Coreix Managed Servers

Rackspace Hosting expects to issue customer service credits from Monday’s data centre outage of between US$2.5 million and US$3.5 million, the company has announced in an SEC filing.

A series of equipment failures contributed to the power outage at a Rackspace data centre near Dallas, where several parts of the facility lost power. The most significant failure involved a bank of generators that malfunctioned, leaving several computing clusters without backup power. Other failures involved equipment that connects the data centre to its two utility feeds, a UPS system and a transfer switch. The outage affected two of the four phases of data centre space in the facility in Grapevine, Texas.

Source: SEC

Twitter has been flooded with complaints about a power outage at Equinix’s Sydney data centre which apparently knocked out data and network systems, including VoIP. Equinix operates facilites in Europe, North America and the Asia Pacific regions, with the data centre in the Sydney suburb of Mascot suffering the reported failure. Equinix’s Sydney office could not give any details about the outage at this time.

VoIP service provider MyNetFone issued a statement about a power outage. “We apologise for the service interruption on Thursday 2nd July 2009 between 11:40am EST and 1:00pm. The problem was caused by a nation-wide power outage which triggered a total loss of power at our colocation facility in Sydney.”

Source: Tech World

Rackspace’s Dallas-Fort Worth facility had “power issues” with its SSL server, bringing sites hosted by its network of cloud servers crashing back to earth. The company also acknowledged a separate power issue affecting the data centre at large. Rackspace acknowledged the problem both on its Twitter account as well as on its status blog. Sometime Monday afternoon Central Time, part of one of Rackspace’s nine data centres suffered a power outage, and then was brought back online around 5:30 PM Central Time. Until about 8:58 PM Central Time, that portion of the data centre, in Dallas-Fort Worth, was transitioning between generator and utility power, Rackspace said on its official blog.

The outages also affected the Secure Sockets Layer (SSL) cluster hosted by Rackspace, apparently making e-commerce and other functions that depend on SSL inoperable for Rackspace-hosted sites. That cluster went down Monday afternoon and was restored at 5:03 PM, went down again at 6:11 PM CDT, was restored at 7:01 PM, and then apparently flickered at about 9:48 PM CDT, after which service was restored, the company said on a separate status blog.

Source: PC Mag