The proposed work is in the area of building general-purpose computing and storage infrastructure for the future datacentre that support all IT activities. Today, such datacentres include various types of servers that support compute, storage I/O, client network I/O, and high-speed LAN applications.
The requirements of such, modern datacentres to support a variety of IT services (mail, dbases, storage, backup, compute intensive applications, online services, etc.) lead to multi-tier architectures that require connectivity among different levels. One of the main problems of using multiple tiers in such architectures is the specialization of each tier to a specific type of functions or applications.
For instance, a cluster used for computing cannot be used to service storage requests as well. This leads to an imbalance of using the available resources. Future datacentres can greatly benefit from symmetric architectures that allow the shifting of resources between tasks.
This is made possible today by the fact that most computing resources within the datacentre are very similar, in most cases PCs or workstations in various forms, such as blade servers. The main inhibitor in moving to such architectures is the different interconnects that are used today for each logical subsystem in a datacentre.
Moreover, the use of multiple, in some sense customized protocols and interconnects leads to high management complexity and cost, to difficulty in upgrading to new generations of each technology, and, in some cases, to proprietary solutions due to incomplete standardization. These are all significant issues for the evolution of datacentres and their ability to effectively support increasing needs.
The goal of this work is to tackle this problem and develop the technology required to unify the network interconnects used today in datacentres and to provide the fundamental technology for evolving to more flexible and effective datacentre architectures.
Call for proposal
See other projects for this call