{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,8]],"date-time":"2024-09-08T10:35:20Z","timestamp":1725791720677},"publisher-location":"Berlin, Heidelberg","reference-count":24,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783642544194"},{"type":"electronic","value":"9783642544200"}],"license":[{"start":{"date-parts":[[2014,1,1]],"date-time":"2014-01-01T00:00:00Z","timestamp":1388534400000},"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":[],"published-print":{"date-parts":[[2014]]},"DOI":"10.1007\/978-3-642-54420-0_69","type":"book-chapter","created":{"date-parts":[[2014,4,9]],"date-time":"2014-04-09T21:40:41Z","timestamp":1397079641000},"page":"707-716","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Model-Driven Resilience Assessment of Modifications to HPC Infrastructures"],"prefix":"10.1007","author":[{"given":"Christian","family":"Straube","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dieter","family":"Kranzlm\u00fcller","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"key":"69_CR1","doi-asserted-by":"crossref","unstructured":"Elliott, J., et al.: Combining Partial Redundancy and Checkpointing for HPC. In: Proc. of the 32th Intl. IEEE Conf. on Distributed Computing Systems, ICDCS (2012)","DOI":"10.1109\/ICDCS.2012.56"},{"key":"69_CR2","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"59","DOI":"10.1007\/978-3-540-68947-8_9","volume-title":"Dependability Metrics","author":"I. Eusgeld","year":"2008","unstructured":"Eusgeld, I., Fechner, B., Salfner, F., Walter, M., Limbourg, P., Zhang, L.: Hardware Reliability. In: Eusgeld, I., Freiling, F.C., Reussner, R. (eds.) Dependability Metrics. LNCS, vol.\u00a04909, pp. 59\u2013103. Springer, Heidelberg (2008)"},{"key":"69_CR3","doi-asserted-by":"crossref","unstructured":"Chen, D., et al.: Looking Under the Hood of the IBM Blue Gene\/Q Network. In: Proc. of the Intl. ACM\/IEEE Conf. on High Performance Computing, Networking, Storage and Analysis, SC 2012 (2012)","DOI":"10.1109\/SC.2012.72"},{"key":"69_CR4","doi-asserted-by":"crossref","unstructured":"Meswani, M., et al.: Modeling and Predicting Disk I\/O Time of HPC Applications. In: Proc. of the High Performance Computing Modernization Program Users Group Conf., HPCMP-UGC (2010)","DOI":"10.1109\/HPCMP-UGC.2010.27"},{"issue":"3","key":"69_CR5","first-page":"77","volume":"38","author":"M. Broadbent","year":"1997","unstructured":"Broadbent, M., Weill, P.: Management by Maxim: How Business and IT Managers Can Create IT Infrastructures. Sloan Management Review\u00a038(3), 77\u201392 (1997)","journal-title":"Sloan Management Review"},{"issue":"4","key":"69_CR6","first-page":"317","volume":"38","author":"H. Song","year":"2006","unstructured":"Song, H., et al.: Availability Modeling and Evaluation on High Performance Cluster Computing Systems. Journal of Research and Practice in Information Technology\u00a038(4), 317\u2013335 (2006)","journal-title":"Journal of Research and Practice in Information Technology"},{"key":"69_CR7","unstructured":"Straube, C., Kranzlm\u00fcller, D.: A Meta Model for the Analysis of Modification Effects onto HPDC Infrastructures. Submitted to 27th Intl. Conf. on Architecture of Computing Systems, ARCS 2014 (2014)"},{"key":"69_CR8","doi-asserted-by":"crossref","unstructured":"Straube, C., Kranzlm\u00fcller, D.: An IT-Infrastructure Capability Model. In: Proc. of the 10th ACM Conf. on Computing Frontiers, CF 2013 (2013)","DOI":"10.1145\/2482767.2482781"},{"key":"69_CR9","doi-asserted-by":"crossref","unstructured":"Jones, W., et al.: Application Monitoring and Checkpointing in HPC: Looking Towards Exascale Systems. In: Proc. of the 50th Annual Southeast Regional Conf. (2012)","DOI":"10.1145\/2184512.2184574"},{"key":"69_CR10","doi-asserted-by":"crossref","unstructured":"Jones, W., et al.: Impact of Sub-Optimal Checkpoint Intervals on Application Efficiency in Computational Clusters. In: Proc. of the 19th Intl. ACM Symposium on High Performance Distributed Computing, HPDC 2010 (2010)","DOI":"10.1145\/1851476.1851509"},{"key":"69_CR11","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"432","DOI":"10.1007\/11549468_50","volume-title":"Euro-Par 2005 Parallel Processing","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 2005. LNCS, vol.