Change is the only inevitable thing and considering everything that has happened around us in the past year and a half, it is high time to kick status-quo thinking to the curb when it comes to Server Acquisition and Maintenance. We need to upgrade our conventional wisdom regarding what and when to buy because upgrading core IT equipment often means overpaying for new equipment while underutilizing what you already have in place. Therefore, it is important to know how to dispel the many myths and misconceptions about upping your IT IQ and preparing for digital transformation while lowering IT infrastructure acquisition costs.
IT leaders face constant pressure to prove the cost-effectiveness of on-premises infrastructures owing to the promise and potential of cloud-hosted services. It all begins with making the right equipment choices with the best price/performance for the task at hand. Most often, changing out components changes the IT acquisition game in your favour.
The latest x86 processors up your performance levels substantially, but do you really need all that horsepower to fuel core business applications? Because most enterprises still have relatively low overall server and CPU utilization across their infrastructures. One study of large enterprises (with more than 100 physical servers) showed an average x86 server CPU utilization only between 8% and 20%.
So, you may be paying for performance you don’t really need depending on the task. Therefore, you need to carefully assess what type of processor, core, and speed are needed to keep the applications running in optimal order. Processors could embody 30% or more of the total cost of server hardware.
Hence, avoiding the highest-performing processor model in favour of a lower-premium choice can deliver hardware savings of about one-third while only impacting the peak performance by just 10%. This is the kind of informed trade-off that most end-users can accept.
The bottom line of this insight is high-end processors are pricey, and so, there’s no valid reason to pay for capacity you don’t use or really need.
When evaluating memory capacity in servers a different approach is often recommended. It is a given rule that more is better when it comes to memory. The initial cost could be on the higher side, but it avoids the cost, time and effort to take down the network later to max out memory.
That being said, prices of dual in-line memory modules (DIMMs) can go topsy-turvy, and purchasing the right model can be exhausting as the menu of models is seemingly endless. Beware that each DIMM may be priced a little differently, and so doing your homework is of utmost importance.
It is tricky to choose the perfect model as per our requirement. For example, the price per GB may vary wildly for the same memory capacity. So, the time you spend in doing all the homework like calculating everything upfront could prove eye-opening and put dollars back in your budget. For example, analysts reported finding 30% savings when cost-comparison shopping for 8x 16GB DIMMS vs. 16x 8GB DIMMs – with no ill impact on net memory capacity or performance last year.
Such volatility could mean that the best deals can change quickly and do so month by month. Conventionally, server memory prices drop over time, but sudden and unexpected shortages can cause a rapid price hike. So, you need to consider a best practices approach that includes calculating DIMMs’ current lowest cost option for each purchase. And, never blindly place an order based on previous procurement.
Maybe, the best option for saving money on memory is considering third-party components. Honestly, even the leading manufacturers do not make their own memory. The vast majority of these storage are rebranded and sold at astronomical markups. So, if you could find a knowledgeable secondary market provider who can help ensure all third-party components are, in fact, high quality, you could save as much as 40% to 60% off manufacturers’ list prices.
The perks of having a reputable secondary market providers is that they too match any manufacturer warranty, while leading sources deliver a lifetime warranty. This makes choosing a reputable secondary market provider as the most cost-effective way to add performance to your data centre.
Solid-state drives (SSDs) are becoming more affordable. Therefore, they are plentiful, which bodes well for server applications. But along with SSDs’ superior performance comes the potential purchasing pitfalls. So, you need to make a calculated choice among offerings in multiple sizes and various form factors, flash technologies, and interfaces.
SSD Pricing also can be volatile, so you have to revisit your procurement strategies at least monthly. Buyers could save at least 40% after reviewing purchasing criteria, which includes consideration for buying SSDs built from cheaper or more reliable flash technologies.
Your purchasing best practices should include qualifying all SSDs considered, with particular attention on those with faster interfaces and smaller form factors so that the you could ensure that the performance matches intended uses and applications. Never opt for high-end drives if applications don’t require them.