"Massive aggregation of low-cost, low-power, commodity infrastructure can form an efficient and
effective compute fabric for key distributed applications."
The participating institutions and external collaborators will build a distributed UK-wide federated testbed of lightweight compute nodes capable of exploring the research issues that arise from such a dynamic infrastructure.
This is in contrast to the existing centralised datacentre approach which occupies acres of land, cost millions of dollars; consumes megawatts of power and relies on a huge global network bandwidth. These trends are not sustainable and it is the emergence of low cost hardware such as the Raspberry Pi that will let us explore better solutions. We envisage a testbed comprising tens of thousands of nodes, geographically distributed and capable of challenging remote off-grid scenarios. In order to facilitate this we introduce the concept of a micro-datacentre, a physically small, low power and low cost compute cluster that can be pushed to the edge of distributed networks, fundamentally changing the current model of the centralised datacentre. We have already built prototype micro-data centres at multiple sites , for example a mini-HPC cluster (Southampton University), a scale model cloud datacentre (Glasgow and Liverpool John Moores University ),
and a decentralized sensing and communication platform for ultra-remote internet blackspots (Cambridge University)
This project is about connecting together our isolated micro-datacenters to produce a federated, geo-distributed testbed. We currently have hundreds of individual nodes and intend to grow this to tens of thousands across the UK academic network. The key challenge in this expansion will be the management of the underlying infrastructure, particularly given complexities in the networking fabric. For example intermittent connectivity, firewalls, and low bandwidth connections. We will use lightweight management and orchestration software, combined with software-defined networking infrastructure to manage our federated testbed.
Through this work, we aim to demonstrate how resource-constrained micro-data centres can be harnessed as generic platforms to run virtualised, network-wide services in a resource-efficient and still high-performing manner, and enable the 'as-a-Service' paradigm over low-cost low-power federated infrastructures.
e.g. Cox and Johnson are editing a special issue of the Electronics journal on `Raspberry Pi Technology'.
We will organize community workshops, separately for both academic and general enthusiast audiences.
We have significant experience in this area, e.g. Glasgow academics have presented invited seminars and hands-on demos at 11 workshop events over the past 3 years. These include BCS events, Pi Jam events, PhD summer schools etc.
Further, many academics, industrialists and enthusiasts across the world consult us for guidance when building their own micro-datacenters. They follow our progress on the Glasgow project blog at http://raspberrypicloud.wordpress.com
We will undertake public engagement of the massive online Raspberry Pi community across the world. We will release open source instructions for all our infrastructure, hardware blueprints, tool configuration and software source code. Initially the aim will be for others to federate with us directly, later we will encourage them to clone their own distributed systems.
We intend to achieve long-term impact via standardization of configuration and deployment protocols for micro-datacenters. We expect to engage with industry and standards bodies to convert our work into official standards. e.g. Colin Perkins interacts regularly with the IETF standardization process.
In terms of the testbed sustainability, we intend to grow over the funded project to a number of sites across JANET - at least 10. We have secured agreement from Heriot Watt and UCL to build Raspberry Pi testbeds there already.
We recognise that new generations of low-power embedded devices are coming onstream all the time. What will the Raspberry Pi 3 look like? We appreciate the need to be able to retarget our software stack to these other devices too. However once the standards are in place and our demonstrator testbed is live, we expect that the open source community will become involved in porting our work to other infrastructures.
- University of Glasgow, United Kingdom (Lead Research Organisation)
- University of Tokyo, Japan (Project Partner)
- Heriot-Watt University, United Kingdom (Project Partner)
- Raspberry Pi Foundation (Project Partner)
- Madanyu (Project Partner)
- ARM Ltd, United Kingdom (Project Partner)
- Microsoft Research Ltd, United Kingdom (Project Partner)