A Mechanism for the Causal Ordered Set Representation in Large-Scale Distributed Systems
Résumé
Distributed systems have undergone a very fast evolution these last years. Large-scale distributed systems have become an integral part of everyday life with the development of new large-scale applications, consisting of thousands of computers and supporting millions of users. Examples include global Internet services, cloud computing systems, " big data " analytics platforms, peer-to-peer systems, wireless sensor networks and so on. The recent research addresses questions related to the way one may design, build, operate and maintain large-scale distributed systems. An other question related to such area, is how to represent causal dependencies in such systems in a minimal way. In general, causal dependencies can be established according to the Happened-Before Relation (HBR), which was introduced by Lamport. The HBR is a strict partial order, and therefore, one main problem linked to it is the combinatorial state explosion. The Immediate Dependency Relation (IDR) and the Causal Order Set Abstraction (CAOS) present a solution for such a problem. In this paper, we propose a mechanism which uses the concepts HBR, IDR, CAOS to model a large-scale distributed system execution in the form of the minimal graph (IDR graph) and the compact graph (CAOS graph). This mechanism is implemented in C++. The results of its execution are given here. The resultant causal graphs can be used for different purposes, such as for the design of more efficient algorithms, validation, verification, and/or the debugging of the existing ones, among others.
Origine : Fichiers produits par l'(les) auteur(s)
Loading...