Alexey Mayshev

So, I've almost solved my problems, so we're starting to sort out the accumulated issues :). It seems that this issue has been resolved, so I'm closing it.

I once tested on a virtual machine with 32 cores, but it didn't give very interesting results. [benchstat.txt](https://github.com/maypok86/otter/files/14647201/benchstat.txt)

Wow, it looks great. I think it's better to merge it a little later, along with the update of otter to v2, along with the redesign of the api, which...

@proost I will try to collect the ideas in [this](https://github.com/maypok86/otter/issues/74) issue. It will be very cool to know your opinion.

Oh, it's not clear at all why this is needed in the onheap cache. Moreover, this will most likely require writing specific code for different operating systems. Perhaps in the...

1. This is usually not about the onheap cache. 2. It is much more correct to architecturally use abstraction and allow the user to implement allocation the way he needs....

Lol, looks like I woke up famous. 😅 @comunidadio yes, it's very likely otter will get that feature as well. Just now I'm following caffeine author's words "After reaching 50-60...

@phuslu > In some server applications(e.g. bidding), the priority of throughputs and P99 latency stability is most important. Yes, this is quite common. > the memory usage and hit ratio...

> we always try to cache as much or even all content as possible in a single process memory. But you will have a hit ratio = 100% in this...

> u should consider having a nottl version like phuslu/lru too. Just don't use the ttl option and you'll get what you want.