For any data center, resilience is a lot more than just a “talent”. It is a well-tested and measured ability to defy issues and avoid disruptions. Here is what you should have in mind.
For humans, resilience is all about having the right life skills to recover as soon as possible from an unexpected disruption. For systems, it is exactly the same. It is the ability to withstand changes in its environment and still function. For data centers, it is the ability to recover quickly and continue operating even after the most impactful disruption.
How is resilience achieved and is it actually measured?
Resilience for the data center is strongly associated with the use of redundant systems and components. Once an element fails, the redundant element takes over. It is important that this process happens seamlessly, without the users of the system noticing and experiencing any issues. Of course, this may not be always possible.
As far as resiliency criteria, managers should be aware that things can be somewhat different, per data center. However, a more general framework of resilience criteria in terms of operations may be as follows:
- Availability or non-availability: This factor is also determined per case, since some organizations may define a system as “up” when it is available to 97% of the users, and some consider it as down.
- Performance of network service: This may include factors such as available bandwidth. Again, it is also a matter of percentage.
- Time to repair: This counts as the time elapsed until the service is restored.
- Network downtime. As it stands, time down for the service.
- Time to response: This can be the time slot between an interruption and the time needed by the redundant system to handle services.
- Number and characteristics of incidents which occurred, on a daily, weekly, monthly, and yearly basis.
While the above-named criteria are mentioned here as an initial roadmap, data center managers should plan metrics after considering all the individual factors which describe their own facility.
Our team at Lamda Hellix are resiliency “experts” and can help your business set up the right metrics and criteria. Contact us via this form.