基于构件软件的抗衰策略分析  

Analysis for Policy of Component-based Software Rejuvenation

作　　者：王平涛[1] 许满武[1] 刘志军[1] 

机构地区：[1]南京大学计算机科学与技术系软件新技术国家重点实验室,南京210093

出　　处：《计算机科学》2009年第5期121-123,180,共4页Computer Science

基　　金：国家自然科学基金(No.60273035);国家高技术研究发展计划"863"(No.2001AA113161);江苏省自然科学基金(No.BK2002080)资助

摘　　要：软件在长期运行过程中由于资源消耗、数据损坏、数值错误累积而引起性能下降的现象被称为软件老化。在软件失效前选择合适时机通过预反应的技术来保持软件性能的方法称作软件抗衰。由于构件软件常常应用在结构复杂、规模庞大的网络环境中,软件老化现象就更为突出。提出了一种针对构件软件的抗衰策略,通过对构件软件进行可靠性分析,构造了一种结合失效性和泊松失败分布的马尔可夫模型,并根据模型进行软件抗衰来保持构件软件的性能。Software aging is the process by which the state of long-running programs degrades over time through exhaustion of system resources, data corruption, or numerical error accumulation. Software rejuvenation is a proactive technique intended to reduce the probability of future unplanned outages due to software aging. The basic idea is to pause or halt the running software, refresh its internal state, and resume or restart it. The aging phenomenon of the component-based software applied to complex large-scale networks is more evident. The paper presented a policy on the component-based software rejuvenation, and designed the model incorporating deterioration and poisson failures by reliability analysis, and rejuvenated the software to maintain performance of system based on the model.

关 键 词：软件老化 软件抗衰 可用性 可靠性 马尔科夫模型 泊松分布 

分 类 号：TP393[自动化与计算机技术—计算机应用技术]