{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,4,12]],"date-time":"2025-04-12T05:47:51Z","timestamp":1744436871344},"reference-count":58,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2006,4,1]],"date-time":"2006-04-01T00:00:00Z","timestamp":1143849600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Cluster Comput"],"published-print":{"date-parts":[[2006,4]]},"DOI":"10.1007\/s10586-006-7562-4","type":"journal-article","created":{"date-parts":[[2006,4,25]],"date-time":"2006-04-25T20:40:56Z","timestamp":1145997656000},"page":"175-190","source":"Crossref","is-referenced-by-count":31,"title":["Autonomous recovery in componentized Internet applications"],"prefix":"10.1007","volume":"9","author":[{"given":"George","family":"Candea","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Emre","family":"Kiciman","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shinichi","family":"Kawamoto","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Armando","family":"Fox","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"key":"7562_CR1","doi-asserted-by":"crossref","unstructured":"M. K. Aguilera, J. C. Mogul, J. L. Wiener, P. Reynolds, and A. Muthitacharoen. Performance debugging for distributed systems of black boxes. In: Proc. 19th ACM Symposium on Operating Systems Principles, Bolton Lauding, NY (2003).","DOI":"10.1145\/945445.945454"},{"key":"7562_CR2","unstructured":"M. Baker and M. Sullivan. The Recovery Box: Using fast recovery to provide high availability in the UNIX environment. In: Proc. Summer USENIX Technical Conference, San Antonio, TX (1992)."},{"key":"7562_CR3","unstructured":"M. Barnes. J2EE application servers: Market overview. The Meta Group, (Mar. 2004)."},{"key":"7562_CR4","doi-asserted-by":"crossref","unstructured":"J.F. Bartlett. A NonStop kernel. In: Proc. 8th ACM Symposium on Operating Systems Principles, Pacific Grove, CA (1981).","DOI":"10.1145\/800216.806587"},{"key":"7562_CR5","doi-asserted-by":"crossref","unstructured":"A. Bouloutas, S. Calo, and A. Finkel. Alarm correlation and fault identification in communication networks. IEEE Transactions on Communications (1994).","DOI":"10.1109\/TCOMM.1994.577079"},{"issue":"4","key":"7562_CR6","doi-asserted-by":"crossref","first-page":"46","DOI":"10.1109\/4236.939450","volume":"5","author":"E. Brewer","year":"July 2001","unstructured":"E. Brewer. Lessons from giant-scale services. IEEE Internet Computing, 5(4) (July 2001) 46\u201355.","journal-title":"IEEE Internet Computing"},{"key":"7562_CR7","unstructured":"A. Brown, G. Kar, and A. Keller. An active approach to characterizing dynamic dependencies for problem determination in a distributed environment. In: Proceedings of the 7th IFIP\/IEEE International Symposium on Integrated Network Management (IM 2001), Seattle, WA (May 2001)."},{"key":"7562_CR8","unstructured":"Business Internet Group. The black Friday report on Web application integrity. San Francisco, CA (2003)."},{"key":"7562_CR9","doi-asserted-by":"crossref","unstructured":"G. Candea, J. Cutler, A. Fox, R. Doshi, P. Garg, and R. Gowda. Reducing recovery time in a small recursively restartable system. In: Proc. International Conference on Dependable Systems and Networks, Washington, DC (June 2002).","DOI":"10.1109\/DSN.2002.1029006"},{"key":"7562_CR10","unstructured":"G. Candea, M. Delgado, M. Chen, and A. Fox. Automatic failure-path inference: A generic introspection technique for software systems. In: Proc. 3rd IEEE Workshop on Internet Applications, San Jose, CA (2003)."},{"key":"7562_CR11","unstructured":"G. Candea and A. Fox. Crash-only software. In: Proc. 9th Workshop on Hot Topics in Operating Systems, Lihue, Hawaii (2003)."