J. Harshan

Sparsity Exploiting Erasure Coding for Resilient Storage and Efficient I/O Access in Delta Based Versioning Systems

In this work, we study the problem of storing reliably an archive of versioned data. Specifically, we focus on systems where the differences (deltas) between subsequent versions rather than the whole objects are stored - a typical model for storing versioned data. For reliability, we propose erasure encoding techniques that exploit the sparsity of information in the deltas while storing them reliably in a distributed back-end storage system, resulting in improved I/O read performance to retrieve the whole versioned archive. Along with the basic techniques, we propose a few optimization heuristics, and evaluate the techniques efficacy analytically and with numerical simulations.

A USRP implementation of wiretap lattice codes

A wiretap channel models a communication channel between a legitimate sender Alice and a legitimate receiver Bob in the presence of an eavesdropper Eve. Confidentiality between Alice and Bob is obtained using wiretap codes, which exploit the difference between the channels to Bob and to Eve. This paper discusses a first implementation of wiretap lattice codes using USRP (Universal Software Radio Peripheral), which focuses on the channel between Alice and Eve. Benefits of coset encoding for Eves confusion are observed, using different lattice codes in small dimensions, and varying the position of the eavesdropper.

Sparsity exploiting erasure coding for distributed storage of versioned data

In this paper we study the problem of storing reliably an archive of versioned data. Specifically, we focus on systems where the differences (deltas) between subsequent versions rather than the whole objects are stored—a typical model for storing versioned data. For reliability, we propose erasure encoding techniques that exploit the sparsity of information in the deltas while storing them reliably in a distributed back-end storage system, resulting in improved I/O read performance to retrieve the whole versioned archive. Along with the basic techniques, we propose a few optimization heuristics, and evaluate the techniques’ efficacy analytically and with numerical simulations.

DiVers: An erasure code based storage architecture for versioning exploiting sparsity

Abstract 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)xa0mechanisms to deploy the coding technique with arbitrarily varying size of data across versions, and (ii)xa0investigating 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.

On Algebraic Manipulation Detection codes from linear codes and their application to storage systems

Algebraic Manipulation Detection (AMD) codes form a cryptographic primitive designed to detect data corruption of the form of an additive operation in an Abelian group. In this paper, we discuss the applicability of AMD codes to protect erasure code based storage systems from a Byzantine adversary injecting fake data in the distributed storage system. We study a special class of AMD codes which relies on classical linear codes for its construction. We explore the design aspects of such AMD codes namely, (i) understanding its design criteria, (ii) studying the fundamental limits of such codes, to facilitate data integrity, and (iii) present some examples.

Performance of lattice coset codes on Universal Software Radio Peripherals

Abstract We consider an experimental setup of three Universal Software Radio Peripherals (USRPs) that implement a wiretap channel, two USRPs are the legitimate players Alice and Bob, while the third USRP is the eavesdropper, whose position we vary to evaluate information leakage. The experimented channels are close to slow fading channels, and coset coding of lattice constellations is used for transmission, allowing to introduce controlled randomness at the transmitter. Simulation and measurement results show to which extent coset coding can provide confidentiality, as a function of Eve’s position, and the amount of randomness used.

Differential Erasure Codes for Efficient Archival of Versioned Data in Cloud Storage Systems

In this paper, we study the problem of storing an archive of versioned data in a reliable and efficient manner. The proposed technique is relevant in cloud settings, where, because of the huge volume of data to be stored, distributed scale-out storage systems deploying erasure codes for fault tolerance is typical. However existing erasure coding techniques do not leverage redundancy of information across multiple versions of a file. We propose a new technique called differential erasure coding DEC where the differences deltas between subsequent versions are stored rather than the whole objects, akini?źto a typical delta encoding technique. However, unlike delta encoding techniques, DEC opportunistically exploits the sparsity i.e., when the differences between two successive versions have few non-zero entries in the updates to store the deltas using sparse sampling techniques applied with erasure coding. We first show that DEC provides significant savings in the storage size for versioned data whenever the update patterns are characterized by in-place alterations. Subsequently, we propose a practical DEC framework so as to reap storage size benefits against not just in-place alterations but also real-world update patterns such as insertions and deletions that alter the overall data sizes. We conduct experiments with several synthetic and practical workloads to demonstrate that the practical variant of DEC provides significant reductions in storage-overhead.