{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,25]],"date-time":"2026-04-25T21:05:27Z","timestamp":1777151127790,"version":"3.51.4"},"publisher-location":"Berlin, Heidelberg","reference-count":10,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"value":"9783540241287","type":"print"},{"value":"9783540305668","type":"electronic"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2004]]},"DOI":"10.1007\/978-3-540-30566-8_27","type":"book-chapter","created":{"date-parts":[[2010,7,2]],"date-time":"2010-07-02T21:07:43Z","timestamp":1278104863000},"page":"217-222","source":"Crossref","is-referenced-by-count":4,"title":["Highly Reliable Linux HPC Clusters: Self-Awareness Approach"],"prefix":"10.1007","author":[{"given":"Chokchai","family":"Leangsuksun","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tong","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yudan","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Stephen L.","family":"Scott","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Richard","family":"Libby","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ibrahim","family":"Haddad","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"key":"27_CR1","doi-asserted-by":"crossref","unstructured":"Leangsuksun, C., Shen, L., Liu, T., Song, H., Scott, S.: Availability Prediction and Modeling of High Availability OSCAR Cluster. In: IEEE International Conference on Cluster Computing (Cluster 2003), Hong Kong, December 2-4 (2003)","DOI":"10.1109\/CLUSTR.2003.1253337"},{"key":"27_CR2","unstructured":"Leangsuksun, C., Shen, L., Liu, T., Song, H., Scott, S.: Dependability Prediction of High Availability OSCAR Cluster Server. In: The 2003 International Conference on Parallel and Distributed Processing Techniques and Applications (PDPTA 2003), Las Vegas, Nevada, USA, June 23-26 (2003)"},{"key":"27_CR3","unstructured":"Finley, B., Frazier, D., Gonyou, A., Jort, A., et al.: SystemImager v3.0.x Manual, February 19 (2003)"},{"key":"27_CR4","unstructured":"Brim, M.J., Mattson, T.G., Scott, S.L.: OSCAR: Open Source Cluster Application Resources. In: Ottawa Linux Symposium 2001, Ottawa, Canada (2001)"},{"issue":"2","key":"27_CR5","first-page":"9","volume":"1","author":"J. Muppala","year":"1994","unstructured":"Muppala, J., Ciardo, G., Trivedi, K.S.: Stochastic Reward Nets for Reliability Prediction, Communications in Reliability. Maintainability and Serviceability: An International Journal published by SAE International\u00a01(2), 9\u201320 (1994)","journal-title":"Maintainability and Serviceability: An International Journal published by SAE International"},{"key":"27_CR6","first-page":"142","volume-title":"Proc. Int. Workshop on Petri Nets and Performance Models","author":"G. Ciardo","year":"1989","unstructured":"Ciardo, G., Muppala, J., Trivedi, K.: SPNP: Stochastic Petri net package. In: Proc. Int. Workshop on Petri Nets and Performance Models, pp. 142\u2013150. IEEE Computer Society Press, Los Alamitos (1989)"},{"key":"27_CR7","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. In: LACSI Symposium, Santa Fe, NM, October 27-29 (2003)"},{"key":"27_CR8","unstructured":"Fagg, G.E., Gabriel, E., Chen, Z., Angskun, T., Bosilca, G., Bukovsky, A., Dongarra, J.J.: Fault Tolerant Communication Library and Applications for High Performance Computing. In: LACSI Symposium 2003, Santa Fe, NM, October 27-29 (2003)"},{"key":"27_CR9","unstructured":"Kottapalli, C.V.: Intelligence based Checkpoint Placement for Parallel MPI programs on Linux Clusters, Master Thesis Report, Computer Science Program, Louisiana Tech University (August 2004) (in preparation)"},{"key":"27_CR10","unstructured":"Leangsuksun, C., et al.: A Failure Predictive and Policy-Based High Availability Strategy for Linux High Performance Computing Cluster. In: The 5th LCI International Conference on Linux Clusters: The HPC Revolution 2004, Austin, TX, May 18-20 (2004)"}],"container-title":["Lecture Notes in Computer Science","Parallel and Distributed Processing and Applications"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-540-30566-8_27.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,11,19]],"date-time":"2020-11-19T04:22:42Z","timestamp":1605759762000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-540-30566-8_27"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2004]]},"ISBN":["9783540241287","9783540305668"],"references-count":10,"URL":"https:\/\/doi.org\/10.1007\/978-3-540-30566-8_27","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2004]]}}}