The Ponemon-Sullivan Privacy Report includes original columns and a roundup of worldwide privacy news. It’s the best way to keep up with Ponemon Institute Research and Bob Sullivan’s opinions. Keep informed, sign up here.
I hear the collective sound of our friends, colleagues, and other interested parties scratching their heads at the release of the most recent piece of Ponemon Institute research, National Survey on Data Center Outages. You read that right, data center outages.
Well, it makes perfect sense to us because, while we are best known for our research in areas of information security and data privacy, we also do a lot of work in the realm of information management, and what could be more basic to good information management than making sure your data center remains operational? When the center goes down, you can’t manage much data (or make much money), can you?
Sponsored by our friends at Emerson Network Power, we were asked to look into how frequently data centers experience unplanned outages and, when they occur, what are the root causes? Knowing these two things helps to plan for contingencies and avert outages in the first place. But even beyond that, we wanted to learn a little more about the problem and give data center managers more information in support of their efforts.
So, we talked to 453 senior professionals involved in data center management and, after asking them a lot of questions we learned (among other things) that in the past 24 months:
·95 percent of data centers experienced an unplanned outage, and the average number of outages during that period was 2.48, with an average duration of 107 minutes;
·Row- and rack-based outages are more common than complete outages, occurring an average of 6.8 times with a 152 minute average duration during the two-year period for row outages and 11.2 times with a 153 minute average duration for rack outages;
·42 percent believe they do not receive full senior management support of their efforts, resulting in inadequate funding, design, and best operational practices; and,
·The most common known root causes of data center outages were UPS failure (65 percent), UPS capacity exceeded (53 percent), accidental emergency power off (EPO) or other human error (51 percent), and UPS equipment failure (49 percent).
The findings of our research suggest unplanned data center outages present a difficult and costly challenge for organizations. In general, failed equipment, data center mishaps and insufficient resources exacerbate the frequency and duration of unplanned outages. Therefore, the challenge for data center management is to effectively communicate to senior leadership the urgent need to implement power, cooling and monitoring systems that increase availability and ensure the performance of mission critical applications.
Let us know what you think of these results and your experience with this issue.