Mutex锁分为两种模式，正常模式 和 饥饿模式
正常模式下, 对于新加入的协程, 它有两种选择, 要么抢到锁,直接结束; 要么抢不到锁, 追加到等待队列尾部, 等待被唤醒
饥饿模式下, 对于新加入的协程只能追加到等待队列尾部, 等待被唤醒。在该模式下, 所有锁竞争者都不能自旋
主要字段
// A Mutex is a mutual exclusion lock.
// The zero value for a Mutex is an unlocked mutex.
//
// A Mutex must not be copied after first use.
//
// In the terminology of the Go memory model,
// the n'th call to Unlock “synchronizes before” the m'th call to Lock
// for any n < m.
// A successful call to TryLock is equivalent to a call to Lock.
// A failed call to TryLock does not establish any “synchronizes before”
// relation at all.
type Mutex struct {
state int32
sema uint32
}
// A Locker represents an object that can be locked and unlocked.
type Locker interface {
Lock()
Unlock()
}
const (
mutexLocked = 1 << iota // 标识上锁成功
mutexWoken // 标识唤醒流程
mutexStarving // 标识进入饥饿模式
mutexWaiterShift = iota // state>>=mutexWaiterShift表示当前阻塞等待锁的协程个数
// Mutex fairness.
//
// Mutex can be in 2 modes of operations: normal and starvation.
// In normal mode waiters are queued in FIFO order, but a woken up waiter
// does not own the mutex and competes with new arriving goroutines over
// the ownership. New arriving goroutines have an advantage -- they are
// already running on CPU and there can be lots of them, so a woken up
// waiter has good chances of losing. In such case it is queued at front
// of the wait queue. If a waiter fails to acquire the mutex for more than 1ms,
// it switches mutex to the starvation mode.
//
// In starvation mode ownership of the mutex is directly handed off from
// the unlocking goroutine to the waiter at the front of the queue.
// New arriving goroutines don't try to acquire the mutex even if it appears
// to be unlocked, and don't try to spin. Instead they queue themselves at
// the tail of the wait queue.
//
// If a waiter receives ownership of the mutex and sees that either
// (1) it is the last waiter in the queue, or (2) it waited for less than 1 ms,
// it switches mutex back to normal operation mode.
//
// Normal mode has considerably better performance as a goroutine can acquire
// a mutex several times in a row even if there are blocked waiters.
// Starvation mode is important to prevent pathological cases of tail latency.
starvationThresholdNs = 1e6 // 等待时间大于1毫秒 则会进入饥饿模式
)
Lock
// Lock locks m.
// If the lock is already in use, the calling goroutine
// blocks until the mutex is available.
func (m *Mutex) Lock() {
// Fast path: grab unlocked mutex.
// 快速路径
if atomic.CompareAndSwapInt32(&m.state, 0, mutexLocked) {
if race.Enabled {
race.Acquire(unsafe.Pointer(m))
}
return
}
// Slow path (outlined so that the fast path can be inlined)
m.lockSlow()
}
lockSlow
func (m *Mutex) lockSlow() {
var waitStartTime int64
starving := false
awoke := false
iter := 0
old := m.state
for {
// 进入以下分支的条件(也就是说该协程会经过有限次的自旋等待来尝试获取锁):
// 1. 锁被占用了并且没有进入饥饿模式
// 2. runtime_canSpin(iter)=true 需要满足比较苛刻的条件, 才会返回true 下文细讲
if old&(mutexLocked|mutexStarving) == mutexLocked && runtime_canSpin(iter) {
// 如果没有设置唤醒标识 并且等待队列为空 通过CAS指令设置唤醒标识
if !awoke && old&mutexWoken == 0 && old>>mutexWaiterShift != 0 &&
atomic.CompareAndSwapInt32(&m.state, old, old|mutexWoken) {
awoke = true
}
// 内部会循环执行 `PAUSE` 指令30次
runtime_doSpin()
iter++
old = m.state
continue
}
new := old
// 非饥饿模式下, 尝试抢锁
if old&mutexStarving == 0 {
new |= mutexLocked
}
// 如果是已经上锁或者处于饥饿模式下 阻塞队列count+1
if old&(mutexLocked|mutexStarving) != 0 {
new += 1 << mutexWaiterShift
}
// The current goroutine switches mutex to starvation mode.
