Capacity and Security of Heterogeneous Distributed Storage Systems

TL;DR

This paper analyzes the capacity and security of heterogeneous distributed storage systems, providing bounds based on node resources and examining the impact of node compromise on secrecy capacity.

Contribution

It introduces bounds on capacity and secrecy capacity for heterogeneous systems, extending understanding beyond homogeneous models.

Findings

Symmetric repair maximizes capacity in homogeneous systems

Bounds depend on average node resources or detailed node characteristics

Secrecy capacity bounds account for potential node compromises

Abstract

We study the capacity of heterogeneous distributed storage systems under repair dynamics. Examples of these systems include peer-to-peer storage clouds, wireless, and Internet caching systems. Nodes in a heterogeneous system can have different storage capacities and different repair bandwidths. We give lower and upper bounds on the system capacity. These bounds depend on either the average resources per node, or on a detailed knowledge of the node characteristics. Moreover, we study the case in which nodes may be compromised by an eavesdropper, and give bounds on the system secrecy capacity. One implication of our results is that symmetric repair maximizes the capacity of a homogeneous system, which justifies the model widely used in the literature.