Systems and techniques for utilizing resource aware queues and/or service sharing in a multi-server environment. According to an example, an application server employs a traffic light metaphor to represent a utilization level of resources of the application server by associating a traffic light with each resource. A mapping is maintained that associates service requests with corresponding sets of affected traffic lights. A deferred queue is maintained for each traffic light to facilitate throttling of service requests directed to the application server that involve a resource that is under pressure. Responsive to receiving a service request directed to the application server, the service request is added directly or indirectly to one of multiple queues maintained in front of the application server based on a priority associated with the service request. Service requests are serviced from the queues in accordance with a priority associated with the queues.