Team reso

Members
Overall Objectives
Scientific Foundations
Application Domains
Software
New Results
Contracts and Grants with Industry
Other Grants and Activities
Dissemination
Bibliography

Section: Overall Objectives

Context

Wavelengths multiplexing and wavelengths switching techniques on optical fibers allow core network infrastructures to rapidly improve their throughput, reliability and flexibility. Links of 40 gigabits per second are now available and 100 gigabits per second are emerging. New technologies like 10 Gigabit/s Ethernet or 10Gigabit/s Myrinet is also driving the increase of bandwidth in local area networks. These improvements have given the opportunity to create high performance distributed systems that aggregate storage and computation resources into a virtual and integrated computing environment. During a decade lot of researches and developments around the concept of grid and utility computing have underlined the strength of this approach. Today, the communication, computation and storage aspects of the Internet tend to converge. They are combined with the deployment of ultra high capacities interconnection networks with predictable performance and the emergence of coarse Grain Web Servers like Google, Yahoo, Amazon providing the content, control, storage and computing resources for the users. All these trends will strongly influence the development of the future Internet. They raise major research issues in networking and services, requiring a new vision of the network of networks and its protocol architecture. Indeed, the current Internet stack (TCP/IP) and its associated simple network management protocol is not consistent with the evolution of the network infrastructure components and its use by emerging services which aim to deliver supercomputing power available to the masses over the Internet. The coordination of networking, computing and storage requires the design, development and deployment of new resource management approaches to discover, reserve, co-allocate and reconfigure resources, schedule and control their usages. The network is not only a black box providing pipes between edge machines, but is becoming a vast cloud increasingly embedding the computational and storage resources to meet the requirement of emerging applications. These resources will be located at important crossroads and access points throughout the network. During the last few years, we have seen that the distinction between packet forwarding and application processing has become blurred. The network community now starts to worry not only about forwarding packets without regard to application semantics, but is increasingly trying to exploit new functionalities within the network to meet the requirements of application. Reciprocally, distributed systems and applications have traditionally been designed to run on top of the Internet, and to take the architecture of the Internet as given. Although the convergence of communication and computation at every level appears to be natural, it is still very difficult to efficiently explore the full range of possibilities it can bring. Most of the proposals exploiting this convergence break the initial design philosophy of the Internet protocol stack (end-to-end argument for example), or if implemented in the application layer present lot of performance, resilience and scalability issues. Recently, ambitious research programs like FIND (NSF) or FIRE (EU) have been launched towards the design of a new protocol architecture for Future Internet and solving the critical issues facing the current architecture. We think that the Internet re-design raises the opportunity to better understand and assess higher-level system requirements, and use these as drivers of the lower layer architecture. In this process, mechanisms that are implemented today as part of applications, may conceivably migrate into the network itself, and this is one of main driver of the researches of RESO. One of the key challenge for large deployment of new high end applications in the Internet is the provisionning of a secure, flexible, transparent and high performance transport infrastructure for data access and processing. Consequently, future high-speed optical networks are addressed not only to support the accelerating and dynamic growth of data traffic but also the new emerging network requirements such as fast and flexible provisioning, QoS levels, and fast recovery procedures of such data intensive applications.


previous
next

Logo Inria