By Topic

Proceedings of IEEE International Computer Performance and Dependability Symposium

4-6 Sept. 1996

Filter Results

Displaying Results 1 - 25 of 41
  • Proceedings of IEEE International Computer Performance and Dependability Symposium

    Publication Year: 1996
    Request permission for commercial reuse | PDF file iconPDF (613 KB)
    Freely Available from IEEE
  • Author index

    Publication Year: 1996
    Request permission for commercial reuse | PDF file iconPDF (74 KB)
    Freely Available from IEEE
  • Bounding asymptotic dependability and performance measures

    Publication Year: 1996, Page(s):176 - 186
    Cited by:  Papers (3)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (696 KB)

    One of the major drawbacks of Markov models is the size of the generated state space. Often its high value (sometimes infinite) makes the numerical analysis impossible to perform. A possible approach to deal with this problem is to bound the measures of interest. In recent years, some methods have been proposed in this direction, mainly for stationary dependability measures. In this paper, we prop... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • First passage times in fluid models with an application to two priority fluid systems

    Publication Year: 1996, Page(s):166 - 175
    Cited by:  Papers (4)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (684 KB)

    In this paper we analyze the first passage time in a fluid flow model where the input and output rates are controlled by a finite state Continuous Time Markov Chain (CTMC). We derive explicit expressions for the Laplace Transform of the joint distribution of the first time the buffer becomes empty and the state of the CTMC at that time. We discuss both infinite and finite buffer cases. We illustra... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Dependability of fault-tolerant systems-explicit modeling of the interactions between hardware and software components

    Publication Year: 1996, Page(s):252 - 261
    Cited by:  Papers (7)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (980 KB)

    This paper addresses the dependability modeling of hardware and software fault-tolerant systems taking into account explicitly the interactions between the various components. It presents a framework for modeling these interactions based on Generalized Stochastic Petri Nets (GSPNs). The modeling approach is modular: the behavior of each component and each interaction is represented by its own GSPN... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Application of threshold partitioning of sparse matrices to Markov chains

    Publication Year: 1996, Page(s):158 - 165
    Cited by:  Papers (7)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (608 KB)

    Three algorithms which permute and partition a sparse matrix are presented as tools for the improved solution of Markov chain problems. One is the algorithm PABLO [SIAM J. Sci. Stat. Computing, vol.11, pp.811-823, 1990] while the other two are modifications of it. In the new algorithms, in addition to the location of the nonzeros, the values of the entries are taken into account. The permuted matr... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Conjoint simulation-a technique for the combined performance and dependability analysis of large-scale computer systems

    Publication Year: 1996, Page(s):68 - 77
    Cited by:  Papers (3)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1108 KB)

    In this paper we propose an approach which seamlessly integrates two modeling techniques to facilitate the simulation and analysis of performance and dependability of large-scale parallel computer systems. The approach, called Conjoint Simulation, combines object-oriented, process-based simulation with Petri net modeling. The approach splits a system into a performance model and a dependability mo... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • The DIN method: a new approach for measuring and rating data processing performance

    Publication Year: 1996, Page(s):200 - 209
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (772 KB)

    When data processing systems changed from “single user, single task” type to “multi user, multi task” type the internal performance measures used traditionally became less suitable. The necessity arose for developing measures for system performance to replace those for component performance. However, soundly based performance definitions and a measurement method, applicable... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Performance and availability evaluation of NUMA architectures

    Publication Year: 1996, Page(s):271 - 280
    Cited by:  Papers (3)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (636 KB)

    A new approximation technique is proposed for obtaining analytic estimates of the performance of computing systems exhibiting non-uniform memory access (NUMA) times, where components are subject to failure and repair. The technique uses a multi-chain mean-value analysis together with a service time scaling factor derived to correct for the non-exponential (deterministic) service times found in mos... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Computation of the distribution of accumulated reward with Fluid Stochastic Petri-Nets

    Publication Year: 1996, Page(s):90 - 95
    Cited by:  Papers (5)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (584 KB)

    We describe the recently introduced Fluid Stochastic Petri-Nets as a means of computing the distribution of the accumulated rate reward in a GSPN. In practice, it is the expected value of a reward which is computed, a quantity which is dependent solely on the solution of the underlying Markov chain. Until now, the instantaneous reward rates have been a function of the GSPN marking only, and the Ma... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Steady state solution of MRSPN with mixed preemption policies

    Publication Year: 1996, Page(s):106 - 115
    Cited by:  Papers (8)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (828 KB)

    Markov Regenerative Stochastic Petri Nets (MRSPN) have been recently recognized as a valuable tool to model systems with non-exponential timed activities. The usual assumption in the implementation of such models is that at most a single non-exponential transition, with associated enabling memory policy, can be enabled in each marking. More recently, new memory policies have been studied in order ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • SIMPLE: a universal tool box for event trace analysis

    Publication Year: 1996
    Cited by:  Patents (7)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (120 KB)

    The event trace analysis system SIMPLE allows the evaluation of arbitrarily formatted event traces. SIMPLE is designed as a software package which comprises independent tools that are all based on a new kind of event trace access: the trace format is described in a trace description language (TDL) and evaluation tools access the event trace through a standardized problem-oriented event trace inter... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • QNAUT: approximately analyzing networks of PH|PH|1|K queues

    Publication Year: 1996
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (92 KB)

