- HAL publications
WIDE Research team
the World Is Distributed Exploring the tension between scale and coordination
- Leader : Francois Taiani
- Type : Project team
- Research center(s) : Rennes
- Field : Networks, Systems and Services, Distributed Computing
- Theme : Distributed Systems and middleware
- Partner(s) : Université Rennes 1
- Collaborator(s) : Institut de recherche en informatique et systèmes aléatoires (IRISA) (UMR6074)
As distributed computing systems are being deployed within a growing number of everyday applications, they are reaching unheard-of levels of scale, dynamicity, and complexity. The construction of such systems requires novel fundamental approaches that stand in stark contrast to existing strategies in many areas of distributed computing research. The objective of the WIDE team is to provide such a foundation, by investigating some of the key fundamental theoretical and practical questions posed by modern distributed computer systems.
More specifically, we would like to explore the inherent tension between scalability and coordination guarantees, and develop novel techniques and paradigms that are adapted to the rapid and profound changes impacting today's distributed systems, both in terms of the application domains they support and the operational constraints they must meet.
Our research revolves around four key objectives.
- Objective 1: Designing Hybrid Scalable Architectures,
- Objective 2: Constructing Personalizable Privacy-aware distributed systems,
- Objective 3: Understanding Controllable Network Diffusion Processes,
- Objective 4: Systemizing Modular Distributed Computability and Efficiency.
These four objectives have in common the inherent tension between coordination and scalability in large-scale distributed systems: strong coordination mechanisms can deliver strong guarantees (in terms of consistency, agreement, fault-tolerance, and privacy protection), but are generally extremely costly and inherently non-scalable if applied indiscriminately. By contrast, highly scalable coordination approaches (such as epidemic protocols, eventual consistency, or self-organizing overlays) perform much better when the size of a system increases, but do not, in most cases, provide any strong guarantees in terms of consistency or agreement.
The above four objectives explore these tensions from four complementary angles: from an architectural perspective (Objective 1), from the point of view of a fundamental system-wide guarantee (privacy protection, Objective 2), looking at one universal scalable mechanism (network diffusion, Objective 3), and considering the interplay between modularity and computability in large-scale systems (Objective 4). These four objectives range from practical concerns (Objectives 1 and 2) to more theoretical questions (Objectives 3 and 4), yet present strong synergies and fertile interaction points. E.g. better understanding network diffusion (Objective 3) is a key enabler to develop more private decentralized systems (Objective 2), while the development of a theoretically sound modular computability hierarchy (Objective 4) will have a direct impact on our work on hybrid architectures (Objective 1).
International and industrial relations
Formal academic collaborations (collaborative and bilateral projects)
- Computer Science Institute of Goiania, Brazil
- EPFL, Switzerland
- Hong Kong Polytechnic University, Hong Kong
- Inria Lille, France
- Inria Paris, France
- Laboratoire d'Informatique Fondamentale de Marseille (LIF), France
- Sorbonne University, Paris, France
- Télécom ParisTech, France
- Univeristy of Bordeaux, Labri, France
- University Paris-Diderot, France
- University of Nantes, LS2N, France
- University of South Brittany, France
- Universität Bremen, Germany
- Vérimag, Grenoble
Formal industrial collaborations (collaborative projects and bilateral contracts)
- Google, USA
- Mediego, Rennes
- Orange, France
- Snips, Paris
Research teams of the same theme :
- COAST - Web Scale Trustworthy Collaborative Service Systems
- CTRL-A - Control for safe Autonomic computing systems
- DELYS - DistributEd aLgorithms and sYStems
- MIMOVE - Middleware on the Move
- MYRIADS - Design and Implementation of Autonomous Distributed Systems
- SPIRALS - Self-adaptation for distributed services and large software systems
- STACK - Software Stack for Massively Geo-Distributed Infrastructures
- WHISPER - Well Honed Infrastructure Software for Programming Environments and Runtimes