\u00a03648, pp. 432\u2013441. Springer, Heidelberg (2005)"},{"key":"69_CR12","unstructured":"DMTF: Common Information Model (CIM) Metamodel (Specification). Technical Report DSP0004, Distributed Management Task Force, DMTF (2012)"},{"key":"69_CR13","unstructured":"Lu, C.: Failure Data Analysis of HPC Systems. CoRR abs\/1302.4779 (2013)"},{"key":"69_CR14","unstructured":"Avizienis, A., et al.: Fundamental Concepts of Dependability. Technical report, University of California, Los Angeles, UCLA (2010)"},{"key":"69_CR15","unstructured":"Verbrugge, S., et al.: General Availability Model for Multilayer Transport Networks. In: Proc. of the 5th Intl. Workshop on Design of Reliable Communication Networks, DRCN 2005 (2005)"},{"key":"69_CR16","doi-asserted-by":"crossref","unstructured":"Pedicini, G., Green, J.: SPOTlight on Testing: Stability, Performance and Operational Testing of LANL HPC Clusters. In: Proc. of the Intl. ACM\/IEEE Conf. for High Performance Computing, Networking, Storage and Analysis, SC 2011 (2011)","DOI":"10.1145\/2063348.2063382"},{"key":"69_CR17","doi-asserted-by":"crossref","unstructured":"Boukerche, A., et al.: Towards Building a Highly-Available Cluster Based Model for High Performance Computing. In: Proc. of the 20th Intl. Parallel and Distributed Processing Symposium, IPDPS 2006 (2006)","DOI":"10.1109\/IPDPS.2006.1639633"},{"key":"69_CR18","unstructured":"Birolini, A.: Reliability Engineering: Theory and Practice. Springer (2007)"},{"key":"69_CR19","unstructured":"Stearley, J.: Defining and Measuring Supercomputer Reliability, Availability, and Serviceability (RAS). In: Proc. of the Linux Clusters Institute Conf. (2005)"},{"key":"69_CR20","doi-asserted-by":"crossref","unstructured":"Chandler, C., et al.: Towards Resilient High Performance Applications Through Real Time Reliability Metric Generation and Autonomous Failure Correction. In: Proc. of the Workshop on Resiliency in High Performance (2009)","DOI":"10.1145\/1552526.1552527"},{"key":"69_CR21","unstructured":"Xu, J., et al.: Networked Windows NT system field failure data analysis. In: Proc. of the Intl. Pacific Rim Symposium on Dependable Computing (1999)"},{"key":"69_CR22","unstructured":"Trivedi, K.: Probability and Statistics with Reliability Queuing and Computer Science Applications. John Wiley & Sons, Inc. (2001)"},{"key":"69_CR23","unstructured":"Military Handbook: Reliability Prediction of Electronic Equipment. Technical Report MIL-HDBK-217F, Department of Defense (1991)"},{"key":"69_CR24","doi-asserted-by":"crossref","unstructured":"Bagchi, S., et al.: Dependency Analysis in Distributed Systems using Fault Injection: Application to Problem Determination in an e-commerce Environment. In: Proc. of the 12th Intl. Workshop on Distributed Systems, DSOM 2001 (2001)","DOI":"10.3990\/2.14"}],"container-title":["Lecture Notes in Computer Science","Euro-Par 2013: Parallel Processing Workshops"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-54420-0_69","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,4,20]],"date-time":"2020-04-20T00:13:32Z","timestamp":1587341612000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-54420-0_69"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2014]]},"ISBN":["9783642544194","9783642544200"],"references-count":24,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-54420-0_69","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2014]]},"assertion":[{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}