{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,10]],"date-time":"2026-01-10T13:28:13Z","timestamp":1768051693947,"version":"3.49.0"},"reference-count":79,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2013,2,12]],"date-time":"2013-02-12T00:00:00Z","timestamp":1360627200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["J Supercomput"],"published-print":{"date-parts":[[2013,9]]},"DOI":"10.1007\/s11227-013-0884-0","type":"journal-article","created":{"date-parts":[[2013,2,11]],"date-time":"2013-02-11T13:01:44Z","timestamp":1360587704000},"page":"1302-1326","source":"Crossref","is-referenced-by-count":206,"title":["A survey of fault tolerance mechanisms and checkpoint\/restart implementations for high performance computing systems"],"prefix":"10.1007","volume":"65","author":[{"given":"Ifeanyi P.","family":"Egwutuoha","sequence":"first","affiliation":[]},{"given":"David","family":"Levy","sequence":"additional","affiliation":[]},{"given":"Bran","family":"Selic","sequence":"additional","affiliation":[]},{"given":"Shiping","family":"Chen","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2013,2,12]]},"reference":[{"key":"884_CR1","first-page":"1","volume-title":"23rd IEEE international parallel and distributed processing symposium","author":"J Ansel","year":"2009","unstructured":"Ansel J, Arya K, Cooperman G (2009) DMTCP: transparent checkpointing for cluster computations and the desktop. In: 23rd IEEE international parallel and distributed processing symposium, Rome, Italy, pp 1\u201312"},{"issue":"1","key":"884_CR2","doi-asserted-by":"publisher","first-page":"87","DOI":"10.1109\/TDSC.2004.4","volume":"1","author":"W Bartlett","year":"2004","unstructured":"Bartlett W, Spainhower L (2004) Commercial fault tolerance: a tale of two systems. IEEE Trans Dependable Secure Comput 1(1):87\u201396","journal-title":"IEEE Trans Dependable Secure Comput"},{"key":"884_CR3","doi-asserted-by":"crossref","unstructured":"Bartlett J, Gray J, Horst B (1986) Fault tolerance in tandem computer systems. Tandem Technical Report","DOI":"10.1007\/978-3-7091-8871-2_3"},{"key":"884_CR4","unstructured":"Blackham B (2005) [Online]. Available: \n                    http:\/\/cryopid.berlios.de\/"},{"key":"884_CR5","volume-title":"IEEE\/ACM SIGARCH","author":"G Bosilca","year":"2002","unstructured":"Bosilca G, Bouteiller A, Cappello et al (2002) MPICH-V: toward a scalable fault tolerant MPI for volatile nodes. In: IEEE\/ACM SIGARCH"},{"key":"884_CR6","volume-title":"Proceedings of the first workshop on evaluating and architecting system dependability (EASY\u201901)","author":"A Brown","year":"2001","unstructured":"Brown A, Patterson DA (2001) To err is human. In: Proceedings of the first workshop on evaluating and architecting system dependability (EASY\u201901), G\u00f6teborg, Sweden, July 2001"},{"key":"884_CR7","unstructured":"Byoung-Jip K (2005) Comparison of the existing checkpoint systems. Technical report, IBM Watson"},{"key":"884_CR8","doi-asserted-by":"publisher","first-page":"212","DOI":"10.1177\/1094342009106189","volume":"23","author":"F Cappello","year":"2009","unstructured":"Cappello F (2009) Fault tolerance in petascale\/exascale systems: current knowledge, challenges and research opportunities. Int J High Perform Comput Appl 23:212\u2013226","journal-title":"Int J High Perform Comput Appl"},{"issue":"4","key":"884_CR9","doi-asserted-by":"publisher","first-page":"378","DOI":"10.1177\/1094342009347767","volume":"23","author":"F Cappello","year":"2009","unstructured":"Cappello F, Geist A, Gropp B, Kale L, Kramer B, Snir M (2009) Toward exascale resilience. Int J High Perform Comput Appl 23(4):378\u2013388","journal-title":"Int J High Perform Comput Appl"},{"key":"884_CR10","unstructured":"CFDR (2012) [Online]. Available: CFDR \n                    http:\/\/cfdr.usenix.org\/"},{"issue":"1","key":"884_CR11","doi-asserted-by":"publisher","first-page":"63","DOI":"10.1145\/214451.214456","volume":"3","author":"KM