An optimal inherently stabilizing routing algorithm for star P2P overlay networks

Abstract

Summary Star graphs possess many desirable properties such as scalable node degrees and diameters, which are essential to facilitate reduced routing table sizes and low maximum path length for routing in large P2P networks. In addition, because a large number of disjoint paths are available and each data/replica in an n‐star can be placed in an (n − 1)‐star, load balancing and alleviation of network bottlenecks can be implemented in star P2P overlay networks. Therefore, star networks have been proposed as viable alternatives to existing overlay topologies for large P2P networks. In this paper, we propose an optimal stabilizing and inherently stabilizing algorithm for routing messages over all disjoint paths between two peers in a star P2P overlay network. The algorithm is optimal in terms of its time complexity in rounds and the length of the longest path traversed by the messages, and fault tolerant due to being stabilizing and inherently stabilizing, allowing the system to withstand transient faults. The algorithm can be used to increase network reliability and survivability in P2P networks. In addition, the usage of all disjoint paths to route messages between two peers leads to increased network bandwidth while distributing the communication overhead across the network and eliminating network bottlenecks in P2P networks. Copyright © 2016 John Wiley & Sons, Ltd.

Multipath Routing Over Star Overlays for Quality of Service Enhancement in Hybrid Content Distribution Peer-to-Peer Networks

“…The same also show that the overlay with the multipath routing does not lead to network bottlenecks. Fourth, our simulation results show that the star overlay networks with the multipath routing algorithm of [16] delivers content from a source to a destination peer over multiple overlay paths in at most D(S n ) + 4 cycles/rounds. The rest of the paper is organized as follows.…”

“…In this section, we present a brief overview of the inherently-stabilizing routing algorithm for star P2P overlay networks [16] that is simulated and evaluated in this paper. The algorithm proposed by Karaata et al is for routing messages over all disjoints paths between two peers in a star P2P overlay network.…”

“…An ideal overlay network with an appropriate number of multipaths between communication endpoints increases the network bandwidth while evenly balancing the network load among peers and links of the network, reduces network bottlenecks, increases system throughput, and provides fair service to users. For instance, star overlay networks [16] and their variations [17] provide a large number of parallel paths, a small graph diameter, scalable lookup service for the peers participating in Peer-to-Peer (P2P) networks and a small degree compared to conventional hypercubic DHTs such as Chord and Kademlia. Existing implementations of hybrid CDN-P2P networks have the following shortcomings that limit their reliability, availability and quality of service.…”

“…As these algorithmic properties are highly desirable for hybrid CDN-P2P networks, we establish the viability of the star overlay networks as an edge network for hybrid CDN-P2P networks to meet their content delivery quality of service requirements. In particular, we simulated the multipath routing algorithm of Karaata et al [16] under a realistic model including the essential aspects that are not considered in [16] for a practical implementation of the algorithm such as buffer requirements of peers, limiting channel capacities, concurrent transmission of multiple content from multiple sources, pipelining/interleaving of multiple messages over the same set of multipaths between two endpoints and message drops. Through our simulation, we established the following.…”

“…P2P overlay networks and multipath routing are presented in Section II providing the required background and terminology. Section III presents a brief overview of the inherently-stabilizing routing algorithm for star P2P overlay networks [16] that is simulated and evaluated in this paper. The network simulation model is described in Section IV.…”