{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,19]],"date-time":"2026-06-19T15:50:53Z","timestamp":1781884253958,"version":"3.54.5"},"reference-count":31,"publisher":"Springer Science and Business Media LLC","issue":"16","license":[{"start":{"date-parts":[[2023,5,15]],"date-time":"2023-05-15T00:00:00Z","timestamp":1684108800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,5,15]],"date-time":"2023-05-15T00:00:00Z","timestamp":1684108800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Supercomput"],"published-print":{"date-parts":[[2023,11]]},"DOI":"10.1007\/s11227-023-05366-1","type":"journal-article","created":{"date-parts":[[2023,5,15]],"date-time":"2023-05-15T16:04:37Z","timestamp":1684166677000},"page":"18445-18479","update-policy":"https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["An empirical study of major page faults for failure diagnosis in cluster systems"],"prefix":"10.1007","volume":"79","author":[{"given":"Edward","family":"Chuah","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Arshad","family":"Jhumka","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sai","family":"Narasimhamurthy","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2023,5,15]]},"reference":[{"key":"5366_CR1","doi-asserted-by":"publisher","unstructured":"Oliner AJ, Kulkarni AV, Aiken A (2010) Using correlated surprise to infer shared influence. In: Proceedings of IEEE\/IFIP International Conference on Dependable Systems and Networks (DSN). https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.1109\/DSN.2010.5544921","DOI":"10.1109\/DSN.2010.5544921"},{"key":"5366_CR2","doi-asserted-by":"publisher","unstructured":"Zheng Z, Yu L, Lan Z, Jones T (2012) 3-dimensional root cause diagnosis via co-analysis. In: Proceedings of ACM International Conference on Autonomic Computing (ICAC). https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.1145\/2371536.2371571","DOI":"10.1145\/2371536.2371571"},{"key":"5366_CR3","doi-asserted-by":"publisher","unstructured":"Chuah E, Jhumka A, Alt S, Evans RT, Suri N (2021) Failure diagnosis for cluster systems using partial correlations. In: Proceedings of IEEE International Symposium on Parallel & Distributed Processing with Applications (ISPA). https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.1109\/ISPA-BDCloud-SocialCom-SustainCom52081.2021.00151","DOI":"10.1109\/ISPA-BDCloud-SocialCom-SustainCom52081.2021.00151"},{"key":"5366_CR4","doi-asserted-by":"publisher","DOI":"10.1177\/1094342014522573","author":"M Snir","year":"2014","unstructured":"...Snir M, Wisniewski RW, Abraham JA, Adve SV, Bagchi S, Balaji P, Belak J, Bose P, Cappello F, Carlson B, Chien AA, Coteus P, Debardeleben NA, Diniz PC, Engelmann C, Erez M, Fazzari S, Geist A, Gupta R, Johnson F, Krishnamoorthy S, Leyffer S, Liberty D, Mitra S, Munson T, Schreiber R, Stearley J, Hensbergen EV (2014) Addressing failures in exascale computing. Int J High Perform Comput Appl. https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.1177\/1094342014522573","journal-title":"Int J High Perform Comput Appl"},{"key":"5366_CR5","doi-asserted-by":"publisher","unstructured":"Martino CD, Baccanico F, Fullop J, Kramer W, Kalbaczyk Z, Iyer R. Lessons learned from the analysis of system failures at petascale: The case of blue waters. In: Proceedings of IEEE\/IFIP International Conference on Dependable Systems and Networks (DSN), p. 2014. https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.1109\/DSN.2014.62","DOI":"10.1109\/DSN.2014.62"},{"key":"5366_CR6","doi-asserted-by":"publisher","unstructured":"Mitra S, Javagal S, Maji AK, Gamblin T, Moody A, Harrell S, Bagchi S (2016) A study of failures in community clusters: The case of conte. In: Proceedings of the 2016 IEEE International Symposium on Software Reliability Engineering Workshops (ISSREW), pp. 189\u2013196. https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.1109\/ISSREW.2016.7","DOI":"10.1109\/ISSREW.2016.7"},{"key":"5366_CR7","doi-asserted-by":"publisher","unstructured":"Gupta S, Patel T, Engelmann C, Tiwari D (2017) Failures in large scale systems: Long-term measurement, analysis, and implications. In: Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis (SC). https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.1145\/3126908.3126937","DOI":"10.1145\/3126908.3126937"},{"key":"5366_CR8","doi-asserted-by":"publisher","unstructured":"Rojas E, Meneses E, Jones T, Maxwell D (2019) Analyzing a five-year failure record of a leadership-class supercomputer. In: Proceedings of the 31st International Symposium on Computer Architecture and High Performance Computing (SBAC-PAD), pp. 196\u2013203. https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.1109\/SBAC-PAD.2019.00040. IEEE","DOI":"10.1109\/SBAC-PAD.2019.00040"},{"key":"5366_CR9","doi-asserted-by":"publisher","unstructured":"Kumar R, Jha S, Mahgoub A, Kalyanam R, Harrell S, Song XC, Kalbarczyk Z, Kramer W, Iyer R, Bagchi S (2020) The mystery of the failing jobs: Insights from operational data from two university-wide computing systems. In: Proceedings of IEEE\/IFIP International Conference on Dependable Systems and Networks (DSN). https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.1109\/DSN48063.2020.00034","DOI":"10.1109\/DSN48063.2020.00034"},{"key":"5366_CR10","doi-asserted-by":"publisher","unstructured":"Liu Z, Lewis R, Kettimuthu R, Harms K, Carns P, Rao N, Foster I, Papka ME (2020) Characterization and identification of HPC applications at leadership computing facility. In: Proceedings of the 34th ACM International Conference on Supercomputing (ICS). Association for Computing Machinery, New York, NY, USA. https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.1145\/3392717.3392774","DOI":"10.1145\/3392717.3392774"},{"key":"5366_CR11","doi-asserted-by":"publisher","first-page":"27","DOI":"10.1016\/j.jpdc.2021.04.001","volume":"154","author":"E Rojas","year":"2021","unstructured":"Rojas E, Meneses E, Jones T, Maxwell D (2021) Understanding failures through the lifetime of a top-level supercomputer. J Parallel Distrib Comput 154:27\u201341. https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.1016\/j.jpdc.2021.04.001","journal-title":"J Parallel Distrib Comput"},{"key":"5366_CR12","doi-asserted-by":"publisher","unstructured":"Ferreira KB, Levy S, Hemmert J, Pedretti K (2022) Understanding memory failures on a petascale Arm system. In: Proceedings of the 31st ACM International Symposium on High-Performance Parallel and Distributed Computing (HPDC), pp. 84\u201396. Association for Computing Machinery, New York, NY, USA. https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.1145\/3502181.3531465","DOI":"10.1145\/3502181.3531465"},{"key":"5366_CR13","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2015.02.054","author":"JP Abraham","year":"2015","unstructured":"Abraham JP, Mathew S (2015) A novel approach to improve the processor performance with page replacement method. Proc Comput Sci. https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.1016\/j.procs.2015.02.054","journal-title":"Proc Comput Sci"},{"key":"5366_CR14","doi-asserted-by":"publisher","DOI":"10.1145\/3547142","author":"C Tirumalasetty","year":"2022","unstructured":"Tirumalasetty C, Chou CC, Reddy N, Gratz P, Abouelwafa A (2022) Reducing minor page fault overheads through enhanced page walker. ACM Trans Arch Code Optim. https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.1145\/3547142","journal-title":"ACM Trans Arch Code Optim"},{"issue":"12","key":"5366_CR15","doi-asserted-by":"publisher","first-page":"3990","DOI":"10.1109\/TPDS.2022.3175666","volume":"33","author":"A