Upcall-based distributed systems have become widespread in recent years. While upcall-based systems provide some obvious advantages, experiences with these systems have exposed unanticipated problems of unpredictability and inefficiency. Incorporating system resources information into flow control is essential in solving these problems. Variants of window-based flow control suitable for distributed systems are investigated. Next, message packing, which improves network bandwidth usage efficiency, and, consequently, message throughput, is presented. Finally, a back pressure mechanism which controls admission of messages into the system by blocking applications at high load is presented. The combination of the window mechanism and the back pressure mechanism provides end-to-end management of system resources. The former manages network resources, while the latter manages operating system resources. The combination maintains good throughput even under high load.