Understanding failures through the lifetime of a top-level supercomputer

Elvis Rojas; Esteban Meneses; Terry Jones; Don Maxwell

doi:10.1016/j.jpdc.2021.04.001

Understanding failures through the lifetime of a top-level supercomputer

Elvis Rojas, Esteban Meneses, Terry Jones, Don Maxwell

Research output: Contribution to journal › Article › peer-review

2 Scopus citations

Abstract

High performance computing systems are required to solve grand challenges in many scientific disciplines. These systems assemble many components to be powerful enough for solving extremely complex problems. An inherent consequence is the intricacy of the interaction of all those components, especially when failures come into the picture. It is crucial to develop an understanding of how these systems fail to design reliable supercomputing platforms in the future. This paper presents the results on studying multi-year failure and workload records of a powerful supercomputer that topped the world rankings. We provide a thorough analysis of the data and characterize the reliability of the system through several dimensions: failure classification, failure-rate modelling, and interplay between failures and workload. The results shed some light on the dynamics of top-level supercomputers and sensitive areas ripe for improvement.

Original language	English
Pages (from-to)	27-41
Number of pages	15
Journal	Journal of Parallel and Distributed Computing
Volume	154
DOIs	https://doi.org/10.1016/j.jpdc.2021.04.001
State	Published - Aug 2021

Funding

This research was partially supported by a machine allocation on Kabré supercomputer at the Costa Rica National High Technology Center. Notice: This manuscript has been authored by UT-Battelle, LLC under Contract No. DE-AC05-00OR22725 with the U.S. Department of Energy. The United States Government retains and the publisher, by accepting the article for publication, acknowledges that the United States Government retains a non-exclusive, paid-up, irrevocable, world-wide license to publish or reproduce the published form of this manuscript, or allow others to do so, for United States Government purposes. The Department of Energy will provide public access to these results of federally sponsored research in accordance with the DOE Public Access Plan ( http://energy.gov/downloads/doe-public-access-plan ).

Funders	Funder number
Costa Rica National High Technology Center
U.S. Department of Energy

Keywords

Failure analysis
Fault tolerance
High performance computing
Resilience

Access to Document

10.1016/j.jpdc.2021.04.001

Cite this

@article{9323990b6b054ace89651396d49cfe73,

title = "Understanding failures through the lifetime of a top-level supercomputer",

abstract = "High performance computing systems are required to solve grand challenges in many scientific disciplines. These systems assemble many components to be powerful enough for solving extremely complex problems. An inherent consequence is the intricacy of the interaction of all those components, especially when failures come into the picture. It is crucial to develop an understanding of how these systems fail to design reliable supercomputing platforms in the future. This paper presents the results on studying multi-year failure and workload records of a powerful supercomputer that topped the world rankings. We provide a thorough analysis of the data and characterize the reliability of the system through several dimensions: failure classification, failure-rate modelling, and interplay between failures and workload. The results shed some light on the dynamics of top-level supercomputers and sensitive areas ripe for improvement.",

keywords = "Failure analysis, Fault tolerance, High performance computing, Resilience",

author = "Elvis Rojas and Esteban Meneses and Terry Jones and Don Maxwell",

note = "Publisher Copyright: {\textcopyright} 2021 Elsevier Inc.",

year = "2021",

month = aug,

doi = "10.1016/j.jpdc.2021.04.001",

language = "English",

volume = "154",

pages = "27--41",

journal = "Journal of Parallel and Distributed Computing",

issn = "0743-7315",

publisher = "Elsevier",

}

TY - JOUR

T1 - Understanding failures through the lifetime of a top-level supercomputer

AU - Rojas, Elvis

AU - Meneses, Esteban

AU - Jones, Terry

AU - Maxwell, Don

PY - 2021/8

Y1 - 2021/8

N2 - High performance computing systems are required to solve grand challenges in many scientific disciplines. These systems assemble many components to be powerful enough for solving extremely complex problems. An inherent consequence is the intricacy of the interaction of all those components, especially when failures come into the picture. It is crucial to develop an understanding of how these systems fail to design reliable supercomputing platforms in the future. This paper presents the results on studying multi-year failure and workload records of a powerful supercomputer that topped the world rankings. We provide a thorough analysis of the data and characterize the reliability of the system through several dimensions: failure classification, failure-rate modelling, and interplay between failures and workload. The results shed some light on the dynamics of top-level supercomputers and sensitive areas ripe for improvement.

AB - High performance computing systems are required to solve grand challenges in many scientific disciplines. These systems assemble many components to be powerful enough for solving extremely complex problems. An inherent consequence is the intricacy of the interaction of all those components, especially when failures come into the picture. It is crucial to develop an understanding of how these systems fail to design reliable supercomputing platforms in the future. This paper presents the results on studying multi-year failure and workload records of a powerful supercomputer that topped the world rankings. We provide a thorough analysis of the data and characterize the reliability of the system through several dimensions: failure classification, failure-rate modelling, and interplay between failures and workload. The results shed some light on the dynamics of top-level supercomputers and sensitive areas ripe for improvement.

KW - Failure analysis

KW - Fault tolerance

KW - High performance computing

KW - Resilience

UR - http://www.scopus.com/inward/record.url?scp=85105698600&partnerID=8YFLogxK

U2 - 10.1016/j.jpdc.2021.04.001

DO - 10.1016/j.jpdc.2021.04.001

M3 - Article

AN - SCOPUS:85105698600

SN - 0743-7315

VL - 154

SP - 27

EP - 41

JO - Journal of Parallel and Distributed Computing

JF - Journal of Parallel and Distributed Computing

ER -

Understanding failures through the lifetime of a top-level supercomputer

Abstract

Funding

Keywords

Access to Document

Other files and links

Fingerprint

Cite this