Gossip-based topology inference for efficient overlay mapping on data centers

Author

Schuett, T. ; Reinefeld, Alexander ; Schintke, Florian ; Hoffmann, Marie

Author_Institution

Zuse Inst., Berlin, Germany

fYear

2009

fDate

9-11 Sept. 2009

Firstpage

147

Lastpage

150

Abstract

We present a distributed algorithm for identifying the location of data centers and their relative sizes. This topology information can be used in P2P systems to improve the routing performance, replica placement, or job scheduling. The algorithm uses gossiping with local agglomerative clustering. It is robust to failures and it correctly identifies outliers that are caused, e.g., by temporarily overloaded nodes or network failures. We present empirical results on the Grid 5000 testbed.

Keywords

computer centres; distributed algorithms; pattern clustering; peer-to-peer computing; scheduling; telecommunication network routing; telecommunication network topology; agglomerative clustering; data center location identification; distributed algorithm; gossip-based topology inference; job scheduling; overlay mapping; peer-to-peer system; replica placement; routing performance; Clustering algorithms; Delay; Distributed algorithms; IP networks; Inference algorithms; Network topology; Peer to peer computing; Robustness; Routing; Testing;

fLanguage

English

Publisher

ieee

Conference_Titel

Peer-to-Peer Computing, 2009. P2P '09. IEEE Ninth International Conference on

Conference_Location

Seattle, WA

Print_ISBN

978-1-4244-5066-4

Electronic_ISBN

978-1-4244-5067-1

Type

conf

DOI

10.1109/P2P.2009.5284553

Filename

5284553