err := client.Get("http://10.100.219.9:8081")
if err != nil {
fmt.Printf("error occurred while fetching page, error: %s", err.Error())
return
}
defer resp.Body.Close()
c, err := ioutil.ReadAll(resp.Body)
if err != nil {
log.Fatalf("Couldn't parse response body. %+v", err)
}
fmt.Println(string(c))
}web服务端默认开启Keep-Alive
package main
import (
"fmt"
"log"
"net/http"
)
// 根据RemoteAddr 知道客户端使用的持久连接
func IndexHandler(w http.ResponseWriter, r *http.Request) {
fmt.Println("receive a request from:", r.RemoteAddr, r.Header)
w.Write([]byte("ok"))
}
func main() {
fmt.Printf("Starting server at port 8081\n")
// net/http 默认开启持久连接
if err := http.ListenAndServe(":8081", http.HandlerFunc(IndexHandler)); err != nil {
log.Fatal(err)
}
}
从服务端的日志看，确实是短连接。
receive a request from: 10.22.38.48:54722 map[Accept-Encoding:[gzip] Connection:[close] User-Agent:[Go-http-client/1.1]]
receive a request from: 10.22.38.48:54724 map[Accept-Encoding:[gzip] Connection:[close] User-Agent:[Go-http-client/1.1]]
receive a request from: 10.22.38.48:54726 map[Accept-Encoding:[gzip] Connection:[close] User-Agent:[Go-http-client/1.1]]
receive a request from: 10.22.38.48:54728 map[Accept-Encoding:[gzip] Connection:[close] User-Agent:[Go-http-client/1.1]]
receive a request from: 10.22.38.48:54731 map[Accept-Encoding:[gzip] Connection:[close] User-Agent:[Go-http-client/1.1]]
receive a request from: 10.22.38.48:54733 map[Accept-Encoding:[gzip] Connection:[close] User-Agent:[Go-http-client/1.1]]
receive a request from: 10.22.38.48:54734 map[Accept-Encoding:[gzip] Connection:[close] User-Agent:[Go-http-client/1.1]]
receive a request from: 10.22.38.48:54738 map[Accept-Encoding:[gzip] Connection:[close] User-Agent:[Go-http-client/1.1]]
receive a request from: 10.22.38.48:54740 map[Accept-Encoding:[gzip] Connection:[close] User-Agent:[Go-http-client/1.1]]
receive a request from: 10.22.38.48:54741 map[Accept-Encoding:[gzip] Connection:[close] User-Agent:[Go-http-client/1.1]]
receive a request from: 10.22.38.48:54743 map[Accept-Encoding:[gzip] Connection:[close] User-Agent:[Go-http-client/1.1]]
receive a request from: 10.22.38.48:54744 map[Accept-Encoding:[gzip] Connection:[close] User-Agent:[Go-http-client/1.1]]
receive a request from: 10.22.38.48:54746 map[Accept-Encoding:[gzip] Connection:[close] User-Agent:[Go-http-client/1.1]]谁是主动断开方？
我想当然的以为 客户端是主动断开方，被现实啪啪打脸。
某一天服务器上超过300的time_wait报警告诉我这tmd是服务器主动终断连接。
常规的TCP4次挥手， 主动断开方会进入time_wait状态，等待2MSL后释放占用的SOCKET
以下是从服务器上tcpdump抓取的tcp连接信息。
红框2,3部分明确提示是从 Server端发起TCP的FIN消息, 之后Client回应ACK确认收到Server的关闭通知； 之后Client再发FIN消息，告知现在可以关闭了， Server端最终发ACK确认收到，并进入Time_WAIT状态，等待2MSL的时间关闭Socket。
特意指出，红框1表示TCP双端同时关闭，此时会在Client,Server同时留下
time_wait痕迹，发生概率较小。
没有源码说个串串
此种情况是服务端主动关闭，我们往回翻一翻golang httpServer的源码
- http.ListenAndServe(":8081")
- server.ListenAndServe()
- srv.Serve(ln)
- go c.serve(connCtx) 使用go协程来处理每个请求
服务器连接处理请求的简略源码如下：
func (c *conn) serve(ctx context.Context) {
c.remoteAddr = c.rwc.RemoteAddr().String()
ctx = context.WithValue(ctx, LocalAddrContextKey, c.rwc.LocalAddr())
defer func() {
if !c.hijacked() {
c.close()
c.setState(c.rwc, StateClosed, runHooks)
}
}()
......
// 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 {
w, err := c.readRequest(ctx)
switch {
case err == errTooLarge:
const publicErr = "431 Request Header Fields Too Large"
fmt.Fprintf(c.rwc, "HTTP/1.1 "+publicErr+errorHeaders+publicErr)
c.closeWriteAndWait()
return
case isUnsupportedTEError(err):
code := StatusNotImplemented
fmt.Fprintf(c.rwc, "HTTP/1.1 %d %s%sUnsupported transfer encoding", code, StatusText(code), errorHeaders)
return
case isCommonNetReadError(err):
return // don't reply
default:
if v, ok := err.(statusError); ok {
fmt.Fprintf(c.rwc, "HTTP/1.1 %d %s: %s%s%d %s: %s", v.code, StatusText(v.code), v.text, errorHeaders, v.code, StatusText(v.code), v.text)
return
}
publicErr := "400 Bad Request"
fmt.Fprintf(c.rwc, "HTTP/1.1 "+publicErr+errorHeaders+publicErr)
return
}
}
serverHandler{c.server}.ServeHTTP(w, w.req)
w.cancelCtx()
if c.hijacked() {
return
}
w.finishRequest()
if !w.shouldReuseConnection() {
if w.requestBodyLimitHit || w.closedRequestBodyEarly() {
c.closeWriteAndWait()
}
return
}
c.setState(c.rwc, StateIdle, runHooks)
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{})
}
}我们需要关注
- for循环，表示尝试复用该conn，用于处理迎面而来的请求
- w.shouldReuseConnection() = false， 表明读取到Client
Connection：Close标头，设置closeAfterReply=true，跳出dor循环，协程即将结束，结束之前执行defer函数，defer函数内close该连接
c.close()
......
// Close the connection.
func (c *conn) close() {
c.finalFlush()
c.rwc.Close()
}- 如果 w.shouldReuseConnection() = true，则将该连接状态置为idle， 并继续走for循环，处理后续请求。
我的收获
- tcp 4次挥手的八股文
- 短连接在服务器上的效应，time_wait，占用可用的SOCKET， 根据实际业务看是否需要切换为长连接
- golang http keep-alive复用tcp连接的源码级分析
- tcpdump抓包的姿势