# Call Capacity and Sizing
The default OVA is sized with capacity for most installations. It has been load tested at 200 calls per second (CPS).
# What is the default capacity of the OVA?
The OVA defaults with 2 vCPU, and hits 200-300 new calls insepctions per second in under 15ms, constant load, 95th percentile.
Scale the OVA to 8 vCPU and get load tested 600+ call inspections per second in under 15ms.
# What happens if it somehow becomes overloaded?
Broadly, the multi-core architecture can support 100 new call real-time policy inspections per Core per second while under 15ms.
If overloaded, the request will be returned error with HTTP code 500, and calls will continue according to the ECC profile setting default - typically allow call.
# What if I want Failover?
It's ready and load tested too. Take a look at the Enterprise HA Kubernetes option.