Rethinking multi-grain timestamps

Talking about a performance trade-off has me thinking that simply using a low-res timestamp works fine? It looks like we are only talking about fail-to-use-cache for a millisecond. (On the occasions that happens.) I suppose media is faster these days, but then also why isn't a layer closer to the media doing that work for the millisecond in the cases where it matters?

Maybe I'm missing something, but nanosecond caching at a higher FS level maybe isn't the right place to do that, especially if it means introducing a swathe of finer-grained changes and adaptations, as has clearly been seen to be problematic?