},{"key":"7562_CR12","unstructured":"G. Candea, S. Kawamoto, Y. Fujiki, and A. Fox. A microrebootable system \u2013 design, implementation, and evaluation. In: Proc. 6th USENIX Symposium on Operating Systems Design and Implementation, San Francisco, CA (Dec. 2004)."},{"key":"7562_CR13","doi-asserted-by":"crossref","unstructured":"E. Cecchet, J. Marguerite, and W. Zwaenepoel. Performance and scalability of EJB applications, In: Proc. 17th Conference on Object-Oriented Programming, Systems, Languages, and Applications, Seattle, WA (2002).","DOI":"10.1145\/582419.582443"},{"key":"7562_CR14","unstructured":"M. Chen, A. Accardi, E. Kiciman, D. Patterson, A. Fox, and E. Brewer. Path-based macroanalysis for large, distributed systems. In: First Symposium on Networked Systems Design and Implementation (2004)."},{"key":"7562_CR15","doi-asserted-by":"crossref","unstructured":"M. Chen, A. Zheng, J. Lloyd, M. Jordan, and E. Brewer. Failure diagnosis using decision trees. In: International Conference on Autonomic Computing, New York, NY (May 2004).","DOI":"10.1109\/ICAC.2004.1301345"},{"key":"7562_CR16","doi-asserted-by":"crossref","unstructured":"R. Chillarege and N. S. Bowen. Understanding large system failures \u2013 a fault injection experiment\u201d. In: Proc. International Symposium on Fault Tolerant Computing (June 1989).","DOI":"10.1109\/FTCS.1989.105592"},{"key":"7562_CR17","unstructured":"J. Choi, M. Choi, and S. Lee. An alarm correlation and fault identification scheme based on OSI managed object classes. In: Proc. of IEEE Conference on Communications (1999)."},{"key":"7562_CR18","unstructured":"T. C. Chou. Personal communication. Oracle Corp. (2003)."},{"key":"7562_CR19","unstructured":"H. Cohen and K. Jacobs. Personal communication. Oracle Corporation (2002)."},{"key":"7562_CR20","unstructured":"K. Coleman, J. Norris, A. Fox, and G. Candea. OnCall: Defeating spikes with a free-marker server cluster. In: Proc. International Conference on Autonomic Computing, New York, NY (May 2004)."},{"key":"7562_CR21","doi-asserted-by":"crossref","unstructured":"A. Diaconescu, A. Mos, and J. Murphy. Automatic performance management in component based software systems. In: First International Conference on Autonomic Computing, New York, NY (May 2004).","DOI":"10.1109\/ICAC.2004.1301366"},{"key":"7562_CR22","unstructured":"S. Duvur. Personal communication. Sun Microsystems (2004)."},{"key":"7562_CR23","doi-asserted-by":"crossref","unstructured":"D. Engler, D. Y. Chen, S. Hallem, A. Chou, and B. Chelf. Bugs as deviant behavior: A general approach to inferring errors in systems code. In: Proc. 18th ACM Symposium on Operating Systems Principles, Lake Louise, Canada (Oct 2001).","DOI":"10.1145\/502034.502041"},{"key":"7562_CR24","unstructured":"J. Gray. Why do computers stop and what can be done about it? In: Proc. 5th Symposium on Reliability in Distributed Software and Database Systems, Los Angeles, CA (1986)."},{"key":"7562_CR25","unstructured":"S. D. Gribble, E. A. Brewer, J. M. Hellerstein, and D. Culler. Scalable, distributed data structures for Internet service construction. In: Proc. 4th USENIX Symposium on Operating Systems Design and Implementation, San Diego, CA (Oct. 2000)."},{"key":"7562_CR26","doi-asserted-by":"crossref","unstructured":"S. Hangal and M. Lam. Tracking down software bugs using automatic anomaly detection. In: Proceedings of the International Conference on Software Engineering (May 2002).","DOI":"10.1145\/581376.581377"},{"key":"7562_CR27","doi-asserted-by":"crossref","unstructured":"M.-C. Hsueh, T. K. Tsai, and R. K. Iyer. Fault injection techniques and tools. IEEE Computer, 30(4) (1997) 75\u201382.","DOI":"10.1109\/2.585157"},{"key":"7562_CR28","unstructured":"J. Boss. Homepage. http:\/\/www.jboss.org\/ (2002)."