The pricing API runs on 2 instances with 4 cores each and normally takes 1,200 requests a second. At 10 seconds the lunchtime peak doubles traffic. Someone left the log level at debug after an incident last week.
From 15 to 60 seconds, answer at least 99.5% of requests with p99 at or under 150 ms, on no more than 2 instances.
ready00:00 / 01:00Success · 10 s–p99 · 10 s–
Goal · measured 00:15–01:00
0 changes · par 1
Requests answered ≥ 99.5%not measured yet
p99 latency ≤ 150 msnot measured yet
Instances ≤ 2 instancesnot measured yet
Service map
Pricing API · pausedSelect a component to inspect
SYSTEM BOUNDARY90% CPUUsers1,200 req/sCLIENTLoad balancer2 instancesSERVICEPricing API6.0 ms CPU/req · 4 ms loggingSERVICECPU HOT
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.
Service map
Pricing API · pausedSelect a component to inspect
SYSTEM BOUNDARY90% CPUUsers1,200 req/sCLIENTLoad balancer2 instancesSERVICEPricing API6.0 ms CPU/req · 4 ms loggingSERVICECPU HOT
SYSTEM BOUNDARY90% CPUUsers1,200 req/sCLIENTLoad balancer2 instancesSERVICEPricing API6.0 ms CPU/req · 4 ms loggingSERVICECPU HOT
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
100/s
Press Start
00:0001:00
Answered–
Failed–
Latency
100 ms
Press Start
00:0001:00
p50–
p95–
p99–
CPU
100%
Press Start
00:0001:00
CPU–
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.