Systems and techniques for servicing requests in an environment having multiple application servers each having one or more queues to store indications of requests to be serviced by the application servers. A utilization level is determined for a first application server of the multiple application servers. The utilization level is compared to a pre-selected utilization threshold level. The system determines whether to service requests allocated to other application servers in response to the comparing. At least one request allocated to a second application server for servicing.