By Dave Eastman, VP of InCommand™, ServerFarm
We’re all aware of preventative medicine, which recognizes the signs of sickness and treats them before illness sets in. It’s a brilliant concept and works well in medicine, but in the data center world, we continue to cruise along with alert systems that only tell us when an incident actually happens. Alarms are set off and “fire-drills” ensue.
In the spirit of preventative medicine, “Data Center Health” and “Risk Assessment” engines constantly analyze and report on the health and risks of a data center, alerting the operations team of pending issues before you end up in panic mode.
So how does your data center measure up? Are you at risk? Do you have health and risk assessments engines providing you valuable data? Do you have dual powered systems plugged into a single circuit? What about single powered systems not connected to an ATS? Do you know what devices will be impacted when any link in a power chain is taken out of service? How about MEP preventative maintenance (PM)? Are your PMs being completed on schedule? And what about device data? Do you have IT assets in your data center without an owner, serial number, asset tag, or P.O. number?
To operate an efficient and reliable data center you need this information at your fingertips. Knowing statistics in real time is much more valuable than learning about them when the alarm goes off or during the annual inventory audit. In fact, if you have the tools to maintain and report on health and risks in real time, you won’t need the pain of annual audits. You will be able to simply print out your data center health report for the latest look at what’s going on in your facility. How cool would that be?