Jogesh K. Muppala

SPNP: stochastic Petri net package

SPNP, a powerful GSPN package that allows the modeling of complex system behaviors, is presented. Advanced constructs are available in SPNP such as marking-dependent arc multiplicities, enabling functions, arrays of places or transitions, and subnets; the full expressive power of the C programming language is also available to increase the flexibility of the net description. Sophisticated steady-state and transient solvers are available including cumulative and up-to-absorption measures. The user is not limited to a predefined set of measures; detailed expressions reflecting exactly the measures sought can be easily specified. The authors conclude by comparing SPNP with two other SPN-based packages, Great SPN and METASAN.<<ETX>>

Automated Generation and Analysis of Markov Reward Models Using Stochastic Reward Nets

Markov and Markov reward models are widely used for the performance and reliability analysis of computer and communication systems. Models of real systems often contain thousands or even millions of states. We propose the use of Stochastic Reward Nets (SRNs) for the automatic generation of these large Markov reward models. SRNs do allow the concise specification of practical performance, reliability and per-formability models.

On the solution of GSPN reward models

Abstract We extend the basic GSPN (generalized stochastic Petri net) model to the GSPN-reward model. This allows the concise specification of both the underlying stochastic process and the rewards attached to the states and the transitions of the stochastic process. The classical method for the steady-state solution of GSPN models, based on the correspondence between GSPNs and continuous-time Markov chains (CTMCs), is compared with a method based on discrete-time Markov chains (DTMCs) previously judged poor. We show that there are GSPNs where the DTMC-based method performs better than the classical method (and others where it performs worse). Finally, we discuss how to perform parametric sensitivity analysis of the measures computed from a GSPN using either solution method.

Real-time systems performance in the presence of failures

A unified methodology for modeling both soft and hard real-time systems is presented. Techniques that combine the effects of performance, reliability/availability, and deadline violation into a single model are used. An online transaction processing system is used as an example to illustrate the modeling techniques. Dynamic failures due to a transaction violating a hard deadline are taken into account by incorporating additional transitions in the Markov chain model of the failure-repair behavior. System performance in the various configurations is considered by using throughput and response-time distribution as reward rates. Since the Markov chains used in computing the distribution of response time are often very large and complex, a higher level interface based on a variation of stochastic Petri nets called stochastic reward nets is used.<<ETX>>

A Survey of BitTorrent Performance

Since its inception, BitTorrent has proved to be the most popular approach for sharing large files using the peer-to-peer paradigm. BitTorrent introduced several innovative mechanisms such as tit-for-tat (TFT) and rarest first to enable efficient distribution of files among the participating peers. Several studies examining the performance of BitTorrent and its mechanisms have been published in the literature. In this paper, we present a survey of performance studies of BitTorrent from 2003 to 2008. We categorize these studies based on the techniques used, the mechanisms studied and the resulting observations about BitTorrent performance. Many of the performance studies also suggested modifications to BitTorrents mechanisms to further improve its performance. We also present a survey of the suggested improvements and categorize them into different groups.

Analysis of nonblocking ATM switches with multiple input queues

An analytical model for the performance analysis of a multiple input queued asynchronous transfer mode (ATM) switch is presented. The interconnection network of the ATM switch is internally nonblocking and each input port maintains a separate queue of cells for each output port. The switch uses parallel iterative matching (PIM) to find the maximal matching between the input and output ports of the switch. A closed-form solution for the maximum throughput of the switch under saturated conditions is derived. It is found that the maximum throughput of the switch exceeds 99% with just four iterations of the PIM algorithm. Using the tagged input queue approach, an analytical model for evaluating the switch performance under an independent identically distributed Bernoulli traffic with the cell destinations uniformly distributed over all output ports is developed. The switch throughput, mean cell delay, and cell loss probability are computed from the analytical model. The accuracy of the analytical model is verified using simulation.

Markov Dependability Models of Complex Systems: Analysis Techniques

Continuous time Markov chains are commonly used for modelling large systems, in order to study their performance and dependability. In this paper, we review solution techniques for Markov and Markov reward models. Several methods are presented for the transient analysis of Markov models, ranging from fully-symbolic to fully-numeric. The Markov reward model is explored further, and methods for computing various reward based measures are discussed including the expected values of rewards and the distributions of accumulated rewards. We also briefly discuss the different types of dependencies that arise in dependability modelling of systems, and show how Markov models can handle some of these dependencies. Finally, we briefly review the Markov regenerative process, which relaxes some of the constraints imposed by the Markov process.

Analyzing concurrent and fault-tolerant software using stochastic reward nets

Abstract We present two software applications and develop models for them. The first application considers a producer-consumer tasking system with an intermediate buffer task and studies how the performance is affected by different selection policies when multiple tasks are ready to synchronize. The second application studies the reliability of a fault-tolerant software system using the recovery block scheme. The model is incrementally augmented by considering clustered failures or the effective arrival rate of inputs to the system. We use stochastic reward nets, a variant of stochastic Pertri nets, to model the two software applications. In both models, each quantity to be computed is defined in terms of either the expected value of a reward rate in steady-state or at a given time θ, or as the expected value of the accumulated reward until absorption or until a given time θ. This allows extreme flexibility while maintaining a rigorous formalization of these quantities.

Techniques for System Dependability Evaluation

A major application area for the probabilistic and numerical techniques explored in the earlier chapters is in characterizing the behavior of complex computer and communication systems. While system performance has received a lot of attention in the past, increasingly system dependability is gaining importance. The proliferation of computer and computer-based communication systems has contributed to this in no small measure. This chapter is thus a step in the direction of summarizing the techniques, tools and recent developments in the field of system dependability evaluation.

A stable queue-based adaptive controller for improving AQM performance

Active queue management (AQM) mechanisms are designed to provide better support for end-to-end congestion control mechanisms of transmission control protocol (TCP) in TCP/IP networks. This paper introduces a stable queue-based adaptive proportional-integral (Q-SAPI) controller for AQM and presents an implementation. The starting points of our approach are the recently developed fluid-flow modeling and control theoretic interpretation of the TCP/AQM dynamics, and the recently developed fixed-gain proportional-integral (PI) controller for AQM. Q-SAPI aims to improve the transient performance of the fixed-gain PI controller while maintaining its steady-state performance over a wide range of uncertainties in round-trip time (RTT) and the number of active TCP flows. The robustness of Q-SAPI is studied in detail, which provides guidelines for selecting control parameters. Through extensive simulations, we demonstrate the ability of Q-SAPI in controlling queue length in both transient and steady states. Q-SAPI achieves this by adapting the controller gains according to the queue length.