// But if the mutex is currently unlocked, don't do the switch.
// Unlock expects that starving mutex has waiters, which will not
// be true in this case.
// 只有锁被占用的情况下 才可以设置为饥饿模式
if starving && old&mutexLocked != 0 {
new |= mutexStarving
}
// 说明当前协程自旋过, 但现在已经自旋结束了,要取消唤醒标识
if awoke {
// The goroutine has been woken from sleep,
// so we need to reset the flag in either case.
if new&mutexWoken == 0 {
throw("sync: inconsistent mutex state")
}
new &^= mutexWoken
}
// CAS尝试更新最新的state状态
if atomic.CompareAndSwapInt32(&m.state, old, new) {
// 说明上锁成功
if old&(mutexLocked|mutexStarving) == 0 {
break // locked the mutex with CAS
}
// If we were already waiting before, queue at the front of the queue.
queueLifo := waitStartTime != 0
if waitStartTime == 0 {
waitStartTime = runtime_nanotime()
}
// 取锁失败了，就使用sleep原语来阻塞当前goroutine
// 通过信号量来排队获取锁
// 如果是新来的协程放到队列尾部
// 如果是被唤醒的协程放到队列头部
runtime_SemacquireMutex(&m.sema, queueLifo, 1)
// 如果被唤醒了 继续执行下面的流程
// 如果该协程等待时间大于1ms 则应该进入饥饿模式(提升锁公平)
starving = starving || runtime_nanotime()-waitStartTime > starvationThresholdNs
old = m.state
// 如果唤醒后是饥饿模式, 这次锁一定是被该协程获取
if old&mutexStarving != 0 {
// If this goroutine was woken and mutex is in starvation mode,
// ownership was handed off to us but mutex is in somewhat
// inconsistent state: mutexLocked is not set and we are still
// accounted as waiter. Fix that.
if old&(mutexLocked|mutexWoken) != 0 || old>>mutexWaiterShift == 0 {
throw("sync: inconsistent mutex state")
}
// 等待队列长度-1
delta := int32(mutexLocked - 1<<mutexWaiterShift)
if !starving || old>>mutexWaiterShift == 1 {
// Exit starvation mode.
// Critical to do it here and consider wait time.
// Starvation mode is so inefficient, that two goroutines
// can go lock-step infinitely once they switch mutex
// to starvation mode.
// 如果等待队列只有一个元素则退出饥饿模式
delta -= mutexStarving
}
atomic.AddInt32(&m.state, delta)
break
}
// 还没有进入饥饿模式, 为了保持公平性, 会同时设置为唤醒模式 与其他新加入的协程一起竞争锁
awoke = true
iter = 0
} else {
// 说明别的协程成功修改了state 重新for循环尝试
old = m.state
}
}
if race.Enabled {
race.Acquire(unsafe.Pointer(m))
}
}
Unlock
// Unlock unlocks m.
// It is a run-time error if m is not locked on entry to Unlock.
//
// A locked Mutex is not associated with a particular goroutine.
// It is allowed for one goroutine to lock a Mutex and then
// arrange for another goroutine to unlock it.
func (m *Mutex) Unlock() {
if race.Enabled {
_ = m.state
race.Release(unsafe.Pointer(m))
}
// Fast path: drop lock bit.
new := atomic.AddInt32(&m.state, -mutexLocked)
if new != 0 {
// Outlined slow path to allow inlining the fast path.
