Advanced pattern recognition for detection of complex software aging phenomena in online transaction processing servers

Proceedings. International Conference on Dependable Systems and Networks Pub Date : 2002-06-23 DOI:10.1109/DSN.2002.1028933

Karen J. Cassidy, K. Gross, A. Malekpour

{"title":"Advanced pattern recognition for detection of complex software aging phenomena in online transaction processing servers","authors":"Karen J. Cassidy, K. Gross, A. Malekpour","doi":"10.1109/DSN.2002.1028933","DOIUrl":null,"url":null,"abstract":"Software aging phenomena have been recently studied; one particularly complex type is shared memory pool latch contention in large OLTP servers. Latch contention onset leads to severe performance degradation until a manual rejuvenation of the DBMS shared memory pool is triggered. Conventional approaches to automated rejuvenation have failed for latch contention because no single resource metric has been identified that can be monitored to alert the onset of this complex mechanism. The current investigation explores the feasibility of applying an advanced pattern recognition method that is embodied in a commercially available equipment condition monitoring system (SmartSignal eCM/spl trade/) for proactive annunciation of software-aging faults. One hundred data signals are monitored from a large OLTP server, collected at 20-60 sec. intervals over a 5-month period. Results show 13 variables consistently deviate from normal operation prior to a latch event, providing up to 2 hours early warning.","PeriodicalId":93807,"journal":{"name":"Proceedings. International Conference on Dependable Systems and Networks","volume":"22 1","pages":"478-482"},"PeriodicalIF":0.0000,"publicationDate":"2002-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"123","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Proceedings. International Conference on Dependable Systems and Networks","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/DSN.2002.1028933","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 123

Abstract

Software aging phenomena have been recently studied; one particularly complex type is shared memory pool latch contention in large OLTP servers. Latch contention onset leads to severe performance degradation until a manual rejuvenation of the DBMS shared memory pool is triggered. Conventional approaches to automated rejuvenation have failed for latch contention because no single resource metric has been identified that can be monitored to alert the onset of this complex mechanism. The current investigation explores the feasibility of applying an advanced pattern recognition method that is embodied in a commercially available equipment condition monitoring system (SmartSignal eCM/spl trade/) for proactive annunciation of software-aging faults. One hundred data signals are monitored from a large OLTP server, collected at 20-60 sec. intervals over a 5-month period. Results show 13 variables consistently deviate from normal operation prior to a latch event, providing up to 2 hours early warning.

查看原文

微信好友朋友圈 QQ好友复制链接

本刊更多论文

基于高级模式识别的在线事务处理服务器复杂软件老化现象检测

软件老化现象最近得到了研究;一种特别复杂的类型是大型OLTP服务器中的共享内存池闩锁争用。闩锁争用会导致严重的性能下降，直到触发手动恢复DBMS共享内存池。传统的自动返老还老方法在闩锁竞争中失败了，因为没有一个单一的资源指标被确定，可以监测来警告这种复杂机制的开始。目前的研究探索了应用先进模式识别方法的可行性，该方法体现在商用设备状态监测系统(SmartSignal eCM/spl trade/)中，用于主动通知软件老化故障。从一个大型OLTP服务器监视100个数据信号，在5个月的周期内每隔20-60秒收集一次。结果显示，在锁存事件之前，13个变量始终偏离正常操作，提供长达2小时的预警。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文去求助

来源期刊

Proceedings. International Conference on Dependable Systems and Networks

自引率

0.00%

发文量

期刊最新文献

Practical and Efficient in-Enclave Verification of Privacy Compliance. Evaluating the security threat of firewall data corruption caused by instruction transient errors Application performance assurance using end-to-end user level monitoring Small byzantine quorum systems CLAIRE: an event-driven simulation tool for test and validation of software programs