Tony Field

ICENI: optimisation of component applications within a Grid environment

Effective exploitation of Computational Grids can only be achieved when applications are fully integrated with the Grid middleware and the underlying computational resources. Fundamental to this exploitation is information. Information about the structure and behaviour of the application, the capability of the computational and networking resources, and the availability and access to these resources by an individual, a group or an organisation.In this paper we describe Imperial College e-Science Networked Infrastructure (ICENI), a Grid middleware framework developed within the London e-Science Centre. ICENI is a platform-independent framework that uses open and extensible XML derived protocols, within a framework built using Java and Jini, to explore effective application execution upon distributed federated resources. We match a high-level application specification, defined as a network of components, to an optimal combination of the currently available component implementations within our Grid environment, by using composite performance models. We demonstrate the effectiveness of this architecture through the high-level specification and solution of a set of linear equations by automatic and selection of optimal resources and implementations.

On cost-efficiency of the global container shipping network

This paper presents a simple formulation in the form of a pipe network for modelling the global container-shipping network. The cost-efficiency and movement-patterns of the current container-shipping network have been investigated using heuristic methods. The model is able to reproduce the overall incomes, costs, and container movement patterns for the industry as well as for the individual shipping lines and ports. It was found that the cost of repositioning empties is 27% of the total world fleet running cost and that overcapacity continues to be a problem. The model is computationally efficient. Implemented in the Java language, it takes one minute to run a full-scale network on a Pentium IV computer.

Optimisation of component-based applications within a grid environment

Effective exploitation of computational grids can only be achieved when applications are fully integrated with the grid middleware and the underlying computational resources. Fundamental to this exploitation is information. Information about the structure and behaviour of the application, the capability of the computational and networking resources, and the availability and access to these resources by an individual, a group or an organisation.This paper describes an integrated grid environment that is open, extensible and platform independent. We match a high-level application specification, defined as a network of components, to an optimal combination of the currently available component implementations within our grid environment. We demonstrate the effectiveness of this architecture through high-level specification and solution of a set of linear equations by automatic and optimal resource and implementation selection.

GILK: A Dynamic Instrumentation Tool for the Linux Kernel

This paper describes a dynamic instrumentation tool for the Linux Kernel which allows a stock Linux kernel to be modified while in execution, with instruments implemented as kernel modules. The Intel x86 architecture poses a particular problem, due to variable length instructions, which this paper addresses for the first time. Finally we present a short case study illustrating its use in understanding i/o behaviour in the kernel. The source code is freely available for download.

Network traffic behaviour in switched Ethernet systems

Measurements on a high-performance Ethernet are shown to match well a truncated Cauchy probability distribution, with a much better fit over smaller file/request sizes than the commonly used Pareto distribution. We observe self-similar characteristics in the traffic at both file servers and at a CPU server elsewhere in the network, which targets, predominantly, file and web servers. This suggests propagation of self-similarity. A simulation model of a single server with Poisson arrivals and Cauchy service demands yields a departure process that follows a power law and matches closely the observed traffic. The simulation is also used to investigate the link between the power laws in the request size distribution and the network traffic by using Levy distributions for the request sizes. This suggests a link between file/request size distribution and self-similarity in traffic, leading to the possibility of using conventional queueing network performance models with processor sharing queueing discipline. This idea is further supported by an additional simulation experiment and suitable models are proposed.

An Integrated Grid Environment for Component Applications

Computational grids present many obstacles to their effective exploitation by non-trivial applications. We present a grid middleware, implemented using Java and Jini, that eliminates these obstacles through the intelligent use of meta-data relating to the structure, behaviour and performance of an application. We demonstrate how different problem sizes and selection criteria (minimum execution time or minimum cost) utilise different implementations for the optimal solution of a set of linear equations.

Fluid Queue Models of Battery Life

We investigate how a power-save mode affects the battery life of a device subject to stochastically determined charging and discharging periods. We use a multi-regime fluid queue, imposing a threshold at some value. When the power level falls below the threshold, (for example, 20% of charge remaining) a power-save mode is entered and the rate of discharge decreased. An expression for the Laplace transform of the battery lifes probability density function is found and inverted numerically in particular instances. We show the life of battery can be significantly improved by the introduction of the power-saving threshold.

THEMIS: COMPONENT DEPENDENCE METADATA IN ADAPTIVE PARALLEL APPLICATIONS

There is a conflict between the goals of improving the quality of scientific software and improving its performance. A key issue is to support reuse and re-assembly of sophisticated software components without compromising performance. This paper describes THEMIS, a programming model and run time library being designed to support cross-component performance optimisation through explicit manipulation of the computation’s iteration space at run-time. Each component is augmented with “component dependence metadata”, which characterises the constraints on its execution order, data distribution and memory access order. We show how this supports dynamic adaptation of each component to exploit the available resources, the context in which its operands are generated, and results are used, and the evolution of the problem instance. Using a computational fluid dynamics visualisation example as motivation, we show how component dependence metadata provides a framework in which a number of interesting optimisations become possible. Examples include data placement optimisation, loop fusion, tiling, memoisation, checkpointing and incrementalisation.

LocTrackJINQS: An Extensible Location-aware Simulation Tool for Multiclass Queueing Networks

This paper presents LocTrackJINQS, a flexible and extensible spatio-temporal simulation tool for systems that involve the flow and processing of customers at multiple service centres. Developed based on the multi-class queueing network simulation package JINQS, LocTrackJINQS retains the abstract model specification power of JINQS while providing additional low-level models of entity movement. Besides traditional performance metrics, LocTrackJINQS produces as output a trace of each entity@?s location in the system over time. It can thus be used to generate synthetic location tracking data for location-based research or applications.

Creating Individual Based Models of the Plankton Ecosystem

The Virtual Ecology Workbench (VEW) is a suite of utilities for creating, executing and analysing biological models of the ocean. At its core is a mathematical language allowing individual plankters to be modelled using equations from laboratory experiments. The language uses conventional mathematical assignments and seven plankton-specific functions. A model consists of a number of different plankton species, each with different behaviour. The compiler produces Java classes which when executed perform a timestep-based, agent-based simulation. Each agent is a Lagrangian Ensemble agent [13] representing a dynamic number of individuals, (a sub-population), that follow the same trajectory. The agents are simulated in a virtual water column that can be anchored, or can drift with ocean currents. This paper shows how the language allows biological oceanographers to create models without the need of conventional programming, the benefits of this approach and some examples of the type of scientific experiments made possible.