Mango-IO: I/O Metrics Consistency Analysis

被引:0
作者
Liem, Radita [1 ]
Oeste, Sebastian [2 ]
Lofstead, Jay [3 ]
Kunkel, Julian [4 ]
机构
[1] Rhein Westfal TH Aachen, Aachen, Germany
[2] Tech Univ Dresden, Dresden, Germany
[3] Sandia Natl Labs, POB 5800, Albuquerque, NM 87185 USA
[4] Gottingen Univ, GWDG, Gottingen, Germany
来源
2023 IEEE INTERNATIONAL CONFERENCE ON CLUSTER COMPUTING WORKSHOPS, CLUSTER WORKSHOPS | 2023年
关键词
performance analysis tools; consistency analysis; Recorder; Darshan; Score-P; Vampir; I/O;
D O I
10.1109/CLUSTERWorkshops61457.2023.00013
中图分类号
TP3 [计算技术、计算机技术];
学科分类号
0812 ;
摘要
Performance tools are inseparable from complex HPC applications' performance analysis and engineering life cycles. Due to the application's complexity, various performance analysis tools are created to serve different analysis purposes and provide a deeper look at certain aspects of the applications. Although these tools might operate differently, having coherent information and consistent metrics across all tools is mandatory for ensuring analysis continuity. It is common for performance analysts to switch their usual performance tools due to various reasons and limitations. In this work, we look specifically at the I/O performance analysis tools landscape and introduce Mango-IO to verify the result consistencies between tools and provide tool-agnostic metrics calculation methods. Our analysis and case study provides lesson learned and guideline for ensuring measurement continuity and comparability.
引用
收藏
页码:18 / 24
页数:7
相关论文
共 17 条
  • [1] Drishti: Guiding End-Users in the I/O Optimization Journey
    Bez, Jean Luca
    Ather, Hammad
    Byna, Suren
    [J]. 2022 IEEE/ACM INTERNATIONAL PARALLEL DATA SYSTEMS WORKSHOP (PDSW), 2022, : 1 - 6
  • [2] I/O Bottleneck Detection and Tuning: Connecting the Dots using Interactive Log Analysis
    Bez, Jean Luca
    Tang, Houjun
    Xie, Bing
    Williams-Young, David
    Latham, Rob
    Ross, Rob
    Oral, Sarp
    Byna, Suren
    [J]. PROCEEDINGS OF IEEE/ACM SIXTH INTERNATIONAL PARALLEL DATA SYSTEMS WORKSHOP (PDSW 2021), 2021, : 15 - 22
  • [3] Carns P, 2009, 2009 IEEE INTERNATIONAL CONFERENCE ON CLUSTER COMPUTING AND WORKSHOPS, P516
  • [4] Carns Philip., 2021, Dagstuhl Reports, V11, P16
  • [5] High order conservative finite difference scheme for variable density low Mach number turbulent flows
    Desjardins, Olivier
    Blanquart, Guillaume
    Balarac, Guillaume
    Pitsch, Heinz
    [J]. JOURNAL OF COMPUTATIONAL PHYSICS, 2008, 227 (15) : 7125 - 7159
  • [6] Isakov M., 2020, P SC20 INT C HIGH, P1, DOI 10.1109/SC41405.2020.00037
  • [7] Property-based Sensitivity Analysis: An approach to identify model implementation and integration errors
    Iwanaga, Takuya
    Sun, Xifu
    Wang, Qian
    Guillaume, Joseph H. A.
    Croke, Barry F. W.
    Rahman, Joel
    Jakeman, Anthony J.
    [J]. ENVIRONMENTAL MODELLING & SOFTWARE, 2021, 139
  • [8] Knupfer Andreas, 2012, Tools for High Performance Computing 2011, P79
  • [9] Tools for Analyzing Parallel I/O
    Kunkel, Julian Martin
    Betke, Eugen
    Bryson, Matt
    Carns, Philip
    Francis, Rosemary
    Frings, Wolfgang
    Laifer, Roland
    Mendez, Sandra
    [J]. HIGH PERFORMANCE COMPUTING, ISC HIGH PERFORMANCE 2018, 2018, 11203 : 49 - 70
  • [10] Chipmunk: Investigating Crash-Consistency in Persistent-Memory File Systems
    LeBlanc, Hayley
    Pailoor, Shankara
    Om, Saran K. R. E.
    Dillig, Isil
    Bornholt, James
    Chidambaram, Vijay
    [J]. PROCEEDINGS OF THE EIGHTEENTH EUROPEAN CONFERENCE ON COMPUTER SYSTEMS, EUROSYS 2023, 2023, : 718 - 733