{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,19]],"date-time":"2026-02-19T02:06:53Z","timestamp":1771466813109,"version":"3.50.1"},"publisher-location":"Cham","reference-count":30,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031998539","type":"print"},{"value":"9783031998546","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,8,27]],"date-time":"2025-08-27T00:00:00Z","timestamp":1756252800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,8,27]],"date-time":"2025-08-27T00:00:00Z","timestamp":1756252800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026]]},"DOI":"10.1007\/978-3-031-99854-6_14","type":"book-chapter","created":{"date-parts":[[2025,8,26]],"date-time":"2025-08-26T05:09:05Z","timestamp":1756184945000},"page":"205-218","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["An Autonomy Loop for\u00a0Dynamic HPC Job Time Limit Adjustment"],"prefix":"10.1007","author":[{"given":"Thomas","family":"Jakobsche","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Osman Seckin","family":"Simsek","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jim","family":"Brandt","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ann","family":"Gentile","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Florina M.","family":"Ciorba","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,8,27]]},"reference":[{"key":"14_CR1","doi-asserted-by":"crossref","unstructured":"Agelastos, A., et al.: The lightweight distributed metric service: a scalable infrastructure for continuous monitoring of large scale computing systems and applications. In: SC 2014: Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis, pp. 154\u2013165. IEEE (2014)","DOI":"10.1109\/SC.2014.18"},{"key":"14_CR2","doi-asserted-by":"crossref","unstructured":"Ansel, J., Arya, K., Cooperman, G.: DMTCP: transparent checkpointing for cluster computations and the desktop. In: 2009 IEEE International Symposium on Parallel & Distributed Processing, pp. 1\u201312. IEEE (2009)","DOI":"10.1109\/IPDPS.2009.5161063"},{"key":"14_CR3","doi-asserted-by":"crossref","unstructured":"Antici, F., Bartolini, A., Domke, J., Kiziltan, Z., Yamamoto, K.: F-DATA: A Fugaku Workload Dataset for Job-Centric Predictive Modelling in HPC Systems (2024)","DOI":"10.1038\/s41597-025-05633-1"},{"key":"14_CR4","doi-asserted-by":"crossref","unstructured":"Antici, F., Seyedkazemi\u00a0Ardebili, M., Bartolini, A., Kiziltan, Z.: PM100: a job power consumption dataset of a large-scale production HPC system. In: Proceedings of the SC 2023 Workshops of the International Conference on High Performance Computing, Network, Storage, and Analysis, pp. 1812\u20131819 (2023)","DOI":"10.1145\/3624062.3624263"},{"key":"14_CR5","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"253","DOI":"10.1007\/11407522_14","volume-title":"Job Scheduling Strategies for Parallel Processing","author":"C Bailey Lee","year":"2005","unstructured":"Bailey Lee, C., Schwartzman, Y., Hardy, J., Snavely, A.: Are user runtime estimates inherently inaccurate? In: Feitelson, D.G., Rudolph, L., Schwiegelshohn, U. (eds.) JSSPP 2004. LNCS, vol. 3277, pp. 253\u2013263. Springer, Heidelberg (2005). https:\/\/doi.org\/10.1007\/11407522_14"},{"key":"14_CR6","doi-asserted-by":"crossref","unstructured":"Bautista-Gomez, L., Benoit, A., Di, S., Herault, T., Robert, Y., Sun, H.: A Survey on Checkpointing Strategies: Should We Always Checkpoint \u00e0 la Young\/Daly? Future Generation Computer Systems (2024)","DOI":"10.1016\/j.future.2024.07.022"},{"issue":"4","key":"14_CR7","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3701986","volume":"9","author":"R Bo\u00ebzennec","year":"2024","unstructured":"Bo\u00ebzennec, R., Dufoss\u00e9, F., Pallez, G.: Qualitatively analyzing optimization objectives in the design of HPC resource manager. ACM Trans. Model. Perform. Eval. Comput. Syst. 9(4), 1\u201328 (2024)","journal-title":"ACM Trans. Model. Perform. Eval. Comput. Syst."