Determination of the configuration computer systems high-performance handling large volumes of data
DOI:
https://doi.org/10.20535/RADAP.2012.49.77-82Keywords:
high-performance computing, computer cluster, storage system, network queuing, mathematical model of computing complexAbstract
This paper provides a mathematical model of computing complex (a network of queuing). In what volume of processed data outgrows memory compute nodes, so all data are divided into equal blocks of fixed size that are distributed through volumes of data storage and process the task is divided into cycles so that one node computing cluster process one unit data for one cycle. Also describes the method for determining the optimal (by the criterion of productivity) complex configurations based on industry standard benchmarks computing clusters and storage systems.
References
Суперкомпьютерные технологии в науке, образовании и промышленности (второй выпуск) / под редакцией: академика В.А.Садовничего, академика Г.И.Савина, чл.-корр. РАН Вл.В.Воеводина. – М. : Изд. Московского ун-та, 2010. – 208с.
Mills R., Sripathi V., Mahinthakumar G., Hammond G., Lichtner P., Smith B. Engineering for Scalable Performance on Cray XT and IBM BlueGene Architectures, 2010.
Мясников В.А., Мельников Ю.Н., Абросимов Л.И.. Методы автоматизированного проектирования систем телеобработки данных. – М. : Энергоатомиздат, 1992. – 299с.
Lee E.K. Performance Modeling and Analysis of Disk Arrays. University of California at Berkeley, 1993.
Downloads
Published
How to Cite
Issue
Section
License
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).