You must log in or register to comment.
I’m not buying it. Every time I’ve seen cross datacenter apps attempted, it’s killed by latency. It doesn’t matter how fast the network, you’ll always have much higher latency between datacenters than within. That’s basic physics. Then you discover how chatty your services are and how quickly that latency adds up to intolerable
One good thing about these initiatives is that a lot of the approaches and tech can be used for other use cases.
If (when?) the AI bubble pops, we can still make use of all these developments.
If you can’t vertically scale your product, better start working on horizontally scaling it.