VICINITY: A Pinch of Randomness Brings out the Structure

Abstract

Overlay networks are central to the operation of large-scale decentralized applications, be it Internet-scale P2P systems deployed in the wild or cloud applications running in a controlled-albeit large-scale-environment. A number of custom solutions exist for individual applications, each employing a tailormade mechanism to build and maintain its specific structure. This paper addresses the role of randomness in developing and maintaining such structures. Taking VICINITY, a generic overlay management framework based on self-organization, we explore tradeoffs between deterministic and probabilistic decision-making for structuring overlays. We come to the conclusion that a pinch of randomness may even be needed in overlay construction, but also that much randomness or randomness alone is not good either.

Nearest Neighbors Graph Construction: Peer Sampling to the Rescue

“…Similarly to KPS and previous gossipbased protocols [6,7,18,24], NNDescent relies on two principles: (i) the assumption that "The neighbor of a neighbor is also likely to be a neighbor" and (ii) a reduced candidate set to limit the number of similarity computations at each iteration.…”

“…In such systems, each peer is connected to a subset of other peers in the network and periodically exchanges some information with one of its neighbors. While such protocols have been initially used to build uniform random topologies [19,21], they have also been applied in the context of several applications to cluster peers according to some specific metric (interest, overlap, etc) to build networks of arbitrary structure [18,24] or to support various applications such as query expansion [7], top-k queries [6] or news recommendation [9]. In such a system, the use of random nodes ensures that connectivity is maintained, each node is responsible to discover its KNN nodes by periodically exchanging neighborhood information with other peers.…”

Atum

“…Vicinity [71] is a protocol for constructing and maintaining an overlay network, which investigates the importance of randomness in large-scale P2P networks. The analysis around this protocol shows that randomness must be complemented with structure (determinism) for effective large-scale P2P networks.…”

Autonomous Multi-dimensional Slicing for Large-Scale Distributed Systems

“…Gossip-based protocols rely on periodic exchange of information between pairs of peers and appropriate nodelocal decisions. They allow implementing a variety of system services based on overlay networks, such as membership management [16], dissemination [7,19], structure and overlays management [15,24], or key-based routing [18,20].…”

“…Another example is that of a system that supports a BitTorrent-like dissemination and download service. The subset of the most stable node could be used for supporting a self-organizing distributed hash table (DHT) [15,20,24], nodes with the largest available bandwidth could be used as helpers for others to download faster [9], while the remaining ones only act as clients.…”