},{"key":"7562_CR29","doi-asserted-by":"crossref","unstructured":"J. O. Kephart and D. M. Chess. The Vision of Autonomic Computing. Computer Magazine (Jan 2003).","DOI":"10.1109\/MC.2003.1160055"},{"key":"7562_CR30","doi-asserted-by":"crossref","unstructured":"E. Kiciman and A. Fox. \u201cDetecting application-level failures in component-based Internet services,\u201d In: IEEE Transactions on Neural Networks: Special Issue on Adaptive Learning Systems in Communication Networks (2005) (invited paper).","DOI":"10.1109\/TNN.2005.853411"},{"key":"7562_CR31","doi-asserted-by":"crossref","unstructured":"E. Lassettre, D. Coleman, Y. Diao, S. Froelich, J. Hellerstein, L. Hsiung, T. Mummert, M. Raghavachari, G. Parker, L. Russell, M. Surendra, V. Tseng, N. Wadia, and P. Ye. Dynamic Surge Protection: An Approach to Handling Unexpected Workload Surges with Resource Actions that have Lead Times. In: Proc. of 1st Workshop on Algorithms and Architectures for Self-Managing Systems, San Diego, CA (June 2003).","DOI":"10.1007\/978-3-540-39671-0_8"},{"key":"7562_CR32","unstructured":"W. LeFebvre. CNN.com\u2014Facing a world crisis. In: 15th USENIX Systems Administration Conference (2001). Invited Talk."},{"key":"7562_CR33","unstructured":"H. Levine. Personal communication. EBates.com (2003)."},{"key":"7562_CR34","unstructured":"B. Ling, E. Kiciman, and A. Fox. Session state: Beyond soft state. In: First Symposium on Networked Systems Design and Implementation (2004)."},{"key":"7562_CR35","unstructured":"D. E. Lowell, S. Chandra, and P. M. Chen. Exploring failure transparency and the limits of generic recovery. In: Proc. 4th USENIX Symposium on Operating Systems Design and Implementation, San Diego, CA (2000)."},{"key":"7562_CR36","unstructured":"A. Messinger. Personal communication. BEA Systems (2004)."},{"key":"7562_CR37","doi-asserted-by":"crossref","unstructured":"R. Miller. Response time in man-computer conversational transactions. In: Proc. AFIPS Fall Joint Computer Conference, volume 33 (1968).","DOI":"10.1145\/1476589.1476628"},{"key":"7562_CR38","unstructured":"N. Mitchell. IBM Research. Personal Communication (2004)."},{"key":"7562_CR39","doi-asserted-by":"crossref","unstructured":"N. Mitchell and G. Sevitsky. LeakBot: An automated and lightweight tool for diagnosing memory leaks in large Java applications. In: Proc. 17th European Conference on Object-Oriented Programming, Darmstadt, Germany (July 2003).","DOI":"10.1007\/978-3-540-45070-2_16"},{"key":"7562_CR40","unstructured":"B. Murphy and N. Davies. System reliability and availability drivers of Tru64 UNIX. In: Proc. 29th International Symposium on Fault-Tolerant Computing, Madison, WI (1999). Tutorial."},{"key":"7562_CR41","doi-asserted-by":"crossref","first-page":"341","DOI":"10.1002\/qre.4680110505","volume":"11","author":"B. Murphy","year":"1995","unstructured":"B. Murphy and T. Gent. Measuring system and software reliability using an automated data collection process. Quality and Reliability Engineering International, 11 (1995) 341\u2013353.","journal-title":"Quality and Reliability Engineering International"},{"key":"7562_CR42","doi-asserted-by":"crossref","unstructured":"N. Nystrom, M. R. Clarkson, and A. C. Myers. Polyglot: An Extensible Compiler Framework for Java. In: Proc. of the 12th International Conference on Compiler Construction, Warsaw, Poland (Apr. 2003).","DOI":"10.1007\/3-540-36579-6_11"},{"key":"7562_CR43","unstructured":"D. Oppenheimer, A. Ganapathi, and D. Patterson. Why do Internet services fail, and what can be done about it? In: Proc. 4th USENIX Symposium on Internet Technologies and Systems, Seattle, WA (2003)."},{"key":"7562_CR44","unstructured":"A. Pal. Personal communication. Yahoo!, Inc. (2002)."},{"key":"7562_CR45","unstructured":"D. Reimer. IBM Research. Personal Communication (2004)."