},{"key":"14_CR8","doi-asserted-by":"crossref","unstructured":"Boito, F., et al.: Autonomy loops for monitoring, operational data analytics, feedback, and response in HPC operations. In: 2023 IEEE International Conference on Cluster Computing Workshops (CLUSTER Workshops), pp. 37\u201343. IEEE (2023)","DOI":"10.1109\/CLUSTERWorkshops61457.2023.00016"},{"key":"14_CR9","doi-asserted-by":"crossref","unstructured":"Borghesi, A., et al.: M100 ExaData: a Data Collection Campaign on the CINECA\u2019s Marconi100 Tier-0 Supercomputer (2023)","DOI":"10.1038\/s41597-023-02174-3"},{"key":"14_CR10","unstructured":"Borghesi, A., et al.: M100 Dataset 1: from 20-03 to 20-12 (2023)"},{"key":"14_CR11","unstructured":"Brandt, J., Ciorba, F., Gentile, A., Ott, M., Wilde, T.: Driving HPC Operations With Holistic Monitoring and Operational Data Analytics (Dagstuhl Seminar 23171). Dagstuhl Reports (2023)"},{"issue":"3","key":"14_CR12","doi-asserted-by":"publisher","first-page":"303","DOI":"10.1016\/j.future.2004.11.016","volume":"22","author":"JT Daly","year":"2006","unstructured":"Daly, J.T.: A higher order estimate of the optimum checkpoint interval for restart dumps. Futur. Gener. Comput. Syst. 22(3), 303\u2013312 (2006)","journal-title":"Futur. Gener. Comput. Syst."},{"key":"14_CR13","unstructured":"Duplyakin, Dmitry, Menear, Kevin: NREL Eagle Supercomputer Jobs (2023)"},{"issue":"2","key":"14_CR14","doi-asserted-by":"publisher","first-page":"336","DOI":"10.1109\/TDSC.2016.2548463","volume":"15","author":"N El-Sayed","year":"2016","unstructured":"El-Sayed, N., Schroeder, B.: Understanding practical tradeoffs in HPC checkpoint-scheduling policies. IEEE Trans. Dependable Secure Comput. 15(2), 336\u2013350 (2016)","journal-title":"IEEE Trans. Dependable Secure Comput."},{"key":"14_CR15","doi-asserted-by":"crossref","unstructured":"Esposito, A., Haine, C., Mohammed, A.: Emergency backup for scientific applications. In: 2022 IEEE\/ACM Third International Symposium on Checkpointing for Supercomputing (SuperCheck), pp.\u00a01\u20138. IEEE (2022)","DOI":"10.1109\/SuperCheck56652.2022.00008"},{"key":"14_CR16","doi-asserted-by":"crossref","unstructured":"Goponenko, A.V., Izadpanah, R., Brandt, J.M., Dechev, D.: Towards workload-adaptive scheduling for HPC clusters. In: 2020 IEEE International Conference on Cluster Computing (CLUSTER), pp. 449\u2013453. IEEE (2020)","DOI":"10.1109\/CLUSTER49012.2020.00064"},{"key":"14_CR17","doi-asserted-by":"crossref","unstructured":"Goponenko, A.V., Lamar, K., Peterson, C., Allan, B.A., Brandt, J.M., Dechev, D.: Metrics for packing efficiency and fairness of HPC cluster batch job scheduling. In: 2022 IEEE 34th International Symposium on Computer Architecture and High Performance Computing (SBAC-PAD), pp. 241\u2013252. IEEE (2022)","DOI":"10.1109\/SBAC-PAD55451.2022.00035"},{"key":"14_CR18","doi-asserted-by":"publisher","unstructured":"Jakobsche, T., Simsek, O.S., Brandt, J., Gentile, A., Ciorba, F.M.: Artifact of the Paper: An Autonomy Loop for Dynamic HPC Job Time Limit Adjustment (2025). https:\/\/doi.org\/10.5281\/zenodo.15585217","DOI":"10.5281\/zenodo.15585217"},{"issue":"1","key":"14_CR19","doi-asserted-by":"publisher","first-page":"41","DOI":"10.1109\/MC.2003.1160055","volume":"36","author":"JO Kephart","year":"2003","unstructured":"Kephart, J.O., Chess, D.M.: The vision of autonomic computing. Computer 36(1), 41\u201350 (2003)","journal-title":"Computer"},{"key":"14_CR20","doi-asserted-by":"crossref","unstructured":"Lamar, K., Goponenko, A., Peterson, C., Allan, B.A., Brandt, J.M., Dechev, D.: Backfilling HPC jobs with a multimodal-aware predictor. In: 2021 IEEE International Conference on Cluster Computing (CLUSTER), pp. 618\u2013622. IEEE (2021)","DOI":"10.1109\/Cluster48925.2021.00093"},{"key":"14_CR21","doi-asserted-by":"crossref","unstructured":"Patel, T., Liu, Z., Kettimuthu, R., Rich, P., Allcock, W., Tiwari, D.: Job characteristics on large-scale systems: long-term analysis, quantification, and implications. In: SC20: International Conference for High Performance Computing, Networking, Storage and Analysis, pp. 1\u201317. IEEE (2020)","DOI":"10.1109\/SC41405.2020.00088"},{"key":"14_CR22","doi-asserted-by":"crossref","unstructured":"Soysal, M., Berghoff, M., Klus\u00e1\u010dek, D., Streit, A.: On the quality of wall time estimates for resource allocation prediction. In: Workshop Proceedings of the 48th International Conference on Parallel Processing, pp.