Chandy","year":"1985","unstructured":"Chandy KM, Lamport L (1985) Distributed snapshots: determining global states of distributed systems. ACM Trans Comput Syst 3(1):63\u201375","journal-title":"ACM Trans Comput Syst"},{"key":"884_CR12","unstructured":"Checkpointing.org (2012) Checkpointing [Online]. Available: \n                    http:\/\/checkpointing.org"},{"key":"884_CR13","unstructured":"Chen F (2010) On performance optimization and system design of flash memory based solid state drives in the storage hierarchy. Ph.D. dissertation, Ohio State University, Computer Science and Engineering, Ohio State University"},{"key":"884_CR14","unstructured":"Chen L, Avizienis A (1978) N-version programming: a fault-tolerance approach to reliability of software operation, June, Toulouse, France, pp 3\u20139"},{"key":"884_CR15","first-page":"169","volume-title":"Proceedings of the 12th USENIX security symposium","author":"M Christodorescu","year":"2003","unstructured":"Christodorescu M, Jha S (2003) Static analysis of executables to detect malicious patterns. In: Proceedings of the 12th USENIX security symposium, pp 169\u2013186"},{"key":"884_CR16","first-page":"273","volume-title":"Proceedings of the 2nd conference on symposium on networked systems design and implementation","author":"C Clark","year":"2005","unstructured":"Clark C, Fraser K, Hand S et al (2005) Live migration of virtual machines. In: Proceedings of the 2nd conference on symposium on networked systems design and implementation, vol 2, May 2005, pp 273\u2013286"},{"key":"884_CR17","volume-title":"Proc 1994 computer measurement group con","author":"II Courtright","year":"1994","unstructured":"Courtright II, William V, Gibson GA (1994) Backward error recovery in redundant disk arrays. In: Proc 1994 computer measurement group con"},{"issue":"2","key":"884_CR18","doi-asserted-by":"publisher","first-page":"56","DOI":"10.1145\/102792.102801","volume":"34","author":"F Cristian","year":"1991","unstructured":"Cristian F (1991) Understanding fault-tolerant distributed systems. Commun ACM 34(2):56\u201388","journal-title":"Commun ACM"},{"key":"884_CR19","volume-title":"Proceedings, tenth symposium on reliable distributed systems","author":"F Cristian","year":"1991","unstructured":"Cristian F, Jahanian F (1991) A timestampbased checkpointing protocol for long-lived distributed computations. In: Proceedings, tenth symposium on reliable distributed systems"},{"key":"884_CR20","first-page":"83","volume-title":"Object-oriented technology ECOOP 2002 workshop reader","author":"K Czarnecki","year":"2002","unstructured":"Czarnecki K, \u00d8sterbye K, V\u00f6lter M (2002) Generative programming. In: Object-oriented technology ECOOP 2002 workshop reader. Springer, Berlin\/Heidelberg, pp 83\u2013115"},{"key":"884_CR21","unstructured":"Duell J, Hargrove P, Roman E (2002) The design and implementation of Berkeley lab\u2019s Linux checkpoint\/restart. Berkeley Lab Technical Report (publication LBNL-54941), December 2002"},{"key":"884_CR22","doi-asserted-by":"crossref","unstructured":"Duell J, Hargrove P, Roman E (2002) Requirements for Linux checkpoint\/restart. Lawrence Berkeley National Laboratory Technical Report LBNL-49659","DOI":"10.2172\/793773"},{"issue":"3","key":"884_CR23","doi-asserted-by":"publisher","first-page":"375","DOI":"10.1145\/568522.568525","volume":"34","author":"ENM Elnozahy","year":"2002","unstructured":"Elnozahy ENM, Alvisi L, Wang YM, Johnson DB (2002) A survey of rollback-recovery protocols in message-passing systems. ACM Comput Surv 34(3):375\u2013408","journal-title":"ACM Comput Surv"},{"key":"884_CR24","doi-asserted-by":"publisher","first-page":"346","DOI":"10.1007\/3-540-45255-9_47","volume-title":"Recent advances in parallel virtual machine and message passing interface","author":"GE Fagg","year":"2000","unstructured":"Fagg GE, Dongarra J (2000) FT-MPI: fault tolerant MPI, supporting dynamic applications in a dynamic world. In: Recent advances in parallel virtual machine