{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,2]],"date-time":"2025-12-02T15:04:01Z","timestamp":1764687841770,"version":"3.37.3"},"reference-count":45,"publisher":"Springer Science and Business Media LLC","issue":"10","license":[{"start":{"date-parts":[[2019,4,23]],"date-time":"2019-04-23T00:00:00Z","timestamp":1555977600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Supercomput"],"published-print":{"date-parts":[[2019,10]]},"DOI":"10.1007\/s11227-019-02857-y","type":"journal-article","created":{"date-parts":[[2019,4,23]],"date-time":"2019-04-23T05:23:53Z","timestamp":1555997033000},"page":"6517-6541","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":12,"title":["Job migration in HPC clusters by means of checkpoint\/restart"],"prefix":"10.1007","volume":"75","author":[{"given":"Manuel","family":"Rodr\u00edguez-Pascual","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiajun","family":"Cao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2528-7485","authenticated-orcid":false,"given":"Jos\u00e9 A.","family":"Mor\u00ed\u00f1igo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gene","family":"Cooperman","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rafael","family":"Mayo-Garc\u00eda","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2019,4,23]]},"reference":[{"doi-asserted-by":"crossref","unstructured":"Flich J et al. (2017) MANGO: exploring manycore architectures for next-generation HPC systems. In: Kubatova H, Novotny M, Skavhaug A (eds) Euromicro Conferences on Digital System Design (DSD), pp 478\u2013485","key":"2857_CR1","DOI":"10.1109\/DSD.2017.51"},{"doi-asserted-by":"crossref","unstructured":"Wyngaard J, Inggs M, Collins J, Farrimond B (2013) Towards a many-core architecture for HPC. In: Cardoso JMP, Morrow K, Diniz PC (eds) 23rd International Conference on Field Programmable Logic and Applications (FPL2013)","key":"2857_CR2","DOI":"10.1109\/FPL.2013.6645595"},{"unstructured":"European technology platform for high performance computing (2017). \n                    www.etp4hpc.eu\n                    \n                  , Strategic Research Agenda","key":"2857_CR3"},{"doi-asserted-by":"crossref","unstructured":"Bailey C, Parry J (2017) Co-design, modelling and simulation challenges: from components to systems. In: Proceedings 23rd International Workshop on Thermal Investigations of ICs and Systems (THERMINIC), pp 1\u20134","key":"2857_CR4","DOI":"10.1109\/THERMINIC.2017.8233783"},{"issue":"6","key":"2857_CR5","doi-asserted-by":"publisher","first-page":"12","DOI":"10.1109\/MC.2017.164","volume":"50","author":"MD Hill","year":"2017","unstructured":"Hill MD, Marty MR (2017) Retrospective on Amdahl\u2019s law in the multicore Era. Computer 50(6):12\u201314","journal-title":"Computer"},{"doi-asserted-by":"crossref","unstructured":"Martineau M, McIntosh-Smith S (2017) The arch project: physics mini-apps for algorithmic exploration and evaluating programming environments on HPC architectures. In: Proceedings IEEE International Conference on Cluster Computing (CLUSTER2017), pp 850\u2013857","key":"2857_CR6","DOI":"10.1109\/CLUSTER.2017.126"},{"issue":"6","key":"2857_CR7","doi-asserted-by":"publisher","first-page":"627","DOI":"10.1007\/s10951-015-0445-x","volume":"19","author":"G Aupy","year":"2016","unstructured":"Aupy G et al (2016) Co-scheduling algorithms for high-throughput workload execution. J Sched 19(6):627\u2013640","journal-title":"J Sched"},{"doi-asserted-by":"crossref","unstructured":"Rajan M, Doerfler D (2010) HPC application performance and scaling: understanding trends and future challenges with application benchmarks on past, present and future tri-lab computing systems. In Psihoyios G, Tsitouras C (eds) Numerical Analysis and Applied Mathematics, vol I\u2013III (AIP Conference Proceedings 1281), pp 1777\u20131780","key":"2857_CR8","DOI":"10.1063\/1.3498221"},{"key":"2857_CR9","series-title":"Lecture Notes in Computer Science","volume-title":"Job scheduling strategies for parallel processing (JSSPP 2003)","author":"AB Yoo","year":"2003","unstructured":"Yoo AB, Jette MA, Grondona M (2003) SLURM: simple linux