Capacity and Security of Heterogeneous Distributed Storage Systems
arXiv:1211.0415 · doi:10.1109/JSAC.2013.131210
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.
7 pages, 2 figures
References in corpus (6)
- Optimal Exact-Regenerating Codes for Distributed Storage at the MSR and MBR Points via a Product-Matrix Construction
- Distributed Storage Allocations
- Fractional Repetition Codes for Repair in Distributed Storage Systems
- A Survey on Network Codes for Distributed Storage
- Cooperative Regenerating Codes
- Non-homogeneous distributed storage systems
Cited by in corpus (13)
- The Storage vs Repair-Bandwidth Trade-off for Clustered Storage Systems
- Codes between MBR and MSR Points with Exact Repair Property
- On Weak Dress Codes for Cloud Storage
- Coded Caching with Distributed Storage
- Non-homogeneous Two-Rack Model for Distributed Storage Systems
- A Connection Between Locally Repairable Codes and Exact Regenerating Codes
- Rack-Aware Regenerating Codes for Data Centers
- Storage and Repair Bandwidth Tradeoff for Distributed Storage Systems with Clusters and Separate Nodes
- Information-theoretically Secure Erasure Codes for Distributed Storage
- On Heterogeneous Regenerating Codes and Capacity of Distributed Storage Systems
- Capacity of Distributed Storage Systems with Clusters and Separate Nodes
- Secure Clustered Distributed Storage Against Eavesdroppers
- An Overflow Problem in Network Coding for Secure Cloud Storage