How can request batching hurt tail latency?
PICTURE THIS: ASYNC / PROMISE
Simple meaning
If you wait too long to fill a batch, every request pays that wait, inflating p99.
WHY — Latency and Throughput instead of guessing?
Why interviewers care about Latency and Throughput:
question about Latency and Throughput.
trade-offs, and what you would actually do on a MLOps project - not buzzwords.
Name the idea, why it exists, then one short example.
End with when you use it and one common pitfall.
STEPS — What happens step by step?
Before you speak the answer, walk the interviewer through these steps:
- 1If you wait too
long to fill a batch, every request pays that wait, inflating p99.
- 2Under sparse traffic the
batch never fills and timeouts appear.
- 3Dynamic batching with a
max delay is the usual compromise.
- 4Give an example
One tiny concrete case you can say aloud.
- 5Common mistake
What juniors usually get wrong.
- 6Close
When you pick this over the alternative.
EXAMPLE — See it in action
Here's a short line you can speak, broken into clear beats:
Note: Adapt this scaffold to your own project — keep it under 60–90 seconds.
Key takeaway
If you wait too long to fill a batch, every request pays that wait, inflating p99. Under sparse traffic the batch never fills and timeouts appear.