A load balancer sends 800 requests a second, round robin, to four instances that can each serve 400. At 10 seconds instance 4's disk starts failing: it stays up and answers its health check, but every request takes ten times as long and it can serve only 80 a second.
From 15 to 60 seconds, answer at least 99.5% of requests with a p99 of 200 ms or less.
All components healthy.requestretrytrial call (half-open)failed
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.
Dashboard
Requests per second
1,000/s
Press Start
00:0001:00
Answered–
Timed out–
Latency
200 ms
Press Start
00:0001:00
p50–
p95–
p99–
Share of traffic
40%
Press Start
00:0001:00
Instance 4–
Instance 1–
Events and logs
Nothing yet. Faults, timeouts, retries, breaker changes, shedding, cache expiry and your own changes appear here, and as markers on the charts.
Slowest recent request
Press Start to see requests.
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.