alt Hacker NewsSo Ashburn VA is a datacenter hub because the very first non-government Internet Exchange Point (IXP) anywhere in the world was there (https://en.wikipedia.org/wiki/MAE-East). Back in the 1990's something like half of all internet traffic all over the world hit MAE-East. That in turn made AWS put their first region there (us-east-1 preceded eu-west-1 by 2 years and us-west-1 by 3 years). Then because there were lots of people who knew how to build DC's- and lots of vendors who knew how to supply them- the Dulles Corridor became a major hub for lots of companies datacenters. For AWS, because us-east-1 was the first, it's by far the most gnarly and weird- and a lot of control planes for other AWS services end up relying on it. Which is why it goes down more often than other regions, and when it does go down it makes national news, unlike, say, eu-south-2 in Spain.
But NoVA is basically the same sort of economic cluster that Paul Krugman won his Nobel Prize in Economics for studying, just for datacenters, not factories.
Replies
The underlying reason is more that by being in us east coast you have about equal latency for customers in us west coast and Europe. That's a very large population covered from a single site.
If you're building a single datacenter site this is where you start building first.
Well said. I'll also add, that with these networks, the sooner you can get traffic off your network the better. There's strong incentive to have your datacenter near these peering points. And since MAE-East was the first, it's been the largest as it's been snowballing the oldest. AOL's HQ was here, Equinix built their peering point soon after MAE-East, etc.
There's a great read about the whole area here: https://www.amazon.com/Internet-Alley-Technology-1945-2005-I...
As for AWS, I often see it repeated that the DCs are the oldest and therefor in disrepair. That's not true; many of the first ones have since been replaced. But there are services that are located here and only here.
But I'll also add, a lot of customers default to using US-East-1 without considering others, and too many deploy in only one AZ. Part of this is AWS's fault as their new services often launch in US-East-1 and West-2 first, so customers go to East-1 to get the new features first.
Speaking as one who was with AWS for 10 years as a TAM and Well-Architected contributor, I saw a lot of customers who didn't design with too much resiliency in mind, and so they get adversely affected when east-1 has an issue (either regional or AZ). The other regions have their fair bit of issues as well. It's not so much that east-1 necessarily fails more than the others, it's that it has so many AZs and so many workloads that people notice it more.