Enhancing the Performance of Locating Data in Chord-Based P2P Systems
Yichun Wu, Chuan-Ming Liu, Jenq‐Haur Wang · 2008
In peer-to-peer (P2P) networks, how to efficiently locate data on distributed hash tables (DHTs) is challenging and has attracted much research attention in recent years. Two measurements are usually considered when discussing the efficient location of data items: the path length (the hop count for resolving a lookup request on the overlay network)and the latency (the actual time period between the issuing and completion of a lookup). In this paper, we propose two protocols based on Chord which is well-known and basic for locating data on DHTs. The first approach, enhanced bidirectional chord (EB-Chord), keeps the finger tables on two directions and uses a heuristic to select the next hop to achieve a short path length. By combining the idea of the Lookup-Parasitic Random Sampling (LPRS), the second approach, enhanced bidirectional chord with lookup-parasitic random sampling (EB-Chord-LPRS), can greatly reduce the average latency. We last validate our protocols through extensive experiments. In comparison with other algorithms, such as Chord, Bidirectional Chord, Low Latency Chord, and LPRS-Chord, our experimental results show that the proposed approaches reduces the path length and latency more than 33% respectively.