and message passing interface, pp\u00a0346\u2013353"},{"key":"884_CR25","unstructured":"Fault tolerance, wikipedia (2012) [Online]. Available: \n                    http:\/\/en.wikipedia.org\/wiki\/Fault-tolerant_system"},{"key":"884_CR26","unstructured":"Fusion-IO (2012) [Online]. Available: \n                    http:\/\/www.rpmgmbh.com\/download\/Whitepaper_Green.pdf"},{"key":"884_CR27","volume-title":"A high performance data integrity assurance based on the determinant technique","author":"JA Ghaeba","year":"2010","unstructured":"Ghaeba JA, Smadia MA, Chebil J (2010) A high performance data integrity assurance based on the determinant technique. Elsevier, Amsterdam"},{"key":"884_CR28","unstructured":"Gibson D (2012) esky [Online]. Available: \n                    http:\/\/esky.sourceforge.net"},{"key":"884_CR29","volume-title":"Handbook of reliability engineering and management","author":"W Grant-Ireson","year":"1988","unstructured":"Grant-Ireson W, Coombs CF (1988) Handbook of reliability engineering and management. McGraw-Hill, New York"},{"issue":"4","key":"884_CR30","doi-asserted-by":"publisher","first-page":"409","DOI":"10.1109\/24.58719","volume":"39","author":"J Gray","year":"1990","unstructured":"Gray J (1990) A census of tandem system availability between 1985 and 1990. IEEE Trans Reliab 39(4):409\u2013418","journal-title":"IEEE Trans Reliab"},{"key":"884_CR31","first-page":"141","volume-title":"Proc 1996 USENIX tech conf","author":"J Gwertzman","year":"1996","unstructured":"Gwertzman J, Seltzer M (1996) World-wide web cache consistency. In: Proc 1996 USENIX tech conf, San Diego, CA, Jan 1996, pp 141\u2013152"},{"key":"884_CR32","volume-title":"3rd int MCeTech conference on etechnologies","author":"C Hobbs","year":"2008","unstructured":"Hobbs C, Becha H, Amyot D (2008) Failure semantics in a SOA environment. In: 3rd int MCeTech conference on etechnologies, Montr\u00e9al"},{"key":"884_CR33","unstructured":"InfiniBand (2012) [Online]. Available: InfiniBand \n                    http:\/\/www.infinibandta.org\/"},{"key":"884_CR34","first-page":"60","volume-title":"2nd institution of engineering and technology international conference on system safety","author":"C Johnson","year":"2007","unstructured":"Johnson C, Holloway C (2007) The dangers of failure masking in fault tolerant software: aspects of a recent in-flight upset event. In: 2nd institution of engineering and technology international conference on system safety, pp 60\u201365"},{"key":"884_CR35","doi-asserted-by":"crossref","unstructured":"Kalaiselvi S, Rajaraman V (2000) A survey of checkpointing algorithms for parallel and distributed computers, pp 489\u2013510","DOI":"10.1007\/BF02703630"},{"key":"884_CR36","volume-title":"Proceedings of int symp on field programmable gate arrays (FPGA)","author":"D Koch","year":"2007","unstructured":"Koch D, Haubelt C, Teich J (2007) Efficient hardware checkpointing concepts, overhead analysis, and implementation. In: Proceedings of int symp on field programmable gate arrays (FPGA)"},{"key":"884_CR37","volume-title":"Fault-tolerant systems","author":"I Koren","year":"2007","unstructured":"Koren I, Krishna C (2007) Fault-tolerant systems. Elsevier\/Morgan Kaufmann, San Diego, San Mateo"},{"key":"884_CR38","doi-asserted-by":"publisher","first-page":"558","DOI":"10.1145\/359545.359563","volume":"21","author":"L Lamport","year":"1978","unstructured":"Lamport L (1978) Time, clocks, and the ordering of events in a distributed system. Commun ACM 21:558\u2013565","journal-title":"Commun ACM"},{"issue":"7","key":"884_CR39","doi-asserted-by":"publisher","first-page":"39","DOI":"10.1109\/2.56851","volume":"23","author":"JC Laprie","year":"1990","unstructured":"Laprie JC, Arlat J, Beounes C, Kanoun K (1990) Definition and analysis of hardware-and software-fault-tolerant architectures. Computer 23(7):39\u201351","journal-title":"Computer"},{"key":"884_CR40","unstructured":"Large software state (2012) [Online]. Available: \n                    http:\/\/www.safeware-eng.com\/White_Papers\/Software%20Safety.htm"},{"issue":"8","key":"884_CR41","doi-asserted-by":"publisher","first-page":"874","DOI":"10.1109\/71.298215","volume":"5","author":"K Li","year":"1994","unstructured":"Li K, Naughton JF, Plank JS (1994) Low-latency, concurrent checkpointing for parallel programs. IEEE Trans Parallel Distrib Syst 5(8):874\u2013879","journal-title":"IEEE Trans Parallel Distrib Syst"},{"key":"884_CR42","first-page":"425","volume-title":"International conference on dependable systems and networks, DSN 2006","author":"Y Liang","year":"2006","unstructured":"Liang Y, Zhang Y, Jette et al (2006) BlueGene\/L failure analysis and prediction models. In: International conference on dependable systems and networks, DSN 2006. IEEE Press, New York, pp 425\u2013434"},{"key":"884_CR43","unstructured":"Lofgren KMJ et al (2001) Wear leveling techniques for flash EEPROM systems. US Patent No 6,230,233, 8 May 2001"},{"key":"884_CR44","unstructured":"Lu CD (2005) Scalable diskless checkpointing for large parallel systems. Ph.D. dissertation, University of Illinois at Urbana-Champaign"},{"issue":"2","key":"884_CR45","doi-asserted-by":"publisher","first-page":"200","DOI":"10.1147\/rd.62.0200","volume":"6","author":"RE Lyons","year":"1962","unstructured":"Lyons RE, Vanderkulk W (1962) The use of triple-modular redundancy to improve computer reliability. IBM J Res Dev 6(2):200\u2013209","journal-title":"IBM J Res Dev"},{"key":"884_CR46","doi-asserted-by":"crossref","unstructured":"Maloney A, Goscinski A (2009) A survey and review of the current state of rollback-recovery for cluster systems. Concurr Comput., 1632\u20131666","DOI":"10.1002\/cpe.1413"},{"issue":"3","key":"884_CR47","doi-asserted-by":"publisher","first-page":"241","DOI":"10.1145\/367701.367728","volume":"32","author":"DS Milojicic","year":"2000","unstructured":"Milojicic DS, Douglis F, Paindaveine Y, Wheeler R, Zhou S (2000) Process migration. ACM Comput Surv 32(3):241\u2013299","journal-title":"ACM Comput Surv"},{"key":"884_CR48","unstructured":"MPI Forum (1994) MPI: a message-passing interface standard. Int J Supercomput Appl High Perform Comput"},{"key":"884_CR49","doi-asserted-by":"crossref","unstructured":"Oliner A, Stearley J (2007) What supercomputers say: a study of five system logs. Washington, DC, pp 575\u2013584","DOI":"10.1109\/DSN.2007.103"},{"issue":"5","key":"884_CR50","doi-asserted-by":"publisher","first-page":"41","DOI":"10.1109\/MIC.2002.1036037","volume":"6","author":"D Oppenheimer","year":"2002","unstructured":"Oppenheimer D, Patterson D (2002) Architecture and dependability of large-scale Internet services. IEEE Internet Comput 6(5):41\u201349","journal-title":"IEEE Internet Comput"},{"issue":"SI","key":"884_CR51","doi-asserted-by":"publisher","first-page":"361","DOI":"10.1145\/844128.844162","volume":"36","author":"S Osman","year":"2002","unstructured":"Osman S, Subhraveti D, Su G, Nieh J (2002) The design and implementation of zap: a system for migration computing environments. Oper Syst Rev 36(SI):361\u2013376","journal-title":"Oper Syst Rev"},{"key":"884_CR52","doi-asserted-by":"publisher","first-page":"101","DOI":"10.1016\/0167-739X(95)00038-T","volume":"12","author":"BJ Overeinder","year":"1996","unstructured":"Overeinder BJ, Sloot RN, Heederik RN, Hertzberger LO (1996) A dynamic load balancing system for parallel cluster computing. Future Gener Comput Syst 12:101\u2013115","journal-title":"Future Gener Comput Syst"},{"key":"884_CR53","unstructured":"PETSc (2012) [Online]. Available: \n                    http:\/\/www.mcs.anl.gov\/petsc\/petsc-as\/"},{"key":"884_CR54","unstructured":"Pinheiro E (2001) \n                    http:\/\/www.research.rutgers.edu\/~edpin\/epckpt\/"},{"key":"884_CR55","first-page":"62","volume-title":"IEEE parallel and distributed technologies","author":"JS Plank","year":"1994","unstructured":"Plank JS, Li K (1994) ickp: a consistent checkpointer for