Where Does Your Data Center Fall With Dependability?

The terms "dependability" and "reliability" are heard throughout the data center industry, and they are often used interchangeably. Dependability is defined as trustworthy and reliable, and reliability is defined as being trustworthy and consistent. The dictionary refers to dependable as a synonym of reliable and reliable as a synonym for dependable.

Even though these terms appear to be linked; reliability is an attribute of dependability.

Whichever term you choose may turn into a Data Center availability conversation and that will be defined as the amount of time your data center is available and can be expressed in 9's.

These are the conditions in which we need and expect our data centers to perform and also keep in mind that availability needs both dependability and reliability.

Review the table below and see where your Data Center falls in the maturity curve of dependability.

1	Undependable	Inefficient design Outages/Downtime Infrastructure silos Hot spots and High Temperatures
2	Improved	Independent power and cooling No monitoring or reporting Lack of lifecycle management No redundancy
3	Enhanced	Dedicated power & cooling systems Single UPS and generator Cabling and pathways lacking Lack of capacity planning
4	Dependable	Dedicated utility power UPS and Battery Backup Redundant cooling systems Back-up generator
5	Hardened	Redundant power Redundant cooling Scalable/Flexible Energy efficient

After reviewing the table above where are with your dependability on the maturity curve? Are you looking for five 9's of availability? The concept of "five 9's" availability is more of a marketing figure and doesn't always stand up in practicality. While 99.999 is impressive that may still leave you with 5.3 minutes a year of downtime.

Unfortunately, even with a substantial investment in your IT hardware and software platforms it is likely not enough to maintain five 9's unless it can be matched with the facilities infrastructure that can support the same business goals.

Below are the actual breakdowns of the availability per the Data Center tiers availability above.

Availability %	Downtime per year	Downtime per quarter	Downtime per month	Downtime per week	Downtime per day (24 hours)
90% ("one nine")	36.53 days	9.13 days	73.05 hours	16.80 hours	2.40 hours
99% ("two nines")	3.65 days	21.9 hours	7.31 hours	1.68 hours	14.40 minutes
99.9% ("three nines")	8.77 hours	2.19 hours	43.83 minutes	10.08 minutes	1.44 minutes
99.99% ("four nines")	52.60 minutes	13.15 minutes	4.38 minutes	1.01 minutes	8.64 seconds
99.999% ("five nines")	5.26 minutes	1.31 minutes	26.30 seconds	6.05 seconds	864.00 milliseconds

The goal of most data centers is sustained continuous operation of the IT equipment. Is this within your grasp?

Let's keep some commonsense principles in mind that will help improve the dependability and reliability in your data center.

Simplicity is more reliable than complexity.
Computers are more reliable than people.
Equipment performance degrades over time and use.
Higher quality equipment has better availability and reliability than poor quality equipment.
The accuracy of un-calibrated sensors and transducers decreases over time.
Starting and stopping equipment imparts more stress than when equipment is in stable operation.

In these cases, the goal is to deliver 100 percent computer room availability. To achieve 100 percent availability, you will need dependability.

Two leading factors that affect the dependability and reliability of a data center: physical infrastructure and operating staff.

Let us help you find the weak links in your reliability chain and bolster your critical facilities infrastructure. Schedule a workshop with our Facilities Infrastructure Team to help evaluate and roadmap your data center to dependability.

And don't forget to meet with our Data Center practice to gain the same dependability with your IT hardware and software so that in the end your data center can truly be dependable.