论文部分内容阅读
权威调查显示,目前每发生一次硬盘故障,平均下来就相当于损失一名员工一周的工作量。如果由于数据丢失重建而导致计算系统停机,停机持续10天就会使公司原有的竞争优势丧失殆尽,由此可见应对数据灾难、保障业务安全的重要性。因维护业务数据和发生灾难时进行抢救所付出的代价,也应归属于TCO的范畴。于是,那些硬盘制造商们便共同提出一个硬盘自监视、自分析和自报告的业界标准——S.M.A.R.T。 S.M.A.R.T标准是为监视硬盘自身的一些特定性能参数而设计的,如读写错误率等等。当这些参数显示可能有隐藏的问题时(大约60％的硬盘故障是可预见的),硬盘会发出报警信号,并被用户或网络管理员接收,以提醒他们对数据进行备份并及时维修。但是,如果系统或网络无人看管,S.M.A.R.T硬盘的报警信号如何才能得到响应?对于隐藏的数据灾难如何能未雨绸缪?随着IBM SMART Reaction的诞生,这些问题迎刃而解。
According to an authoritative survey, every time there is a hard disk failure, it is equivalent to losing an employee’s workload for one week. If the computing system is down due to data loss and reconstruction, downtime will continue to cause the company’s original competitive advantage to be lost for 10 days. This shows the importance of responding to data disasters and ensuring business security. The price paid for the maintenance of business data and the rescue of disasters should also be attributed to the TCO category. Thus, those hard disk manufacturers jointly proposed an industry standard for self-monitoring, self-analysis, and self-reporting of hard drives—S.M.A.R.T. The S.M.A.R.T standard is designed to monitor certain hard disk performance parameters, such as read/write error rates. When these parameters show that there may be hidden problems (approximately 60% of hard disk failures are foreseeable), the hard disk will send an alarm signal and be received by the user or network administrator to remind them to back up the data and repair it in time. However, if the system or network is left unattended, how can the alarm signal of S.M.A.R.T’s hard disk be able to get response? How can we plan for the hidden data disaster? With the birth of IBM SMART Reaction, these problems can be solved.