Internet Communication with End-to-End Performance Guarantees

Abstract

This paper describes the Session Reservation Protocol (SRP). SRP is defined in the DARPA Internet family of protocols. It allows communicating clients to reserve the resources, such as CPU and network bandwidth, necessary to achieve given performance (delay and throughput) objectives. The immediate goal of SRP is to enable IP-based distributed systems to handle “continuous media” (digital audio and video). However, SRP is applicable to any application that requires guaranteed-performance communication. The design goals of SRP include (1) independence from transport protocols (SRP can be used with standard protocols such as TCP or with specialized protocols); (2) compatibility with IP (data packet formats are not modified); (3) a host implementing SRP can benefit from its use even when communicating with hosts not supporting SRP. SRP is based on a workload and scheduling model called the DASH Resource Model. This model defines a parameterization of client workload, an abstract interface for hardware resources, and an end-to-end algorithm for negotiated resource reservation based on cost minimization. SRP implements this end-to-end algorithm, handling those resources related to network communication. The approach can easily be applied to other network environments such as OSI communication.