Type
Conference PaperKAUST Department
Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) DivisionComputer Science Program
Date
2017-09-27Online Publication Date
2017-09-27Print Publication Date
2017Permanent link to this record
http://hdl.handle.net/10754/625905
Metadata
Show full item recordAbstract
Multi-tenant distributed systems composed of small services, such as Service-oriented Architectures (SOAs) and Micro-services, raise new challenges in attaining high performance and efficient resource utilization. In these systems, a request execution spans tens to thousands of processes, and the execution paths and resource demands on different services are generally not known when a request first enters the system. In this paper, we highlight the fundamental challenges of regulating load and scheduling in SOAs while meeting end-to-end performance objectives on metrics of concern to both tenants and operators. We design Wisp, a framework for building SOAs that transparently adapts rate limiters and request schedulers system-wide according to operator policies to satisfy end-to-end goals while responding to changing system conditions. In evaluations against production as well as synthetic workloads, Wisp successfully enforces a range of end-to-end performance objectives, such as reducing average latencies, meeting deadlines, providing fairness and isolation, and avoiding system overload.Citation
Suresh L, Bodik P, Menache I, Canini M, Ciucu F (2017) Distributed resource management across process boundaries. Proceedings of the 2017 Symposium on Cloud Computing - SoCC ’17. Available: http://dx.doi.org/10.1145/3127479.3132020.Sponsors
We thank our shepherd, Iqbal Mohomed, and the anonymous reviewers for their feedback. We thank Madan Musuvathi, Srikanth Kandula, and Virajith Jalaparti for the useful discussions that helped shape this paper.Additional Links
https://dl.acm.org/citation.cfm?doid=3127479.3132020ae974a485f413a2113503eed53cd6c53
10.1145/3127479.3132020