There was an incident from AWS affecting our ap-1 region.
When: 23:12 ~ 23:31, Feb 19, 2021 KST (14:12 ~ 14:31, Feb 19, 2021 UTC)
Impact: We observed multiple failures during that time in ap-1.
Possible cause: AWS experienced an increase in ambient temperatures within a section of a single Availability Zone within the AP-NORTHEAST-1 Region. Starting at 6:03 AM PST, some EC2 instances were impaired and some EBS volumes experienced degraded performance as a result of the increase in temperature. The root cause was a loss of power to the cooling system within a section of the affected Availability Zone.
Next step: We excluded instances affected and newly rolled them out. The system has been operational at 23:31 Feb 19, for almost all instances in the region. Finally, all have been operational including the rest of the customer's instances.