{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,18]],"date-time":"2025-11-18T12:17:46Z","timestamp":1763468266086,"version":"3.41.0"},"publisher-location":"Cham","reference-count":21,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319172477"},{"type":"electronic","value":"9783319172484"}],"license":[{"start":{"date-parts":[[2015,1,1]],"date-time":"2015-01-01T00:00:00Z","timestamp":1420070400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2015,1,1]],"date-time":"2015-01-01T00:00:00Z","timestamp":1420070400000},"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":[[2015]]},"DOI":"10.1007\/978-3-319-17248-4_12","type":"book-chapter","created":{"date-parts":[[2015,4,17]],"date-time":"2015-04-17T15:11:09Z","timestamp":1429283469000},"page":"237-248","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["A Case for Epidemic Fault Detection and Group Membership in HPC Storage Systems"],"prefix":"10.1007","author":[{"given":"Shane","family":"Snyder","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Philip","family":"Carns","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jonathan","family":"Jenkins","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kevin","family":"Harms","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Robert","family":"Ross","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Misbah","family":"Mubarak","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Christopher","family":"Carothers","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2015,4,18]]},"reference":[{"key":"12_CR1","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"126","DOI":"10.1007\/BFb0030680","volume-title":"Distributed Algorithms","author":"MK Aguilera","year":"1997","unstructured":"Aguilera, M.K., Chen, W., Toueg, S.: Heartbeat: A timeout-free failure detector for quiescent reliable communication. In: Mavronicolas, Marios (ed.) WDAG 1997. LNCS, vol. 1320, pp. 126\u2013140. Springer, Heidelberg (1997)"},{"key":"12_CR2","doi-asserted-by":"crossref","unstructured":"Alexandrov, A., Ionescu, M.F., Schauser, K.E., Scheiman, C.: LogGP: Incorporating long messages into the LogP model \u2013 one step closer towards a realistic model for parallel computation. In: Proceedings of the Seventh Annual ACM Symposium on Parallel Algorithms and Architectures, SPAA 1995, pp. 95\u2013105. ACM, New York (1995). http:\/\/doi.acm.org\/10.1145\/215399.215427","DOI":"10.1145\/215399.215427"},{"issue":"4","key":"12_CR3","doi-asserted-by":"publisher","first-page":"311","DOI":"10.1145\/210223.210224","volume":"13","author":"Y Amir","year":"1995","unstructured":"Amir, Y., Moser, L.E., Melliar-Smith, P.M., Agarwal, D.A., Ciarfella, P.: The totem single-ring ordering and membership protocol. ACM Trans. Comput. Syst. 13(4), 311\u2013342 (1995)","journal-title":"ACM Trans. Comput. Syst."},{"key":"12_CR4","doi-asserted-by":"crossref","unstructured":"Barnes, Jr., P.D., Carothers, C.D., Jefferson, D.R., LaPre, J.M.: Warp speed: Executing time warp on 1,966,080 cores. In: Proceedings of the 2013 ACM SIGSIM Conference on Principles of Advanced Discrete Simulation, SIGSIM-PADS 2013, pp. 327\u2013336. ACM, New York (2013). http:\/\/doi.acm.org\/10.1145\/2486092.2486134","DOI":"10.1145\/2486092.2486134"},{"key":"12_CR5","unstructured":"Beekhof, A.: Pacemaker: a scalable high availability cluster resource manager. http:\/\/clusterlabs.org\/. Retrieved July 2014"},{"issue":"12","key":"12_CR6","doi-asserted-by":"publisher","first-page":"37","DOI":"10.1145\/163298.163303","volume":"36","author":"KP Birman","year":"1993","unstructured":"Birman, K.P.: The process group approach to reliable distributed computing. Commun. ACM 36(12), 37\u201353 (1993). http:\/\/doi.acm.org\/10.1145\/163298.163303","journal-title":"Commun. ACM"},{"issue":"2","key":"12_CR7","doi-asserted-by":"publisher","first-page":"41","DOI":"10.1145\/312203.312207","volume":"17","author":"KP Birman","year":"1999","unstructured":"Birman, K.P., Hayden, M., Ozkasap, O., Xiao, Z., Budiu, M., Minsky, Y.: Bimodal multicast. ACM Trans. Comput. Syst. 17(2), 41\u201388 (1999). http:\/\/doi.acm.org\/10.1145\/312203.312207","journal-title":"ACM Trans. Comput. Syst."},{"issue":"5","key":"12_CR8","doi-asserted-by":"publisher","first-page":"561","DOI":"10.1109\/TC.2002.1004595","volume":"51","author":"W Chen","year":"2002","unstructured":"Chen, W., Toueg, S., Aguilera, M.K.: On the quality of service of failure detectors. IEEE Trans. Comput. 51(5), 561\u2013580 (2002)","journal-title":"IEEE Trans. Comput."