},{"key":"7562_CR46","doi-asserted-by":"crossref","unstructured":"I. Rouvellou and G. W. Hart. Automatic alarm correlation for fault identification. In: Proc. IEEE INFOCOM '95 (1995).","DOI":"10.1109\/INFCOM.1995.515921"},{"key":"7562_CR47","unstructured":"W. D. Smith. TPC-W: Benchmarking an E-Commerce solution. Transaction Processing Council (2002)."},{"key":"7562_CR48","doi-asserted-by":"crossref","unstructured":"L. Spainhower and T. A. Gregg. IBM S\/390 parallel enterprise server G5 fault tolerance: A historical perspective. IBM Journal of Research and Development, 43(5\/6) (1999).","DOI":"10.1147\/rd.435.0863"},{"key":"7562_CR49","doi-asserted-by":"crossref","unstructured":"M. Stoncbraker. The design of the Postgres storage system. In: Proc. 13th Conference on Very Large Databases, Brighton, England (1987).","DOI":"10.21236\/ADA187244"},{"key":"7562_CR50","doi-asserted-by":"crossref","unstructured":"M. Sullivan and R. Chillarege. Software defects and their impact on system availability \u2014 a study of field failures in operating systems. In: Proc. 21st International Symposium on Fault-Tolerant Computing, Montr\u00e9al, Canada (1991).","DOI":"10.1109\/FTCS.1991.146625"},{"key":"7562_CR51","unstructured":"Sun_Microsystems. Java Pet Store Demo. http:\/\/developer.java.sun.com\/developer\/releases\/petstore\/ (2002)."},{"key":"7562_CR52","unstructured":"TBD. A major Internet auction site. Terms of disclosure are being negotiated (May 2004)."},{"key":"7562_CR53","unstructured":"Y.-M. Wang, Y. Huang, K.-P. Vo, P.-Y. Chung, and C. M. R. Kintala. Checkpointing and its applications. In: Proc. 25th International Symposium on Fault-Tolerant Computing (1995)."},{"key":"7562_CR54","unstructured":"Y.-M. Wang, C. Verbowski, and D. R. Simon. Persistent-state checkpoint comparison for troubleshooting configuration failures. In: Proc. of the IEEE Conference on Dependable Systems and Networks (2003)."},{"key":"7562_CR55","doi-asserted-by":"crossref","unstructured":"A. Ward, P. Glynn, and K. Richardson. Internet service performance failure detection. In: Proc. Web Server Performance Workshop (1998).","DOI":"10.1145\/306225.306237"},{"key":"7562_CR56","doi-asserted-by":"crossref","unstructured":"K. Whisnant, R. Iyer, P. Hones, R. Some, and D. Rennels. Experimental evaluation of the REE SIFT environment for space-borne applications. In: Proc. International Conference on Dependable Systems and Networks, Washington, DC (2002).","DOI":"10.1109\/DSN.2002.1029004"},{"issue":"8","key":"7562_CR57","doi-asserted-by":"crossref","first-page":"37","DOI":"10.1109\/MC.2003.1220580","volume":"36","author":"A. P. Wood","year":"Aug. 2003","unstructured":"A. P. Wood. Software reliability from the customer view. IEEE Computer, 36(8) (Aug. 2003) 37\u201342.","journal-title":"IEEE Computer"},{"key":"7562_CR58","doi-asserted-by":"crossref","unstructured":"A. Yemeni and S. Kliger. High speed and robust event correlation. IEEE Communications Magazine, 34(5) (May 1996).","DOI":"10.1109\/35.492975"}],"container-title":["Cluster Computing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10586-006-7562-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10586-006-7562-4\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10586-006-7562-4","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,5,30]],"date-time":"2019-05-30T14:40:08Z","timestamp":1559227208000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10586-006-7562-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2006,4]]},"references-count":58,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2006,4]]}},"alternative-id":["7562"],"URL":"https:\/\/doi.org\/10.1007\/s10586-006-7562-4","relation":{},"ISSN":["1386-7857","1573-7543"],"issn-type":[{"value":"1386-7857","type":"print"},{"value":"1573-7543","type":"electronic"}],"subject":[],"published":{"date-parts":[[2006,4]]}}}