Hopefully it’s simply M5 didn’t have a server ready and they’ll migrate back.
Vultr has a great assortment of bare metal servers.
Our primary server died around 11pm last night (PST), so we switched to our secondary server, but then our secondary server died around 6am, and we didn't have a third.
The plan was always "in the unlikely event that both servers die at the same time, be able to spin HN up on AWS." We knew it would take us several hours to do that, but it seemed an ok tradeoff given how unlikely the both-servers-die-at-the-same-time scenario seemed at the time. (It doesn't seem so unlikely now. In fact it seems to have a probability of 1.)
Given what we knew when we made that plan, I'm pretty pleased with how things have turned out so far (fingers crossed—no jinx—definitely not gloating). We had done dry runs of this and made good-enough notes. It sucks to have been down for 8 hours, but it could have been worse, and without good backups (thank you sctb!) it would have been catastrophic.
Having someone as good as mthurman do most of the work is also a really good idea.
_____
Related:
Appears “mthurman” is Mark Thurman, a software engineer at Y Combinator since 2016; HN profile has no obvious clues.