Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “software fault tolerance”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 253 records · Page 14

Software safety

Software safety and its relationship to other qualities are discussed. It is shown that standard reliability and fault tolerance techniques will not solve the safety problem for the present. A new attitude requires: looking at what you do NOT want software to do along with what you want it to do; and assuming things will go wrong. New procedures and changes to entire software development process are necessary: special software safety analysis techniques are needed; and design techniques, especially eliminating complexity, can be very helpful.

Leveson, Nancy↗

Advanced information processing system: Local system services

The Advanced Information Processing System (AIPS) is a multi-computer architecture composed of hardware and software building blocks that can be configured to meet a broad range of application requirements. The hardware building blocks are fault-tolerant, general-purpose computers, fault-and damage-tolerant networks (both computer and input/output), and interfaces between the networks and the computers. The software building blocks are the major software functions: local system services, input/output, system services, inter-computer system services, and the system manager. The foundation of the local system services is an operating system with the functions required for a traditional real-time multi-tasking computer, such as task scheduling, inter-task communication, memory management, interrupt handling, and time maintenance. Resting on this foundation are the redundancy management functions necessary in a redundant computer and the status reporting functions required for an operator interface. The functional requirements, functional design and detailed specifications for all the local system services are documented.

Burkhardt, Laura↗

Design and validation of fault-tolerant flight systems

Flight systems must be validated to show that they are consistent with the requirements of their intended applications. While high reliability is difficult to validate, the additional complexity of fault tolerance further compounds the validation problem. The objective of NASA’s research is to develop a methodology for designing validatable fault-tolerant systems. Under the design-for-validation philosophy, emphasis is placed on developing validation methods that can be incorporated into the design process right from the start and design methods and guidance which, while incorporating fault tolerance, can assure validatability. This paper examines the statistical issues of validating highly reliable, fault tolerant system. There are many problems associated with traditional methods of designing and validating these potentially complex hardware and software systems. Useful design-for-validation methods, which include structured specification and design methodologies, mathematical proof techniques, analytical modeling, simulation and emulation, and physical testing, are discussed. Important design issues associated with fault tolerance are presented along with the related validation concerns which must be addressed. Experience has shown that synchronization and Byzantine resilience must accompany fault tolerance. Other design attributes associated with fault tolerance may be used by a designer on the basis of cost, weight, performance, and validation considerations.

Computer systems↗

Affinity-aware checkpoint restart

Current checkpointing techniques employed to overcome faults for HPC applications result in inferior application performance after restart from a checkpoint for a number of applications. This is due to a lack of page and core affinity awareness of the checkpoint/restart (C/R) mechanism, i.e., application tasks originally pinned to cores may be restarted on different cores, and in case of non-uniform memory architectures (NUMA), quite common today, memory pages associated with tasks on a NUMA node may be associated with a different NUMA node after restart. Here, this work contributes a novel design technique for C/R mechanisms to preserve task-to-core maps and NUMA node specific page affinities across restarts. Experimental results with BLCR, a C/R mechanism, enhanced with affinity awareness demonstrate significant performance benefits of 37%-73% for the NAS Parallel Benchmark codes and 6-12% for NAMD with negligible overheads instead of up to nearly four times longer an execution times without affinity-aware restarts on 16 cores.

97 MATHEMATICS AND COMPUTING↗

Airborne Advanced Reconfigurable Computer System (ARCS)

A digital computer subsystem fault-tolerant concept was defined, and the potential benefits and costs of such a subsystem were assessed when used as the central element of a new transport's flight control system. The derived advanced reconfigurable computer system (ARCS) is a triple-redundant computer subsystem that automatically reconfigures, under multiple fault conditions, from triplex to duplex to simplex operation, with redundancy recovery if the fault condition is transient. The study included criteria development covering factors at the aircraft's operation level that would influence the design of a fault-tolerant system for commercial airline use. A new reliability analysis tool was developed for evaluating redundant, fault-tolerant system availability and survivability; and a stringent digital system software design methodology was used to achieve design/implementation visibility.

Bjurman, B. E.↗

Advanced Communication and Networking Technologies for Mars Exploration

Next-generation Mars communications networks will provide communications and navigation services to a wide variety of Mars science vehicles including: spacecraft that are arriving at Mars, spacecraft that are entering and descending in the Mars atmosphere, scientific orbiter spacecraft, spacecraft that return Mars samples to Earth, landers, rovers, aerobots, airplanes, and sensing pods. In the current architecture plans, the communication services will be provided using capabilities deployed on the science vehicles as well as dedicated communication satellites that will together make up the Mars network. This network will evolve as additional vehicles arrive, depart or end their useful missions. Cost savings and increased reliability will result from the ability to share communication services between missions. This paper discusses the basic architecture that is needed to support the Mars Communications Network part of NASA's Space Science Enterprise (SSE) communications architecture. The network may use various networking technologies such as those employed in the terrestrial Internet, as well as special purpose deep-space protocols to move data and commands autonomously between vehicles, at disparate Mars vicinity sites (on the surface or in near-Mars space) and between Mars vehicles and earthbound users. The architecture of the spacecraft on-board local communications is being reconsidered in light of these new networking requirements. The trend towards increasingly autonomous operation of the spacecraft is aimed at reducing the dependence on resource scheduling provided by Earth-based operators and increasing system fault tolerance. However, these benefits will result in increased communication and software development requirements. As a result, the envisioned Mars communications infrastructure requires both hardware and protocol technology advancements. This paper will describe a number of the critical technology needs and some of the ongoing research activities.

