Section: Overall Objectives

Presentation of RESO

Overview. The RESO team belongs to the “Laboratoire de l'Informatique du Parallélisme” (LIP) - Unité Mixte de Recherche (UMR) CNRS-INRIA-ENS with Université Claude Bernard of Lyon. The research activities of RESO essentially fit the “communicating" scientific priority of INRIA strategic plan 2008-2012, but since 2010 we are also reinforcing some work in the lines of the challenge “modeling, simulating and optimizing complex dynamic systems". In this direction, RESO is focusing on resource management and communication protocols in the context of high speed networks and virtualized infrastructures (clouds). We apply our results to the domain of high demanding applications and Future Internet.

Objectives. As the use of networks for on-demand computing is gaining in the large Internet, new bandwidth and network resource sharing paradigms are necessary to enable a customized traffic delivery that is dependent of the originating application. The coordination of networking, computing and storage capacities requires the design, development and deployment of new resource management mechanisms ableautonomously identify, reserve, co-allocate and reconfigure the available resources. Eventually, this adaptive administration should turn possible to control the usage of shared resources to meet the volatility of the applications' demand.

The core of RESO's research activity lies in the development of such networking service, with special emphasis on:

• application-wise Quality of Service,

• traffic-aware transport protocols,

• energy consumption efficiency,

• network metrology.

All these interacting aspects have in common the same target, which is that of an efficient and dynamic network resource provisioning and scheduling.

One of the key challenge in this direction, is the provisioning of a secure, flexible, transparent and adapted transport infrastructure for high performance data access and processing. The resulting concept of Network As a Service aims at proposing context-aware solutions that autonomously adapt the allocated IT infrastructures to sustain the current needs or constraints of the Future Internet. This is one of the main motivations for RESO's outcomes.

Methodology. The RESO approach relies on the theoretical and practical analysis of the limitations of current network practices, to motivate the exploration of new paradigms that show more adapted to the emerging infrastructures. This research framework at the interface of a specific network context and a challenging application domain, induces a close interaction between these two layers. Our methodology is based on a deep evaluation of the functionalities and the performance of high speed infrastructures and on a study of the high end and original requirements prior to design and to evaluate the proposed solutions.

Schematically, our approach is organized into four major research axes :

• Axis 1: Optimized protocol implementations and networking equipements.

  Since several years, virtualization of the operating system is used in end system to improve security, isolation, reliability and flexibility of the environments. These mechanisms becoming incontrovertible in large scale distributed system, we explore how the same can also be adapted and used in data transport networks and specifically in switching and routing equipments.

• Axis 2: Quality of Service and Transport layer for Future Networks.

  The goal of this axis is to guarantee quality of service in machine/user to machine/user communication while using efficiently the resources of the future networks.

• Axis 3: High Speed Network's traffic metrology, analysis and modelling.

  . This activity consists in measuring along time, the nature and the amount of exchanged information between the constituents of a system. It is then a matter of using the collected data to forecast the network load evolution, so as to anticipate congestion, and more widely, to guarantee a certain (probabilistic) Quality of Service, meliorating the resources usage.

• Axis 4: Network Services for high demanding applications.

  this axis focuses on the application of the solutions to the grid context and on their implementation in a real environment such as the national research instrument Grid5000.