Better data management is crucial to the success of scientific investigations of global change. New modes of research about the Earth, especially the synergistic interactions between observations and models, require m...
详细信息
Better data management is crucial to the success of scientific investigations of global change. New modes of research about the Earth, especially the synergistic interactions between observations and models, require massive amounts of diverse data to be stored, organized, accessed, distributed, visualized, and analyzed. To address technical issues of better data management, participants in Sequoia 2000, a collaborative effort between computer scientists and Earth scientists at several campuses of the University of California and at Digital Equipment Corporation (DEC), apply refinements in computing to specific applications. The software architecture includes layers for a common device interface, the file system, the database management system (DBMS), applications, and the network. Early prototype applications of this software include a global-change data schema, integration of a general circulation model (GCM), remote sensing, and a data system for climate studies. Longer range efforts include transfer protocols for moving elements of the database, controllers for secondary and tertiary storage, distributed file system, and a distributed DBMS.< >
Summary form only given. Optical-storage technology makes use of laser light for recording digital data on rotating-disk media. It is characterized by the combination of high storage density, high data rate, fast acce...
详细信息
Summary form only given. Optical-storage technology makes use of laser light for recording digital data on rotating-disk media. It is characterized by the combination of high storage density, high data rate, fast access time, high reliability, and media removability. The author considers optical storage technology and its application.< >
Most recovery schemes that have been proposed for distributed Shared Memory (DSM) systems.require unnecessarily high checkpointing frequency and checkpoint traffic, which are sensitive to the frequency of interprocess...
详细信息
Most recovery schemes that have been proposed for distributed Shared Memory (DSM) systems.require unnecessarily high checkpointing frequency and checkpoint traffic, which are sensitive to the frequency of interprocess communication in the applications. For message-passing systems. low overhead error recovery based on coordinated checkpointing allows the frequency of checkpointing to be determined only by the reliability requirements of the application. Efficient adaptation of this approach to DSM multicomputers is complicated by the absence of explicit messages in DSM systems. the presence of a shared and partially replicated address space, and the presence of a distributed coherency directory. We present solutions to these issues, and propose an error recovery scheme based on coordinated checkpointing and rollback for DSM multicomputers. Our performance evaluation based on trace-driven simulations indicates that this scheme incurs less checkpoint traffic than recovery schemes previously proposed for DSM systems.< >
Fault tolerant software utilizes redundancy and diversity in an attempt to tolerate software design faults. The two most widely studied approaches to software fault tolerance are called Recovery Blocks (RB) and N-vers...
详细信息
ISBN:
(纸本)078030943X
Fault tolerant software utilizes redundancy and diversity in an attempt to tolerate software design faults. The two most widely studied approaches to software fault tolerance are called Recovery Blocks (RB) and N-version Programming (NVP). Both RB and NVP have been the subject of numerous research efforts and publications. These research efforts primarily address design issues such as independence, implementation issues that arise in distributedsystems. and experimental performance analysis. Very few researchers have addressed the analysis of the reliability of fault tolerant software. In this paper we present fault tree models that can be used for qualitative and quantitative analysis of fault tolerant software. There are several advantages to a simple fault tree model of fault tolerant software, in addition to the intrinsic beauty of simplicity. First, the implications of the conclusions drawn from the model are easier for the reader to understand. Second, the qualitative effects of the input parameters are easier to deduce. third, a reader can develop a model of a similar system and be confident of the results. Finally, and most important, a simple fault tree model of fault tolerant software can more easily be combined with an analysis of the hardware structure on which it executes. This combination will facilitate the integrated analysis of fault tolerant hardware and softwaresystems.
A new reliability model is introduced for selecting the best software fault-tolerant (FT) design. This model uses a task graph technique that allows different candidate FT configurations to be analyzed based on the st...
详细信息
The proceedings contain 26 papers. The special focus in this conference is on Computer Performance Modeling, Measurement and Evaluation. The topics include: Parallel simulation;properties and analysis of queueing netw...
ISBN:
(纸本)9783540572978
The proceedings contain 26 papers. The special focus in this conference is on Computer Performance Modeling, Measurement and Evaluation. The topics include: Parallel simulation;properties and analysis of queueing network models with finite capacities;performance analysis and optimization with the power-series algorithm;multiprocessor and distributed system design;response time distributions in queueing network models;fast simulation of rare events in queueing and reliability models;an inlxoduction to modeling dynamic behavior with time series analysis;issues in trace-driven simulation;maximum entropy analysis of queueing network models;performance modeling using DSPN express;relaxation for massively parallel discrete event simulation;an overview of tes processes and modeling methodology;performance engineering of client-server systems.queueing networks with finite capacities;performance instrumentation techniques for parallel systems.a survey of bottleneck analysis in closed networks of queues;software performance engineering;performance measurement using system monitors;providing quality of service packet switched networks;dependability and performability analysis;architectures and algorithms for digital multimedia on-demand servers;analysis and control of polling systems.modeling and analysis of transaction processing systems.
A new reliability model is introduced for selecting the best software fault-tolerant (FT) design. This model uses a task graph technique that allows different candidate FT configurations to be analyzed based on the st...
详细信息
A new reliability model is introduced for selecting the best software fault-tolerant (FT) design. This model uses a task graph technique that allows different candidate FT configurations to be analyzed based on the structure and organization of different distributed embedded systems.reliability prediction with this approach can be useful for addressing system dependability issues (i.e., fault detection/recovery processes and steady-state availability) in addition to ascertaining fault coverage (i.e., the likelihood of missing and/or false faults). The results of analyzing three different Simplified Unmanned Vehicle System (SUVS) FT configurations are presented. This work is described within the framework of the Conservative and Do-best FT design policies and fits consistent with a software development model for real-time control systems.that was introduced in earlier work by the authors.
Factory communications in the 1990s have all the complexity of full-fledged distributedsystems. While emerging standards such as Fieldbus solve the interconnection problem, in general they do not address the more gen...
详细信息
Factory communications in the 1990s have all the complexity of full-fledged distributedsystems. While emerging standards such as Fieldbus solve the interconnection problem, in general they do not address the more general problem of reliable, transparent communication among cooperating, distributed applications. These new applications are known to require network layer and transparent layer services to achieve reliable end-to-end communication across an arbitrary network topology. The Xpress Transfer Protocol is designed to solve this problem by providing increased functionality and performance in the general area of real-time systems.control.< >
Binary optimization models for the design of distributed, fault-tolerant computing systems.are considered, with a focus on the task allocation and file assignment modeling schema proposed by J. Bannister and K. Trived...
详细信息
暂无评论