    With QNAUT we can perform the (approximate) analysis of possibly large, open networks of PH|PH|1 and PH|PH|1|K queues. Since up till now there are no exact means available to study such queueing networks (QNs), the approach supported by QNAUT is currently the best alternative. Starting point of our approach is the analysis of large open QNs as proposed by W. Whitt (known as QNA) in which large QNs... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A structured approach to redundant disk array implementation

    Publication Year: 1996, Page(s):11 - 20
    Cited by:  Papers (3)  |  Patents (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (784 KB)

    Error recovery in redundant disk arrays is typically performed in an ad hoc fashion, requiring architecture-specific code which limits extensibility and is difficult to verify. In this paper, we describe a technique for automating the execution of redundant disk array operations, including recovery from errors, independent of array architecture. Our approach employs a graphical representation of a... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Synchronisation delay in hardware fault-tolerance techniques

    Publication Year: 1996, Page(s):240 - 249
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (880 KB)

    This work deals with analytical modelling of synchronisation delay experienced in multiprocessing systems which execute redundant software to improve dependability figures. We propose a stochastic model based on a queuing network approach of system behaviour. We derive a bounded approximation of the distribution function of synchronisation delay by applying the matrix-geometric technique to analys... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • On queueing with customer impatience until the beginning of service

    Publication Year: 1996, Page(s):150 - 157
    Cited by:  Papers (4)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (496 KB)

    We study queueing systems where customers have strict deadlines until the beginning of their service. An analytic method is given for the analysis of a class of such queues, namely, M(n)/M/m/FCFS+G and M(n)/M/m/FCFS/K+G models. These are queues with state-dependent Poisson arrival process, exponential service times, multiple servers, FCFS service discipline, infinite or finite capacity, and genera... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Overview of UltraSAN

    Publication Year: 1996
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (92 KB)

    UltraSAN is a software package for model-based evaluation of systems represented as stochastic activity networks (SANs). SANs incorporate features of both stochastic Petri nets and queueing models, where parameters in a model such as case distributions, activity times, state transition rules, and reward variables can be marking dependent. Users may build SAN models using an X-Windows based user in... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • MultiKron: performance measurement instrumentation

    Publication Year: 1996
    Cited by:  Patents (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (88 KB)

    The focus of our instrumentation work at NIST is to provide hardware support in obtaining performance measurement data of parallel computers, as well as uniprocessors, with tolerable perturbation to both the executing processes and the architecture on which they are executing. Tracing events and counting are two basic concepts of performance measurement-both should be controlled from within the co... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Performance visualization: 2-D, 3-D, and beyond

    Publication Year: 1996, Page(s):188 - 197
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (2016 KB)

    During the past ten years, performance data visualization techniques have evolved from static, two-dimensional graphics to dynamic graphics and immersive virtual environments. We sketch the domain of applicability for each visualization technique using analysis of input/output behavior and WWW traffic as example problem domains. With this background, we describe experiences with virtual environmen... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A non-homogeneous Markov software reliability model with imperfect repair

    Publication Year: 1996, Page(s):262 - 270
    Cited by:  Papers (6)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (616 KB)

    This paper reviews existing non-homogeneous Poisson process (NHPP) software reliability models and their limitations, and proposes a more powerful non-homogeneous Markov model for the fault detection/removal problem. In addition, this non-homogeneous Markov model allows for the possibility of a finite time to repair a fault and for imperfections in the repair process. The proposed scheme provides ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • On-line recovery for rediscovered software problems

    Publication Year: 1996, Page(s):78 - 87
    Cited by:  Papers (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (864 KB)

    This paper discusses a method that can allow a system to avoid or recover from the exercise of certain known faults at runtime and thus make certain software upgrades unnecessary. The method uses the knowledge of the characteristic symptoms of a software fault and the appropriate recovery action for the fault to detect and recover from the future exercise of the fault. An analysis of field data sh... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Performance analysis tool for cache-based real-time systems with preemptions

    Publication Year: 1996, Page(s):210 - 218
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (676 KB)

    Dependable real-time systems are essential to time-critical applications. The systems that run these applications require high degrees of performance and predictability. Although memory caching has long been known as a means of increasing system performance, it is typically unpredictable in nature. This paper presents a technique of using preferred preemption points to increase the predictability ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Using time to improve the performance of coordinated checkpointing

    Publication Year: 1996, Page(s):282 - 291
    Cited by:  Papers (15)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (840 KB)

    This paper describes and evaluates a coordinated checkpoint protocol that uses time to eliminate several performance overheads that are present in traditional protocols. The time-based protocol does not have to exchange coordination messages, does not need to add information to the processes' messages, and only accesses stable storage when checkpoints are saved. This protocol uses a simple initial... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • The effects of LAN-like input traffic on a switch access node

    Publication Year: 1996, Page(s):96 - 105
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (736 KB)

    This paper addresses the modeling and analysis of a switching network access node. This is an area of importance due to forthcoming high-speed ATM backbone networks and the need to transmit data for current and future network applications. The nature of these applications must be considered when designing an access node to a switching network. A traffic arrival process for the network and characte... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Exact and approximate analysis of ATM cell loss correlation

    Publication Year: 1996, Page(s):120 - 129
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (816 KB)

    Cell loss behavior is analyzed for an ATM switch with homogeneous Markov sources. While prior work in this regard has focused mainly on measures such as the steady-state loss probability and conditional loss probability, we consider a more refined measure, namely the probability distribution of a cell loss period. Evaluation is based on a discrete-time, finite-state Markov process where cell arriv... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.