Systems composed of interacting autonomous agents offer a promising software engineering approach for developing applications in complex domains. However, this multiagent system paradigm introduces a number of new abstractions and design/development issues when compared with more traditional approaches to software development. Accordingly, new analysis and design methodologies, as well as new tools, are needed to effectively engineer such systems.

In "Grids" and "collaboratories," we find distributed communities of resource providers and resource consumers, within which often complex and dynamic policies govern who can use which resources for which purpose. We propose a new approach to the representation, maintenance, and enforcement of such policies that provides a scalable mechanism for specifying and enforcing these policies. Our approach allows resource providers to delegate some of the authority for maintaining fine-grained access control policies to communities, while still maintaining ultimate control over their resources. We also describe a prototype implementation of this approach and an application in a data management context.

An emerging class of data-intensive applications involve the geographically dispersed extraction of complex scientific information from very large collections of measured or computed data. Such applications arise, for example, in experimental physics, where the data in question is generated by accelerators, and in simulation science, where the data is generated by supercomputers. So-called Data Grids provide essential infrastructure for such applications, much as the Internet provides essential services for applications such as e-mail and the Web. We describe here two services that we believe are fundamental to any Data Grid: reliable, high-speed transport and replica management. Our high-speed transport service, GridFTP, extends the popular FTP protocol with new features required for Data Grid applications, such as striping and partial file access. Our replica management service integrates a replica catalog with GridFTP transfers to provide for the creation, registration, location, and management of dataset replicas. We present the design of both services and also preliminary performance results. Our implementations exploit security and other services provided by the Globus Toolkit.

Dynamic mapping (matching and scheduling) heuristics for a class of independent tasks using heterogeneous distributed computing systems are studied. Two types of mapping heuristics are considered: on-line and batch mode heuristics. Three new heuristics, one for batch and two for on-line, are introduced as part of this research. Simulation studies are performed to compare these heuristics with some existing ones. In total, five on-line heuristics and three batch heuristics are examined. The on-line heuristics consider, to varying degrees and in different ways, task affinity for different machines and machine ready times. The batch heuristics consider these factors, as well as aging of tasks waiting to execute. The simulation results reveal that the choice of mapping heuristic depends on parameters such as: (a) the structure of the heterogeneity among tasks and machines, (b) the optimization requirements, and (c) the arrival rate of the tasks. 1.

. Dynamic replication can be used to reduce bandwidth consumption and access latency in high performance "data grids" where users require remote access to large files. Different replication strategies can be defined depending on when, where, and how replicas are created and destroyed. We describe a simulation framework that we have developed to enable comparative studies of alternative dynamic replication strategies. We present preliminary results obtained with this simulator, in which we evaluate the performance of five different replication strategies for three different kinds of access patterns. The data in this scenario is read-only and so there are no consistency issues involved. The simulation results show that significant savings in latency and bandwidth can be obtained if the access patterns contain a small degree of geographical locality. 1

The Information Power Grid (IPG) is emerging as an infrastructure that will enable distributed applications – such as video conferencing and distributed interactive simulation – to seamlessly integrate collections of heterogeneous workstations, multiprocessors, and mobile nodes, over heterogeneous wide-area networks. This paper introduces a framework for developing efficient collective communication schedules in such systems. Our framework consists of analytical models of the heterogeneous system, scheduling algorithms for the collective communication pattern, and performance evaluation mechanisms. We show that previous models, which considered node heterogeneity but ignored network heterogeneity, can lead to solutions which are worse than the optimal by an unbounded factor. We then introduce an enhanced communication model, and develop three heuristic algorithms for the broadcast and multicast patterns. The completion time of the schedule is chosen as the performance metric. The heuristic algorithms are FEF (Fastest Edge First), ECEF (Earliest Completing Edge First), and ECEF with look-ahead. For small system sizes, we find the optimal solution using exhaustive search. Our simulationexperiments indicate that the performance of our heuristic algorithms is close to optimal. For performance evaluation of larger systems, we have also developed a simple lower bound on the completion time. Our heuristic algorithms achieve significant performance improvements over previous approaches. 1.

The ecient implementation of collective communication operations has received much attention. Initial eorts modeled network communication and produced \optimal" trees based on those models. However, the models used by these initial eorts assumed equal point-to-point latencies between any two processes. This assumption is violated in heterogeneous systems such as clusters of SMPs and wide-area \computational grids", and as a result, collective operations that utilize the trees generated by these models perform suboptimally. In response, more recent work has focused on creating topology-aware trees for collective operations that minimize communication across slower channels (e.g., a wide-area network). While these efforts have signicant communication benets, they all limit their view of the network to only two layers. We present a strategy based upon a multilayer view of the network. By creating multilevel topology trees we take advantage of communication cost dierences at every lev...

Monitoring and information services form a key component of a distributed system, or Grid. A quantitative study of such services can aid in understanding the performance limitations, advise in the deployment of the monitoring system, and help evaluate future development work. To this end, we study the performance of three monitoring and information services for distributed

In the Internet, mobile code is ubiquitous and includes such examples as browser plug-ins, Java applets, and document macros. In this paper, we address an important vulnerability in mobile code security that exists in remote execution systems such as Condor, Globus, and SETI@Home. These systems schedule user jobs for execution on remote idle machines. However, they send most of their important system calls back to the local machine for execution. Hence, an evil process on the remote machine can manipulate a user’s job to send destructive system calls back to the local machine. We have developed techniques to remotely detect such manipulation. Before the job is submitted for remote execution, we construct a model of the user’s binary program using static analysis. This binary analysis is applicable to commodity remote execution systems and applications. During remote job execution, the model checks all system calls arriving at the local machine. Execution is only allowed to continue while the model remains valid. We begin with a finite-state machine model that accepts sequences of system calls and then build optimizations into the model to improve its precision and efficiency. We also propose two program transformations, renaming and null call insertion, that have a significant impact on the precision and efficiency. As a desirable side-effect, these techniques also obfuscate the program, thus making it harder for the adversary to reverse engineer the code. We have implemented a simulated remote execution environment to demonstrate how optimizations and transformations of the binary program increase the precision and efficiency. In our test programs, unoptimized models increase run-time by 0.5 % or less. At moderate levels of optimization, run-time increases by less than 13 % with precision gains reaching 74%.

e-Science offers a promising vision of how computer and communication technology can support and enhance the scientific process. It does this by enabling scientists to generate, analyse, share and discuss their insights, experiments and results in an effective manner. The underlying computer infrastructure that provides these facilities is commonly referred to as the Grid. At this time, there are a number of grid applications being developed and there is a whole raft of computer technologies that provide fragments of the necessary functionality. However there is currently a major gap between these endeavours and the vision of e-Science in which there is a high degree of easy-to-use and seamless automation and in which there are flexible collaborations and computations on a global scale. To bridge this practice–aspiration divide, this paper presents a research agenda whose aim is to move from the current state of the art in e-Science infrastructure, to the future infrastructure that is needed to support the full richness of the e-Science vision. Here the future e-Science research infrastructure is termed the Semantic Grid (Semantic Grid to Grid is meant to connote a similar relationship to the one that exists between the Semantic Web and the Web). In particular, we present a conceptual architecture for the Semantic Grid. This architecture adopts a service-oriented perspective in which distinct stakeholders in the scientific process, represented as software agents, provide services to one another, under various service level agreements, in various forms of marketplace. We then focus predominantly on the issues concerned with the way that knowledge is acquired and used in such environments since we believe this is the key differentiator between current grid endeavours and those envisioned for the Semantic Grid. 1.