Some breaks are just too difficult to predict. For example, I work in ecommerce and we had a page break because the content team pushed too many items into an array, that caused a back-end service to throw errors. Because we were the middle-service, taking from the CMS and making the request to back-end, not sure how we could have seen that issue coming in advance (and no one knew there was a limit).
Absolutely. I think a great filter for developers is determining how well they understand this. Over-simplification of problems and certainty about one’s ability to build reliable services at scale is a massive red flag to me.
I have to say some of the hardest challenges I’ve encountered were in e-commerce, too.
It’s a lot harder and more interesting than I think many people realize. I learned so much working on those projects.
In one case, the system relied on SQLite and god damn did things go sideways as the company grew its customer base. That was the fastest database migration project I’ve ever been on, haha.
I often think it could have worked today. SQLite has made huge leaps in the areas we were struggling. I’m not sure it would have been a forever solution (the company is massive now), but it would have bought us some much-needed time. It’s funny how that stuff changes. A lot of my takeaways about SQLite 10 years ago don’t apply quite the same anymore. I use it for things now that I never would have back then.
All requests expect errors. How a developer handles them... well...
And for limit checking, how often do you write array limit handlers? And if the BE contract doesn't specify? Additionally, it will need as a regression unit test, because who knows when the next developer will remove that limit check.
