不同任务粒度下校验式IP-SWAN系统的性能评价模型

在不同的任务粒度下,RAID5结构的 IP-SWAN 系统的请求数据流动有很大的不同。在详细分析了校验式IP-SWAN 系统在读任务、大数据写任务和小数据写任务下的数据流程的基础上,建立了 IP-SWAN 系统的闭合排队网络模型,研究了在不同任务类型和粒度下系统各个部件服务需求的计算方法,并采用 MVA 分析法在理论上对 IP-SWAN 系统的吞吐量进行了计算。实验测试结果表明,理论模型的数值计算结果与实验结果基本一致,能够反映实际系统性能的变化趋势。     

On the accuracy of two analytical models for evaluating the performance of Gigabit Ethernet hosts

In this paper we develop and assess the accuracy of two analytical models that capture the behavior of network hosts when subjected to heavy load such as that of Gigabit Ethernet. The first analytical model is based on Markov processes and queuing theory, and the second is a pure Markov process. In order to validate the models and assess their accuracy, two different numerical examples are presented. The two numerical examples use system parameters that are realistic and appropriate for modern hardware. Both analytical models give closed-form solutions that facilitate the study of a number of important system performance metrics. These metrics include throughput, latency, stability condition, CPU utilizations of interrupt handling and protocol processing, and CPU availability for user applications. The two models give mathematically equivalent closed-form solutions for all metrics except for latency. To address latency, we compare the results of both models with the results of a discrete-event simulation. The latency accuracy of the two models is assessed relative to simulation in terms of differences and percentage errors. The paper shows that the second model is more accurate.     

Stochastic models for performance analysis of multistate flexible manufacturing cells

Performance analysis of flexible manufacturing cells (FMCs) can help companies find the pros and cons of production processes. However, the emphasis has been on issues like cell formation, layout design and scheduling optimization. Little seems to have been done to assess the reliability of an FMC. In this paper, we develop the stochastic models for the performance analysis mainly on the reliability of two different FMCs configured from a set of teaching intelligent flexible manufacturing system (TIFMS). The closed form solutions of probabilities of system states are obtained. Then, utilization rate of equipment in the cell and productivities of the two FMCs as the performance indexes are calculated and optimized. Compared to simulation methods, the closed form solutions make calculations of the performance indexes faster and more accurate. When random variables in the stochastic models are assumed to follow non-exponential distributions, the effects of them on the performance indexes are discussed. The objective of this paper is to fill up the gap that the closed form solutions are difficult to obtain as the number of machine tool increases. Another objective is to optimize the performance indexes to help engineers better evaluate the performance of FMC. Numerical analysis cases are used to illustrate the proposed stochastic models.     

A practical approach for performance-driven UML modelling of handheld devices - A case study

In this article, we present a performance engineering enhanced modelling methodology for designing embedded devices and describe the experiences we have gained in applying this methodology during the design of a DVB-H enabled handheld device. The methodology uses UML 2.0 to model the system following a strict separation of architectural and behavioural aspects of the system. For this purpose we employ the new composite structure diagram and show its advantages over already established approaches. This methodology specially aims on an easy application by non performance experts. From the model, a multiclass queueing network is generated for the analysis of the system performance. The configuration of hardware resources and resource demands is done using the standard SPT Profile which is extended where necessary. This makes queueing theory accessible to system designers even if they are not familiar with the underlying mathematics. In this way the acceptance of developers to use performance engineering in their daily work is increased. Special attention has been put on an easy evaluation of design alternatives. We describe our implementation and its seamless integration into a UML 2.0 CASE tool.     

A compression-gathering technique for improving the performance of ISO 11898 networks

ISO 11898 (CAN) networks suffer from serious limitations on both the maximum network extension and the allowable bit rate because of the particular arbitration technique they adopt.

In this paper, a modification of the basic ISO 11898 protocol is described which combines the content compression and data gathering techniques and provides high performance services for periodic data exchanges and message transmissions.

The new protocol yields, on the average, a 10-times performance improvement over conventional CAN without worsening neither the responsiveness nor the bus length, and also features a satisfactory degree of compatibility with the original standard protocol.     

