ABSTRACT
Realizing highly available datacenter power infrastructure is an extremely expensive proposition with costs more than doubling as we move from three 9's (Tier-1) to six 9's (Tier-4) of availability. Existing approaches only consider the cost/availability trade-off for a restricted set of power infrastructure configurations, relying mainly on component redundancy. A number of additional knobs such as centralized vs. distributed component placement and power-feed interconnect topology also exist, whose impact has only been studied in limited forms. In this paper, we develop detailed datacenter availability models using Continuous-time Markov Chains and Reliability Block Diagrams to quantify the cost-availability trade-off offered by these power infrastructure knobs.
- APC UPS. http://www.apc.com/products/.Google Scholar
- APC White paper 75: Comparing UPS System Design Configurations, 2008.Google Scholar
- L. A. Barroso and U. Holzle. The Datacenter as a Computer: Design of Warehouse-Scale Machines. Morgan and Claypool Publishers, 2009. Google ScholarDigital Library
- Gold Book, IEEE Recommended Practice for the Design of Reliable Industrial and Commercial Power Systems, 1998.Google Scholar
- Google Servers-level Batteries. news.cnet.com/8301-1001_3-10209580-92.html.Google Scholar
- J. Hamilton. Internet-scale Service Infrastructure Efficiency, ISCA Keynote, 2009. Google ScholarDigital Library
- Liebert White paper: Choosing The Right UPS for Small and Midsize Datacenters, 2004.Google Scholar
- M. Marwah, P. Maciel, A. Shah, R. Sharma, T. Christian, V. Almeida, C. Araújo, E. Souza, G. Callou, B. Silva, S. Galdino, and J. Pires. Quantifying the sustainability impact of data center availability. SIGMETRICS Perform. Eval. Rev., 2010. Google ScholarDigital Library
- S. Pelley, D. Meisner, P. Zandevakili, T. F. Wenisch, and J. Underwood. Power Routing: Dynamic Power Provisioning in the Data Center. In Proceedings of the Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS), 2010. Google ScholarDigital Library
- K. G. B. W. P. Turner, J. H. Seader. Tier Classifications Define Site Infrastructure Performance, 2008.Google Scholar
Index Terms
- Towards realizing a low cost and highly available datacenter power infrastructure
Recommendations
Low-latency multi-datacenter databases using replicated commit
Web service providers have been using NoSQL datastores to provide scalability and availability for globally distributed data at the cost of sacrificing transactional guarantees. Recently, major web service providers like Google have moved towards ...
Highly available transactions: virtues and limitations
To minimize network latency and remain online during server failures and network partitions, many modern distributed data storage systems eschew transactional functionality, which provides strong semantic guarantees for groups of multiple operations ...
Comments