Psistakis","year":"2022","unstructured":"Psistakis A, Chrysos N, Chaix F, Asiminakis M, Gianioudis M, Xirouchakis P, Papaefstathiou V, Katevenis M (2022) Optimized page fault handling during RDMA. IEEE Trans Parallel Distrib Syst 33(12):3990\u20134005. https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.1109\/TPDS.2022.3175666","journal-title":"IEEE Trans Parallel Distrib Syst"},{"key":"5366_CR16","doi-asserted-by":"publisher","unstructured":"Chuah E, Jhumka A, Narasimharmuthy S, Hammond J, Browne JC, Barth B (2013) Linking resource usage anomalies with system failures from cluster log data. In: Proceedings of IEEE International Symposium on Reliable Distributed Systems (SRDS). https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.1109\/SRDS.2013.20","DOI":"10.1109\/SRDS.2013.20"},{"key":"5366_CR17","doi-asserted-by":"publisher","unstructured":"Chuah E, Jhumka A, Browne JC, Gurumdimma N, Narasimharmuthy S, Barth B (2016) Using message logs and resource use data for cluster failure diagnosis. In: Proceedings of IEEE International Conference on High Performance Computing (HiPC). https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.1109\/HiPC.2016.035","DOI":"10.1109\/HiPC.2016.035"},{"key":"5366_CR18","doi-asserted-by":"publisher","unstructured":"Fu X, Ren R, Zhan J, Zhou W, Jia Z, Lu G (2012) Logmaster: Mining event correlations in logs of large-scale cluster systems. In: Proceedings of IEEE International Symposium on Reliable Distributed Systems (SRDS), pp. 71\u201380. https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.1109\/SRDS.2012.40","DOI":"10.1109\/SRDS.2012.40"},{"key":"5366_CR19","doi-asserted-by":"publisher","unstructured":"Fu X, Ren R, McKee SA, Zhan J, Sun N (2014) Digging deeper into cluster system logs for failure prediction and root cause diagnosis. In: Proceedings of IEEE International Conference on Cluster Computing (CLUSTER). https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.1109\/CLUSTER.2014.6968768","DOI":"10.1109\/CLUSTER.2014.6968768"},{"key":"5366_CR20","doi-asserted-by":"publisher","unstructured":"Hammond JL, Minyard T, Browne J (2010) End-to-end framework for fault management for open source clusters: Ranger. In: Proceedings of ACM TeraGrid Conference. https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.1145\/1838574.1838583","DOI":"10.1145\/1838574.1838583"},{"issue":"1","key":"5366_CR21","doi-asserted-by":"publisher","first-page":"11","DOI":"10.1109\/TDSC.2004.2","volume":"1","author":"A Avizienis","year":"2004","unstructured":"Avizienis A, Lapire J-C, Randell B, Landwehr C (2004) Basic concepts and taxonomy of dependable and secure computing. IEEE Trans Dependable Secure Comput 1(1):11\u201333. https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.1109\/TDSC.2004.2","journal-title":"IEEE Trans Dependable Secure Comput"},{"key":"5366_CR22","volume-title":"Computer system architecture","author":"MM Mano","year":"1993","unstructured":"Mano MM (1993) Computer system architecture. Prentice Hall International Edition, Boston"},{"key":"5366_CR23","volume-title":"Introduction to data mining","author":"P-N Tan","year":"2006","unstructured":"Tan P-N, Steinbach M, Kumar V (2006) Introduction to data mining. Addison-Wesley, Boston"},{"key":"5366_CR24","doi-asserted-by":"publisher","unstructured":"Evans RT, Browne JC, Barth WL (2016) Understanding application and system performance through system-wide monitoring. In: Proceedings of IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW). https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.1109\/IPDPSW.2016.145","DOI":"10.1109\/IPDPSW.2016.145"},{"key":"5366_CR25","doi-asserted-by":"publisher","DOI":"10.1109\/MCSE.2015.68","author":"JT Palmer","year":"2015","unstructured":"Palmer JT, Gallo SM, Furlani TR, Jones MD, DeLeon RL, White