/usr/local/go/src/internal/poll/fd_unix.go
fd_unix.go
FD struct
// FD is a file descriptor. The net and os packages use this type as a
// field of a larger type representing a network connection or OS file.
type FD struct {
// Lock sysfd and serialize access to Read and Write methods.
fdmu fdMutex
// System file descriptor. Immutable until Close.
Sysfd int
// I/O poller.
pd pollDesc
// Writev cache.
iovecs *[]syscall.Iovec
// Semaphore signaled when file is closed.
csema uint32
// Non-zero if this file has been set to blocking mode.
isBlocking uint32
// Whether this is a streaming descriptor, as opposed to a
// packet-based descriptor like a UDP socket. Immutable.
IsStream bool
// Whether a zero byte read indicates EOF. This is false for a
// message based socket connection.
ZeroReadIsEOF bool
// Whether this is a file rather than a network socket.
isFile bool
}
Accept()
// Accept wraps the accept network call.
func (fd *FD) Accept() (int, syscall.Sockaddr, string, error) {
if err := fd.readLock(); err != nil {
return -1, nil, "", err
}
defer fd.readUnlock()
if err := fd.pd.prepareRead(fd.isFile); err != nil {
return -1, nil, "", err
}
for {
// 会被 Block 在这里，直到有新连接进来
s, rsa, errcall, err := accept(fd.Sysfd)
if err == nil {
return s, rsa, "", err
}
switch err {
case syscall.EAGAIN:
if fd.pd.pollable() {
if err = fd.pd.waitRead(fd.isFile); err == nil {
continue
}
}
case syscall.ECONNABORTED:
// This means that a socket on the listen
// queue was closed before we Accept()ed it;
// it's a silly error, so try again.
continue
}
return -1, nil, errcall, err
}
}
// Init initializes the FD. The Sysfd field should already be set.
// This can be called multiple times on a single FD.
// The net argument is a network name from the net package (e.g., "tcp"),
// or "file".
// Set pollable to true if fd should be managed by runtime netpoll.
func (fd *FD) Init(net string, pollable bool) error {
...
err := fd.pd.init(fd)
...
}
func (pd *pollDesc) init(fd *FD) error {
serverInit.Do(runtime_pollServerInit)
ctx, errno := runtime_pollOpen(uintptr(fd.Sysfd))
if errno != 0 {
if ctx != 0 {
runtime_pollUnblock(ctx)
runtime_pollClose(ctx)
}
return errnoErr(syscall.Errno(errno))
}
pd.runtimeCtx = ctx
return nil
}
Read()
// Read implements io.Reader.
func (fd *FD) Read(p []byte) (int, error) {
...
for {
//
n, err := syscall.Read(fd.Sysfd, p)
if err != nil {
n = 0
if err == syscall.EAGAIN && fd.pd.pollable() {
// 判断当前情况是不是已经没有内容可读了，如果是，则进入 poll block
if err = fd.pd.waitRead(fd.isFile); err == nil {
continue
}
}
...
}
err = fd.eofError(n, err)
return n, err
}
}
// /usr/local/go/src/syscall/syscall_unix.go
func Read(fd int, p []byte) (n int, err error) {
n, err = read(fd, p)
if race.Enabled {
if n > 0 {
race.WriteRange(unsafe.Pointer(&p[0]), n)
}
if err == nil {
race.Acquire(unsafe.Pointer(&ioSync))
}
}
if msanenabled && n > 0 {
msanWrite(unsafe.Pointer(&p[0]), n)
}
return
}
- 当有内容可读时，会从
fd.pd.waitRead中的block释放出来，syscall.Read会返回读取到内容的长度
- 当已经没有内容可读时，
syscall.Read会返回 EAGAIN 和 -1，且不会阻塞在这个function。而是最后被阻塞在fd.pd.waitRead(fd.isFile)
// /usr/local/go/src/internal/poll/fd_poll_runtime.go
func (pd *pollDesc) waitRead(isFile bool) error {
return pd.wait('r', isFile)
}
func (pd *pollDesc) wait(mode int, isFile bool) error {
if pd.runtimeCtx == 0 {
return errors.New("waiting for unsupported file type")
}
// 当没有数据可读时，会被阻塞在这里，因此这个G进入sleep，
// 当有新数据到来时（I/O data is readable in kernel space），会从这里继续执行
res := runtime_pollWait(pd.runtimeCtx, mode)
return convertErr(res, isFile)
}
// /usr/local/go/src/runtime/netpoll.go
//go:linkname poll_runtime_pollWait internal/poll.runtime_pollWait
func poll_runtime_pollWait(pd *pollDesc, mode int) int {
...