Bhasin, Kul↗

Motion-Based System Identification and Fault Detection and Isolation Technologies for Thruster Controlled Spacecraft

By analyzing the motions of a thruster-controlled spacecraft, it is possible to provide on-line (1) thruster fault detection and isolation (FDI), and (2) vehicle mass- and thruster-property identification (ID). Technologies developed recently at NASA Ames have significantly improved the speed and accuracy of these ID and FDI capabilities, making them feasible for application to a broad class of spacecraft. Since these technologies use existing sensors, the improved system robustness and performance that comes with the thruster fault tolerance and system ID can be achieved through a software-only implementation. This contrasts with the added cost, mass, and hardware complexity commonly required by FDI. Originally developed in partnership with NASA - Johnson Space Center to provide thruster FDI capability for the X-38 during re-entry, these technologies are most recently being applied to the MIT SPHERES experimental spacecraft to fly on the International Space Station in 2004. The model-based FDI uses a maximum-likelihood calculation at its core, while the ID is based upon recursive least squares estimation. Flight test results from the SPHERES implementation, as flown aboard the NASA KC-1 35A 0-g simulator aircraft in November 2003 are presented.

Wilson, Edward↗

Advanced Information Processing System (AIPS)-based fault tolerant avionics architecture for launch vehicles

An avionics architecture for the advanced launch system (ALS) that uses validated hardware and software building blocks developed under the advanced information processing system program is presented. The AIPS for ALS architecture defined is preliminary, and reliability requirements can be met by the AIPS hardware and software building blocks that are built using the state-of-the-art technology available in the 1992-93 time frame. The level of detail in the architecture definition reflects the level of detail available in the ALS requirements. As the avionics requirements are refined, the architecture can also be refined and defined in greater detail with the help of analysis and simulation tools. A useful methodology is demonstrated for investigating the impact of the avionics suite to the recurring cost of the ALS. It is shown that allowing the vehicle to launch with selected detected failures can potentially reduce the recurring launch costs. A comparative analysis shows that validated fault-tolerant avionics built out of Class B parts can result in lower life-cycle-cost in comparison to simplex avionics built out of Class S parts or other redundant architectures.

Lala, Jaynarayan H.↗

A Runtime Environment for Supporting Research in Resilient HPC System Software & Tools

The high-performance computing (HPC) community continues to increase the size and complexity of hardware platforms that support advanced scientific workloads. The runtime environment (RTE) is a crucial layer in the software stack for these large-scale systems. The RTE manages the interface between the operating system and the application running in parallel on the machine. The deployment of applications and tools on large-scale HPC computing systems requires the RTE to manage process creation in a scalable manner, support sparse connectivity, and provide fault tolerance. We have developed a new RTE that provides a basis for building distributed execution environments and developing tools for HPC to aid research in system software and resilience. This paper describes the software architecture of the Scalable runTime Component Infrastructure (STCI), which is intended to provide a complete infrastructure for scalable start-up and management of many processes in large-scale HPC systems. We highlight features of the current implementation, which is provided as a system library that allows developers to easily use and integrate STCI in their tools and/or applications. The motivation for this work has been to support ongoing research activities in fault-tolerance for large-scale systems. We discuss the advantages of the modular framework employed and describe two use cases that demonstrate its capabilities: (i) an alternate runtime for a Message Passing Interface (MPI) stack, and (ii) a distributed control and communication substrate for a fault-injection tool.

Computer Science↗

An overview of the Hadoop/MapReduce/HBase framework and its current applications in bioinformatics

Bioinformatics researchers are increasingly confronted with analysis of ultra large-scale data sets, a problem that will only increase at an alarming rate in coming years. Recent developments in open source software, that is, the Hadoop project and associated software, provide a foundation for scaling to petabyte scale data warehouses on Linux clusters, providing fault-tolerant parallelized analysis on such data using a programming style named MapReduce. An overview is given of the current usage within the bioinformatics community of Hadoop, a top-level Apache Software Foundation project, and of associated open source software projects. The concepts behind Hadoop and the associated HBase project are defined, and current bioinformatics software that employ Hadoop is described. The focus is on next-generation sequencing, as the leading application area to date.

43 PARTICLE ACCELERATORS↗

RAMP: A fault tolerant distributed microcomputer structure for aircraft navigation and control

RAMP consists of distributed sets of parallel computers partioned on the basis of software and packaging constraints. To minimize hardware and software complexity, the processors operate asynchronously. It was shown that through the design of asymptotically stable control laws, data errors due to the asynchronism were minimized. It was further shown that by designing control laws with this property and making minor hardware modifications to the RAMP modules, the system became inherently tolerant to intermittent faults. A laboratory version of RAMP was constructed and is described in the paper along with the experimental results.

