Microsoft has revealed it was forced to take swift action in response to phenomenal demand for its Azure cloud services during the early stages of the pandemic.
A new blog post published by the firm outlines how, in order to ensure Microsoft Azure was able to support the efforts of front-line services, as well as the many businesses forced to transition to a remote model, datacenter staff worked “round-the-clock” installing new servers. Product teams, meanwhile, hunted for efficiency gains to free up resources and capacity for customers.
With the epicenter of demand positioned in central Europe, the company doubled the capacity on one of its own transatlantic undersea web cables, and arranged for the operator of another to allocate additional capacity to Azure customers.
Microsoft also shifted internal Azure workloads to take place outside of peak hours in different territories, funnelling traffic away from regions experiencing high demand.
Microsoft Azure pandemic response
Microsoft said that while its cloud service is designed to expand and contract with demand, challenges posed by the pandemic were unlike any the Azure team had previously encountered.
“The scope and scale of the response to Covid-19 was completely unprecedented, in terms of how much the world went digital inside a month,” said Mark Simms, a software architect involved in managing the Azure response.
“So the work that we had to do to get through the initial surge in demand and free up capacity for our customers to run critical health and safety workloads was also unprecedented. We made some pretty profound changes in order to do the right thing, and we did them under a very short time frame.”
From a business perspective, demand for Microsoft Teams skyrocketed, but so too demand for services such as Windows Virtual Desktop and Azure Active Directory’s Application Proxy as organizations came to terms with securing a remote workforce.
To handle this surge, Microsoft boosted the capacity of its fiber optic network by 110 terabits over two months, and also added 12 edge sites to minimize congestion.
The firm also used data from China and Italy, two countries that suffered high coronavirus incidences early in the pandemic, to map out anticipated effects on traffic as the virus spread across the globe.
“Normally, you find and fix issues organically as you grow. When you take software and put it under explosive growth – with services getting used an order of magnitude more in one day – you tend to find all of those in a really short period of time,” explained John Sheehan, Microsoft Distinguished Engineer for Azure Quality.
Having scaled and stabilized the service, Microsoft has now turned its focus to unearthing micro efficiencies to better support Azure’s increasingly wide customer base.