PDF, 4.3 MB
Zipped PostScript, 4.5 MB
PDF, 4.3 MB
Zipped PostScript, 4.5 MB
HTML
HTML
PDF, 184 KB
Zipped PostScript, 318 KB
Using grid resources to execute scientific applications requiring a large amount of computing power is attractive but not easy from the user point of view. Vigne is a grid operating system designed to provide users with a simplified view of a grid. Vigne deals with the huge number of nodes in a large-scale grid and with the nodes' dynamic behavior by using peer-to-peer overlays as a keystone. In this paper, we show why it is highly desirable to use structured and unstructured peer-to-peer overlays for building the high-level services of Vigne grid operating system. To show the interest of our approach, we detail the features of two Vigne services built on top of peer-to-peer overlays. We also present experimental results obtained on the Grid'5000 testbed showing the scalability of the Vigne infrastructure based on overlays and its practical interest for the implementation of Vigne distributed services.
PDF, 179 KB
Zipped PostScript, 473 KB
Data replication permits a better network bandwidth utilization and minimizes the effect of latency in large-scale systems such as computing grids. However, the cost of maintaining the data consistent between replicas may become difficult if the read/write system has to ensure sequential consistency. In this paper, we limit the overhead due to the data consistency protocols by introducing a new dynamic quorum protocol called the elementary permutation protocol.This protocol permits the dynamic reconfiguration of a tree-structured coterie \cite{Agrawal91Efficient} in function of the load of the machines that possess the data replicas. It applies a tree transformation in order to obtain a new less loaded coterie.This permutation is based on the load information of a small group of machines possessing the copies. The implementation and the evaluation of our algorithm have been based on the existing atomic read/write service of \cite{Lynch97Robust}. We demonstrate that the elementary permutation ameliorates the system's throughput upto 50\% in the best case. The results of our simulation show that the tree reconfiguration based on the elementary permutation is more efficient for a relatively small number of copies.
PDF, 241 KB
Zipped PostScript, 335 KB
This paper describes a dynamic load balancing tool intended for computational investigators who have little familiarity with programming for a message-passing environment. Motivated by the PAR DOALL directive available in some compilers for shared-memory systems, the tool is designed to simplify the manual conversion of sequential programs containing computationally intensive one- or two-dimensional loops with independent iterates into parallel programs that execute with high efficiency on general-purpose clusters. The tool implements a dynamic loop scheduling strategy to address load imbalance which may be induced by the non-uniformity of loop iterate times, and by the heterogeneity of processors. The tool is based on the Message Passing Interface library for wide availability. Experimental results of two scientific applications that utilize the tool on a Linux cluster are presented to demonstrate sample achievable performance, and to underscore the effectiveness of the two-level dynamic load balancing strategy.
PDF, 132 KB
Zipped PostScript, 295 KB
This paper describes a parallel implementation of a Lanczos-based method to solve generalised eigenvalue problems related to the modal computation of arbitrarily shaped waveguides. This efficient implementation is intended for execution mainly in moderate-low cost workstations (2 to 4 processors). The problem under study has several features: the involved matrices are sparse with a certain structure, and all the eigenvalues needed are contained in a given interval. The novel parallel algorithms proposed show excellent speed-up for small number of processors.
PDF, 214 KB
Zipped PostScript, 339 KB
This paper presents the design of InfiniWrite, the implementation of a lightweight communication interface called RWAPI over the InfiniBand interconnect for clusters of PCs. Since the specifications of the InfiniBand interconnect provide many ways to transfer data, we are discussing some issues regarding the choices between InfiniBand capabilities. We implemented RWAPI on top of the grid-oriented architecture called GRWA and evaluated the communication performance. GRWA has been developed to provide performance to higher applications on a wide variety of architectures. We obtain a very low latency and a throughput very close to the maximum user bandwidth for messages as small as 4 kilo-bytes.
PDF, 802 KB
Zipped PostScript, 1.2 MB
The centralised management of distributed computing infrastructures presents a number of considerable challenges, not least of which is the effective monitoring of physical resources and middleware components to provide an accurate operational picture for use by administrative or management staff. The detection and presentation of real-time information pertaining to the performance and availability of computing resources is a difficult yet critical activity.
This architecture is intended to enhance the service monitoring experience of a Grid operations team. We have designed and implemented an extensible agent-based architecture capable of detecting and aggregating status information using low-level sensors, functionality tests and existing information systems. To date it has been successfully deployed across eighteen Grid-Ireland sites.
PDF, 539 KB
Zipped PostScript, 535 KB
Supporting range query over Peer-to-Peer systems has attracted many research efforts in recent years. In this paper, we propose a new multidimensional indexing structure for P2P systems called Distributed Hilbert R-trees (DHR-trees). DHR-trees enables multidimensional range query to be executed similarly as in overlapping regions tree in P2P systems. Its distributed structure makes it fault-tolerant and scalable to dynamic network environment with a large number of peers as well. Our experiments shows that it performs well on multidimensional range query while the maintenance cost is reasonably low.
PDF, 1.7 MB
Zipped PostScript, 1.7 MB
Scheduling is an important factor for the efficient execution of computational workflows on Grid environments. A large number of static scheduling heuristics has been presented in the literature. These algorithms allocate tasks before job execution starts and assume a precise knowledge of timing information, which may be difficult to obtain in general. To overcome this limitation of static strategies, dynamic scheduling strategies may be needed for a changing environment such as the Grid. While they incur run-time overheads, they may better adapt to timing changes during job execution. In this work, we analyse five well-known heuristics (min-min, max-min, sufferage, HEFT and random) when used as static and dynamic scheduling strategies in a grid environment in which computing resources exhibit congruent performance differences. The analysis shows that non-list based heuristics are more sensitive than list-based heuristics to inaccuracies in timing information. Static list-based heuristics perform well in the presence of low or moderate inaccuracies. Dynamic versions of these heuristics may be needed only in environments where high inaccuracies are observed. Our analysis also shows that list-based heuristics significantly outperform non-list based heuristics in all cases and, therefore, constitute the most suitable strategies by which to schedule workflows either statically or dynamically.
PDF, 674 KB
Zipped PostScript, 1.4 MB
The integration of Web Services and Software Agents brings new opportunities to deliver value added services in SOAs. This paper describes the functional model, the architecture design and the prototypal implementation of a platform for services adaptation and delivery. Agents technology is exploited to reconfigure the server platform to adapt the service provision to heterogeneous and handled devices. Virtual services are built on the platform for each client profile by conditioning the SOAP requests coming from WS requestors and adapting the returned responses. A general straightforward approach to extend client application in order to exploit platform facilities is described. Mobile agents are able to access and compose services accessing them by standard interfaces. User authentication, service discovery and publication, personalization are other provided facilities. Technological interoperability is provided by Web Services technology.