Strong consistency of infinitesimal perturbation analysis for tandem queueing networks

Strong consistency of infinitesimal perturbation analysis for the sojourn times in a class of tandem queueing networks is proved. Service times at the queues are correlated, and they are affine functions of the variable parameters. Differentiability of the average sojourn times is not assumed, but proved. The analysis is not based on assumptions of regenerative cycles of the networks but on stability and ergodicity of the queueing processes involved. The proof of strong consistency is based on a set of abstract conditions, described in terms of properties of the sample performance functions. These conditions are first shown to be sufficient for strong consistency, and then their validity for the networks in question is proved.Research supported in part by the NSF under grants Nos. ECS85-15449 and CDR-8803012, under ONR contract nos. N00014-90-K-1093 and N00014-89-J-1023, and under Army contract no. DAAL-03-83-K-0171. This author is now with the Department of Manufacturing Engineering, Boston University, Boston, MA 02215.     

A multi-class queuing network analysis methodology for improving hospital emergency department performance

This paper derives an open queuing network model of an emergency department (ED) design intended to increase the capacity of an ED to treat patients. The methodology captures hospital-specific differences in patient acuity mix, arrival patterns and volumes, and efficiencies of processes in a single common computational model. A spreadsheet implementation of the resulting queuing equations is used by managers, in real time, to size ED areas using waiting time and overflow probability as quality of service targets. Non-homogeneous arrival patterns, non-exponential service time distributions, and multiple patient types are all incorporated. The methodology has been applied to a fleet of hospitals for validation. Results from one of them are used to demonstrate the methodology.     

Methodology for predicting performance of distributed and parallel systems

This paper describes an accurate and efficient method to model and predict the performance of distributed/parallel systems. Various performance measures, such as the expected user response time, the system throughput and the average server utilization, can be easily estimated using this method. The methodology is based on known product form queueing network methods, with some additional approximations. The method is illustrated by evaluating performance of a multi-client multi-server distributed system. A system model is constructed and mapped to a probabilistic queueing network model which is used to predict its behavior. The effects of user think time and various design parameters on the performance of the system are investigated by both the analytical method and computer simulation. The accuracy of the former is verified. The methodology is applied to identify the bottleneck server and to establish proper balance between clients and servers in distributed/parallel systems.     

Moments of accumulated reward and completion time in Markovian models with application to unreliable manufacturing systems

Performance evaluation models are used by companies to design, adapt, manage and control their production systems. In the literature, most of the effort has been dedicated to the development of efficient methodologies to estimate the first moment performance measures of production systems, such as the expected production rate, the buffer levels and the mean completion time. However, there is industrial evidence that the higher moments of the production output may drastically impact on the capability of managing the system operations, causing the observed system performance to be highly different from what expected. This paper presents a methodology to analyze the cumulated output and the lot completion time moments of Markovian reward models. Both the discrete and continuous time cases are considered. The technique is applied to unreliable manufacturing systems characterized by general Markovian structures. Numerical results show how the theory developed in this paper can be applied to analyse the dependency of the output variability and the service level on the system parameters. Moreover, they highlight previously uninvestigated features of the system behavior that are useful while operating the system in practical settings.     

Contention-based performance evaluation of multidimensional range search in peer-to-peer networks

Performance evaluation of peer-to-peer search techniques has hitherto been based on simple performance metrics, such as message hop counts and total network traffic, mostly disregarding the inherently concurrent nature of peer-to-peer networks, where contention may arise. This paper is concerned with quantifying the effects of contention in P2P networks, focusing on networks for multidimensional range search. We evaluate peer-to-peer networks derived from recently proposed works, introducing two novel metrics related to concurrency and contention, namely responsiveness and throughput. Our results highlight the impact of contention on these networks, and demonstrate that some studied networks do not scale in the presence of contention. Also, our results indicate that certain P2P network properties believed to be desirable (e.g. even data distribution or uniform peer access) may not be as critical as previously believed.     

