Data Center Power

Amazon's Data Center Power Outages: Build Better-Distributed Cloud Infrastructures

By Rachel Ramsey TMCnet Web Editor

With heat waves and tornado warnings, this summer’s weather has been pretty rocky for the East Coast. Even for Amazon, the weather hasn’t been nice to its data centers. Less than two weeks after announcing a cable fault in a power distribution system of its electricity provider, Amazon Web Services (News - Alert) (AWS) in the U.S.-East -1 region suffered another outage last week.

Severe East Coast thunderstorms have led to power outages for its Internet-based computing services, which are used by hundreds of thousands of businesses to store data and run websites. The storms impacted power to several data centers in northern Virginia, and in one location backup power didn’t operate correctly.

On the evening of June 29, storms brought down power connections for more than one million customers of Dominion Virginia Power, including users of Netflix, Pinterest and Instagram.

By July 1, many customers in the region were still without power, so even if Amazon’s services were up, those using devices that needed plugging in would have missed the services placed in Amazon’s cloud.

A power outage earlier in June also affected Amazon’s cloud customers. The outage caused downtime for customers of popular Web services such as Pinterest, Heroku, Quora, Foursquare (News - Alert) and others.

One of the most recent high-profile Amazon cloud outages happened in August 2011, when a data center in Dublin lost power. The incident was initially blamed on a lightning strike, but the utility that was providing electricity to the data center later denied that lightning was the culprit.

Amazon’s typical response to customers affected by such outages is instructing them to build better-distributed cloud infrastructures, replicating virtual servers and data across multiple geographically separated physical data centers.

Newvem, a beta testing service that helps companies plan big AWS sites, discovered that 40 percent of Amazon’s biggest Web customers made the outage worse on themselves because they don’t follow the first rule in computing: making backups.

Amazon’s storage cloud, Amazon S3, stores more than one trillion objects: 1,000,000,000,000 files, images or other bits of data, equivalent to 42 objects to every person on Earth, 3.3 objects for every start in our galaxy or, if you were counting them all, at a rate of one per second, it would take you 31,710 years.

Server Technology (News - Alert) produces quality rackmount power distribution and monitoring solutions that help manage power capacity, reduce downtime and improve energy efficiency. Server Tech eliminates single points of failure, reducing downtime and costs. It offers a variety of data center power services, solutions and products including a selection of power distribution units (PDUs) and its Sentry Power System, which combines its PDUs and Sentry Power Manager (SPM) power monitoring software to provide a tightly-integrated system for rack-level data center power distribution and data center power monitoring and management.

Want to learn more about the latest in communications and technology? Then be sure to attend ITEXPO West 2012, taking place Oct. 2-5, in Austin, TX. ITEXPO (News - Alert) offers an educational program to help corporate decision makers select the right IP-based voice, video, fax and unified communications solutions to improve their operations. It's also where service providers learn how to profitably roll out the services their subscribers are clamoring for – and where resellers can learn about new growth opportunities. For more information on registering for ITEXPO click here.

Stay in touch with everything happening at ITEXPO. Follow us on Twitter.