Dunn, W. R.↗

The embedded software life cycle - An expanded view

Six common issues that are encountered in the development of software for embedded computer systems are discussed from the perspective of their interrelationships with the development process and/or the system itself. Particular attention is given to concurrent hardware/software development, prototyping, the inaccessibility of the operational system, fault tolerance, the long life cycle, and inheritance. It is noted that the life cycle for embedded software must include elements beyond simply the specification and implementation of the target software.

Larman, Brian T.↗

Analytical sensor redundancy assessment

The rationale and mechanization of sensor fault tolerance based on analytical redundancy principles are described. The concept involves the substitution of software procedures, such as an observer algorithm, to supplant additional hardware components. The observer synthesizes values of sensor states in lieu of their direct measurement. Such information can then be used, for example, to determine which of two disagreeing sensors is more correct, thus enhancing sensor fault survivability. Here a stability augmentation system is used as an example application, with required modifications being made to a quadruplex digital flight control system. The impact on software structure and the resultant revalidation effort are illustrated as well. Also, the use of an observer algorithm for wind gust filtering of the angle-of-attack sensor signal is presented.

Mulcare, D. B.↗

Advanced information processing system

Design and performance details of the advanced information processing system (AIPS) for fault and damage tolerant data processing on aircraft and spacecraft are presented. AIPS comprises several computers distributed throughout the vehicle and linked by a damage tolerant data bus. Most I/O functions are available to all the computers, which run in a TDMA mode. Each computer performs separate specific tasks in normal operation and assumes other tasks in degraded modes. Redundant software assures that all fault monitoring, logging and reporting are automated, together with control functions. Redundant duplex links and damage-spread limitation provide the fault tolerance. Details of an advanced design of a laboratory-scale proof-of-concept system are described, including functional operations.

Lala, J. H.↗

A Tunable, Software-based DRAM Error Detection and Correction Library for HPC

Proposed exascale systems will present a number of considerable resiliency challenges. In particular, DRAM soft-errors, or bit-flips, are expected to greatly increase due to the increased memory density of these systems. Current hardware-based fault-tolerance methods will be unsuitable for addressing the expected soft error frequency rate. As a result, additional software will be needed to address this challenge. In this paper we introduce LIBSDC, a tunable, transparent silent data corruption detection and correction library for HPC applications. LIBSDC provides comprehensive SDC protection for program memory by implementing on-demand page integrity verification. Experimental benchmarks with Mantevo HPCCG show that once tuned, LIBSDC is able to achieve SDC protection with 50\% overhead of resources, less than the 100\% needed for double modular redundancy.

99 GENERAL AND MISCELLANEOUS↗

Codesign Challenges for Exascale Systems: Performance, Power and Reliability

The complexity of large-scale parallel systems necessitates the simultaneous optimization of multiple hardware and software components in order to achieve goals in performance, energy efficiency, and fault tolerance. Using tools such as performance modeling that enable exploration of design alternatives prior to implementation, we demonstrate the benefits of a co-design methodology for optimizing extreme-scale systems on the path to Exascale systems and workloads.

Kerbyson, Darren J.↗

Matrix Algebra for GPU and Multicore Architectures (MAGMA) for Large Petascale Systems

The goal of the MAGMA project is to create a new generation of linear algebra libraries that achieve the fastest possible time to an accurate solution on hybrid Multicore+GPU-based systems, using all the processing power that future high-end systems can make available within given energy constraints. Our efforts at the University of Tennessee achieved the goals set in all of the five areas identified in the proposal: 1. Communication optimal algorithms; 2. Autotuning for GPU and hybrid processors; 3. Scheduling and memory management techniques for heterogeneity and scale; 4. Fault tolerance and robustness for large scale systems; 5. Building energy efficiency into software foundations. The University of Tennessee’s main contributions, as proposed, were the research and software development of new algorithms for hybrid multi/many-core CPUs and GPUs, as related to two-sided factorizations and complete eigenproblem solvers, hybrid BLAS, and energy efficiency for dense, as well as sparse, operations. Furthermore, as proposed, we investigated and experimented with various techniques targeting the five main areas outlined.

97 MATHEMATICS AND COMPUTING↗

Space station data system analysis/architecture study. Task 2: Options development, DR-5. Volume 2: Design options

The primary objective of Task 2 is the development of an information base that will support the conduct of trade studies and provide sufficient data to make key design/programmatic decisions. This includes: (1) the establishment of option categories that are most likely to influence Space Station Data System (SSDS) definition; (2) the identification of preferred options in each category; and (3) the characterization of these options with respect to performance attributes, constraints, cost and risk. This volume contains the options development for the design category. This category comprises alternative structures, configurations and techniques that can be used to develop designs that are responsive to the SSDS requirements. The specific areas discussed are software, including data base management and distributed operating systems; system architecture, including fault tolerance and system growth/automation/autonomy and system interfaces; time management; and system security/privacy. Also discussed are space communications and local area networking.

Source record↗