BROADCAST: Basic Research On Advanced Distributed Computing: from Algorithms to SysTems

From Navigators

Latest revision as of 18:20, 13 November 2012

• Research Line(s): Fault and Intrusion Tolerance in Open Distributed Systems (FIT)
• Sponsor: Esprit BRA
• Coordinator: U. Newcastle
• Partners: EPF de Lausanne, INESC, INRIA, INRIA-IRISA, Univ. de Bologna, Univ. Joseph Fourier, Univ. of Newcastle, Univ. Twente
• Start Date: Oct. 1992
• Duration: 36 months
• Keywords: groups, distributed systems, large scale, CSCW
• Team at INESC: 6 researchers, including

Large-scale distributed systems comprising several thousands to millions of individual computer systems (nodes) are coming into existence both as a consequence of technological advances and the demands placed by applications. The increase in scale adds a new dimension to the problems of building distributed systems, and requires rethinking of many of the existing computational paradigms, algorithms and structuring principles for distributed computing. The objective of the BROADCAST project is to develop the principles for understanding, designing, and implementing LSDCS. The project will address the following tasks: Fundamental Concepts; Systems Architecture; Systems Engineering.

Aims

The main objective of the BROADCAST project is to develop the underlying principles of designing and implementing large scale distributed computing systems (LSDCS). We expect LSDCS to exhibit great diversity of node and communications capability. Nodes will range from (mobile) laptop computers, workstations to supercomputers.

In order to meet the main objective of the BROADCAST project, it is necessary then to understand the impact of two main factors responsible for the growth of interest in LSDCS: (i) application requirements; (ii) user expectations on technology.

Approach and Methods

It is intended to investigate the adequate properties of: multicasting communication; group communication protocols; group management services, such as membership, replication and cooperation; global time services. Investigation will be also directed towards the development of suitable CSCGW paradigms, in imbrication with the more fundamental group activity paradigms mentioned above. Prototyping in later stages is considered paramount, to test in a real world the techniques to be developed.

Progress and Results

Several papers, reports and surveys produced in the three streams of project activity: concepts and paradigms; architecture and protocols; applications. Main results of INESC: survey on groupware; framework for reliable LSDCS, leading to the design of NavTech.

Potential

It is expected that research in this area will lead to an innovative system, to support large scale distributed applications, such as CSCGW or on-line transactions.

Publications

• François Cosquer, Luís Rodrigues, Paulo Verissimo, “Using Tailored Failure Suspectors to Support Distributed Cooperative Applications”, in October 1995. Proceedings of the 7th International Conference on Parallel and Distributed Computing and Systems. Washington, D.C., USA, Oct. 1995.

• Luís Rodrigues, Paulo Verissimo, “Causal separators and topological timestamping: an approach to support causal multicast in large-scale systems”, in May 1995. Proceedings of the 15th International Conference on Distributed Computing Systems. Vancouver, British Columbia, Canada, May 1995.

• Luís Rodrigues, Paulo Verissimo, “How to avoid the cost of causal communication in large-scale systems”, in September 1994. Proceedings of the 6th SIGOPS European Workshop. Dagstuhl, Germany, Sept. 1994.

• François Cosquer, Paulo Verissimo, “Survey of Selected Groupware Applications and Supporting Platforms”, Missing institution, Tech. Rep., Jul. 1994. July 1994. (Also available as Broadcast Technical Report 2nd Year Vol.1) (Submitted for publication)

• Luís Rodrigues, Paulo Verissimo, “Replicated object management using group technology”, in September 1993. Proceedings of the 4th Workshop on Future Trends of Distributed Computing Systems. Lisboa, Portugal, Sept. 1993.

• Paulo Verissimo, Werner Vogels, Luís Rodrigues, “A Framework for Structuring Group Support in LSDCs”, Missing institution, Tech. Rep., Sept. 1993. September 1993. INESC, Lisboa, Portugal

• Paulo Verissimo, Luís Rodrigues, “Group orientation: a paradigm for modern distributed systems”, in September 1992. Proceedings of the 5th ACM SIGOPS European Workshop. Mont Saint-Michel, France, Sept. 1992.

BibTeX