A hierarchical approach for availability and performance analysis of private cloud storage services

摘要

Cloud computing brings new technologies and concepts that support communication services and data storage. Services like OneDrive, Google Drive and DropBox increase data availability and provide new features as synchronization and collaboration. These services require high availability and performance characteristics like high throughput and low probability that a timeout occurs, since it is fundamental to guarantee both business continuity and uninterrupted public services. In this research, we aim at evaluating availability and performance-related metrics for private cloud storage services. A hierarchical model-based strategy is proposed to evaluate distinct metrics by means of the composition of continuous-time Markov chains, reliability block diagrams and stochastic Petri nets. A case study is presented to illustrate the applicability of the proposed models through a cloud storage service hosted in the Eucalyptus platform. We also adopt availability importance index to identify the most critical components in relation to the system availability. Our numerical analyses indicate that, for instance, the adoption of redundant components reduces the probability that timeouts occur and the probability that users are attended due to failures. Furthermore, the results obtained from the stochastic models show that the proposed approach is indeed a good approximation to the measures obtained from the experiments conducted in a real cloud environment.