//
for !netpollblock(pd, int32(mode), false) {
err = netpollcheckerr(pd, int32(mode))
if err != 0 {
return err
}
// Can happen if timeout has fired and unblocked us,
// but before we had a chance to run, timeout has been reset.
// Pretend it has not happened and retry.
}
return 0
}
// /usr/local/go/src/runtime/netpoll.go
// returns true if IO is ready, or false if timedout or closed
// waitio - wait only for completed IO, ignore errors
func netpollblock(pd *pollDesc, mode int32, waitio bool) bool {
gpp := &pd.rg
if mode == 'w' {
gpp = &pd.wg
}
// set the gpp semaphore to WAIT
for {
old := *gpp
if old == pdReady {
*gpp = 0
return true
}
if old != 0 {
throw("runtime: double wait")
}
if atomic.Casuintptr(gpp, 0, pdWait) {
break
}
}
// need to recheck error states after setting gpp to WAIT
// this is necessary because runtime_pollUnblock/runtime_pollSetDeadline/deadlineimpl
// do the opposite: store to closing/rd/wd, membarrier, load of rg/wg
if waitio || netpollcheckerr(pd, mode) == 0 {
gopark(netpollblockcommit, unsafe.Pointer(gpp), waitReasonIOWait, traceEvGoBlockNet, 5)
}
// be careful to not lose concurrent READY notification
old := atomic.Xchguintptr(gpp, 0)
if old > pdWait {
throw("runtime: corrupted polldesc")
}
return old == pdReady
}
// /usr/local/go/src/runtime/proc.go
// Puts the current goroutine into a waiting state and calls unlockf.
// If unlockf returns false, the goroutine is resumed.
// unlockf must not access this G's stack, as it may be moved between
// the call to gopark and the call to unlockf.
// Reason explains why the goroutine has been parked.
// It is displayed in stack traces and heap dumps.
// Reasons should be unique and descriptive.
// Do not re-use reasons, add new ones.
func gopark(unlockf func(*g, unsafe.Pointer) bool, lock unsafe.Pointer, reason waitReason, traceEv byte, traceskip int) {
if reason != waitReasonSleep {
checkTimeouts() // timeouts may expire while two goroutines keep the scheduler busy
}
mp := acquirem()
gp := mp.curg
status := readgstatus(gp)
if status != _Grunning && status != _Gscanrunning {
throw("gopark: bad g status")
}
mp.waitlock = lock
mp.waitunlockf = unlockf
gp.waitreason = reason
mp.waittraceev = traceEv
mp.waittraceskip = traceskip
releasem(mp)
// can't do anything that might move the G between Ms here.
mcall(park_m)
}
Write()
// /usr/local/go/src/internal/poll/fd_unix.go
// Write implements io.Writer.
func (fd *FD) Write(p []byte) (int, error) {
。。。
var nn int
for {
...
// 当 p 中有数据时， n 为写入的长度，err为nil
n, err := syscall.Write(fd.Sysfd, p[nn:max])
if n > 0 {
nn += n
}
if nn == len(p) { // 当已经把 p 中数据通过调用 syscall write 全部写入后，直接return
return nn, err
}
if err == syscall.EAGAIN && fd.pd.pollable() {
// 暂时不知道什么情况下回进到这里
if err = fd.pd.waitWrite(fd.isFile); err == nil {
continue
}
}
...
}
}
// /usr/local/go/src/syscall/syscall_unix.go
// represents the syscall write
func Write(fd int, p []byte) (n int, err error) {
if race.Enabled {
race.ReleaseMerge(unsafe.Pointer(&ioSync))
}
if faketime && (fd == 1 || fd == 2) {
n = faketimeWrite(fd, p)
if n < 0 {
n, err = 0, errnoErr(Errno(-n))
}
} else {
n, err = write(fd, p)
}
if race.Enabled && n > 0 {
race.ReadRange(unsafe.Pointer(&p[0]), n)
}
if msanenabled && n > 0 {
msanRead(unsafe.Pointer(&p[0]), n)
}
return
}
Reference