George Tsouloupas

GridBench: a tool for benchmarking grids

The aim of the GridBench suite of benchmarks is to bring together a core set of benchmarks for characterizing grid nodes or collections of grid resources. In order to do this in an organized and flexible way we provide a framework for running benchmarks on grid environments as well as collecting, archiving, and publishing the results. This framework allows for convenient integration of new and existing benchmarks into the suite.

First Prototype of the CrossGrid Testbed

The CrossGrid project is developing new grid middleware components, tools and applications with a special focus on parallel and interactive computing. In order to support the development effort and provide a test infrastructure, an international grid testbed has been deployed across 9 countries. Through the deployment of the testbed and its supporting services, CrossGrid is also contributing to another important project objective, the expansion of the grid coverage in Europe. This paper describes the status of the CrossGrid testbed.

GridBench: A tool for the interactive performance exploration of Grid infrastructures

As Grids rapidly expand in size and complexity, the task of benchmarking and testing, interactive or unattended, quickly becomes unmanageable. In this article we describe the difficulties of testing/benchmarking resources in large Grid infrastructures and we present the software architecture implementation of GridBench, an extensible tool for testing, benchmarking and ranking of Grid resources. We give an overview of GridBench services and tools, which support the easy definition, invocation and management of tests and benchmarking experiments. We also show how the tool can be used in the analysis of benchmarking results and how the measurements can be used to complement the information provided by Grid Information Services and used as a basis for resource selection and user-driven resource ranking. In order to illustrate the usage of the tool, we describe scenarios for using the GridBench framework to perform test/benchmark experiments and analyze the results.

Characterization of Computational Grid Resources Using Low-Level Benchmarks

An important factor that needs to be taken into account by end-users and systems (schedulers, resource brokers, policy brokers) when mapping applications to the Grid is the performance capacity of hardware resources attached to the Grid and made available through its Virtual Organizations. In this article, we examine the problem of characterizing the performance capacity of Grid resources using benchmarking. We examine the conditions under which such characterization experiments can be implemented in a Grid setting and present the challenges that arise in the Grid context. We specify a small number of performance metrics and propose a suite of microbenchmarks to estimate these metrics for sites that belong to large Virtual Organizations. We describe benchmarking experiments conducted with, and published through GridBench, a tool that we built to manage benchmarking experiments over the Grid and to publish and analyze performance metrics. Finally we show how results derived from GridBench can help end-users assess the performance capacity of resources belonging to a large Virtual Organization.

GridBench: a workbench for grid benchmarking

In this article we present the GridBench, an extensible tool for benchmarking and testing Grid resources. We give an overview of the GridBench services and tools that provide easy invocation of benchmarks and management of results. We also show how the tool can be used in the analysis of results and how the measurements can be used to complement the information provided by Grid information services and used as a basis for resource selection. In order to illustrate the usage of the tool, we describe scenarios for using the GridBench framework and the GridBench “virtual workbench” to perform benchmarking experiments and analyze the results.

Grid resource ranking using low-level performance measurements

This paper outlines a feasible approach to ranking Grid resources based on an easily obtainable application-specific performance model utilizing low-level performance metrics. First, Grid resources are characterized using low-level performance metrics; Then the performance of a given application is associated to the low-level performance measurements via a Ranking Function; Finally, the Ranking Function is used to rank all available resources on the Grid with respect to the specific application at hand. We show that this approach yields accurate results.

Grid resource selection by application benchmarking for computational haemodynamics applications

Grid benchmarking for improved computational resource selection can shed a light for improving the performance of computationally intensive applications. In this paper we report on a number of experiments with a biomedical parallel application to investigate the levels of performance offered by hardware resources distributed across a pan-European computational Grid network. We provide a number of performance measurements based on the iteration time per processor and communication delay between processors, for a blood flow simulation benchmark based on the lattice Boltzmann method. We have found that the performance results obtained from real application benchmarking are much more useful for running our biomedical application on a highly distributed grid infrastructure than the regular resource information provided by standard Grid information services to resource brokers.

Experience with the international testbed in the crossgrid project

The International Testbed of the CrossGrid Project has been in operation for the last three years, including 16 sites in 9 countries across Europe. The main achievements in installation and operation are described, and also the substantial experience gained on providing support to application and middleware developers in the project. Results are presented showing the availability of a realistic Grid framework to execute distributed interactive and parallel jobs.

Heterogeneous grid computing: issues and early benchmarks

A heterogeneous implementation of the current LCG2/EGEE grid computing software is supported in the Grid-Ireland infrastructure. The porting and testing of the current software version of LCG2 is presented for different flavours of Linux, namely Red Hat 7.3, Red Hat 9 and Fedora Core 2. The GridBench micro-benchmarks developed in CrossGrid are used to compare the different platforms.

Ranking and Performance Exploration of Grid Infrastructures: An Interactive Approach

In the ever-growing grid infrastructures picking the right resources is not an easy task. There are situations were finding enough idle CPUs that satisfy a set of minimum nominal hardware requirements is simply not enough. In many such occasions, users or VO managers need to be involved in the resource selection process, either by excluding resources or by indicating preference, more so when resources are not for free. To support users in this task, we propose an interactive and user-driven approach to a performance-based ranking of grid resources. Using the GridBench framework and the provided suite of micro-benchmarks, the user is able to interactively explore and rank what is currently available on the grid in order to pinpoint the right resources. Through this framework, the user is able to interactively compose ranked lists of grid resources using custom ranking functions that are based on low-level measurements