Abstract
With the advent of Internet services, big data and cloud computing, high-throughput computing has generated much research interest, especially on high-throughput cloud servers. However, three basic questions are still not satisfactorily answered: (1) What are the basic metrics (what throughput and high-throughput of what)? (2) What are the main factors most beneficial to increasing throughput? (3) Are there any fundamental constraints and how high can the throughput go? This article addresses these issues by utilizing the fifty-year progress in Little’s law, to reveal three fundamental relations among the seven basic quantities of throughput (λ), number of active threads (L), waiting time (W), system power (P), thread energy (E), Watts per thread ω, threads per Joule θ. In addition to Little’s law L = λW, we obtain P = λE and λ = Lωθ, under reasonable assumptions. These equations help give a first order estimation of performance and power consumption targets for billion-thread cloud servers.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Barroso L, Hoelzle U. The datacenter as a computer: an introduction to the design of warehouse-scale machines. Synthesis Lectures on Computer Architecture, 2009, 4(1): 1–108
Cloudstone. http://radlab.cs.berkeley.edu/wiki/projects/cloudstone
Little J. Little’s law as viewed on its 50th anniversary. Operational Research, 2011, 59(3): 536–549
Little J, Graves S. Little’s law. In: Chhajed D, Lowe T J, eds. Building Intuition: Insights from Basic Operations Management Models and Principles. New York: Springer Science and Business Media LLC, 2008
Garland M, Kirk D. Understanding throughput-oriented architectures. Communications of the ACM, 2010, 53(11): 58–66
Hanlon C. A conversation with john hennessy and david patterson. ACM Queue, 2006–2007, 4(10): 14–22
Brumelle S L. On the relation between customer and time averages queues. Journal of Applied Probability, 1971, 8(3): 508–520
Heyman D, Stidham S J. The relation between customer and time averages in queues. Operational Research, 1980, 28(4): 983–994
Glanz J. Google details, and defends, its use of electricity. The New York Times, 2011
High-throughput computing. http://research.cs.wisc.edu/condor/htc.html. see also http://en.wikipedia.org/wiki/condor_high-throughput_computing_system and http://en.wikipedia.org/wiki/high-throughput_computing
Many-task computing. http://en.wikipedia.org/wiki/Many-task_computing
Little J. A proof for the queuing formula: L = λW. Operational Research, 1961, 9(3): 383–387
El-Taha M, Stidham S. Sample-Path Analysis of Queueing Systems. Springer Netherlands, 1999
Author information
Authors and Affiliations
Corresponding author
Additional information
Zhiwei Xu is a professor and CTO of the Institute of Computing Technology of the Chinese Academy of Sciences. His research interests include network computing science and Internet operating systems. His prior industrial experience includs chief engineer of Dawning Corp., a leading high-performance computer vendor in China. He currently leads “Cloud-Sea Computing Systems”, a ten-year research project of the Chinese Academy of Sciences that aims at developing billion-thread computers with elastic processors by 2020. Xu holds a PhD from the University of Southern California.
Rights and permissions
About this article
Cite this article
Xu, Z. How much power is needed for a billion-thread high-throughput server?. Front. Comput. Sci. 6, 339–346 (2012). https://doi.org/10.1007/s11704-012-2071-5
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11704-012-2071-5