func longSyscall() {
	timeout := syscall.NsecToTimeval(int64(5 * time.Second))
	fds := make([]syscall.FdSet, 1)
	if _, err := syscall.Select(0, &fds[0], nil, nil, &timeout); err != nil {
		fmt.Println("Error:", err)
	}
	fmt.Println("Select returned after timeout")
}
func main() {
	threads := runtime.GOMAXPROCS(0)
	for i := 0; i < threads; i++ {
		go longSyscall()
	}
	time.Sleep(8 * time.Second)
}

func sysmon() {
    ...
    idle := 0 // how many cycles in succession we had not wokeup somebody
    delay := uint32(0)
    ...
    for {
		if idle == 0 { // start with 20us sleep...
			delay = 20
		} else if idle > 50 { // start doubling the sleep after 1ms...
			delay *= 2
		}
		if delay > 10*1000 { // up to 10ms
			delay = 10 * 1000
		}
		usleep(delay)
        ...
        // retake P's blocked in syscalls
		// and preempt long running G's
		if retake(now) != 0 {
			idle = 0
		} else {
			idle++
		}
        ...
    }
}

func retake(now int64) uint32 {
	n := 0
	lock(&allpLock)
	for i := 0; i < len(allp); i++ {
		pp := allp[i]
		if pp == nil {
			continue
		}
		pd := &pp.sysmontick
		s := pp.status
		sysretake := false
        if s == _Prunning || s == _Psyscall {                           // goroutine 處于 _Prunning 或 _Psyscall 時會搶占
			// Preempt G if it's running for too long.
			t := int64(pp.schedtick)
			if int64(pd.schedtick) != t {
				pd.schedtick = uint32(t)
				pd.schedwhen = now
			} else if pd.schedwhen+forcePreemptNS <= now {   
                // 對于 _Prunning 或者 _Psyscall 運行時間過長的情況，都會進入 preemptone
                // preemptone 我們在運行時間過長的搶占中介紹過，它主要設(shè)置了 goroutine 的標志位
                // 對于處于系統(tǒng)調(diào)用的 goroutine，這么設(shè)置并不會搶占。因為線程一直處于系統(tǒng)調(diào)用狀態(tài)           
				preemptone(pp)                                          
				// In case of syscall, preemptone() doesn't
				// work, because there is no M wired to P.
				sysretake = true
			}
		}
        if s == _Psyscall {                                             
            // Retake P from syscall if it's there for more than 1 sysmon tick (at least 20us).
            // P 處于系統(tǒng)調(diào)用之中，需要檢查是否需要搶占
            // syscalltick 用于記錄系統(tǒng)調(diào)用的次數(shù)，在完成系統(tǒng)調(diào)用之后加 1
			t := int64(pp.syscalltick)
			if !sysretake && int64(pd.syscalltick) != t {
                // pd.syscalltick != pp.syscalltick，說明已經(jīng)不是上次觀察到的系統(tǒng)調(diào)用了，  
                // 而是另外一次系統(tǒng)調(diào)用，需要重新記錄 tick 和 when 值
				pd.syscalltick = uint32(t)
				pd.syscallwhen = now
				continue
			}
            // On the one hand we don't want to retake Ps if there is no other work to do,
			// but on the other hand we want to retake them eventually
			// because they can prevent the sysmon thread from deep sleep.
            // 如果滿足下面三個條件的一個則執(zhí)行搶占：
            // 1. 線程綁定的本地隊列中有可運行的 goroutine
            // 2. 沒有無所事事的 P（表示大家都挺忙的，那就不要執(zhí)行系統(tǒng)調(diào)用那么長時間占資源了）
            // 3. 執(zhí)行系統(tǒng)調(diào)用時間超過 10ms 的
			if runqempty(pp) && sched.nmspinning.Load()+sched.npidle.Load() > 0 && pd.syscallwhen+10*1000*1000 > now {
				continue
			}
            // 下面是執(zhí)行搶占的邏輯
            unlock(&allpLock)
			// Need to decrement number of idle locked M's
			// (pretending that one more is running) before the CAS.
			// Otherwise the M from which we retake can exit the syscall,
			// increment nmidle and report deadlock.
			incidlelocked(-1)
			if atomic.Cas(&pp.status, s, _Pidle) {                  // 將 P 的狀態(tài)更新為 _Pidle
				n++                                                 // 搶占次數(shù) + 1
				pp.syscalltick++                                    // 系統(tǒng)調(diào)用搶占次數(shù) + 1              
				handoffp(pp)                                        // handoffp 搶占
			}
			incidlelocked(1)
			lock(&allpLock)
        }
    }
    unlock(&allpLock)
	return uint32(n)
}

// Hands off P from syscall or locked M.
// Always runs without a P, so write barriers are not allowed.
//
//go:nowritebarrierrec
func handoffp(pp *p) {
    // if it has local work, start it straight away
    // 這里如果 P 的本地有工作（goroutine），或者全局有工作的話
    // 將 P 和其它線程綁定，其它線程指的是不是執(zhí)行系統(tǒng)調(diào)用的那個線程
    // 執(zhí)行系統(tǒng)調(diào)用的線程不需要 P 了，這時候把 P 釋放出來，算是資源的合理利用，相比于線程，P 是有限的
	if !runqempty(pp) || sched.runqsize != 0 {
		startm(pp, false, false)
		return
	}
    ...
    // no local work, check that there are no spinning/idle M's,
	// otherwise our help is not required
	if sched.nmspinning.Load()+sched.npidle.Load() == 0 && sched.nmspinning.CompareAndSwap(0, 1) { // TODO: fast atomic
		sched.needspinning.Store(0)
		startm(pp, true, false)
		return
	}
    ...
    // 判斷全局隊列有沒有工作要處理
    if sched.runqsize != 0 {
		unlock(&sched.lock)
		startm(pp, false, false)
		return
	}
    ...
    // 如果都沒有工作，那就把 P 放到全局空閑隊列中
    pidleput(pp, 0)
	unlock(&sched.lock)
}

func sysmon() {
	...
	idle := 0 // how many cycles in succession we had not wokeup somebody
	delay := uint32(0)
	for {
		if idle == 0 { // start with 20us sleep...
			delay = 20                  // 如果 idle == 0，表示 sysmon 需要打起精神來，要隔 20us 監(jiān)控一次
		} else if idle > 50 { // start doubling the sleep after 1ms...
			delay *= 2                  // 如果 idle 大于 50，表示循環(huán)了 50 次都沒有搶占，sysmon 將加倍休眠，比較空，sysmon 也不浪費資源，先睡一會
		}
		if delay > 10*1000 { // up to 10ms
			delay = 10 * 1000           // 當然，不能無限制睡下去。最大休眠時間設(shè)置成 10ms
		}
        if retake(now) != 0 {               
			idle = 0                    // 有搶占，則 idle = 0，表示 sysmon 要忙起來
		} else {
			idle++                      // 沒有搶占，idle + 1
		}
    ...
    }
    ...
}