International audienceLarge scale distributed systems such as Grids are difficult to study from theoretical models and simulators only. Most Grids deployed at large scale are production platforms that are inappropriate research tools because of their limited reconfiguration, control and monitoring capabilities. In this paper, we present Grid'5000, a 5000 CPU nation-wide infrastructure for research in Grid computing. Grid'5000 is designed to provide a scientific tool for computer scientists similar to the large-scale instruments used by physicists, astronomers, and biologists. We describe the motivations, design considerations, architecture, control, and monitoring infrastructure of this experimental platform. We present configuration examples and performance results for the reconfiguration subsystem

Abstract

After the seminal work by Taqqu et al. relating selfsimilarity to heavy-tailed distributions, a number of research articles verified that aggregated Internet traffic time series show selfsimilarity and that Internet attributes, like Web file sizes and flow lengths, were heavy-tailed. However, the validation of the theoretical prediction relating self-similarity and heavy tails remains unsatisfactorily addressed, being investigated using either numerical or network simulations, or from uncontrolled Web traffic data. Notably, this prediction has never been conclusively verified on real networks using controlled and stationary scenarios, prescribing specific heavy-tailed distributions, and estimating confidence intervals. With this goal in mind, we use the potential and facilities offered by the large-scale, deeply reconfigurable and fully controllable experimental Grid5000 instrument, combined with state-ofthe-art estimators, to investigate the prediction's observability on real networks. To this end, we organize a large number of controlled traffic circulation sessions on a nationwide real network involving 200 independent hosts. We use a FPGA-based measurement system to collect the corresponding traffic at packet level. We then estimate both the self-similarity exponent of the aggregated time series and the heavy-tail index of flow-size distributions, independently. Not only do our results complement and validate, with a striking accuracy, some conclusions drawn from a series of pioneering studies, but they also bring in new insights on the controversial role of certain components of real networks.

International audienceData grid applications require often an access to infrastructures with high performance data movement facilities coordinated with computational resources. Other applications need interconnections of large scale instruments with HPC platforms. In these context, dynamic provisioning of customized computing and networking infrastructure as well as resource virtualization are appealing technologies. Therefore new models and tools must be studied and developed to allow users create and handle such on-demand virtual infrastructures within grid platforms or even within the Internet. This work presents VXDL, a language for virtual resources interconnection networks specification and modeling. Besides allowing end resources description, VXDL lets users describe the desirable virtual network topology, including virtual routers and timeline. In this paper we motivate and present the key features of our modeling language. We explore typical examples to demonstrates the expressiveness and the pertinence of it. Then we detail experimental results based on the execution of NAS benchmark on virtual infrastructures, conforming different VXDL specifications

Tight coordination of resource allocation among end points in Grid networks often requires a data mover service to transfer a voluminous dataset from one site to another in a specified time interval. With flexibility at its best, the transfer can start from any time after its arrival, use any and even time variant bandwidth value, as long as it is completed before its deadline. Given a set of such tasks, we study the Bulk Data Transfer Scheduling (BDTS) problem, which searches for the optimal bandwidth allocation profile for each task to minimize the overall network congestion. We show that the multi-interval scheduling, which divides the active window of a task into multiple intervals and assigns bandwidth value independently in each of them, is both sufficient and necessary to attain the optimality in BDTS. Specifically, we show that BDTS can be solved in polynomial time as a Maximum Concurrent Flow Problem. The optimal solution attained is in the form of multi-interval scheduling with the number of intervals upper-bounded. Simulations are conducted over several representative topologies to demonstrate the significant advantage of optimal solutions.

Fault-tolerant frameworks provide highly available services by means of fault detection and fault recovery mechanisms. These frameworks need to meet different constraints related to the fault model strength, performance, and resource consumption. One of the factors that led to this work is the observation that current fault-tolerant frameworks are not always adapted to existing Internet services. In fact, most of the proposed frameworks are not transport-level-or session-level-aware, although the concerned services range from regular services like HTTP and FTP to more recent Internet services such as multimodal conferencing and voice over IP. In this work we give a comprehensive overview of fault tolerance concepts, approaches, and issues. We show how the redundancy of application servers can be invested to ensure efficient failover of Internet services when the legitimate processing server goes down.

SUMMARYWith the expansion and convergence of communication and computing, dynamic provisioning of customized networking and processing infrastructures, as well as resource virtualization, are appealing concepts and technologies. Therefore, new models and tools are needed to allow users to create, trust and enjoy such on-demand virtual infrastructures within a wide area context. This paper presents the HIPerNET framework we are designing and developing for creating, managing and controlling virtual infrastructures in the context of high-speed Internet. The key idea of this proposal is the combination of network-and system-virtualization associated with controlled resource reservation to provide fully isolated environments. HIPerNET's motivations and design principles are presented. Then we examine specifi cally how this framework handles the virtual infrastructures, called Virtual Private eXecution Infrastructures (VPXI). To help specifying customized isolated infrastructures, HIPerNET relies on VXDL, a language for VPXI description and modeling which considers end-host resource as well as the virtual network topology interconnecting them, including virtual routers. After the specifi cation, allocation and scheduling phases, HIPerNET helps in provisioning, deploying and confi guring virtual private execution infrastructures. This means, it triggers the dynamic confi guration of all the equipments involved. In this paper we concentrate on network confi guration, particularly to achieve network performance isolation. We also study and evaluate mechanisms to implement and confi gure virtual-link control. Experimental results obtained within the Grid'5000 testbed are presented and analyzed.

Grid computing is a promising way to aggregate geographically distant machines and to allow them to work together to solve large problems. After studying Grid network requirements, we observe that the network must take part of the Grid computing session to provide intelligent adaptative transport of Grid data streams. By proposing new intelligent dynamic services, active network can be the perfect companion to easily and efficiently deploy and maintain Grid environments and applications. This paper presents the Active Grid Architecture (A-Grid) which focus on active networks adaptation for supporting Grid environments and applications. We focus the benefit of active networking for the grid on three aspects: High performance and dynamic active services, Active Reliable Multicast, and Active Quality of Service.