multicomputers. In: IEEE parallel and distributed technologies, vol\u00a02, pp\u00a062\u201367"},{"key":"884_CR56","volume-title":"Conference proceedings","author":"JS Plank","year":"1995","unstructured":"Plank JS, Beck M, Kingsley G, Li K (1995) Libckpt: transparent checkpointing under UNIX. In: Conference proceedings. Usenix, Berkeley"},{"key":"884_CR57","first-page":"29","volume-title":"The problem of replica determinism","author":"S Poledna","year":"1996","unstructured":"Poledna S (1996) The problem of replica determinism. Kluwer Academic, Boston, pp 29\u201330"},{"key":"884_CR58","doi-asserted-by":"publisher","first-page":"58","DOI":"10.1109\/FTCS.1997.614078","volume-title":"Proceedings of he 27th international symposium on fault-tolerant computing (FTCS\u201997)","author":"B Ramkumar","year":"1997","unstructured":"Ramkumar B, Strumpen V (1997) Portable checkpointing for heterogeneous archtitectures. In: Proceedings of he 27th international symposium on fault-tolerant computing (FTCS\u201997), pp 58\u201367"},{"issue":"2","key":"884_CR59","doi-asserted-by":"publisher","first-page":"220","DOI":"10.1109\/TSE.1975.6312842","volume":"SE-1","author":"B Randell","year":"1975","unstructured":"Randell B (1975) System structure for software fault tolerance. IEEE Trans Softw Eng SE-1(2):220\u2013232","journal-title":"IEEE Trans Softw Eng"},{"key":"884_CR60","unstructured":"Roman E (2002) A survey of checkpoint\/restart implementations. Berkeley Lab Technical Report (publication LBNL-54942)"},{"key":"884_CR61","first-page":"1","volume-title":"IEEE international parallel and distributed processing symposium","author":"J Ruscio","year":"2007","unstructured":"Ruscio J, Heffner M, Varadarajan S (2007) DejaVu: transparent user-level checkpointing, migration, and recovery for distributed systems. In: IEEE international parallel and distributed processing symposium, pp 1\u201310"},{"key":"884_CR62","volume-title":"Proceedings of the 19th IEEE international parallel and distributed processing symposium (IPDPS\u201905)\u2014workshop 18","author":"JC Sancho","year":"2005","unstructured":"Sancho JC, Petrini F, Davis K, Gioiosa R, Jiang S (2005) Current practice and a direction forward in checkpoint\/restart implementations for fault olerance. In: Proceedings of the 19th IEEE international parallel and distributed processing symposium (IPDPS\u201905)\u2014workshop 18"},{"issue":"4","key":"884_CR63","doi-asserted-by":"publisher","first-page":"479","DOI":"10.1177\/1094342005056139","volume":"19","author":"S Sankaran","year":"2005","unstructured":"Sankaran S, Squyres JM, Barrett B 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"},{"issue":"1","key":"884_CR64","doi-asserted-by":"publisher","DOI":"10.1088\/1742-6596\/78\/1\/012022","volume":"78","author":"B Schroeder","year":"2007","unstructured":"Schroeder B, Gibson G (2007) Understanding failures in petascale computers. J Phys Conf Ser 78(1):012022","journal-title":"J Phys Conf Ser"},{"issue":"4","key":"884_CR65","doi-asserted-by":"publisher","first-page":"337","DOI":"10.1109\/TDSC.2009.4","volume":"7","author":"B Schroeder","year":"2010","unstructured":"Schroeder B, Gibson GA (2010) A large-scale study of failures in high performance computing systems. IEEE Trans Dependable Secure Comput 7(4):337\u2013350","journal-title":"IEEE Trans Dependable Secure Comput"},{"key":"884_CR66","volume-title":"Supercomputing","author":"M Schulz","year":"2004","unstructured":"Schulz M, Bronevetsky G, Fernandes R, Marques D, Pingali K, Stodghill P (2004) Implementation and evaluation of a scalable application-level checkpoint-recovery scheme for MPI programs. In: Supercomputing, Pittsburgh, PA"},{"key":"884_CR67","series-title":"LNCS","first-page":"1","volume-title":"VECPAR 2010","author":"J Shalf","year":"2011","unstructured":"Shalf J, Dosanjh S, Morrison J (2011) Exascale computing technology challenges. In: VECPAR 2010, LNCS, vol 6449. Springer, Berlin, Heidelberg, pp 1\u201325"},{"key":"884_CR68","unstructured":"Slivinski