Microsoft has blamed a power sag and insufficient staff numbers for an outage that took out its Australia East cloud region last week.
According to Microsoft, the power sag tripped a subset of the cooling units in one data center, which caused the temperature to rise and forced the shutdown of servers.
Microsoft said that it had only three people on site at the time of the outage, which was not enough to restart the chillers in a timely manner. The company has since increased the number of staff on site to seven.
Microsoft is also investigating why its emergency procedures did not include provisions for an incident of this sort.
The outage affected Azure and other Microsoft cloud services, and lasted for over 24 hours. Microsoft said that it is working to improve its infrastructure and procedures to prevent similar outages from happening in the future.
The sources for this piece include an article in TheRegister.