Name
Abstract | ||
|---|---|---|
Active-network technology envisions deploying execution environments in network elements so that application-specific processing can be applied to network traffic. To provide safety and efficiency, individual nodes must include mechanisms to manage resource use. This implies that nodes must understand resource demands associated with specific traffic. Well-accepted metrics exist for expressing bandwidth (bits per second) and memory (bytes) in units independent of particular nodes. Unfortunately, no well-accepted, platform-independent metric exists to express processing demands. This paper describes and evaluates an approach to model processing demand for active packets in a form interpretable among heterogeneous nodes in an active network. The paper applies the model in two applications: controlling the use of CPU and predicting CPU demand. The model yields improved performance when compared against the approach currently used in many execution environments. The paper also discusses the limits of the proposed model, and outlines future research that might lead to improved outcomes |
Year | DOI | Venue |
|---|---|---|
2002 | 10.1109/DANCE.2002.1003517 | San Francisco, CA |
Keywords | Field | DocType |
model yields improved performance,cpu demand,network traffic,active networks,heterogeneous active networks,cpu use,active network,model processing demand,application-specific processing,modeling cpu demand,execution environment,network element,computer system benchmarking,resource management,predictive models,network architecture,resource manager,resource allocation,central processing unit,nist,packet switching,intelligent networks,heterogeneity,computer networks,software engineering,mathematical models,nodes,throughput,computer applications | Resource management,Central processing unit,Computer science,Network packet,Network architecture,Computer network,Active networking,Resource allocation,Network element,Throughput | Conference |
ISBN | Citations | PageRank |
0-7695-1564-9 | 1 | 0.43 |
References | Authors | |
19 | 3 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Virginie Galtier | 1 | 17 | 4.12 |
| Kevin L. Mills | 2 | 123 | 16.06 |
| Yannick Carlinet | 3 | 27 | 3.62 |