They’re just storing doubles in their own format too. I’m not sure if they even need any spatial lookups on the data, they didn’t mention anything about that in the article. Maybe they do that in-memory?

Aren’t time series databases like Prometheus pretty good at storing this kind of data?

Percentiles of the measured startup times.

p100: 100% of the startups were slower, this is the maximum time they measured.

p50: 50% were slower than this

And so on to p0, which is the smallest measured time.