\u00a01\u20138 (2019)","DOI":"10.1145\/3339186.3339204"},{"key":"14_CR23","doi-asserted-by":"crossref","unstructured":"Tarraf, A., et al.: Malleability in modern HPC systems: current experiences, challenges, and future opportunities. IEEE Trans. Parallel Distrib. Syst. (2024)","DOI":"10.1109\/TPDS.2024.3406764"},{"issue":"6","key":"14_CR24","doi-asserted-by":"publisher","first-page":"789","DOI":"10.1109\/TPDS.2007.70606","volume":"18","author":"D Tsafrir","year":"2007","unstructured":"Tsafrir, D., Etsion, Y., Feitelson, D.G.: Backfilling using system-generated predictions rather than user runtime estimates. IEEE Trans. Parallel Distrib. Syst. 18(6), 789\u2013803 (2007)","journal-title":"IEEE Trans. Parallel Distrib. Syst."},{"issue":"20","key":"14_CR25","doi-asserted-by":"publisher","first-page":"9448","DOI":"10.3390\/app11209448","volume":"11","author":"Q Wang","year":"2021","unstructured":"Wang, Q., Zhang, H., Qu, C., Shen, Y., Liu, X., Li, J.: Rlschert: an HPC job scheduler using deep reinforcement learning and remaining time prediction. Appl. Sci. 11(20), 9448 (2021)","journal-title":"Appl. Sci."},{"issue":"19","key":"14_CR26","doi-asserted-by":"publisher","DOI":"10.1002\/cpe.8141","volume":"36","author":"D Yokelson","year":"2024","unstructured":"Yokelson, D., et al.: SOMA: observability, monitoring, and in situ analytics for exascale applications. Concurr. Comput. Pract. Exp. 36(19), e8141 (2024)","journal-title":"Concurr. Comput. Pract. Exp."},{"key":"14_CR27","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"44","DOI":"10.1007\/10968987_3","volume-title":"Job Scheduling Strategies for Parallel Processing","author":"AB Yoo","year":"2003","unstructured":"Yoo, A.B., Jette, M.A., Grondona, M.: SLURM: simple Linux utility for resource management. In: Feitelson, D., Rudolph, L., Schwiegelshohn, U. (eds.) JSSPP 2003. LNCS, vol. 2862, pp. 44\u201360. Springer, Heidelberg (2003). https:\/\/doi.org\/10.1007\/10968987_3"},{"issue":"9","key":"14_CR28","doi-asserted-by":"publisher","first-page":"530","DOI":"10.1145\/361147.361115","volume":"17","author":"JW Young","year":"1974","unstructured":"Young, J.W.: A first order approximation to the optimum checkpoint interval. Commun. ACM 17(9), 530\u2013531 (1974)","journal-title":"Commun. ACM"},{"key":"14_CR29","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"163","DOI":"10.1007\/978-3-319-96983-1_12","volume-title":"Euro-Par 2018: Parallel Processing","author":"M Zasadzi\u0144ski","year":"2018","unstructured":"Zasadzi\u0144ski, M., Munt\u00e9s-Mulero, V., Sol\u00e9, M., Carrera, D., Ludwig, T.: Early termination of failed HPC jobs through machine and deep learning. In: Aldinucci, M., Padovani, L., Torquati, M. (eds.) Euro-Par 2018. LNCS, vol. 11014, pp. 163\u2013177. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-319-96983-1_12"},{"key":"14_CR30","doi-asserted-by":"crossref","unstructured":"Zhang, D., Dai, D., He, Y., Bao, F.S., Xie, B.: RLScheduler: an automated HPC batch job scheduler using reinforcement learning. In: SC20: International Conference for High Performance Computing, Networking, Storage and Analysis, pp. 1\u201315. IEEE (2020)","DOI":"10.1109\/SC41405.2020.00035"}],"container-title":["Lecture Notes in Computer Science","Euro-Par 2025: Parallel Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-99854-6_14","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,10]],"date-time":"2025-09-10T00:36:17Z","timestamp":1757464577000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-99854-6_14"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,27]]},"ISBN":["9783031998539","9783031998546"],"references-count":30,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-99854-6_14","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,8,27]]},"assertion":[{"value":"27 August 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"The authors\u00a0have no competing interests to declare that are relevant to the content of this article.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Disclosure of Interests"}},{"value":"Euro-Par","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Parallel Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Dresden","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Germany","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"25 August 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 August 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"31","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"europar2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/2025.euro-par.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}