Challenge 21 · intermediate · Microservices
Find the bottleneck
A request goes from the gateway to orders, which calls inventory and pricing in parallel. At 10 seconds two deploys land together: orders v118 and pricing v42. Soon the gateway is timing out, orders is queueing, and every dashboard is red. You can roll back either deploy, add orders replicas, or cache inventory, but each change counts.
From 15 to 60 seconds, answer at least 99% of requests with a p99 of 200 ms or less, in as few changes as you can: read the traces, logs and per-service latency first.
Goal · measured 00:15–01:00
0 changes · par 1- Requests answered ≥ 99.0%not measured yet
- p99 at the gateway ≤ 200 msnot measured yet
Service map
What changed
Turn on a fault or change a defence while the run plays. Its effect shows here: the 5 seconds before against 5 seconds after it settles.
This is a simulation. Its numbers come from a model of a typical system, not from measuring real servers. The same link and seed always give the same run. How the Chaos Lab works.