Markov-chain model and algorithmic procedure for the performance analysis of closed cyclic queues

This paper presents a model and an algorithmic procedure to analyze closed cyclic queues that are subject to blocking. We consider the first two moments of the processing time and present the fitting of phase-type distributions such that the number of phases and transitions is minimal. Using phase-type distributions, we enable the analysis of queueing systems with processing times with any coefficient of variation. We model the closed cyclic queues subject to blocking as continuous-time Markov chains. The implementation procedure covers the state-space generation and the determination of the infinitesimal generator matrix. Apart from rounding errors, we obtain exact results for the queueing model this way. The results are useful as reference values for the output of approximate approaches. Further, the algorithmic procedure enables a repeated analysis of different configuration alternatives as needed in optimization procedures. Though the method is very fast for small cyclic queues, it takes a long computation time for larger systems. Furthermore, the size of the queueing model to be analyzed is restricted due to the limited working memory with its present-day capacity. In a numerical study, the computation times for different configurations are investigated, limits in the size of the applicable queueing model are given, and numerical results of the performance measures are provided.     

Admission control mechanism and performance analysis based on stochastic automata networks formalism

IEEE 802.16 has been designed to support QoS (Quality of Service) in Wireless broadband Metropolitan Networks (WMAN), and specifically in the access networks. To achieve this, the IEEE 802.16.e amendment introduces the service differentiation by five service classes (UGS, ertPS, rtPS, nrtPS and BE). To maintain the QoS of active connections and to avoid any congestion in the network, an Admission Control (AC) is defined. AC aims to accept or reject a new connection according to the negotiated parameters and the availability of resources in the network. This mechanism is not standardized and let to the operators. We tackle this point, by proposing in this study a new Admission Control (AC) that improves the QoS of BE traffic by avoiding a strict bandwidth assignment of other traffics (rtPS and nrtPS) as is defined in major previous studies. The proposed mechanism is based on token bucket for rtPS, nrtPS and BE traffics in order to reduce lightly the number of accepted connections and to improve considerably the number of accepted BE connections. To evaluate the performance of the proposed scheme, we use PEPS (Performance Evaluation of Parallel Systems) which is a powerful tool based on models which can be described with Stochastic Automata Networks (SAN). PEPS can solve complex models with a large state space and with many synchronized events. Therefore, we show that this tool is suitable for wireless network, and specifically for the proposed scheme, toward numerical results we show as we expected that our proposed AC outperform the classical one by reducing lightly the performance of other service classes.     

Analysing the performance of an automated pathology specimen handling system

This paper determines the performance of a pathology specimen handling system currently under development that performs two fundamental functions, sample tube sorting and sample tube aliquoting. In order to do this a novel capacity model and a simulation model have been developed to analyse the performance of the machine. A capacity model and a simulation model are necessary in order to measure the efficiency of the conveyor system as a means of transferring pucks and tubes between modules as each is insufficient on its own. Furthermore strategies for controlling the machine and eliminating deadlocks are also developed in order to optimise the machine performance and to make it robust. From numerical investigations the best number of pucks and the best puck queue sizes are determined in order to maximise throughput. The results show that a complex relationship exists between the number of pucks, the puck queue sizes and the primary tube arrivals and keeping these components in balance is essential in maintaining system performance.     

A combined queueing network and stochastic Petri-net approach for evaluating the performability of fault-tolerant computer systems

In this paper the performability analysis of fault-tolerant computer systems using a hierarchical decomposition technique is presented. A special class of queueing network (QN) models, the so-called BCMP [4], and generalized stochastic Petri nets (GSPN) [1] which are often used to separately model performance and reliability respectively, have been combined in order to preserve the best modelling features of both.

A conceptual model is decomposed into GSPN and BCMP submodels, which are solved in isolation. Then, the remaining GSPN portion of the model is aggregated with flow-equivalents of BCMP models, in order to compute performability measures. The substitutes of BCMP models are presented by means of simple GSPN constructs, thereby preserving the 1st and 2nd moments of the throughput. A simple example of a data communication system where failed transmissions are corrected, is presented.     

