Data centre tiers
Data center tiers are defined levels of resiliency and redundancy for IT facility infrastructure. They are widely used in the data center, ISP and cloud computing industries as part of the engineering design for high availability systems. The data center tier system was created by the Uptime Institute.[1]
The standard data center tiers are:[2]
- Tier I: no redundancy
- Tier II: partial N+1 redundancy
- Tier III: full N+1 redundancy of all systems, including power supply and cooling distribution paths
- Tier IV: as Tier III, but with 2N+1 redundancy of all systems
A Tier III system is intended to operate at Tier II resiliency even when under maintenance, and a Tier IV system is intended to operate at Tier III resiliency even when under maintenance.
Most commercial data centers are Tier III; instead of using Tier IV datacentres, many large service providers typically use multiple availability zones to implement of their services, thus achieving greater resilience than would be possible with any single data centre.[citation needed]
| Tier | Uptime guarantee per year | Downtime per year | Component redundancy |
|---|---|---|---|
| Tier 4 | 99.995% | <26.3 minutes | Fault tolerant (2N or 2N+1) |
| Tier 3 | 99.982% | <1.6 hours | Full N+1 |
| Tier 2 | 99.741% | <22 hours | Partial power and cooling redundancy (partial N+1) |
| Tier 1 | 99.671% | <28.8 hours | None |
See also
[edit]References
[edit]- ^ "Tier Classification System". Uptime Institute. Retrieved 2023-09-15.
- ^ "Breaking Down Data Center Tier Level Classifications". www.coresite.com. Retrieved 2023-09-15.
 | This computing article is a stub. You can help Wikipedia by expanding it. |
 | This engineering-related article is a stub. You can help Wikipedia by expanding it. |