Kubernetes 中有很多需要重试的地方，比如重启 Pod、CSI 的 PVC 挂载重试等。出错重试时通常都会等待一个指数增长的时间，本文就来解析这个等待重试的机制。
Pod 的 CrashLoopBackOff 状态
经常使用 Kubernetes 的朋友应该对 CrashLoopBackOff 不陌生，这是一种较常见的 Pod 异常状态。通常发生在 Pod 内的进程启动失败或意外退出（退出码不为 0），而 Pod 的重启策略为 OnFailure 或 Always，kubelet 重启该 Pod 后。
该状态表示 Pod 在运行失败不断重启的循环中，而 kubelet 每次重启的时候都会等待指数级增长的时间。这个重启等待时间就是通过 backoff 实现的，以下是相关代码：
// If a container is still in backoff, the function will return a brief backoff error and
// a detailed error message.
func (m *kubeGenericRuntimeManager) doBackOff(pod *v1.Pod, container *v1.Container, podStatus *kubecontainer.PodStatus, backOff *flowcontrol.Backoff) (bool, string, error) {
var cStatus *kubecontainer.Status
for _, c := range podStatus.ContainerStatuses {
if c.Name == container.Name && c.State == kubecontainer.ContainerStateExited {
cStatus = c
break
}
}
if cStatus == nil {
returnfalse, "", nil
}
klog.V(3).InfoS("Checking backoff for container in pod", "containerName", container.Name, "pod", klog.KObj(pod))
// Use the finished time of the latest exited container as the start point to calculate whether to do back-off.
ts := cStatus.FinishedAt
// backOff requires a unique key to identify the container.
key := getStableKey(pod, container)
if backOff.IsInBackOffSince(key, ts) {
if containerRef, err := kubecontainer.GenerateContainerRef(pod, container); err == nil {
m.recorder.Eventf(containerRef, v1.EventTypeWarning, events.BackOffStartContainer,
fmt.Sprintf("Back-off restarting failed container %s in pod %s", container.Name, format.Pod(pod)))
}
err := fmt.Errorf("back-off %s restarting failed container=%s pod=%s", backOff.Get(key), container.Name, format.Pod(pod))
klog.V(3).InfoS("Back-off restarting failed container", "err", err.Error())
returntrue, err.Error(), kubecontainer.ErrCrashLoopBackOff
}
backOff.Next(key, ts)
returnfalse, "", nil
}backoff 的用法
使用 backoff 的方法很简单，只需要用到 .IsInBackOffSince 和 .Next 方法：
func startBackoff() {
backOff := flowcontrol.NewBackOff(5*time.Second, 60*time.Second)
backOffID := "test"
lastDo := time.Now()
t := time.NewTicker(1 * time.Second)
defer t.Stop()
forrange t.C {
if backOff.IsInBackOffSince(backOffID, lastDo) { // 判断当前是否应该执行
continue
}
fmt.Printf("doing work after %s\n", time.Now().Sub(lastDo))
backOff.Next(backOffID, time.Now()) // 标记已经执行过了
lastDo = time.Now()
}
}以上代码的输出结果：
doing work after 1.001035775s
doing work after 5.999162394s
doing work after 10.9999193s
doing work after 21.000754631s
doing work after 40.999154124s
...也可以对特定 id 重新计时：
backOff.Reset(backOffID)将所有 id 全部清除：
backOff.GC()backoff 的实现原理
backoff 的实现就百来行代码，短小精悍。主结构体内定义了每个 id 对应的任务执行时间和等待时间。
在记录当前执行时间时，将等待时间设置为上一次等待时间乘 2，实现等待时间指数级增长的效果：
func (p *Backoff) Next(id string, eventTime time.Time) {
p.Lock()
defer p.Unlock()
entry, ok := p.perItemBackoff[id]
if !ok || hasExpired(eventTime, entry.lastUpdate, p.maxDuration) {
entry = p.initEntryUnsafe(id)
entry.backoff += p.jitter(entry.backoff)
} else {
delay := entry.backoff * 2 // exponential
delay += p.jitter(entry.backoff) // add some jitter to the delay
entry.backoff = min(delay, p.maxDuration)
}
entry.lastUpdate = p.Clock.Now()
}判断当前是否需要执行时，只需要判断是否到了等待时间即可：
func (p *Backoff) IsInBackOffSince(id string, eventTime time.Time) bool {
p.RLock()
defer p.RUnlock()
entry, ok := p.perItemBackoff[id]
if !ok {
returnfalse
}
if hasExpired(eventTime, entry.lastUpdate, p.maxDuration) {
returnfalse
}
return p.Clock.Since(eventTime) < entry.backoff
}
