A survey and comparison of peer-to-peer overlay network schemes

Abstract

Abstract-Over the Internet today, computing and communications environments are significantly more complex and chaotic than classical distributed systems, lacking any centralized organization or hierarchical control. There has been much interest in emerging Peer-to-Peer (P2P) network overlays because they provide a good substrate for creating large-scale data sharing, content distribution and application-level multicast applications. These P2P networks try to provide a long list of features such as: selection of nearby peers, redundant storage, efficient search/location of data items, data permanence or guarantees, hierarchical naming, trust and authentication, and, anonymity. P2P networks potentially offer an efficient routing architecture that is self-organizing, massively scalable, and robust in the wide-area, combining fault tolerance, load balancing and explicit notion of locality. In this paper, we present a survey and comparison of various Structured and Unstructured P2P networks. We categorize the various schemes into these two groups in the design spectrum and discuss the application-level network performance of each group.

D3S – A Distributed Storage Service

“…In sum, BT networks natively supports resource sharing, which requires self organization, load balancing, redundant storage, efficient search of data items, data guarantees, trust and authentication, massive scalability properties and fault-tolerance (i.e., if one peer on the network fails the whole network is not compromised) [5]. These characteristics are thus imported to our implementation, meeting many of the requirements of cloud storage services.…”

“…Nowadays, BitTorrent is actually one of the most popular protocols for transferring large files, with over 150 million active users 5 .…”

Survey-based Comparison of Chord Overlay Networks

“…This peer is called the successor peer of key k, denoted by successor(k). To maintain consistent hashing mapping when a peer n joins the network, certain keys whose IDs are equal or less than the ID of the joined node that were previously assigned to n's successor now need to be reassigned to n. When peer n leaves the Chord ring, all of its assigned keys are reassigned to n's successor and its become responsible for theses keys [4,5].…”

Query Incentive Networks

“…Early systems such as Gnutella and Freenet, as well as research systems including Chord, CAN, Tapestry, and Pastry, proposed algorithms for distributing information across a network of peers, and then allowing decentralized searches to proceed by routing queries to the appropriate content [16].…”