We are increasingly relying on online services to store, access, share, and disseminate critical information from anywhere and at all times. Such services include email, digital storage, photos, video, health and financial services, etc. With increasing evidence of non-fail-stop failures in practical systems, Byzantine fault tolerant state machine replication technique is becoming increasingly attractive for building highlyreliable services in order to tolerate such failures. However, existing Byzantine fault tolerant techniques fall short of providing high availability, high performance, and long-term data durability guarantees with competitive replication cost. In this dissertation, we present BFT replication techniques that facilitate the design and implementation of such highly-reliable services by providing high availability, high performance and high durability with competitive replication cost (hardware, software, network, management). First, we propose CBASE, a BFT state machine replication architecture that leverages application-level parallelism to improve throughput of the replicated system by identifying and executing independent requests concurrently. Traditional state machine replication based Byzantine fault tolerant (BFT) techniques provide high availability and security but fail to provide high throughput. This limitation stems from the fundamental assumption of generalized state machine replication techniques that all replicas execute requests sequentially in the same total order to ensure consistency across replicas. Our architecture thus provides a general way to exploit application parallelism in order to provide high throughput without compromising correctness. Second, we present Zyzzyva, an efficient BFT agreement protocol that uses speculation to significantly reduce the performance overhead and replication cost of BFT state machine replication. In Zyzzyva, replicas respond to a client’s request without first running an expensive three-phase commit protocol to reach agreement on the order in which the request must be processed. Instead, they optimistically adopt the order proposed by the primary and respond immediately to the client. Replicas can thus become temporarily inconsistent with one another, but clients detect inconsistencies, help correct replicas converge on a single total ordering of requests, and only rely on responses that are consistent with this total order. This approach allows Zyzzyva to reduce replication overheads to near their theoretical minima. Third, we design and implement SafeStore, a distributed storage system designed to maintain long-term data durability despite conventional hardware and software faults, environmental disruptions, and administrative failures caused by human error or malice. The architecture of SafeStore is based on fault isolation, which SafeStore applies aggressively along administrative, physical, and temporal dimensions by spreading data across autonomous storage service providers (SSPs). SafeStore also performs an efficient end-to-end audit of SSPs to detect data loss quickly and improve data durability by reducing MTTR. SafeStore offers durable storage with cost, performance, and availability competitive with traditional storage systems. We evaluate these techniques by implementing BFT replication libraries and further demonstrate the practicality of these approaches by implementing an NFS based replicated file system(CBASE-FS) and a durable storage system (SafeStore-FS). / text

Not available / text

Our research is the first in-depth study in the use of the Micron Automata Processor, a novel re-configurable streaming co-processor which is purpose-built to execute thousands of Non-deterministic Finite Automata (NFA) in parallel. By design, this processor is well-suited to accelerate applications which need to find all occurrences of thousands of complex string-patterns in the input data. We have validated this by implementing two such applications, one from network security and the other from bioinformatics, both of which are significantly faster than their state-of-art counterparts. Our research has also widened the scope of the applications which can be accelerated through this processor by finding ways to quickly program any generic graph into it and then search for hard to find features like maximal-cliques and Hamiltonian paths. These applications and algorithms have yielded valuable design-inputs for next generation of the chip which is currently in design phase. We hope that this work paves the way to the early adoption of this upcoming architecture and to efficient solution of some of the currently computationally challenging problems.

published_or_final_version / Computer Science / Master / Master of Philosophy

This dissertation demonstrates new methods for increasing the performance and scalability of high performance networking technologies for use in clustered computing systems, concentrating on Ethernet/High-Speed networking convergence. The motivation behind the improvement of high performance networking technologies and their importance to the viability of modern data centers is discussed first. It then introduces the concepts of high performance networking in a commercial data center context as well as high performance computing (HPC) and describes some of the most important challenges facing such networks in the future. It reviews current relevant literature and discusses problems that are not yet solved. Through a study of existing high performance networks, the most promising features for future networks are identified. Sockets Direct Protocol (SDP) is shown to have unexpected performance issues for commercial applications, due to inefficiencies in handling large numbers of simultaneous connections. The first SDP over eXtended Reliable Connections implementation is developed to reduce connection management overhead, demonstrating that performance issues are related to protocol overhead at the SDP level. Datagram offloading for IP over InfiniBand (IPoIB) is found to work well. In the first work of its kind, hybrid high-speed/Ethernet networks are shown to resolve the issues of SDP underperformance and demonstrate the potential for hybrid high-speed networking local area Remote Direct Memory Access (RDMA) technologies and Ethernet wide area networking for data centers. Given the promising results from these studies, a set of solutions to enhance performance at the local and wide area network level for Ethernet is introduced, providing a scalable, connectionless, socket-compatible, fully RDMA-capable networking technology, datagram-iWARP. A novel method of performing RDMA Write operations (called RDMA Write-Record) and RDMA Read over unreliable datagrams over Ethernet is designed, implemented and tested. It shows its applicability in scientific and commercial application spaces and is applicable to other verbs-based networking interfaces such as InfiniBand. The newly proposed RDMA methods, both for send/recv and RDMA Write-Record, are supplemented with interfaces for both socket-based applications and Message Passing Interface (MPI) applications. An MPI implementation is adapted to support datagram-iWARP. Both scalability and performance improvements are demonstrated for HPC and commercial applications. / Thesis (Ph.D, Electrical & Computer Engineering) -- Queen's University, 2012-09-25 09:43:55.262