utility for resource management. In: Feitelson D, Rudolph L, Schwiegelshohn U (eds) Job scheduling strategies for parallel processing (JSSPP 2003), vol 2862. Lecture Notes in Computer Science. Springer, Berlin"},{"doi-asserted-by":"crossref","unstructured":"Ansel J, Arya K, Cooperman G (2009) DMTCP: transparent checkpointing for cluster computations and the desktop. In: IEEE International Symposium on Parallel & Distributed Processing, Rome, pp 1\u201312","key":"2857_CR10","DOI":"10.1109\/IPDPS.2009.5161063"},{"key":"2857_CR11","doi-asserted-by":"publisher","first-page":"45","DOI":"10.1016\/j.future.2015.04.016","volume":"51","author":"J Tao","year":"2015","unstructured":"Tao J, Kolodziej J, Ranjan R, Jayaraman PP, Buyya R (2015) A note on new trends in data-aware scheduling and resource provisioning in modern HPC system. Future Gener Comput Syst 51:45\u201346","journal-title":"Future Gener Comput Syst"},{"issue":"5","key":"2857_CR12","doi-asserted-by":"publisher","first-page":"634","DOI":"10.1049\/iet-com.2016.0691","volume":"12","author":"X Ge","year":"2018","unstructured":"Ge X, Jin H, Leung VCM (2018) Joint opportunistic user scheduling and power allocation: throughput optimisation and fair resource sharing. IET Commun 12(5):634\u2013640","journal-title":"IET Commun"},{"key":"2857_CR13","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-387-09766-4","volume-title":"Encyclopedia of parallel computing","author":"D Padua","year":"2011","unstructured":"Padua D (2011) Encyclopedia of parallel computing. Springer, New York"},{"key":"2857_CR14","doi-asserted-by":"publisher","first-page":"494","DOI":"10.1088\/1742-6596\/46\/1\/067","volume":"46","author":"PH Hargrove","year":"2006","unstructured":"Hargrove PH, Duell JC (2006) Berkeley lab checkpoint\/restart (BLCR) for linux clusters. J Phys Conf Ser 46:494\u2013499","journal-title":"J Phys Conf Ser"},{"issue":"4","key":"2857_CR15","doi-asserted-by":"publisher","first-page":"479","DOI":"10.1177\/1094342005056139","volume":"19","author":"S Sankaran","year":"2005","unstructured":"Sankaran S et al (2005) The Lam\/Mpi checkpoint\/restart framework: system-initiated checkpointing. Int J High Perform Comput Appl 19(4):479\u2013493","journal-title":"Int J High Perform Comput Appl"},{"doi-asserted-by":"crossref","unstructured":"Cao J, Arya K, Garg R, Matott S, Panda DK, Subramoni H, Vienne J, Cooperman G (2016) System-level scalable checkpoint-restart for petascale computing. In: Proceedings IEEE 22nd International Conference on Parallel and Distributed Systems (ICPADS), pp 932\u2013941","key":"2857_CR16","DOI":"10.1109\/ICPADS.2016.0125"},{"unstructured":"https:\/\/criu.org\/Main_Page","key":"2857_CR17"},{"doi-asserted-by":"crossref","unstructured":"Li W, Kanso A, Gherbi A (2015) Leveraging linux containers to achieve high availability for cloud services. In: Proceedings IEEE International Conference on Cloud Engineering, Tempe, AZ, pp 76\u201383","key":"2857_CR18","DOI":"10.1109\/IC2E.2015.17"},{"doi-asserted-by":"crossref","unstructured":"Vogt D, Giuffrida C, Bos H, Tanenbaum AS (2015) Lightweight memory checkpointing. In: Proceedings 45th Annual IEEE\/IFIP International Conference on Dependable Systems and Networks, Rio de Janeiro, pp 474\u2013484","key":"2857_CR19","DOI":"10.1109\/DSN.2015.45"},{"doi-asserted-by":"crossref","unstructured":"Takizawa H, Amrizal MA, Komatsu K, Egawa R (2017) An application-level incremental checkpointing mechanism with automatic parameter tuning. In: 5th International Symposium on Computing and Networking (CANDAR), Aomori, pp 389\u2013394","key":"2857_CR20","DOI":"10.1109\/CANDAR.2017.96"},{"key":"2857_CR21","doi-asserted-by":"publisher","first-page":"66","DOI":"10.1016\/j.future.2013.04.017","volume":"30","author":"KB Ferreira","year":"2014","unstructured":"Ferreira KB, Riesen R, Bridges P, Arnold D, Brightwell R (2014) Accelerating incremental checkpointing for extreme-scale computing. Future Gener Comput Syst 30:66\u201377","journal-title":"Future Gener Comput Syst"},{"doi-asserted-by":"crossref","unstructured":"Moody A, Bronevetsky G, Mohror K, Supinski BR (2010) Design, modeling, and