// To hide unlockSlow during tracing we skip one extra frame when tracing GoUnblock.
m.unlockSlow(new)
}
}
unlockSlow
func (m *Mutex) unlockSlow(new int32) {
// 不能多次执行unclock
if (new+mutexLocked)&mutexLocked == 0 {
fatal("sync: unlock of unlocked mutex")
}
if new&mutexStarving == 0 {
old := new
for {
// If there are no waiters or a goroutine has already
// been woken or grabbed the lock, no need to wake anyone.
// In starvation mode ownership is directly handed off from unlocking
// goroutine to the next waiter. We are not part of this chain,
// since we did not observe mutexStarving when we unlocked the mutex above.
// So get off the way.
// 1. 没有被阻塞的协程, 直接返回
// 2. 有阻塞的协程, 但处于唤醒模式下, 直接返回
// 3. 有阻塞的协程, 但被上锁了。可能发生在for循环内
// 第一次CAS不成功, 可能因为CAS前被新加入的协程抢到锁, 直接返回
// 4. 有阻塞的协程, 但锁处于饥饿模式下
// 进入循环前是「非 Starving」状态，而现在却是 Starving 模式
// 说明这段时间里出现了 (Lock/Unlock)../Lock 连续调用, 导致「被其他 Unlock // 调用唤醒的协程拿不到锁,进入到 Starving 模式.
// 此情况下应该直接退出, 交给下一次 Unlock 调用处理
if old>>mutexWaiterShift == 0 || old&(mutexLocked|mutexWoken|mutexStarving) != 0 {
return
}
// Grab the right to wake someone.
// 等待队列-1 设置唤醒标识
new = (old - 1<<mutexWaiterShift) | mutexWoken
if atomic.CompareAndSwapInt32(&m.state, old, new) {
runtime_Semrelease(&m.sema, false, 1)
return
}
old = m.state
}
} else {
// Starving mode: handoff mutex ownership to the next waiter, and yield
// our time slice so that the next waiter can start to run immediately.
// Note: mutexLocked is not set, the waiter will set it after wakeup.
// But mutex is still considered locked if mutexStarving is set,
// so new coming goroutines won't acquire it.
// 饥饿模式下 手递手唤醒一个协程
runtime_Semrelease(&m.sema, true, 1)
}
}
runtime_canSpin
可以自旋的条件:
- 重试次数小于4
- GOMAXPROCS>1
- 至少有一个处于running状态的P并且本地runq为空 可见自旋获取锁的条件很苛刻了
// src/runtime/proc.go
active_spin = 4
// Active spinning for sync.Mutex.
//
//go:linkname sync_runtime_canSpin sync.runtime_canSpin
//go:nosplit
func sync_runtime_canSpin(i int) bool {
// sync.Mutex is cooperative, so we are conservative with spinning.
// Spin only few times and only if running on a multicore machine and
// GOMAXPROCS>1 and there is at least one other running P and local runq is empty.
// As opposed to runtime mutex we don't do passive spinning here,
// because there can be work on global runq or on other Ps.
if i >= active_spin || ncpu <= 1 || gomaxprocs <= int32(sched.npidle+sched.nmspinning)+1 {
return false
}
if p := getg().m.p.ptr(); !runqempty(p) {
return false
}
return true
}
阻塞与唤醒语义
// SemacquireMutex is like Semacquire, but for profiling contended Mutexes.
// If lifo is true, queue waiter at the head of wait queue.
// skipframes is the number of frames to omit during tracing, counting from
// runtime_SemacquireMutex's caller.
func runtime_SemacquireMutex(s *uint32, lifo bool, skipframes int)
// Semrelease atomically increments *s and notifies a waiting goroutine
// if one is blocked in Semacquire.
// It is intended as a simple wakeup primitive for use by the synchronization
// library and should not be used directly.
// If handoff is true, pass count directly to the first waiter.
// skipframes is the number of frames to omit during tracing, counting from
// runtime_Semrelease's caller.
func runtime_Semrelease(s *uint32, handoff bool, skipframes int)
