「23」GPM main入口函数

发表于 本文字数： 11k 阅读时长 ≈ 10 分钟

前面g0和m0瞎扯了部分的入口和一些关键的点。

本来应该扯扯shedule调度方面的知识，但是这个先往后放一节吧，

先学习下这个「入口函数」，毕竟对于每一个项目都会有一个入口的相关逻辑，那么go源码是怎么处理的？

有没有什么可以借鉴的嘞？！

接下来该到main函数的相关处理。

go version: 1.14.3

code分析

main函数入口

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

// The main goroutine.
func main() {
	g := getg()

	// Racectx of m0->g0 is used only as the parent of the main goroutine.
	// It must not be used for anything else.
	g.m.g0.racectx = 0

	// Max stack size is 1 GB on 64-bit, 250 MB on 32-bit.
	// Using decimal instead of binary GB and MB because
    // they look nicer in the stack overflow failure message.
    
    //最大栈空间限制
	if sys.PtrSize == 8 {
		maxstacksize = 1000000000
	} else {
		maxstacksize = 250000000
	}

	// Allow newproc to start new Ms.
	mainStarted = true

    //如果是wasm，就不要调度程序了.
    if GOARCH != "wasm" { // no threads on wasm yet, so no sysmon

		//系统栈调用
		systemstack(func() {
            // newm的回调函数，，，一个M一个sysmon P
			newm(sysmon, nil)
		})
	}

	// Lock the main goroutine onto this, the main OS thread,
	// during initialization. Most programs won't care, but a few
	// do require certain calls to be made by the main thread.
	// Those can arrange for main.main to run in the main thread
	// by calling runtime.LockOSThread during initialization
	// to preserve the lock.
	lockOSThread()

	if g.m != &m0 {
		throw("runtime.main not on m0")
	}

	doInit(&runtime_inittask) // must be before defer
	if nanotime() == 0 {
		throw("nanotime returning zero")
	}

	// Defer unlock so that runtime.Goexit during init does the unlock too.
	needUnlock := true
	defer func() {
		if needUnlock {
			unlockOSThread()
		}
	}()

	// Record when the world started.
	runtimeInitTime = nanotime()

    //启动GC
	gcenable()

	main_init_done = make(chan bool)
	if iscgo {
		if _cgo_thread_start == nil {
			throw("_cgo_thread_start missing")
		}
		if GOOS != "windows" {
			if _cgo_setenv == nil {
				throw("_cgo_setenv missing")
			}
			if _cgo_unsetenv == nil {
				throw("_cgo_unsetenv missing")
			}
		}
		if _cgo_notify_runtime_init_done == nil {
			throw("_cgo_notify_runtime_init_done missing")
		}
		// Start the template thread in case we enter Go from
		// a C-created thread and need to create a new thread.
		startTemplateThread()
		cgocall(_cgo_notify_runtime_init_done, nil)
	}

	doInit(&main_inittask)

	close(main_init_done)

	needUnlock = false
	unlockOSThread()

	if isarchive || islibrary {
		// A program compiled with -buildmode=c-archive or c-shared
		// has a main, but it is not executed.
		return
    }
    
    //对于main函数的回调，也就是用户写的main程序
	fn := main_main // make an indirect call, as the linker doesn't know the address of the main package when laying down the runtime
	fn()
	if raceenabled {
		racefini()
	}

	// Make racy client program work: if panicking on
	// another goroutine at the same time as main returns,
	// let the other goroutine finish printing the panic trace.
    // Once it does, it will exit. See issues 3934 and 20018.
    //判断panicDefer函数，，，，，，
	if atomic.Load(&runningPanicDefers) != 0 {
		// Running deferred functions should not take long.
		for c := 0; c < 1000; c++ {
			if atomic.Load(&runningPanicDefers) == 0 {
				break
			}
			Gosched()
		}
    }
    // 判断panic
	if atomic.Load(&panicking) != 0 {
		gopark(nil, nil, waitReasonPanicWait, traceEvGoStop, 1)
	}
    //正常退出了那.....
	exit(0)
	for {
		var x *int32
		*x = 0
	}
}

systemstack

这个函数，在整个系统中较为重要，来看看官方说明

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
// systemstack runs fn on a system stack.
// If systemstack is called from the per-OS-thread (g0) stack, or
// if systemstack is called from the signal handling (gsignal) stack,
// systemstack calls fn directly and returns.
//g0 stack或者信号处理的，就直接调用并返回。

// Otherwise, systemstack is being called from the limited stack
// of an ordinary goroutine. In this case, systemstack switches
// to the per-OS-thread stack, calls fn, and switches back.
// It is common to use a func literal as the argument, in order
// to share inputs and outputs with the code around the call
// to system stack:
//
//	... set up y ...
//	systemstack(func() {
//		x = bigcall(y)
//	})
//	... use x ...
//
//go:noescape
func systemstack(fn func())

newm

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
// Create a new m. It will start off with a call to fn, or else the scheduler.
// fn needs to be static and not a heap allocated closure.
// May run with m.p==nil, so write barriers are not allowed.
//go:nowritebarrierrec

