Efficient content location using interest-based locality in peer-to-peer systems

Abstract

Locating content in decentralized peer-to-peer systems is a challenging problem. Gnutella, a popular file-sharing application, relies on flooding queries to all peers. Although flooding is simple and robust, it is not scalable. In this paper, we explore how to retain the simplicity of Gnutella, while addressing its inherent weakness: scalability. We propose a content location solution in which peers loosely organize themselves into an interest-based structure on top of the existing Gnutella network. Our approach exploits a simple, yet powerful principle called interest-based locality, which posits that if a peer has a particular piece of content that one is interested in, it is very likely that it will have other items that one is interested in as well. When using our algorithm, called interest-based shortcuts, a significant amount of flooding can be avoided, making Gnutella a more competitive solution. In addition, shortcuts are modular and can be used to improve the performance of other content location mechanisms including distributed hash table schemes. We demonstrate the existence of interest-based locality in five diverse traces of content distribution applications, two of which are traces of popular peer-to-peer file-sharing applications. Simulation results show that interest-based shortcuts often resolve queries quickly in one peer-to-peer hop, while reducing the total load in the system by a factor of 3 to 7.

Semantics‐Based Resource Discovery in Large‐Scale Grids

“…The ShortCut approach is chosen as one comparison reference since it is simple yet effective, and many popular applications (e.g., [23], [25], [26], [27]) use this approach as their basic routing scheme. Moreover, it is comparable to our approach in the sense that it creates clusters on top of the unstructured network.…”

Searching Dynamic Communities with Personal Indexes

“…While its routing approach is efficient, especially when churn is high its performance suffers from (de-)registering complex semantics in the distributed indices. [18] first considers the semantics of the query to exploit interest-based locality in a static network. They use shortcuts that are generated after each successful query and are used to further requests, hence they are comparable to content provider shortcuts.…”

“…The design of the content provider shortcut overlay departs from existing work as published by [18], [19], or [7] and exploits the simple, yet powerful principle of interest- based locality. That means if a content provider peer has a particular piece of content that a peer is interested in, it can be considered very likely that the content provider will also have other interesting items for that peer.…”

“…As a baseline we compare INGA with an index size of 40 entries against the interest based locality strategy (IBL) of [18] with an LRU strategy and an index size of 40 entries, the naive algorithm of Gnutella (Naive) and REMINDIN [19].…”

“…To determine an optimal weighting of the parameter (a, b, c) of the index policy, we conducted experiments where we only consider the similarity locality (a = 10, b = 0, c = 0) , where we only consider the community locality (with a = 0, b = 10, c = 0), where we only consider the LRU-Locality (a = 0, b = 0, c = 10) and an 'optimal' combination (a = 3, b = 6, c = 1). [18] proposes a LRU strategy to update the index. We found out that there are better strategies.…”