Skip to main content
Orpheus scales workers based on queue depth, not CPU.

Default Scaling

With defaults, Orpheus:
  • Adds workers when queue backs up
  • Removes idle workers after 5 minutes
  • Always keeps at least min_workers warm

How Scaling Works

Every 5 seconds, Orpheus checks:
Example:
  • 12 requests queued, 3 workers
  • Utilization = 12/3 = 4.0
  • 4.0 > 3.0 → scale up

Monitor Scaling

Output:

Tuning for Your Workload

Fast Tasks (< 1 second)

Slow Tasks (> 30 seconds)

Bursty Traffic

Cost-Sensitive

min_workers: 0 means cold starts. First request after idle period will be slower.

Zero Cold Starts

For instant responses:
This keeps one worker running even with no traffic.

Test Scaling

Send concurrent requests:

Scaling Limits

If max_workers reached and queue still growing, requests wait.

Troubleshooting

Fix common issues →