{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,3]],"date-time":"2026-10-03T10:31:09Z","timestamp":1791023469784,"version":"4.1.0"},"reference-count":24,"publisher":"Springer Science and Business Media LLC","issue":"5","license":[{"start":{"date-parts":[[2009,8,5]],"date-time":"2009-08-05T00:00:00Z","timestamp":1249430400000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Int J Parallel Prog"],"published-print":{"date-parts":[[2009,10]]},"DOI":"10.1007\/s10766-009-0115-8","type":"journal-article","created":{"date-parts":[[2009,8,4]],"date-time":"2009-08-04T10:19:07Z","timestamp":1249381147000},"page":"433-461","source":"Crossref","is-referenced-by-count":7,"title":["Fault-Management in P2P-MPI"],"prefix":"10.1007","volume":"37","author":[{"given":"St\u00e9phane","family":"Genaud","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Emmanuel","family":"Jeannot","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Choopan","family":"Rattanapoka","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2009,8,5]]},"reference":[{"key":"115_CR1","doi-asserted-by":"crossref","unstructured":"Alvisi, L., Marzullo, K.: Message logging: pessimistic, optimistic, and causal. In: Proceeding of the 15th International Conference on Distributed Computing Systems (ICDCS\u201995), pp. 229\u2013236 (1995)","DOI":"10.1109\/ICDCS.1995.500024"},{"key":"115_CR2","doi-asserted-by":"crossref","unstructured":"Amdahl, G.M.: Validity of the single processor approach to achieving large scale computing capabilities. In: Proceedings of AFIPS 1967 Spring Joint Computer Conference, vol. 30, pp. 483\u2013485, (1967)","DOI":"10.1145\/1465482.1465560"},{"key":"115_CR3","doi-asserted-by":"crossref","unstructured":"Baker, M., Carpenter, B., Shafi, A.: MPJ express: towards thread safe java HPC. In: CLUSTER. IEEE (2006)","DOI":"10.1109\/CLUSTR.2006.311890"},{"issue":"4","key":"115_CR4","doi-asserted-by":"crossref","first-page":"303","DOI":"10.1023\/B:CLUS.0000039491.64560.8a","volume":"7","author":"R. Batchu","year":"2004","unstructured":"Batchu R., Dandass Y.S., Skjellum A., Beddhu M.: MPI\/FT: a model-based approach to low-overhead fault tolerant message-passing middleware. Clust. Comput. 7(4), 303\u2013315 (2004)","journal-title":"Clust. Comput."},{"key":"115_CR5","doi-asserted-by":"crossref","unstructured":"Bornemann, M., van Nieuwpoort, R.V., Kielmann, T.: MPJ\/Ibis: a flexible and efficient message passing platform for java. In: Euro PVM\/MPI 2005 (2005)","DOI":"10.1007\/11557265_30"},{"key":"115_CR6","doi-asserted-by":"crossref","unstructured":"Bouteiller, A., Cappello, F., H\u00e9rault, T., Krawezik, G., Lemarinier, P., Magniette, F.: Mpich-v2: a fault tolerant mpi for volatile nodes based on pessimistic sender based message logging. In: Proceedings of the ACM\/IEEE SC2003 Conference on High Performance Networking and Computing, p. 25. ACM (2003)","DOI":"10.1145\/1048935.1050176"},{"issue":"3","key":"115_CR7","doi-asserted-by":"crossref","first-page":"417","DOI":"10.1016\/j.future.2004.04.011","volume":"21","author":"F. Cappello","year":"2005","unstructured":"Cappello F., Djilali S., Fedak G., H\u00e9rault T., Magniette F., N\u00e9ri V., Lodygensky O.: Computing on large-scale distributed systems: Xtremweb architecture, programming models, security, tests and convergence with grid. Future Generation Comp. Syst. 21(3), 417\u2013437 (2005)","journal-title":"Future Generation Comp. Syst."