Go GPM 模型

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19
20
21
22
23

                           +---------------------sysmon-------------------+
                           |                                              |
                           |                                              |
               +---+   +---|-------+                 +--------+       +---|---+
go func() ---->| G |-->| P | Local | <== balance ==> | global | <---->| P | M |
               +---+   +-----------+                 +--------+       +---|---+
                 |                                        |               |
                 |    +---+                               |               |
                 +--->| M | <--- find runnable -----------+----- steal <--+
                      +---+
                        |
                        |
  +----execute <----schedule--+
  |                           |
  |                           |
  +---> G.fn ---> goexit -----+

1. go creates a new goroutine
2. newly created goroutine being put into local or global queue
3. a M is being waken or created to execute goroutine
4. schedule loop
5. try its best to get a goroutine to execute
6. clear, reenter schedule loop

  1
  2
  3
  4
  5
  6
  7
  8
  9
 10
 11
 12
 13
 14
 15
 16
 17
 18
 19
 20
 21
 22
 23
 24
 25
 26
 27
 28
 29
 30
 31
 32
 33
 34
 35
 36
 37
 38
 39
 40
 41
 42
 43
 44
 45
 46
 47
 48
 49
 50
 51
 52
 53
 54
 55
 56
 57
 58
 59
 60
 61
 62
 63
 64
 65
 66
 67
 68
 69
 70
 71
 72
 73
 74
 75
 76
 77
 78
 79
 80
 81
 82
 83
 84
 85
 86
 87
 88
 89
 90
 91
 92
 93
 94
 95
 96
 97
 98
 99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150

// $GOROOT/src/runtime/proc.go

// Always runs without a P, so write barriers are not allowed.
//
//go:nowritebarrierrec
func sysmon() {
	lock(&sched.lock)
	sched.nmsys++
	checkdead()
	unlock(&sched.lock)

	lasttrace := int64(0)
	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)

		// sysmon should not enter deep sleep if schedtrace is enabled so that
		// it can print that information at the right time.
		//
		// It should also not enter deep sleep if there are any active P's so
		// that it can retake P's from syscalls, preempt long running G's, and
		// poll the network if all P's are busy for long stretches.
		//
		// It should wakeup from deep sleep if any P's become active either due
		// to exiting a syscall or waking up due to a timer expiring so that it
		// can resume performing those duties. If it wakes from a syscall it
		// resets idle and delay as a bet that since it had retaken a P from a
		// syscall before, it may need to do it again shortly after the
		// application starts work again. It does not reset idle when waking
		// from a timer to avoid adding system load to applications that spend
		// most of their time sleeping.
		now := nanotime()
		if debug.schedtrace <= 0 && (sched.gcwaiting != 0 || atomic.Load(&sched.npidle) == uint32(gomaxprocs)) {
			lock(&sched.lock)
			if atomic.Load(&sched.gcwaiting) != 0 || atomic.Load(&sched.npidle) == uint32(gomaxprocs) {
				syscallWake := false
				next := timeSleepUntil()
				if next > now {
					atomic.Store(&sched.sysmonwait, 1)
					unlock(&sched.lock)
					// Make wake-up period small enough
					// for the sampling to be correct.
					sleep := forcegcperiod / 2
					if next-now < sleep {
						sleep = next - now
					}
					shouldRelax := sleep >= osRelaxMinNS
					if shouldRelax {
						osRelax(true)
					}
					syscallWake = notetsleep(&sched.sysmonnote, sleep)
					if shouldRelax {
						osRelax(false)
					}
					lock(&sched.lock)
					atomic.Store(&sched.sysmonwait, 0)
					noteclear(&sched.sysmonnote)
				}
				if syscallWake {
					idle = 0
					delay = 20
				}
			}
			unlock(&sched.lock)
		}

		lock(&sched.sysmonlock)
		// Update now in case we blocked on sysmonnote or spent a long time
		// blocked on schedlock or sysmonlock above.
		now = nanotime()

		// trigger libc interceptors if needed
		if *cgo_yield != nil {
			asmcgocall(*cgo_yield, nil)
		}
		// 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)
			}
		}
		if GOOS == "netbsd" && needSysmonWorkaround {
			// netpoll is responsible for waiting for timer
			// expiration, so we typically don't have to worry
			// about starting an M to service timers. (Note that
			// sleep for timeSleepUntil above simply ensures sysmon
			// starts running again when that timer expiration may
			// cause Go code to run again).
			//
			// However, netbsd has a kernel bug that sometimes
			// misses netpollBreak wake-ups, which can lead to
			// unbounded delays servicing timers. If we detect this
			// overrun, then startm to get something to handle the
			// timer.
			//
			// See issue 42515 and
			// https://gnats.netbsd.org/cgi-bin/query-pr-single.pl?number=50094.
			if next := timeSleepUntil(); next < now {
				startm(nil, false)
			}
		}
		if scavenger.sysmonWake.Load() != 0 {
			// Kick the scavenger awake if someone requested it.
			scavenger.wake()
		}
		// retake P's blocked in syscalls
		// and preempt long running G's
		if retake(now) != 0 {
			idle = 0
		} else {
			idle++
		}
		// 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)
		}
		if debug.schedtrace > 0 && lasttrace+int64(debug.schedtrace)*1000000 <= now {
			lasttrace = now
			schedtrace(debug.scheddetail > 0)
		}
		unlock(&sched.sysmonlock)
	}
}