[1a1a11a]

I might be dumb about estimating throughput. According to https://github.com/Cyan4973/xxHash, the best hash function can only do 100s M hashes per second, how can a local cache run at such throughput? I assume when measuring cache throughput, one need to calculate hash, look up, (maybe compare keys), and copy the data.

[NovaX]

Are you comparing a single threaded hash benchmark to a multithreaded cache benchmark? An unbounded concurrent hash table has 1B reads/s on a 16 core machine (~60M ops/s per thread)

[1a1a11a]

Oh, my bad, thank you for pointing out! BTW, just for my curiosity, where is the 1B reads/s benchmark?

[NovaX]

A multi-threaded benchmark of a cache should be fully populated and use a scrambled Zipfian distribution. This emulates hot/cold entries and highlights the areas of contention (locks, CASes, etc). A lock-free read benefits thanks to cpu cache efficiency causing super linear growth.

This shows if the implementation could be a bottleneck and scales well enough, after which the hit rate and other factors are more important than raw throughput. I would rather sacrifice a few nanos on a read than suffer much lower hit rates or have long pauses on a write due to eviction inefficiencies.

[1] https://github.com/ben-manes/caffeine/wiki/Benchmarks#read-1...

[2] https://github.com/ben-manes/caffeine/blob/master/caffeine/s...