Selenonium cations are electron deficient species in which the central selenium atom is bonded to three carbon chains (aryl or alkyl). Trimethylselenonium iodide was synthesized by reaction of methyllithium with metallic selenium to produce methylselenolithium which was, in turn, reacted with the appropriate alkylbromide. The selenide thus formed was further methylated at the selenium atom with methyl iodide in methanol in the presence of sodium tetraphenylborate. After several recrystallizations the selenonium analytes were characterized by AAS, FT-IR, $ sp1$H-NMR, $ sp{13}$C-NMR, FAB-MS and LAMMA spectroscopic techniques and used as standards for analytical methods development. / The analysis was performed by high performance liquid chromatography with atomic absorption detection. The chromatography on a cynopropyl silica bonded phase was optimized for mobile phase composition by response surface analysis. The resulting surface response plots permitted a differentiation between the mechanisms of action of two mobile phase modifiers: triethylamine and trimethylsulfonium iodide. The improvement in chromatographic efficiency resulted in two to three fold decrease in the limit of detection. An extraction procedure with liquefied phenol was evaluated for the determination, by HPLC-AAS, of traces of selenonium cations in biological samples. The advantages and shortcomings of the HPLC-THG-AAS approach are discussed.

No description available.

Amadori rearrangement product (ARP) of tryptophan with glucose was synthesized according to a published procedure, and its decomposition was studied at two different concentrations and at two temperatures, 110$ sp circ$C and 140$ sp circ$C over a period of 6 hrs. A RP-HPLC system was developed to separate and quantitate the decomposition products of the ARP. The results indicated that, the ARP can decompose to form the following products, hydroxymethylfurfural (HMF), maltol, indole, $ beta$-carbolines (norharman and harman) and tryptophan. Further, using the same analytical method, the following systems were also analyzed for the presence of the above mentioned products (a) D-glucose and D-mannose with tryptophan; (b) D-glucose; and (c) tryptophan. In addition, rate constants and activation energies for the decomposition and formation reaction were calculated. Plausible mechanisms for the formation of the decomposition products are suggested.

In cellular studies of patients with lipid related disorders such as mammary cancers, leukemia, and artheroscierosis, separation of molecular species of oxidized phosphatidylcholine (PC) can be an important assistance in research or diagnosis. Goals of this project were to optimize separation of oxidized and unoxidized PC molecular species in a single HPLC chromatogram followed by in line identification of hydroperoxides. Oxidized egg PC's were produced using UV light exposure in air. Separations were performed on an Ultrasphere ODS column and an Asahipak ODPVA column using a Waters 2695 system with photodiode array. The ODPVA column routinely gave 10 times larger plate numbers. Various mobile phase mixtures (methanol, acetonitrile, water) and gradients were tested. The optimum gradient on our system is (1) 5 minutes, 47 % methanol/40 % acetonitrile/13 water in a linear gradient to (2) 17 minutes, 49 % methanol/40 % acetonitrile/11 % water to (3) 18 minutes, 29 % methanol/60 % acetonitrile/11 % water linearly to (4) 50 minutes, 31 % methanol/60 % acetonitrile/9 % water continued isocratically to 110 minutes. Oxidized hydroperoxides were detected by fluorescence using a post column reaction with diphenyl-1 pyrenylphosphine (DPPP). Both iron (III) and pyridine were tested as catalysts for this reaction. / Department of Chemistry

Using archival analysis and interviews this study examined the career pathways, learning experiences, and athletic experiences of 11 high-performance head hockey coaches who played goal in ice hockey. Guided by the learning situations discussed in Wright, Trudel, and Culver (2007) the interviews revealed four important learning experiences common to all the coaches: coach interactions, books and videotapes, coach clinics and academic education, and experiences related to playing and coaching. Like Werthner and Trudel (2009) the results indicated that certain similarities aside, each coach’s career pathway is idiosyncratic with elite athletic experience being an important, but not imperative, aspect of high-performance coaches’ career development. The findings provide insight into how these individuals acquired their coaching knowledge and provide a more complete picture of the developmental pathways associated with becoming a high-performance head hockey coach.