We propose a new approach for constructing P2P networks based on a dynamic decomposition of a continuous space into cells corresponding to processors. We demonstrate the power of these design rules by suggesting two new architectures, one for DHT (Distributed Hash Table) and the other for dynamic expander networks. The DHT network, which we call Distance Halving, allows logarithmic routing and load, while preserving constant degrees. Our second construction builds a network that is guaranteed to be an expander. The resulting topologies are simple to maintain and implement. Their simplicity makes it easy to modify and add protocols. We show it is possible to reduce the dilation and the load of the DHT with a small increase of the degree. We present a provably good protocol for relieving hot spots and a construction with high fault tolerance. Finally we show that, using our approach, it is possible to construct any family of constant degree graphs in a dynamic environment, though with worst parameters. Therefore we expect that more distributed data structures could be designed and implemented in a dynamic environment.

Abstract not found

This paper presents the architecture of PIER , an Internetscale query engine we have been building over the last three years. PIER is the first general-purpose relational query processor targeted at a peer-to-peer (p2p) architecture of thousands or millions of participating nodes on the Internet. It supports massively distributed, database-style dataflows for snapshot and continuous queries. It is intended to serve as a building block for a diverse set of Internet-scale informationcentric applications, particularly those that tap into the standardized data readily available on networked machines, including packet headers, system logs, and file names

A pervasive requirement of distributed systems is to deal with churn — change in the set of participating nodes due to joins, graceful leaves, and failures. A high churn rate can increase costs or decrease service quality. This paper studies how to reduce churn by selecting which subset of a set of available nodes to use. First, we provide a comparison of the performance of a range of different node selection strategies in five real-world traces. Among our findings is that the simple strategy of picking a uniform-random replacement whenever a node fails performs surprisingly well. We explain its performance through analysis in a stochastic model. Second, we show that a class of strategies, which we call “Preference List ” strategies, arise commonly as a result of optimizing for a metric other than churn, and produce high churn relative to more randomized strategies under realistic node failure patterns. Using this insight, we demonstrate and explain differences in performance for designs that incorporate varying degrees of randomization. We give examples from a variety of protocols, including anycast, overlay multicast, and distributed hash tables. In many cases, simply adding some randomization can go a long way towards reducing churn.

Despite the abundance of frequently changing information, the Web lacks a publish-subscribe interface for delivering updates to clients. The use of naïve polling for detecting updates leads to poor performance and limited scalability as clients do not detect updates quickly and servers face high loads imposed by active polling. This paper describes a novel publish-subscribe system for the Web called Corona, which provides high performance and scalability through optimal resource allocation. Users register interest in Web pages through existing instant messaging services. Corona monitors the subscribed Web pages, detects updates efficiently by allocating polling load among cooperating peers, and disseminates updates quickly to users. Allocation of resources for polling is driven by a distributed optimization engine that achieves the best update performance without exceeding load limits on content servers. Large-scale simulations and measurements from PlanetLab deployment demonstrate that Corona achieves orders of magnitude improvement in update performance at a modest cost. 1

Abstract. Chord is a distributed hash table (DHT) that requires only O(logn) links per node and performs searches with latency and message cost O(logn), where n is the number of peers in the network. Chord assumes all nodes behave according to protocol. We give a variant of Chord which is robust with high probability for any time period during which: 1) there are always at least z total peers in the network for some integer z; 2) there are no more than (1/4 − ǫ)z insertion events for Byzantine peers for a fixed ǫ> 0; and 3) the number of insertion and deletion events for correct peers is no more than z k for some tunable parameter k. We assume there is an computationally unbounded adversary controlling the Byzantine peers and that the IP-addresses of all the Byzantine peers and the locations where they join the network are carefully selected by this adversary. Our notion of robustness is rather strong in that we not only guarantee that searches can be performed but also that we can enforce any set of “proper behavior ” such as contributing new material, etc. In comparison to Chord, the resources required by this new variant are only a polylogarithmic factor greater in communication, messaging, and linking costs. 1

Abstract — Existing solutions to achieve load balancing in DHTs incur a high overhead either in terms of routing state or in terms of load movement generated by nodes arriving or departing the system. In this paper, we propose a set of general techniques and use them to develop a protocol based on Chord, called Y0, that achieves load balancing with minimal overhead under the typical assumption that the load is uniformly distributed in the identifier space. In particular, we prove that Y0 can achieve near-optimal load balancing, while moving little load to maintain the balance, and increasing the size of the routing tables by at most a constant factor. Using extensive simulations based on real-world and synthetic capacity distributions, we show that Y0 reduces the load imbalance of Chord from O(log n) to a less than 4 without increasing the number of links that a node needs to maintain. In addition, we study the effect of heterogeneity on both DHTs, demonstrating significantly reduced average route length as node capacities become increasingly heterogeneous. For a real-word distribution of node capacities, the route length in Y0 is asymptotically less than half the route length in the case of a homogeneous system. Index Terms — System design, Simulations I.

Peer-to-peer systems can be used to form a low-latency decentralized data delivery system. Structured peer-to-peer systems provide both low latency and excellent load balance with uniform query and data distributions. Under the more common skewed access distributions, however, individual nodes are easily overloaded, resulting in poor global performance and lost messages. This paper describes a lightweight, adaptive, and system-neutral replication protocol, calledLAR, that maintains low access latencies and good load balance even under highly skewed demand. We apply LAR to Chord and show that it has lower overhead and better performance than existing replication strategies. 1.

Structured peer-to-peer hash tables provide decentralization, self-organization, failure-resilience, and good worst-case lookup performance for applications, but suffer from high latencies (O( )) in the average case. Such high latencies prohibit them from being used in many relevant, demanding applications such as DNS. In this paper, we present a proactive replication framework that can achieve O( ) lookup performance for common Zipf-like query distributions. This framework is based around a closed-form solution that achieves O( ) lookup performance with low storage requirements, bandwidth overhead and network load. Simulations show that this replication framework can realistically achieve good latencies, outperform passive caching, and adapt efficiently to sudden changes in object popularity, also known as flash crowds. This framework provides a feasible substrate for high-performance, low-latency applications, such as peer-to-peer domain name service.

Abstract—The Knowledge Grid needs to operate with a scalable platform to provide large-scale intelligent services. A key function of such a platform is to efficiently support various complex queries in a dynamic large-scale network environment. This paper proposes a platform to support index-based path queries by incorporating a semantic overlay with an underlying structured P2P network that provides object location and management services. Various distributed indexing structures can be dynamically formed by publishing semantic objects as indexing nodes. Queries are forwarded along the chains of semantic object pointers to search for objects. We investigate the deployment of a scalable distributed trie index for broadcast queries on key strings, propose a decentralized load balancing method for solving the problem of uneven load distribution incurred by heterogeneity of loads and node capacities and by the distributed trie index, and give an approach for improving the availability of the semantic overlay and its trie index. Experiments demonstrate the scalability of the proposed platform. Index Terms—Peer-to-peer, semantic overlay, knowledge grid, path query, distributed trie index, load balancing, replication.