evaluation of a scalable multi-level checkpointing system. In: Proceedings ACM\/IEEE International Conference for High Performance Computing, Networking, Storage and Analysis, pp 1\u201311","key":"2857_CR22","DOI":"10.2172\/984082"},{"doi-asserted-by":"crossref","unstructured":"Bautista-Gomez L, Tsuboi S, Komatitsch D, Cappello F, Maruyama N, Matsuoka S (2011) FTI: high performance fault tolerance interface for hybrid systems. In: Proceedings International Conference for High Performance Computing, Networking, Storage and Analysis, Seattle, WA, pp 1\u201312","key":"2857_CR23","DOI":"10.1145\/2063384.2063427"},{"issue":"3","key":"2857_CR24","doi-asserted-by":"publisher","first-page":"175","DOI":"10.1016\/S0164-1212(97)10018-8","volume":"41","author":"MP Tiemeyer","year":"1998","unstructured":"Tiemeyer MP, Wong JSK (1998) A task migration algorithm for heterogeneous distributed computing systems. J Syst Softw 41(3):175\u2013188","journal-title":"J Syst Softw"},{"issue":"8","key":"2857_CR25","doi-asserted-by":"publisher","first-page":"2285","DOI":"10.1109\/TPDS.2017.2658572","volume":"28","author":"K Tsakalozos","year":"2017","unstructured":"Tsakalozos K, Verroios V, Roussopoulos M, Delis A (2017) Live VM migration under time-constraints in share-nothing IaaS-clouds. IEEE Trans Parallel Distrib Syst 28(8):2285\u20132298","journal-title":"IEEE Trans Parallel Distrib Syst"},{"doi-asserted-by":"crossref","unstructured":"Jaswal T, Kaur K (2016) An enhanced hybrid approach for reducing downtime, cost and power consumption of live VM migration. In: Proceedings International Conference on Advances in Information Communication Technology & Computing, vol 72","key":"2857_CR26","DOI":"10.1145\/2979779.2979851"},{"issue":"3","key":"2857_CR27","doi-asserted-by":"publisher","first-page":"328","DOI":"10.1007\/s11227-010-0381-7","volume":"56","author":"A Bargi","year":"2011","unstructured":"Bargi A, Sarbazi-Azad H (2011) Task migration in three-dimensional meshes. J Supercomput 56(3):328\u2013352","journal-title":"J Supercomput"},{"unstructured":"Kale LV, Krishnan S (1993) CHARM\u2009++: a portable concurrent object oriented system based on C\u2009++. In: Proceedings of the 8th Annual Conference on Object-Oriented Programming Systems, Languages, and Applications, pp 91\u2013108","key":"2857_CR28"},{"doi-asserted-by":"crossref","unstructured":"Iserte S, Mayo R, Quintana-Ort\u00ed SE, Beltran V, Pe\u00f1a JA (2017) Efficient scalable computing through flexible applications and adaptive workloads. In: 46th International Conference on Parallel Processing Workshops (ICPPW), pp 180\u2013189","key":"2857_CR29","DOI":"10.1109\/ICPPW.2017.36"},{"key":"2857_CR30","doi-asserted-by":"publisher","first-page":"316","DOI":"10.1007\/s11227-016-1863-z","volume":"73","author":"N Losada","year":"2017","unstructured":"Losada N, Mart\u00edn MJ, Gonz\u00e1lez P (2017) J Supercomput 73:316\u2013329","journal-title":"J Supercomput"},{"key":"2857_CR31","doi-asserted-by":"publisher","first-page":"100","DOI":"10.1007\/s11227-016-1629-7","volume":"73","author":"N Losada","year":"2017","unstructured":"Losada N, Cores I, Mart\u00edn MJ et al (2017) J Supercomput 73:100","journal-title":"J Supercomput"},{"unstructured":"http:\/\/research.cs.wisc.edu\/htcondor\/","key":"2857_CR32"},{"key":"2857_CR33","doi-asserted-by":"publisher","first-page":"165","DOI":"10.1049\/iet-cdt.2015.0131","volume":"10","author":"S Afsharpour","year":"2016","unstructured":"Afsharpour S, Patologhy A, Fazeli M (2016) Performance\/energy aware task migration algorithm for many-core chips. Comput Digit Tech 10:165\u2013173","journal-title":"Comput Digit Tech"},{"issue":"3","key":"2857_CR34","doi-asserted-by":"publisher","first-page":"1141","DOI":"10.1007\/s11227-014-1144-7","volume":"68","author":"S Holmbacka","year":"2014","unstructured":"Holmbacka S et al (2014) A task migration mechanism for distributed many-core operating systems. J Supercomput 68(3):1141\u20131162","journal-title":"J Supercomput"},{"issue":"5","key":"2857_CR35","doi-asserted-by":"publisher","first-page":"14","DOI":"10.1109\/MIC.2009.119","volume":"13","author":"B