Msysmondaemonsysmongo tool trace
sysmon20us~10ms
// src/runtime/proc.go

// forcegcperiod is the maximum time in nanoseconds between garbage
// collections. If we go this long without a garbage collection, one
// is forced to run.
//
// This is a variable for testing purposes. It normally doesn't change.
var forcegcperiod int64 = 2 * 60 * 1e9

// Always runs without a P, so write barriers are not allowed.
//
//go:nowritebarrierrec
func sysmon() {
    ......

    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)

        ......
    }

    ......
}
sysmon()
sysmon工作职责
Ggo runtime schedulerGGP
Gsysmon

网络轮询器监控

网络请求G网络轮询器(NetPoller)Pgoroutinesysmon
sysmon20us~10ms网络轮询器Gruntime.netpoll10msfindrunnable()
netpoll()injectglist()netpoll()
// src/runtime/proc.go

func sysmon() {
    ......

    for {
        ......

        // poll network if not polled for more than 10ms
        lastpoll := int64(atomic.Load64(&sched.lastpoll))
        if netpollinited() && lastpoll != 0 && lastpoll+10*1000*1000 < now {
            atomic.Cas64(&sched.lastpoll, uint64(lastpoll), uint64(now))
            list := netpoll(0) // non-blocking - returns list of goroutines
            if !list.empty() {
                // Need to decrement number of idle locked M's
                // (pretending that one more is running) before injectglist.
                // Otherwise it can lead to the following situation:
                // injectglist grabs all P's but before it starts M's to run the P's,
                // another M returns from syscall, finishes running its G,
                // observes that there is no work to do and no other running M's
                // and reports deadlock.
                incidlelocked(-1)
                injectglist(&list)
                incidlelocked(1)
            }
        }

        ......
    }

    ......
}

系统调用syscall监控

系统调用_Psyscall
// src/runtime/proc.go

func sysmon() {
    ......

    for {
        ......

        // retake P's blocked in syscalls
        // and preempt long running G's
        if retake(now) != 0 {
            idle = 0
        } else {
            idle++
        }

        ......
    }

    ......
}
syscall_Psyscall
// forcePreemptNS is the time slice given to a G before it is
// preempted.
const forcePreemptNS = 10 * 1000 * 1000 // 10ms

func retake(now int64) uint32 {
    n := 0

    // 全局p锁
    lock(&allpLock)

    // 遍历每个P
    for i := 0; i < len(allp); i++ {
        _p_ := allp[i]

        // 1. p == nil 说明通过runtime.GOMAXPROCS 动态对P进行了调大,但当前还未初始化使用 直接跳过
        if _p_ == nil {
            // This can happen if procresize has grown
            // allp but not yet created new Ps.
            continue
        }

        // 
        pd := &_p_.sysmontick
        s := _p_.status
        sysretake := false

        // 2. P的状态为 _Prunning或_Psyscall的情况
        if s == _Prunning || s == _Psyscall {
            // Preempt G if it's running for too long.
            // 运行时间过长
            t := int64(_p_.schedtick)

            // 如果 p.sysmontick.schedtick != p.schedtick,则进行次数同步,并指定调度时间为now
            if int64(pd.schedtick) != t {
                pd.schedtick = uint32(t)
                pd.schedwhen = now
            } else if pd.schedwhen+forcePreemptNS <= now {
                // 如果 p上次调度时间 + 10ms <= now,说明下次调度的时候有点长,需要立即进行调度
                // 但是当前P 是_Psyscall 状态的话,并不会抢占P,因为这种情况下M并没有与P绑定
                preemptone(_p_)
                // In case of syscall, preemptone() doesn't
                // work, because there is no M wired to P.
                sysretake = true
            }
        }

        // 3. 系统调用
        if s == _Psyscall {
            // Retake P from syscall if it's there for more than 1 sysmon tick (at least 20us).
            t := int64(_p_.syscalltick)
            if !sysretake && int64(pd.syscalltick) != t {
                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.
            if runqempty(_p_) && atomic.Load(&sched.nmspinning)+atomic.Load(&sched.npidle) > 0 && pd.syscallwhen+10*1000*1000 > now {
                continue
            }
            // Drop allpLock so we can take sched.lock.
            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(&_p_.status, s, _Pidle) {
                if trace.enabled {
                    traceGoSysBlock(_p_)
                    traceProcStop(_p_)
                }
                n++
                _p_.syscalltick++
                handoffp(_p_)
            }
            incidlelocked(1)
            lock(&allpLock)
        }

    }

    // 全局p锁
    unlock(&allpLock)
    return uint32(n)    
}

队此之外还有由于原子、互斥量或通道操作调用导致 Goroutine 阻塞或直接调用 sleep 导致的阻塞也会导致调度器对G进行切换。

垃圾回收

两分钟sysmon
// src/runtime/proc.go

func sysmon() {
    ......

    for {
        ......

        // check if we need to force a GC
        if t := (gcTrigger{kind: gcTriggerTime, now: now}); t.test() && atomic.Load(&forcegc.idle) != 0 {
            lock(&forcegc.lock)
            forcegc.idle = 0
            var list gList
            list.push(forcegc.g)
            injectglist(&list)
            unlock(&forcegc.lock)
        }
        ......
    }

    ......
}
参考资料

本文如有错误,欢迎大家在下方留言指出。