"So in the fall of 2019, the SoniKube team based at Hill Air Force Base in Utah set out to get Kubernetes running on an F-16 jet."

Am I wrong for being horrified by this statement? This seems like a lot of added complexity where you want minimal complexity. Then again, can't say I've ever tried to run a container orchestrator on a F-16.

This seems like a slippery slope - I think I'd prefer waterfall to a MVP driven workflow for this kind of stuff.

Am airplane is am extremely complex interconnected set of systems. Monitoring, security policies, restarts, and zero downtime deployments are pretty sensible reasons to use kube.

Also, they can take any kube deployed code from a 3rd party and instantly run it at edge on the jet with nearly no security concerns (aside from cpu exploits).

Kube is just fancy systemd.

I'm guessing this deployed on a secondary computer, not on any flight-critical computers; no way it would have passed airworthiness otherwise (even in a demo). As a result, the worst that could probably happen would be the pilot having to power-cycle the secondary computer.

My thoughts too. “What could possibly go wrong?”

Looking at the systems on existing jets that have been successful and not, it should be obvious that this is a very bad idea.

Kudos to the sales team that got this to happen though!