Scale and reliability 0/11

Lesson 10 of 11

Tail latency

Explain why waiting for many servers raises tail latency, and when hedged requests help or add too much load.

1,326 words · 6 min read Ultra Premium Useful background: Latency numbers, SLOs and error budgets

In this lesson

  1. The slow requests
  2. Sources of variability
  3. Fan-out and dependence
  4. Tail-tolerant techniques
  5. A search fan-out
  6. Calculate the tail
  7. Hedge a read
  8. What stays true
  9. Costs and tradeoffs
  10. Common mistakes
  11. Related topics and practice

Ultra Premium

Unlock this lesson

Ultra Premium opens the 11 premium lessons in Scale and reliability, along with the rest of WhiteBox's premium lessons and problems.

Not ready yet? Read the free lesson: Backpressure