Sized two fraud services for Prime Day from load tests, $12,344 a year saved
When the org scaled up for Prime Day, I load-tested two fraud services, set each host count from the results and cut 18 hosts.
- Cost
- Reliability
- Fraud and risk
$12,344
per year saved
$6,446 + $5,898
18
hosts removed
9 per service
What would have happened
Both services would be over-provisioned for peak by habit.
The call
Benchmark first, then size.
What I did
Ran the load tests, worked out the right host count for each service and resized both fleets.
What changed
18 hosts removed and $12,344 a year saved, with capacity checked against peak traffic.
Proof
The original documents are held in my private record and can be shared on request.