theine-go

In fact, lock-free queues have several problems at once, which prompted me to give up on them almost immediately. 1. Yes, S3-FIFO can be implemented using lock-free queues, but the problem is that each write to a filled cache using this design will cause a large number of additional atomic operations not friendly to the processor's cache, while bp-wrapper on the contrary amortizes this load. And reading with frequency update on hot entries can have a bad effect on performance. In many ways this is exactly what the last posts in my discussion with Ben are about (not really about this, but the current problem with otter read speed is caused by a similar problem). https://github.com/Yiling-J/theine-go/issues/29#issuecomment... 2. But the main problem for me is not even that. Lock-free queues work fine as long as you only need to support Get

I think you may be right. The library author said he made many changes because implementing the eviction policy following the paper's design was pretty awful. > First, I tried to implement cache on hash table and lock free queues, as the authors wrote. I was annoyed, s3-fifo was indeed many times faster than lru cache implemented on hash table with global mutex, but still lost to ristretto and theine, which use bp-wrapper techniques. The profiler also showed that it was the eviction policy that was spending the bulk of the time. And I was only able to beat ristretto and theine after rewriting the implementation using bp-wrapper. > In summary, I completely disagree about the scalability advantage of S3-FIFO over the other policies > Though to be honest, what was causing the hit ratio to go down in DS1 I still don't understand https://githu