ragingwire redundancy
ragingwire redundancy
ragingwire redundancy
ragingwire redundancy
ragingwire redundancy

Redundancy Model by RagingWire

Feb. 19, 2016
Understanding the differences between data center facilities, and the impact of those differences on reliability, is critical in choosing a data center partner.

When businesses evaluate wholesale data center colocation solutions they consider power availability, scalability, and visibility as the key decision criteria areas. Understanding the differences between data center facilities, and the impact of those differences on reliability, is critical in choosing a data center partner.

Most colocation providers follow any one of the two delivery models for providing infrastructure to wholesale customers: Shared or Dedicated. In a shared model, the customer is allocated a portion of the total infrastructure of the facility. Shared facilities are typically provided for customers who demand less than 1 MW of power, but are still interested in a wholesale relationship. Shared colocation providers often oversubscribe their infrastructure, counting on multiple customers not peaking their usage at the same time. Because of oversubscription, shared facilities can be less expensive than dedicated, but the wholesale customer can be at risk from the bad behavior of other tenants in the facility.

In a dedicated delivery model, the customer is allocated a fixed infrastructure that is isolated from other customers. Dedicated infrastructure typically cannot scale beyond the initial allocation. And while dedicated infrastructure isolates one customer from another, it usually comes at a higher price due to capacity management challenges and often leads to lower availability due to the small number of fault domains.

This paper presents RagingWire’s distributed redundancy model which is an enhancement of shared and dedicated infrastructure models. This patented design offers wholesale customers the benefits of both shared and dedicated delivery, while exceeding the availability of either. RagingWire’s distributed redundancy model, provides dedicated equipment at the distribution level to customers who exceed 200 kW of demand, but distributes the load at the UPS and generator level across the facility, using a patented 2N+2® electrical design. RagingWire does not oversubscribe its infrastructure so customers are not at risk from the load or actions of other customers.

RagingWire’s 2N+2® electrical system exceeds the Uptime Institute’s Tier IV standard for electrical delivery because it provides both concurrent maintainability and fault tolerance. UnlikeTier IV standard designs, RagingWire data centers maintain fault tolerance while maintenance is underway. This system provides the highest level of provable availability in the industry, and it allows RagingWire to offer wholesale customers the most robust Service Level Agreement (SLA) in the industry: 100% availability with no exclusions for maintenance.