What is a data center?

Data centers started out as privately owned, tightly controlled on-premises facilities housing traditional IT infrastructure for the exclusive use of one company. Recently, they've evolved into remote facilities or networks of facilities owned by cloud service providers (CSPs). These CSP data centers house virtualized IT infrastructure for the shared use of multiple companies and customers.

Data centers date back to the 1940s. The US military's Electrical Numerical Integrator and Computer (ENIAC), completed in 1945 at the University of Pennsylvania, is an early example of a data center that required dedicated space to house its massive machines.

Over the years, computers became more size-efficient, requiring less physical space. In the 1990s, microcomputers came on the scene, drastically reducing the amount of space needed for IT operations. These microcomputers that began filling old mainframe computer rooms became known as “servers,” and the rooms became known as “data centers.”

The advent of cloud computing in the early 2000s significantly disrupted the traditional data center landscape. Cloud services allow organizations to access computing resources on-demand, over the internet, with pay-per-use pricing—enabling the flexibility to scale up or down as needed.

In 2006, Google launched the first hyperscale data center in The Dalles, Oregon. This hyperscale facility currently occupies 1.3 million square feet of space and employs a staff of approximately 200 data center operators.¹

A study from McKinsey & Company projects the industry to grow at 10% a year through 2030, with global spending on the construction of new facilities reaching USD49 billion.²

There are different types of data center facilities, and a single company might use more than one type, depending on workloads and business needs.

This data center model hosts all IT infrastructure and data on-premises. Many companies choose on-premises data centers. They have more control over information security and can more easily comply with regulations such as the European Union General Data Protection Regulation (GDPR) or the US Health Insurance Portability and Accountability Act (HIPAA). The company is responsible for all deployment, monitoring and management tasks in an enterprise data center.

Cloud data centers (also called cloud computing data centers) house IT infrastructure resources for shared use by multiple customers—from scores to millions—through an internet connection.

Many of the largest cloud data centers—called hyperscale data centers—are run by major cloud service providers (CSPs), such as Amazon Web Services (AWS), Google Cloud Platform, IBM Cloud and Microsoft Azure. These companies have major data centers in every region of the world. For example, IBM operates over 60 IBM Cloud Data Centers in various locations around the world.

Hyperscale data centers are larger than traditional data centers and can cover millions of square feet. They typically contain at least 5,000 servers and miles of connection equipment, and they can sometimes be as large as 60,000 square feet.

Cloud service providers typically maintain smaller, edge data centers (EDCs) located closer to cloud customers (and cloud customers’ customers). Edge data centers form the foundation for edge computing, a distributed computing framework that brings applications closer to end users. Edge data centers are ideal for real-time, data-intensive workloads like big data analytics, artificial intelligence (AI), machine learning (ML) and content delivery. They help minimize latency, improving overall application performance and customer experience.

Managed data centers and colocation facilities are options for organizations that lack the space, staff or expertise to manage their IT infrastructure on-premises. These options are ideal for those who prefer not to host their infrastructure by using the shared resources of a public cloud data center.

In a managed data center, the client company leases dedicated servers, storage and networking hardware from the provider, and the provider handles the client company's administration, monitoring and management.

In a colocation facility, the client company owns all the infrastructure and leases a dedicated space to host it within the facility. In the traditional colocation model, the client company has sole access to the hardware and full responsibility for managing it. This model is ideal for privacy and security but often impractical, particularly during outages or emergencies. Today, most colocation providers offer management and monitoring services to clients who want them.

Companies often choose managed data centers and colocation facilities to house remote data backup and disaster recovery (DR) technology for small and midsized businesses (SMBs).

Most modern data centers, including in-house on-premises ones, have evolved from the traditional IT architecture. Instead of running each application or workload on dedicated hardware, they now use a cloud architecture where physical resources such as CPUs, storage and networking are virtualized. Virtualization enables these resources to be abstracted from their physical limits and pooled into capacity that can be allocated across multiple applications and workloads in whatever quantities they require.

