Abstract | ||
---|---|---|
Understanding the characteristics of the Internet delay sp ace (i.e., the all-pairs set of static round-trip propagation delays a mong edge networks in the Internet) is important for the design of global-scale distributed systems. For instance, algorithms used in over lay net- works are often sensitive to violations of the triangle ineq uality and to the growth properties within the Internet delay space. Si nce de- signers of distributed systems often rely on simulation and emula- tion to study design alternatives, they need a realistic mod el of the Internet delay space. Our analysis shows that existing models do not adequately cap- ture important properties of the Internet delay space. In th is paper, we analyze measured delays among thousands of Internet edge net- works and identify key properties that are important for distributed system design. Furthermore, we derive a simple model of the In- ternet delay space based on our analytical findings. This mod el preserves the relevant metrics far better than existing models, al- lows for a compact representation, and can be used to synthesize delay data for simulations and emulations at a scale where direct measurement and storage are impractical. |
Year | DOI | Venue |
---|---|---|
2006 | 10.1145/1177080.1177091 | IEEE/ACM Transactions on Networking |
Keywords | Field | DocType |
system design,analysis,simulation,internet edge network,static round-trip propagation delay,delay data,measurement,realistic model,design alternative,important property,simple model,internet delay space,modeling,distributed system,edge network,synthesis,performance | Network delay,Distributed system design,Computer science,Internet traffic engineering,Computer network,Emulation,Triangle inequality,Overlay network,The Internet | Conference |
Volume | Issue | ISBN |
18 | 1 | 1-59593-561-4 |
Citations | PageRank | References |
74 | 3.17 | 27 |
Authors | ||
6 |
Name | Order | Citations | PageRank |
---|---|---|---|
Bo Zhang | 1 | 133 | 6.74 |
T. S. Eugene Ng | 2 | 2491 | 274.31 |
Animesh Nandi | 3 | 1140 | 76.25 |
Rudolf H. Riedi | 4 | 485 | 39.83 |
Peter Druschel | 5 | 8715 | 861.36 |
Guohui Wang | 6 | 1088 | 60.78 |