Use the form below to send requests at a configurable rate and processing time. Under load you should see request queueing, which can trigger an upscale if autoscaling is configured.

Requests

Sent, in-flight, and finished request counts.

Sent Pending Completed

Metrics

Response and queue times from completed requests. Hover last queue time for X-Request-Start.

Last Average
Response time
Queue time

Send requests

Choose how long each request takes, how much of that time sleeps vs burns CPU, and how fast to send them.

How long do you want each request to take?

How much of each request should sleep (vs burn CPU)?

How many requests per second do you want to send?