Virtualization also enables software-defined infrastructure (SDI)—infrastructure that can be provisioned, configured, run, maintained and "spun down" programmatically without human intervention.

This virtualization has led to new data center architectures such as software-defined data centers (SDDC), a server management concept that virtualizes infrastructure elements such as networking, storage and compute, delivering them as a service. This capability allows organizations to optimize infrastructure for each application and workload without making physical changes, which can help improve performance and control costs. As-a-service data center models are poised to become more prevalent, with IDC forecasting that 65% of tech buyers will prioritize these models by 2026.³

The combination of cloud architecture and SDI offers many advantages to data centers and their users, such as:

• Optimal utilization of compute, storage and networking resources
• Rapid deployment of applications and services
• Scalability
• Variety of services and data center solutions
• Cloud-native development

Servers are powerful computers that deliver applications, services and data to end-user devices. Data center servers come in several form factors:

• Rack-mount servers are wide, flat, stand-alone servers the size of a small pizza box. They are stacked on top of each other in a rack to save space (versus a tower or desktop server). Each rack-mount server has its own power supply, cooling fans, network switches and ports, along with the usual processor, memory and storage.
• Blade servers are designed to save even more space. Each blade contains processors, network controllers, memory and sometimes storage. They're made to fit into a chassis that holds multiple blades and includes the power supply, network management and other resources for all the blades in the chassis.
• Mainframes are high-performance computers with multiple processors that can do the work of an entire room of rack-mount or blade servers. The first virtualizable computers, mainframes can process billions of calculations and transactions in real time.

The choice of server form factor depends on many factors, including available space in the data center, the workloads running on the servers, the available power and cost.

Most servers include some local storage capability—direct-attached storage (DAS)—to enable the most frequently used data (hot data) to remain close to the CPU.

Two other data center storage configurations include network attached storage (NAS) and a storage area network (SAN).

NAS provides data storage and data access to multiple servers over a standard Ethernet connection. The NAS device is usually a dedicated server with various storage media such as hard disk drives (HDDs) or solid-state drives (SSDs)

Like NAS, a SAN enables shared storage, but it uses a separate network for the data and involves a more complex mix of multiple storage servers, application servers and storage management software.

A single data center might use all three storage configurations—DAS, NAS and SAN—and file storage, block storage and object storage types.

Data center network topology refers to the physical layout and interconnection of a data center's network devices, including infrastructure, connections between servers and components, and data flow.

The data center network consists of various network equipment, such as switches, routers and fiber optics that network traffic across the servers (called east/west traffic) and to or from the servers to the clients (called north/south traffic).

As noted above, a data center typically has virtualized network services. This capability enables the creation of software-defined overlay networks, built on top of the network's physical infrastructure, to accommodate specific security controls or service level agreements (SLAs).

Data centers need high-bandwidth connections to allow for communications between servers and storage systems and between inbound and outbound network traffic. For hyperscale data centers, bandwidth requirements can range from several gigabits per second (Gbps) to terabits per second (Tbps).

Data centers need to be always-on at every level. Most servers feature dual power supplies. Battery-powered uninterruptible power supplies (UPS) protect against power surges and brief power outages. Powerful generators can take effect if a more severe power outage occurs.

Cable management is an important data center design concern, as various cables connect thousands of servers. If cable wires are too near to each other, they can cause cross-talk, which can negatively impact data transfer rates and signal transmission. Also, if too many cables are packed together, they can generate excessive heat. Data center construction and expansion must consider building codes and industry standards to ensure efficient and safe cabling.

Data center downtime is costly to data center providers and to their customers. Data center operators and architects go to great lengths to increase the resiliency of their systems. These measures include redundant arrays of independent disks (RAIDs) to protect against data loss or corruption in the case of storage media failure. Other measures include backup data center cooling infrastructure that keeps servers running at optimal temperatures, even if the primary cooling system fails.

