CMU-CS-98-150
Computer Science Department
School of Computer Science, Carnegie Mellon University



CMU-CS-98-150

Beagle: A Resource Allocation Protocol for Advanced Services Internet

Prashant Chandra, Allan Fisher, Peter Steenkiste

October 1998

CMU-CS-98-150.ps
CMU-CS-98-150.pdf


Keywords: Computer networks, resource allocation, signaling protocols


There is an emerging class of multi-party, multimedia, multi-flow applications (e.g distributed, interactive simulation) that have a high-level structure that imposes dependencies between resource allocations for flows within the application. These applications are also capable of making intelligent decisions on how resource allocation should be controlled within the application. The development of such applications is enabled by an Internet that is evolving towards providing ubiquitous, value-added, customizable services. Resource management mechanisms can exploit the high-level structure of applications to achieve better quality for applications and improved resource efficiency for the network. This paper describes a resource allocation protocol that allows this class of applications to optimize resource allocation using high-level application-domain knowledge.

The Beagle protocol uses an application mesh as the basic unit of resource allocation. The application mesh is a logical entity that encapsulates all the computation and communication resources that are allocated to an application at end-points and inside the network. Beagle provides support for allocating computational resources and for delegates --- downloadable code fragments that can be used to customize resource management during runtime. Beagle provides a way for applications to optimize resource allocation by expressing a wide range of sharing policies to share resources amongst its flows. Beagle also provides support for aggregation of resource allocation at various granularities. This paper discusses the design of the Beagle components, describes a prototype implementation and presents preliminary performance evaluation results.

17 pages


Return to: SCS Technical Report Collection
School of Computer Science homepage

This page maintained by reports@cs.cmu.edu