Ali Ghodsi

The essence of P2P: a reference architecture for overlay networks

The success of the P2P idea has created a huge diversity of approaches, among which overlay networks, for example, Gnutella, Kazaa, Chord, Pastry, Tapestry, P-Grid, or DKS, have received specific attention from both developers and researchers. A wide variety of algorithms, data structures, and architectures have been proposed. The terminologies and abstractions used, however, have become quite inconsistent since the P2P paradigm has attracted people from many different communities, e.g., networking, databases, distributed systems, graph theory, complexity theory, biology, etc. In this paper we propose a reference model for overlay networks which is capable of modeling different approaches in this domain in a generic manner. It is intended to allow researchers and users to assess the properties of concrete systems, to establish a common vocabulary for scientific discussion, to facilitate the qualitative comparison of the systems, and to serve as the basis for defining a standardized API to make overlay networks interoperable.

A framework for structured peer-to-peer overlay networks

Structured peer-to-peer overlay networks have recently emerged as good candidate infrastructure for building novel large-scale and robust Internet applications in which participating peers share computing resources as equals. In the past three year, various structured peer-to-peer overlay networks have been proposed, and probably more are to come. We present a framework for understanding, analyzing and designing structured peer-to-peer overlay networks. The main objective of the paper is to provide practical guidelines for the design of structured overlay networks by identifying a fundamental element in the construction of overlay networks: the embedding of k–ary trees. Then, a number of effective techniques for maintaining these overlay networks are discussed. The proposed framework has been effective in the development of the DKS system, whose preliminary design appears in [2].

A Practical Approach to Network Size Estimation for Structured Overlays

Structured overlay networks have recently received much attention due to their self-* properties under dynamic and decentralized settings. The number of nodes in an overlay fluctuates all the time due to churn. Since knowledge of the size of the overlay is a core requirement for many systems, estimating the size in a decentralized manner is a challenge taken up by recent research activities. Gossip-based Aggregation has been shown to give accurate estimates for the network size, but previous work done is highly sensitive to node failures. In this paper, we present a gossip-based aggregation-style network size estimation algorithm. We discuss shortcomings of existing aggregation-based size estimation algorithms, and give a solution that is highly robust to node failures and is adaptive to network delays. We examine our solution in various scenarios to demonstrate its effectiveness.

Key-based consistency and availability in structured overlay networks

Structured Overlay Networks (SONs) provide a promising platform for high performance applications since they are scalable, fault-tolerant and self-managing. SONs provide lookup services that map keys to nodes that can be used as processing or storage resources. In SONs, lookups for a key may return inconsistent results. Consequently, it is difficult to provide consistent data services on top of SONs that build on key-based search. In this paper, we study the frequency of occurrence of inconsistent lookups. We show that the affect of lookup inconsistencies can be reduced by using node responsibilities. We present our results as a trade-off between consistency and availability of keys.

Dealing with network partitions in structured overlay networks

Structured overlay networks form a major class of peer-to-peer systems, which are touted for their abilities to scale, tolerate failures, and self-manage. Any long-lived Internet-scale distributed system is destined to face network partitions. Although the problem of network partitions and mergers is highly related to fault-tolerance and self-management in large-scale systems, it has hardly been studied in the context of structured peer-to-peer systems. These systems have mainly been studied under churn (frequent joins/failures), which as a side effect solves the problem of network partitions, as it is similar to massive node failures. Yet, the crucial aspect of network mergers has been ignored. In fact, it has been claimed that ring-based structured overlay networks, which constitute the majority of the structured overlays, are intrinsically ill-suited for merging rings. In this paper, we present an algorithm for merging multiple similar ring-based overlays when the underlying network merges. We examine the solution in dynamic conditions, showing how our solution is resilient to churn during the merger, something widely believed to be difficult or impossible. We evaluate the algorithm for various scenarios and show that even when falsely detecting a merger, the algorithm quickly terminates and does not clutter the network with many messages. The algorithm is flexible as the tradeoff between message complexity and time complexity can be adjusted by a parameter.

