Answers are grounded in this paper and cite their sources.
Distributed storage systems such as Hadoop File System or Google File System(GFS) ensure data availability and durability using replication. This paper is on the analysis of the efficiency of replication mechanism that the location of the copies of a given file at some server. The of the loads of the nodes of the network is investigated for policies. Three replication mechanisms are tested against simulations the context of a real implementation of a such a system: Random, Least and Power of Choice. The simulations show that some of these policies may lead to quite unbalanced: if \β is the average number of copies per node it turns out, at equilibrium, the load of the nodes may exhibit a high variability. It shown in this paper that a simple variant of a power of choice type has a striking effect on the loads of the nodes: at equilibrium, the of the load of a node has a bounded support, most of nodes have a less than 2\β which is an interesting property for the design of the space of these systems. Mathematical models are introduced and investigated to explain this phenomenon. The analysis of these systems turns out to be quite mainly because of the large dimensionality of the state spaces. Our study relies on probabilistic methods, mean-field analysis, to the asymptotic behavior of an arbitrary node of the network when the number of nodes gets large. An additional ingredient is the use of calculus with marked Poisson point processes to establish some of results.
No takes yet. Share an insight, caveat, or question.
Sun et al. (2017) studied this question.