序
本文次要钻研一下cortex的Backoff
Backoff
github.com/cortexproject/cortex/pkg/util/backoff.go
// Backoff implements exponential backoff with randomized wait timestype Backoff struct { cfg BackoffConfig ctx context.Context numRetries int nextDelayMin time.Duration nextDelayMax time.Duration}// NewBackoff creates a Backoff object. Pass a Context that can also terminate the operation.func NewBackoff(ctx context.Context, cfg BackoffConfig) *Backoff { return &Backoff{ cfg: cfg, ctx: ctx, nextDelayMin: cfg.MinBackoff, nextDelayMax: doubleDuration(cfg.MinBackoff, cfg.MaxBackoff), }}Backoff定义了cfg、ctx、numRetries、nextDelayMin、nextDelayMax属性；NewBackoff提供了基于BackoffConfig的工厂办法，默认的nextDelayMin为cfg.MinBackoff
BackoffConfig
github.com/cortexproject/cortex/pkg/util/backoff.go
// BackoffConfig configures a Backofftype BackoffConfig struct { MinBackoff time.Duration `yaml:"min_period"` // start backoff at this level MaxBackoff time.Duration `yaml:"max_period"` // increase exponentially to this level MaxRetries int `yaml:"max_retries"` // give up after this many; zero means infinite retries}BackoffConfig定义了MinBackoff、MaxBackoff、MaxRetries属性
Ongoing
github.com/cortexproject/cortex/pkg/util/backoff.go
// Reset the Backoff back to its initial conditionfunc (b *Backoff) Reset() { b.numRetries = 0 b.nextDelayMin = b.cfg.MinBackoff b.nextDelayMax = doubleDuration(b.cfg.MinBackoff, b.cfg.MaxBackoff)}// Ongoing returns true if caller should keep goingfunc (b *Backoff) Ongoing() bool { // Stop if Context has errored or max retry count is exceeded return b.ctx.Err() == nil && (b.cfg.MaxRetries == 0 || b.numRetries < b.cfg.MaxRetries)}// Err returns the reason for terminating the backoff, or nil if it didn't terminatefunc (b *Backoff) Err() error { if b.ctx.Err() != nil { return b.ctx.Err() } if b.cfg.MaxRetries != 0 && b.numRetries >= b.cfg.MaxRetries { return fmt.Errorf("terminated after %d retries", b.numRetries) } return nil}// NumRetries returns the number of retries so farfunc (b *Backoff) NumRetries() int { return b.numRetries}// Wait sleeps for the backoff time then increases the retry count and backoff time// Returns immediately if Context is terminatedfunc (b *Backoff) Wait() { // Increase the number of retries and get the next delay sleepTime := b.NextDelay() if b.Ongoing() { select { case <-b.ctx.Done(): case <-time.After(sleepTime): } }}func (b *Backoff) NextDelay() time.Duration { b.numRetries++ // Handle the edge case the min and max have the same value // (or due to some misconfig max is < min) if b.nextDelayMin >= b.nextDelayMax { return b.nextDelayMin } // Add a jitter within the next exponential backoff range sleepTime := b.nextDelayMin + time.Duration(rand.Int63n(int64(b.nextDelayMax-b.nextDelayMin))) // Apply the exponential backoff to calculate the next jitter // range, unless we've already reached the max if b.nextDelayMax < b.cfg.MaxBackoff { b.nextDelayMin = doubleDuration(b.nextDelayMin, b.cfg.MaxBackoff) b.nextDelayMax = doubleDuration(b.nextDelayMax, b.cfg.MaxBackoff) } return sleepTime}func doubleDuration(value time.Duration, max time.Duration) time.Duration { value = value * 2 if value <= max { return value } return max}Backoff次要提供了Ongoing及Wait办法；Ongoing返回bool用于示意是否能够持续，如果err为nil且b.cfg.MaxRetries或者b.numRetries < b.cfg.MaxRetries返回true；Wait办法会期待执行实现或者是b.NextDelay()工夫到；NextDelay办法会递增numRetries而后计算sleepTime；Err办法返回ctx的Err或者是重试次数超限的谬误
实例
// NewBackoffRetry gRPC middleware.func NewBackoffRetry(cfg util.BackoffConfig) grpc.UnaryClientInterceptor { return func(ctx context.Context, method string, req, reply interface{}, cc *grpc.ClientConn, invoker grpc.UnaryInvoker, opts ...grpc.CallOption) error { backoff := util.NewBackoff(ctx, cfg) for backoff.Ongoing() { err := invoker(ctx, method, req, reply, cc, opts...) if err == nil { return nil } if status.Code(err) != codes.ResourceExhausted { return err } backoff.Wait() } return backoff.Err() }}NewBackoffRetry展现了如何应用backoff，通过for循环，条件为backoff.Ongoing()，两头执行要重试的操作，最初执行backoff.Wait()，如果没有提前返回最初返回backoff.Err()
小结
cortex提供了Backoff，能够基于MinBackoff、MaxBackoff、MaxRetries来进行重试。
doc
- cortex