Abstract. In this position paper, we present an efficient algorithm for performing a broadcast operation with minimal cost in structured DHTbased P2P networks. In a system of N nodes, a broadcast message originating at an arbitrary node reaches all other nodes after exactly N − 1 messages. We emphasize the perception of a class of DHT systems as a form of distributed k-ary search and we take advantage of that perception in constructing a spanning tree that is utilized for efficient broadcasting. We consider broadcasting as a basic service that adds to existing DHTs the ability to search using arbitrary queries as well as dissiminate/collect global information.

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

Structured peer-to-peer systems rely on replication as a basic means to provide fault-tolerance in presence of high churn. Most select replicas using either multiple hash functions, successor-lists, or leaf-sets. We show that all three alternatives have limitations. We present and provide full algorithmic specification for a generic replication scheme called symmetric replication which only needs O(1) message for every join and leave operation to maintain any replication degree. The scheme is applicable to all existing structured peer-to-peer systems, and can be implemented on-top of any DHT. The scheme has been implemented in our DKS system, and is used to do load-balancing, end-to-end faulttolerance, and to increase the security by using distributed voting. We outline an extension to the scheme, implemented in DKS, which adds routing proximity to reduce latencies. The scheme is particularly suitable for use with erasure codes, as it can be used to fetch a random subset of the replicas for decoding. 1 Introduction Research on structured peer-to-peer systems have produced systems which have strong performance in presence of dynamism. To cope with the dynamism, these systems rely on replication as a basic means to achieve robustness and faulttolerance. Most existing structured peer-to-peer systems either use multiple hash functions, successor-lists, or leaf-sets for choosing replicas. Contribution. We analyze using multiple hash functions, successor-lists, and leaf-sets, and point out their disadvantages. Thereafter, we propose a new replication scheme, called symmetric replication, which we have implemented and added to the DKS system[1]. We provide full algorithmic specification of our scheme, something which we have not found for any other replication schemes for structured peer-to-peer systems. The advantages of symmetric replication This work was funded by the European project EVERGROW, the Vinnova project GES3 in Sweden.

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].

No abstract

No abstract

We propose a snap-stabilizing synchronization technique, called the Neighborhood Synchronizer[Formula: see text] that synchronizes nodes with their neighbors in a tree network. The [Formula: see text] scheme has optimal memory requirement — only one bit per processor. [Formula: see text] is snap-stabilizing [11], meaning that it always behaves according to its specification. The proposed synchronizer being snap-stabilizing is optimal in terms of stabilization time. We show an application of the synchronizer by designing an efficient broadcast algorithm [Formula: see text] in tree networks. [Formula: see text] is also snap-stabilizing and needs only 2h + 2m - 1 rounds to broadcast m messages, where h is the height of the tree.

Structured peer-to-peer systems have emerged as infrastructures for resource sharing in large-scale, distributed, and dynamic environments. One challenge in these systems is to efficiently maintain routing information in the presence of nodes joining, leaving, and failing. Many systems use costly periodic stabilization protocols to ensure that the routing information is up-to-date.In this paper, we present a novel technique called correctionon-change, which identifies and notifies all nodes that have outdated routing information as a result of a node joining, leaving, or failing. Effective failure handling is simplified as the detection of a failure triggers a correction-on-change which updates all the nodes that have a pointer to the failed node. The resulting system has increased robustness as nodes with stale routing information are immediately updated.We proof the correctness of the algorithms and evaluate its performance by means of simulation. Experimental results show that for the same amount of maintenance bandwidth correctionon-change makes the system by far more robust when compared to periodic stabilization. Moreover, compared to adaptive stabilization which adjusts its frequency to the dynamism in the system, correction-on-change gives the same performance but with considerably less maintenance bandwidth. As correction-onchange immediately updates incorrect routing entries the average lookup length is maintained close to the theoretical average in the presence of high dynamism. We show how the technique can be applied to our DKS system as well as the Chord system. 1 We note that term correction-on-change was independently introduced in [1]. 2 The number of joins, leaves and failures.