Your data center is one of the most critical resources within your organization. When employees and customers are unable to access the servers and storage systems in the data center, your entire organization can shut down. When you consider that 70 percent of network downtime can be attributed to physical layer problems and that cabling is a key component of your physical layer, it is of paramount importance that consideration is given to the following three principles of data center cabling infrastructure design.

Principle 1: Space Planning

Environmentally-controlled real estate is expensive, and maximizing space is critical (see Table 1). Data center racks and equipment can take up an enormous amount of real estate, and future network demands may require even more space.

Data center requirements continuously change. Designing in plenty of empty floor space enables reallocating space to a particular function, and adding new equipment as needed. As connections, bandwidth and storage requirements grow, so do the amount of cabling connecting key areas and equipment. Choosing high-density cabling and connectivity solutions that require less rack, floor, and pathway space will leave more room for reconfiguration and growth.

Principle 2: Reliability

Uninterrupted service and continuous access are critical to daily operations and productivity. With downtime translating directly to loss of income, data centers must be designed for redundant, fail-safe reliability (see Figure 1).

Data center reliability is impacted by the performance of the cabling infrastructure. The infrastructure must consistently protect cabling and connections while supporting the flow of data without errors that cause retransmission and delays. The cabling should also support current bandwidth needs while enabling migration to higher network speeds.

Cabling and connectivity backed by a reputable vendor with guaranteed error-free performance can help minimize poor transmission both now and in the future. Components that maintain proper bend radius throughout cable routing paths are also critical - both at initial installation and when cables are added (see Figure 2).

Principle 3: Manageability

The cabling infrastructure should be designed as a highly manageable utility to accommodate disaster recovery, upgrades and modifications. Manageability starts with unified cable management that keeps cabling and connections properly stored and organized, easy to locate and access, and simple to reconfigure.

The use of a central patching location in a cross-connect scenario provides an easy-to-manage infrastructure whereby all network elements have permanent connections that once terminated, are never handled again. In this scenario, all modifications, rerouting, upgrades, and maintenance activities are accomplished using semi-permanent patch cord connections (see Figure 3).

Of course, adding cross-connects and patching adds more connectors and passive ports in the network. Yet it is mistaken to assume that more connections equate to more downtime and performance issues. Connectors and cable only fail due to errors by people in handling and movement; left alone, cable and connectors just don't fail. A manageable infrastructure requires a cable management platform that encourages best practices by technicians so that the infrastructure is not a source of failure.

Designing a reliable and manageable cabling infrastructure includes many other factors, including creation of zone distribution areas, establishing clear cable pathways, having multiple service provider hand-off points, and many other considerations. For more details, go to www.adc.com to review the following white papers and guides:

• Designing an Optimized Data Center (101818AE)
• TIA-942 Data Center Standards Overview (102264AE)
• Data Center Infrastructure Design Guide (102944AE)
• The Three Principles of Data Center Infrastructure Design (102261AE)

Summary

When executed properly, the three principles of data center cabling infrastructure design will:

• Lower your total cost of ownership
• Support your future growth plans
• Reduce your risk of downtime
• Maximize performance
• Improve your ability to reconfigure

When selecting fiber and copper cable, connectivity and cable management solutions for the data center, it is important to choose products and services that satisfy the three principles of data center cabling infrastructure design. In conjunction with standards-based implementations of other data center components this will make your data center robust, resilient and scalable.

ADC's John Schmidt is the Sr. Product Manager, TrueNet Business Development for Structured Cabling, 952-403-8059; email: john.schmidt@adc.com; web: www.adc.com.