.png){kind=icon}
.png){kind=icon}
Return
DiVers: An erasure code based storage architecture for versioning exploiting sparsity
.png){kind=icon}
PRE
AI
DOI：10.1016/j.future.2016.01.005.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
We propose a differential versioning based data storage (DiVers) architecture for distributed storage systems, which relies on a novel erasure coding technique that exploits sparsity across versions. The emphasis of this work is to demonstrate how sparsity exploiting codes (SEC), originally designed for I/O optimization, can be extended to significantly reduce storage overhead in a repository of versioned data. In addition to facilitating reduced storage, we address some key reliability aspects for DiVers such as (i) mechanisms to deploy the coding technique with arbitrarily varying size of data across versions, and (ii) investigating the right allocation strategy for the encoded blocks over a network of distributed nodes across different versions so as to achieve the best fault tolerance. We also discuss system issues related to the management of data structures for accessing and manipulating the files over the differential versions. (C) 2016 Elsevier B.V. All rights reserved.
Keywords:
Datacenter networking
Version management
Fault tolerance
Erasure coding
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
F
IF:
6.1
Papers:
6.8K
Citations:
2.3W