One Size Does Not Fit All (Datacenters Included)

By Michael McNerney, Supermicro

Today's IT departments must respond to a wide range of demands made by many groups within an enterprise. New technologies are being developed and deployed while entire companies are moving to completely digital infrastructure. As IoT technologies and the need for computing near the edge increase in importance, data centers need to be modernized – specifically to process data transactions at orders of magnitude more than they were initially designed for.

A wide range of servers and software products, combined with easy-to-use solutions, will enable organizations of all sizes to benefit and meet their business goals. The process of picking a system that meets your needs and environment can be a tricky one, so here is a quick breakdown to help you sort out your options:

Edge And IoT

The infrastructure needed at the Edge requires quite different components than those in a data center. Such servers that collect and filter sensor data, and those that reside as part of the telco infrastructures, are very different from the types of systems installed in air-conditioned data centers.

Systems that live at the Edge need to withstand a range of harsh outdoor environments, perform after earthquakes, and even potentially withstand vandalism acts. In most cases, the systems must be self-cooled (no fans) and may have to run with low amounts of power. Choosing the right type of equipment for these physical environments should be of high importance. NEBS Level 3 certification is an excellent way to identify equipment that can handle these extreme edge environments. Such servers have passed strict specifications for thermal testing, airflow patterns, acoustic limits, failover, and partial operational requirements, and much more.

Distributed Data Centers

Not all data centers consume megawatts of power and consist of thousands of servers and storage systems. Intermediate type systems may need to operate in a controlled environment without a large-scale data center resiliency. For this, airflow might be limited, but the external conditions won't be as harsh compared to the Edge. Additionally, the density of computing and storage systems may be the dominant capability needed since physical space may be limited. Be sure to choose from your suppliers' hardware options based on the specific data center needs. Since the requirements are typically known in advance, the servers should be selected according to more detailed specifications than those of a full hyperscale data center.

Full-Scale Data Center

Massive data centers can handle a wide range of servers, storage, and networking systems. Various form factors can be used depending on workloads and the associated needs for storage and network capabilities:

• High-density computing systems such as blades enable workloads like HPC and data analytics.
• Systems that can accommodate multiple GPU systems are excellent choices for Artificial Intelligence and Machine Learning.
• Shared cooling and power supplies reduce the environmental impact by using less electricity but are less expandable.
• Specific applications that are used for real-time analytics need massive amounts of memory.
• Other applications benefit from having 4 CPUs housed in the same enclosure, while traditional enterprise workloads use low-cost single socket systems.

As the needs of full-scale data centers continue to emerge and evolve, the suppliers that can deliver many form factors of servers and storage with various capabilities and capacities to organizations implementing large-scale data centers will emerge as a trusted supplier.

The next steps in this process will be to evaluate your infrastructure and determine the storage and software needed to complete your data center.

Storage Choices

Traditional hard disk drives (HDD) are being replaced by Solid State Drives (SSD) due to their ability to access data significantly faster. Additionally, SSDs cost less to operate because they utilize less power than HDDs. Storage requirements vary considerably for each customer and being able to supply a wide range of storage systems, both in performance and capacity, is essential for any infrastructure installation. Systems that contain both drives tier the storage for enterprises, where "hot" data may be stored on the SSDs, and "warm" or "cold" data on the higher capacity HDDs.

New technologies, such as Persistent Memory, offer a fresh look at combining technologies that contain data when power is lost (persistence) and act to expand the memory that CPUs need to access in a timely manner. Businesses that need extreme redundancies and fail-safes for security, compliance, or customer service reasons should consider storage utilizing persistent memory. Look at your storage needs and how applications may have differing algorithms for check-pointing and restarting.

Software Ecosystems

Whether it's single servers at the Edge or massive cloud data centers, software plays a significant role in implementing server and storage infrastructure. Besides the expected software supplied by system vendors that monitor and control servers at the rack level, solutions that combine the right sized hardware with the underlying software solution are of critical importance.

Based on industry-standard CPUs, operating systems, and defined interfaces, open systems allow for a significant catalog of software to be pre-installed or loaded onto these systems. Many end customers require the testing and installing of a specific software stack, which simplifies the bring-up of servers and storage systems, resulting in a faster time to production. Consider the entire solution that will meet your needs, where your time to production will be faster than having to piece together parts on your own.

Server and storage systems that respond quickly and are right sized for various IT requirements are the wave of the future. The CPU performance, storage capacity, and power demands will continue to be critical elements and can make or break an efficient and optimized solution. Similarly, workloads vary from the Edge to hyper-scale data centers, and the choice of hardware needs to match the customer requirements. While a comprehensive product range from an OEM supplier may seem daunting at first, defining end user requirements and determining the right solution will benefit everyone in the end.

About The Author

Michael McNerney is VP of Marketing and Network Security for Supermicro.