Methodology to quantify I/O performance based on analytical models

被引:0
|
作者
Heger, DA [1 ]
机构
[1] IBM Corp, Austin, TX 78758 USA
关键词
D O I
暂无
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
The goal of this study was to first, identify a pragmatic approach to evaluate and quantify I/O performance and second, to convert the approach into a working analytical I/O model that allows quantifying I/O performance under real world conditions. The focus was on incorporating OS, as well as hardware specific I/O optimization features into the analysis and to establish a framework that allows quantifying the performance of potential hardware configuration alternatives without the necessity to physically implement the different infrastructures. The point of convergence was on modeling an entire I/O stack, while incorporating the major software and hardware I/O optimization features that are present in the I/O path.
引用
收藏
页码:363 / 375
页数:13
相关论文
共 50 条
  • [1] A KNOWLEDGE-BASED METHODOLOGY FOR TUNING ANALYTICAL MODELS
    FREEDMAN, RS
    STUZIN, GJ
    IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS, 1991, 21 (02): : 347 - 358
  • [2] An analytical methodology to quantify the incorporation of enzymes in polyalkylcyanoacrylate nanoparticles based on size exclusion chromatography
    Martins, MBF
    Supico, A
    Simoes, SID
    Gaspar, R
    Cruz, MEM
    JOURNAL OF PHARMACEUTICAL AND BIOMEDICAL ANALYSIS, 1997, 15 (06) : 811 - 818
  • [3] Evaluation of analytical performance based on partial order methodology
    Carlsen, Lars
    Bruggernann, Rainer
    Kenessova, Olga
    Erzhigitov, Erkin
    TALANTA, 2015, 132 : 285 - 293
  • [4] Measurement-based modeling and analysis methodology for characterizing parallel I/O performance
    Sharma, S
    Iyer, RK
    FIFTH INTERNATIONAL CONFERENCE ON HIGH PERFORMANCE COMPUTING, PROCEEDINGS, 1998, : 391 - 398
  • [5] Methodology to evaluate performance of the I/O systems on High Performance Computers
    Mendez, Sandra
    Rexachs, Dolores
    JOURNAL OF COMPUTER SCIENCE & TECHNOLOGY, 2013, 13 (03): : 173 - 174
  • [6] Analytical Models Quantify Military Benefit of Collaborative Search
    Friedman, Melvin H.
    Du Bosq, Todd W.
    Flug, Eric A.
    INFRARED IMAGING SYSTEMS: DESIGN, ANALYSIS, MODELING, AND TESTING XXI, 2010, 7662
  • [7] VALIDATION OF AN ANALYTICAL METHODOLOGY TO QUANTIFY CYANOGENIC GLUCOSIDES IN COMMERCIAL CASSAVA PRODUCTS
    Ortiz, Darwin
    Sanchez, Teresa
    Acosta, Harold
    Pachon, Helena
    VITAE-REVISTA DE LA FACULTAD DE QUIMICA FARMACEUTICA, 2011, 18 (03): : 318 - 323
  • [8] A statistics-based performance testing methodology: a case study for the I/O bound tasks
    Sultanov, Andriy
    Protsyk, Maksym
    Kuzyshyn, Maksym
    Omelkina, Daria
    Shevchuk, Vyacheslav
    Farenyuk, Oleg
    2022 IEEE 17TH INTERNATIONAL CONFERENCE ON COMPUTER SCIENCES AND INFORMATION TECHNOLOGIES (CSIT), 2022, : 486 - 489
  • [9] An analytical methodology to derive power models based on hardware and software metrics
    Dolz, Manuel F.
    Kunkel, Julian
    Chasapis, Konstantinos
    Catalan, Sandra
    COMPUTER SCIENCE-RESEARCH AND DEVELOPMENT, 2016, 31 (04): : 165 - 174
  • [10] Collective I/O tuning using analytical and machine learning models
    Isaila, Florin
    Balaprakash, Prasanna
    Wild, Stefan M.
    Kimpe, Dries
    Latham, Rob
    Ross, Rob
    Hovland, Paul
    2015 IEEE INTERNATIONAL CONFERENCE ON CLUSTER COMPUTING - CLUSTER 2015, 2015, : 128 - 137