Sotomayor","year":"2009","unstructured":"Sotomayor B, Montero RS, Llorente IM, Foster I (2009) Virtual infrastructure management in private and hybrid clouds. IEEE Internet Comput 13(5):14\u201322","journal-title":"IEEE Internet Comput"},{"issue":"3","key":"2857_CR36","first-page":"38","volume":"55","author":"O Sefraoui","year":"2012","unstructured":"Sefraoui O, Aissaoui M, Eleuldj M (2012) OpenStack: toward an open-source solution for cloud computing. Int J Comput Appl 55(3):38\u201342","journal-title":"Int J Comput Appl"},{"unstructured":"Boucher R (2016) Cloning running services with docker and CRIU. In: Docker Conference","key":"2857_CR37"},{"doi-asserted-by":"crossref","unstructured":"Villamayor J, Rexachs D, Luque E (2017) A fault tolerance manager with distributed coordinated checkpoints for automatic recovery. In: International Conference on High Performance Computing & Simulation (HPCS), Genoa, pp 452\u2013459","key":"2857_CR38","DOI":"10.1109\/HPCS.2017.73"},{"doi-asserted-by":"crossref","unstructured":"Cabello U, Rodriguez J, Meneses A, Mendoza S, Decouchant D (2014) Fault tolerance in heterogeneous multi-cluster systems through a task migration mechanism. In: Proceedings 11th International Conference on Electrical Engineering, Computing Science and Automatic Control","key":"2857_CR39","DOI":"10.1109\/ICEEE.2014.6978266"},{"key":"2857_CR40","doi-asserted-by":"publisher","first-page":"138","DOI":"10.1007\/978-3-642-04633-9_8","volume":"5798","author":"JA Pascual","year":"2009","unstructured":"Pascual JA, Navaridas J, Miguel-Alonso J (2009) Effects of topology-aware allocation policies on scheduling performance. Lect Notes Comput Sci 5798:138\u2013144","journal-title":"Lect Notes Comput Sci"},{"unstructured":"http:\/\/rdgroups.ciemat.es\/web\/sci-track\/intranet","key":"2857_CR41"},{"key":"2857_CR42","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9781139939690","volume-title":"Workload modeling for computer systems performance evaluation","author":"DG Feitelson","year":"2015","unstructured":"Feitelson DG (2015) Workload modeling for computer systems performance evaluation. Cambridge University Press, Cambridge"},{"doi-asserted-by":"crossref","unstructured":"Garg R, Mohan A, Sullivan M, Cooperman G (2018) CRUM: checkpoint-restart support for CUDA\u2019s unified memory. In: IEEE International Conference on Cluster Computing (CLUSTER), pp 302\u2013313","key":"2857_CR43","DOI":"10.1109\/CLUSTER.2018.00047"},{"doi-asserted-by":"crossref","unstructured":"Levy S, Topp B, Ferreira KB, Widener P, Arnold D, Hoefler T (2014) Using simulation to evaluate the performance of resilience strategies and process failures, SANDIA report, SAND2014-0688","key":"2857_CR44","DOI":"10.2172\/1204092"},{"key":"2857_CR45","doi-asserted-by":"publisher","first-page":"245","DOI":"10.1016\/j.future.2016.05.042","volume":"78","author":"A Fern\u00e1ndez-Anta","year":"2018","unstructured":"Fern\u00e1ndez-Anta A et al (2018) Competitive analysis of fundamental scheduling algorithms on a fault-prone machine and the impact of resource augmentation. Future Gener Comput Syst 78:245\u2013256","journal-title":"Future Gener Comput Syst"}],"container-title":["The Journal of Supercomputing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-019-02857-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11227-019-02857-y\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-019-02857-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,4,21]],"date-time":"2020-04-21T23:06:25Z","timestamp":1587510385000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11227-019-02857-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,4,23]]},"references-count":45,"journal-issue":{"issue":"10","published-print":{"date-parts":[[2019,10]]}},"alternative-id":["2857"],"URL":"https:\/\/doi.org\/10.1007\/s11227-019-02857-y","relation":{},"ISSN":["0920-8542","1573-0484"],"issn-type":[{"type":"print","value":"0920-8542"},{"type":"electronic","value":"1573-0484"}],"subject":[],"published":{"date-parts":[[2019,4,23]]},"assertion":[{"value":"23 April 2019","order":1,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}