TOWARDS A CLOUD COMPUTING RESEARCH AGENDA
📜 Abstract
The 2008 LADIS workshop on Large Scale Distributed Systems brought together leaders from the commercial cloud computing community with researchers working on a variety of topics in distributed computing. The dialog yielded some surprises: some hot research topics seem to be of limited near-term importance to the cloud builders, while some of their practical challenges seem to pose new questions to us as systems researchers. This brief note summarizes our impressions.
✨ Summary
The paper reports lessons from the 2008 LADIS workshop, where distributed-systems researchers compared their priorities with the operational requirements of large commercial cloud providers. It argues that cloud computing should be understood not only as an external utility-like service, but also as a highly automated collection of large-scale data-center mechanisms. The authors emphasize that scalability and robustness often depend more on decoupling, asynchronous operation, autonomous recovery, and gradual convergence than on strong synchronization, distributed locking, ACID transactions, or Byzantine consensus on the critical path.
The proposed research agenda includes power-aware data-center management; formal models, metrics, and verification methods for convergent consistency; stability analysis and scalability testing for large event-notification and management platforms; virtualization-aware distributed-systems design; and architectures based on commodity hardware, autonomous recovery, and resistance to churn, load surges, oscillations, and other destabilizing effects.
Subsequent literature confirms that the paper became a recognized reference in cloud-computing research. A 2016 citation and co-citation analysis of 214 cloud-computing papers included it among the important foundational works used to map major research themes and identify future research directions. (sciencedirect.com) Its proposed emphasis on energy-aware infrastructure was also cited in later algorithmic work on energy-efficient scheduling, including research on partial machine shutdown. (people.iiis.tsinghua.edu.cn) The paper itself was published in ACM SIGACT News in June 2009, volume 40, issue 2, pages 68–80. (pure.royalholloway.ac.uk)