Model-driven monitoring support for the multi-view performance analysis of parallel embedded applications

This paper describes an approach to carry out performance analysis of parallel embedded applications. The approach is based on measurement, but in addition, the idea of driving the measurement process (application instrumentation and monitoring) by a behavioral model is introduced. Using this model, highly comprehensible performance information can be collected. The whole approach is based on this behavioral model, one instrumentation method and two tools, one for monitoring and the other for visualization and analysis. Each of these is briefly described, and the steps to carry out performance analysis using them are clearly defined. They are explained by means of a case study. Finally, one method to evaluate the intrusiveness of the monitoring approach is proposed, and the intrusiveness results for the case study are presented.     

Performance impacts of autocorrelated flows in multi-tiered systems

This paper presents an analysis of the performance effects of burstiness in multi-tiered systems. We introduce a compact characterization of burstiness based on autocorrelation that can be used in capacity planning, performance prediction, and admission control. We show that if autocorrelation exists either in the arrival or the service process of any of the tiers in a multi-tiered system, then autocorrelation propagates to all tiers of the system. We also observe the surprising result that in spite of the fact that the bottleneck resource in the system is far from saturation and that the measured throughput and utilizations of other resources are also modest, user response times are very high. When autocorrelation is not considered, this underutilization of resources falsely indicates that the system can sustain higher capacities.

We examine the behavior of a small queuing system that helps us understand this counter-intuitive behavior and quantify the performance degradation that originates from autocorrelated flows. We present a case study in an experimental multi-tiered Internet server and devise a model to capture the observed behavior. Our evaluation indicates that the model is in excellent agreement with experimental results and captures the propagation of autocorrelation in the multi-tiered system and resulting performance trends. Finally, we analyze an admission control algorithm that takes autocorrelation into account and improves performance by reducing the long tail of the response time distribution.     

A unified view of product-form approximation techniques for general closed queueing networks

Two major approximate techniques have been proposed for the analysis of general closed queueing networks, namely the aggregation method and Marie's method. The idea of the aggregation technique is to replace a subsystem (a subnetwork) by a flow equivalent single-server with load-dependent service rates. The parameters of the equivalent server are obtained by analyzing the subsystem in isolation as a closed system with different populations. The idea of Marie's method is also to replace a subsystem by an equivalent exponential service station with load-dependent service rates. However, in this case, the parameters of the equivalent server are obtained by analyzing the subsystem in isolation under a load-dependent Poisson arrival process. Moreover, in Marie's case, the procedure is iterative.

In this paper we provide a general and unified view of these two methods. The contributions of this paper are the following. We first show that their common principle is to partition the network into a set of subsystems and then to define an equivalent product-form network. To each subsystem is associated a load-dependent exponential station in the equivalent network. We define a set of rules in order to partition any general closed network with various features such as general service time distributions, pupulation constraints, finite buffers, state-dependent routing. We then show that the aggregation method and Marie's method are two ways of obtaining the parameters of the equivalent network associated with a given partition. Finally, we provide a discussion pertaining to the comparison of the two methods with respect to their accuracy and computational complexity.     

基于网络模拟的多媒体网络性能评价方法

计算机模拟是多媒体网络性能评价的一种重要手段。该文在分析多媒体网络特点及其性能评价指标的基础上,着重讨论了运用计算机模拟技术对多媒体网络进行性能评价的方法。还根据讨论结果完成了一个模拟实验,对一个特定多媒体网络在不同多媒体业务下的一些性能指标进行了分析,并根据分析结果,给出了该性能指标的性能空间。     

A performance model for analysis of heterogeneous multi-cluster systems

This paper addresses the problem of performance modeling for large-scale heterogeneous distributed systems with emphases on multi-cluster computing systems. Since the overall performance of distributed systems is often depends on the effectiveness of its communication network, the study of the interconnection networks for these systems is very important. Performance modeling is required to avoid poorly chosen components and architectures as well as discovering a serious shortfall during system testing just prior to deployment time. However, the multiplicity of components and associated complexity make performance analysis of distributed computing systems a challenging task. To this end, we present an analytical performance model for the interconnection networks of heterogeneous multi-cluster systems. The analysis is based on a parametric family of fat-trees, the m-port n-tree, and a deterministic routing algorithm, which is proposed in this paper. The model is validated through comprehensive simulation, which demonstrated that the proposed model exhibits a good degree of accuracy for various system organizations and under different working conditions.