Handling Network Partitions and Mergers in Structured Overlay Networks

Structured overlay networks form a major class of peer- to-peer systems, which are touted for their abilities to scale, tolerate failures, and self-manage. Any long-lived Internet-scale distributed system is destined to face network partitions. Although the problem of network partitions and mergers is highly related to fault-tolerance and self-management in large-scale systems, it has hardly been studied in the context of structured peer-to-peer systems. These systems have mainly been studied under churn (frequent joins/failures), which as a side effect solves the problem of network partitions, as it is similar to massive node failures. Yet, the crucial aspect of network mergers has been ignored. In fact, it has been claimed that ring-based structured overlay networks, which constitute the majority of the structured overlays, are intrinsically ill-suited for merging rings. In this paper, we present an algorithm for merging multiple similar ring-based overlays when the underlying network merges. We examine the solution in dynamic conditions, showing how our solution is resilient to churn dur- ng the merger, something widely believed to be difficult or mpossible. We evaluate the algorithm for various scenar- os and show that even when falsely detecting a merger, the algorithm quickly terminates and does not clutter the network with many messages. The algorithm is flexible as the tradeoff between message complexity and time complexity can be adjusted by a parameter.

On Consistency Of Data In Structured Overlay Networks

Data consistency can be violated in Distributed Hash Tables (DHTs) due to inconsistent lookups. In this paper, we identify the events leading to inconsistent lookups and inconsistent responsibilities for a key. We find the inaccuracy of failure detectors as the main reason for inconsistencies. By simulations with inaccurate failure detectors, we study the probability of reaching a system configuration which may lead to inconsistent data. We analyze majority-based algorithms for operations on replicated data. To ensure that concurrent operations do not violate consistency, they have to use non-disjoint sets of replicas. We analytically derive the probability of concurrent operations including disjoint replica sets. By combining the simulation and analytical results, we show that the probability for a violation of data consistency is negligibly low for majority-based algorithms in DHTs.

Gossiping over storage systems is practical

Gossip-based mechanisms are touted for their simplicity, limited resource usage, robustness to failures, and tunable system behavior. These qualities make gossiping an ideal mechanism for storage systems that are responsible for maintaining and updating data in a mist of failures and limited resources (e.g., intermittent network connectivity, limited bandwidth, constrained communication range, or limited battery power). We focus on persistent storage systems that, unlike mere caches, are responsible for both the durability and the consistency of data. Examples of such systems may be encountered in many different environments, in particular: wide-area networks (constrained by limited bandwidth), wireless sensor networks (characterized by limited resources), and mobile ad hoc networks (suffering from intermittent connectivity). In this paper, we demonstrate the qualities of gossiping in these three respective environments.

Implementing dynamic querying search in k-ary DHT-based overlays

Distributed Hash Tables (DHTs) provide scalable mechanisms for implementing resource discovery services in structured Peer-to-Peer (P2P) networks. However, DHT-based lookups do not support some types of queries which are fundamental in several classes of applications. A way to support arbitrary queries in structured P2P networks is implementing unstructured search techniques on top of DHT-based overlays. This approach has been exploited in the design of DQDHT, a P2P search algorithm that combines the dynamic querying (DQ) technique used in unstructured networks with an algorithm for efficient broadcast over a DHT. Similarly to DQ, DQ-DHT dynamically adapts the search extent on the basis of the desired number of results and the popularity of the resource to be found. Differently from DQ, DQ-DHT exploits the structural constraints of the DHT to avoid message duplications. The original DQ-DHT algorithm has been implemented using Chord as basic overlay. In this paper we focus on extending DQ-DHT to work in k-ary DHT-based overlays. In a k-ary DHT, broadcast takes only O(logkN) hops using O(logkN) pointers per node. We exploit this “k-ary principle” in DQ-DHT to improve the search time with respect to the original Chord-based implementation. This paper describes the implementation of DQ-DHT over a k-ary DHT and analyzes its performance in terms of search time and generated number of messages in different configuration scenarios.

Exploiting the synergy between gossiping and structured overlays

In this position paper we argue for exploiting the synergy between gossip-based algorithms and structured overlay networks (SON). These two strands of research have both aimed at building fault-tolerant, dynamic, self-managing, and large-scale distributed systems. Despite the common goals, the two areas have, however, been relatively isolated. We focus on three problem domains where there is an untapped potential of using gossiping combined with SONs. We argue for applying gossip-based membership for ring-based SONs---such as Chord and Bamboo---to make them handle partition mergers and loopy networks. We argue that small world SONs---such as Accordion and Mercury---are specifically well-suited for gossip-based membership management. The benefits would be better graph-theoretic properties. Finally, we argue that gossip-based algorithms could use the overlay constructed by SONs. For example, many unreliable broadcast algorithms for SONs could be augmented with anti-entropy protocols. Similarly, gossip-based aggregation could be used in SONs for network size estimation and load-balancing purposes.