{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T19:48:38Z","timestamp":1782416918439,"version":"3.54.5"},"reference-count":34,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2010,12]]},"DOI":"10.1109\/hipc.2010.5713159","type":"proceedings-article","created":{"date-parts":[[2011,2,16]],"date-time":"2011-02-16T00:26:36Z","timestamp":1297815996000},"page":"1-10","source":"Crossref","is-referenced-by-count":38,"title":["Diagnosing the root-causes of failures from cluster log files"],"prefix":"10.1109","author":[{"given":"Edward","family":"Chuah","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shyh-hao","family":"Kuo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Paul","family":"Hiew","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"William-Chandra","family":"Tjhi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gary","family":"Lee","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"John","family":"Hammond","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Marek T.","family":"Michalewicz","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Terence","family":"Hung","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"James C.","family":"Browne","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref33","year":"0","journal-title":"Hadoop"},{"key":"ref32","article-title":"Recognition of error symptoms in large systems","author":"iyer","year":"1986","journal-title":"1986 ACM Fall Joint Computer Conference"},{"key":"ref31","author":"agresti","year":"2009","journal-title":"Statistics The Art and Science of Learning from Data"},{"key":"ref30","year":"2001","journal-title":"IEEE"},{"key":"ref34","year":"0","journal-title":"Lustre"},{"key":"ref10","article-title":"One graph is worth a thousand logs: Uncovering hidden structures in massive system event logs","author":"aharon","year":"2009","journal-title":"Proceedings of 20th European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/HIPC.2009.5433202"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/1557019.1557154"},{"key":"ref13","year":"0","journal-title":"Sisyphus Log Data Mining Toolkit"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/NOMS.2008.4575281"},{"key":"ref15","article-title":"Automated system monitoring and notification with swatch","author":"hansen","year":"1993","journal-title":"Proc Usenix Large Installation System Administration Conf"},{"key":"ref16","article-title":"Listening to your cluster with logs","author":"prewett","year":"2004","journal-title":"Proc 5th Int'l Conf Linux Clusters The HPC Revolution"},{"key":"ref17","article-title":"Real-time log file analysis using the simple event correlator (sec)","author":"rouillard","year":"2004","journal-title":"Proc 18th USENIX Conf System Administration"},{"key":"ref18","article-title":"A method for building a machine data web from machine data","author":"baum","year":"2006","journal-title":"US Patent No"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CCGRID.2008.107"},{"key":"ref28","article-title":"Troubleshooting chronic conditions in large ip networks","year":"2008","journal-title":"ACM International Conference On Emerging Networking Experiments And Technologies"},{"key":"ref4","article-title":"Filtering failure logs for a bluegene\/l prototype","author":"liang","year":"2005","journal-title":"Proc IEEE International Conference on Dependable Systems and Networks"},{"key":"ref27","article-title":"Picviz: finding a needle in a haystack","author":"tricaud","year":"2008","journal-title":"1st UNIX Workshop on the Analysis of System Logs"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/DSN.2006.5"},{"key":"ref6","doi-asserted-by":"crossref","DOI":"10.1016\/j.jpdc.2009.03.007","article-title":"An analysis of clustered failures on large supercomputing systems","volume":"69","author":"hacker","year":"2009","journal-title":"Journal of Parallel and Distributed Computing"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/1592568.1592596"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/DSN.2007.103"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CLUSTR.2004.1392628"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/11564096_62"},{"key":"ref2","article-title":"Discovering frequent episodes in event sequences","volume":"1","author":"mannila","year":"2004","journal-title":"Data Mining and Knowledge Discovery"},{"key":"ref9","article-title":"Analyzing system logs: A new view of what's important","author":"sabato","year":"2007","journal-title":"Proceedings 2nd Usenix Workshop on Tackling Computer Systems Problems with Machine Learning Techniques"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/FTCS.1992.243597"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2008.132"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/DSN.2006.18"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2009.52"},{"key":"ref24","article-title":"Mining console logs for large-scale system problem detection","author":"xu","year":"2008","journal-title":"Proceedings of 3rd Workshop on Tackling Computer Systems Problems with Machine Learning Techniques"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICPP.2008.17"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/DSN.2009.5270289"},{"key":"ref25","article-title":"Error log processing for accurate failure prediction","author":"salfner","year":"2008","journal-title":"1st UNIX Workshop on the Analysis of System Logs"}],"event":{"name":"2010 International Conference on High Performance Computing (HiPC)","location":"Goa, India","start":{"date-parts":[[2010,12,19]]},"end":{"date-parts":[[2010,12,22]]}},"container-title":["2010 International Conference on High Performance Computing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx5\/5708271\/5713158\/05713159.pdf?arnumber=5713159","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2017,6,19]],"date-time":"2017-06-19T19:48:39Z","timestamp":1497901719000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/5713159\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2010,12]]},"references-count":34,"URL":"https:\/\/doi.org\/10.1109\/hipc.2010.5713159","relation":{},"subject":[],"published":{"date-parts":[[2010,12]]}}}