Of definitions and specifications for each area of

This preview shows page 37 - 39 out of 64 pages.

of definitions and specifications for each area of the data center. The data center reliability tiers are the most common expression of how business-critical and how fault-tolerant a data center can become. The chart below from an Uptime Institute white paper shows the tiers side by side and compares numerous features and benefits. The price to availability ratios are stark with the most dramatic jump from Tier II to Tier III. While this yields the most dramatic gain, it also commands a 50 percent price premium. Accordingly, there are very few Tier IV data centers today because usually they are just too expensive to justify. (See Uptime Institute Tiers sidebar on the following page for more information.) Tier I: Basic Only 1 N 20% 20-30 20-30 12" 85 208,480 3 1965 $450 28.8 hrs 99.671% Number of delivery paths Redundant components Support space to raised floor ratio Initial watts/ft Ultimate watts/ft Raised floor height Floor loading pounds/ft Utility voltage Months to implement Year first deployed Construction $/ft raised floor Annual IT downtime due to site Site availability Tier II: Redundant Components Only 1 N+1 30% 40-50 40-50 18" 100 208,480 3 to 6 1970 $600 22.0 hrs 99.749% Tier III: Concurrently Maintainable 1 active 1 passive N+1 80-90% 40-60 100-150 30-36" 150 12-15kV 15 to 20 1985 $900 1.6 hrs 99.982% Tier IV: Fault Tolerant 2 active 2 (N+1) 100% 50-80 150+ 30-36" 150+ 12-15kV 15 to 20 1995 $1,100+ 0.4 hrs 99.995% Tier Similarities and Differences for Data Center Design Variables
36 | | Section 4 - Best Practices for Data Centers: Standards and Associations UPTIME INSTITUTE TIERS Tier I (Basic) (N*): Need single path for power and cooling distribution, no redundant components, 99.671 percent availability. Susceptible to disruptions from both planned and unplanned activity. UPS or generator is a single-module system with many single points of failure. To perform annual preventive maintenance and repair work, the infrastructure must be completely shut down. Tier II (Redundant Components) (N+1): “Need plus one” single path for power and cooling distribution, redundant components, slightly less susceptible to disruptions–99.749 percent availability. Maintenance of the critical power path and other parts of the site infrastructure require a processing shutdown. Tier III (Concurrently Maintainable) (N+1): Multiple power and cooling distribution paths, but only one path active. Allows for any planned site infrastructure activity without disrupting the computer hardware operations. Contains redundant components that are concurrently maintainable with 99.982 percent availability. Tier III sites are often designed to be upgraded to Tier IV sites when cost allows. Tier IV (Fault Tolerant) 2(N+1): S+S* multiple active power and cooling distribution paths, redundant components, 99.995 percent availability. The site infrastructure is able to sustain at least one worst-case unplanned failure or event with no critical load impact. S+S=System+System–two separate UPS systems in which each system has N+1 redundancy. This requires all computer hardware to have dual power inputs. It supports high availability IT concepts that employ CPU clustering, RAID and DASD

  • Left Quote Icon

    Student Picture

  • Left Quote Icon

    Student Picture

  • Left Quote Icon

    Student Picture