Brought to you by Data Center Knowledge
A long list of Microsoft Azure cloud services malfunctioned for hours Friday for a subset of customers using services hosted in a Microsoft data center in Japan due to a cooling failure.
Customers had trouble connecting to resources that leverage storage infrastructure in the Japan East region, according to an update on the Azure status website.
“Engineers have identified the underlying cause as loss of cooling which caused some resources to undergo an automated shutdown to avoid overheating and ensure data integrity and resilience,” the status page read as of noon Pacific Time.
While the most consequential cloud outage of the year so far – the Amazon Web Services storage service meltdown in late February – was caused by a mistyped command, today’s incident in Japan serves as a reminder of the extremely physical nature of the cloud.
Cooling-related data center outages are common, but not nearly as common as electrical infrastructure problems. Malfunctioning uninterruptible power supplies have consistently been reported as the most common cause of data center outages in regular surveys by the Ponemon Institute, commissioned by the company formerly known as Emerson Network Power (now known as Vertiv).
The issues started around 7 a.m. Pacific Time and continued into the afternoon as Azure engineers worked to restore the systems.
Both storage and virtual machines were impacted, along with many more cloud services, such as Web Apps, Backup, HDInsight, Key Vault, and Site Recovery.
Microsoft Azure launched its Japan East region, hosted in a data center in the Saitama Prefecture, and its Japan West region, hosted in a data center in the Osaka Prefecture, in 2014.