},{"key":"12_CR9","unstructured":"Cope, J., Liu, N., Lang, S., Carns, P., Carothers, C., Ross, R.: Codes: Enabling co-design of multilayer exascale storage architectures. In: Proceedings of the Workshop on Emerging Supercomputing Technologies (2011)"},{"key":"12_CR10","unstructured":"Dake, S.C., Caulfield, C., Beekhof, A.: The Corosync cluster engine. In: Linux Symposium, vol. 85 (2008)"},{"key":"12_CR11","unstructured":"Das, A., Gupta, I., Motivala, A.: Swim: Scalable weakly-consistent infection-style process group membership protocol. In: Proceedings of the 2002 International Conference on Dependable Systems and Networks, DSN 2002, pp. 303\u2013312. IEEE Computer Society Press, Washington, DC (2002). http:\/\/ieeexplore.ieee.org\/xpls\/abs_all.jsp?arnumber=1028914"},{"key":"12_CR12","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"11","DOI":"10.1007\/3-540-48158-3_2","volume-title":"Recent Advances in Parallel Virtual Machine and Message Passing Interface","author":"W Gropp","year":"1999","unstructured":"Gropp, W., Lusk, E.: Reproducible measurements of MPI performance characteristics. In: Margalef, T., Dongarra, J., Luque, E. (eds.) PVM\/MPI 1999. LNCS, vol. 1697, pp. 11\u201318. Springer, Heidelberg (1999)"},{"key":"12_CR13","doi-asserted-by":"crossref","unstructured":"Gupta, I., Chandra, T.D., Goldszmidt, G.S.: On scalable and efficient distributed failure detectors. In: Proceedings of the Twentieth Annual ACM Symposium on Principles of Distributed Computing, PODC 2001, pp. 170\u2013179. ACM Press, New York (2001). http:\/\/doi.acm.org\/10.1145\/383962.384010","DOI":"10.1145\/383962.384010"},{"key":"12_CR14","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"659","DOI":"10.1007\/978-3-540-75444-2_62","volume-title":"High Performance Computing and Communications","author":"T Hoefler","year":"2007","unstructured":"Hoefler, T., Mehlan, T., Lumsdaine, A., Rehm, W.: Netgauge: a network performance measurement framework. In: Perrott, R., Chapman, B.M., Subhlok, J., de Mello, R.F., Yang, L.T. (eds.) HPCC 2007. LNCS, vol. 4782, pp. 659\u2013671. Springer, Heidelberg (2007)"},{"key":"12_CR15","doi-asserted-by":"crossref","unstructured":"Jahanian, F., Fakhouri, S., Rajkumar, R.: Processor group membership protocols: specification, design and implementation. In: Proceedings of the 12th Symposium on Reliable Distributed Systems, pp. 2\u201311, October 1993","DOI":"10.1109\/RELDIS.1993.393478"},{"issue":"2","key":"12_CR16","doi-asserted-by":"publisher","first-page":"35","DOI":"10.1145\/1773912.1773922","volume":"44","author":"A Lakshman","year":"2010","unstructured":"Lakshman, A., Malik, P.: Cassandra: A decentralized structured storage system. SIGOPS Operating Sys. Rev. 44(2), 35\u201340 (2010). http:\/\/doi.acm.org\/10.1145\/1773912.1773922","journal-title":"SIGOPS Operating Sys. Rev."},{"issue":"2","key":"12_CR17","doi-asserted-by":"publisher","first-page":"133","DOI":"10.1145\/279227.279229","volume":"16","author":"L Lamport","year":"1998","unstructured":"Lamport, L.: The part-time parliament. ACM Trans. Comput. Syst. (TOCS) 16(2), 133\u2013169 (1998)","journal-title":"ACM Trans. Comput. Syst. (TOCS)"},{"key":"12_CR18","doi-asserted-by":"crossref","unstructured":"Liu, N., Cope, J., Carns, P., Carothers, C., Ross, R., Grider, G., Crume, A., Maltzahn, C.: On the role of burst buffers in leadership-class storage systems. In: 2012 IEEE 28th Symposium on Mass Storage Systems and Technologies (MSST), pp. 1\u201311. IEEE (2012)","DOI":"10.1109\/MSST.2012.6232369"},{"issue":"1","key":"12_CR19","doi-asserted-by":"publisher","first-page":"31","DOI":"10.1109\/32.481515","volume":"22","author":"MK Reiter","year":"1996","unstructured":"Reiter, M.K.: A secure group membership protocol. IEEE Trans. Softw. Eng. 22(1), 31\u201342 (1996)","journal-title":"IEEE Trans. Softw. Eng."},{"key":"12_CR20","first-page":"55","volume-title":"Middleware 1998","author":"R van Renesse","year":"1998","unstructured":"van Renesse, R., Minsky, Y., Hayden, M.: A gossip-style failure detection service. In: Davies, N., Jochen, S., Raymond, K. (eds.) Middleware 1998, pp. 55\u201370. Springer, London (1998). http:\/\/dx.doi.org\/10.1007\/978-1-4471-1283-9_4"},{"key":"12_CR21","unstructured":"Weil, S.A., Brandt, S.A., Miller, E.L., Long, D.D.E., Maltzahn, C.: Ceph: A scalable, high-performance distributed file system. In: Proceedings of the 7th Symposium on Operating Systems Design and Implementation, OSDI 2006, pp. 307\u2013320. USENIX Association, Berkeley (2006). http:\/\/dl.acm.org\/citation.cfm?id=1298485"}],"container-title":["Lecture Notes in Computer Science","High Performance Computing Systems. Performance Modeling, Benchmarking, and Simulation"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-17248-4_12","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,22]],"date-time":"2025-05-22T17:55:53Z","timestamp":1747936553000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-319-17248-4_12"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015]]},"ISBN":["9783319172477","9783319172484"],"references-count":21,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-17248-4_12","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2015]]},"assertion":[{"value":"18 April 2015","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}}]}}