Redfish Green500 Benchmarker (RGB): Towards Automation of the Green500 Process for Data Centers

被引:0
|
作者
Hojati, Elham [1 ]
Hass, Jon [2 ]
Sill, Alan [1 ]
Chen, Yong [1 ]
机构
[1] Texas Tech Univ, Lubbock, TX 79409 USA
[2] Dell Inc, Austin, TX USA
基金
美国国家科学基金会;
关键词
Redfish Standard; Green500; Performance; Power Usage; Energy Efficiency; Energy Consumption; Data Center; Supercomputer; Cluster; High Performance Computing; PERFORMANCE;
D O I
10.1109/greentech46478.2020.9289729
中图分类号
X [环境科学、安全科学];
学科分类号
08 ; 0830 ;
摘要
The goal of this research study is to develop and demonstrate methods to automate benchmarking the energy efficiency of high performance computing systems based on the Green500 methodology via direct measurements obtained from the baseboard management controllers using Redfish standard, instead of via an external power meter and a manual process. To achieve this goal, we have designed and developed an automatic Green500 benchmark tool based on Redfish, called RGB (Redfish Green500 Benchmarker). This tool also evaluates implementations of the Redfish standard to determine their ability to meet the requirements of the Green500 benchmarking protocols. We further develop another tool, RGB Checker, which checks the level of the accuracy and the precision of the RGB tool based on the Redfish standard. We have performed validation tests using these tools on a production cluster, on several different testbeds with various types of servers, and on a simulated environment.
引用
收藏
页码:47 / 52
页数:6
相关论文
共 14 条
  • [1] The Green500 list: escapades to exascale
    Scogland, Tom
    Subramaniam, Balaji
    Feng, Wu-Chun
    [J]. COMPUTER SCIENCE-RESEARCH AND DEVELOPMENT, 2013, 28 (2-3): : 109 - 117
  • [2] The Green500 List: Year One
    Feng, W.
    Scogland, T.
    [J]. 2009 IEEE INTERNATIONAL SYMPOSIUM ON PARALLEL & DISTRIBUTED PROCESSING, VOLS 1-5, 2009, : 1976 - 1982
  • [3] The Green500 List: Encouraging sustainable supercomputing
    Feng, Wu-Chun
    Cameron, Kirk W.
    [J]. COMPUTER, 2007, 40 (12) : 50 - +
  • [4] Qualifying for the Green500: Experience with the newest generation of supercomputers at LANL
    Yilk, Todd
    [J]. SUSTAINABLE COMPUTING-INFORMATICS & SYSTEMS, 2018, 18 : 25 - 33
  • [5] Trends in Energy-Efficient Computing: A Perspective from the Green500
    Subramaniam, Balaji
    Saunders, Winston
    Scogland, Tom
    Feng, Wu-chun
    [J]. 2013 INTERNATIONAL GREEN COMPUTING CONFERENCE (IGCC), 2013,
  • [6] Node Variability in Large-Scale Power Measurements: Perspectives from the Green500, Top500 and EEHPCWG
    Scogland, Thomas
    Azose, Jonathan
    Rohr, David
    Rivoire, Suzanne
    Bates, Natalie
    Hackenberg, Daniel
    [J]. PROCEEDINGS OF SC15: THE INTERNATIONAL CONFERENCE FOR HIGH PERFORMANCE COMPUTING, NETWORKING, STORAGE AND ANALYSIS, 2015,
  • [7] Lattice-CSC: Optimizing and Building an Efficient Supercomputer for Lattice-QCD and to Achieve First Place in Green500
    Rohr, David
    Bach, Matthias
    Neskovic, Gvozden
    Lindenstruth, Volker
    Pinke, Christopher
    Philipsen, Owe
    [J]. HIGH PERFORMANCE COMPUTING, ISC HIGH PERFORMANCE 2015, 2015, 9137 : 179 - 196
  • [8] The L-CSC cluster: Optimizing power efficiency to become the greenest supercomputer in the world in the Green500 list of November 2014
    Rohr, David
    Nešković, Gvozden
    Lindenstruth, Volker
    [J]. Supercomputing Frontiers and Innovations, 2015, 2 (03) : 41 - 48
  • [9] Full Scaling Automation for Sustainable Development of Green Data Centers
    Wang, Shiyu
    Sun, Yinbo
    Shi, Xiaoming
    Zhu Shiyi
    Ma, Lin-Tao
    Zhang, James
    Zheng, YangFei
    Jian, Liu
    [J]. PROCEEDINGS OF THE THIRTY-SECOND INTERNATIONAL JOINT CONFERENCE ON ARTIFICIAL INTELLIGENCE, IJCAI 2023, 2023, : 6264 - 6271
  • [10] A Green Greedy Process Scheduler for Cloud Data Centers
    Karthik, C.
    Gupta, Aayush
    Chandrasekaran, K.
    [J]. 2014 INTERNATIONAL CONFERENCE ON CONTEMPORARY COMPUTING AND INFORMATICS (IC3I), 2014, : 1302 - 1309