A code design framework for multi-rack distributed storage

Abstract

In practical distributed storage networks, data centres house hundreds of racks, each of which contains several storage nodes. However, the majority of works in distributed storage assume a simple network model with a collection of identical storage nodes with same communication cost between the nodes. In this paper, we consider a more realistic rack model of storage network and present a code design framework for this model. Using our code construction method, node failures within a rack can be repaired locally by survived nodes in the same rack or by the other survived racks when the information content of the same rack is not sufficient to repair the failed nodes.