We were ready to invest in HC tools, but they were so damn brittle once we actually got past the smooth apple-like marketing and actually used them. Plenty of odd, not-well-documented behavior, random crashes, even the clusters required a bunch of manual steps to recover from. A major reason to even have a cluster is the self-healing, something tools like MongoDB did right 10+ years ago. Yet we had to manually edit a peers.json file and do all this garbage half the time when our clusters kept dying. It was infuriating. I kept insisting my devops guy had to be wrong when he told me that was the way it was done. I just couldn't believe that anything in 2021 required manual editing of JSON files when we have a million different self-discovery mechanisms (whether it's cloud metadata, or mDNS, etc). But he was 100% right, much to my disbelief.

So we ultimately pulled the plug after months of HC stuff running our QA system, because I just didn't feel comfortable pushing it to production given all the random crashes and behavior issues. And I feel vindicated.

I think if their stuff was more solid, I would 100% be happy to pay for it for our use cases. I thought generally that their ideas and levels of abstraction felt "right"