{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,2]],"date-time":"2025-07-02T04:12:11Z","timestamp":1751429531116,"version":"3.41.0"},"publisher-location":"Cham","reference-count":26,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319751771"},{"type":"electronic","value":"9783319751788"}],"license":[{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018]]},"DOI":"10.1007\/978-3-319-75178-8_47","type":"book-chapter","created":{"date-parts":[[2018,2,7]],"date-time":"2018-02-07T07:12:27Z","timestamp":1517987547000},"page":"581-592","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["It\u2019s Not the Heat, It\u2019s the Humidity: Scheduling Resilience Activity at Scale"],"prefix":"10.1007","author":[{"given":"Patrick M.","family":"Widener","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kurt B.","family":"Ferreira","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Scott","family":"Levy","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2018,2,8]]},"reference":[{"key":"47_CR1","unstructured":"Alvisi, L., Elnozahy, E., Rao, S., Husain, S., de Mel, A.: An analysis of communication induced checkpointing. In: Twenty-Ninth Annual International Symposium on Fault-Tolerant Computing, 1999. Digest of Papers, pp. 242\u2013249 (1999)"},{"key":"47_CR2","doi-asserted-by":"crossref","unstructured":"Bronevetsky, G.: Communication-sensitive static dataflow for parallel message passing applications. In: Proceedings of the 7th annual IEEE\/ACM International Symposium on Code Generation and Optimization, pp. 1\u201312. IEEE Computer Society (2009)","DOI":"10.1109\/CGO.2009.32"},{"key":"#cr-split#-47_CR3.1","unstructured":"Cappello, F., Geist, A., Gropp, W., Kale, S., Kramer, B., Snir, M.: Toward exascale resilience: 2014 update. Supercomput. Front. Innov. 1"},{"key":"#cr-split#-47_CR3.2","unstructured":"(1) (2014). http:\/\/superfri.org\/superfri\/article\/view\/14"},{"key":"47_CR4","doi-asserted-by":"publisher","unstructured":"Culler, D., Karp, R., Patterson, D., Sahay, A., Schauser, K.E., Santos, E., Subramonian, R., von Eicken, T.: LogP: towards a realistic model of parallel computation. In: Proceedings of the Fourth ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming, PPOPP 1993, pp. 1\u201312. ACM, New York (1993). https:\/\/doi.org\/10.1145\/155332.155333","DOI":"10.1145\/155332.155333"},{"issue":"3","key":"47_CR5","doi-asserted-by":"publisher","first-page":"375","DOI":"10.1145\/568522.568525","volume":"34","author":"EN Elnozahy","year":"2002","unstructured":"Elnozahy, E.N., Alvisi, L., Wang, Y.M., Johnson, D.B.: A survey of rollback-recovery protocols in message-passing systems. ACM Comput. Surv. 34(3), 375\u2013408 (2002)","journal-title":"ACM Comput. Surv."},{"key":"47_CR6","doi-asserted-by":"crossref","unstructured":"Ferreira, K., Riesen, R., Stearley, J., Laros III, J.H., Oldfield, R., Pedretti, K., Bridges, P., Arnold, D., Brightwell, R.: Evaluating the viability of process replication reliability for exascale systems. In: Proceedings of the ACM\/IEEE International Conference on High Performance Computing, Networking, Storage, and Analysis, (SC 2011), November 2011","DOI":"10.1145\/2063384.2063443"},{"key":"47_CR7","doi-asserted-by":"crossref","unstructured":"Ferreira, K.B., Bridges, P., Brightwell, R.: Characterizing application sensitivity to OS interference using kernel-level noise injection. In: Proceedings of the 2008 ACM\/IEEE conference on Supercomputing, p. 19. IEEE Press (2008)","DOI":"10.1109\/SC.2008.5219920"},{"key":"47_CR8","doi-asserted-by":"crossref","unstructured":"Ferreira, K.B., Levy, S., Widener, P., Arnold, D., Hoefler, T.: Understanding the effects of communication and coordination on checkpointing at scale. In: Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis (SC 2014), pp. 883\u2013894. IEEE Press (2014)","DOI":"10.1109\/SC.2014.77"},{"key":"47_CR9","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"272","DOI":"10.1007\/978-3-642-24449-0_31","volume-title":"Recent Advances in the Message Passing Interface","author":"KB Ferreira","year":"2011","unstructured":"Ferreira, K.B., Riesen, R., Brighwell, R., Bridges, P., Arnold, D.: libhashckpt: hash-based incremental checkpointing using GPU\u2019s. In: Cotronis, Y., Danalis, A., Nikolopoulos, D.S., Dongarra, J. (eds.) EuroMPI 2011. LNCS, vol. 6960, pp. 272\u2013281. Springer, Heidelberg (2011). https:\/\/doi.org\/10.1007\/978-3-642-24449-0_31"},{"key":"47_CR10","doi-asserted-by":"crossref","unstructured":"Gioiosa, R., Sancho, J.C., Jiang, S., Petrini, F., Davis, K.: Transparent, incremental checkpointing at kernel level: a foundation for fault tolerance for parallel computers. In: Proceedings of the 2005 ACM\/IEEE Conference on Supercomputing, p. 9. IEEE Computer Society (2005)","DOI":"10.1109\/SC.2005.76"},{"key":"47_CR11","doi-asserted-by":"crossref","unstructured":"Guermouche, A., Ropars, T., Brunet, E., Snir, M., Cappello, F.: Uncoordinated checkpointing without domino effect for send-deterministic MPI applications. In: International Parallel Distributed Processing Symposium (IPDPS), pp. 989\u20131000, May 2011","DOI":"10.1109\/IPDPS.2011.95"},{"key":"47_CR12","unstructured":"Heroux, M.A., Doerfler, D.W., Crozier, P.S., Willenbring, J.M., Edwards, H.C., Williams, A., Rajan, M., Keiter, E.R., Thornquist, H.K., Numrich, R.W.: Improving performance via mini-applications. Technical report, Sandia National Laboratories (2009)"},{"key":"47_CR13","doi-asserted-by":"crossref","unstructured":"Hoefler, T., Schneider, T., Lumsdaine, A.: LogGOPSim - simulating large-scale applications in the LogGOPS model. In: Proceedings of the 19th ACM International Symposium on High Performance Distributed Computing, pp. 597\u2013604. ACM, June 2010","DOI":"10.1145\/1851476.1851564"},{"key":"47_CR14","doi-asserted-by":"crossref","unstructured":"Ibtesham, D., Arnold, D., Bridges, P.G., Ferreira, K.B., Brightwell, R.: On the viability of compression for reducing the overheads of checkpoint\/restart-based fault tolerance. In: 2012 41st International Conference on Parallel Processing (ICPP), pp. 148\u2013157. IEEE (2012)","DOI":"10.1109\/ICPP.2012.45"},{"key":"47_CR15","doi-asserted-by":"crossref","unstructured":"Islam, T.Z., Mohror, K., Bagchi, S., Moody, A., De Supinski, B.R., Eigenmann, R.: McrEngine: a scalable checkpointing system using data-aware aggregation and compression. In: 2012 International Conference for High Performance Computing, Networking, Storage and Analysis (SC), pp. 1\u201311. IEEE (2012)","DOI":"10.1109\/SC.2012.77"},{"key":"47_CR16","doi-asserted-by":"crossref","unstructured":"Johnson, D.B., Zwaenepoel, W.: Recovery in distributed systems using asynchronous message logging and checkpointing. In: Proceedings of the Seventh Annual ACM Symposium on Principles of Distributed Computing, pp. 171\u2013181 (1988)","DOI":"10.1145\/62546.62575"},{"key":"47_CR17","doi-asserted-by":"crossref","unstructured":"Karlin, I., Bhatele, A., Chamberlain, B.L., Cohen, J., Devito, Z., Gokhale, M., Haque, R., Hornung, R., Keasler, J., Laney, D., Luke, E., Lloyd, S., McGraw, J., Neely, R., Richards, D., Schulz, M., Still, C.H., Wang, F., Wong, D.: LULESH programming model and performance ports overview. Technical report, LLNL-TR-608824, Lawrence Livermore National Laboratory, December 2012","DOI":"10.2172\/1059462"},{"issue":"3","key":"47_CR18","doi-asserted-by":"publisher","first-page":"382","DOI":"10.1145\/357172.357176","volume":"4","author":"L Lamport","year":"1982","unstructured":"Lamport, L., Shostak, R., Pease, M.: The Byzantine generals problem. ACM Trans. Program. Lang. Syst. (TOPLAS) 4(3), 382\u2013401 (1982)","journal-title":"ACM Trans. Program. Lang. Syst. (TOPLAS)"},{"key":"47_CR19","doi-asserted-by":"crossref","unstructured":"Levy, S., Ferreira, K.B., Bridges, P.G.: Improving application resilience to memory errors with lightweight compression. In: SC16: International Conference for High Performance Computing, Networking, Storage and Analysis, pp. 323\u2013334. IEEE (2016)","DOI":"10.1109\/SC.2016.27"},{"key":"47_CR20","doi-asserted-by":"crossref","unstructured":"Levy, S., Topp, B., Ferreira, K.B., Arnold, D., Hoefler, T., Widener, P.: Using simulation to evaluate the performance of resilience strategies at scale. In: 2013 SC Companion: High Performance Computing, Networking, Storage and Analysis (SCC). IEEE (2013)","DOI":"10.2172\/1204092"},{"issue":"12","key":"47_CR21","doi-asserted-by":"publisher","first-page":"1632","DOI":"10.1002\/cpe.1413","volume":"21","author":"A Maloney","year":"2009","unstructured":"Maloney, A., Goscinski, A.: A survey and review of the current state of rollback-recovery for cluster systems. Concurr. Comput. Pract. Exp. 21(12), 1632\u20131666 (2009)","journal-title":"Concurr. Comput. Pract. Exp."},{"key":"47_CR22","doi-asserted-by":"crossref","unstructured":"Monnet, S., Morin, C., Badrinath, R.: A hierarchical checkpointing protocol for parallel applications in cluster federations. In: Proceedings of 18th International Parallel and Distributed Processing Symposium, p. 211. IEEE (2004)","DOI":"10.1109\/IPDPS.2004.1303242"},{"key":"47_CR23","doi-asserted-by":"publisher","unstructured":"Moody, A., Bronevetsky, G., Mohror, K., de Supinski, B.R.: Design, modeling, and evaluation of a scalable multi-level checkpointing system. In: Proceedings of the 2010 ACM\/IEEE International Conference for High Performance Computing, Networking, Storage and Analysis (SC10), SC 2010, pp. 1\u201311. IEEE Computer Society, Washington, DC (2010). https:\/\/doi.org\/10.1109\/SC.2010.18","DOI":"10.1109\/SC.2010.18"},{"issue":"1","key":"47_CR24","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1006\/jcph.1995.1039","volume":"117","author":"S Plimpton","year":"1995","unstructured":"Plimpton, S.: Fast parallel algorithms for short-range molecular-dynamics. J. Comput. Phys. 117(1), 1\u201319 (1995)","journal-title":"J. Comput. Phys."},{"key":"47_CR25","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"623","DOI":"10.1007\/978-3-319-58943-5_50","volume-title":"Euro-Par 2016: Parallel Processing Workshops","author":"PM Widener","year":"2017","unstructured":"Widener, P.M., Ferreira, K.B., Levy, S.: Horseshoes and hand grenades: the case for approximate coordination in local checkpointing protocols. In: Desprez, F. (ed.) Euro-Par 2016. LNCS, vol. 10104, pp. 623\u2013634. Springer, Cham (2017). https:\/\/doi.org\/10.1007\/978-3-319-58943-5_50"}],"container-title":["Lecture Notes in Computer Science","Euro-Par 2017: Parallel Processing Workshops"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-75178-8_47","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T12:06:41Z","timestamp":1751371601000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-319-75178-8_47"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783319751771","9783319751788"],"references-count":26,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-75178-8_47","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2018]]},"assertion":[{"value":"8 February 2018","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"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":"Santiago de Compostela","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Spain","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2017","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28 August 2017","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"1 September 2017","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"europar2017","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/europar2017.usc.es","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}