This is an excerpt from Quartz’s new book The Objects that Power the Global Economy. You may not have seen these objects before, but they’ve already changed the way you live. Each chapter examines an object that is driving radical change in the global economy. This is from the chapter on the server farm, which explores the heart of the internet.
WHEN SERVERS FAIL
-
February 2015
On Feb. 1, an outage in a Fujitsu data center in Perth during a thunderstorm affected the systems of Western Australia’s department of health. The department cares for the state’s population of 2.6 million people and oversees 2.5 million sq km (960,000 sq miles), which is the largest area administered by a single health department in the world. Three months later, Fujitsu announced an AU$10 million (US$8 million) update to the data center.
-
September 2015
On Sep. 20, Amazon Web Services’ DynamoDB database service received too many requests from users. AWS had to pause requests, which affected their cloud service. Clients like Netflix, Medium, Pocket, and IMDb experienced slowdowns and disruptions for about five hours.
-
December 2015
On Dec. 3, a configuration problem in the Microsoft Azure cloud-computing service left users in western and northern Europe without access to their emails for about four hours. The issue caused traffic to be wrongly routed, which in turn caused a service interruption that took down the Office 365 suite.
-
January 2016
On Jan. 14, a maintenance operation caused a power outage in a Verizon data center, which took down JetBlue’s website for about two hours. As a result, 36 JetBlue flights were delayed and four were cancelled.
-
January 2016
On Jan. 28, GitHub’s primary data center experienced a power disruption that caused a quarter of its servers to reboot, which in turn took GitHub’s website down for two hours. GitHub’s library of open-source code is used by 5.8 million active users worldwide.
-
July 2016
On July 27, three burned-out HVAC fans produced smoke and activated the fire alarm inside a data center in Ottawa, Canada, which forced an evacuation and emergency shutdown. The outage downed email servers and left some 50,000 public-service workers cut off from their emails throughout the day.
-
August 2016
On Aug. 8, a small fire in a power supply caused a “massive failure” at Delta’s Technology Command Center in Atlanta, which resulted in a loss of power. Some computers were down for five hours and at least 1,900 flights were cancelled over four days. That small fire cost Delta $150 million.
-
February 2017
On Feb. 28, a typo in code written by an AWS employee resulted in the outage of 54 of the 100 largest online retailers in the world for four hours. Some experienced slow downs, but Express and Lululemon went offline completely. Risk-analytics startup Cyence estimated a loss of $150 million for S&P 500 companies due to the outage.
Check out Quartz’s new book The Objects that Power the Global Economy.