Evaluation de la fiabilité d’une table de hachage distribuée construite dans un plan hyperbolique

Abstract

HAL is a multi-disciplinary open access archive for the deposit and dissemination of scientific research documents, whether they are published or not. The documents may come from teaching and research institutions in France or abroad, or from public or private research centers. L'archive ouverte pluridisciplinaire HAL, est destinée au dépôt et à la diffusion de documents scientifiques de niveau recherche, publiés ou non, émanant des établissements d'enseignement et de recherche français ou étrangers, des laboratoires publics ou privés. ABSTRACT. A distributed hash table needs to route requests in a scalable way. Although several solutions do exist, they often require nodes to connect to each others by following a specific topology and to maintain routing tables. We propose a greedy routing algorithm based on virtual coordinates taken from the hyperbolic plane for building a distributed hash table while letting nodes connect to any others as they wish and without maintaining any routing table. In this paper, we use this algorithm to define a new scalable and reliable distributed hash table system. We provide a scalability analysis and we evaluate its performance and efficiency by carrying out simulations including other existing solutions. Results show that our system brings more flexibility to the nodes while still being scalable and reliable in presence of churn.MOTS-CLÉS : plan hyperbolique, routage glouton, table de hachage distribuée.

Untitled

“…The maintenance of the routing tables used to store information on the evolution of a network is very important unrealistic in a distributed environment, the substitution of DHTs by the creation of virtual networks over the initial networks, allow to reduce the size of the table in each node while considerably increasing the efficiency search algorithm [6]. The construction technique of the overlay remains the same and takes place in three steps regardless of the DHT topology [11]:…”

“…Our prototype is built from the DHT [6] starting point of our research and MapReduce. In our approach, we propose a distributed platform based on a DHT model built on an overlaying network without imposing a particular topology just like the major DHTs proposed in 3.5, but using several master nodes defined by a virtual address, as described below.…”

“…It is a simple and scalable faulttolerant data processing environment that allows its users to process massive distributed and large-scale data to extract new knowledge. Recent studies have shown the limitations of MapReduce [5] and have proposed DHTs [6], [7] as solutions for incidents that could impact the digital world. As part of this work, we present our architecture inspired by [6] to which we will add some properties of digital imaging [8] for better data management and we will end with an intuitive comparison of our model with existing models.…”

“…Recent studies have shown the limitations of MapReduce [5] and have proposed DHTs [6], [7] as solutions for incidents that could impact the digital world. As part of this work, we present our architecture inspired by [6] to which we will add some properties of digital imaging [8] for better data management and we will end with an intuitive comparison of our model with existing models. Our future work will focus on a hybrid DHT -MapReduce architecture that will exploit the limitations of MapReduce and the performance of our DHT and an analysis of the simulation results of our model and existing models.…”

A Survey on Secure and Resilient Session Schemes: Technical Comparison and Assessment

“…However, HIP introduces a rendezvous mechanism in order to address this simultaneous mobility issue. Unlike previous mobility methods, SEMOS proposes a new mobility scheme based on identifiers provided by a DHT infrastructure [43][44][45]. Each SEMOS host is identified separately by a name and an address defined as coordinates taken from the hyperbolic plane.…”