Thesis (Ph. D.)--State University of New York at Binghamton, Thomas J. Watson School of Engineering and Applied Science, Department of Computer Science, 2009. / Includes bibliographical references.

Thesis (M.S.)--State University of New York at Binghamton, Thomas J. Watson School of Engineering and Applied Science, Department of Computer Science, 2009. / Includes bibliographical references.

Thesis (Ph. D.)--University of Washington, 1996. / Vita. Includes bibliographical references (p. [111]-120).

Thesis (M.S.)--University of Florida, 2004. / Title from title page of source document. Document formatted into pages; contains 85 pages. Includes vita. Includes bibliographical references.

Thesis (Ph.D.) -- Mississippi State University. Department of Computer Science and Engineering. / Title from title screen. Includes bibliographical references.

Thesis (Ph. D.)--University of Washington, 2000. / Vita. Includes bibliographical references (p. 140-150).

Thesis (Ph. D.)--State University of New York at Binghamton, Thomas J. Watson School of Engineering and Applied Science, Department of Systems Science and Industrial Engineering, 2008. / Includes bibliographical references.

Thesis (Ph. D.)--University of Texas at Austin, 2008. / Vita. Includes bibliographical references.

The past decade has witnessed the rapid growth of data in large-scale distributed storage systems. Triplication, a reliability mechanism with 3x storage overhead and adopted by large-scale distributed storage systems, introduces heavy storage cost as data amount in storage systems keep growing. Consequently, erasure codes have been introduced in many storage systems because they can provide a higher storage efficiency and fault tolerance than data replication. However, erasure coding has many performance degradation factors in both I/O and computation operations, resulting in great performance degradation in large-scale erasure-coded storage systems. In this thesis, we investigate how to eliminate some key performance issues in I/O and computation operations for applying erasure coding in large-scale storage systems. We also propose a prototype named ESetStore to improve the recovery performance of erasure-coded storage systems. We introduce our studies as follows. First, we study the encoding and decoding performance of the erasure coding, which can be a key bottleneck with the state-of-the-art disk I/O throughput and network bandwidth. We propose a graphics processing unit (GPU)-based implementation of erasure coding named G-CRS, which employs the Cauchy Reed-Solomon (CRS) code, to improve the encoding and decoding performance. To maximize the coding performance of G-CRS by fully utilizing the GPU computational power, we designed and implemented a set of optimization strategies. Our evaluation results demonstrated that G-CRS is 10 times faster than most of the other coding libraries. Second, we investigate the performance degradation introduced by intensive I/O operations in recovery for large-scale erasure-coded storage systems. To improve the recovery performance, we propose a data placement algorithm named ESet. We define a configurable parameter named overlapping factor for system administrators to easily achieve desirable recovery I/O parallelism. Our simulation results show that ESet can significantly improve the data recovery performance without violating the reliability requirement by distributing data and code blocks across different failure domains. Third, we take a look at the performance of applying coding techniques to in-memory storage. A reliable in-memory cache for key-value stores named R-Memcached is designed and proposed. This work can be served as a prelude of applying erasure coding to in-memory metadata storage. R-Memcached exploits coding techniques to achieve reliability, and can tolerate up to two node failures. Our experimental results show that R-Memcached can maintain very good latency and throughput performance even during the period of node failures. At last, we design and implement a prototype named ESetStore for erasure-coded storage systems. The ESetStore integrates our data placement algorithm ESet to bring fast data recovery for storage systems.

Memory is a part of cognition. It is essential for an individual to function normally in society. It encompasses an individual's lifetime experience, thus defining his identity. This thesis develops the concept of a machine-based personal memory manager which captures and manages an individual's day-to-day external memories. Rather than accumulating large amounts of data which has to be mined for useful memories, the machine-based memory manager automatically organizes memories as they are captured to enable their quick retrieval and use. The main functions of the machine-based memory manager envisioned in this thesis are the support and the augmentation of an individual's biological memory system. In the thesis, a model for a machine-based memory manager is developed. A visual programming environment, which can be used to build context aware applications as well as a proof-of-concept machine-based memory manager, is conceptualized and implemented. An experimental machine-based memory manager is implemented and evaluated. The model describes a machine-based memory manager which manages an individual's external memories by context. It addresses the management of external memories which accumulate over long periods of time by proposing a context aware file system which automatically organizes external memories by context. It describes how personal memory management can be facilitated by machine using six entities (life streams, memory producers, memory consumers, a memory manager, memory fragments and context descriptors) and the processes in which these entities participate (memory capture, memory encoding and decoding, memory decoding and retrieval). The visual programming environment represents a development tool which contains facilities that support context aware application programming. For example, it provides facilities which enable the definition and use of virtual sensors. It enables rapid programming with a focus on component re-use and dynamic composition of applications through a visual interface. The experimental machine-based memory manager serves as an example implementation of the machine-based memory manager which is described by the model developed in this thesis. The hardware used in its implementation consists of widely available components such as a camera, microphone and sub-notebook computer which are assembled in the form of a wearable computer. The software is constructed using the visual programming environment developed in this thesis. It contains multiple sensor drivers, context interpreters, a context aware file system as well as memory retrieval and presentation interfaces. The evaluation of the machine-based memory manager shows that it is possible to create a machine which monitors the states of an individual and his environment, and manages his external memories, thus supporting and augmenting his biological memory.