go 中的死锁检测，第三方工具 go

前言

最近提交了一份死锁代码，导致某个功能不可用，前端小哥纳闷反馈，这昨天还能用的，今天怎么就不行了？

再一看原来是死锁了

问题

bug

官方是否提供了死锁检测呢？

解决

上网搜了一圈，发现官网没有死锁检测，接下来介绍今天的主角：https://github.com/sasha-s/go-deadlock，这是基于运行时的代码检测的。

deadlocksync

先来看一个简单使用的例子：

// 测试 deadlock 的锁检测超时时间
// 同一把锁在不同的协程中去获取
func tGoDeadlock1() {
	start := time.Now()
	defer func() {
		fmt.Println("耗时：", time.Now().Sub(start))
	}()

	var wg sync.WaitGroup
	wg.Add(1)

	deadlock.Opts.DeadlockTimeout = time.Second // 获取锁超时控制
	//deadlock.Opts.Disable = true // 生产环境可以将其设置为 true
	var mu deadlock.Mutex
	mu.Lock()
	go func() {
		mu.Lock()
		defer mu.Unlock()
		fmt.Println("i'm in goroutine")
		wg.Done()
	}()

	time.Sleep(time.Second * 15)
	mu.Unlock()

	wg.Wait()
}

panicpanic1sdeadlock.Opts.DeadlockTimeout = time.Second1s

源码分析

locklockOrder

type lockOrder struct {
	mu    sync.Mutex
	cur   map[interface{}]stackGID // stacktraces + gids for the locks currently taken.
	order map[beforeAfter]ss       // expected order of locks.
}

type stackGID struct {
	stack []uintptr
	gid   int64
}

type beforeAfter struct {
	before interface{}
	after  interface{}
}

type ss struct {
	before []uintptr
	after  []uintptr
}

下面再贴一小部分源码，看看其具体的过程。

获取锁:

func (m *Mutex) Lock() {
	lock(m.mu.Lock, m)
}

func lock(lockFn func(), ptr interface{}) {
	if Opts.Disable {
		lockFn()
		return
	}
	stack := callers(1)
	preLock(stack, ptr)
	if Opts.DeadlockTimeout <= 0 {
		lockFn()
	} else {
		ch := make(chan struct{})
		currentID := goid.Get()
		go func() {
			for {
				t := time.NewTimer(Opts.DeadlockTimeout)
				defer t.Stop() // This runs after the losure finishes, but it's OK.
				select {
				case <-t.C:
					lo.mu.Lock()
					prev, ok := lo.cur[ptr]
					if !ok {
						lo.mu.Unlock()
						break // Nobody seems to be holding the lock, try again.
					}
					Opts.mu.Lock()
					fmt.Fprintln(Opts.LogBuf, header)
					fmt.Fprintln(Opts.LogBuf, "Previous place where the lock was grabbed")
					fmt.Fprintf(Opts.LogBuf, "goroutine %v lock %p\n", prev.gid, ptr)
					printStack(Opts.LogBuf, prev.stack)
					fmt.Fprintln(Opts.LogBuf, "Have been trying to lock it again for more than", Opts.DeadlockTimeout)
					fmt.Fprintf(Opts.LogBuf, "goroutine %v lock %p\n", currentID, ptr)
					printStack(Opts.LogBuf, stack)
					stacks := stacks()
					grs := bytes.Split(stacks, []byte("\n\n"))
					for _, g := range grs {
						if goid.ExtractGID(g) == prev.gid {
							fmt.Fprintln(Opts.LogBuf, "Here is what goroutine", prev.gid, "doing now")
							Opts.LogBuf.Write(g)
							fmt.Fprintln(Opts.LogBuf)
						}
					}
					lo.other(ptr)
					if Opts.PrintAllCurrentGoroutines {
						fmt.Fprintln(Opts.LogBuf, "All current goroutines:")
						Opts.LogBuf.Write(stacks)
					}
					fmt.Fprintln(Opts.LogBuf)
					if buf, ok := Opts.LogBuf.(*bufio.Writer); ok {
						buf.Flush()
					}
					Opts.mu.Unlock()
					lo.mu.Unlock()
					Opts.OnPotentialDeadlock()
					<-ch
					return
				case <-ch:
					return
				}
			}
		}()
		lockFn()
		postLock(stack, ptr)
		close(ch)
		return
	}
	postLock(stack, ptr)
}

func preLock(stack []uintptr, p interface{}) {
	lo.preLock(stack, p)
}

func (l *lockOrder) preLock(stack []uintptr, p interface{}) {
	if Opts.DisableLockOrderDetection {
		return
	}
	gid := goid.Get()
	l.mu.Lock()
	for b, bs := range l.cur {
		if b == p {
			if bs.gid == gid {
				Opts.mu.Lock()
				fmt.Fprintln(Opts.LogBuf, header, "Recursive locking:")
				fmt.Fprintf(Opts.LogBuf, "current goroutine %d lock %p\n", gid, b)
				printStack(Opts.LogBuf, stack)
				fmt.Fprintln(Opts.LogBuf, "Previous place where the lock was grabbed (same goroutine)")
				printStack(Opts.LogBuf, bs.stack)
				l.other(p)
				if buf, ok := Opts.LogBuf.(*bufio.Writer); ok {
					buf.Flush()
				}
				Opts.mu.Unlock()
				Opts.OnPotentialDeadlock()
			}
			continue
		}
		if bs.gid != gid { // We want locks taken in the same goroutine only.
			continue
		}
		if s, ok := l.order[beforeAfter{p, b}]; ok {
			Opts.mu.Lock()
			fmt.Fprintln(Opts.LogBuf, header, "Inconsistent locking. saw this ordering in one goroutine:")
			fmt.Fprintln(Opts.LogBuf, "happened before")
			printStack(Opts.LogBuf, s.before)
			fmt.Fprintln(Opts.LogBuf, "happened after")
			printStack(Opts.LogBuf, s.after)
			fmt.Fprintln(Opts.LogBuf, "in another goroutine: happened before")
			printStack(Opts.LogBuf, bs.stack)
			fmt.Fprintln(Opts.LogBuf, "happened after")
			printStack(Opts.LogBuf, stack)
			l.other(p)
			fmt.Fprintln(Opts.LogBuf)
			if buf, ok := Opts.LogBuf.(*bufio.Writer); ok {
				buf.Flush()
			}
			Opts.mu.Unlock()
			Opts.OnPotentialDeadlock()
		}
		l.order[beforeAfter{b, p}] = ss{bs.stack, stack}
		if len(l.order) == Opts.MaxMapSize { // Reset the map to keep memory footprint bounded.
			l.order = map[beforeAfter]ss{}
		}
	}
	l.mu.Unlock()
}

释放锁：

func (m *Mutex) Unlock() {
	m.mu.Unlock()
	if !Opts.Disable {
		postUnlock(m)
	}
}

func postUnlock(p interface{}) {
	lo.postUnlock(p)
}

func (l *lockOrder) postUnlock(p interface{}) {
	l.mu.Lock()
	delete(l.cur, p)
	l.mu.Unlock()
}

总结

MutexCondOncePoolWaitGroupLock

deadlockdeadlock.Opts.Disable = true

syncTestgo-deadlock.go