2021-10-10

GO实战-断点调试

环境：

• ubuntu 18.04
• go 1.17.1

准备代码：

package main

func main() {
	println("hello world")
}

准备工具dlv：

$ git clone https://github.com/go-delve/delve.git $GOPATH/src/github.com/go-delve/delve
或者 go get github.com/derekparker/delve/cmd/dlv
$ cd $GOPATH/src/github.com/go-delve/delve
$ make install

编译代码：

go build main.go

获取程序入口地址：

readelf -h ./main

使用断点功能找到入口：

$ dlv exec ./main

使用断点调试功能，查看 Go 的 runtime 的下列函数执行流程，使用 IDE 查看函数的调用方：

必做：runqput，runqget，globrunqput，globrunqget
选做：schedule，findrunnable，sysmon

runqput：

• runnext为空时，将g放到runnext上；
• runnext为非空时，将runnext上oldg放到本地队列上，新g放到runnext；
• 本地队列为满的情况，将本地的一半g与oldg放到全局队列，新g放到runnext上

func runqput(_p_ *p, gp *g, next bool) {
	if randomizeScheduler && next && fastrand()%2 == 0 {
		next = false
	}

	if next {
	retryNext:
		oldnext := _p_.runnext
		if !_p_.runnext.cas(oldnext, guintptr(unsafe.Pointer(gp))) {
			goto retryNext
		}
		if oldnext == 0 {
			return
		}
		// Kick the old runnext out to the regular run queue.
		gp = oldnext.ptr()
	}

retry:
	h := atomic.LoadAcq(&_p_.runqhead) // load-acquire, synchronize with consumers
	t := _p_.runqtail
	if t-h < uint32(len(_p_.runq)) {
		_p_.runq[t%uint32(len(_p_.runq))].set(gp)
		atomic.StoreRel(&_p_.runqtail, t+1) // store-release, makes the item available for consumption
		return
	}
	if runqputslow(_p_, gp, h, t) {
		return
	}
	// the queue is not full, now the put above must succeed
	goto retry
}

// Put g and a batch of work from local runnable queue on global queue.
// Executed only by the owner P.
func runqputslow(_p_ *p, gp *g, h, t uint32) bool {
	var batch [len(_p_.runq)/2 + 1]*g

	// First, grab a batch from local queue.
	n := t - h
	n = n / 2
	if n != uint32(len(_p_.runq)/2) {
		throw("runqputslow: queue is not full")
	}
	for i := uint32(0); i < n; i++ {
		batch[i] = _p_.runq[(h+i)%uint32(len(_p_.runq))].ptr()
	}
	if !atomic.CasRel(&_p_.runqhead, h, h+n) { // cas-release, commits consume
		return false
	}
	batch[n] = gp

	if randomizeScheduler {
		for i := uint32(1); i <= n; i++ {
			j := fastrandn(i + 1)
			batch[i], batch[j] = batch[j], batch[i]
		}
	}

	// Link the goroutines.
	for i := uint32(0); i < n; i++ {
		batch[i].schedlink.set(batch[i+1])
	}
	var q gQueue
	q.head.set(batch[0])
	q.tail.set(batch[n])

	// Now put the batch on global queue.
	lock(&sched.lock)
	globrunqputbatch(&q, int32(n+1))
	unlock(&sched.lock)
	return true
}

runqget：

• runnext非空，直接获取runnext上的g
• runnext为空，从本地队列runq的头获取g

// Get g from local runnable queue.
// If inheritTime is true, gp should inherit the remaining time in the
// current time slice. Otherwise, it should start a new time slice.
// Executed only by the owner P.
func runqget(_p_ *p) (gp *g, inheritTime bool) {
	// If there's a runnext, it's the next G to run.
	for {
		next := _p_.runnext
		if next == 0 {
			break
		}
		if _p_.runnext.cas(next, 0) {
			return next.ptr(), true
		}
	}

	for {
		h := atomic.LoadAcq(&_p_.runqhead) // load-acquire, synchronize with other consumers
		t := _p_.runqtail
		if t == h {
			return nil, false
		}
		gp := _p_.runq[h%uint32(len(_p_.runq))].ptr()
		if atomic.CasRel(&_p_.runqhead, h, h+1) { // cas-release, commits consume
			return gp, false
		}
	}
}

globrunqput:

• 将g放到全局队列中

// Put gp on the global runnable queue.
// sched.lock must be held.
// May run during STW, so write barriers are not allowed.
//go:nowritebarrierrec
func globrunqput(gp *g) {
	assertLockHeld(&sched.lock)

	sched.runq.pushBack(gp)
	sched.runqsize++
}

globrunqget:

• 从全局队列取出一部风放到本地队列

// Try get a batch of G's from the global runnable queue.
// sched.lock must be held.
func globrunqget(_p_ *p, max int32) *g {
	assertLockHeld(&sched.lock)

	if sched.runqsize == 0 {
		return nil
	}

	n := sched.runqsize/gomaxprocs + 1
	if n > sched.runqsize {
		n = sched.runqsize
	}
	if max > 0 && n > max {
		n = max
	}
	if n > int32(len(_p_.runq))/2 {
		n = int32(len(_p_.runq)) / 2
	}

	sched.runqsize -= n

	gp := sched.runq.pop()
	n--
	for ; n > 0; n-- {
		gp1 := sched.runq.pop()
		runqput(_p_, gp1, false)
	}
	return gp
}

消费端总结：

• schedule每61次从全局队列中获取g
• runnext非空，直接获取runnext上的g
• runnext为空、local run queue非空，从本地队列的头部获取g
• runnext为空、local run queue为空、global run queue非空，从全局队列找，最多拿128个，为本地数量的一半，并执行拿过来的第一个
• runnext为空、local run queue为空、global run queue为空，从其它p的local run queue队头偷取它的一半放到本地队列，并执行最后一个g