Bench-style network research in an Internet instance laboratory

被引:11
作者
Barford, P [1 ]
Landweber, L [1 ]
机构
[1] Univ Wisconsin, Dept Comp Sci, Madison, WI 53706 USA
关键词
D O I
10.1145/956993.956997
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Network researchers employ a variety of experimental methods and tools including analytic modeling techniques, simulators, and widely deployed measurement infrastructures. It is natural to assume that the overall scope of network research may be limited by the type and capability of the tools and test Systems that are available. In this paper we describe a new, bench-style approach for conducting network research that we argue is essential for effectively investigating different classes of important problems. We describe the architecture for the workbench environment that enables this approach -what we call the Internet Instance Laboratory (IIL). The conceptual model for an IIL is a highly configurable laboratory environment containing commercial networking equipment typical of any end-to-end path in the Internet. An IIL would also have the capability to create accurately a broad range of conditions across all networking layers. The two most important advantages of an IIL are the ability to instrument entire end-to-end paths and the ability to install new equipment or protocols in any location in the environment. Clearly, neither of these opportunities is available in the live Internet. While an IIL offers significant capabilities, developing such a testbed is not without significant challenges. We describe these challenges and approaches for addressing them. Finally, we discuss different classes of research questions that would become tractable if an IIL were available.
引用
收藏
页码:21 / 26
页数:6
相关论文
共 26 条
[1]  
Adams A., 1998, IEEE NETWORK
[2]  
[Anonymous], 2330 IETF RFC
[3]  
APISDORF J, 1996, P USENIX 10 SYST ADM
[4]   Internet Web servers: Workload characterization and performance implications [J].
Arlitt, MF ;
Williamson, CL .
IEEE-ACM TRANSACTIONS ON NETWORKING, 1997, 5 (05) :631-645
[5]  
Barford P., 1998, Performance Evaluation Review, V26, P151, DOI 10.1145/277858.277897
[6]  
BARFORD P, 1998, SPECIAL ISSUE WORLD
[7]  
BRESLAU L, 1999, P IEEE INFOCOM 99 NY
[8]  
*COMM RES HOR NETW, 2001, LOOK OV FENC NETW NE
[9]   Self-similarity in World Wide Web traffic: Evidence and possible causes [J].
Crovella, ME ;
Bestavros, A .
IEEE-ACM TRANSACTIONS ON NETWORKING, 1997, 5 (06) :835-846
[10]  
DOWNEY A, 1999, P ACM SIGCOMM 99 CAM