Multi-tenant Latency Optimization in Erasure-Coded Storage with Differentiated Services

The effect of coding on content retrieval latency in data center storage system is drawing more and more significant attention these days, and customizing elastic service latency for the tenants is undoubtedly appealing to cloud storage, but it also comes with great technical challenges: due to the lack of analytic latency models for erasure-coded storage, most of the literature is limited to the analysis of average service latency, e.g., [1], [2], having assumptions like homogeneous files, exponential service time distribution [3], fixed erasure codes [4], which is unsuitable for a multi-tenant cloud environment where each tenant has a different latency requirement for accessing files in an erasure-coded, online cloud storage. Optimizing differentiated service delay in an erasure-coded storage system is an open problem. This work considers an erasure-coded storage with multiple tenants and differentiated delay demands, studies two types of service policies, non-preemptive priority queue and weighted queue, quantifying service latency of these policies, propose a novel optimization framework that provides differentiated service latency to meet heterogeneous application requirements in cloud storage.