JP, Simakov N, Patra AK, Sperhac J, Yearke T, Rathsam R, Innus M, Cornelius CD, Browne JC, Barth WL, Evans RT (2015) Open XDMoD: a tool for the comprehensive management of high-performance computing resources. Comput Sci Eng. https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.1109\/MCSE.2015.68","journal-title":"Comput Sci Eng"},{"key":"5366_CR26","volume-title":"Statistics: the art and science of learning from data","author":"A Agresti","year":"2009","unstructured":"Agresti A, Franklin C (2009) Statistics: the art and science of learning from data. Prentice Hall International, Boston"},{"issue":"1","key":"5366_CR27","doi-asserted-by":"crossref","first-page":"267","DOI":"10.1111\/j.2517-6161.1996.tb02080.x","volume":"58","author":"R Tibshirani","year":"1996","unstructured":"Tibshirani R (1996) Regression shrinkage and selection via the lasso. J Roy Stat Soc: Ser B (Methodol) 58(1):267\u2013288","journal-title":"J Roy Stat Soc: Ser B (Methodol)"},{"issue":"1","key":"5366_CR28","doi-asserted-by":"publisher","first-page":"80","DOI":"10.1080\/00401706.2000.10485983","volume":"42","author":"AE Hoerl","year":"2000","unstructured":"Hoerl AE, Kennard RW (2000) Ridge regression: Biased estimation for nonorthogonal problems. Technometrics 42(1):80\u201386","journal-title":"Technometrics"},{"issue":"2","key":"5366_CR29","doi-asserted-by":"publisher","first-page":"301","DOI":"10.1111\/j.1467-9868.2005.00503.x","volume":"67","author":"H Zou","year":"2005","unstructured":"Zou H, Hastie T (2005) Regularization and variable selection via the elastic net. J Royal Stat Soc Ser B (Stat Methodol) 67(2):301\u2013320","journal-title":"J Royal Stat Soc Ser B (Stat Methodol)"},{"key":"5366_CR30","volume-title":"Probab Stat Eng Sci","author":"RE Walpole","year":"1998","unstructured":"Walpole RE, Myers RH, Myers SL (1998) Probab Stat Eng Sci. Prentice Hall International, Boston"},{"key":"5366_CR31","doi-asserted-by":"publisher","unstructured":"Das A, M\u00fcller F, Rountree B (2021) Systemic assessment of node failures in HPC production platforms. In: Proceedings of IEEE International Parallel and Distributed Processing Symposium (IPDPS). https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.1109\/IPDPS49936.2021.00035","DOI":"10.1109\/IPDPS49936.2021.00035"}],"container-title":["The Journal of Supercomputing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/link.springer.com\/content\/pdf\/10.1007\/s11227-023-05366-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/link.springer.com\/article\/10.1007\/s11227-023-05366-1\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/link.springer.com\/content\/pdf\/10.1007\/s11227-023-05366-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,20]],"date-time":"2024-10-20T11:42:45Z","timestamp":1729424565000},"score":1,"resource":{"primary":{"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/link.springer.com\/10.1007\/s11227-023-05366-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,5,15]]},"references-count":31,"journal-issue":{"issue":"16","published-print":{"date-parts":[[2023,11]]}},"alternative-id":["5366"],"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.1007\/s11227-023-05366-1","relation":{},"ISSN":["0920-8542","1573-0484"],"issn-type":[{"value":"0920-8542","type":"print"},{"value":"1573-0484","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,5,15]]},"assertion":[{"value":"28 April 2023","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"15 May 2023","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"All authors certify that they have no affiliations with or involvement in any organization or entity with any financial interest or non-financial interest in the subject matter or materials discussed in this manuscript.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical approval"}}]}}