Following Amazon's fire on Friday, ComputerworldUK picks out the most unexpected data centre disasters
Amazon suffered a large fire in its data centre in Virginia on Friday morning. Luckily, no-one was harmed and the building was under construction - so no AWS operations were affected.
But several firms haven't had such luck in the past. We compile the top ten most unexpected data centre outages.
1. 1. Yahoo goes down
Yahoo's data centre staff were driven nuts by several rodents in its Santa Clara location.
Mike Christian, a director of engineering at the internet giant told a conference in 2012: "A frying squirrel did take out half of our Santa Clara data centre two years back."
Surprisingly, squirrels are often the cause of power outages in the US.
Image credit: iStock/Busypix
2. 2. NSA hit by 'electrical surges'
The US National Security Agency's spying operation was affected by electrical surges in its Utah data centre in 2013 with a reported loss of hundreds of thousands of dollars worth of machinery. The facility - a 65 megawatt load - was one of the largest of its kind and reportedly cost $1.53 billion (£1 billion).
Image credit: Flickr/See-Ming Lee
3. 3. Trucker ploughs into power cable at Rackspace
On 2 December 2007, Rackspace suffered embarassment as a truck driver drove into a power transformer at their Texas data centre, plunging websites that depended on its servers offline.
Image credit: iStock/dimedrol68
4. 4. Fat fingers deal a blow to Joyent
An administrator at cloud provider Joyent rebooted every single virtual server hosted in the company's data centre in May last year in one swipe, much to the firm's embarassment.
"It should go without saying that we're mortified by this...the immediate cause was operator error, there are broader systemic issues that allowed a fat finger to take down a data centre," said CTO at Joyent, in a post on Hacker News.
5. 5. Lightning strikes Amazon and Microsoft data centres
Microsoft and Amazon's European cloud services were out for a weekend after its data centres were hit by lightning in Dublin in 2011.
The natural disaster took out the main power and the backup generator which meant that businesses on AWS EC2 platform and Microsoft's Business Productivity Online Suite went offline.
Image credit: Flickr/Oregon Department for Transport
6. 6. Shark attacks Google
Not quite an attack on a data centre - but in August last year, Google's Cloud product manager Dan Belcher said that the search giant wraps its trans-Pacific underwater cables in Kevlar to prevent against shark attacks. Several theories as to why sharks are attracted to underwater cables exist - including the idea that they mistake pulsing currents for threats.
Image credit: iStock/ElizabethHoffman
7. 7. Burglars bust Vodafone's servers
In February 2011, burglars broke into a Vodafone datacentre in Basingstoke. The thieves stole its network equipment which meant customers lost voice, text and internet access on their mobile phones.
Image credit: iStock/Stocksnapper
8. 8. Hurricane Sandy
The Huffington Post, Gawker, Gizmodo and Buzzfeed went offline after a the basement flooded at a data centre hosted by Datagram during Hurricane Sandy. Similarly, many leading telecoms firms such as Verizon were left without power during one of the worst storms in US history.
Image credit: iStock/harvepino
9. 9. Storms rock HBOS
HBOS - the banking firm which owns Halifax and Bank of Scotland - was unable to offer customers cash-machine, over-the-counter or online services for six hours when a storm struck its Yorkshire-based data centre in November 2009.
Image credit: iStock/fotografstockholm
10. 10. Worker killed during data centre construction
In November 2008 one man died and six people were injured when 60 gas cannisters exploded, destroying part of the HSBC data centre building in Welwyn Garden City, Hertfordshire. The building was being renovated for Laing O'Rourke-owned engineering firm Crown House Technologies.