},{"issue":"11","key":"115_CR8","doi-asserted-by":"crossref","first-page":"1019","DOI":"10.1002\/1096-9128(200009)12:11<1019::AID-CPE518>3.0.CO;2-G","volume":"12","author":"B. Carpenter","year":"2000","unstructured":"Carpenter B., Getov V., Judd G., Skjellum A., Fox G.: Mpj: Mpi-like message passing for java. Concurr. Pract. Exp. 12(11), 1019\u20131038 (2000)","journal-title":"Concurr. Pract. Exp."},{"issue":"2","key":"115_CR9","doi-asserted-by":"crossref","first-page":"225","DOI":"10.1145\/226643.226647","volume":"43","author":"T.D. Chandra","year":"1996","unstructured":"Chandra T.D., Toueg S.: Unreliable failure detectors for reliable distributed systems. J. ACM 43(2), 225\u2013267 (1996)","journal-title":"J. ACM"},{"key":"115_CR10","volume-title":"MAPLE reference manual","author":"B.W. Char","year":"1989","unstructured":"Char B.W., Geddes K.O., Gonnet G.H., Monagan M.B., Watt S.M.: MAPLE reference manual. University of Waterloo, Waterloo Maple Software, Waterloo (1989)"},{"issue":"3","key":"115_CR11","doi-asserted-by":"crossref","first-page":"225","DOI":"10.1007\/s10723-006-9040-x","volume":"4","author":"W. Cirne","year":"2006","unstructured":"Cirne W., Brasileiro F.V., Andrade N., Costa L., Andrade A., Novaes R., Mowbray M.: Labs of the world, unite!!!. J. Grid Comput. 4(3), 225\u2013246 (2006)","journal-title":"J. Grid Comput."},{"issue":"4","key":"115_CR12","doi-asserted-by":"crossref","first-page":"372","DOI":"10.1145\/1041680.1041682","volume":"36","author":"X. D\u00e9fago","year":"2004","unstructured":"D\u00e9fago X., Schiper A., Urb\u00e1n P.: Total order broadcast and multicast algorithms: taxonomy and survey. ACM Comput. Surv. 36(4), 372\u2013421 (2004)","journal-title":"ACM Comput. Surv."},{"key":"115_CR13","doi-asserted-by":"crossref","unstructured":"Felber, P., Defago, X., Guerraoui, R., Oser, P.: Failure detectors as first class objects. In: Proceeding of the 9th IEEE Intl. Symposium on Distributed Objects and Applications (DOA\u201999), pp. 132\u2013141, (1999)","DOI":"10.1109\/DOA.1999.794001"},{"issue":"1","key":"115_CR14","doi-asserted-by":"crossref","first-page":"27","DOI":"10.1007\/s10723-006-9056-2","volume":"5","author":"S. Genaud","year":"2007","unstructured":"Genaud S., Rattanapoka C.: P2P-MPI: a peer-to-peer framework for robust execution of message passing parallel programs on grids. J. Grid Comput. 5(1), 27\u201342 (2007)","journal-title":"J. Grid Comput."},{"key":"115_CR15","first-page":"432","volume-title":"Euro-Par, volume 3648 of Lecture Notes in Computer Science","author":"D. Nurmi","year":"2005","unstructured":"Nurmi D., Brevik J., Wolski R.: Modeling machine availability in enterprise and wide-area distributed computing environments. In: Cunha, J.C., Medeiros, P.D. (eds) Euro-Par, volume 3648 of Lecture Notes in Computer Science, pp. 432\u2013441. Springer, Berlin (2005)"},{"issue":"3","key":"115_CR16","doi-asserted-by":"crossref","first-page":"197","DOI":"10.1023\/A:1011494323443","volume":"4","author":"S. Ranganathan","year":"2001","unstructured":"Ranganathan S., George A.D., Todd R.W., Chidester M.C.: Gossip-style failure detection and distributed consensus for scalable heterogeneous clusters. Clust. Comput. 4(3), 197\u2013209 (2001)","journal-title":"Clust. Comput."