> They literally run physical servers all over the world ... I've got to imagine then that this business has huge capital costs, and it's nearly impossible to grow a very capital intensive business without outside capital.
I genuinely struggle to understand how Fly.io managed (manages) to have this much physical server presence to date, having raised only ~$16M prior to this round. Hire a dozen engineers and that money starts to go fast. The regions page [1] shows 34 cities largely across 4 continents, but technically across 6 if you count the 1 region each in Africa and Australia.
Maybe they have managed to get inside other existing cloud's data centers and it's not literally their own physical hardware, or behind-the-scenes they are leasing collocated servers, etc.
I would love some insight here if one of the founders in the thread sees this.
The short answer is that none of our regions are so big that we have to own our own top-of-rack switching yet (though some are getting close), so we can take a random spot in (say) an Equinix rack, rather than having to engineer a network (we run our own BGP for Anycast, but our uplinks are just DAC connections to our upstream providers switches.
For what it's worth: we've been on our own hardware ever since we launched, long before the 14MM Intel/Dell round. It's really the only way we can see to make the margins make sense. A big part of the premise of AWS and GCP is that they're allocating hyperscaler-grade resources to the task of making sure they claim most of the margins in hosting things on their own platform, not middlemen --- though that may be more true for some services (like EC2) than others (like S3).
I think it's a good question, but the linked article says unambiguously near the bottom that they run their own hardware:
> Why We Raised A Bunch Of Money
> Here's what we think it takes to build this kind of platform:
> A hardware fleet. Fly.io has always run on its own hardware. There are fun, technical, “control your own destiny” reasons to rack hardware instead of layering on top of commodity clouds. But it's really just economics. If you want to get people to build apps on your platform, you need a shot at being around 10 years from now. Hardware is what makes the margins work.
you can finance new hardware and rack in a managed colo for extremely cheap. like really cheap.
i was in this business until a couple of years ago.
we'd quote prices for potential customers currently in public cloud and they literally wouldn't believe us. it actually became an impediment in the sales cycle and part of the reason we sold. people are dumb, but i'd be even dumber if i expected them to change for my benefit.
I genuinely struggle to understand how Fly.io managed (manages) to have this much physical server presence to date, having raised only ~$16M prior to this round. Hire a dozen engineers and that money starts to go fast. The regions page [1] shows 34 cities largely across 4 continents, but technically across 6 if you count the 1 region each in Africa and Australia.
Maybe they have managed to get inside other existing cloud's data centers and it's not literally their own physical hardware, or behind-the-scenes they are leasing collocated servers, etc.
I would love some insight here if one of the founders in the thread sees this.
[1]: https://fly.io/docs/reference/regions/