Developing strategies at the data center level

Data centers are the infrastructure for modern businesses to run their businesses. They power the IT systems that run complex businesses, including servers, backup systems, network equipment, and other technical components. There are currently more than 8.5 million data centers distributed around the world, and there are currently more than 3 million data centers in the United States.

[[264728]]

Keeping IT systems up and running is critical. However, not all IT infrastructure and business needs are the same. That’s why data center tiers exist. This term refers to the different types of systems, components, and infrastructure configured in a data center divided into groups or tiers.

Each level is designed to meet specific IT and equipment needs. For example, the top level of a data center involves the basic needs of the infrastructure, while the fourth level consists of the most complex components. Let's take a look at each level of a data center.

Data Center Tier Standards and Requirements

Understanding how data center tiers work is essential to designing an effective IT strategy. The tier classification system was created by the Uptime Institute in the mid-1990s. Since then, the framework has evolved from shared industry terminology to a global standard that includes third-party verification of critical data center infrastructure.

The data center tier system is progressive, meaning each tier builds on the tier below it and incorporates requirements from lower tiers.

Here is the role each tier plays in a data center:

***Tier: Basic Capacity

A Tier 4 data center facility contains dedicated infrastructure to support information technology outside of an office environment. It can be viewed as a tool to achieve operational sustainability at a tactical level. Uptime Institute notes that an organization's Tier 4 data center needs are primarily driven by time-to-market and initial cost issues rather than lifecycle costs. It typically includes:

• Provide dedicated space for IT systems such as servers and backup devices.
• Uninterruptible Power Supply (UPS) devices are used to cope with power fluctuations and power failures.
• Cooling equipment to keep systems running at optimum temperatures.
• Engine/generators to keep systems running and online during extended power outages.

Second level: redundant capacity components

Tier II data center frameworks contain redundant critical power and cooling components. These measures provide a level of security against power outages and other major events that could shut down or damage systems. Tier II is also tactical in nature. Most organizations that rely on Tier I and Tier II capabilities do not require real-time capabilities, according to the Uptime Institute. Tier II systems and equipment typically include:

• Power and cooling equipment such as modular UPS, air conditioning chillers or water pumps.
• Engine/Generator.

Level 3: Parallel maintainable systems

Tier III data center facilities can operate without impacting IT systems during data center equipment upgrades, changes, or maintenance. Data centers with Tier III capabilities avoid disruptions or downtime by establishing redundant transmission paths for power and cooling. Uptime Institute notes that the effective life of Tier III (and Tier IV) data center infrastructure solutions exceeds current IT requirements. More importantly, they are often utilized by organizations that recognize the cost of disruption or damage, which is measured in actual losses and market share.

Level 4: Fault Tolerance

The infrastructure of a Tier IV data center builds on the capabilities of a Tier III facility by building fault tolerance into the data center topology. Fault tolerance describes the ability to limit the impact of an outage or disruption before it impacts IT operations. It is especially important for mission-critical applications and systems. This tier represents the most strategic level of protection. It typically involves multiple redundant systems.

Data Center Tier List

The development and evolution of data centers

As data centers become more complex and interconnected, and high-performance computing (HPC) workloads and cloud computing have become mainstream applications in the enterprise, data center tiering strategies must address new and different issues. Modern equipment is undoubtedly different from the data centers of the 1980s, which were usually equipped with mainframes or mid-sized supercomputing systems.

In order to adopt the right data center tier, it is particularly important to understand how the service provider builds and maintains its data center. There are several key factors, which in some cases may be related to industry organizations and standards, such as those created by the Telecommunications Industry Association (TIA). Key factors may include:

• Geographic location/risk and local standards
• Commercial Building Standards.
• Wiring standards.
• Cooling system.
• Fiber optic coding.
• Operational practice.
• Equipment standards, including maintenance and replacement of UPS equipment, generators, and other equipment.

Data Center Tiers and Cloud Computing

When organizations want to build a more flexible and agile IT framework, hosted data centers and various cloud computing facilities (including hybrid clouds) require close attention and different considerations. In fact, today's data center is often a large private cloud.

• These data center facilities must provide the levels of availability that business requires—often deployed in multiple locations. Given the growth of multi-cloud computing, these data centers often need to adopt a multi-cloud strategy.
• Since organizations have no control over data center systems, service level agreements (SLAs) are a key consideration.
• Uptime Institute has expanded its data center rating to include operational sustainability. This involves staff and operational components, which include priority behaviors and risks. This is an aspect that enterprises should consider when migrating to cloud platforms and possibly infrastructure as a service (IaaS).

How to Develop a Data Center Strategy

The starting point for understanding data center tiers is to understand the needs of the organization and how a tiered strategy fits in, especially as cloud computing accelerates. The challenge of vetting cloud computing vendors grows as enterprises adopt the services of external data center service providers and, in some cases, use cloud computing services from cloud computing vendors.

As a result, many organizations are turning to outside organizations to assess their data centers based on their compliance with a specific tier. However, the Uptime Institute is the only organization that rates and certifies data centers. This ensures that the facility is built as designed, that the site functions and equipment works as billed, and that the data center can demonstrate performance standards that match its tier designation. However, it is worth noting that some organizations now use standards that exceed those of the Uptime Institute and TIA.

It is also important to realize that tiering is not the only consideration when selecting a data center provider. Configuration management, security, usage levels, licensing requirements, disaster recovery, and possibly rack capacity and density issues are also important considerations. For businesses looking to connect to data center tiers, it is also important to understand the specific services provided and the guaranteed quality of service (QoS) levels.

Key Steps to Improve Stratification

It is important to match your organization's requirements with the appropriate data center tier. Here are some tips for determining your enterprise needs and establishing the appropriate data center tier level:

Step 1: Assess business needs

Understand the specific availability and performance requirements of various enterprise systems and applications. For example, a branch office of a financial services company does not require the same level of performance and protection as an e-commerce system or a securities trading system. This assessment may need to be extended to supply partners and customers.

Step 2: Determine the level of risk

What types of outages or downtime are likely? How would an outage or system failure affect the business? If a system or application were to fail for a few minutes or hours, what would the cost be in terms of financial loss and reputation? It is critical to document the cost of a business outage and compare it to the cost of maintaining or purchasing a specific data center tier.

Step 3: Evaluate internal needs and/or external suppliers

Determine what changes you need to make when running your own data center? If you are looking for compute, bandwidth or cloud resources from an outside provider, determine the vendor's certifications, rankings, policies, procedures, protections and the service-level agreements they offer (including compensation for noncompliance).

Step 4: Map the system into layers

With all the necessary information at hand, enterprises can determine what makes sense and what factors will minimize costs while mitigating risk. It is critical to avoid vague language and decisions and ensure that all tiering decisions are based on specific and defensible criteria. It is also critical to establish notification systems to understand if and when a data center does not meet established tiering standards.

Data Center Tier Strategy: The Cutting Edge

What is the most important step in your data center tiering strategy? Understanding exactly why it is important to have a comprehensive strategy in place.

Paying attention to the data center tier can help companies improve performance, reduce costs and ensure that the business supports current and future technology and performance requirements. According to AFCOM's 2018 Data Center Industry Status Study, the need for due diligence is growing. Currently, nearly 60% of companies have 2 to 9 data center facilities, but by 2021, the average number of data centers managed by organizations will increase to 10.2. In addition, many existing data center facilities will need renovation and transformation.

What is certain is that as an organization grows and evolves, and business-critical services become mandatory, executing a data center tiering strategy becomes increasingly important. It will be core to successful IT and business.