},{"key":"115_CR17","doi-asserted-by":"crossref","unstructured":"Renesse, R.V., Minsky, Y., Hayden, M.: A gossip-style failure detection service. In: IFIP International Conference on Distributed Systems Platforms and Open Distributed Middleware, pp. 55\u201370, England, (1998)","DOI":"10.1007\/978-1-4471-1283-9_4"},{"issue":"4","key":"115_CR18","doi-asserted-by":"crossref","first-page":"479","DOI":"10.1177\/1094342005056139","volume":"19","author":"S. Sankaran","year":"2005","unstructured":"Sankaran S., Squyres J.M., Barrett B., Lumsdaine A., Duell J., Hargrove P., Roman E.: The LAM\/MPI checkpoint\/restart framework: system-initiated checkpointing. Int. J. High Perform. Comput. Appl. 19(4), 479\u2013493 (2005)","journal-title":"Int. J. High Perform. Comput. Appl."},{"key":"115_CR19","first-page":"169","volume-title":"Replication management using the state machine approach, Chapter 7","author":"F.B. Schneider","year":"1993","unstructured":"Schneider F.B.: Replication management using the state machine approach, Chapter 7, pp. 169\u2013195. ACM Press, New York (1993)"},{"key":"115_CR20","doi-asserted-by":"crossref","unstructured":"Shudo, K., Tanaka, Y., Sekiguchi, S.: P3: P2P-based middleware enabling transfer and aggregation of computational resource. In: 5th International Workshop on Global and Peer-to-Peer Computing. IEEE, (2005)","DOI":"10.1109\/CCGRID.2005.1558563"},{"key":"115_CR21","volume-title":"MPI: the complete reference","author":"M. Snir","year":"1995","unstructured":"Snir M., Otto S.W., Walker D.W., Dongarra J., Huss-Lederman S.: MPI: the complete reference. MIT Press, Cambridge (1995)"},{"key":"115_CR22","doi-asserted-by":"crossref","unstructured":"Stellner, G.: CoCheck: checkpointing and process migration for MPI. In: Proceedings of the 10th International Parallel Processing Symposium (IPPS\u201996), pp. 526\u2013531 (1996)","DOI":"10.1109\/IPPS.1996.508106"},{"issue":"7-8","key":"115_CR23","doi-asserted-by":"crossref","first-page":"1079","DOI":"10.1002\/cpe.860","volume":"17","author":"R. Nieuwpoort van","year":"2005","unstructured":"Nieuwpoort R., Maassen J., Wrzesinska G., Hofman R.F.H., Jacobs C.J.H., Kielmann T., Bal H.E.: Ibis: a flexible and efficient java-based grid programming environment. Concurr. Pract. Exp. 17(7-8), 1079\u20131107 (2005)","journal-title":"Concurr. Pract. Exp."},{"key":"115_CR24","first-page":"257","volume-title":"HiPC, volume 4873 of Lecture Notes in Computer Science","author":"J.P. Walters","year":"2007","unstructured":"Walters J.P., Chaudhary V.: A scalable asynchronous replication-based strategy for fault tolerant MPI applications. In: Aluru, S., Parashar, M., Badrinath, R., Prasanna, V.K. (eds) HiPC, volume 4873 of Lecture Notes in Computer Science, pp. 257\u2013268. Springer, Berlin (2007)"}],"container-title":["International Journal of Parallel Programming"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10766-009-0115-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10766-009-0115-8\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10766-009-0115-8","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,11]],"date-time":"2025-02-11T16:34:19Z","timestamp":1739291659000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10766-009-0115-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2009,8,5]]},"references-count":24,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2009,10]]}},"alternative-id":["115"],"URL":"https:\/\/doi.org\/10.1007\/s10766-009-0115-8","relation":{},"ISSN":["0885-7458","1573-7640"],"issn-type":[{"value":"0885-7458","type":"print"},{"value":"1573-7640","type":"electronic"}],"subject":[],"published":{"date-parts":[[2009,8,5]]}}}