T, Broglio C, Wild C et al. (1984) Study of fault-tolerant software technology. NASA CR 172385, Langley Research, Center, VA"},{"key":"884_CR69","volume-title":"Proc IPPS","author":"G Stellner","year":"1996","unstructured":"Stellner G (1996) Cocheck: checkpointing and process migration for MPI. In: Proc IPPS"},{"key":"884_CR70","first-page":"159","volume-title":"IEEE international workshop on intelligent data acquisition and advanced computing systems: technology and applications","author":"OO Sudakov","year":"2007","unstructured":"Sudakov OO, Meshcheriakov IS, Boyko YV (2007) CHPOX: transparent checkpointing system for Linux clusters. In: IEEE international workshop on intelligent data acquisition and advanced computing systems: technology and applications, pp 159\u2013164"},{"key":"884_CR71","doi-asserted-by":"crossref","first-page":"16","DOI":"10.1109\/SC.2000.10013","volume-title":"ACM\/IEEE 2000 conference","author":"T Takahashi","year":"2000","unstructured":"Takahashi T, Sumimoto S, Hori A, Harada H, Ishikawa Y (2000) PM2: high performance communication middleware for heterogeneous network environments, in supercomputing. In: ACM\/IEEE 2000 conference. IEEE Press, New York, p 16"},{"key":"884_CR72","unstructured":"Team Condor (2010) Condor version 7.5.3 manual. University of Wisconsin\u2013Madison"},{"key":"884_CR73","doi-asserted-by":"crossref","unstructured":"Teodorescu R, Nakano J, Torrellas J (2006) SWICH: a prototype for efficient cache-level checkpointing and rollback. IEEE Micro","DOI":"10.1109\/MM.2006.100"},{"key":"884_CR74","unstructured":"Top500 (2012) [Online]. Available: \n                    http:\/\/www.top500.org"},{"key":"884_CR75","first-page":"221","volume-title":"Proc of the 3rd ICDCIT conf","author":"J Walters","year":"2006","unstructured":"Walters J, Chaudhary V (2006) Application-level checkpointing techniques for parallel programs. In: Proc of the 3rd ICDCIT conf, pp 221\u2013234"},{"issue":"5","key":"884_CR76","doi-asserted-by":"publisher","first-page":"546","DOI":"10.1109\/71.382324","volume":"6","author":"Y-M Wang","year":"1995","unstructured":"Wang Y-M, Chung P-Y, Lin I-J, Fuchs WK (1995) Checkpoint space reclamation for uncoordinated checkpointing in message-passing systems. IEEE Trans Parallel Distrib Syst 6(5):546\u2013554","journal-title":"IEEE Trans Parallel Distrib Syst"},{"key":"884_CR77","doi-asserted-by":"crossref","DOI":"10.1093\/gmo\/9781561592630.article.28248","volume-title":"FREENIX track: USENIX annual technical conference","author":"RD William","year":"2001","unstructured":"William RD, James EL Jr (2001) User-level checkpointing for LinuxThreads programs. In: FREENIX track: USENIX annual technical conference"},{"key":"884_CR78","unstructured":"Zandy V (2002) ckpt [Online]. Available: \n                    http:\/\/pages.cs.wisc.edu\/~zandy\/ckpt\/"},{"key":"884_CR79","unstructured":"Zhong H, Nieh J (2001) CRAK: Linux checkpoint\/restart as a kernel module. Technical Report CUCS-014-01, Department of Computer Science, Columbia University"}],"container-title":["The Journal of Supercomputing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-013-0884-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11227-013-0884-0\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-013-0884-0","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-013-0884-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,9,26]],"date-time":"2019-09-26T23:01:04Z","timestamp":1569538864000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11227-013-0884-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2013,2,12]]},"references-count":79,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2013,9]]}},"alternative-id":["884"],"URL":"https:\/\/doi.org\/10.1007\/s11227-013-0884-0","relation":{},"ISSN":["0920-8542","1573-0484"],"issn-type":[{"value":"0920-8542","type":"print"},{"value":"1573-0484","type":"electronic"}],"subject":[],"published":{"date-parts":[[2013,2,12]]}}}