How does it compare to the "Fastest Hashtable" by Malte Skarupke? ( https://probablydance.com/2017/02/26/i-wrote-the-fastest-has... )
Writing a Very Fast Hash Table with Tiny Memory Footprints
51–53 of 53 posts
Re: Writing a Very Fast Hash Table with Tiny Memory Footprints
#52Look up MDBM. I spent a lot of time with a logic analyzer watching the cache misses go across the bus. I'd be pretty surprised if someone has done better. I can find the code and repost it.
> I can find the code and repost it. Here it is.. https://github.com/yahoo/mdbm
So Yahoo took the code and did all sorts of stuff to it.
I've got the code pre-yahoo and that's the stuff that is
fast.
It's part of BitKeeper which is open source.
Re: Writing a Very Fast Hash Table with Tiny Memory Footprints
#53Earlier quoted context omitted.
Thanks for the reference. I'm collecting a list of embedded key-value store to benchmark against. I'll tryout with this one first!
LMDB
I would expect this hash table to be much faster than LMDB for tables that fit in RAM. It doesn't have transactions or any kind of concurrent access guarantees so naturally it has lower access overhead. For data sets larger than RAM, or in multithreaded environments, it will be pretty unusable.