"The company initially confirmed the outage by, somehow, tweeting, from its @support account. We were unable to see the tweet, because Twitter was down."
I mean, one part of me has worked on the backend of uber-high-bandwidth computing services and understands that there is no analogue to performance at that scale, and the other part is like "IT PUTS WORDS THAT PEOPLE POSTED ON A BUNCH OF PAGES, YOU CAN IMPLEMENT THE CORE FUNCTIONALITY IN AN AFTERNOON."
I was waiting on this to appear on Hacker News. I take to Twitter to complain whenever a service is down. Now that Twitter is down... I guess all that is left is this HN thread.
Wonder what's caused the outage, they're leveraging Mesos/Aurora pretty heavily AFAIK which is what I'm moving towards so would rather it wasn't something on that side of things.