Many large data center providers have data centers located in geographically distinct regions. If a natural disaster or political disruption occurs in one region, operations can fail over to a different region for uninterrupted services.

The Uptime Institute uses a four-tier system to rate the redundancy and resiliency of data centers.⁴

• Tier I: Provides basic redundancy capacity components, such as uninterruptible power supply (UPS) and 24x7 cooling, to support IT operations for an office setting or beyond.
• Tier II: Adds extra redundant power and cooling subsystems—such as generators and energy storage devices—to improve safety against disruptions.
• Tier III: Adds redundant components as a key differentiator from other data centers. Tier III facilities require no shutdowns when equipment needs maintenance or replacement.
  
• Tier IV: Adds fault tolerance by implementing several independent, physically isolated redundant capacity components, so that when a piece of equipment fails, IT operations have no impact.
  

Data centers are designed and equipped to control interrelated environmental factors that can damage or destroy hardware and lead to expensive or catastrophic downtime.

• Temperature: Most data centers employ a combination of air cooling and liquid cooling to keep servers and other hardware operating within the proper temperature ranges. Air cooling is air conditioning—specifically, computer room air conditioning (CRAC). CRAC targets an entire server room, or at specific rows or racks of servers. Liquid cooling technologies pump liquid directly to processors or sometimes immerse servers in coolant. Data center providers are increasingly turning to liquid cooling for greater energy efficiency and sustainability as it requires less electricity and water than air cooling.
• Humidity: High humidity can cause equipment to rust; low humidity can increase the risk of static electricity surges. Humidity control equipment includes CRAC systems, proper ventilation and humidity sensors.
• Static electricity: As little as 25 volts of static discharge can damage equipment or corrupt data. Data center facilities contain equipment to monitor static electricity and discharge it safely.
• Fire: For obvious reasons, data centers must include fire-prevention equipment that is tested regularly.

Data centers contain sensitive information and business-critical applications, which call for a comprehensive security strategy that spans physical data centers and multicloud environments.

Data center security measures include the physical security of hardware and storage devices, along with administrative and access controls. It also covers the security of software applications and organizational policies and procedures. Hyperscale data centers, for instance, require specialized firewalls and other protocols for enhanced cybersecurity.

Data center management encompasses the tasks and tools organizations need to keep their private data centers operational, secure and compliant. The person responsible for carrying out these tasks is known as a data center manager.

A data center manager performs general maintenance, such as software and hardware upgrades, general cleaning or deciding the physical arrangement of servers. They also take proactive or reactive measures against any threat or event that harms the data center.

Data center managers in the enterprise can use data center infrastructure management (DCIM) solutions to simplify overall management and achieve IT performance optimization. These software solutions provide a centralized platform for data center managers to monitor, measure, manage and control all data center elements in real time. This includes everything from on-premises IT components to facilities such as heating, cooling and lighting.

Sustainability in business is a crucial part of environmental, social and governance (ESG) practices. Gartner notes that 87% of business leaders plan to invest more in sustainability in the coming years.⁵ To that end, reducing the environmental impact of data centers aligns with broader business goals in the global effort to combat climate change.

Today’s proliferation of AI-driven workloads is driving data center growth. Goldman Sachs Research estimates that data center power demand will grow 160% by 2030.⁵

The need to reduce power usage is driving enterprise organizations to push for renewable energy solutions to power their hyperscale data centers. This occurrence has led to the growth in green data centers, or sustainable data centers, facilities that house IT infrastructure and use energy-efficient technologies to optimize energy use and minimize environmental impact.

By embracing technologies such as virtualization, energy-efficient hardware and renewable energy sources in data centers, organizations can optimize energy use, reduce waste and save money. Certifications play a pivotal role in recognizing and promoting sustainable practices within data centers. Notable certifications and associations include Leadership in Energy and Environmental Design (LEED), Energy Star and the Green Grid.