This assumes it only takes a single disk read to locate and retreive an object from the cache (which is unlikely to be the case).

OK, one small read plus one huge read would top-out at about 10.1ms, according to that graph.

Also a big assumption (which we could verify by looking at the relevant implementations, but I'm not going to)

Why is that unlikely to be the case?

There's going to be at least one level of indirection, and at least some of those indirections are going to be on-disk.

(Anyone who is not running their OS and temp space on NVME should not expect good performance. Such a configuration has been very cheap for several years now.)

> Such a configuration has been very cheap for several years now.

This is a very weird comment, considering that a) it's cheaper than yesteryear but SATA SDD (or even modern magnetic HDDs) are still sold and are in active use and b) ignores phones completely, where a large number of sites would have mobile-dominated visitors and can't just switch to an NVMe-like performance even for those with large disposable incomes (because at the end of the day even with UFS phones are still slower than NVMe latency-wise).