//用于创建新的M，fn:sysmon函数，类似于事件驱动类型的。
func newm(fn func(), _p_ *p) {
	//分配内存
	mp := allocm(_p_, fn)
	mp.nextp.set(_p_)
	mp.sigmask = initSigmask
	if gp := getg(); gp != nil && gp.m != nil && (gp.m.lockedExt != 0 || gp.m.incgo) && GOOS != "plan9" {
		// We're on a locked M or a thread that may have been
		// started by C. The kernel state of this thread may
		// be strange (the user may have locked it for that
		// purpose). We don't want to clone that into another
		// thread. Instead, ask a known-good thread to create
		// the thread for us.
		//
		// This is disabled on Plan 9. See golang.org/issue/22227.
		//
		// TODO: This may be unnecessary on Windows, which
		// doesn't model thread creation off fork.
		lock(&newmHandoff.lock)
		if newmHandoff.haveTemplateThread == 0 {
			throw("on a locked thread with no template thread")
		}
		mp.schedlink = newmHandoff.newm
		newmHandoff.newm.set(mp)
		if newmHandoff.waiting {
			newmHandoff.waiting = false
			notewakeup(&newmHandoff.wake)
		}
		unlock(&newmHandoff.lock)
		return
	}
	newm1(mp)
}

主要是以下几个函数：

  • allocm
  • notewakeup
  • newm1

sysmon

学习系统监控之前，先学下部分函数的使用和其大概含义：

  • checkdead
  • usleep
  • timeSleepUntil
  • nanotime
  • netpollinited
  • startm
  • retake
  • gcTrigger
  • injectglist

先看下主体流程

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

// Always runs without a P, so write barriers are not allowed.
//
//go:nowritebarrierrec
func sysmon() {
	lock(&sched.lock)
	sched.nmsys++
	//基于running中的M，检查死锁，，，，
	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
		}
		//休眠时间
		usleep(delay)
		//获取时间
		now := nanotime()
		// 休眠等待唤醒信号
		next, _ := timeSleepUntil()
		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) {
				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)
					}
					notetsleep(&sched.sysmonnote, sleep)
					if shouldRelax {
						osRelax(false)
					}
					now = nanotime()
					next, _ = timeSleepUntil()
					lock(&sched.lock)
					atomic.Store(&sched.sysmonwait, 0)
					noteclear(&sched.sysmonnote)
				}
				idle = 0
				delay = 20
			}
			unlock(&sched.lock)
		}
		lock(&sched.sysmonlock)
		{
			// If we spent a long time blocked on sysmonlock
			// then we want to update now and next since it's
			// likely stale.
			now1 := nanotime()
			if now1-now > 50*1000 /* 50µs */ {
				next, _ = timeSleepUntil()
			}
			now = now1
		}

		// trigger libc interceptors if needed
		if *cgo_yield != nil {
			asmcgocall(*cgo_yield, nil)
		}
		// poll network if not polled for more than 10ms
		//在队列中等待调度超过10ms，就给交给global抢渡了
		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)
				//注入全局g队列中
				injectglist(&list)
				incidlelocked(1)
			}
		}
		if next < now {
			// There are timers that should have already run,
			// perhaps because there is an unpreemptible P.
			// Try to start an M to run them.
			//需要一个新的M来跑P上面的G。
			startm(nil, false)
		}
		if atomic.Load(&scavenge.sysmonWake) != 0 {
			// Kick the scavenger awake if someone requested it.
			wakeScavenger()
		}
		// retake P's blocked in syscalls
		// and preempt long running G's
		// 循环所有的allp，进行抢夺。
		if retake(now) != 0 {
			idle = 0
		} else {
			idle++
		}
		// check if we need to force a GC
		//强行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)
	}
}

doInit

这一部分在源码看来，没有具体的作用，，，，，，，，todo标签吧。

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
func doInit(t *initTask) {
	switch t.state {
	case 2: // fully initialized
		return
	case 1: // initialization in progress
		throw("recursive call during initialization - linker skew")
	default: // not initialized yet
		t.state = 1 // initialization in progress
		for i := uintptr(0); i < t.ndeps; i++ {
			p := add(unsafe.Pointer(t), (3+i)*sys.PtrSize)
			t2 := *(**initTask)(p)
			doInit(t2)
		}
		for i := uintptr(0); i < t.nfns; i++ {
			p := add(unsafe.Pointer(t), (3+t.ndeps+i)*sys.PtrSize)
			f := *(*func())(unsafe.Pointer(&p))
			f()
		}
		t.state = 2 // initialization done
	}
}

gcenable

1
2
3
4
5
6
7
8
9
10
11
12
13
// gcenable is called after the bulk of the runtime initialization,
// just before we're about to start letting user code run.
// It kicks off the background sweeper goroutine, the background
// scavenger goroutine, and enables GC.
func gcenable() {
	// Kick off sweeping and scavenging.
	c := make(chan int, 2)
	go bgsweep(c)
	go bgscavenge(c)
	<-c
	<-c
	memstats.enablegc = true // now that runtime is initialized, GC is okay
}

Gosched

1
2
3
4
5
6
// Gosched yields the processor, allowing other goroutines to run. It does not
// suspend the current goroutine, so execution resumes automatically.
func Gosched() {
	checkTimeouts()
	mcall(gosched_m)
}

gopark

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
// 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
	//mp解绑
	releasem(mp)
	// can't do anything that might move the G between Ms here.
	mcall(park_m)
}

后续

关于里面的重要部分实现细节，不是本次关注的重点，，，，

1
2
3
4
5
6
7
8
9
这次主要看到的是Go围绕main函数，为了程序的正常启动，所做的工作.

无论是g的启动还是调度监控方面，也就是从整个生命周期来考虑，，，，，，


还有一个就是关于panic的处理，采用事件驱动的方式，很好的获取到panic,进行后续的处理。

最后还有一个关于全局locktrhead，，，，，，粒度尽量细小，有利于提高性能。