When it comes to protecting your IT infrastructure, settling for less than you demand or require is not an option. Reliable up-time depends on three main factors, power continuity, cooling effectiveness and network connectivity. A weakness or lack of redundancy in any of these areas can have costly effects on your business. According to the most recent Ponemon Institute report, an unplanned data center outage costs an average of $7,900 per minute – up 41 percent in three years. These are staggering statistics, so why settle for a blanket statement regarding redundancy from a data center provider that you’re considering? Examine these four key elements when consulting with a data center provider.
Power is the heart of any data center or IT facility. It is critical to ask for full A/B power feeds. If redundant sources of power share a path at any point from the curb to the equipment, then it is at risk of failure. With full A/B power, there are two completely independent power paths. Both paths have at least one of the following, utility power source, main distribution panel, back-up generator, automatic transfer switch, uninterruptible power supply and maintenance bypass panel, power distribution unit, rack level PDU, and the server’s internal power supply. Each path is capable of supporting 100% of the entire peak load, resulting in full redundancy and no single point of failure that can interrupt the operation of the data center or your equipment.
Whether you just purchased all new equipment for a colocation solution or you’re considering a dedicated or cloud solution, cooling is critical to the functionality and performance of the equipment. If cooling fails, you may not know it until your server overheats. Look for a provider that maintains at least two different types of cooling infrastructure, such as rooftop units plus external condensers and CRAC units.
Commonly overlooked, inquiring about the quality of the gear used to connect your servers to the Internet is also a critical element of infrastructure redundancy. Common life span of switches and routers is typically 5 years and ensuring that the provider is routinely maintaining and replacing aging equipment will result in greater redundancy. Ensure that there is also layer 2 and layer 3 redundancies in place so that there is no single point of failure.
Look for a provider that has peering arrangements with multiple providers to ensure a robust connection from the facility to the worldwide Internet. Multiple peering connections provide you the opportunity to have an optimized route for better performance of communication to specific vendors or carriers.
There are certain demands and requirements that are critical to each and every business’ IT infrastructure. Having a clear and concise vision of the absolute requirements that you need prior to speaking with any providers will allow you dictate which providers will make your short list. All providers should be willing and able to provide you the information that you need to determine if they can meet your critical demands and requirements. There are certain areas of your IT infrastructure road map that can be considered negotiable or open to different avenues but infrastructure redundancy should not be one of them.